From 915d02f2a2f0d83e891846c550b411eda8620ee7 Mon Sep 17 00:00:00 2001 From: Waldemar Brodkorb Date: Wed, 9 Nov 2016 08:55:33 +0100 Subject: linux: update to 4.4.30, fix cris arch on this version --- .../linux/patches/4.4.28/coldfire-sighandler.patch | 100 - target/linux/patches/4.4.28/crisv32.patch | 33 - .../patches/4.4.28/initramfs-nosizelimit.patch | 57 - target/linux/patches/4.4.28/ld-or1k.patch | 12 - target/linux/patches/4.4.28/macsonic.patch | 11 - target/linux/patches/4.4.28/mips-xz.patch | 12 - target/linux/patches/4.4.28/patch-realtime | 30987 ------------------- target/linux/patches/4.4.28/revert-sparc.patch | 319 - target/linux/patches/4.4.28/startup.patch | 34 - .../linux/patches/4.4.28/use-libgcc-for-sh.patch | 29 - target/linux/patches/4.4.28/versatile-nommu.patch | 16 - .../linux/patches/4.4.30/coldfire-sighandler.patch | 100 + target/linux/patches/4.4.30/crisv32.patch | 33 + .../patches/4.4.30/crisv32_ethernet_driver.patch | 4048 +++ .../patches/4.4.30/initramfs-nosizelimit.patch | 57 + target/linux/patches/4.4.30/ld-or1k.patch | 12 + target/linux/patches/4.4.30/macsonic.patch | 11 + target/linux/patches/4.4.30/mips-xz.patch | 12 + target/linux/patches/4.4.30/patch-realtime | 30987 +++++++++++++++++++ target/linux/patches/4.4.30/revert-sparc.patch | 319 + target/linux/patches/4.4.30/startup.patch | 34 + .../linux/patches/4.4.30/use-libgcc-for-sh.patch | 29 + target/linux/patches/4.4.30/versatile-nommu.patch | 16 + 23 files changed, 35658 insertions(+), 31610 deletions(-) delete mode 100644 target/linux/patches/4.4.28/coldfire-sighandler.patch delete mode 100644 target/linux/patches/4.4.28/crisv32.patch delete mode 100644 target/linux/patches/4.4.28/initramfs-nosizelimit.patch delete mode 100644 target/linux/patches/4.4.28/ld-or1k.patch delete mode 100644 target/linux/patches/4.4.28/macsonic.patch delete mode 100644 target/linux/patches/4.4.28/mips-xz.patch delete mode 100644 target/linux/patches/4.4.28/patch-realtime delete mode 100644 target/linux/patches/4.4.28/revert-sparc.patch delete mode 100644 target/linux/patches/4.4.28/startup.patch delete mode 100644 target/linux/patches/4.4.28/use-libgcc-for-sh.patch delete mode 100644 target/linux/patches/4.4.28/versatile-nommu.patch create mode 100644 target/linux/patches/4.4.30/coldfire-sighandler.patch create mode 100644 target/linux/patches/4.4.30/crisv32.patch create mode 100644 target/linux/patches/4.4.30/crisv32_ethernet_driver.patch create mode 100644 target/linux/patches/4.4.30/initramfs-nosizelimit.patch create mode 100644 target/linux/patches/4.4.30/ld-or1k.patch create mode 100644 target/linux/patches/4.4.30/macsonic.patch create mode 100644 target/linux/patches/4.4.30/mips-xz.patch create mode 100644 target/linux/patches/4.4.30/patch-realtime create mode 100644 target/linux/patches/4.4.30/revert-sparc.patch create mode 100644 target/linux/patches/4.4.30/startup.patch create mode 100644 target/linux/patches/4.4.30/use-libgcc-for-sh.patch create mode 100644 target/linux/patches/4.4.30/versatile-nommu.patch (limited to 'target/linux') diff --git a/target/linux/patches/4.4.28/coldfire-sighandler.patch b/target/linux/patches/4.4.28/coldfire-sighandler.patch deleted file mode 100644 index c52a4e228..000000000 --- a/target/linux/patches/4.4.28/coldfire-sighandler.patch +++ /dev/null @@ -1,100 +0,0 @@ -From a95517992a37488c0bc8b629c47c570e580e407d Mon Sep 17 00:00:00 2001 -From: Greg Ungerer -Date: Mon, 15 Feb 2016 16:36:29 +1000 -Subject: m68k: Use conventional function parameters for do_sigreturn - -Create conventional stack parameters for the calls to do_sigreturn and -do_rt_sigreturn. The current C code for do_sigreturn and do_rt_sigreturn -dig into the stack to create local pointers to the saved switch stack -and the pt_regs structs. - -The motivation for this change is a problem with non-MMU targets that -have broken signal return paths on newer versions of gcc. It appears as -though gcc has determined that the pointers into the saved stack structs, -and the saved structs themselves, are function parameters and updates to -them will be lost on function return, so they are optimized away. This -results in large parts of restore_sigcontext() and mangle_kernel_stack() -functions being removed. Of course this results in non-functional code -causing kernel oops. This problem has been observed with gcc version -5.2 and 5.3, and probably exists in earlier versions as well. - -Using conventional stack parameter pointers passed to these functions has -the advantage of the code here not needing to know the exact details of -how the underlying entry handler layed these structs out on the stack. -So the rather ugly pointer setup casting and arg referencing can be -removed. - -The resulting code after this change is a few bytes larger (due to the -overhead of creating the stack args and their tear down). Not being hot -paths I don't think this is too much of a problem here. - -An alternative solution is to put a barrier() in the do_sigreturn() code, -but this doesn't feel quite as clean as this solution. - -This change has been compile tested on all defconfigs, and run tested on -Atari (through aranym), ColdFire with MMU (M5407EVB) and ColdFire with -no-MMU (QEMU and M5208EVB). - -Signed-off-by: Greg Ungerer -Acked-by: Andreas Schwab -Signed-off-by: Geert Uytterhoeven ---- - arch/m68k/kernel/entry.S | 6 ++++++ - arch/m68k/kernel/signal.c | 8 ++------ - 2 files changed, 8 insertions(+), 6 deletions(-) - -diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S -index b54ac7a..97cd3ea 100644 ---- a/arch/m68k/kernel/entry.S -+++ b/arch/m68k/kernel/entry.S -@@ -71,13 +71,19 @@ ENTRY(__sys_vfork) - - ENTRY(sys_sigreturn) - SAVE_SWITCH_STACK -+ movel %sp,%sp@- | switch_stack pointer -+ pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer - jbsr do_sigreturn -+ addql #8,%sp - RESTORE_SWITCH_STACK - rts - - ENTRY(sys_rt_sigreturn) - SAVE_SWITCH_STACK -+ movel %sp,%sp@- | switch_stack pointer -+ pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer - jbsr do_rt_sigreturn -+ addql #8,%sp - RESTORE_SWITCH_STACK - rts - -diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c -index af1c4f3..2dcee3a 100644 ---- a/arch/m68k/kernel/signal.c -+++ b/arch/m68k/kernel/signal.c -@@ -737,10 +737,8 @@ badframe: - return 1; - } - --asmlinkage int do_sigreturn(unsigned long __unused) -+asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) - { -- struct switch_stack *sw = (struct switch_stack *) &__unused; -- struct pt_regs *regs = (struct pt_regs *) (sw + 1); - unsigned long usp = rdusp(); - struct sigframe __user *frame = (struct sigframe __user *)(usp - 4); - sigset_t set; -@@ -764,10 +762,8 @@ badframe: - return 0; - } - --asmlinkage int do_rt_sigreturn(unsigned long __unused) -+asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) - { -- struct switch_stack *sw = (struct switch_stack *) &__unused; -- struct pt_regs *regs = (struct pt_regs *) (sw + 1); - unsigned long usp = rdusp(); - struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4); - sigset_t set; --- -cgit v0.12 - diff --git a/target/linux/patches/4.4.28/crisv32.patch b/target/linux/patches/4.4.28/crisv32.patch deleted file mode 100644 index cb9b0d028..000000000 --- a/target/linux/patches/4.4.28/crisv32.patch +++ /dev/null @@ -1,33 +0,0 @@ -diff -Nur linux-4.4.13.orig/arch/cris/arch-v32/mm/intmem.c linux-4.4.13/arch/cris/arch-v32/mm/intmem.c ---- linux-4.4.13.orig/arch/cris/arch-v32/mm/intmem.c 2016-06-08 03:14:51.000000000 +0200 -+++ linux-4.4.13/arch/cris/arch-v32/mm/intmem.c 2016-06-21 20:40:18.919361891 +0200 -@@ -113,14 +113,14 @@ - - allocation->status = STATUS_FREE; - /* Join with prev and/or next if also free */ -- if ((prev != &intmem_allocations) && -+ if ((&prev->entry != &intmem_allocations) && - (prev->status == STATUS_FREE)) { - prev->size += allocation->size; - list_del(&allocation->entry); - kfree(allocation); - allocation = prev; - } -- if ((next != &intmem_allocations) && -+ if ((&next->entry != &intmem_allocations) && - (next->status == STATUS_FREE)) { - allocation->size += next->size; - list_del(&next->entry); -@@ -145,5 +145,11 @@ - (unsigned long)intmem_virtual + MEM_INTMEM_START + - RESERVED_SIZE); - } --device_initcall(crisv32_intmem_init); - -+static int __init crisv32_intmem_setup(void) -+{ -+ crisv32_intmem_init(); -+ -+ return 0; -+} -+device_initcall(crisv32_intmem_setup); diff --git a/target/linux/patches/4.4.28/initramfs-nosizelimit.patch b/target/linux/patches/4.4.28/initramfs-nosizelimit.patch deleted file mode 100644 index 40d2f6bd8..000000000 --- a/target/linux/patches/4.4.28/initramfs-nosizelimit.patch +++ /dev/null @@ -1,57 +0,0 @@ -From 9a18df7a71bfa620b1278777d64783a359d7eb4e Mon Sep 17 00:00:00 2001 -From: Thorsten Glaser -Date: Sun, 4 May 2014 01:37:54 +0200 -Subject: [PATCH] mount tmpfs-as-rootfs (initramfs) with -o - nr_blocks=0,nr_inodes=0 - -I would have preferred to write this patch to be able to pass -rootflags=nr_blocks=0,nr_inodes=0 on the kernel command line, -and then hand these rootflags over to the initramfs (tmpfs) -mount in the same way the kernel hands them over to the block -device rootfs mount. But at least the Debian/m68k initrd also -parses $rootflags from the environment and adds it to the call -to the user-space mount for the eventual root device, which -would make the kernel command line rootflags option be used in -both places (tmpfs and e.g. ext4) which is guaranteed to error -out in at least one of them. - -This change is intended to aid people in a setup where the -initrd is the final root filesystem, i.e. not mounted over. -This is especially useful in automated tests running on qemu -for boards with constrained memory (e.g. 64 MiB on sh4). - -Considering that the initramfs is normally emptied out then -overmounted, this change is probably safe for setups where -initramfs just hosts early userspace, too, since the tmpfs -backing it is not accessible any more later on, AFAICT. - -Signed-off-by: Thorsten Glaser ---- - init/do_mounts.c | 4 ++++ - 1 file changed, 4 insertions(+) - -diff --git a/init/do_mounts.c b/init/do_mounts.c -index 82f2288..55a4cfe 100644 ---- a/init/do_mounts.c -+++ b/init/do_mounts.c -@@ -594,6 +594,7 @@ out: - } - - static bool is_tmpfs; -+static char tmpfs_rootflags[] = "nr_blocks=0,nr_inodes=0"; - static struct dentry *rootfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) - { -@@ -606,6 +607,9 @@ static struct dentry *rootfs_mount(struct file_system_type *fs_type, - if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs) - fill = shmem_fill_super; - -+ if (is_tmpfs) -+ data = tmpfs_rootflags; -+ - return mount_nodev(fs_type, flags, data, fill); - } - --- -2.0.0.rc0 - diff --git a/target/linux/patches/4.4.28/ld-or1k.patch b/target/linux/patches/4.4.28/ld-or1k.patch deleted file mode 100644 index 264f9166f..000000000 --- a/target/linux/patches/4.4.28/ld-or1k.patch +++ /dev/null @@ -1,12 +0,0 @@ -diff -Nur linux-4.4.5.orig/arch/openrisc/kernel/vmlinux.lds.S linux-4.4.5/arch/openrisc/kernel/vmlinux.lds.S ---- linux-4.4.5.orig/arch/openrisc/kernel/vmlinux.lds.S 2016-03-10 00:35:58.000000000 +0100 -+++ linux-4.4.5/arch/openrisc/kernel/vmlinux.lds.S 2016-03-16 09:21:07.933535532 +0100 -@@ -30,7 +30,7 @@ - #include - #include - --OUTPUT_FORMAT("elf32-or32", "elf32-or32", "elf32-or32") -+OUTPUT_FORMAT("elf32-or1k", "elf32-or1k", "elf32-or1k") - jiffies = jiffies_64 + 4; - - SECTIONS diff --git a/target/linux/patches/4.4.28/macsonic.patch b/target/linux/patches/4.4.28/macsonic.patch deleted file mode 100644 index 75a6fcad2..000000000 --- a/target/linux/patches/4.4.28/macsonic.patch +++ /dev/null @@ -1,11 +0,0 @@ -diff -Nur linux-4.4.6.orig/drivers/net/ethernet/natsemi/Kconfig linux-4.4.6/drivers/net/ethernet/natsemi/Kconfig ---- linux-4.4.6.orig/drivers/net/ethernet/natsemi/Kconfig 2016-03-16 16:43:17.000000000 +0100 -+++ linux-4.4.6/drivers/net/ethernet/natsemi/Kconfig 2016-03-18 10:43:34.000000000 +0100 -@@ -18,6 +18,7 @@ - config MACSONIC - tristate "Macintosh SONIC based ethernet (onboard, NuBus, LC, CS)" - depends on MAC -+ select BITREVERSE - ---help--- - Support for NatSemi SONIC based Ethernet devices. This includes - the onboard Ethernet in many Quadras as well as some LC-PDS, diff --git a/target/linux/patches/4.4.28/mips-xz.patch b/target/linux/patches/4.4.28/mips-xz.patch deleted file mode 100644 index 5cfac6254..000000000 --- a/target/linux/patches/4.4.28/mips-xz.patch +++ /dev/null @@ -1,12 +0,0 @@ -diff -Nur linux-4.4.5.orig/arch/mips/boot/compressed/Makefile linux-4.4.5/arch/mips/boot/compressed/Makefile ---- linux-4.4.5.orig/arch/mips/boot/compressed/Makefile 2016-03-10 00:35:58.000000000 +0100 -+++ linux-4.4.5/arch/mips/boot/compressed/Makefile 2016-03-15 11:35:31.951795457 +0100 -@@ -41,7 +41,7 @@ - endif - - ifdef CONFIG_KERNEL_XZ --vmlinuzobjs-y += $(obj)/../../lib/ashldi3.o -+vmlinuzobjs-y += $(obj)/../../lib/ashldi3.o $(obj)/../../lib/bswapsi.o - endif - - targets += vmlinux.bin diff --git a/target/linux/patches/4.4.28/patch-realtime b/target/linux/patches/4.4.28/patch-realtime deleted file mode 100644 index 9dd3be37b..000000000 --- a/target/linux/patches/4.4.28/patch-realtime +++ /dev/null @@ -1,30987 +0,0 @@ -diff -Nur linux-4.4.28.orig/arch/arm/include/asm/switch_to.h linux-4.4.28/arch/arm/include/asm/switch_to.h ---- linux-4.4.28.orig/arch/arm/include/asm/switch_to.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/include/asm/switch_to.h 2016-11-01 21:26:56.728210258 +0100 -@@ -3,6 +3,13 @@ - - #include - -+#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM -+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); -+#else -+static inline void -+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } -+#endif -+ - /* - * For v7 SMP cores running a preemptible kernel we may be pre-empted - * during a TLB maintenance operation, so execute an inner-shareable dsb -@@ -25,6 +32,7 @@ - #define switch_to(prev,next,last) \ - do { \ - __complete_pending_tlbi(); \ -+ switch_kmaps(prev, next); \ - last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ - } while (0) - -diff -Nur linux-4.4.28.orig/arch/arm/include/asm/thread_info.h linux-4.4.28/arch/arm/include/asm/thread_info.h ---- linux-4.4.28.orig/arch/arm/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/include/asm/thread_info.h 2016-11-01 21:26:56.748211548 +0100 -@@ -49,6 +49,7 @@ - struct thread_info { - unsigned long flags; /* low level flags */ - int preempt_count; /* 0 => preemptable, <0 => bug */ -+ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ - mm_segment_t addr_limit; /* address limit */ - struct task_struct *task; /* main task structure */ - __u32 cpu; /* cpu */ -@@ -142,7 +143,8 @@ - #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ - #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ - #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ --#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ -+#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ -+#define TIF_NEED_RESCHED_LAZY 7 - - #define TIF_NOHZ 12 /* in adaptive nohz mode */ - #define TIF_USING_IWMMXT 17 -@@ -152,6 +154,7 @@ - #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) - #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) - #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) -+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) - #define _TIF_UPROBE (1 << TIF_UPROBE) - #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) - #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) -@@ -167,7 +170,8 @@ - * Change these and you break ASM code in entry-common.S - */ - #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ -- _TIF_NOTIFY_RESUME | _TIF_UPROBE) -+ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ -+ _TIF_NEED_RESCHED_LAZY) - - #endif /* __KERNEL__ */ - #endif /* __ASM_ARM_THREAD_INFO_H */ -diff -Nur linux-4.4.28.orig/arch/arm/Kconfig linux-4.4.28/arch/arm/Kconfig ---- linux-4.4.28.orig/arch/arm/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/Kconfig 2016-11-01 21:26:56.696208202 +0100 -@@ -33,7 +33,7 @@ - select HARDIRQS_SW_RESEND - select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) - select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 -- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 -+ select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !PREEMPT_RT_BASE - select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 - select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) - select HAVE_ARCH_TRACEHOOK -@@ -68,6 +68,7 @@ - select HAVE_PERF_EVENTS - select HAVE_PERF_REGS - select HAVE_PERF_USER_STACK_DUMP -+ select HAVE_PREEMPT_LAZY - select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_SYSCALL_TRACEPOINTS -diff -Nur linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c linux-4.4.28/arch/arm/kernel/asm-offsets.c ---- linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/asm-offsets.c 2016-11-01 21:26:56.760212322 +0100 -@@ -65,6 +65,7 @@ - BLANK(); - DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); - DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); -+ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); - DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); - DEFINE(TI_TASK, offsetof(struct thread_info, task)); - DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); -diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-armv.S linux-4.4.28/arch/arm/kernel/entry-armv.S ---- linux-4.4.28.orig/arch/arm/kernel/entry-armv.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/entry-armv.S 2016-11-01 21:26:56.764212578 +0100 -@@ -215,11 +215,18 @@ - #ifdef CONFIG_PREEMPT - get_thread_info tsk - ldr r8, [tsk, #TI_PREEMPT] @ get preempt count -- ldr r0, [tsk, #TI_FLAGS] @ get flags - teq r8, #0 @ if preempt count != 0 -+ bne 1f @ return from exeption -+ ldr r0, [tsk, #TI_FLAGS] @ get flags -+ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set -+ blne svc_preempt @ preempt! -+ -+ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count -+ teq r8, #0 @ if preempt lazy count != 0 - movne r0, #0 @ force flags to 0 -- tst r0, #_TIF_NEED_RESCHED -+ tst r0, #_TIF_NEED_RESCHED_LAZY - blne svc_preempt -+1: - #endif - - svc_exit r5, irq = 1 @ return from exception -@@ -234,8 +241,14 @@ - 1: bl preempt_schedule_irq @ irq en/disable is done inside - ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS - tst r0, #_TIF_NEED_RESCHED -+ bne 1b -+ tst r0, #_TIF_NEED_RESCHED_LAZY - reteq r8 @ go again -- b 1b -+ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count -+ teq r0, #0 @ if preempt lazy count != 0 -+ beq 1b -+ ret r8 @ go again -+ - #endif - - __und_fault: -diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-common.S linux-4.4.28/arch/arm/kernel/entry-common.S ---- linux-4.4.28.orig/arch/arm/kernel/entry-common.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/entry-common.S 2016-11-01 21:26:56.764212578 +0100 -@@ -36,7 +36,9 @@ - UNWIND(.cantunwind ) - disable_irq_notrace @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing -- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK -+ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) -+ bne fast_work_pending -+ tst r1, #_TIF_SECCOMP - bne fast_work_pending - - /* perform architecture specific actions before user return */ -@@ -62,8 +64,11 @@ - str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 - disable_irq_notrace @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing -- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK -+ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) -+ bne do_slower_path -+ tst r1, #_TIF_SECCOMP - beq no_work_pending -+do_slower_path: - UNWIND(.fnend ) - ENDPROC(ret_fast_syscall) - -diff -Nur linux-4.4.28.orig/arch/arm/kernel/process.c linux-4.4.28/arch/arm/kernel/process.c ---- linux-4.4.28.orig/arch/arm/kernel/process.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/process.c 2016-11-01 21:26:56.772213095 +0100 -@@ -319,6 +319,30 @@ - } - - #ifdef CONFIG_MMU -+/* -+ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not -+ * initialized by pgtable_page_ctor() then a coredump of the vector page will -+ * fail. -+ */ -+static int __init vectors_user_mapping_init_page(void) -+{ -+ struct page *page; -+ unsigned long addr = 0xffff0000; -+ pgd_t *pgd; -+ pud_t *pud; -+ pmd_t *pmd; -+ -+ pgd = pgd_offset_k(addr); -+ pud = pud_offset(pgd, addr); -+ pmd = pmd_offset(pud, addr); -+ page = pmd_page(*(pmd)); -+ -+ pgtable_page_ctor(page); -+ -+ return 0; -+} -+late_initcall(vectors_user_mapping_init_page); -+ - #ifdef CONFIG_KUSER_HELPERS - /* - * The vectors page is always readable from user space for the -diff -Nur linux-4.4.28.orig/arch/arm/kernel/signal.c linux-4.4.28/arch/arm/kernel/signal.c ---- linux-4.4.28.orig/arch/arm/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/signal.c 2016-11-01 21:26:56.772213095 +0100 -@@ -572,7 +572,8 @@ - */ - trace_hardirqs_off(); - do { -- if (likely(thread_flags & _TIF_NEED_RESCHED)) { -+ if (likely(thread_flags & (_TIF_NEED_RESCHED | -+ _TIF_NEED_RESCHED_LAZY))) { - schedule(); - } else { - if (unlikely(!user_mode(regs))) -diff -Nur linux-4.4.28.orig/arch/arm/kernel/smp.c linux-4.4.28/arch/arm/kernel/smp.c ---- linux-4.4.28.orig/arch/arm/kernel/smp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/smp.c 2016-11-01 21:26:56.772213095 +0100 -@@ -230,8 +230,6 @@ - flush_cache_louis(); - local_flush_tlb_all(); - -- clear_tasks_mm_cpumask(cpu); -- - return 0; - } - -@@ -247,6 +245,9 @@ - pr_err("CPU%u: cpu didn't die\n", cpu); - return; - } -+ -+ clear_tasks_mm_cpumask(cpu); -+ - pr_notice("CPU%u: shutdown\n", cpu); - - /* -diff -Nur linux-4.4.28.orig/arch/arm/kernel/unwind.c linux-4.4.28/arch/arm/kernel/unwind.c ---- linux-4.4.28.orig/arch/arm/kernel/unwind.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kernel/unwind.c 2016-11-01 21:26:56.776213352 +0100 -@@ -93,7 +93,7 @@ - static const struct unwind_idx *__origin_unwind_idx; - extern const struct unwind_idx __stop_unwind_idx[]; - --static DEFINE_SPINLOCK(unwind_lock); -+static DEFINE_RAW_SPINLOCK(unwind_lock); - static LIST_HEAD(unwind_tables); - - /* Convert a prel31 symbol to an absolute address */ -@@ -201,7 +201,7 @@ - /* module unwind tables */ - struct unwind_table *table; - -- spin_lock_irqsave(&unwind_lock, flags); -+ raw_spin_lock_irqsave(&unwind_lock, flags); - list_for_each_entry(table, &unwind_tables, list) { - if (addr >= table->begin_addr && - addr < table->end_addr) { -@@ -213,7 +213,7 @@ - break; - } - } -- spin_unlock_irqrestore(&unwind_lock, flags); -+ raw_spin_unlock_irqrestore(&unwind_lock, flags); - } - - pr_debug("%s: idx = %p\n", __func__, idx); -@@ -529,9 +529,9 @@ - tab->begin_addr = text_addr; - tab->end_addr = text_addr + text_size; - -- spin_lock_irqsave(&unwind_lock, flags); -+ raw_spin_lock_irqsave(&unwind_lock, flags); - list_add_tail(&tab->list, &unwind_tables); -- spin_unlock_irqrestore(&unwind_lock, flags); -+ raw_spin_unlock_irqrestore(&unwind_lock, flags); - - return tab; - } -@@ -543,9 +543,9 @@ - if (!tab) - return; - -- spin_lock_irqsave(&unwind_lock, flags); -+ raw_spin_lock_irqsave(&unwind_lock, flags); - list_del(&tab->list); -- spin_unlock_irqrestore(&unwind_lock, flags); -+ raw_spin_unlock_irqrestore(&unwind_lock, flags); - - kfree(tab); - } -diff -Nur linux-4.4.28.orig/arch/arm/kvm/arm.c linux-4.4.28/arch/arm/kvm/arm.c ---- linux-4.4.28.orig/arch/arm/kvm/arm.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kvm/arm.c 2016-11-01 21:26:56.776213352 +0100 -@@ -496,18 +496,18 @@ - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { -- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); -+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - - vcpu->arch.pause = false; -- wake_up_interruptible(wq); -+ swake_up(wq); - } - } - - static void vcpu_sleep(struct kvm_vcpu *vcpu) - { -- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); -+ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - -- wait_event_interruptible(*wq, ((!vcpu->arch.power_off) && -+ swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && - (!vcpu->arch.pause))); - } - -@@ -566,7 +566,7 @@ - * involves poking the GIC, which must be done in a - * non-preemptible context. - */ -- preempt_disable(); -+ migrate_disable(); - kvm_timer_flush_hwstate(vcpu); - kvm_vgic_flush_hwstate(vcpu); - -@@ -585,7 +585,7 @@ - local_irq_enable(); - kvm_timer_sync_hwstate(vcpu); - kvm_vgic_sync_hwstate(vcpu); -- preempt_enable(); -+ migrate_enable(); - continue; - } - -@@ -639,7 +639,7 @@ - - kvm_vgic_sync_hwstate(vcpu); - -- preempt_enable(); -+ migrate_enable(); - - ret = handle_exit(vcpu, run, ret); - } -diff -Nur linux-4.4.28.orig/arch/arm/kvm/psci.c linux-4.4.28/arch/arm/kvm/psci.c ---- linux-4.4.28.orig/arch/arm/kvm/psci.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/kvm/psci.c 2016-11-01 21:26:56.780213616 +0100 -@@ -70,7 +70,7 @@ - { - struct kvm *kvm = source_vcpu->kvm; - struct kvm_vcpu *vcpu = NULL; -- wait_queue_head_t *wq; -+ struct swait_queue_head *wq; - unsigned long cpu_id; - unsigned long context_id; - phys_addr_t target_pc; -@@ -119,7 +119,7 @@ - smp_mb(); /* Make sure the above is visible */ - - wq = kvm_arch_vcpu_wq(vcpu); -- wake_up_interruptible(wq); -+ swake_up(wq); - - return PSCI_RET_SUCCESS; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c linux-4.4.28/arch/arm/mach-at91/at91rm9200.c ---- linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/at91rm9200.c 2016-11-01 21:26:56.784213869 +0100 -@@ -12,7 +12,6 @@ - #include - - #include --#include - - #include "generic.h" - #include "soc.h" -@@ -33,7 +32,6 @@ - - of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); - -- arm_pm_idle = at91rm9200_idle; - at91rm9200_pm_init(); - } - -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c linux-4.4.28/arch/arm/mach-at91/at91sam9.c ---- linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/at91sam9.c 2016-11-01 21:26:56.784213869 +0100 -@@ -62,8 +62,6 @@ - soc_dev = soc_device_to_device(soc); - - of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); -- -- arm_pm_idle = at91sam9_idle; - } - - static void __init at91sam9_dt_device_init(void) -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/generic.h linux-4.4.28/arch/arm/mach-at91/generic.h ---- linux-4.4.28.orig/arch/arm/mach-at91/generic.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/generic.h 2016-11-01 21:26:56.784213869 +0100 -@@ -11,27 +11,18 @@ - #ifndef _AT91_GENERIC_H - #define _AT91_GENERIC_H - --#include --#include -- -- /* Map io */ --extern void __init at91_map_io(void); --extern void __init at91_alt_map_io(void); -- --/* idle */ --extern void at91rm9200_idle(void); --extern void at91sam9_idle(void); -- - #ifdef CONFIG_PM - extern void __init at91rm9200_pm_init(void); - extern void __init at91sam9260_pm_init(void); - extern void __init at91sam9g45_pm_init(void); - extern void __init at91sam9x5_pm_init(void); -+extern void __init sama5_pm_init(void); - #else - static inline void __init at91rm9200_pm_init(void) { } - static inline void __init at91sam9260_pm_init(void) { } - static inline void __init at91sam9g45_pm_init(void) { } - static inline void __init at91sam9x5_pm_init(void) { } -+static inline void __init sama5_pm_init(void) { } - #endif - - #endif /* _AT91_GENERIC_H */ -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/Kconfig linux-4.4.28/arch/arm/mach-at91/Kconfig ---- linux-4.4.28.orig/arch/arm/mach-at91/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/Kconfig 2016-11-01 21:26:56.784213869 +0100 -@@ -99,6 +99,7 @@ - config COMMON_CLK_AT91 - bool - select COMMON_CLK -+ select MFD_SYSCON - - config HAVE_AT91_SMD - bool -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/pm.c linux-4.4.28/arch/arm/mach-at91/pm.c ---- linux-4.4.28.orig/arch/arm/mach-at91/pm.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/pm.c 2016-11-01 21:26:56.788214125 +0100 -@@ -31,10 +31,13 @@ - #include - #include - #include -+#include - - #include "generic.h" - #include "pm.h" - -+static void __iomem *pmc; -+ - /* - * FIXME: this is needed to communicate between the pinctrl driver and - * the PM implementation in the machine. Possibly part of the PM -@@ -87,7 +90,7 @@ - unsigned long scsr; - int i; - -- scsr = at91_pmc_read(AT91_PMC_SCSR); -+ scsr = readl(pmc + AT91_PMC_SCSR); - - /* USB must not be using PLLB */ - if ((scsr & at91_pm_data.uhp_udp_mask) != 0) { -@@ -101,8 +104,7 @@ - - if ((scsr & (AT91_PMC_PCK0 << i)) == 0) - continue; -- -- css = at91_pmc_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS; -+ css = readl(pmc + AT91_PMC_PCKR(i)) & AT91_PMC_CSS; - if (css != AT91_PMC_CSS_SLOW) { - pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css); - return 0; -@@ -145,8 +147,8 @@ - flush_cache_all(); - outer_disable(); - -- at91_suspend_sram_fn(at91_pmc_base, at91_ramc_base[0], -- at91_ramc_base[1], pm_data); -+ at91_suspend_sram_fn(pmc, at91_ramc_base[0], -+ at91_ramc_base[1], pm_data); - - outer_resume(); - } -@@ -353,6 +355,21 @@ - at91_pm_set_standby(standby); - } - -+void at91rm9200_idle(void) -+{ -+ /* -+ * Disable the processor clock. The processor will be automatically -+ * re-enabled by an interrupt or by a reset. -+ */ -+ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); -+} -+ -+void at91sam9_idle(void) -+{ -+ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); -+ cpu_do_idle(); -+} -+ - static void __init at91_pm_sram_init(void) - { - struct gen_pool *sram_pool; -@@ -399,13 +416,36 @@ - &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); - } - --static void __init at91_pm_init(void) -+static const struct of_device_id atmel_pmc_ids[] __initconst = { -+ { .compatible = "atmel,at91rm9200-pmc" }, -+ { .compatible = "atmel,at91sam9260-pmc" }, -+ { .compatible = "atmel,at91sam9g45-pmc" }, -+ { .compatible = "atmel,at91sam9n12-pmc" }, -+ { .compatible = "atmel,at91sam9x5-pmc" }, -+ { .compatible = "atmel,sama5d3-pmc" }, -+ { .compatible = "atmel,sama5d2-pmc" }, -+ { /* sentinel */ }, -+}; -+ -+static void __init at91_pm_init(void (*pm_idle)(void)) - { -- at91_pm_sram_init(); -+ struct device_node *pmc_np; - - if (at91_cpuidle_device.dev.platform_data) - platform_device_register(&at91_cpuidle_device); - -+ pmc_np = of_find_matching_node(NULL, atmel_pmc_ids); -+ pmc = of_iomap(pmc_np, 0); -+ if (!pmc) { -+ pr_err("AT91: PM not supported, PMC not found\n"); -+ return; -+ } -+ -+ if (pm_idle) -+ arm_pm_idle = pm_idle; -+ -+ at91_pm_sram_init(); -+ - if (at91_suspend_sram_fn) - suspend_set_ops(&at91_pm_ops); - else -@@ -424,7 +464,7 @@ - at91_pm_data.uhp_udp_mask = AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP; - at91_pm_data.memctrl = AT91_MEMCTRL_MC; - -- at91_pm_init(); -+ at91_pm_init(at91rm9200_idle); - } - - void __init at91sam9260_pm_init(void) -@@ -432,7 +472,7 @@ - at91_dt_ramc(); - at91_pm_data.memctrl = AT91_MEMCTRL_SDRAMC; - at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; -- return at91_pm_init(); -+ at91_pm_init(at91sam9_idle); - } - - void __init at91sam9g45_pm_init(void) -@@ -440,7 +480,7 @@ - at91_dt_ramc(); - at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP; - at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; -- return at91_pm_init(); -+ at91_pm_init(at91sam9_idle); - } - - void __init at91sam9x5_pm_init(void) -@@ -448,5 +488,13 @@ - at91_dt_ramc(); - at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; - at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; -- return at91_pm_init(); -+ at91_pm_init(at91sam9_idle); -+} -+ -+void __init sama5_pm_init(void) -+{ -+ at91_dt_ramc(); -+ at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; -+ at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; -+ at91_pm_init(NULL); - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/sama5.c linux-4.4.28/arch/arm/mach-at91/sama5.c ---- linux-4.4.28.orig/arch/arm/mach-at91/sama5.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-at91/sama5.c 2016-11-01 21:26:56.788214125 +0100 -@@ -51,7 +51,7 @@ - soc_dev = soc_device_to_device(soc); - - of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); -- at91sam9x5_pm_init(); -+ sama5_pm_init(); - } - - static const char *const sama5_dt_board_compat[] __initconst = { -diff -Nur linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c linux-4.4.28/arch/arm/mach-exynos/platsmp.c ---- linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-exynos/platsmp.c 2016-11-01 21:26:56.796214642 +0100 -@@ -230,7 +230,7 @@ - return (void __iomem *)(S5P_VA_SCU); - } - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - static void exynos_secondary_init(unsigned int cpu) - { -@@ -243,8 +243,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) -@@ -308,7 +308,7 @@ - * Set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * The secondary processor is waiting to be released from -@@ -335,7 +335,7 @@ - - if (timeout == 0) { - printk(KERN_ERR "cpu1 power enable failed"); -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - return -ETIMEDOUT; - } - } -@@ -381,7 +381,7 @@ - * calibrations, then wait for it to finish - */ - fail: -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return pen_release != -1 ? ret : 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c linux-4.4.28/arch/arm/mach-hisi/platmcpm.c ---- linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-hisi/platmcpm.c 2016-11-01 21:26:56.800214899 +0100 -@@ -61,7 +61,7 @@ - - static void __iomem *sysctrl, *fabric; - static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - static u32 fabric_phys_addr; - /* - * [0]: bootwrapper physical address -@@ -113,7 +113,7 @@ - if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) - return -EINVAL; - -- spin_lock_irq(&boot_lock); -+ raw_spin_lock_irq(&boot_lock); - - if (hip04_cpu_table[cluster][cpu]) - goto out; -@@ -147,7 +147,7 @@ - - out: - hip04_cpu_table[cluster][cpu]++; -- spin_unlock_irq(&boot_lock); -+ raw_spin_unlock_irq(&boot_lock); - - return 0; - } -@@ -162,11 +162,11 @@ - cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); - cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); - -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - hip04_cpu_table[cluster][cpu]--; - if (hip04_cpu_table[cluster][cpu] == 1) { - /* A power_up request went ahead of us. */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - return; - } else if (hip04_cpu_table[cluster][cpu] > 1) { - pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); -@@ -174,7 +174,7 @@ - } - - last_man = hip04_cluster_is_down(cluster); -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - if (last_man) { - /* Since it's Cortex A15, disable L2 prefetching. */ - asm volatile( -@@ -203,7 +203,7 @@ - cpu >= HIP04_MAX_CPUS_PER_CLUSTER); - - count = TIMEOUT_MSEC / POLL_MSEC; -- spin_lock_irq(&boot_lock); -+ raw_spin_lock_irq(&boot_lock); - for (tries = 0; tries < count; tries++) { - if (hip04_cpu_table[cluster][cpu]) - goto err; -@@ -211,10 +211,10 @@ - data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); - if (data & CORE_WFI_STATUS(cpu)) - break; -- spin_unlock_irq(&boot_lock); -+ raw_spin_unlock_irq(&boot_lock); - /* Wait for clean L2 when the whole cluster is down. */ - msleep(POLL_MSEC); -- spin_lock_irq(&boot_lock); -+ raw_spin_lock_irq(&boot_lock); - } - if (tries >= count) - goto err; -@@ -231,10 +231,10 @@ - goto err; - if (hip04_cluster_is_down(cluster)) - hip04_set_snoop_filter(cluster, 0); -- spin_unlock_irq(&boot_lock); -+ raw_spin_unlock_irq(&boot_lock); - return 1; - err: -- spin_unlock_irq(&boot_lock); -+ raw_spin_unlock_irq(&boot_lock); - return 0; - } - #endif -diff -Nur linux-4.4.28.orig/arch/arm/mach-imx/Kconfig linux-4.4.28/arch/arm/mach-imx/Kconfig ---- linux-4.4.28.orig/arch/arm/mach-imx/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-imx/Kconfig 2016-11-01 21:26:56.804215163 +0100 -@@ -524,7 +524,7 @@ - bool "i.MX6 Quad/DualLite support" - select ARM_ERRATA_764369 if SMP - select HAVE_ARM_SCU if SMP -- select HAVE_ARM_TWD if SMP -+ select HAVE_ARM_TWD - select PCI_DOMAINS if PCI - select PINCTRL_IMX6Q - select SOC_IMX6 -diff -Nur linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c linux-4.4.28/arch/arm/mach-omap2/omap-smp.c ---- linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-omap2/omap-smp.c 2016-11-01 21:26:56.836217219 +0100 -@@ -43,7 +43,7 @@ - /* SCU base address */ - static void __iomem *scu_base; - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - void __iomem *omap4_get_scu_base(void) - { -@@ -74,8 +74,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) -@@ -89,7 +89,7 @@ - * Set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * Update the AuxCoreBoot0 with boot state for secondary core. -@@ -166,7 +166,7 @@ - * Now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c linux-4.4.28/arch/arm/mach-prima2/platsmp.c ---- linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-prima2/platsmp.c 2016-11-01 21:26:56.864219031 +0100 -@@ -22,7 +22,7 @@ - - static void __iomem *clk_base; - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - static void sirfsoc_secondary_init(unsigned int cpu) - { -@@ -36,8 +36,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - static const struct of_device_id clk_ids[] = { -@@ -75,7 +75,7 @@ - /* make sure write buffer is drained */ - mb(); - -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * The secondary processor is waiting to be released from -@@ -107,7 +107,7 @@ - * now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return pen_release != -1 ? -ENOSYS : 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c linux-4.4.28/arch/arm/mach-qcom/platsmp.c ---- linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-qcom/platsmp.c 2016-11-01 21:26:56.872219540 +0100 -@@ -46,7 +46,7 @@ - - extern void secondary_startup_arm(void); - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - #ifdef CONFIG_HOTPLUG_CPU - static void qcom_cpu_die(unsigned int cpu) -@@ -60,8 +60,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - static int scss_release_secondary(unsigned int cpu) -@@ -284,7 +284,7 @@ - * set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * Send the secondary CPU a soft interrupt, thereby causing -@@ -297,7 +297,7 @@ - * now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return ret; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c linux-4.4.28/arch/arm/mach-spear/platsmp.c ---- linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-spear/platsmp.c 2016-11-01 21:26:56.896221093 +0100 -@@ -32,7 +32,7 @@ - sync_cache_w(&pen_release); - } - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - static void __iomem *scu_base = IOMEM(VA_SCU_BASE); - -@@ -47,8 +47,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) -@@ -59,7 +59,7 @@ - * set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * The secondary processor is waiting to be released from -@@ -84,7 +84,7 @@ - * now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return pen_release != -1 ? -ENOSYS : 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c linux-4.4.28/arch/arm/mach-sti/platsmp.c ---- linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mach-sti/platsmp.c 2016-11-01 21:26:56.896221093 +0100 -@@ -35,7 +35,7 @@ - sync_cache_w(&pen_release); - } - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - static void sti_secondary_init(unsigned int cpu) - { -@@ -48,8 +48,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) -@@ -60,7 +60,7 @@ - * set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * The secondary processor is waiting to be released from -@@ -91,7 +91,7 @@ - * now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return pen_release != -1 ? -ENOSYS : 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mm/fault.c linux-4.4.28/arch/arm/mm/fault.c ---- linux-4.4.28.orig/arch/arm/mm/fault.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mm/fault.c 2016-11-01 21:26:56.900221345 +0100 -@@ -430,6 +430,9 @@ - if (addr < TASK_SIZE) - return do_page_fault(addr, fsr, regs); - -+ if (interrupts_enabled(regs)) -+ local_irq_enable(); -+ - if (user_mode(regs)) - goto bad_area; - -@@ -497,6 +500,9 @@ - static int - do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) - { -+ if (interrupts_enabled(regs)) -+ local_irq_enable(); -+ - do_bad_area(addr, fsr, regs); - return 0; - } -diff -Nur linux-4.4.28.orig/arch/arm/mm/highmem.c linux-4.4.28/arch/arm/mm/highmem.c ---- linux-4.4.28.orig/arch/arm/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/mm/highmem.c 2016-11-01 21:26:56.904221609 +0100 -@@ -34,6 +34,11 @@ - return *ptep; - } - -+static unsigned int fixmap_idx(int type) -+{ -+ return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); -+} -+ - void *kmap(struct page *page) - { - might_sleep(); -@@ -54,12 +59,13 @@ - - void *kmap_atomic(struct page *page) - { -+ pte_t pte = mk_pte(page, kmap_prot); - unsigned int idx; - unsigned long vaddr; - void *kmap; - int type; - -- preempt_disable(); -+ preempt_disable_nort(); - pagefault_disable(); - if (!PageHighMem(page)) - return page_address(page); -@@ -79,7 +85,7 @@ - - type = kmap_atomic_idx_push(); - -- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); -+ idx = fixmap_idx(type); - vaddr = __fix_to_virt(idx); - #ifdef CONFIG_DEBUG_HIGHMEM - /* -@@ -93,7 +99,10 @@ - * in place, so the contained TLB flush ensures the TLB is updated - * with the new mapping. - */ -- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = pte; -+#endif -+ set_fixmap_pte(idx, pte); - - return (void *)vaddr; - } -@@ -106,44 +115,75 @@ - - if (kvaddr >= (void *)FIXADDR_START) { - type = kmap_atomic_idx(); -- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); -+ idx = fixmap_idx(type); - - if (cache_is_vivt()) - __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = __pte(0); -+#endif - #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(vaddr != __fix_to_virt(idx)); -- set_fixmap_pte(idx, __pte(0)); - #else - (void) idx; /* to kill a warning */ - #endif -+ set_fixmap_pte(idx, __pte(0)); - kmap_atomic_idx_pop(); - } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { - /* this address was obtained through kmap_high_get() */ - kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); - } - pagefault_enable(); -- preempt_enable(); -+ preempt_enable_nort(); - } - EXPORT_SYMBOL(__kunmap_atomic); - - void *kmap_atomic_pfn(unsigned long pfn) - { -+ pte_t pte = pfn_pte(pfn, kmap_prot); - unsigned long vaddr; - int idx, type; - struct page *page = pfn_to_page(pfn); - -- preempt_disable(); -+ preempt_disable_nort(); - pagefault_disable(); - if (!PageHighMem(page)) - return page_address(page); - - type = kmap_atomic_idx_push(); -- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); -+ idx = fixmap_idx(type); - vaddr = __fix_to_virt(idx); - #ifdef CONFIG_DEBUG_HIGHMEM - BUG_ON(!pte_none(get_fixmap_pte(vaddr))); - #endif -- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = pte; -+#endif -+ set_fixmap_pte(idx, pte); - - return (void *)vaddr; - } -+#if defined CONFIG_PREEMPT_RT_FULL -+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) -+{ -+ int i; -+ -+ /* -+ * Clear @prev's kmap_atomic mappings -+ */ -+ for (i = 0; i < prev_p->kmap_idx; i++) { -+ int idx = fixmap_idx(i); -+ -+ set_fixmap_pte(idx, __pte(0)); -+ } -+ /* -+ * Restore @next_p's kmap_atomic mappings -+ */ -+ for (i = 0; i < next_p->kmap_idx; i++) { -+ int idx = fixmap_idx(i); -+ -+ if (!pte_none(next_p->kmap_pte[i])) -+ set_fixmap_pte(idx, next_p->kmap_pte[i]); -+ } -+} -+#endif -diff -Nur linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c linux-4.4.28/arch/arm/plat-versatile/platsmp.c ---- linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm/plat-versatile/platsmp.c 2016-11-01 21:26:56.936223672 +0100 -@@ -30,7 +30,7 @@ - sync_cache_w(&pen_release); - } - --static DEFINE_SPINLOCK(boot_lock); -+static DEFINE_RAW_SPINLOCK(boot_lock); - - void versatile_secondary_init(unsigned int cpu) - { -@@ -43,8 +43,8 @@ - /* - * Synchronise with the boot thread. - */ -- spin_lock(&boot_lock); -- spin_unlock(&boot_lock); -+ raw_spin_lock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - } - - int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) -@@ -55,7 +55,7 @@ - * Set synchronisation state between this boot processor - * and the secondary one - */ -- spin_lock(&boot_lock); -+ raw_spin_lock(&boot_lock); - - /* - * This is really belt and braces; we hold unintended secondary -@@ -85,7 +85,7 @@ - * now the secondary core is starting up let it run its - * calibrations, then wait for it to finish - */ -- spin_unlock(&boot_lock); -+ raw_spin_unlock(&boot_lock); - - return pen_release != -1 ? -ENOSYS : 0; - } -diff -Nur linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h linux-4.4.28/arch/arm64/include/asm/thread_info.h ---- linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm64/include/asm/thread_info.h 2016-11-01 21:26:56.948224439 +0100 -@@ -49,6 +49,7 @@ - mm_segment_t addr_limit; /* address limit */ - struct task_struct *task; /* main task structure */ - int preempt_count; /* 0 => preemptable, <0 => bug */ -+ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ - int cpu; /* cpu */ - }; - -@@ -103,6 +104,7 @@ - #define TIF_NEED_RESCHED 1 - #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ - #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ -+#define TIF_NEED_RESCHED_LAZY 4 - #define TIF_NOHZ 7 - #define TIF_SYSCALL_TRACE 8 - #define TIF_SYSCALL_AUDIT 9 -@@ -118,6 +120,7 @@ - #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) - #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) - #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) -+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) - #define _TIF_NOHZ (1 << TIF_NOHZ) - #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) - #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) -@@ -126,7 +129,8 @@ - #define _TIF_32BIT (1 << TIF_32BIT) - - #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ -- _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) -+ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ -+ _TIF_NEED_RESCHED_LAZY) - - #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ -diff -Nur linux-4.4.28.orig/arch/arm64/Kconfig linux-4.4.28/arch/arm64/Kconfig ---- linux-4.4.28.orig/arch/arm64/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm64/Kconfig 2016-11-01 21:26:56.944224187 +0100 -@@ -76,6 +76,7 @@ - select HAVE_PERF_REGS - select HAVE_PERF_USER_STACK_DUMP - select HAVE_RCU_TABLE_FREE -+ select HAVE_PREEMPT_LAZY - select HAVE_SYSCALL_TRACEPOINTS - select IOMMU_DMA if IOMMU_SUPPORT - select IRQ_DOMAIN -@@ -582,7 +583,7 @@ - - config XEN - bool "Xen guest support on ARM64" -- depends on ARM64 && OF -+ depends on ARM64 && OF && !PREEMPT_RT_FULL - select SWIOTLB_XEN - help - Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. -diff -Nur linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c linux-4.4.28/arch/arm64/kernel/asm-offsets.c ---- linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm64/kernel/asm-offsets.c 2016-11-01 21:26:56.976226250 +0100 -@@ -35,6 +35,7 @@ - BLANK(); - DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); - DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); -+ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); - DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); - DEFINE(TI_TASK, offsetof(struct thread_info, task)); - DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); -diff -Nur linux-4.4.28.orig/arch/arm64/kernel/entry.S linux-4.4.28/arch/arm64/kernel/entry.S ---- linux-4.4.28.orig/arch/arm64/kernel/entry.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/arm64/kernel/entry.S 2016-11-01 21:26:56.976226250 +0100 -@@ -376,11 +376,16 @@ - #ifdef CONFIG_PREEMPT - get_thread_info tsk - ldr w24, [tsk, #TI_PREEMPT] // get preempt count -- cbnz w24, 1f // preempt count != 0 -+ cbnz w24, 2f // preempt count != 0 - ldr x0, [tsk, #TI_FLAGS] // get flags -- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? -- bl el1_preempt -+ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? -+ -+ ldr w24, [tsk, #TI_PREEMPT_LAZY] // get preempt lazy count -+ cbnz w24, 2f // preempt lazy count != 0 -+ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? - 1: -+ bl el1_preempt -+2: - #endif - #ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_on -@@ -394,6 +399,7 @@ - 1: bl preempt_schedule_irq // irq en/disable is done inside - ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS - tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? -+ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? - ret x24 - #endif - -@@ -638,6 +644,7 @@ - */ - work_pending: - tbnz x1, #TIF_NEED_RESCHED, work_resched -+ tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched - /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ - ldr x2, [sp, #S_PSTATE] - mov x0, sp // 'regs' -diff -Nur linux-4.4.28.orig/arch/Kconfig linux-4.4.28/arch/Kconfig ---- linux-4.4.28.orig/arch/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/Kconfig 2016-11-01 21:26:56.688207681 +0100 -@@ -9,6 +9,7 @@ - tristate "OProfile system profiling" - depends on PROFILING - depends on HAVE_OPROFILE -+ depends on !PREEMPT_RT_FULL - select RING_BUFFER - select RING_BUFFER_ALLOW_SWAP - help -@@ -52,6 +53,7 @@ - config JUMP_LABEL - bool "Optimize very unlikely/likely branches" - depends on HAVE_ARCH_JUMP_LABEL -+ depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST) - help - This option enables a transparent branch optimization that - makes certain almost-always-true or almost-always-false branch -diff -Nur linux-4.4.28.orig/arch/mips/Kconfig linux-4.4.28/arch/mips/Kconfig ---- linux-4.4.28.orig/arch/mips/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/mips/Kconfig 2016-11-01 21:26:57.008228310 +0100 -@@ -2410,7 +2410,7 @@ - # - config HIGHMEM - bool "High Memory Support" -- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA -+ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL - - config CPU_SUPPORTS_HIGHMEM - bool -diff -Nur linux-4.4.28.orig/arch/mips/kvm/mips.c linux-4.4.28/arch/mips/kvm/mips.c ---- linux-4.4.28.orig/arch/mips/kvm/mips.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/mips/kvm/mips.c 2016-11-01 21:26:57.044230629 +0100 -@@ -454,8 +454,8 @@ - - dvcpu->arch.wait = 0; - -- if (waitqueue_active(&dvcpu->wq)) -- wake_up_interruptible(&dvcpu->wq); -+ if (swait_active(&dvcpu->wq)) -+ swake_up(&dvcpu->wq); - - return 0; - } -@@ -1183,8 +1183,8 @@ - kvm_mips_callbacks->queue_timer_int(vcpu); - - vcpu->arch.wait = 0; -- if (waitqueue_active(&vcpu->wq)) -- wake_up_interruptible(&vcpu->wq); -+ if (swait_active(&vcpu->wq)) -+ swake_up(&vcpu->wq); - } - - /* low level hrtimer wake routine */ -diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h linux-4.4.28/arch/powerpc/include/asm/kvm_host.h ---- linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/include/asm/kvm_host.h 2016-11-01 21:26:57.116235270 +0100 -@@ -286,7 +286,7 @@ - struct list_head runnable_threads; - struct list_head preempt_list; - spinlock_t lock; -- wait_queue_head_t wq; -+ struct swait_queue_head wq; - spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ - u64 stolen_tb; - u64 preempt_tb; -@@ -626,7 +626,7 @@ - u8 prodded; - u32 last_inst; - -- wait_queue_head_t *wqp; -+ struct swait_queue_head *wqp; - struct kvmppc_vcore *vcore; - int ret; - int trap; -diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h linux-4.4.28/arch/powerpc/include/asm/thread_info.h ---- linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/include/asm/thread_info.h 2016-11-01 21:26:57.124235787 +0100 -@@ -42,6 +42,8 @@ - int cpu; /* cpu we're on */ - int preempt_count; /* 0 => preemptable, - <0 => BUG */ -+ int preempt_lazy_count; /* 0 => preemptable, -+ <0 => BUG */ - unsigned long local_flags; /* private flags for thread */ - - /* low level flags - has atomic operations done on it */ -@@ -82,8 +84,7 @@ - #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ - #define TIF_SIGPENDING 1 /* signal pending */ - #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ --#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling -- TIF_NEED_RESCHED */ -+#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */ - #define TIF_32BIT 4 /* 32 bit binary */ - #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ - #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ -@@ -101,6 +102,8 @@ - #if defined(CONFIG_PPC64) - #define TIF_ELF2ABI 18 /* function descriptors must die! */ - #endif -+#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling -+ TIF_NEED_RESCHED */ - - /* as above, but as bit values */ - #define _TIF_SYSCALL_TRACE (1<flags) - set_bits(irqtp->flags, &curtp->flags); - } -+#endif - - irq_hw_number_t virq_to_hw(unsigned int virq) - { -diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S linux-4.4.28/arch/powerpc/kernel/misc_32.S ---- linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/kernel/misc_32.S 2016-11-01 21:26:57.156237855 +0100 -@@ -40,6 +40,7 @@ - * We store the saved ksp_limit in the unused part - * of the STACK_FRAME_OVERHEAD - */ -+#ifndef CONFIG_PREEMPT_RT_FULL - _GLOBAL(call_do_softirq) - mflr r0 - stw r0,4(r1) -@@ -56,6 +57,7 @@ - stw r10,THREAD+KSP_LIMIT(r2) - mtlr r0 - blr -+#endif - - /* - * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); -diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S linux-4.4.28/arch/powerpc/kernel/misc_64.S ---- linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/kernel/misc_64.S 2016-11-01 21:26:57.160238107 +0100 -@@ -30,6 +30,7 @@ - - .text - -+#ifndef CONFIG_PREEMPT_RT_FULL - _GLOBAL(call_do_softirq) - mflr r0 - std r0,16(r1) -@@ -40,6 +41,7 @@ - ld r0,16(r1) - mtlr r0 - blr -+#endif - - _GLOBAL(call_do_irq) - mflr r0 -diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c linux-4.4.28/arch/powerpc/kvm/book3s_hv.c ---- linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/kvm/book3s_hv.c 2016-11-01 21:26:57.184239655 +0100 -@@ -114,11 +114,11 @@ - static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) - { - int cpu; -- wait_queue_head_t *wqp; -+ struct swait_queue_head *wqp; - - wqp = kvm_arch_vcpu_wq(vcpu); -- if (waitqueue_active(wqp)) { -- wake_up_interruptible(wqp); -+ if (swait_active(wqp)) { -+ swake_up(wqp); - ++vcpu->stat.halt_wakeup; - } - -@@ -707,8 +707,8 @@ - tvcpu->arch.prodded = 1; - smp_mb(); - if (vcpu->arch.ceded) { -- if (waitqueue_active(&vcpu->wq)) { -- wake_up_interruptible(&vcpu->wq); -+ if (swait_active(&vcpu->wq)) { -+ swake_up(&vcpu->wq); - vcpu->stat.halt_wakeup++; - } - } -@@ -1447,7 +1447,7 @@ - INIT_LIST_HEAD(&vcore->runnable_threads); - spin_lock_init(&vcore->lock); - spin_lock_init(&vcore->stoltb_lock); -- init_waitqueue_head(&vcore->wq); -+ init_swait_queue_head(&vcore->wq); - vcore->preempt_tb = TB_NIL; - vcore->lpcr = kvm->arch.lpcr; - vcore->first_vcpuid = core * threads_per_subcore; -@@ -2519,10 +2519,9 @@ - { - struct kvm_vcpu *vcpu; - int do_sleep = 1; -+ DECLARE_SWAITQUEUE(wait); - -- DEFINE_WAIT(wait); -- -- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); -+ prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); - - /* - * Check one last time for pending exceptions and ceded state after -@@ -2536,7 +2535,7 @@ - } - - if (!do_sleep) { -- finish_wait(&vc->wq, &wait); -+ finish_swait(&vc->wq, &wait); - return; - } - -@@ -2544,7 +2543,7 @@ - trace_kvmppc_vcore_blocked(vc, 0); - spin_unlock(&vc->lock); - schedule(); -- finish_wait(&vc->wq, &wait); -+ finish_swait(&vc->wq, &wait); - spin_lock(&vc->lock); - vc->vcore_state = VCORE_INACTIVE; - trace_kvmppc_vcore_blocked(vc, 1); -@@ -2600,7 +2599,7 @@ - kvmppc_start_thread(vcpu, vc); - trace_kvm_guest_enter(vcpu); - } else if (vc->vcore_state == VCORE_SLEEPING) { -- wake_up(&vc->wq); -+ swake_up(&vc->wq); - } - - } -diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/Kconfig linux-4.4.28/arch/powerpc/kvm/Kconfig ---- linux-4.4.28.orig/arch/powerpc/kvm/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/kvm/Kconfig 2016-11-01 21:26:57.168238628 +0100 -@@ -172,6 +172,7 @@ - config KVM_MPIC - bool "KVM in-kernel MPIC emulation" - depends on KVM && E500 -+ depends on !PREEMPT_RT_FULL - select HAVE_KVM_IRQCHIP - select HAVE_KVM_IRQFD - select HAVE_KVM_IRQ_ROUTING -diff -Nur linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c ---- linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c 2016-11-01 21:26:57.192240175 +0100 -@@ -752,7 +752,7 @@ - } - pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); - -- res = wait_event_interruptible(dev->done.wait, -+ res = swait_event_interruptible(dev->done.wait, - dev->done.done || kthread_should_stop()); - if (kthread_should_stop()) - res = -EINTR; -diff -Nur linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h linux-4.4.28/arch/s390/include/asm/kvm_host.h ---- linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/s390/include/asm/kvm_host.h 2016-11-01 21:26:57.204240949 +0100 -@@ -427,7 +427,7 @@ - struct kvm_s390_local_interrupt { - spinlock_t lock; - struct kvm_s390_float_interrupt *float_int; -- wait_queue_head_t *wq; -+ struct swait_queue_head *wq; - atomic_t *cpuflags; - DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); - struct kvm_s390_irq_payload irq; -diff -Nur linux-4.4.28.orig/arch/s390/kvm/interrupt.c linux-4.4.28/arch/s390/kvm/interrupt.c ---- linux-4.4.28.orig/arch/s390/kvm/interrupt.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/s390/kvm/interrupt.c 2016-11-01 21:26:57.224242231 +0100 -@@ -868,13 +868,13 @@ - - void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) - { -- if (waitqueue_active(&vcpu->wq)) { -+ if (swait_active(&vcpu->wq)) { - /* - * The vcpu gave up the cpu voluntarily, mark it as a good - * yield-candidate. - */ - vcpu->preempted = true; -- wake_up_interruptible(&vcpu->wq); -+ swake_up(&vcpu->wq); - vcpu->stat.halt_wakeup++; - } - } -diff -Nur linux-4.4.28.orig/arch/sh/kernel/irq.c linux-4.4.28/arch/sh/kernel/irq.c ---- linux-4.4.28.orig/arch/sh/kernel/irq.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/sh/kernel/irq.c 2016-11-01 21:26:57.284246099 +0100 -@@ -147,6 +147,7 @@ - hardirq_ctx[cpu] = NULL; - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - void do_softirq_own_stack(void) - { - struct thread_info *curctx; -@@ -174,6 +175,7 @@ - "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" - ); - } -+#endif - #else - static inline void handle_one_irq(unsigned int irq) - { -diff -Nur linux-4.4.28.orig/arch/sparc/Kconfig linux-4.4.28/arch/sparc/Kconfig ---- linux-4.4.28.orig/arch/sparc/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/sparc/Kconfig 2016-11-01 21:26:57.460257444 +0100 -@@ -189,12 +189,10 @@ - source kernel/Kconfig.hz - - config RWSEM_GENERIC_SPINLOCK -- bool -- default y if SPARC32 -+ def_bool PREEMPT_RT_FULL - - config RWSEM_XCHGADD_ALGORITHM -- bool -- default y if SPARC64 -+ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL - - config GENERIC_HWEIGHT - bool -diff -Nur linux-4.4.28.orig/arch/sparc/kernel/irq_64.c linux-4.4.28/arch/sparc/kernel/irq_64.c ---- linux-4.4.28.orig/arch/sparc/kernel/irq_64.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/sparc/kernel/irq_64.c 2016-11-01 21:26:57.488259255 +0100 -@@ -854,6 +854,7 @@ - set_irq_regs(old_regs); - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - void do_softirq_own_stack(void) - { - void *orig_sp, *sp = softirq_stack[smp_processor_id()]; -@@ -868,6 +869,7 @@ - __asm__ __volatile__("mov %0, %%sp" - : : "r" (orig_sp)); - } -+#endif - - #ifdef CONFIG_HOTPLUG_CPU - void fixup_irqs(void) -diff -Nur linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c ---- linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c 2016-11-01 21:26:57.524261570 +0100 -@@ -383,14 +383,14 @@ - err = blkcipher_walk_virt(desc, &walk); - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - -- kernel_fpu_begin(); - while ((nbytes = walk.nbytes)) { -+ kernel_fpu_begin(); - aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, -- nbytes & AES_BLOCK_MASK); -+ nbytes & AES_BLOCK_MASK); -+ kernel_fpu_end(); - nbytes &= AES_BLOCK_SIZE - 1; - err = blkcipher_walk_done(desc, &walk, nbytes); - } -- kernel_fpu_end(); - - return err; - } -@@ -407,14 +407,14 @@ - err = blkcipher_walk_virt(desc, &walk); - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - -- kernel_fpu_begin(); - while ((nbytes = walk.nbytes)) { -+ kernel_fpu_begin(); - aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK); -+ kernel_fpu_end(); - nbytes &= AES_BLOCK_SIZE - 1; - err = blkcipher_walk_done(desc, &walk, nbytes); - } -- kernel_fpu_end(); - - return err; - } -@@ -431,14 +431,14 @@ - err = blkcipher_walk_virt(desc, &walk); - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - -- kernel_fpu_begin(); - while ((nbytes = walk.nbytes)) { -+ kernel_fpu_begin(); - aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK, walk.iv); -+ kernel_fpu_end(); - nbytes &= AES_BLOCK_SIZE - 1; - err = blkcipher_walk_done(desc, &walk, nbytes); - } -- kernel_fpu_end(); - - return err; - } -@@ -455,14 +455,14 @@ - err = blkcipher_walk_virt(desc, &walk); - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - -- kernel_fpu_begin(); - while ((nbytes = walk.nbytes)) { -+ kernel_fpu_begin(); - aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK, walk.iv); -+ kernel_fpu_end(); - nbytes &= AES_BLOCK_SIZE - 1; - err = blkcipher_walk_done(desc, &walk, nbytes); - } -- kernel_fpu_end(); - - return err; - } -@@ -514,18 +514,20 @@ - err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - -- kernel_fpu_begin(); - while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { -+ kernel_fpu_begin(); - aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, - nbytes & AES_BLOCK_MASK, walk.iv); -+ kernel_fpu_end(); - nbytes &= AES_BLOCK_SIZE - 1; - err = blkcipher_walk_done(desc, &walk, nbytes); - } - if (walk.nbytes) { -+ kernel_fpu_begin(); - ctr_crypt_final(ctx, &walk); -+ kernel_fpu_end(); - err = blkcipher_walk_done(desc, &walk, 0); - } -- kernel_fpu_end(); - - return err; - } -diff -Nur linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c ---- linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c 2016-11-01 21:26:57.528261834 +0100 -@@ -59,7 +59,7 @@ - static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, - bool enc) - { -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); - const unsigned int bsize = CAST5_BLOCK_SIZE; - unsigned int nbytes; -@@ -75,7 +75,7 @@ - u8 *wsrc = walk->src.virt.addr; - u8 *wdst = walk->dst.virt.addr; - -- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); -+ fpu_enabled = cast5_fpu_begin(false, nbytes); - - /* Process multi-block batch */ - if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { -@@ -103,10 +103,9 @@ - } while (nbytes >= bsize); - - done: -+ cast5_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, walk, nbytes); - } -- -- cast5_fpu_end(fpu_enabled); - return err; - } - -@@ -227,7 +226,7 @@ - static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) - { -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct blkcipher_walk walk; - int err; - -@@ -236,12 +235,11 @@ - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - - while ((nbytes = walk.nbytes)) { -- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); -+ fpu_enabled = cast5_fpu_begin(false, nbytes); - nbytes = __cbc_decrypt(desc, &walk); -+ cast5_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, &walk, nbytes); - } -- -- cast5_fpu_end(fpu_enabled); - return err; - } - -@@ -311,7 +309,7 @@ - static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) - { -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct blkcipher_walk walk; - int err; - -@@ -320,13 +318,12 @@ - desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; - - while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { -- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); -+ fpu_enabled = cast5_fpu_begin(false, nbytes); - nbytes = __ctr_crypt(desc, &walk); -+ cast5_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, &walk, nbytes); - } - -- cast5_fpu_end(fpu_enabled); -- - if (walk.nbytes) { - ctr_crypt_final(desc, &walk); - err = blkcipher_walk_done(desc, &walk, 0); -diff -Nur linux-4.4.28.orig/arch/x86/crypto/glue_helper.c linux-4.4.28/arch/x86/crypto/glue_helper.c ---- linux-4.4.28.orig/arch/x86/crypto/glue_helper.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/crypto/glue_helper.c 2016-11-01 21:26:57.536262350 +0100 -@@ -39,7 +39,7 @@ - void *ctx = crypto_blkcipher_ctx(desc->tfm); - const unsigned int bsize = 128 / 8; - unsigned int nbytes, i, func_bytes; -- bool fpu_enabled = false; -+ bool fpu_enabled; - int err; - - err = blkcipher_walk_virt(desc, walk); -@@ -49,7 +49,7 @@ - u8 *wdst = walk->dst.virt.addr; - - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, -- desc, fpu_enabled, nbytes); -+ desc, false, nbytes); - - for (i = 0; i < gctx->num_funcs; i++) { - func_bytes = bsize * gctx->funcs[i].num_blocks; -@@ -71,10 +71,10 @@ - } - - done: -+ glue_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, walk, nbytes); - } - -- glue_fpu_end(fpu_enabled); - return err; - } - -@@ -194,7 +194,7 @@ - struct scatterlist *src, unsigned int nbytes) - { - const unsigned int bsize = 128 / 8; -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct blkcipher_walk walk; - int err; - -@@ -203,12 +203,12 @@ - - while ((nbytes = walk.nbytes)) { - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, -- desc, fpu_enabled, nbytes); -+ desc, false, nbytes); - nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk); -+ glue_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, &walk, nbytes); - } - -- glue_fpu_end(fpu_enabled); - return err; - } - EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit); -@@ -277,7 +277,7 @@ - struct scatterlist *src, unsigned int nbytes) - { - const unsigned int bsize = 128 / 8; -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct blkcipher_walk walk; - int err; - -@@ -286,13 +286,12 @@ - - while ((nbytes = walk.nbytes) >= bsize) { - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, -- desc, fpu_enabled, nbytes); -+ desc, false, nbytes); - nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk); -+ glue_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, &walk, nbytes); - } - -- glue_fpu_end(fpu_enabled); -- - if (walk.nbytes) { - glue_ctr_crypt_final_128bit( - gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk); -@@ -347,7 +346,7 @@ - void *tweak_ctx, void *crypt_ctx) - { - const unsigned int bsize = 128 / 8; -- bool fpu_enabled = false; -+ bool fpu_enabled; - struct blkcipher_walk walk; - int err; - -@@ -360,21 +359,21 @@ - - /* set minimum length to bsize, for tweak_fn */ - fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, -- desc, fpu_enabled, -+ desc, false, - nbytes < bsize ? bsize : nbytes); -- - /* calculate first value of T */ - tweak_fn(tweak_ctx, walk.iv, walk.iv); -+ glue_fpu_end(fpu_enabled); - - while (nbytes) { -+ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, -+ desc, false, nbytes); - nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk); - -+ glue_fpu_end(fpu_enabled); - err = blkcipher_walk_done(desc, &walk, nbytes); - nbytes = walk.nbytes; - } -- -- glue_fpu_end(fpu_enabled); -- - return err; - } - EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit); -diff -Nur linux-4.4.28.orig/arch/x86/entry/common.c linux-4.4.28/arch/x86/entry/common.c ---- linux-4.4.28.orig/arch/x86/entry/common.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/entry/common.c 2016-11-01 21:26:57.544262865 +0100 -@@ -220,7 +220,7 @@ - - #define EXIT_TO_USERMODE_LOOP_FLAGS \ - (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ -- _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY) -+ _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY) - - static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) - { -@@ -236,9 +236,16 @@ - /* We have work to do. */ - local_irq_enable(); - -- if (cached_flags & _TIF_NEED_RESCHED) -+ if (cached_flags & _TIF_NEED_RESCHED_MASK) - schedule(); - -+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND -+ if (unlikely(current->forced_info.si_signo)) { -+ struct task_struct *t = current; -+ force_sig_info(t->forced_info.si_signo, &t->forced_info, t); -+ t->forced_info.si_signo = 0; -+ } -+#endif - if (cached_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - -diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_32.S linux-4.4.28/arch/x86/entry/entry_32.S ---- linux-4.4.28.orig/arch/x86/entry/entry_32.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/entry/entry_32.S 2016-11-01 21:26:57.548263117 +0100 -@@ -278,8 +278,24 @@ - ENTRY(resume_kernel) - DISABLE_INTERRUPTS(CLBR_ANY) - need_resched: -+ # preempt count == 0 + NEED_RS set? - cmpl $0, PER_CPU_VAR(__preempt_count) -+#ifndef CONFIG_PREEMPT_LAZY - jnz restore_all -+#else -+ jz test_int_off -+ -+ # atleast preempt count == 0 ? -+ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) -+ jne restore_all -+ -+ cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? -+ jnz restore_all -+ -+ testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) -+ jz restore_all -+test_int_off: -+#endif - testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all - call preempt_schedule_irq -diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_64.S linux-4.4.28/arch/x86/entry/entry_64.S ---- linux-4.4.28.orig/arch/x86/entry/entry_64.S 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/entry/entry_64.S 2016-11-01 21:26:57.548263117 +0100 -@@ -579,7 +579,23 @@ - bt $9, EFLAGS(%rsp) /* were interrupts off? */ - jnc 1f - 0: cmpl $0, PER_CPU_VAR(__preempt_count) -+#ifndef CONFIG_PREEMPT_LAZY - jnz 1f -+#else -+ jz do_preempt_schedule_irq -+ -+ # atleast preempt count == 0 ? -+ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) -+ jnz 1f -+ -+ GET_THREAD_INFO(%rcx) -+ cmpl $0, TI_preempt_lazy_count(%rcx) -+ jnz 1f -+ -+ bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) -+ jnc 1f -+do_preempt_schedule_irq: -+#endif - call preempt_schedule_irq - jmp 0b - 1: -@@ -867,6 +883,7 @@ - jmp 2b - .previous - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* Call softirq on interrupt stack. Interrupts are off. */ - ENTRY(do_softirq_own_stack) - pushq %rbp -@@ -879,6 +896,7 @@ - decl PER_CPU_VAR(irq_count) - ret - END(do_softirq_own_stack) -+#endif - - #ifdef CONFIG_XEN - idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/preempt.h linux-4.4.28/arch/x86/include/asm/preempt.h ---- linux-4.4.28.orig/arch/x86/include/asm/preempt.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/preempt.h 2016-11-01 21:26:57.556263632 +0100 -@@ -79,17 +79,46 @@ - * a decrement which hits zero means we have no preempt_count and should - * reschedule. - */ --static __always_inline bool __preempt_count_dec_and_test(void) -+static __always_inline bool ____preempt_count_dec_and_test(void) - { - GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); - } - -+static __always_inline bool __preempt_count_dec_and_test(void) -+{ -+ if (____preempt_count_dec_and_test()) -+ return true; -+#ifdef CONFIG_PREEMPT_LAZY -+ if (current_thread_info()->preempt_lazy_count) -+ return false; -+ return test_thread_flag(TIF_NEED_RESCHED_LAZY); -+#else -+ return false; -+#endif -+} -+ - /* - * Returns true when we need to resched and can (barring IRQ state). - */ - static __always_inline bool should_resched(int preempt_offset) - { -+#ifdef CONFIG_PREEMPT_LAZY -+ u32 tmp; -+ -+ tmp = raw_cpu_read_4(__preempt_count); -+ if (tmp == preempt_offset) -+ return true; -+ -+ /* preempt count == 0 ? */ -+ tmp &= ~PREEMPT_NEED_RESCHED; -+ if (tmp) -+ return false; -+ if (current_thread_info()->preempt_lazy_count) -+ return false; -+ return test_thread_flag(TIF_NEED_RESCHED_LAZY); -+#else - return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); -+#endif - } - - #ifdef CONFIG_PREEMPT -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/signal.h linux-4.4.28/arch/x86/include/asm/signal.h ---- linux-4.4.28.orig/arch/x86/include/asm/signal.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/signal.h 2016-11-01 21:26:57.556263632 +0100 -@@ -23,6 +23,19 @@ - unsigned long sig[_NSIG_WORDS]; - } sigset_t; - -+/* -+ * Because some traps use the IST stack, we must keep preemption -+ * disabled while calling do_trap(), but do_trap() may call -+ * force_sig_info() which will grab the signal spin_locks for the -+ * task, which in PREEMPT_RT_FULL are mutexes. By defining -+ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set -+ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the -+ * trap. -+ */ -+#if defined(CONFIG_PREEMPT_RT_FULL) -+#define ARCH_RT_DELAYS_SIGNAL_SEND -+#endif -+ - #ifndef CONFIG_COMPAT - typedef sigset_t compat_sigset_t; - #endif -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h linux-4.4.28/arch/x86/include/asm/stackprotector.h ---- linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/stackprotector.h 2016-11-01 21:26:57.560263897 +0100 -@@ -59,7 +59,7 @@ - */ - static __always_inline void boot_init_stack_canary(void) - { -- u64 canary; -+ u64 uninitialized_var(canary); - u64 tsc; - - #ifdef CONFIG_X86_64 -@@ -70,8 +70,15 @@ - * of randomness. The TSC only matters for very early init, - * there it already has some randomness on most systems. Later - * on during the bootup the random pool has true entropy too. -+ * -+ * For preempt-rt we need to weaken the randomness a bit, as -+ * we can't call into the random generator from atomic context -+ * due to locking constraints. We just leave canary -+ * uninitialized and use the TSC based randomness on top of it. - */ -+#ifndef CONFIG_PREEMPT_RT_FULL - get_random_bytes(&canary, sizeof(canary)); -+#endif - tsc = rdtsc(); - canary += tsc + (tsc << 32UL); - -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/thread_info.h linux-4.4.28/arch/x86/include/asm/thread_info.h ---- linux-4.4.28.orig/arch/x86/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/thread_info.h 2016-11-01 21:26:57.560263897 +0100 -@@ -58,6 +58,8 @@ - __u32 status; /* thread synchronous flags */ - __u32 cpu; /* current CPU */ - mm_segment_t addr_limit; -+ int preempt_lazy_count; /* 0 => lazy preemptable -+ <0 => BUG */ - unsigned int sig_on_uaccess_error:1; - unsigned int uaccess_err:1; /* uaccess failed */ - }; -@@ -95,6 +97,7 @@ - #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ - #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ - #define TIF_SECCOMP 8 /* secure computing */ -+#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ - #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ - #define TIF_UPROBE 12 /* breakpointed or singlestepping */ - #define TIF_NOTSC 16 /* TSC is not accessible in userland */ -@@ -119,6 +122,7 @@ - #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) - #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) - #define _TIF_SECCOMP (1 << TIF_SECCOMP) -+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) - #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) - #define _TIF_UPROBE (1 << TIF_UPROBE) - #define _TIF_NOTSC (1 << TIF_NOTSC) -@@ -152,6 +156,8 @@ - #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) - #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) - -+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) -+ - #define STACK_WARN (THREAD_SIZE/8) - - /* -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h ---- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h 2016-11-01 21:26:57.568264412 +0100 -@@ -615,9 +615,9 @@ - cycles_t send_message; - cycles_t period_end; - cycles_t period_time; -- spinlock_t uvhub_lock; -- spinlock_t queue_lock; -- spinlock_t disable_lock; -+ raw_spinlock_t uvhub_lock; -+ raw_spinlock_t queue_lock; -+ raw_spinlock_t disable_lock; - /* tunables */ - int max_concurr; - int max_concurr_const; -@@ -776,15 +776,15 @@ - * to be lowered below the current 'v'. atomic_add_unless can only stop - * on equal. - */ --static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) -+static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u) - { -- spin_lock(lock); -+ raw_spin_lock(lock); - if (atomic_read(v) >= u) { -- spin_unlock(lock); -+ raw_spin_unlock(lock); - return 0; - } - atomic_inc(v); -- spin_unlock(lock); -+ raw_spin_unlock(lock); - return 1; - } - -diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h ---- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h 2016-11-01 21:26:57.568264412 +0100 -@@ -492,7 +492,7 @@ - unsigned short nr_online_cpus; - unsigned short pnode; - short memory_nid; -- spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ -+ raw_spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ - unsigned long nmi_count; /* obsolete, see uv_hub_nmi */ - }; - extern struct uv_blade_info *uv_blade_info; -diff -Nur linux-4.4.28.orig/arch/x86/Kconfig linux-4.4.28/arch/x86/Kconfig ---- linux-4.4.28.orig/arch/x86/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/Kconfig 2016-11-01 21:26:57.508260538 +0100 -@@ -17,6 +17,7 @@ - ### Arch settings - config X86 - def_bool y -+ select HAVE_PREEMPT_LAZY - select ACPI_LEGACY_TABLES_LOOKUP if ACPI - select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI - select ANON_INODES -@@ -212,8 +213,11 @@ - def_bool y - depends on ISA_DMA_API - -+config RWSEM_GENERIC_SPINLOCK -+ def_bool PREEMPT_RT_FULL -+ - config RWSEM_XCHGADD_ALGORITHM -- def_bool y -+ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL - - config GENERIC_CALIBRATE_DELAY - def_bool y -@@ -848,7 +852,7 @@ - config MAXSMP - bool "Enable Maximum number of SMP Processors and NUMA Nodes" - depends on X86_64 && SMP && DEBUG_KERNEL -- select CPUMASK_OFFSTACK -+ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL - ---help--- - Enable maximum number of CPUS and NUMA Nodes for this architecture. - If unsure, say N. -diff -Nur linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c linux-4.4.28/arch/x86/kernel/acpi/boot.c ---- linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/acpi/boot.c 2016-11-01 21:26:57.580265179 +0100 -@@ -87,7 +87,9 @@ - * ->ioapic_mutex - * ->ioapic_lock - */ -+#ifdef CONFIG_X86_IO_APIC - static DEFINE_MUTEX(acpi_ioapic_lock); -+#endif - - /* -------------------------------------------------------------------------- - Boot-time Configuration -diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c linux-4.4.28/arch/x86/kernel/apic/io_apic.c ---- linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/apic/io_apic.c 2016-11-01 21:26:57.600266475 +0100 -@@ -1711,7 +1711,8 @@ - static inline bool ioapic_irqd_mask(struct irq_data *data) - { - /* If we are moving the irq we need to mask it */ -- if (unlikely(irqd_is_setaffinity_pending(data))) { -+ if (unlikely(irqd_is_setaffinity_pending(data) && -+ !irqd_irq_inprogress(data))) { - mask_ioapic_irq(data); - return true; - } -diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c ---- linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c 2016-11-01 21:26:57.612267242 +0100 -@@ -947,7 +947,7 @@ - uv_blade_info[blade].pnode = pnode; - uv_blade_info[blade].nr_possible_cpus = 0; - uv_blade_info[blade].nr_online_cpus = 0; -- spin_lock_init(&uv_blade_info[blade].nmi_lock); -+ raw_spin_lock_init(&uv_blade_info[blade].nmi_lock); - min_pnode = min(pnode, min_pnode); - max_pnode = max(pnode, max_pnode); - blade++; -diff -Nur linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c linux-4.4.28/arch/x86/kernel/asm-offsets.c ---- linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/asm-offsets.c 2016-11-01 21:26:57.612267242 +0100 -@@ -32,6 +32,7 @@ - OFFSET(TI_flags, thread_info, flags); - OFFSET(TI_status, thread_info, status); - OFFSET(TI_addr_limit, thread_info, addr_limit); -+ OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); - - BLANK(); - OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); -@@ -89,4 +90,5 @@ - - BLANK(); - DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); -+ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); - } -diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c ---- linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c 2016-11-01 21:26:57.624268022 +0100 -@@ -41,6 +41,8 @@ - #include - #include - #include -+#include -+#include - - #include - #include -@@ -1236,7 +1238,7 @@ - static unsigned long check_interval = INITIAL_CHECK_INTERVAL; - - static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ --static DEFINE_PER_CPU(struct timer_list, mce_timer); -+static DEFINE_PER_CPU(struct hrtimer, mce_timer); - - static unsigned long mce_adjust_timer_default(unsigned long interval) - { -@@ -1245,32 +1247,18 @@ - - static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; - --static void __restart_timer(struct timer_list *t, unsigned long interval) -+static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval) - { -- unsigned long when = jiffies + interval; -- unsigned long flags; -- -- local_irq_save(flags); -- -- if (timer_pending(t)) { -- if (time_before(when, t->expires)) -- mod_timer_pinned(t, when); -- } else { -- t->expires = round_jiffies(when); -- add_timer_on(t, smp_processor_id()); -- } -- -- local_irq_restore(flags); -+ if (!interval) -+ return HRTIMER_NORESTART; -+ hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval))); -+ return HRTIMER_RESTART; - } - --static void mce_timer_fn(unsigned long data) -+static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) - { -- struct timer_list *t = this_cpu_ptr(&mce_timer); -- int cpu = smp_processor_id(); - unsigned long iv; - -- WARN_ON(cpu != data); -- - iv = __this_cpu_read(mce_next_interval); - - if (mce_available(this_cpu_ptr(&cpu_info))) { -@@ -1293,7 +1281,7 @@ - - done: - __this_cpu_write(mce_next_interval, iv); -- __restart_timer(t, iv); -+ return __restart_timer(timer, iv); - } - - /* -@@ -1301,7 +1289,7 @@ - */ - void mce_timer_kick(unsigned long interval) - { -- struct timer_list *t = this_cpu_ptr(&mce_timer); -+ struct hrtimer *t = this_cpu_ptr(&mce_timer); - unsigned long iv = __this_cpu_read(mce_next_interval); - - __restart_timer(t, interval); -@@ -1316,7 +1304,7 @@ - int cpu; - - for_each_online_cpu(cpu) -- del_timer_sync(&per_cpu(mce_timer, cpu)); -+ hrtimer_cancel(&per_cpu(mce_timer, cpu)); - } - - static void mce_do_trigger(struct work_struct *work) -@@ -1326,6 +1314,56 @@ - - static DECLARE_WORK(mce_trigger_work, mce_do_trigger); - -+static void __mce_notify_work(struct swork_event *event) -+{ -+ /* Not more than two messages every minute */ -+ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); -+ -+ /* wake processes polling /dev/mcelog */ -+ wake_up_interruptible(&mce_chrdev_wait); -+ -+ /* -+ * There is no risk of missing notifications because -+ * work_pending is always cleared before the function is -+ * executed. -+ */ -+ if (mce_helper[0] && !work_pending(&mce_trigger_work)) -+ schedule_work(&mce_trigger_work); -+ -+ if (__ratelimit(&ratelimit)) -+ pr_info(HW_ERR "Machine check events logged\n"); -+} -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+static bool notify_work_ready __read_mostly; -+static struct swork_event notify_work; -+ -+static int mce_notify_work_init(void) -+{ -+ int err; -+ -+ err = swork_get(); -+ if (err) -+ return err; -+ -+ INIT_SWORK(¬ify_work, __mce_notify_work); -+ notify_work_ready = true; -+ return 0; -+} -+ -+static void mce_notify_work(void) -+{ -+ if (notify_work_ready) -+ swork_queue(¬ify_work); -+} -+#else -+static void mce_notify_work(void) -+{ -+ __mce_notify_work(NULL); -+} -+static inline int mce_notify_work_init(void) { return 0; } -+#endif -+ - /* - * Notify the user(s) about new machine check events. - * Can be called from interrupt context, but not from machine check/NMI -@@ -1333,19 +1371,8 @@ - */ - int mce_notify_irq(void) - { -- /* Not more than two messages every minute */ -- static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); -- - if (test_and_clear_bit(0, &mce_need_notify)) { -- /* wake processes polling /dev/mcelog */ -- wake_up_interruptible(&mce_chrdev_wait); -- -- if (mce_helper[0]) -- schedule_work(&mce_trigger_work); -- -- if (__ratelimit(&ratelimit)) -- pr_info(HW_ERR "Machine check events logged\n"); -- -+ mce_notify_work(); - return 1; - } - return 0; -@@ -1639,7 +1666,7 @@ - } - } - --static void mce_start_timer(unsigned int cpu, struct timer_list *t) -+static void mce_start_timer(unsigned int cpu, struct hrtimer *t) - { - unsigned long iv = check_interval * HZ; - -@@ -1648,16 +1675,17 @@ - - per_cpu(mce_next_interval, cpu) = iv; - -- t->expires = round_jiffies(jiffies + iv); -- add_timer_on(t, cpu); -+ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), -+ 0, HRTIMER_MODE_REL_PINNED); - } - - static void __mcheck_cpu_init_timer(void) - { -- struct timer_list *t = this_cpu_ptr(&mce_timer); -+ struct hrtimer *t = this_cpu_ptr(&mce_timer); - unsigned int cpu = smp_processor_id(); - -- setup_timer(t, mce_timer_fn, cpu); -+ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); -+ t->function = mce_timer_fn; - mce_start_timer(cpu, t); - } - -@@ -2376,6 +2404,8 @@ - if (!mce_available(raw_cpu_ptr(&cpu_info))) - return; - -+ hrtimer_cancel(this_cpu_ptr(&mce_timer)); -+ - if (!(action & CPU_TASKS_FROZEN)) - cmci_clear(); - -@@ -2398,6 +2428,7 @@ - if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); - } -+ __mcheck_cpu_init_timer(); - } - - /* Get notified when a cpu comes on/off. Be hotplug friendly. */ -@@ -2405,7 +2436,6 @@ - mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) - { - unsigned int cpu = (unsigned long)hcpu; -- struct timer_list *t = &per_cpu(mce_timer, cpu); - - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: -@@ -2425,11 +2455,9 @@ - break; - case CPU_DOWN_PREPARE: - smp_call_function_single(cpu, mce_disable_cpu, &action, 1); -- del_timer_sync(t); - break; - case CPU_DOWN_FAILED: - smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); -- mce_start_timer(cpu, t); - break; - } - -@@ -2468,6 +2496,10 @@ - goto err_out; - } - -+ err = mce_notify_work_init(); -+ if (err) -+ goto err_out; -+ - if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { - err = -ENOMEM; - goto err_out; -diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c ---- linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-11-01 21:26:57.636268789 +0100 -@@ -117,7 +117,7 @@ - }; - - struct rapl_pmu { -- spinlock_t lock; -+ raw_spinlock_t lock; - int n_active; /* number of active events */ - struct list_head active_list; - struct pmu *pmu; /* pointer to rapl_pmu_class */ -@@ -220,13 +220,13 @@ - if (!pmu->n_active) - return HRTIMER_NORESTART; - -- spin_lock_irqsave(&pmu->lock, flags); -+ raw_spin_lock_irqsave(&pmu->lock, flags); - - list_for_each_entry(event, &pmu->active_list, active_entry) { - rapl_event_update(event); - } - -- spin_unlock_irqrestore(&pmu->lock, flags); -+ raw_spin_unlock_irqrestore(&pmu->lock, flags); - - hrtimer_forward_now(hrtimer, pmu->timer_interval); - -@@ -263,9 +263,9 @@ - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); - unsigned long flags; - -- spin_lock_irqsave(&pmu->lock, flags); -+ raw_spin_lock_irqsave(&pmu->lock, flags); - __rapl_pmu_event_start(pmu, event); -- spin_unlock_irqrestore(&pmu->lock, flags); -+ raw_spin_unlock_irqrestore(&pmu->lock, flags); - } - - static void rapl_pmu_event_stop(struct perf_event *event, int mode) -@@ -274,7 +274,7 @@ - struct hw_perf_event *hwc = &event->hw; - unsigned long flags; - -- spin_lock_irqsave(&pmu->lock, flags); -+ raw_spin_lock_irqsave(&pmu->lock, flags); - - /* mark event as deactivated and stopped */ - if (!(hwc->state & PERF_HES_STOPPED)) { -@@ -299,7 +299,7 @@ - hwc->state |= PERF_HES_UPTODATE; - } - -- spin_unlock_irqrestore(&pmu->lock, flags); -+ raw_spin_unlock_irqrestore(&pmu->lock, flags); - } - - static int rapl_pmu_event_add(struct perf_event *event, int mode) -@@ -308,14 +308,14 @@ - struct hw_perf_event *hwc = &event->hw; - unsigned long flags; - -- spin_lock_irqsave(&pmu->lock, flags); -+ raw_spin_lock_irqsave(&pmu->lock, flags); - - hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - - if (mode & PERF_EF_START) - __rapl_pmu_event_start(pmu, event); - -- spin_unlock_irqrestore(&pmu->lock, flags); -+ raw_spin_unlock_irqrestore(&pmu->lock, flags); - - return 0; - } -@@ -603,7 +603,7 @@ - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); - if (!pmu) - return -1; -- spin_lock_init(&pmu->lock); -+ raw_spin_lock_init(&pmu->lock); - - INIT_LIST_HEAD(&pmu->active_list); - -diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c linux-4.4.28/arch/x86/kernel/dumpstack_32.c ---- linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/dumpstack_32.c 2016-11-01 21:26:57.648269569 +0100 -@@ -42,7 +42,7 @@ - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) - { -- const unsigned cpu = get_cpu(); -+ const unsigned cpu = get_cpu_light(); - int graph = 0; - u32 *prev_esp; - -@@ -86,7 +86,7 @@ - break; - touch_nmi_watchdog(); - } -- put_cpu(); -+ put_cpu_light(); - } - EXPORT_SYMBOL(dump_trace); - -diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c linux-4.4.28/arch/x86/kernel/dumpstack_64.c ---- linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/dumpstack_64.c 2016-11-01 21:26:57.648269569 +0100 -@@ -152,7 +152,7 @@ - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) - { -- const unsigned cpu = get_cpu(); -+ const unsigned cpu = get_cpu_light(); - struct thread_info *tinfo; - unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); - unsigned long dummy; -@@ -241,7 +241,7 @@ - * This handles the process stack: - */ - bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); -- put_cpu(); -+ put_cpu_light(); - } - EXPORT_SYMBOL(dump_trace); - -@@ -255,7 +255,7 @@ - int cpu; - int i; - -- preempt_disable(); -+ migrate_disable(); - cpu = smp_processor_id(); - - irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); -@@ -291,7 +291,7 @@ - pr_cont(" %016lx", *stack++); - touch_nmi_watchdog(); - } -- preempt_enable(); -+ migrate_enable(); - - pr_cont("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); -diff -Nur linux-4.4.28.orig/arch/x86/kernel/irq_32.c linux-4.4.28/arch/x86/kernel/irq_32.c ---- linux-4.4.28.orig/arch/x86/kernel/irq_32.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/irq_32.c 2016-11-01 21:26:57.652269821 +0100 -@@ -128,6 +128,7 @@ - cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - void do_softirq_own_stack(void) - { - struct thread_info *curstk; -@@ -146,6 +147,7 @@ - - call_on_stack(__do_softirq, isp); - } -+#endif - - bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) - { -diff -Nur linux-4.4.28.orig/arch/x86/kernel/kvm.c linux-4.4.28/arch/x86/kernel/kvm.c ---- linux-4.4.28.orig/arch/x86/kernel/kvm.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/kvm.c 2016-11-01 21:26:57.652269821 +0100 -@@ -36,6 +36,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -91,14 +92,14 @@ - - struct kvm_task_sleep_node { - struct hlist_node link; -- wait_queue_head_t wq; -+ struct swait_queue_head wq; - u32 token; - int cpu; - bool halted; - }; - - static struct kvm_task_sleep_head { -- spinlock_t lock; -+ raw_spinlock_t lock; - struct hlist_head list; - } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; - -@@ -122,17 +123,17 @@ - u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); - struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; - struct kvm_task_sleep_node n, *e; -- DEFINE_WAIT(wait); -+ DECLARE_SWAITQUEUE(wait); - - rcu_irq_enter(); - -- spin_lock(&b->lock); -+ raw_spin_lock(&b->lock); - e = _find_apf_task(b, token); - if (e) { - /* dummy entry exist -> wake up was delivered ahead of PF */ - hlist_del(&e->link); - kfree(e); -- spin_unlock(&b->lock); -+ raw_spin_unlock(&b->lock); - - rcu_irq_exit(); - return; -@@ -141,13 +142,13 @@ - n.token = token; - n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || preempt_count() > 1; -- init_waitqueue_head(&n.wq); -+ init_swait_queue_head(&n.wq); - hlist_add_head(&n.link, &b->list); -- spin_unlock(&b->lock); -+ raw_spin_unlock(&b->lock); - - for (;;) { - if (!n.halted) -- prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); -+ prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); - if (hlist_unhashed(&n.link)) - break; - -@@ -166,7 +167,7 @@ - } - } - if (!n.halted) -- finish_wait(&n.wq, &wait); -+ finish_swait(&n.wq, &wait); - - rcu_irq_exit(); - return; -@@ -178,8 +179,8 @@ - hlist_del_init(&n->link); - if (n->halted) - smp_send_reschedule(n->cpu); -- else if (waitqueue_active(&n->wq)) -- wake_up(&n->wq); -+ else if (swait_active(&n->wq)) -+ swake_up(&n->wq); - } - - static void apf_task_wake_all(void) -@@ -189,14 +190,14 @@ - for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { - struct hlist_node *p, *next; - struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; -- spin_lock(&b->lock); -+ raw_spin_lock(&b->lock); - hlist_for_each_safe(p, next, &b->list) { - struct kvm_task_sleep_node *n = - hlist_entry(p, typeof(*n), link); - if (n->cpu == smp_processor_id()) - apf_task_wake_one(n); - } -- spin_unlock(&b->lock); -+ raw_spin_unlock(&b->lock); - } - } - -@@ -212,7 +213,7 @@ - } - - again: -- spin_lock(&b->lock); -+ raw_spin_lock(&b->lock); - n = _find_apf_task(b, token); - if (!n) { - /* -@@ -225,17 +226,17 @@ - * Allocation failed! Busy wait while other cpu - * handles async PF. - */ -- spin_unlock(&b->lock); -+ raw_spin_unlock(&b->lock); - cpu_relax(); - goto again; - } - n->token = token; - n->cpu = smp_processor_id(); -- init_waitqueue_head(&n->wq); -+ init_swait_queue_head(&n->wq); - hlist_add_head(&n->link, &b->list); - } else - apf_task_wake_one(n); -- spin_unlock(&b->lock); -+ raw_spin_unlock(&b->lock); - return; - } - EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); -@@ -486,7 +487,7 @@ - paravirt_ops_setup(); - register_reboot_notifier(&kvm_pv_reboot_nb); - for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) -- spin_lock_init(&async_pf_sleepers[i].lock); -+ raw_spin_lock_init(&async_pf_sleepers[i].lock); - if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) - x86_init.irqs.trap_init = kvm_apf_trap_init; - -diff -Nur linux-4.4.28.orig/arch/x86/kernel/nmi.c linux-4.4.28/arch/x86/kernel/nmi.c ---- linux-4.4.28.orig/arch/x86/kernel/nmi.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/nmi.c 2016-11-01 21:26:57.660270336 +0100 -@@ -231,7 +231,7 @@ - #endif - - if (panic_on_unrecovered_nmi) -- panic("NMI: Not continuing"); -+ nmi_panic(regs, "NMI: Not continuing"); - - pr_emerg("Dazed and confused, but trying to continue\n"); - -@@ -255,8 +255,16 @@ - reason, smp_processor_id()); - show_regs(regs); - -- if (panic_on_io_nmi) -- panic("NMI IOCK error: Not continuing"); -+ if (panic_on_io_nmi) { -+ nmi_panic(regs, "NMI IOCK error: Not continuing"); -+ -+ /* -+ * If we end up here, it means we have received an NMI while -+ * processing panic(). Simply return without delaying and -+ * re-enabling NMIs. -+ */ -+ return; -+ } - - /* Re-enable the IOCK line, wait for a few seconds */ - reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; -@@ -297,7 +305,7 @@ - - pr_emerg("Do you have a strange power saving mode enabled?\n"); - if (unknown_nmi_panic || panic_on_unrecovered_nmi) -- panic("NMI: Not continuing"); -+ nmi_panic(regs, "NMI: Not continuing"); - - pr_emerg("Dazed and confused, but trying to continue\n"); - } -diff -Nur linux-4.4.28.orig/arch/x86/kernel/process_32.c linux-4.4.28/arch/x86/kernel/process_32.c ---- linux-4.4.28.orig/arch/x86/kernel/process_32.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/process_32.c 2016-11-01 21:26:57.664270598 +0100 -@@ -35,6 +35,7 @@ - #include - #include - #include -+#include - - #include - #include -@@ -210,6 +211,35 @@ - } - EXPORT_SYMBOL_GPL(start_thread); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) -+{ -+ int i; -+ -+ /* -+ * Clear @prev's kmap_atomic mappings -+ */ -+ for (i = 0; i < prev_p->kmap_idx; i++) { -+ int idx = i + KM_TYPE_NR * smp_processor_id(); -+ pte_t *ptep = kmap_pte - idx; -+ -+ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); -+ } -+ /* -+ * Restore @next_p's kmap_atomic mappings -+ */ -+ for (i = 0; i < next_p->kmap_idx; i++) { -+ int idx = i + KM_TYPE_NR * smp_processor_id(); -+ -+ if (!pte_none(next_p->kmap_pte[i])) -+ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); -+ } -+} -+#else -+static inline void -+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } -+#endif -+ - - /* - * switch_to(x,y) should switch tasks from x to y. -@@ -286,6 +316,8 @@ - task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) - __switch_to_xtra(prev_p, next_p, tss); - -+ switch_kmaps(prev_p, next_p); -+ - /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so -diff -Nur linux-4.4.28.orig/arch/x86/kernel/reboot.c linux-4.4.28/arch/x86/kernel/reboot.c ---- linux-4.4.28.orig/arch/x86/kernel/reboot.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kernel/reboot.c 2016-11-01 21:26:57.664270598 +0100 -@@ -726,6 +726,7 @@ - static nmi_shootdown_cb shootdown_callback; - - static atomic_t waiting_for_crash_ipi; -+static int crash_ipi_issued; - - static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) - { -@@ -788,6 +789,9 @@ - - smp_send_nmi_allbutself(); - -+ /* Kick CPUs looping in NMI context. */ -+ WRITE_ONCE(crash_ipi_issued, 1); -+ - msecs = 1000; /* Wait at most a second for the other cpus to stop */ - while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { - mdelay(1); -@@ -796,6 +800,22 @@ - - /* Leave the nmi callback set */ - } -+ -+/* Override the weak function in kernel/panic.c */ -+void nmi_panic_self_stop(struct pt_regs *regs) -+{ -+ while (1) { -+ /* -+ * Wait for the crash dumping IPI to be issued, and then -+ * call its callback directly. -+ */ -+ if (READ_ONCE(crash_ipi_issued)) -+ crash_nmi_callback(0, regs); /* Don't return */ -+ -+ cpu_relax(); -+ } -+} -+ - #else /* !CONFIG_SMP */ - void nmi_shootdown_cpus(nmi_shootdown_cb callback) - { -diff -Nur linux-4.4.28.orig/arch/x86/kvm/lapic.c linux-4.4.28/arch/x86/kvm/lapic.c ---- linux-4.4.28.orig/arch/x86/kvm/lapic.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kvm/lapic.c 2016-11-01 21:26:57.672271115 +0100 -@@ -1195,7 +1195,7 @@ - static void apic_timer_expired(struct kvm_lapic *apic) - { - struct kvm_vcpu *vcpu = apic->vcpu; -- wait_queue_head_t *q = &vcpu->wq; -+ struct swait_queue_head *q = &vcpu->wq; - struct kvm_timer *ktimer = &apic->lapic_timer; - - if (atomic_read(&apic->lapic_timer.pending)) -@@ -1204,8 +1204,8 @@ - atomic_inc(&apic->lapic_timer.pending); - kvm_set_pending_timer(vcpu); - -- if (waitqueue_active(q)) -- wake_up_interruptible(q); -+ if (swait_active(q)) -+ swake_up(q); - - if (apic_lvtt_tscdeadline(apic)) - ktimer->expired_tscdeadline = ktimer->tscdeadline; -@@ -1801,6 +1801,7 @@ - hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - apic->lapic_timer.timer.function = apic_timer_fn; -+ apic->lapic_timer.timer.irqsafe = 1; - - /* - * APIC is created enabled. This will prevent kvm_lapic_set_base from -diff -Nur linux-4.4.28.orig/arch/x86/kvm/x86.c linux-4.4.28/arch/x86/kvm/x86.c ---- linux-4.4.28.orig/arch/x86/kvm/x86.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/kvm/x86.c 2016-11-01 21:26:57.732274981 +0100 -@@ -5792,6 +5792,13 @@ - goto out; - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { -+ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); -+ return -EOPNOTSUPP; -+ } -+#endif -+ - r = kvm_mmu_module_init(); - if (r) - goto out_free_percpu; -diff -Nur linux-4.4.28.orig/arch/x86/mm/highmem_32.c linux-4.4.28/arch/x86/mm/highmem_32.c ---- linux-4.4.28.orig/arch/x86/mm/highmem_32.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/mm/highmem_32.c 2016-11-01 21:26:57.740275502 +0100 -@@ -32,10 +32,11 @@ - */ - void *kmap_atomic_prot(struct page *page, pgprot_t prot) - { -+ pte_t pte = mk_pte(page, prot); - unsigned long vaddr; - int idx, type; - -- preempt_disable(); -+ preempt_disable_nort(); - pagefault_disable(); - - if (!PageHighMem(page)) -@@ -45,7 +46,10 @@ - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - BUG_ON(!pte_none(*(kmap_pte-idx))); -- set_pte(kmap_pte-idx, mk_pte(page, prot)); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = pte; -+#endif -+ set_pte(kmap_pte-idx, pte); - arch_flush_lazy_mmu_mode(); - - return (void *)vaddr; -@@ -88,6 +92,9 @@ - * is a bad idea also, in case the page changes cacheability - * attributes or becomes a protected page in a hypervisor. - */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = __pte(0); -+#endif - kpte_clear_flush(kmap_pte-idx, vaddr); - kmap_atomic_idx_pop(); - arch_flush_lazy_mmu_mode(); -@@ -100,7 +107,7 @@ - #endif - - pagefault_enable(); -- preempt_enable(); -+ preempt_enable_nort(); - } - EXPORT_SYMBOL(__kunmap_atomic); - -diff -Nur linux-4.4.28.orig/arch/x86/mm/iomap_32.c linux-4.4.28/arch/x86/mm/iomap_32.c ---- linux-4.4.28.orig/arch/x86/mm/iomap_32.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/mm/iomap_32.c 2016-11-01 21:26:57.740275502 +0100 -@@ -56,6 +56,7 @@ - - void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) - { -+ pte_t pte = pfn_pte(pfn, prot); - unsigned long vaddr; - int idx, type; - -@@ -65,7 +66,12 @@ - type = kmap_atomic_idx_push(); - idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); -- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); -+ WARN_ON(!pte_none(*(kmap_pte - idx))); -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = pte; -+#endif -+ set_pte(kmap_pte - idx, pte); - arch_flush_lazy_mmu_mode(); - - return (void *)vaddr; -@@ -113,6 +119,9 @@ - * is a bad idea also, in case the page changes cacheability - * attributes or becomes a protected page in a hypervisor. - */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ current->kmap_pte[type] = __pte(0); -+#endif - kpte_clear_flush(kmap_pte-idx, vaddr); - kmap_atomic_idx_pop(); - } -diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c linux-4.4.28/arch/x86/platform/uv/tlb_uv.c ---- linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/platform/uv/tlb_uv.c 2016-11-01 21:26:57.768277302 +0100 -@@ -714,9 +714,9 @@ - - quiesce_local_uvhub(hmaster); - -- spin_lock(&hmaster->queue_lock); -+ raw_spin_lock(&hmaster->queue_lock); - reset_with_ipi(&bau_desc->distribution, bcp); -- spin_unlock(&hmaster->queue_lock); -+ raw_spin_unlock(&hmaster->queue_lock); - - end_uvhub_quiesce(hmaster); - -@@ -736,9 +736,9 @@ - - quiesce_local_uvhub(hmaster); - -- spin_lock(&hmaster->queue_lock); -+ raw_spin_lock(&hmaster->queue_lock); - reset_with_ipi(&bau_desc->distribution, bcp); -- spin_unlock(&hmaster->queue_lock); -+ raw_spin_unlock(&hmaster->queue_lock); - - end_uvhub_quiesce(hmaster); - -@@ -759,7 +759,7 @@ - cycles_t tm1; - - hmaster = bcp->uvhub_master; -- spin_lock(&hmaster->disable_lock); -+ raw_spin_lock(&hmaster->disable_lock); - if (!bcp->baudisabled) { - stat->s_bau_disabled++; - tm1 = get_cycles(); -@@ -772,7 +772,7 @@ - } - } - } -- spin_unlock(&hmaster->disable_lock); -+ raw_spin_unlock(&hmaster->disable_lock); - } - - static void count_max_concurr(int stat, struct bau_control *bcp, -@@ -835,7 +835,7 @@ - */ - static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat) - { -- spinlock_t *lock = &hmaster->uvhub_lock; -+ raw_spinlock_t *lock = &hmaster->uvhub_lock; - atomic_t *v; - - v = &hmaster->active_descriptor_count; -@@ -968,7 +968,7 @@ - struct bau_control *hmaster; - - hmaster = bcp->uvhub_master; -- spin_lock(&hmaster->disable_lock); -+ raw_spin_lock(&hmaster->disable_lock); - if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { - stat->s_bau_reenabled++; - for_each_present_cpu(tcpu) { -@@ -980,10 +980,10 @@ - tbcp->period_giveups = 0; - } - } -- spin_unlock(&hmaster->disable_lock); -+ raw_spin_unlock(&hmaster->disable_lock); - return 0; - } -- spin_unlock(&hmaster->disable_lock); -+ raw_spin_unlock(&hmaster->disable_lock); - return -1; - } - -@@ -1901,9 +1901,9 @@ - bcp->cong_reps = congested_reps; - bcp->disabled_period = sec_2_cycles(disabled_period); - bcp->giveup_limit = giveup_limit; -- spin_lock_init(&bcp->queue_lock); -- spin_lock_init(&bcp->uvhub_lock); -- spin_lock_init(&bcp->disable_lock); -+ raw_spin_lock_init(&bcp->queue_lock); -+ raw_spin_lock_init(&bcp->uvhub_lock); -+ raw_spin_lock_init(&bcp->disable_lock); - } - } - -diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c linux-4.4.28/arch/x86/platform/uv/uv_time.c ---- linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/arch/x86/platform/uv/uv_time.c 2016-11-01 21:26:57.768277302 +0100 -@@ -57,7 +57,7 @@ - - /* There is one of these allocated per node */ - struct uv_rtc_timer_head { -- spinlock_t lock; -+ raw_spinlock_t lock; - /* next cpu waiting for timer, local node relative: */ - int next_cpu; - /* number of cpus on this node: */ -@@ -177,7 +177,7 @@ - uv_rtc_deallocate_timers(); - return -ENOMEM; - } -- spin_lock_init(&head->lock); -+ raw_spin_lock_init(&head->lock); - head->ncpus = uv_blade_nr_possible_cpus(bid); - head->next_cpu = -1; - blade_info[bid] = head; -@@ -231,7 +231,7 @@ - unsigned long flags; - int next_cpu; - -- spin_lock_irqsave(&head->lock, flags); -+ raw_spin_lock_irqsave(&head->lock, flags); - - next_cpu = head->next_cpu; - *t = expires; -@@ -243,12 +243,12 @@ - if (uv_setup_intr(cpu, expires)) { - *t = ULLONG_MAX; - uv_rtc_find_next_timer(head, pnode); -- spin_unlock_irqrestore(&head->lock, flags); -+ raw_spin_unlock_irqrestore(&head->lock, flags); - return -ETIME; - } - } - -- spin_unlock_irqrestore(&head->lock, flags); -+ raw_spin_unlock_irqrestore(&head->lock, flags); - return 0; - } - -@@ -267,7 +267,7 @@ - unsigned long flags; - int rc = 0; - -- spin_lock_irqsave(&head->lock, flags); -+ raw_spin_lock_irqsave(&head->lock, flags); - - if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) - rc = 1; -@@ -279,7 +279,7 @@ - uv_rtc_find_next_timer(head, pnode); - } - -- spin_unlock_irqrestore(&head->lock, flags); -+ raw_spin_unlock_irqrestore(&head->lock, flags); - - return rc; - } -@@ -299,13 +299,18 @@ - static cycle_t uv_read_rtc(struct clocksource *cs) - { - unsigned long offset; -+ cycle_t cycles; - -+ preempt_disable(); - if (uv_get_min_hub_revision_id() == 1) - offset = 0; - else - offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE; - -- return (cycle_t)uv_read_local_mmr(UVH_RTC | offset); -+ cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset); -+ preempt_enable(); -+ -+ return cycles; - } - - /* -diff -Nur linux-4.4.28.orig/block/blk-core.c linux-4.4.28/block/blk-core.c ---- linux-4.4.28.orig/block/blk-core.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-core.c 2016-11-01 21:26:57.788278596 +0100 -@@ -125,6 +125,9 @@ - - INIT_LIST_HEAD(&rq->queuelist); - INIT_LIST_HEAD(&rq->timeout_list); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); -+#endif - rq->cpu = -1; - rq->q = q; - rq->__sector = (sector_t) -1; -@@ -233,7 +236,7 @@ - **/ - void blk_start_queue(struct request_queue *q) - { -- WARN_ON(!irqs_disabled()); -+ WARN_ON_NONRT(!irqs_disabled()); - - queue_flag_clear(QUEUE_FLAG_STOPPED, q); - __blk_run_queue(q); -@@ -659,7 +662,7 @@ - if (!gfpflags_allow_blocking(gfp)) - return -EBUSY; - -- ret = wait_event_interruptible(q->mq_freeze_wq, -+ ret = swait_event_interruptible(q->mq_freeze_wq, - !atomic_read(&q->mq_freeze_depth) || - blk_queue_dying(q)); - if (blk_queue_dying(q)) -@@ -679,7 +682,7 @@ - struct request_queue *q = - container_of(ref, struct request_queue, q_usage_counter); - -- wake_up_all(&q->mq_freeze_wq); -+ swake_up_all(&q->mq_freeze_wq); - } - - struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) -@@ -741,7 +744,7 @@ - q->bypass_depth = 1; - __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags); - -- init_waitqueue_head(&q->mq_freeze_wq); -+ init_swait_queue_head(&q->mq_freeze_wq); - - /* - * Init percpu_ref in atomic mode so that it's faster to shutdown. -@@ -3200,7 +3203,7 @@ - blk_run_queue_async(q); - else - __blk_run_queue(q); -- spin_unlock(q->queue_lock); -+ spin_unlock_irq(q->queue_lock); - } - - static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) -@@ -3248,7 +3251,6 @@ - void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) - { - struct request_queue *q; -- unsigned long flags; - struct request *rq; - LIST_HEAD(list); - unsigned int depth; -@@ -3268,11 +3270,6 @@ - q = NULL; - depth = 0; - -- /* -- * Save and disable interrupts here, to avoid doing it for every -- * queue lock we have to take. -- */ -- local_irq_save(flags); - while (!list_empty(&list)) { - rq = list_entry_rq(list.next); - list_del_init(&rq->queuelist); -@@ -3285,7 +3282,7 @@ - queue_unplugged(q, depth, from_schedule); - q = rq->q; - depth = 0; -- spin_lock(q->queue_lock); -+ spin_lock_irq(q->queue_lock); - } - - /* -@@ -3312,8 +3309,6 @@ - */ - if (q) - queue_unplugged(q, depth, from_schedule); -- -- local_irq_restore(flags); - } - - void blk_finish_plug(struct blk_plug *plug) -diff -Nur linux-4.4.28.orig/block/blk-ioc.c linux-4.4.28/block/blk-ioc.c ---- linux-4.4.28.orig/block/blk-ioc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-ioc.c 2016-11-01 21:26:57.800279369 +0100 -@@ -7,6 +7,7 @@ - #include - #include - #include -+#include - - #include "blk.h" - -@@ -109,7 +110,7 @@ - spin_unlock(q->queue_lock); - } else { - spin_unlock_irqrestore(&ioc->lock, flags); -- cpu_relax(); -+ cpu_chill(); - spin_lock_irqsave_nested(&ioc->lock, flags, 1); - } - } -@@ -187,7 +188,7 @@ - spin_unlock(icq->q->queue_lock); - } else { - spin_unlock_irqrestore(&ioc->lock, flags); -- cpu_relax(); -+ cpu_chill(); - goto retry; - } - } -diff -Nur linux-4.4.28.orig/block/blk-iopoll.c linux-4.4.28/block/blk-iopoll.c ---- linux-4.4.28.orig/block/blk-iopoll.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-iopoll.c 2016-11-01 21:26:57.800279369 +0100 -@@ -35,6 +35,7 @@ - list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); - __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - EXPORT_SYMBOL(blk_iopoll_sched); - -@@ -132,6 +133,7 @@ - __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); - - local_irq_enable(); -+ preempt_check_resched_rt(); - } - - /** -@@ -201,6 +203,7 @@ - this_cpu_ptr(&blk_cpu_iopoll)); - __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); - local_irq_enable(); -+ preempt_check_resched_rt(); - } - - return NOTIFY_OK; -diff -Nur linux-4.4.28.orig/block/blk-mq.c linux-4.4.28/block/blk-mq.c ---- linux-4.4.28.orig/block/blk-mq.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-mq.c 2016-11-01 21:26:57.812280143 +0100 -@@ -92,7 +92,7 @@ - - static void blk_mq_freeze_queue_wait(struct request_queue *q) - { -- wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); -+ swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); - } - - /* -@@ -130,7 +130,7 @@ - WARN_ON_ONCE(freeze_depth < 0); - if (!freeze_depth) { - percpu_ref_reinit(&q->q_usage_counter); -- wake_up_all(&q->mq_freeze_wq); -+ swake_up_all(&q->mq_freeze_wq); - } - } - EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); -@@ -149,7 +149,7 @@ - * dying, we need to ensure that processes currently waiting on - * the queue are notified as well. - */ -- wake_up_all(&q->mq_freeze_wq); -+ swake_up_all(&q->mq_freeze_wq); - } - - bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) -@@ -196,6 +196,9 @@ - rq->resid_len = 0; - rq->sense = NULL; - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); -+#endif - INIT_LIST_HEAD(&rq->timeout_list); - rq->timeout = 0; - -@@ -325,6 +328,17 @@ - } - EXPORT_SYMBOL(blk_mq_end_request); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ -+void __blk_mq_complete_request_remote_work(struct work_struct *work) -+{ -+ struct request *rq = container_of(work, struct request, work); -+ -+ rq->q->softirq_done_fn(rq); -+} -+ -+#else -+ - static void __blk_mq_complete_request_remote(void *data) - { - struct request *rq = data; -@@ -332,6 +346,8 @@ - rq->q->softirq_done_fn(rq); - } - -+#endif -+ - static void blk_mq_ipi_complete_request(struct request *rq) - { - struct blk_mq_ctx *ctx = rq->mq_ctx; -@@ -343,19 +359,23 @@ - return; - } - -- cpu = get_cpu(); -+ cpu = get_cpu_light(); - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) - shared = cpus_share_cache(cpu, ctx->cpu); - - if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ schedule_work_on(ctx->cpu, &rq->work); -+#else - rq->csd.func = __blk_mq_complete_request_remote; - rq->csd.info = rq; - rq->csd.flags = 0; - smp_call_function_single_async(ctx->cpu, &rq->csd); -+#endif - } else { - rq->q->softirq_done_fn(rq); - } -- put_cpu(); -+ put_cpu_light(); - } - - static void __blk_mq_complete_request(struct request *rq) -@@ -864,14 +884,14 @@ - return; - - if (!async) { -- int cpu = get_cpu(); -+ int cpu = get_cpu_light(); - if (cpumask_test_cpu(cpu, hctx->cpumask)) { - __blk_mq_run_hw_queue(hctx); -- put_cpu(); -+ put_cpu_light(); - return; - } - -- put_cpu(); -+ put_cpu_light(); - } - - kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), -@@ -1619,7 +1639,7 @@ - { - struct blk_mq_hw_ctx *hctx = data; - -- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) -+ if (action == CPU_POST_DEAD) - return blk_mq_hctx_cpu_offline(hctx, cpu); - - /* -diff -Nur linux-4.4.28.orig/block/blk-mq-cpu.c linux-4.4.28/block/blk-mq-cpu.c ---- linux-4.4.28.orig/block/blk-mq-cpu.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-mq-cpu.c 2016-11-01 21:26:57.800279369 +0100 -@@ -16,7 +16,7 @@ - #include "blk-mq.h" - - static LIST_HEAD(blk_mq_cpu_notify_list); --static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock); -+static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock); - - static int blk_mq_main_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -@@ -25,7 +25,10 @@ - struct blk_mq_cpu_notifier *notify; - int ret = NOTIFY_OK; - -- raw_spin_lock(&blk_mq_cpu_notify_lock); -+ if (action != CPU_POST_DEAD) -+ return NOTIFY_OK; -+ -+ spin_lock(&blk_mq_cpu_notify_lock); - - list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) { - ret = notify->notify(notify->data, action, cpu); -@@ -33,7 +36,7 @@ - break; - } - -- raw_spin_unlock(&blk_mq_cpu_notify_lock); -+ spin_unlock(&blk_mq_cpu_notify_lock); - return ret; - } - -@@ -41,16 +44,16 @@ - { - BUG_ON(!notifier->notify); - -- raw_spin_lock(&blk_mq_cpu_notify_lock); -+ spin_lock(&blk_mq_cpu_notify_lock); - list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list); -- raw_spin_unlock(&blk_mq_cpu_notify_lock); -+ spin_unlock(&blk_mq_cpu_notify_lock); - } - - void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier) - { -- raw_spin_lock(&blk_mq_cpu_notify_lock); -+ spin_lock(&blk_mq_cpu_notify_lock); - list_del(¬ifier->list); -- raw_spin_unlock(&blk_mq_cpu_notify_lock); -+ spin_unlock(&blk_mq_cpu_notify_lock); - } - - void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, -diff -Nur linux-4.4.28.orig/block/blk-mq.h linux-4.4.28/block/blk-mq.h ---- linux-4.4.28.orig/block/blk-mq.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-mq.h 2016-11-01 21:26:57.812280143 +0100 -@@ -74,7 +74,10 @@ - static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, - unsigned int cpu) - { -- return per_cpu_ptr(q->queue_ctx, cpu); -+ struct blk_mq_ctx *ctx; -+ -+ ctx = per_cpu_ptr(q->queue_ctx, cpu); -+ return ctx; - } - - /* -@@ -85,12 +88,12 @@ - */ - static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) - { -- return __blk_mq_get_ctx(q, get_cpu()); -+ return __blk_mq_get_ctx(q, get_cpu_light()); - } - - static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) - { -- put_cpu(); -+ put_cpu_light(); - } - - struct blk_mq_alloc_data { -diff -Nur linux-4.4.28.orig/block/blk-softirq.c linux-4.4.28/block/blk-softirq.c ---- linux-4.4.28.orig/block/blk-softirq.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/blk-softirq.c 2016-11-01 21:26:57.812280143 +0100 -@@ -51,6 +51,7 @@ - raise_softirq_irqoff(BLOCK_SOFTIRQ); - - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - - /* -@@ -93,6 +94,7 @@ - this_cpu_ptr(&blk_cpu_done)); - raise_softirq_irqoff(BLOCK_SOFTIRQ); - local_irq_enable(); -+ preempt_check_resched_rt(); - } - - return NOTIFY_OK; -@@ -150,6 +152,7 @@ - goto do_local; - - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - - /** -diff -Nur linux-4.4.28.orig/block/bounce.c linux-4.4.28/block/bounce.c ---- linux-4.4.28.orig/block/bounce.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/block/bounce.c 2016-11-01 21:26:57.812280143 +0100 -@@ -55,11 +55,11 @@ - unsigned long flags; - unsigned char *vto; - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - vto = kmap_atomic(to->bv_page); - memcpy(vto + to->bv_offset, vfrom, to->bv_len); - kunmap_atomic(vto); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - - #else /* CONFIG_HIGHMEM */ -diff -Nur linux-4.4.28.orig/crypto/algapi.c linux-4.4.28/crypto/algapi.c ---- linux-4.4.28.orig/crypto/algapi.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/crypto/algapi.c 2016-11-01 21:26:57.824280917 +0100 -@@ -719,13 +719,13 @@ - - int crypto_register_notifier(struct notifier_block *nb) - { -- return blocking_notifier_chain_register(&crypto_chain, nb); -+ return srcu_notifier_chain_register(&crypto_chain, nb); - } - EXPORT_SYMBOL_GPL(crypto_register_notifier); - - int crypto_unregister_notifier(struct notifier_block *nb) - { -- return blocking_notifier_chain_unregister(&crypto_chain, nb); -+ return srcu_notifier_chain_unregister(&crypto_chain, nb); - } - EXPORT_SYMBOL_GPL(crypto_unregister_notifier); - -diff -Nur linux-4.4.28.orig/crypto/api.c linux-4.4.28/crypto/api.c ---- linux-4.4.28.orig/crypto/api.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/crypto/api.c 2016-11-01 21:26:57.828281169 +0100 -@@ -31,7 +31,7 @@ - DECLARE_RWSEM(crypto_alg_sem); - EXPORT_SYMBOL_GPL(crypto_alg_sem); - --BLOCKING_NOTIFIER_HEAD(crypto_chain); -+SRCU_NOTIFIER_HEAD(crypto_chain); - EXPORT_SYMBOL_GPL(crypto_chain); - - static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); -@@ -236,10 +236,10 @@ - { - int ok; - -- ok = blocking_notifier_call_chain(&crypto_chain, val, v); -+ ok = srcu_notifier_call_chain(&crypto_chain, val, v); - if (ok == NOTIFY_DONE) { - request_module("cryptomgr"); -- ok = blocking_notifier_call_chain(&crypto_chain, val, v); -+ ok = srcu_notifier_call_chain(&crypto_chain, val, v); - } - - return ok; -diff -Nur linux-4.4.28.orig/crypto/internal.h linux-4.4.28/crypto/internal.h ---- linux-4.4.28.orig/crypto/internal.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/crypto/internal.h 2016-11-01 21:26:57.832281426 +0100 -@@ -47,7 +47,7 @@ - - extern struct list_head crypto_alg_list; - extern struct rw_semaphore crypto_alg_sem; --extern struct blocking_notifier_head crypto_chain; -+extern struct srcu_notifier_head crypto_chain; - - #ifdef CONFIG_PROC_FS - void __init crypto_init_proc(void); -@@ -143,7 +143,7 @@ - - static inline void crypto_notify(unsigned long val, void *v) - { -- blocking_notifier_call_chain(&crypto_chain, val, v); -+ srcu_notifier_call_chain(&crypto_chain, val, v); - } - - #endif /* _CRYPTO_INTERNAL_H */ -diff -Nur linux-4.4.28.orig/Documentation/hwlat_detector.txt linux-4.4.28/Documentation/hwlat_detector.txt ---- linux-4.4.28.orig/Documentation/hwlat_detector.txt 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/Documentation/hwlat_detector.txt 2016-11-01 21:26:56.600202005 +0100 -@@ -0,0 +1,64 @@ -+Introduction: -+------------- -+ -+The module hwlat_detector is a special purpose kernel module that is used to -+detect large system latencies induced by the behavior of certain underlying -+hardware or firmware, independent of Linux itself. The code was developed -+originally to detect SMIs (System Management Interrupts) on x86 systems, -+however there is nothing x86 specific about this patchset. It was -+originally written for use by the "RT" patch since the Real Time -+kernel is highly latency sensitive. -+ -+SMIs are usually not serviced by the Linux kernel, which typically does not -+even know that they are occuring. SMIs are instead are set up by BIOS code -+and are serviced by BIOS code, usually for "critical" events such as -+management of thermal sensors and fans. Sometimes though, SMIs are used for -+other tasks and those tasks can spend an inordinate amount of time in the -+handler (sometimes measured in milliseconds). Obviously this is a problem if -+you are trying to keep event service latencies down in the microsecond range. -+ -+The hardware latency detector works by hogging all of the cpus for configurable -+amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter -+for some period, then looking for gaps in the TSC data. Any gap indicates a -+time when the polling was interrupted and since the machine is stopped and -+interrupts turned off the only thing that could do that would be an SMI. -+ -+Note that the SMI detector should *NEVER* be used in a production environment. -+It is intended to be run manually to determine if the hardware platform has a -+problem with long system firmware service routines. -+ -+Usage: -+------ -+ -+Loading the module hwlat_detector passing the parameter "enabled=1" (or by -+setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only -+step required to start the hwlat_detector. It is possible to redefine the -+threshold in microseconds (us) above which latency spikes will be taken -+into account (parameter "threshold="). -+ -+Example: -+ -+ # modprobe hwlat_detector enabled=1 threshold=100 -+ -+After the module is loaded, it creates a directory named "hwlat_detector" under -+the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary -+to have debugfs mounted, which might be on /sys/debug on your system. -+ -+The /debug/hwlat_detector interface contains the following files: -+ -+count - number of latency spikes observed since last reset -+enable - a global enable/disable toggle (0/1), resets count -+max - maximum hardware latency actually observed (usecs) -+sample - a pipe from which to read current raw sample data -+ in the format -+ (can be opened O_NONBLOCK for a single sample) -+threshold - minimum latency value to be considered (usecs) -+width - time period to sample with CPUs held (usecs) -+ must be less than the total window size (enforced) -+window - total period of sampling, width being inside (usecs) -+ -+By default we will set width to 500,000 and window to 1,000,000, meaning that -+we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we -+observe any latencies that exceed the threshold (initially 100 usecs), -+then we write to a global sample ring buffer of 8K samples, which is -+consumed by reading from the "sample" (pipe) debugfs file interface. -diff -Nur linux-4.4.28.orig/Documentation/kernel-parameters.txt linux-4.4.28/Documentation/kernel-parameters.txt ---- linux-4.4.28.orig/Documentation/kernel-parameters.txt 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/Documentation/kernel-parameters.txt 2016-11-01 21:26:56.640204584 +0100 -@@ -1636,6 +1636,15 @@ - ip= [IP_PNP] - See Documentation/filesystems/nfs/nfsroot.txt. - -+ irqaffinity= [SMP] Set the default irq affinity mask -+ Format: -+ ,..., -+ or -+ - -+ (must be a positive range in ascending order) -+ or a mixture -+ ,...,- -+ - irqfixup [HW] - When an interrupt is not handled search all handlers - for it. Intended to get systems with badly broken -diff -Nur linux-4.4.28.orig/Documentation/sysrq.txt linux-4.4.28/Documentation/sysrq.txt ---- linux-4.4.28.orig/Documentation/sysrq.txt 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/Documentation/sysrq.txt 2016-11-01 21:26:56.652205360 +0100 -@@ -59,10 +59,17 @@ - On other - If you know of the key combos for other architectures, please - let me know so I can add them to this section. - --On all - write a character to /proc/sysrq-trigger. e.g.: -- -+On all - write a character to /proc/sysrq-trigger, e.g.: - echo t > /proc/sysrq-trigger - -+On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g. -+ echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq -+ Send an ICMP echo request with this pattern plus the particular -+ SysRq command key. Example: -+ # ping -c1 -s57 -p0102030468 -+ will trigger the SysRq-H (help) command. -+ -+ - * What are the 'command' keys? - ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - 'b' - Will immediately reboot the system without syncing or unmounting -diff -Nur linux-4.4.28.orig/Documentation/trace/histograms.txt linux-4.4.28/Documentation/trace/histograms.txt ---- linux-4.4.28.orig/Documentation/trace/histograms.txt 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/Documentation/trace/histograms.txt 2016-11-01 21:26:56.672206655 +0100 -@@ -0,0 +1,186 @@ -+ Using the Linux Kernel Latency Histograms -+ -+ -+This document gives a short explanation how to enable, configure and use -+latency histograms. Latency histograms are primarily relevant in the -+context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) -+and are used in the quality management of the Linux real-time -+capabilities. -+ -+ -+* Purpose of latency histograms -+ -+A latency histogram continuously accumulates the frequencies of latency -+data. There are two types of histograms -+- potential sources of latencies -+- effective latencies -+ -+ -+* Potential sources of latencies -+ -+Potential sources of latencies are code segments where interrupts, -+preemption or both are disabled (aka critical sections). To create -+histograms of potential sources of latency, the kernel stores the time -+stamp at the start of a critical section, determines the time elapsed -+when the end of the section is reached, and increments the frequency -+counter of that latency value - irrespective of whether any concurrently -+running process is affected by latency or not. -+- Configuration items (in the Kernel hacking/Tracers submenu) -+ CONFIG_INTERRUPT_OFF_LATENCY -+ CONFIG_PREEMPT_OFF_LATENCY -+ -+ -+* Effective latencies -+ -+Effective latencies are actually occuring during wakeup of a process. To -+determine effective latencies, the kernel stores the time stamp when a -+process is scheduled to be woken up, and determines the duration of the -+wakeup time shortly before control is passed over to this process. Note -+that the apparent latency in user space may be somewhat longer, since the -+process may be interrupted after control is passed over to it but before -+the execution in user space takes place. Simply measuring the interval -+between enqueuing and wakeup may also not appropriate in cases when a -+process is scheduled as a result of a timer expiration. The timer may have -+missed its deadline, e.g. due to disabled interrupts, but this latency -+would not be registered. Therefore, the offsets of missed timers are -+recorded in a separate histogram. If both wakeup latency and missed timer -+offsets are configured and enabled, a third histogram may be enabled that -+records the overall latency as a sum of the timer latency, if any, and the -+wakeup latency. This histogram is called "timerandwakeup". -+- Configuration items (in the Kernel hacking/Tracers submenu) -+ CONFIG_WAKEUP_LATENCY -+ CONFIG_MISSED_TIMER_OFSETS -+ -+ -+* Usage -+ -+The interface to the administration of the latency histograms is located -+in the debugfs file system. To mount it, either enter -+ -+mount -t sysfs nodev /sys -+mount -t debugfs nodev /sys/kernel/debug -+ -+from shell command line level, or add -+ -+nodev /sys sysfs defaults 0 0 -+nodev /sys/kernel/debug debugfs defaults 0 0 -+ -+to the file /etc/fstab. All latency histogram related files are then -+available in the directory /sys/kernel/debug/tracing/latency_hist. A -+particular histogram type is enabled by writing non-zero to the related -+variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. -+Select "preemptirqsoff" for the histograms of potential sources of -+latencies and "wakeup" for histograms of effective latencies etc. The -+histogram data - one per CPU - are available in the files -+ -+/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx -+/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx -+/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx -+/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx -+/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx -+/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx -+/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx -+ -+The histograms are reset by writing non-zero to the file "reset" in a -+particular latency directory. To reset all latency data, use -+ -+#!/bin/sh -+ -+TRACINGDIR=/sys/kernel/debug/tracing -+HISTDIR=$TRACINGDIR/latency_hist -+ -+if test -d $HISTDIR -+then -+ cd $HISTDIR -+ for i in `find . | grep /reset$` -+ do -+ echo 1 >$i -+ done -+fi -+ -+ -+* Data format -+ -+Latency data are stored with a resolution of one microsecond. The -+maximum latency is 10,240 microseconds. The data are only valid, if the -+overflow register is empty. Every output line contains the latency in -+microseconds in the first row and the number of samples in the second -+row. To display only lines with a positive latency count, use, for -+example, -+ -+grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 -+ -+#Minimum latency: 0 microseconds. -+#Average latency: 0 microseconds. -+#Maximum latency: 25 microseconds. -+#Total samples: 3104770694 -+#There are 0 samples greater or equal than 10240 microseconds -+#usecs samples -+ 0 2984486876 -+ 1 49843506 -+ 2 58219047 -+ 3 5348126 -+ 4 2187960 -+ 5 3388262 -+ 6 959289 -+ 7 208294 -+ 8 40420 -+ 9 4485 -+ 10 14918 -+ 11 18340 -+ 12 25052 -+ 13 19455 -+ 14 5602 -+ 15 969 -+ 16 47 -+ 17 18 -+ 18 14 -+ 19 1 -+ 20 3 -+ 21 2 -+ 22 5 -+ 23 2 -+ 25 1 -+ -+ -+* Wakeup latency of a selected process -+ -+To only collect wakeup latency data of a particular process, write the -+PID of the requested process to -+ -+/sys/kernel/debug/tracing/latency_hist/wakeup/pid -+ -+PIDs are not considered, if this variable is set to 0. -+ -+ -+* Details of the process with the highest wakeup latency so far -+ -+Selected data of the process that suffered from the highest wakeup -+latency that occurred in a particular CPU are available in the file -+ -+/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. -+ -+In addition, other relevant system data at the time when the -+latency occurred are given. -+ -+The format of the data is (all in one line): -+ () \ -+<- -+ -+The value of is only relevant in the combined timer -+and wakeup latency recording. In the wakeup recording, it is -+always 0, in the missed_timer_offsets recording, it is the same -+as . -+ -+When retrospectively searching for the origin of a latency and -+tracing was not enabled, it may be helpful to know the name and -+some basic data of the task that (finally) was switching to the -+late real-tlme task. In addition to the victim's data, also the -+data of the possible culprit are therefore displayed after the -+"<-" symbol. -+ -+Finally, the timestamp of the time when the latency occurred -+in . after the most recent system boot -+is provided. -+ -+These data are also reset when the wakeup histogram is reset. -diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h linux-4.4.28/drivers/acpi/acpica/acglobal.h ---- linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/acpi/acpica/acglobal.h 2016-11-01 21:26:57.844282199 +0100 -@@ -116,7 +116,7 @@ - * interrupt level - */ - ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */ --ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ -+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ - ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock); - - /* Mutex for _OSI support */ -diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c linux-4.4.28/drivers/acpi/acpica/hwregs.c ---- linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/acpi/acpica/hwregs.c 2016-11-01 21:26:57.852282717 +0100 -@@ -269,14 +269,14 @@ - ACPI_BITMASK_ALL_FIXED_STATUS, - ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address))); - -- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); -+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); - - /* Clear the fixed events in PM1 A/B */ - - status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS, - ACPI_BITMASK_ALL_FIXED_STATUS); - -- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); -+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); - - if (ACPI_FAILURE(status)) { - goto exit; -diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c linux-4.4.28/drivers/acpi/acpica/hwxface.c ---- linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/acpi/acpica/hwxface.c 2016-11-01 21:26:57.852282717 +0100 -@@ -374,7 +374,7 @@ - return_ACPI_STATUS(AE_BAD_PARAMETER); - } - -- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); -+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); - - /* - * At this point, we know that the parent register is one of the -@@ -435,7 +435,7 @@ - - unlock_and_exit: - -- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); -+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); - return_ACPI_STATUS(status); - } - -diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c linux-4.4.28/drivers/acpi/acpica/utmutex.c ---- linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/acpi/acpica/utmutex.c 2016-11-01 21:26:57.864283490 +0100 -@@ -88,7 +88,7 @@ - return_ACPI_STATUS (status); - } - -- status = acpi_os_create_lock (&acpi_gbl_hardware_lock); -+ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock); - if (ACPI_FAILURE (status)) { - return_ACPI_STATUS (status); - } -@@ -156,7 +156,7 @@ - /* Delete the spinlocks */ - - acpi_os_delete_lock(acpi_gbl_gpe_lock); -- acpi_os_delete_lock(acpi_gbl_hardware_lock); -+ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock); - acpi_os_delete_lock(acpi_gbl_reference_count_lock); - - /* Delete the reader/writer lock */ -diff -Nur linux-4.4.28.orig/drivers/ata/libata-sff.c linux-4.4.28/drivers/ata/libata-sff.c ---- linux-4.4.28.orig/drivers/ata/libata-sff.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ata/libata-sff.c 2016-11-01 21:26:57.884284784 +0100 -@@ -678,9 +678,9 @@ - unsigned long flags; - unsigned int consumed; - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - consumed = ata_sff_data_xfer32(dev, buf, buflen, rw); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - return consumed; - } -@@ -719,7 +719,7 @@ - unsigned long flags; - - /* FIXME: use a bounce buffer */ -- local_irq_save(flags); -+ local_irq_save_nort(flags); - buf = kmap_atomic(page); - - /* do the actual data transfer */ -@@ -727,7 +727,7 @@ - do_write); - - kunmap_atomic(buf); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } else { - buf = page_address(page); - ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size, -@@ -864,7 +864,7 @@ - unsigned long flags; - - /* FIXME: use bounce buffer */ -- local_irq_save(flags); -+ local_irq_save_nort(flags); - buf = kmap_atomic(page); - - /* do the actual data transfer */ -@@ -872,7 +872,7 @@ - count, rw); - - kunmap_atomic(buf); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } else { - buf = page_address(page); - consumed = ap->ops->sff_data_xfer(dev, buf + offset, -diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.c linux-4.4.28/drivers/block/zram/zram_drv.c ---- linux-4.4.28.orig/drivers/block/zram/zram_drv.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/block/zram/zram_drv.c 2016-11-01 21:26:57.892285294 +0100 -@@ -520,6 +520,8 @@ - goto out_error; - } - -+ zram_meta_init_table_locks(meta, disksize); -+ - return meta; - - out_error: -@@ -568,12 +570,12 @@ - unsigned long handle; - size_t size; - -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - handle = meta->table[index].handle; - size = zram_get_obj_size(meta, index); - - if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - clear_page(mem); - return 0; - } -@@ -584,7 +586,7 @@ - else - ret = zcomp_decompress(zram->comp, cmem, size, mem); - zs_unmap_object(meta->mem_pool, handle); -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - - /* Should NEVER happen. Return bio error if it does. */ - if (unlikely(ret)) { -@@ -604,14 +606,14 @@ - struct zram_meta *meta = zram->meta; - page = bvec->bv_page; - -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - if (unlikely(!meta->table[index].handle) || - zram_test_flag(meta, index, ZRAM_ZERO)) { -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - handle_zero_page(bvec); - return 0; - } -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - - if (is_partial_io(bvec)) - /* Use a temporary buffer to decompress the page */ -@@ -689,10 +691,10 @@ - if (user_mem) - kunmap_atomic(user_mem); - /* Free memory associated with this sector now. */ -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - zram_free_page(zram, index); - zram_set_flag(meta, index, ZRAM_ZERO); -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - - atomic64_inc(&zram->stats.zero_pages); - ret = 0; -@@ -752,12 +754,12 @@ - * Free memory associated with this sector - * before overwriting unused sectors. - */ -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - zram_free_page(zram, index); - - meta->table[index].handle = handle; - zram_set_obj_size(meta, index, clen); -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - - /* Update stats */ - atomic64_add(clen, &zram->stats.compr_data_size); -@@ -800,9 +802,9 @@ - } - - while (n >= PAGE_SIZE) { -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - zram_free_page(zram, index); -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - atomic64_inc(&zram->stats.notify_free); - index++; - n -= PAGE_SIZE; -@@ -928,9 +930,9 @@ - zram = bdev->bd_disk->private_data; - meta = zram->meta; - -- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_lock_table(&meta->table[index]); - zram_free_page(zram, index); -- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); -+ zram_unlock_table(&meta->table[index]); - atomic64_inc(&zram->stats.notify_free); - } - -diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.h linux-4.4.28/drivers/block/zram/zram_drv.h ---- linux-4.4.28.orig/drivers/block/zram/zram_drv.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/block/zram/zram_drv.h 2016-11-01 21:26:57.892285294 +0100 -@@ -72,6 +72,9 @@ - struct zram_table_entry { - unsigned long handle; - unsigned long value; -+#ifdef CONFIG_PREEMPT_RT_BASE -+ spinlock_t lock; -+#endif - }; - - struct zram_stats { -@@ -119,4 +122,42 @@ - */ - bool claim; /* Protected by bdev->bd_mutex */ - }; -+ -+#ifndef CONFIG_PREEMPT_RT_BASE -+static inline void zram_lock_table(struct zram_table_entry *table) -+{ -+ bit_spin_lock(ZRAM_ACCESS, &table->value); -+} -+ -+static inline void zram_unlock_table(struct zram_table_entry *table) -+{ -+ bit_spin_unlock(ZRAM_ACCESS, &table->value); -+} -+ -+static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) { } -+#else /* CONFIG_PREEMPT_RT_BASE */ -+static inline void zram_lock_table(struct zram_table_entry *table) -+{ -+ spin_lock(&table->lock); -+ __set_bit(ZRAM_ACCESS, &table->value); -+} -+ -+static inline void zram_unlock_table(struct zram_table_entry *table) -+{ -+ __clear_bit(ZRAM_ACCESS, &table->value); -+ spin_unlock(&table->lock); -+} -+ -+static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) -+{ -+ size_t num_pages = disksize >> PAGE_SHIFT; -+ size_t index; -+ -+ for (index = 0; index < num_pages; index++) { -+ spinlock_t *lock = &meta->table[index].lock; -+ spin_lock_init(lock); -+ } -+} -+#endif /* CONFIG_PREEMPT_RT_BASE */ -+ - #endif -diff -Nur linux-4.4.28.orig/drivers/char/random.c linux-4.4.28/drivers/char/random.c ---- linux-4.4.28.orig/drivers/char/random.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/char/random.c 2016-11-01 21:26:57.900285811 +0100 -@@ -799,8 +799,6 @@ - } sample; - long delta, delta2, delta3; - -- preempt_disable(); -- - sample.jiffies = jiffies; - sample.cycles = random_get_entropy(); - sample.num = num; -@@ -841,7 +839,6 @@ - */ - credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); - } -- preempt_enable(); - } - - void add_input_randomness(unsigned int type, unsigned int code, -@@ -894,28 +891,27 @@ - return *(ptr + f->reg_idx++); - } - --void add_interrupt_randomness(int irq, int irq_flags) -+void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) - { - struct entropy_store *r; - struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); -- struct pt_regs *regs = get_irq_regs(); - unsigned long now = jiffies; - cycles_t cycles = random_get_entropy(); - __u32 c_high, j_high; -- __u64 ip; - unsigned long seed; - int credit = 0; - - if (cycles == 0) -- cycles = get_reg(fast_pool, regs); -+ cycles = get_reg(fast_pool, NULL); - c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; - j_high = (sizeof(now) > 4) ? now >> 32 : 0; - fast_pool->pool[0] ^= cycles ^ j_high ^ irq; - fast_pool->pool[1] ^= now ^ c_high; -- ip = regs ? instruction_pointer(regs) : _RET_IP_; -+ if (!ip) -+ ip = _RET_IP_; - fast_pool->pool[2] ^= ip; - fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : -- get_reg(fast_pool, regs); -+ get_reg(fast_pool, NULL); - - fast_mix(fast_pool); - add_interrupt_bench(cycles); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-generated.c linux-4.4.28/drivers/clk/at91/clk-generated.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-generated.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-generated.c 2016-11-01 21:26:57.916286841 +0100 -@@ -15,8 +15,8 @@ - #include - #include - #include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -28,8 +28,9 @@ - - struct clk_generated { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - struct clk_range range; -+ spinlock_t *lock; - u32 id; - u32 gckdiv; - u8 parent_id; -@@ -41,49 +42,52 @@ - static int clk_generated_enable(struct clk_hw *hw) - { - struct clk_generated *gck = to_clk_generated(hw); -- struct at91_pmc *pmc = gck->pmc; -- u32 tmp; -+ unsigned long flags; - - pr_debug("GCLK: %s, gckdiv = %d, parent id = %d\n", - __func__, gck->gckdiv, gck->parent_id); - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR) & -- ~(AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK); -- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_GCKCSS(gck->parent_id) -- | AT91_PMC_PCR_CMD -- | AT91_PMC_PCR_GCKDIV(gck->gckdiv) -- | AT91_PMC_PCR_GCKEN); -- pmc_unlock(pmc); -+ spin_lock_irqsave(gck->lock, flags); -+ regmap_write(gck->regmap, AT91_PMC_PCR, -+ (gck->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_update_bits(gck->regmap, AT91_PMC_PCR, -+ AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK | -+ AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN, -+ AT91_PMC_PCR_GCKCSS(gck->parent_id) | -+ AT91_PMC_PCR_CMD | -+ AT91_PMC_PCR_GCKDIV(gck->gckdiv) | -+ AT91_PMC_PCR_GCKEN); -+ spin_unlock_irqrestore(gck->lock, flags); - return 0; - } - - static void clk_generated_disable(struct clk_hw *hw) - { - struct clk_generated *gck = to_clk_generated(hw); -- struct at91_pmc *pmc = gck->pmc; -- u32 tmp; -+ unsigned long flags; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_GCKEN; -- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD); -- pmc_unlock(pmc); -+ spin_lock_irqsave(gck->lock, flags); -+ regmap_write(gck->regmap, AT91_PMC_PCR, -+ (gck->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_update_bits(gck->regmap, AT91_PMC_PCR, -+ AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN, -+ AT91_PMC_PCR_CMD); -+ spin_unlock_irqrestore(gck->lock, flags); - } - - static int clk_generated_is_enabled(struct clk_hw *hw) - { - struct clk_generated *gck = to_clk_generated(hw); -- struct at91_pmc *pmc = gck->pmc; -- int ret; -+ unsigned long flags; -+ unsigned int status; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); -- ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_GCKEN); -- pmc_unlock(pmc); -+ spin_lock_irqsave(gck->lock, flags); -+ regmap_write(gck->regmap, AT91_PMC_PCR, -+ (gck->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_read(gck->regmap, AT91_PMC_PCR, &status); -+ spin_unlock_irqrestore(gck->lock, flags); - -- return ret; -+ return status & AT91_PMC_PCR_GCKEN ? 1 : 0; - } - - static unsigned long -@@ -214,13 +218,14 @@ - */ - static void clk_generated_startup(struct clk_generated *gck) - { -- struct at91_pmc *pmc = gck->pmc; - u32 tmp; -+ unsigned long flags; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR); -- pmc_unlock(pmc); -+ spin_lock_irqsave(gck->lock, flags); -+ regmap_write(gck->regmap, AT91_PMC_PCR, -+ (gck->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_read(gck->regmap, AT91_PMC_PCR, &tmp); -+ spin_unlock_irqrestore(gck->lock, flags); - - gck->parent_id = (tmp & AT91_PMC_PCR_GCKCSS_MASK) - >> AT91_PMC_PCR_GCKCSS_OFFSET; -@@ -229,8 +234,8 @@ - } - - static struct clk * __init --at91_clk_register_generated(struct at91_pmc *pmc, const char *name, -- const char **parent_names, u8 num_parents, -+at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock, const char -+ *name, const char **parent_names, u8 num_parents, - u8 id, const struct clk_range *range) - { - struct clk_generated *gck; -@@ -249,7 +254,8 @@ - - gck->id = id; - gck->hw.init = &init; -- gck->pmc = pmc; -+ gck->regmap = regmap; -+ gck->lock = lock; - gck->range = *range; - - clk = clk_register(NULL, &gck->hw); -@@ -261,8 +267,7 @@ - return clk; - } - --void __init of_sama5d2_clk_generated_setup(struct device_node *np, -- struct at91_pmc *pmc) -+void __init of_sama5d2_clk_generated_setup(struct device_node *np) - { - int num; - u32 id; -@@ -272,6 +277,7 @@ - const char *parent_names[GENERATED_SOURCE_MAX]; - struct device_node *gcknp; - struct clk_range range = CLK_RANGE(0, 0); -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > GENERATED_SOURCE_MAX) -@@ -283,6 +289,10 @@ - if (!num || num > PERIPHERAL_MAX) - return; - -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ - for_each_child_of_node(np, gcknp) { - if (of_property_read_u32(gcknp, "reg", &id)) - continue; -@@ -296,11 +306,14 @@ - of_at91_get_clk_range(gcknp, "atmel,clk-output-range", - &range); - -- clk = at91_clk_register_generated(pmc, name, parent_names, -- num_parents, id, &range); -+ clk = at91_clk_register_generated(regmap, &pmc_pcr_lock, name, -+ parent_names, num_parents, -+ id, &range); - if (IS_ERR(clk)) - continue; - - of_clk_add_provider(gcknp, of_clk_src_simple_get, clk); - } - } -+CLK_OF_DECLARE(of_sama5d2_clk_generated_setup, "atmel,sama5d2-clk-generated", -+ of_sama5d2_clk_generated_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c linux-4.4.28/drivers/clk/at91/clk-h32mx.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-h32mx.c 2016-11-01 21:26:57.916286841 +0100 -@@ -15,15 +15,9 @@ - #include - #include - #include --#include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -31,7 +25,7 @@ - - struct clk_sama5d4_h32mx { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - #define to_clk_sama5d4_h32mx(hw) container_of(hw, struct clk_sama5d4_h32mx, hw) -@@ -40,8 +34,10 @@ - unsigned long parent_rate) - { - struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw); -+ unsigned int mckr; - -- if (pmc_read(h32mxclk->pmc, AT91_PMC_MCKR) & AT91_PMC_H32MXDIV) -+ regmap_read(h32mxclk->regmap, AT91_PMC_MCKR, &mckr); -+ if (mckr & AT91_PMC_H32MXDIV) - return parent_rate / 2; - - if (parent_rate > H32MX_MAX_FREQ) -@@ -70,18 +66,16 @@ - unsigned long parent_rate) - { - struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw); -- struct at91_pmc *pmc = h32mxclk->pmc; -- u32 tmp; -+ u32 mckr = 0; - - if (parent_rate != rate && (parent_rate / 2) != rate) - return -EINVAL; - -- pmc_lock(pmc); -- tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_H32MXDIV; - if ((parent_rate / 2) == rate) -- tmp |= AT91_PMC_H32MXDIV; -- pmc_write(pmc, AT91_PMC_MCKR, tmp); -- pmc_unlock(pmc); -+ mckr = AT91_PMC_H32MXDIV; -+ -+ regmap_update_bits(h32mxclk->regmap, AT91_PMC_MCKR, -+ AT91_PMC_H32MXDIV, mckr); - - return 0; - } -@@ -92,14 +86,18 @@ - .set_rate = clk_sama5d4_h32mx_set_rate, - }; - --void __init of_sama5d4_clk_h32mx_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_sama5d4_clk_h32mx_setup(struct device_node *np) - { - struct clk_sama5d4_h32mx *h32mxclk; - struct clk_init_data init; - const char *parent_name; -+ struct regmap *regmap; - struct clk *clk; - -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ - h32mxclk = kzalloc(sizeof(*h32mxclk), GFP_KERNEL); - if (!h32mxclk) - return; -@@ -113,7 +111,7 @@ - init.flags = CLK_SET_RATE_GATE; - - h32mxclk->hw.init = &init; -- h32mxclk->pmc = pmc; -+ h32mxclk->regmap = regmap; - - clk = clk_register(NULL, &h32mxclk->hw); - if (IS_ERR(clk)) { -@@ -123,3 +121,5 @@ - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(of_sama5d4_clk_h32mx_setup, "atmel,sama5d4-clk-h32mx", -+ of_sama5d4_clk_h32mx_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-main.c linux-4.4.28/drivers/clk/at91/clk-main.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-main.c 2016-11-01 21:26:57.920287105 +0100 -@@ -13,13 +13,8 @@ - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -34,18 +29,14 @@ - - struct clk_main_osc { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - }; - - #define to_clk_main_osc(hw) container_of(hw, struct clk_main_osc, hw) - - struct clk_main_rc_osc { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - unsigned long frequency; - unsigned long accuracy; - }; -@@ -54,51 +45,47 @@ - - struct clk_rm9200_main { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - #define to_clk_rm9200_main(hw) container_of(hw, struct clk_rm9200_main, hw) - - struct clk_sam9x5_main { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - u8 parent; - }; - - #define to_clk_sam9x5_main(hw) container_of(hw, struct clk_sam9x5_main, hw) - --static irqreturn_t clk_main_osc_irq_handler(int irq, void *dev_id) -+static inline bool clk_main_osc_ready(struct regmap *regmap) - { -- struct clk_main_osc *osc = dev_id; -+ unsigned int status; - -- wake_up(&osc->wait); -- disable_irq_nosync(osc->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & AT91_PMC_MOSCS; - } - - static int clk_main_osc_prepare(struct clk_hw *hw) - { - struct clk_main_osc *osc = to_clk_main_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -+ struct regmap *regmap = osc->regmap; - u32 tmp; - -- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; -+ regmap_read(regmap, AT91_CKGR_MOR, &tmp); -+ tmp &= ~MOR_KEY_MASK; -+ - if (tmp & AT91_PMC_OSCBYPASS) - return 0; - - if (!(tmp & AT91_PMC_MOSCEN)) { - tmp |= AT91_PMC_MOSCEN | AT91_PMC_KEY; -- pmc_write(pmc, AT91_CKGR_MOR, tmp); -+ regmap_write(regmap, AT91_CKGR_MOR, tmp); - } - -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS)) { -- enable_irq(osc->irq); -- wait_event(osc->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS); -- } -+ while (!clk_main_osc_ready(regmap)) -+ cpu_relax(); - - return 0; - } -@@ -106,9 +93,10 @@ - static void clk_main_osc_unprepare(struct clk_hw *hw) - { - struct clk_main_osc *osc = to_clk_main_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); -+ struct regmap *regmap = osc->regmap; -+ u32 tmp; - -+ regmap_read(regmap, AT91_CKGR_MOR, &tmp); - if (tmp & AT91_PMC_OSCBYPASS) - return; - -@@ -116,20 +104,22 @@ - return; - - tmp &= ~(AT91_PMC_KEY | AT91_PMC_MOSCEN); -- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); -+ regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); - } - - static int clk_main_osc_is_prepared(struct clk_hw *hw) - { - struct clk_main_osc *osc = to_clk_main_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); -+ struct regmap *regmap = osc->regmap; -+ u32 tmp, status; - -+ regmap_read(regmap, AT91_CKGR_MOR, &tmp); - if (tmp & AT91_PMC_OSCBYPASS) - return 1; - -- return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS) && -- (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN)); -+ regmap_read(regmap, AT91_PMC_SR, &status); -+ -+ return (status & AT91_PMC_MOSCS) && (tmp & AT91_PMC_MOSCEN); - } - - static const struct clk_ops main_osc_ops = { -@@ -139,18 +129,16 @@ - }; - - static struct clk * __init --at91_clk_register_main_osc(struct at91_pmc *pmc, -- unsigned int irq, -+at91_clk_register_main_osc(struct regmap *regmap, - const char *name, - const char *parent_name, - bool bypass) - { -- int ret; - struct clk_main_osc *osc; - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !irq || !name || !parent_name) -+ if (!name || !parent_name) - return ERR_PTR(-EINVAL); - - osc = kzalloc(sizeof(*osc), GFP_KERNEL); -@@ -164,85 +152,70 @@ - init.flags = CLK_IGNORE_UNUSED; - - osc->hw.init = &init; -- osc->pmc = pmc; -- osc->irq = irq; -- -- init_waitqueue_head(&osc->wait); -- irq_set_status_flags(osc->irq, IRQ_NOAUTOEN); -- ret = request_irq(osc->irq, clk_main_osc_irq_handler, -- IRQF_TRIGGER_HIGH, name, osc); -- if (ret) { -- kfree(osc); -- return ERR_PTR(ret); -- } -+ osc->regmap = regmap; - - if (bypass) -- pmc_write(pmc, AT91_CKGR_MOR, -- (pmc_read(pmc, AT91_CKGR_MOR) & -- ~(MOR_KEY_MASK | AT91_PMC_MOSCEN)) | -- AT91_PMC_OSCBYPASS | AT91_PMC_KEY); -+ regmap_update_bits(regmap, -+ AT91_CKGR_MOR, MOR_KEY_MASK | -+ AT91_PMC_MOSCEN, -+ AT91_PMC_OSCBYPASS | AT91_PMC_KEY); - - clk = clk_register(NULL, &osc->hw); -- if (IS_ERR(clk)) { -- free_irq(irq, osc); -+ if (IS_ERR(clk)) - kfree(osc); -- } - - return clk; - } - --void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np) - { - struct clk *clk; -- unsigned int irq; - const char *name = np->name; - const char *parent_name; -+ struct regmap *regmap; - bool bypass; - - of_property_read_string(np, "clock-output-names", &name); - bypass = of_property_read_bool(np, "atmel,osc-bypass"); - parent_name = of_clk_get_parent_name(np, 0); - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) - return; - -- clk = at91_clk_register_main_osc(pmc, irq, name, parent_name, bypass); -+ clk = at91_clk_register_main_osc(regmap, name, parent_name, bypass); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91rm9200_clk_main_osc, "atmel,at91rm9200-clk-main-osc", -+ of_at91rm9200_clk_main_osc_setup); - --static irqreturn_t clk_main_rc_osc_irq_handler(int irq, void *dev_id) -+static bool clk_main_rc_osc_ready(struct regmap *regmap) - { -- struct clk_main_rc_osc *osc = dev_id; -+ unsigned int status; - -- wake_up(&osc->wait); -- disable_irq_nosync(osc->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & AT91_PMC_MOSCRCS; - } - - static int clk_main_rc_osc_prepare(struct clk_hw *hw) - { - struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -- u32 tmp; -+ struct regmap *regmap = osc->regmap; -+ unsigned int mor; - -- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; -+ regmap_read(regmap, AT91_CKGR_MOR, &mor); - -- if (!(tmp & AT91_PMC_MOSCRCEN)) { -- tmp |= AT91_PMC_MOSCRCEN | AT91_PMC_KEY; -- pmc_write(pmc, AT91_CKGR_MOR, tmp); -- } -+ if (!(mor & AT91_PMC_MOSCRCEN)) -+ regmap_update_bits(regmap, AT91_CKGR_MOR, -+ MOR_KEY_MASK | AT91_PMC_MOSCRCEN, -+ AT91_PMC_MOSCRCEN | AT91_PMC_KEY); - -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS)) { -- enable_irq(osc->irq); -- wait_event(osc->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS); -- } -+ while (!clk_main_rc_osc_ready(regmap)) -+ cpu_relax(); - - return 0; - } -@@ -250,23 +223,28 @@ - static void clk_main_rc_osc_unprepare(struct clk_hw *hw) - { - struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); -+ struct regmap *regmap = osc->regmap; -+ unsigned int mor; - -- if (!(tmp & AT91_PMC_MOSCRCEN)) -+ regmap_read(regmap, AT91_CKGR_MOR, &mor); -+ -+ if (!(mor & AT91_PMC_MOSCRCEN)) - return; - -- tmp &= ~(MOR_KEY_MASK | AT91_PMC_MOSCRCEN); -- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); -+ regmap_update_bits(regmap, AT91_CKGR_MOR, -+ MOR_KEY_MASK | AT91_PMC_MOSCRCEN, AT91_PMC_KEY); - } - - static int clk_main_rc_osc_is_prepared(struct clk_hw *hw) - { - struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); -- struct at91_pmc *pmc = osc->pmc; -+ struct regmap *regmap = osc->regmap; -+ unsigned int mor, status; -+ -+ regmap_read(regmap, AT91_CKGR_MOR, &mor); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS) && -- (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCRCEN)); -+ return (mor & AT91_PMC_MOSCRCEN) && (status & AT91_PMC_MOSCRCS); - } - - static unsigned long clk_main_rc_osc_recalc_rate(struct clk_hw *hw, -@@ -294,17 +272,15 @@ - }; - - static struct clk * __init --at91_clk_register_main_rc_osc(struct at91_pmc *pmc, -- unsigned int irq, -+at91_clk_register_main_rc_osc(struct regmap *regmap, - const char *name, - u32 frequency, u32 accuracy) - { -- int ret; - struct clk_main_rc_osc *osc; - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !irq || !name || !frequency) -+ if (!name || !frequency) - return ERR_PTR(-EINVAL); - - osc = kzalloc(sizeof(*osc), GFP_KERNEL); -@@ -318,63 +294,53 @@ - init.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED; - - osc->hw.init = &init; -- osc->pmc = pmc; -- osc->irq = irq; -+ osc->regmap = regmap; - osc->frequency = frequency; - osc->accuracy = accuracy; - -- init_waitqueue_head(&osc->wait); -- irq_set_status_flags(osc->irq, IRQ_NOAUTOEN); -- ret = request_irq(osc->irq, clk_main_rc_osc_irq_handler, -- IRQF_TRIGGER_HIGH, name, osc); -- if (ret) -- return ERR_PTR(ret); -- - clk = clk_register(NULL, &osc->hw); -- if (IS_ERR(clk)) { -- free_irq(irq, osc); -+ if (IS_ERR(clk)) - kfree(osc); -- } - - return clk; - } - --void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np) - { - struct clk *clk; -- unsigned int irq; - u32 frequency = 0; - u32 accuracy = 0; - const char *name = np->name; -+ struct regmap *regmap; - - of_property_read_string(np, "clock-output-names", &name); - of_property_read_u32(np, "clock-frequency", &frequency); - of_property_read_u32(np, "clock-accuracy", &accuracy); - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) - return; - -- clk = at91_clk_register_main_rc_osc(pmc, irq, name, frequency, -- accuracy); -+ clk = at91_clk_register_main_rc_osc(regmap, name, frequency, accuracy); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9x5_clk_main_rc_osc, "atmel,at91sam9x5-clk-main-rc-osc", -+ of_at91sam9x5_clk_main_rc_osc_setup); - - --static int clk_main_probe_frequency(struct at91_pmc *pmc) -+static int clk_main_probe_frequency(struct regmap *regmap) - { - unsigned long prep_time, timeout; -- u32 tmp; -+ unsigned int mcfr; - - timeout = jiffies + usecs_to_jiffies(MAINFRDY_TIMEOUT); - do { - prep_time = jiffies; -- tmp = pmc_read(pmc, AT91_CKGR_MCFR); -- if (tmp & AT91_PMC_MAINRDY) -+ regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); -+ if (mcfr & AT91_PMC_MAINRDY) - return 0; - usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); - } while (time_before(prep_time, timeout)); -@@ -382,34 +348,37 @@ - return -ETIMEDOUT; - } - --static unsigned long clk_main_recalc_rate(struct at91_pmc *pmc, -+static unsigned long clk_main_recalc_rate(struct regmap *regmap, - unsigned long parent_rate) - { -- u32 tmp; -+ unsigned int mcfr; - - if (parent_rate) - return parent_rate; - - pr_warn("Main crystal frequency not set, using approximate value\n"); -- tmp = pmc_read(pmc, AT91_CKGR_MCFR); -- if (!(tmp & AT91_PMC_MAINRDY)) -+ regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); -+ if (!(mcfr & AT91_PMC_MAINRDY)) - return 0; - -- return ((tmp & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV; -+ return ((mcfr & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV; - } - - static int clk_rm9200_main_prepare(struct clk_hw *hw) - { - struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); - -- return clk_main_probe_frequency(clkmain->pmc); -+ return clk_main_probe_frequency(clkmain->regmap); - } - - static int clk_rm9200_main_is_prepared(struct clk_hw *hw) - { - struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); -+ unsigned int status; -+ -+ regmap_read(clkmain->regmap, AT91_CKGR_MCFR, &status); - -- return !!(pmc_read(clkmain->pmc, AT91_CKGR_MCFR) & AT91_PMC_MAINRDY); -+ return status & AT91_PMC_MAINRDY ? 1 : 0; - } - - static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw, -@@ -417,7 +386,7 @@ - { - struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); - -- return clk_main_recalc_rate(clkmain->pmc, parent_rate); -+ return clk_main_recalc_rate(clkmain->regmap, parent_rate); - } - - static const struct clk_ops rm9200_main_ops = { -@@ -427,7 +396,7 @@ - }; - - static struct clk * __init --at91_clk_register_rm9200_main(struct at91_pmc *pmc, -+at91_clk_register_rm9200_main(struct regmap *regmap, - const char *name, - const char *parent_name) - { -@@ -435,7 +404,7 @@ - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !name) -+ if (!name) - return ERR_PTR(-EINVAL); - - if (!parent_name) -@@ -452,7 +421,7 @@ - init.flags = 0; - - clkmain->hw.init = &init; -- clkmain->pmc = pmc; -+ clkmain->regmap = regmap; - - clk = clk_register(NULL, &clkmain->hw); - if (IS_ERR(clk)) -@@ -461,52 +430,54 @@ - return clk; - } - --void __init of_at91rm9200_clk_main_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_main_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_name; - const char *name = np->name; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91_clk_register_rm9200_main(pmc, name, parent_name); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ -+ clk = at91_clk_register_rm9200_main(regmap, name, parent_name); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91rm9200_clk_main, "atmel,at91rm9200-clk-main", -+ of_at91rm9200_clk_main_setup); - --static irqreturn_t clk_sam9x5_main_irq_handler(int irq, void *dev_id) -+static inline bool clk_sam9x5_main_ready(struct regmap *regmap) - { -- struct clk_sam9x5_main *clkmain = dev_id; -+ unsigned int status; - -- wake_up(&clkmain->wait); -- disable_irq_nosync(clkmain->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & AT91_PMC_MOSCSELS ? 1 : 0; - } - - static int clk_sam9x5_main_prepare(struct clk_hw *hw) - { - struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); -- struct at91_pmc *pmc = clkmain->pmc; -+ struct regmap *regmap = clkmain->regmap; - -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) { -- enable_irq(clkmain->irq); -- wait_event(clkmain->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); -- } -+ while (!clk_sam9x5_main_ready(regmap)) -+ cpu_relax(); - -- return clk_main_probe_frequency(pmc); -+ return clk_main_probe_frequency(regmap); - } - - static int clk_sam9x5_main_is_prepared(struct clk_hw *hw) - { - struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); - -- return !!(pmc_read(clkmain->pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); -+ return clk_sam9x5_main_ready(clkmain->regmap); - } - - static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw, -@@ -514,30 +485,28 @@ - { - struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); - -- return clk_main_recalc_rate(clkmain->pmc, parent_rate); -+ return clk_main_recalc_rate(clkmain->regmap, parent_rate); - } - - static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index) - { - struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); -- struct at91_pmc *pmc = clkmain->pmc; -- u32 tmp; -+ struct regmap *regmap = clkmain->regmap; -+ unsigned int tmp; - - if (index > 1) - return -EINVAL; - -- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; -+ regmap_read(regmap, AT91_CKGR_MOR, &tmp); -+ tmp &= ~MOR_KEY_MASK; - - if (index && !(tmp & AT91_PMC_MOSCSEL)) -- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL); -+ regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL); - else if (!index && (tmp & AT91_PMC_MOSCSEL)) -- pmc_write(pmc, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL); -+ regmap_write(regmap, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL); - -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) { -- enable_irq(clkmain->irq); -- wait_event(clkmain->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); -- } -+ while (!clk_sam9x5_main_ready(regmap)) -+ cpu_relax(); - - return 0; - } -@@ -545,8 +514,11 @@ - static u8 clk_sam9x5_main_get_parent(struct clk_hw *hw) - { - struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); -+ unsigned int status; -+ -+ regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status); - -- return !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN); -+ return status & AT91_PMC_MOSCEN ? 1 : 0; - } - - static const struct clk_ops sam9x5_main_ops = { -@@ -558,18 +530,17 @@ - }; - - static struct clk * __init --at91_clk_register_sam9x5_main(struct at91_pmc *pmc, -- unsigned int irq, -+at91_clk_register_sam9x5_main(struct regmap *regmap, - const char *name, - const char **parent_names, - int num_parents) - { -- int ret; - struct clk_sam9x5_main *clkmain; - struct clk *clk = NULL; - struct clk_init_data init; -+ unsigned int status; - -- if (!pmc || !irq || !name) -+ if (!name) - return ERR_PTR(-EINVAL); - - if (!parent_names || !num_parents) -@@ -586,51 +557,42 @@ - init.flags = CLK_SET_PARENT_GATE; - - clkmain->hw.init = &init; -- clkmain->pmc = pmc; -- clkmain->irq = irq; -- clkmain->parent = !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & -- AT91_PMC_MOSCEN); -- init_waitqueue_head(&clkmain->wait); -- irq_set_status_flags(clkmain->irq, IRQ_NOAUTOEN); -- ret = request_irq(clkmain->irq, clk_sam9x5_main_irq_handler, -- IRQF_TRIGGER_HIGH, name, clkmain); -- if (ret) -- return ERR_PTR(ret); -+ clkmain->regmap = regmap; -+ regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status); -+ clkmain->parent = status & AT91_PMC_MOSCEN ? 1 : 0; - - clk = clk_register(NULL, &clkmain->hw); -- if (IS_ERR(clk)) { -- free_irq(clkmain->irq, clkmain); -+ if (IS_ERR(clk)) - kfree(clkmain); -- } - - return clk; - } - --void __init of_at91sam9x5_clk_main_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_main_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_names[2]; - int num_parents; -- unsigned int irq; - const char *name = np->name; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > 2) - return; - - of_clk_parent_fill(np, parent_names, num_parents); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; - - of_property_read_string(np, "clock-output-names", &name); - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -- return; -- -- clk = at91_clk_register_sam9x5_main(pmc, irq, name, parent_names, -+ clk = at91_clk_register_sam9x5_main(regmap, name, parent_names, - num_parents); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9x5_clk_main, "atmel,at91sam9x5-clk-main", -+ of_at91sam9x5_clk_main_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-master.c linux-4.4.28/drivers/clk/at91/clk-master.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-master.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-master.c 2016-11-01 21:26:57.920287105 +0100 -@@ -12,13 +12,8 @@ - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -44,32 +39,26 @@ - - struct clk_master { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - const struct clk_master_layout *layout; - const struct clk_master_characteristics *characteristics; - }; - --static irqreturn_t clk_master_irq_handler(int irq, void *dev_id) -+static inline bool clk_master_ready(struct regmap *regmap) - { -- struct clk_master *master = (struct clk_master *)dev_id; -+ unsigned int status; - -- wake_up(&master->wait); -- disable_irq_nosync(master->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & AT91_PMC_MCKRDY ? 1 : 0; - } -+ - static int clk_master_prepare(struct clk_hw *hw) - { - struct clk_master *master = to_clk_master(hw); -- struct at91_pmc *pmc = master->pmc; - -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY)) { -- enable_irq(master->irq); -- wait_event(master->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY); -- } -+ while (!clk_master_ready(master->regmap)) -+ cpu_relax(); - - return 0; - } -@@ -78,7 +67,7 @@ - { - struct clk_master *master = to_clk_master(hw); - -- return !!(pmc_read(master->pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY); -+ return clk_master_ready(master->regmap); - } - - static unsigned long clk_master_recalc_rate(struct clk_hw *hw, -@@ -88,18 +77,16 @@ - u8 div; - unsigned long rate = parent_rate; - struct clk_master *master = to_clk_master(hw); -- struct at91_pmc *pmc = master->pmc; - const struct clk_master_layout *layout = master->layout; - const struct clk_master_characteristics *characteristics = - master->characteristics; -- u32 tmp; -+ unsigned int mckr; - -- pmc_lock(pmc); -- tmp = pmc_read(pmc, AT91_PMC_MCKR) & layout->mask; -- pmc_unlock(pmc); -+ regmap_read(master->regmap, AT91_PMC_MCKR, &mckr); -+ mckr &= layout->mask; - -- pres = (tmp >> layout->pres_shift) & MASTER_PRES_MASK; -- div = (tmp >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK; -+ pres = (mckr >> layout->pres_shift) & MASTER_PRES_MASK; -+ div = (mckr >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK; - - if (characteristics->have_div3_pres && pres == MASTER_PRES_MAX) - rate /= 3; -@@ -119,9 +106,11 @@ - static u8 clk_master_get_parent(struct clk_hw *hw) - { - struct clk_master *master = to_clk_master(hw); -- struct at91_pmc *pmc = master->pmc; -+ unsigned int mckr; - -- return pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_CSS; -+ regmap_read(master->regmap, AT91_PMC_MCKR, &mckr); -+ -+ return mckr & AT91_PMC_CSS; - } - - static const struct clk_ops master_ops = { -@@ -132,18 +121,17 @@ - }; - - static struct clk * __init --at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq, -+at91_clk_register_master(struct regmap *regmap, - const char *name, int num_parents, - const char **parent_names, - const struct clk_master_layout *layout, - const struct clk_master_characteristics *characteristics) - { -- int ret; - struct clk_master *master; - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !irq || !name || !num_parents || !parent_names) -+ if (!name || !num_parents || !parent_names) - return ERR_PTR(-EINVAL); - - master = kzalloc(sizeof(*master), GFP_KERNEL); -@@ -159,20 +147,10 @@ - master->hw.init = &init; - master->layout = layout; - master->characteristics = characteristics; -- master->pmc = pmc; -- master->irq = irq; -- init_waitqueue_head(&master->wait); -- irq_set_status_flags(master->irq, IRQ_NOAUTOEN); -- ret = request_irq(master->irq, clk_master_irq_handler, -- IRQF_TRIGGER_HIGH, "clk-master", master); -- if (ret) { -- kfree(master); -- return ERR_PTR(ret); -- } -+ master->regmap = regmap; - - clk = clk_register(NULL, &master->hw); - if (IS_ERR(clk)) { -- free_irq(master->irq, master); - kfree(master); - } - -@@ -217,15 +195,15 @@ - } - - static void __init --of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc, -+of_at91_clk_master_setup(struct device_node *np, - const struct clk_master_layout *layout) - { - struct clk *clk; - int num_parents; -- unsigned int irq; - const char *parent_names[MASTER_SOURCE_MAX]; - const char *name = np->name; - struct clk_master_characteristics *characteristics; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX) -@@ -239,11 +217,11 @@ - if (!characteristics) - return; - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -- goto out_free_characteristics; -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; - -- clk = at91_clk_register_master(pmc, irq, name, num_parents, -+ clk = at91_clk_register_master(regmap, name, num_parents, - parent_names, layout, - characteristics); - if (IS_ERR(clk)) -@@ -256,14 +234,16 @@ - kfree(characteristics); - } - --void __init of_at91rm9200_clk_master_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_master_setup(struct device_node *np) - { -- of_at91_clk_master_setup(np, pmc, &at91rm9200_master_layout); -+ of_at91_clk_master_setup(np, &at91rm9200_master_layout); - } -+CLK_OF_DECLARE(at91rm9200_clk_master, "atmel,at91rm9200-clk-master", -+ of_at91rm9200_clk_master_setup); - --void __init of_at91sam9x5_clk_master_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_master_setup(struct device_node *np) - { -- of_at91_clk_master_setup(np, pmc, &at91sam9x5_master_layout); -+ of_at91_clk_master_setup(np, &at91sam9x5_master_layout); - } -+CLK_OF_DECLARE(at91sam9x5_clk_master, "atmel,at91sam9x5-clk-master", -+ of_at91sam9x5_clk_master_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c linux-4.4.28/drivers/clk/at91/clk-peripheral.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-peripheral.c 2016-11-01 21:26:57.920287105 +0100 -@@ -12,11 +12,13 @@ - #include - #include - #include --#include --#include -+#include -+#include - - #include "pmc.h" - -+DEFINE_SPINLOCK(pmc_pcr_lock); -+ - #define PERIPHERAL_MAX 64 - - #define PERIPHERAL_AT91RM9200 0 -@@ -33,7 +35,7 @@ - - struct clk_peripheral { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - u32 id; - }; - -@@ -41,8 +43,9 @@ - - struct clk_sam9x5_peripheral { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - struct clk_range range; -+ spinlock_t *lock; - u32 id; - u32 div; - bool auto_div; -@@ -54,7 +57,6 @@ - static int clk_peripheral_enable(struct clk_hw *hw) - { - struct clk_peripheral *periph = to_clk_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; - int offset = AT91_PMC_PCER; - u32 id = periph->id; - -@@ -62,14 +64,14 @@ - return 0; - if (id > PERIPHERAL_ID_MAX) - offset = AT91_PMC_PCER1; -- pmc_write(pmc, offset, PERIPHERAL_MASK(id)); -+ regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id)); -+ - return 0; - } - - static void clk_peripheral_disable(struct clk_hw *hw) - { - struct clk_peripheral *periph = to_clk_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; - int offset = AT91_PMC_PCDR; - u32 id = periph->id; - -@@ -77,21 +79,23 @@ - return; - if (id > PERIPHERAL_ID_MAX) - offset = AT91_PMC_PCDR1; -- pmc_write(pmc, offset, PERIPHERAL_MASK(id)); -+ regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id)); - } - - static int clk_peripheral_is_enabled(struct clk_hw *hw) - { - struct clk_peripheral *periph = to_clk_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; - int offset = AT91_PMC_PCSR; -+ unsigned int status; - u32 id = periph->id; - - if (id < PERIPHERAL_ID_MIN) - return 1; - if (id > PERIPHERAL_ID_MAX) - offset = AT91_PMC_PCSR1; -- return !!(pmc_read(pmc, offset) & PERIPHERAL_MASK(id)); -+ regmap_read(periph->regmap, offset, &status); -+ -+ return status & PERIPHERAL_MASK(id) ? 1 : 0; - } - - static const struct clk_ops peripheral_ops = { -@@ -101,14 +105,14 @@ - }; - - static struct clk * __init --at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name, -+at91_clk_register_peripheral(struct regmap *regmap, const char *name, - const char *parent_name, u32 id) - { - struct clk_peripheral *periph; - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !name || !parent_name || id > PERIPHERAL_ID_MAX) -+ if (!name || !parent_name || id > PERIPHERAL_ID_MAX) - return ERR_PTR(-EINVAL); - - periph = kzalloc(sizeof(*periph), GFP_KERNEL); -@@ -123,7 +127,7 @@ - - periph->id = id; - periph->hw.init = &init; -- periph->pmc = pmc; -+ periph->regmap = regmap; - - clk = clk_register(NULL, &periph->hw); - if (IS_ERR(clk)) -@@ -160,53 +164,58 @@ - static int clk_sam9x5_peripheral_enable(struct clk_hw *hw) - { - struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; -- u32 tmp; -+ unsigned long flags; - - if (periph->id < PERIPHERAL_ID_MIN) - return 0; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_DIV_MASK; -- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_DIV(periph->div) -- | AT91_PMC_PCR_CMD -- | AT91_PMC_PCR_EN); -- pmc_unlock(pmc); -+ spin_lock_irqsave(periph->lock, flags); -+ regmap_write(periph->regmap, AT91_PMC_PCR, -+ (periph->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_update_bits(periph->regmap, AT91_PMC_PCR, -+ AT91_PMC_PCR_DIV_MASK | AT91_PMC_PCR_CMD | -+ AT91_PMC_PCR_EN, -+ AT91_PMC_PCR_DIV(periph->div) | -+ AT91_PMC_PCR_CMD | -+ AT91_PMC_PCR_EN); -+ spin_unlock_irqrestore(periph->lock, flags); -+ - return 0; - } - - static void clk_sam9x5_peripheral_disable(struct clk_hw *hw) - { - struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; -- u32 tmp; -+ unsigned long flags; - - if (periph->id < PERIPHERAL_ID_MIN) - return; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_EN; -- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD); -- pmc_unlock(pmc); -+ spin_lock_irqsave(periph->lock, flags); -+ regmap_write(periph->regmap, AT91_PMC_PCR, -+ (periph->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_update_bits(periph->regmap, AT91_PMC_PCR, -+ AT91_PMC_PCR_EN | AT91_PMC_PCR_CMD, -+ AT91_PMC_PCR_CMD); -+ spin_unlock_irqrestore(periph->lock, flags); - } - - static int clk_sam9x5_peripheral_is_enabled(struct clk_hw *hw) - { - struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; -- int ret; -+ unsigned long flags; -+ unsigned int status; - - if (periph->id < PERIPHERAL_ID_MIN) - return 1; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); -- ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_EN); -- pmc_unlock(pmc); -+ spin_lock_irqsave(periph->lock, flags); -+ regmap_write(periph->regmap, AT91_PMC_PCR, -+ (periph->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_read(periph->regmap, AT91_PMC_PCR, &status); -+ spin_unlock_irqrestore(periph->lock, flags); - -- return ret; -+ return status & AT91_PMC_PCR_EN ? 1 : 0; - } - - static unsigned long -@@ -214,19 +223,20 @@ - unsigned long parent_rate) - { - struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); -- struct at91_pmc *pmc = periph->pmc; -- u32 tmp; -+ unsigned long flags; -+ unsigned int status; - - if (periph->id < PERIPHERAL_ID_MIN) - return parent_rate; - -- pmc_lock(pmc); -- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); -- tmp = pmc_read(pmc, AT91_PMC_PCR); -- pmc_unlock(pmc); -+ spin_lock_irqsave(periph->lock, flags); -+ regmap_write(periph->regmap, AT91_PMC_PCR, -+ (periph->id & AT91_PMC_PCR_PID_MASK)); -+ regmap_read(periph->regmap, AT91_PMC_PCR, &status); -+ spin_unlock_irqrestore(periph->lock, flags); - -- if (tmp & AT91_PMC_PCR_EN) { -- periph->div = PERIPHERAL_RSHIFT(tmp); -+ if (status & AT91_PMC_PCR_EN) { -+ periph->div = PERIPHERAL_RSHIFT(status); - periph->auto_div = false; - } else { - clk_sam9x5_peripheral_autodiv(periph); -@@ -318,15 +328,15 @@ - }; - - static struct clk * __init --at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name, -- const char *parent_name, u32 id, -- const struct clk_range *range) -+at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock, -+ const char *name, const char *parent_name, -+ u32 id, const struct clk_range *range) - { - struct clk_sam9x5_peripheral *periph; - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !name || !parent_name) -+ if (!name || !parent_name) - return ERR_PTR(-EINVAL); - - periph = kzalloc(sizeof(*periph), GFP_KERNEL); -@@ -342,7 +352,8 @@ - periph->id = id; - periph->hw.init = &init; - periph->div = 0; -- periph->pmc = pmc; -+ periph->regmap = regmap; -+ periph->lock = lock; - periph->auto_div = true; - periph->range = *range; - -@@ -356,7 +367,7 @@ - } - - static void __init --of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type) -+of_at91_clk_periph_setup(struct device_node *np, u8 type) - { - int num; - u32 id; -@@ -364,6 +375,7 @@ - const char *parent_name; - const char *name; - struct device_node *periphclknp; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - if (!parent_name) -@@ -373,6 +385,10 @@ - if (!num || num > PERIPHERAL_MAX) - return; - -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ - for_each_child_of_node(np, periphclknp) { - if (of_property_read_u32(periphclknp, "reg", &id)) - continue; -@@ -384,7 +400,7 @@ - name = periphclknp->name; - - if (type == PERIPHERAL_AT91RM9200) { -- clk = at91_clk_register_peripheral(pmc, name, -+ clk = at91_clk_register_peripheral(regmap, name, - parent_name, id); - } else { - struct clk_range range = CLK_RANGE(0, 0); -@@ -393,7 +409,9 @@ - "atmel,clk-output-range", - &range); - -- clk = at91_clk_register_sam9x5_peripheral(pmc, name, -+ clk = at91_clk_register_sam9x5_peripheral(regmap, -+ &pmc_pcr_lock, -+ name, - parent_name, - id, &range); - } -@@ -405,14 +423,16 @@ - } - } - --void __init of_at91rm9200_clk_periph_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_periph_setup(struct device_node *np) - { -- of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91RM9200); -+ of_at91_clk_periph_setup(np, PERIPHERAL_AT91RM9200); - } -+CLK_OF_DECLARE(at91rm9200_clk_periph, "atmel,at91rm9200-clk-peripheral", -+ of_at91rm9200_clk_periph_setup); - --void __init of_at91sam9x5_clk_periph_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_periph_setup(struct device_node *np) - { -- of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91SAM9X5); -+ of_at91_clk_periph_setup(np, PERIPHERAL_AT91SAM9X5); - } -+CLK_OF_DECLARE(at91sam9x5_clk_periph, "atmel,at91sam9x5-clk-peripheral", -+ of_at91sam9x5_clk_periph_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-pll.c linux-4.4.28/drivers/clk/at91/clk-pll.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-pll.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-pll.c 2016-11-01 21:26:57.924287358 +0100 -@@ -12,14 +12,8 @@ - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -58,9 +52,7 @@ - - struct clk_pll { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - u8 id; - u8 div; - u8 range; -@@ -69,20 +61,19 @@ - const struct clk_pll_characteristics *characteristics; - }; - --static irqreturn_t clk_pll_irq_handler(int irq, void *dev_id) -+static inline bool clk_pll_ready(struct regmap *regmap, int id) - { -- struct clk_pll *pll = (struct clk_pll *)dev_id; -+ unsigned int status; - -- wake_up(&pll->wait); -- disable_irq_nosync(pll->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & PLL_STATUS_MASK(id) ? 1 : 0; - } - - static int clk_pll_prepare(struct clk_hw *hw) - { - struct clk_pll *pll = to_clk_pll(hw); -- struct at91_pmc *pmc = pll->pmc; -+ struct regmap *regmap = pll->regmap; - const struct clk_pll_layout *layout = pll->layout; - const struct clk_pll_characteristics *characteristics = - pll->characteristics; -@@ -90,39 +81,34 @@ - u32 mask = PLL_STATUS_MASK(id); - int offset = PLL_REG(id); - u8 out = 0; -- u32 pllr, icpr; -+ unsigned int pllr; -+ unsigned int status; - u8 div; - u16 mul; - -- pllr = pmc_read(pmc, offset); -+ regmap_read(regmap, offset, &pllr); - div = PLL_DIV(pllr); - mul = PLL_MUL(pllr, layout); - -- if ((pmc_read(pmc, AT91_PMC_SR) & mask) && -+ regmap_read(regmap, AT91_PMC_SR, &status); -+ if ((status & mask) && - (div == pll->div && mul == pll->mul)) - return 0; - - if (characteristics->out) - out = characteristics->out[pll->range]; -- if (characteristics->icpll) { -- icpr = pmc_read(pmc, AT91_PMC_PLLICPR) & ~PLL_ICPR_MASK(id); -- icpr |= (characteristics->icpll[pll->range] << -- PLL_ICPR_SHIFT(id)); -- pmc_write(pmc, AT91_PMC_PLLICPR, icpr); -- } - -- pllr &= ~layout->pllr_mask; -- pllr |= layout->pllr_mask & -- (pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) | -- (out << PLL_OUT_SHIFT) | -- ((pll->mul & layout->mul_mask) << layout->mul_shift)); -- pmc_write(pmc, offset, pllr); -- -- while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) { -- enable_irq(pll->irq); -- wait_event(pll->wait, -- pmc_read(pmc, AT91_PMC_SR) & mask); -- } -+ if (characteristics->icpll) -+ regmap_update_bits(regmap, AT91_PMC_PLLICPR, PLL_ICPR_MASK(id), -+ characteristics->icpll[pll->range] << PLL_ICPR_SHIFT(id)); -+ -+ regmap_update_bits(regmap, offset, layout->pllr_mask, -+ pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) | -+ (out << PLL_OUT_SHIFT) | -+ ((pll->mul & layout->mul_mask) << layout->mul_shift)); -+ -+ while (!clk_pll_ready(regmap, pll->id)) -+ cpu_relax(); - - return 0; - } -@@ -130,32 +116,35 @@ - static int clk_pll_is_prepared(struct clk_hw *hw) - { - struct clk_pll *pll = to_clk_pll(hw); -- struct at91_pmc *pmc = pll->pmc; - -- return !!(pmc_read(pmc, AT91_PMC_SR) & -- PLL_STATUS_MASK(pll->id)); -+ return clk_pll_ready(pll->regmap, pll->id); - } - - static void clk_pll_unprepare(struct clk_hw *hw) - { - struct clk_pll *pll = to_clk_pll(hw); -- struct at91_pmc *pmc = pll->pmc; -- const struct clk_pll_layout *layout = pll->layout; -- int offset = PLL_REG(pll->id); -- u32 tmp = pmc_read(pmc, offset) & ~(layout->pllr_mask); -+ unsigned int mask = pll->layout->pllr_mask; - -- pmc_write(pmc, offset, tmp); -+ regmap_update_bits(pll->regmap, PLL_REG(pll->id), mask, ~mask); - } - - static unsigned long clk_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) - { - struct clk_pll *pll = to_clk_pll(hw); -+ unsigned int pllr; -+ u16 mul; -+ u8 div; -+ -+ regmap_read(pll->regmap, PLL_REG(pll->id), &pllr); -+ -+ div = PLL_DIV(pllr); -+ mul = PLL_MUL(pllr, pll->layout); - -- if (!pll->div || !pll->mul) -+ if (!div || !mul) - return 0; - -- return (parent_rate / pll->div) * (pll->mul + 1); -+ return (parent_rate / div) * (mul + 1); - } - - static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate, -@@ -308,7 +297,7 @@ - }; - - static struct clk * __init --at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name, -+at91_clk_register_pll(struct regmap *regmap, const char *name, - const char *parent_name, u8 id, - const struct clk_pll_layout *layout, - const struct clk_pll_characteristics *characteristics) -@@ -316,9 +305,8 @@ - struct clk_pll *pll; - struct clk *clk = NULL; - struct clk_init_data init; -- int ret; - int offset = PLL_REG(id); -- u32 tmp; -+ unsigned int pllr; - - if (id > PLL_MAX_ID) - return ERR_PTR(-EINVAL); -@@ -337,23 +325,13 @@ - pll->hw.init = &init; - pll->layout = layout; - pll->characteristics = characteristics; -- pll->pmc = pmc; -- pll->irq = irq; -- tmp = pmc_read(pmc, offset) & layout->pllr_mask; -- pll->div = PLL_DIV(tmp); -- pll->mul = PLL_MUL(tmp, layout); -- init_waitqueue_head(&pll->wait); -- irq_set_status_flags(pll->irq, IRQ_NOAUTOEN); -- ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH, -- id ? "clk-pllb" : "clk-plla", pll); -- if (ret) { -- kfree(pll); -- return ERR_PTR(ret); -- } -+ pll->regmap = regmap; -+ regmap_read(regmap, offset, &pllr); -+ pll->div = PLL_DIV(pllr); -+ pll->mul = PLL_MUL(pllr, layout); - - clk = clk_register(NULL, &pll->hw); - if (IS_ERR(clk)) { -- free_irq(pll->irq, pll); - kfree(pll); - } - -@@ -483,12 +461,12 @@ - } - - static void __init --of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc, -+of_at91_clk_pll_setup(struct device_node *np, - const struct clk_pll_layout *layout) - { - u32 id; -- unsigned int irq; - struct clk *clk; -+ struct regmap *regmap; - const char *parent_name; - const char *name = np->name; - struct clk_pll_characteristics *characteristics; -@@ -500,15 +478,15 @@ - - of_property_read_string(np, "clock-output-names", &name); - -- characteristics = of_at91_clk_pll_get_characteristics(np); -- if (!characteristics) -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) - return; - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -+ characteristics = of_at91_clk_pll_get_characteristics(np); -+ if (!characteristics) - return; - -- clk = at91_clk_register_pll(pmc, irq, name, parent_name, id, layout, -+ clk = at91_clk_register_pll(regmap, name, parent_name, id, layout, - characteristics); - if (IS_ERR(clk)) - goto out_free_characteristics; -@@ -520,26 +498,30 @@ - kfree(characteristics); - } - --void __init of_at91rm9200_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_pll_setup(struct device_node *np) - { -- of_at91_clk_pll_setup(np, pmc, &at91rm9200_pll_layout); -+ of_at91_clk_pll_setup(np, &at91rm9200_pll_layout); - } -+CLK_OF_DECLARE(at91rm9200_clk_pll, "atmel,at91rm9200-clk-pll", -+ of_at91rm9200_clk_pll_setup); - --void __init of_at91sam9g45_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9g45_clk_pll_setup(struct device_node *np) - { -- of_at91_clk_pll_setup(np, pmc, &at91sam9g45_pll_layout); -+ of_at91_clk_pll_setup(np, &at91sam9g45_pll_layout); - } -+CLK_OF_DECLARE(at91sam9g45_clk_pll, "atmel,at91sam9g45-clk-pll", -+ of_at91sam9g45_clk_pll_setup); - --void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np) - { -- of_at91_clk_pll_setup(np, pmc, &at91sam9g20_pllb_layout); -+ of_at91_clk_pll_setup(np, &at91sam9g20_pllb_layout); - } -+CLK_OF_DECLARE(at91sam9g20_clk_pllb, "atmel,at91sam9g20-clk-pllb", -+ of_at91sam9g20_clk_pllb_setup); - --void __init of_sama5d3_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_sama5d3_clk_pll_setup(struct device_node *np) - { -- of_at91_clk_pll_setup(np, pmc, &sama5d3_pll_layout); -+ of_at91_clk_pll_setup(np, &sama5d3_pll_layout); - } -+CLK_OF_DECLARE(sama5d3_clk_pll, "atmel,sama5d3-clk-pll", -+ of_sama5d3_clk_pll_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c linux-4.4.28/drivers/clk/at91/clk-plldiv.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-plldiv.c 2016-11-01 21:26:57.924287358 +0100 -@@ -12,8 +12,8 @@ - #include - #include - #include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -21,16 +21,18 @@ - - struct clk_plldiv { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - static unsigned long clk_plldiv_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) - { - struct clk_plldiv *plldiv = to_clk_plldiv(hw); -- struct at91_pmc *pmc = plldiv->pmc; -+ unsigned int mckr; - -- if (pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_PLLADIV2) -+ regmap_read(plldiv->regmap, AT91_PMC_MCKR, &mckr); -+ -+ if (mckr & AT91_PMC_PLLADIV2) - return parent_rate / 2; - - return parent_rate; -@@ -57,18 +59,12 @@ - unsigned long parent_rate) - { - struct clk_plldiv *plldiv = to_clk_plldiv(hw); -- struct at91_pmc *pmc = plldiv->pmc; -- u32 tmp; - -- if (parent_rate != rate && (parent_rate / 2) != rate) -+ if ((parent_rate != rate) && (parent_rate / 2 != rate)) - return -EINVAL; - -- pmc_lock(pmc); -- tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_PLLADIV2; -- if ((parent_rate / 2) == rate) -- tmp |= AT91_PMC_PLLADIV2; -- pmc_write(pmc, AT91_PMC_MCKR, tmp); -- pmc_unlock(pmc); -+ regmap_update_bits(plldiv->regmap, AT91_PMC_MCKR, AT91_PMC_PLLADIV2, -+ parent_rate != rate ? AT91_PMC_PLLADIV2 : 0); - - return 0; - } -@@ -80,7 +76,7 @@ - }; - - static struct clk * __init --at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name, -+at91_clk_register_plldiv(struct regmap *regmap, const char *name, - const char *parent_name) - { - struct clk_plldiv *plldiv; -@@ -98,7 +94,7 @@ - init.flags = CLK_SET_RATE_GATE; - - plldiv->hw.init = &init; -- plldiv->pmc = pmc; -+ plldiv->regmap = regmap; - - clk = clk_register(NULL, &plldiv->hw); - -@@ -109,27 +105,27 @@ - } - - static void __init --of_at91_clk_plldiv_setup(struct device_node *np, struct at91_pmc *pmc) -+of_at91sam9x5_clk_plldiv_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_name; - const char *name = np->name; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91_clk_register_plldiv(pmc, name, parent_name); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; - -+ clk = at91_clk_register_plldiv(regmap, name, parent_name); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - return; - } -- --void __init of_at91sam9x5_clk_plldiv_setup(struct device_node *np, -- struct at91_pmc *pmc) --{ -- of_at91_clk_plldiv_setup(np, pmc); --} -+CLK_OF_DECLARE(at91sam9x5_clk_plldiv, "atmel,at91sam9x5-clk-plldiv", -+ of_at91sam9x5_clk_plldiv_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c linux-4.4.28/drivers/clk/at91/clk-programmable.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-programmable.c 2016-11-01 21:26:57.936288132 +0100 -@@ -12,10 +12,8 @@ - #include - #include - #include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -24,6 +22,7 @@ - - #define PROG_STATUS_MASK(id) (1 << ((id) + 8)) - #define PROG_PRES_MASK 0x7 -+#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & PROG_PRES_MASK) - #define PROG_MAX_RM9200_CSS 3 - - struct clk_programmable_layout { -@@ -34,7 +33,7 @@ - - struct clk_programmable { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - u8 id; - const struct clk_programmable_layout *layout; - }; -@@ -44,14 +43,12 @@ - static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) - { -- u32 pres; - struct clk_programmable *prog = to_clk_programmable(hw); -- struct at91_pmc *pmc = prog->pmc; -- const struct clk_programmable_layout *layout = prog->layout; -+ unsigned int pckr; -+ -+ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); - -- pres = (pmc_read(pmc, AT91_PMC_PCKR(prog->id)) >> layout->pres_shift) & -- PROG_PRES_MASK; -- return parent_rate >> pres; -+ return parent_rate >> PROG_PRES(prog->layout, pckr); - } - - static int clk_programmable_determine_rate(struct clk_hw *hw, -@@ -101,36 +98,36 @@ - { - struct clk_programmable *prog = to_clk_programmable(hw); - const struct clk_programmable_layout *layout = prog->layout; -- struct at91_pmc *pmc = prog->pmc; -- u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & ~layout->css_mask; -+ unsigned int mask = layout->css_mask; -+ unsigned int pckr = 0; - - if (layout->have_slck_mck) -- tmp &= AT91_PMC_CSSMCK_MCK; -+ mask |= AT91_PMC_CSSMCK_MCK; - - if (index > layout->css_mask) { -- if (index > PROG_MAX_RM9200_CSS && layout->have_slck_mck) { -- tmp |= AT91_PMC_CSSMCK_MCK; -- return 0; -- } else { -+ if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck) - return -EINVAL; -- } -+ -+ pckr |= AT91_PMC_CSSMCK_MCK; - } - -- pmc_write(pmc, AT91_PMC_PCKR(prog->id), tmp | index); -+ regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), mask, pckr); -+ - return 0; - } - - static u8 clk_programmable_get_parent(struct clk_hw *hw) - { -- u32 tmp; -- u8 ret; - struct clk_programmable *prog = to_clk_programmable(hw); -- struct at91_pmc *pmc = prog->pmc; - const struct clk_programmable_layout *layout = prog->layout; -+ unsigned int pckr; -+ u8 ret; -+ -+ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); -+ -+ ret = pckr & layout->css_mask; - -- tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)); -- ret = tmp & layout->css_mask; -- if (layout->have_slck_mck && (tmp & AT91_PMC_CSSMCK_MCK) && !ret) -+ if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret) - ret = PROG_MAX_RM9200_CSS + 1; - - return ret; -@@ -140,26 +137,27 @@ - unsigned long parent_rate) - { - struct clk_programmable *prog = to_clk_programmable(hw); -- struct at91_pmc *pmc = prog->pmc; - const struct clk_programmable_layout *layout = prog->layout; - unsigned long div = parent_rate / rate; -+ unsigned int pckr; - int shift = 0; -- u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & -- ~(PROG_PRES_MASK << layout->pres_shift); -+ -+ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); - - if (!div) - return -EINVAL; - - shift = fls(div) - 1; - -- if (div != (1<= PROG_PRES_MASK) - return -EINVAL; - -- pmc_write(pmc, AT91_PMC_PCKR(prog->id), -- tmp | (shift << layout->pres_shift)); -+ regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), -+ PROG_PRES_MASK << layout->pres_shift, -+ shift << layout->pres_shift); - - return 0; - } -@@ -173,7 +171,7 @@ - }; - - static struct clk * __init --at91_clk_register_programmable(struct at91_pmc *pmc, -+at91_clk_register_programmable(struct regmap *regmap, - const char *name, const char **parent_names, - u8 num_parents, u8 id, - const struct clk_programmable_layout *layout) -@@ -198,7 +196,7 @@ - prog->id = id; - prog->layout = layout; - prog->hw.init = &init; -- prog->pmc = pmc; -+ prog->regmap = regmap; - - clk = clk_register(NULL, &prog->hw); - if (IS_ERR(clk)) -@@ -226,7 +224,7 @@ - }; - - static void __init --of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc, -+of_at91_clk_prog_setup(struct device_node *np, - const struct clk_programmable_layout *layout) - { - int num; -@@ -236,6 +234,7 @@ - const char *parent_names[PROG_SOURCE_MAX]; - const char *name; - struct device_node *progclknp; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX) -@@ -247,6 +246,10 @@ - if (!num || num > (PROG_ID_MAX + 1)) - return; - -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ - for_each_child_of_node(np, progclknp) { - if (of_property_read_u32(progclknp, "reg", &id)) - continue; -@@ -254,7 +257,7 @@ - if (of_property_read_string(np, "clock-output-names", &name)) - name = progclknp->name; - -- clk = at91_clk_register_programmable(pmc, name, -+ clk = at91_clk_register_programmable(regmap, name, - parent_names, num_parents, - id, layout); - if (IS_ERR(clk)) -@@ -265,20 +268,23 @@ - } - - --void __init of_at91rm9200_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_prog_setup(struct device_node *np) - { -- of_at91_clk_prog_setup(np, pmc, &at91rm9200_programmable_layout); -+ of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout); - } -+CLK_OF_DECLARE(at91rm9200_clk_prog, "atmel,at91rm9200-clk-programmable", -+ of_at91rm9200_clk_prog_setup); - --void __init of_at91sam9g45_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9g45_clk_prog_setup(struct device_node *np) - { -- of_at91_clk_prog_setup(np, pmc, &at91sam9g45_programmable_layout); -+ of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout); - } -+CLK_OF_DECLARE(at91sam9g45_clk_prog, "atmel,at91sam9g45-clk-programmable", -+ of_at91sam9g45_clk_prog_setup); - --void __init of_at91sam9x5_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_prog_setup(struct device_node *np) - { -- of_at91_clk_prog_setup(np, pmc, &at91sam9x5_programmable_layout); -+ of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout); - } -+CLK_OF_DECLARE(at91sam9x5_clk_prog, "atmel,at91sam9x5-clk-programmable", -+ of_at91sam9x5_clk_prog_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-slow.c linux-4.4.28/drivers/clk/at91/clk-slow.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-slow.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-slow.c 2016-11-01 21:26:57.940288388 +0100 -@@ -13,17 +13,11 @@ - #include - #include - #include --#include - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - #include "sckc.h" -@@ -59,7 +53,7 @@ - - struct clk_sam9260_slow { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - #define to_clk_sam9260_slow(hw) container_of(hw, struct clk_sam9260_slow, hw) -@@ -393,8 +387,11 @@ - static u8 clk_sam9260_slow_get_parent(struct clk_hw *hw) - { - struct clk_sam9260_slow *slowck = to_clk_sam9260_slow(hw); -+ unsigned int status; - -- return !!(pmc_read(slowck->pmc, AT91_PMC_SR) & AT91_PMC_OSCSEL); -+ regmap_read(slowck->regmap, AT91_PMC_SR, &status); -+ -+ return status & AT91_PMC_OSCSEL ? 1 : 0; - } - - static const struct clk_ops sam9260_slow_ops = { -@@ -402,7 +399,7 @@ - }; - - static struct clk * __init --at91_clk_register_sam9260_slow(struct at91_pmc *pmc, -+at91_clk_register_sam9260_slow(struct regmap *regmap, - const char *name, - const char **parent_names, - int num_parents) -@@ -411,7 +408,7 @@ - struct clk *clk = NULL; - struct clk_init_data init; - -- if (!pmc || !name) -+ if (!name) - return ERR_PTR(-EINVAL); - - if (!parent_names || !num_parents) -@@ -428,7 +425,7 @@ - init.flags = 0; - - slowck->hw.init = &init; -- slowck->pmc = pmc; -+ slowck->regmap = regmap; - - clk = clk_register(NULL, &slowck->hw); - if (IS_ERR(clk)) -@@ -439,29 +436,34 @@ - return clk; - } - --void __init of_at91sam9260_clk_slow_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9260_clk_slow_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_names[2]; - int num_parents; - const char *name = np->name; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents != 2) - return; - - of_clk_parent_fill(np, parent_names, num_parents); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91_clk_register_sam9260_slow(pmc, name, parent_names, -+ clk = at91_clk_register_sam9260_slow(regmap, name, parent_names, - num_parents); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9260_clk_slow, "atmel,at91sam9260-clk-slow", -+ of_at91sam9260_clk_slow_setup); - - /* - * FIXME: All slow clk users are not properly claiming it (get + prepare + -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-smd.c linux-4.4.28/drivers/clk/at91/clk-smd.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-smd.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-smd.c 2016-11-01 21:26:57.940288388 +0100 -@@ -12,8 +12,8 @@ - #include - #include - #include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -24,7 +24,7 @@ - - struct at91sam9x5_clk_smd { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - #define to_at91sam9x5_clk_smd(hw) \ -@@ -33,13 +33,13 @@ - static unsigned long at91sam9x5_clk_smd_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) - { -- u32 tmp; -- u8 smddiv; - struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); -- struct at91_pmc *pmc = smd->pmc; -+ unsigned int smdr; -+ u8 smddiv; -+ -+ regmap_read(smd->regmap, AT91_PMC_SMD, &smdr); -+ smddiv = (smdr & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT; - -- tmp = pmc_read(pmc, AT91_PMC_SMD); -- smddiv = (tmp & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT; - return parent_rate / (smddiv + 1); - } - -@@ -67,40 +67,38 @@ - - static int at91sam9x5_clk_smd_set_parent(struct clk_hw *hw, u8 index) - { -- u32 tmp; - struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); -- struct at91_pmc *pmc = smd->pmc; - - if (index > 1) - return -EINVAL; -- tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMDS; -- if (index) -- tmp |= AT91_PMC_SMDS; -- pmc_write(pmc, AT91_PMC_SMD, tmp); -+ -+ regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMDS, -+ index ? AT91_PMC_SMDS : 0); -+ - return 0; - } - - static u8 at91sam9x5_clk_smd_get_parent(struct clk_hw *hw) - { - struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); -- struct at91_pmc *pmc = smd->pmc; -+ unsigned int smdr; - -- return pmc_read(pmc, AT91_PMC_SMD) & AT91_PMC_SMDS; -+ regmap_read(smd->regmap, AT91_PMC_SMD, &smdr); -+ -+ return smdr & AT91_PMC_SMDS; - } - - static int at91sam9x5_clk_smd_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) - { -- u32 tmp; - struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); -- struct at91_pmc *pmc = smd->pmc; - unsigned long div = parent_rate / rate; - - if (parent_rate % rate || div < 1 || div > (SMD_MAX_DIV + 1)) - return -EINVAL; -- tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMD_DIV; -- tmp |= (div - 1) << SMD_DIV_SHIFT; -- pmc_write(pmc, AT91_PMC_SMD, tmp); -+ -+ regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMD_DIV, -+ (div - 1) << SMD_DIV_SHIFT); - - return 0; - } -@@ -114,7 +112,7 @@ - }; - - static struct clk * __init --at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name, -+at91sam9x5_clk_register_smd(struct regmap *regmap, const char *name, - const char **parent_names, u8 num_parents) - { - struct at91sam9x5_clk_smd *smd; -@@ -132,7 +130,7 @@ - init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE; - - smd->hw.init = &init; -- smd->pmc = pmc; -+ smd->regmap = regmap; - - clk = clk_register(NULL, &smd->hw); - if (IS_ERR(clk)) -@@ -141,13 +139,13 @@ - return clk; - } - --void __init of_at91sam9x5_clk_smd_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_smd_setup(struct device_node *np) - { - struct clk *clk; - int num_parents; - const char *parent_names[SMD_SOURCE_MAX]; - const char *name = np->name; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX) -@@ -157,10 +155,16 @@ - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91sam9x5_clk_register_smd(pmc, name, parent_names, -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ -+ clk = at91sam9x5_clk_register_smd(regmap, name, parent_names, - num_parents); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9x5_clk_smd, "atmel,at91sam9x5-clk-smd", -+ of_at91sam9x5_clk_smd_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-system.c linux-4.4.28/drivers/clk/at91/clk-system.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-system.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-system.c 2016-11-01 21:26:57.940288388 +0100 -@@ -12,13 +12,8 @@ - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -29,9 +24,7 @@ - #define to_clk_system(hw) container_of(hw, struct clk_system, hw) - struct clk_system { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - u8 id; - }; - -@@ -39,58 +32,54 @@ - { - return (id >= 8) && (id <= 15); - } --static irqreturn_t clk_system_irq_handler(int irq, void *dev_id) -+ -+static inline bool clk_system_ready(struct regmap *regmap, int id) - { -- struct clk_system *sys = (struct clk_system *)dev_id; -+ unsigned int status; - -- wake_up(&sys->wait); -- disable_irq_nosync(sys->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & (1 << id) ? 1 : 0; - } - - static int clk_system_prepare(struct clk_hw *hw) - { - struct clk_system *sys = to_clk_system(hw); -- struct at91_pmc *pmc = sys->pmc; -- u32 mask = 1 << sys->id; - -- pmc_write(pmc, AT91_PMC_SCER, mask); -+ regmap_write(sys->regmap, AT91_PMC_SCER, 1 << sys->id); - - if (!is_pck(sys->id)) - return 0; - -- while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) { -- if (sys->irq) { -- enable_irq(sys->irq); -- wait_event(sys->wait, -- pmc_read(pmc, AT91_PMC_SR) & mask); -- } else -- cpu_relax(); -- } -+ while (!clk_system_ready(sys->regmap, sys->id)) -+ cpu_relax(); -+ - return 0; - } - - static void clk_system_unprepare(struct clk_hw *hw) - { - struct clk_system *sys = to_clk_system(hw); -- struct at91_pmc *pmc = sys->pmc; - -- pmc_write(pmc, AT91_PMC_SCDR, 1 << sys->id); -+ regmap_write(sys->regmap, AT91_PMC_SCDR, 1 << sys->id); - } - - static int clk_system_is_prepared(struct clk_hw *hw) - { - struct clk_system *sys = to_clk_system(hw); -- struct at91_pmc *pmc = sys->pmc; -+ unsigned int status; -+ -+ regmap_read(sys->regmap, AT91_PMC_SCSR, &status); - -- if (!(pmc_read(pmc, AT91_PMC_SCSR) & (1 << sys->id))) -+ if (!(status & (1 << sys->id))) - return 0; - - if (!is_pck(sys->id)) - return 1; - -- return !!(pmc_read(pmc, AT91_PMC_SR) & (1 << sys->id)); -+ regmap_read(sys->regmap, AT91_PMC_SR, &status); -+ -+ return status & (1 << sys->id) ? 1 : 0; - } - - static const struct clk_ops system_ops = { -@@ -100,13 +89,12 @@ - }; - - static struct clk * __init --at91_clk_register_system(struct at91_pmc *pmc, const char *name, -- const char *parent_name, u8 id, int irq) -+at91_clk_register_system(struct regmap *regmap, const char *name, -+ const char *parent_name, u8 id) - { - struct clk_system *sys; - struct clk *clk = NULL; - struct clk_init_data init; -- int ret; - - if (!parent_name || id > SYSTEM_MAX_ID) - return ERR_PTR(-EINVAL); -@@ -123,44 +111,33 @@ - - sys->id = id; - sys->hw.init = &init; -- sys->pmc = pmc; -- sys->irq = irq; -- if (irq) { -- init_waitqueue_head(&sys->wait); -- irq_set_status_flags(sys->irq, IRQ_NOAUTOEN); -- ret = request_irq(sys->irq, clk_system_irq_handler, -- IRQF_TRIGGER_HIGH, name, sys); -- if (ret) { -- kfree(sys); -- return ERR_PTR(ret); -- } -- } -+ sys->regmap = regmap; - - clk = clk_register(NULL, &sys->hw); -- if (IS_ERR(clk)) { -- if (irq) -- free_irq(sys->irq, sys); -+ if (IS_ERR(clk)) - kfree(sys); -- } - - return clk; - } - --static void __init --of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_sys_setup(struct device_node *np) - { - int num; -- int irq = 0; - u32 id; - struct clk *clk; - const char *name; - struct device_node *sysclknp; - const char *parent_name; -+ struct regmap *regmap; - - num = of_get_child_count(np); - if (num > (SYSTEM_MAX_ID + 1)) - return; - -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ - for_each_child_of_node(np, sysclknp) { - if (of_property_read_u32(sysclknp, "reg", &id)) - continue; -@@ -168,21 +145,14 @@ - if (of_property_read_string(np, "clock-output-names", &name)) - name = sysclknp->name; - -- if (is_pck(id)) -- irq = irq_of_parse_and_map(sysclknp, 0); -- - parent_name = of_clk_get_parent_name(sysclknp, 0); - -- clk = at91_clk_register_system(pmc, name, parent_name, id, irq); -+ clk = at91_clk_register_system(regmap, name, parent_name, id); - if (IS_ERR(clk)) - continue; - - of_clk_add_provider(sysclknp, of_clk_src_simple_get, clk); - } - } -- --void __init of_at91rm9200_clk_sys_setup(struct device_node *np, -- struct at91_pmc *pmc) --{ -- of_at91_clk_sys_setup(np, pmc); --} -+CLK_OF_DECLARE(at91rm9200_clk_sys, "atmel,at91rm9200-clk-system", -+ of_at91rm9200_clk_sys_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-usb.c linux-4.4.28/drivers/clk/at91/clk-usb.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-usb.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-usb.c 2016-11-01 21:26:57.940288388 +0100 -@@ -12,8 +12,8 @@ - #include - #include - #include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -27,7 +27,7 @@ - - struct at91sam9x5_clk_usb { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - }; - - #define to_at91sam9x5_clk_usb(hw) \ -@@ -35,7 +35,7 @@ - - struct at91rm9200_clk_usb { - struct clk_hw hw; -- struct at91_pmc *pmc; -+ struct regmap *regmap; - u32 divisors[4]; - }; - -@@ -45,13 +45,12 @@ - static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) - { -- u32 tmp; -- u8 usbdiv; - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; -+ unsigned int usbr; -+ u8 usbdiv; - -- tmp = pmc_read(pmc, AT91_PMC_USB); -- usbdiv = (tmp & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT; -+ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); -+ usbdiv = (usbr & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT; - - return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1)); - } -@@ -109,33 +108,31 @@ - - static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index) - { -- u32 tmp; - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; - - if (index > 1) - return -EINVAL; -- tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS; -- if (index) -- tmp |= AT91_PMC_USBS; -- pmc_write(pmc, AT91_PMC_USB, tmp); -+ -+ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, -+ index ? AT91_PMC_USBS : 0); -+ - return 0; - } - - static u8 at91sam9x5_clk_usb_get_parent(struct clk_hw *hw) - { - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; -+ unsigned int usbr; - -- return pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS; -+ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); -+ -+ return usbr & AT91_PMC_USBS; - } - - static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) - { -- u32 tmp; - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; - unsigned long div; - - if (!rate) -@@ -145,9 +142,8 @@ - if (div > SAM9X5_USB_MAX_DIV + 1 || !div) - return -EINVAL; - -- tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_OHCIUSBDIV; -- tmp |= (div - 1) << SAM9X5_USB_DIV_SHIFT; -- pmc_write(pmc, AT91_PMC_USB, tmp); -+ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_OHCIUSBDIV, -+ (div - 1) << SAM9X5_USB_DIV_SHIFT); - - return 0; - } -@@ -163,28 +159,28 @@ - static int at91sam9n12_clk_usb_enable(struct clk_hw *hw) - { - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; - -- pmc_write(pmc, AT91_PMC_USB, -- pmc_read(pmc, AT91_PMC_USB) | AT91_PMC_USBS); -+ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, -+ AT91_PMC_USBS); -+ - return 0; - } - - static void at91sam9n12_clk_usb_disable(struct clk_hw *hw) - { - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; - -- pmc_write(pmc, AT91_PMC_USB, -- pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS); -+ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, 0); - } - - static int at91sam9n12_clk_usb_is_enabled(struct clk_hw *hw) - { - struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; -+ unsigned int usbr; - -- return !!(pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS); -+ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); -+ -+ return usbr & AT91_PMC_USBS; - } - - static const struct clk_ops at91sam9n12_usb_ops = { -@@ -197,7 +193,7 @@ - }; - - static struct clk * __init --at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name, -+at91sam9x5_clk_register_usb(struct regmap *regmap, const char *name, - const char **parent_names, u8 num_parents) - { - struct at91sam9x5_clk_usb *usb; -@@ -216,7 +212,7 @@ - CLK_SET_RATE_PARENT; - - usb->hw.init = &init; -- usb->pmc = pmc; -+ usb->regmap = regmap; - - clk = clk_register(NULL, &usb->hw); - if (IS_ERR(clk)) -@@ -226,7 +222,7 @@ - } - - static struct clk * __init --at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name, -+at91sam9n12_clk_register_usb(struct regmap *regmap, const char *name, - const char *parent_name) - { - struct at91sam9x5_clk_usb *usb; -@@ -244,7 +240,7 @@ - init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT; - - usb->hw.init = &init; -- usb->pmc = pmc; -+ usb->regmap = regmap; - - clk = clk_register(NULL, &usb->hw); - if (IS_ERR(clk)) -@@ -257,12 +253,12 @@ - unsigned long parent_rate) - { - struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; -- u32 tmp; -+ unsigned int pllbr; - u8 usbdiv; - -- tmp = pmc_read(pmc, AT91_CKGR_PLLBR); -- usbdiv = (tmp & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT; -+ regmap_read(usb->regmap, AT91_CKGR_PLLBR, &pllbr); -+ -+ usbdiv = (pllbr & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT; - if (usb->divisors[usbdiv]) - return parent_rate / usb->divisors[usbdiv]; - -@@ -310,10 +306,8 @@ - static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) - { -- u32 tmp; - int i; - struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw); -- struct at91_pmc *pmc = usb->pmc; - unsigned long div; - - if (!rate) -@@ -323,10 +317,10 @@ - - for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) { - if (usb->divisors[i] == div) { -- tmp = pmc_read(pmc, AT91_CKGR_PLLBR) & -- ~AT91_PMC_USBDIV; -- tmp |= i << RM9200_USB_DIV_SHIFT; -- pmc_write(pmc, AT91_CKGR_PLLBR, tmp); -+ regmap_update_bits(usb->regmap, AT91_CKGR_PLLBR, -+ AT91_PMC_USBDIV, -+ i << RM9200_USB_DIV_SHIFT); -+ - return 0; - } - } -@@ -341,7 +335,7 @@ - }; - - static struct clk * __init --at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name, -+at91rm9200_clk_register_usb(struct regmap *regmap, const char *name, - const char *parent_name, const u32 *divisors) - { - struct at91rm9200_clk_usb *usb; -@@ -359,7 +353,7 @@ - init.flags = CLK_SET_RATE_PARENT; - - usb->hw.init = &init; -- usb->pmc = pmc; -+ usb->regmap = regmap; - memcpy(usb->divisors, divisors, sizeof(usb->divisors)); - - clk = clk_register(NULL, &usb->hw); -@@ -369,13 +363,13 @@ - return clk; - } - --void __init of_at91sam9x5_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_usb_setup(struct device_node *np) - { - struct clk *clk; - int num_parents; - const char *parent_names[USB_SOURCE_MAX]; - const char *name = np->name; -+ struct regmap *regmap; - - num_parents = of_clk_get_parent_count(np); - if (num_parents <= 0 || num_parents > USB_SOURCE_MAX) -@@ -385,19 +379,26 @@ - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91sam9x5_clk_register_usb(pmc, name, parent_names, num_parents); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ -+ clk = at91sam9x5_clk_register_usb(regmap, name, parent_names, -+ num_parents); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9x5_clk_usb, "atmel,at91sam9x5-clk-usb", -+ of_at91sam9x5_clk_usb_setup); - --void __init of_at91sam9n12_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91sam9n12_clk_usb_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_name; - const char *name = np->name; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - if (!parent_name) -@@ -405,20 +406,26 @@ - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91sam9n12_clk_register_usb(pmc, name, parent_name); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ -+ clk = at91sam9n12_clk_register_usb(regmap, name, parent_name); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91sam9n12_clk_usb, "atmel,at91sam9n12-clk-usb", -+ of_at91sam9n12_clk_usb_setup); - --void __init of_at91rm9200_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc) -+static void __init of_at91rm9200_clk_usb_setup(struct device_node *np) - { - struct clk *clk; - const char *parent_name; - const char *name = np->name; - u32 divisors[4] = {0, 0, 0, 0}; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - if (!parent_name) -@@ -430,9 +437,15 @@ - - of_property_read_string(np, "clock-output-names", &name); - -- clk = at91rm9200_clk_register_usb(pmc, name, parent_name, divisors); -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) -+ return; -+ -+ clk = at91rm9200_clk_register_usb(regmap, name, parent_name, divisors); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - } -+CLK_OF_DECLARE(at91rm9200_clk_usb, "atmel,at91rm9200-clk-usb", -+ of_at91rm9200_clk_usb_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c linux-4.4.28/drivers/clk/at91/clk-utmi.c ---- linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/clk-utmi.c 2016-11-01 21:26:57.940288388 +0100 -@@ -11,14 +11,9 @@ - #include - #include - #include --#include --#include - #include --#include --#include --#include --#include --#include -+#include -+#include - - #include "pmc.h" - -@@ -26,37 +21,30 @@ - - struct clk_utmi { - struct clk_hw hw; -- struct at91_pmc *pmc; -- unsigned int irq; -- wait_queue_head_t wait; -+ struct regmap *regmap; - }; - - #define to_clk_utmi(hw) container_of(hw, struct clk_utmi, hw) - --static irqreturn_t clk_utmi_irq_handler(int irq, void *dev_id) -+static inline bool clk_utmi_ready(struct regmap *regmap) - { -- struct clk_utmi *utmi = (struct clk_utmi *)dev_id; -+ unsigned int status; - -- wake_up(&utmi->wait); -- disable_irq_nosync(utmi->irq); -+ regmap_read(regmap, AT91_PMC_SR, &status); - -- return IRQ_HANDLED; -+ return status & AT91_PMC_LOCKU; - } - - static int clk_utmi_prepare(struct clk_hw *hw) - { - struct clk_utmi *utmi = to_clk_utmi(hw); -- struct at91_pmc *pmc = utmi->pmc; -- u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) | AT91_PMC_UPLLEN | -- AT91_PMC_UPLLCOUNT | AT91_PMC_BIASEN; -- -- pmc_write(pmc, AT91_CKGR_UCKR, tmp); -- -- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU)) { -- enable_irq(utmi->irq); -- wait_event(utmi->wait, -- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU); -- } -+ unsigned int uckr = AT91_PMC_UPLLEN | AT91_PMC_UPLLCOUNT | -+ AT91_PMC_BIASEN; -+ -+ regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, uckr, uckr); -+ -+ while (!clk_utmi_ready(utmi->regmap)) -+ cpu_relax(); - - return 0; - } -@@ -64,18 +52,15 @@ - static int clk_utmi_is_prepared(struct clk_hw *hw) - { - struct clk_utmi *utmi = to_clk_utmi(hw); -- struct at91_pmc *pmc = utmi->pmc; - -- return !!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU); -+ return clk_utmi_ready(utmi->regmap); - } - - static void clk_utmi_unprepare(struct clk_hw *hw) - { - struct clk_utmi *utmi = to_clk_utmi(hw); -- struct at91_pmc *pmc = utmi->pmc; -- u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) & ~AT91_PMC_UPLLEN; - -- pmc_write(pmc, AT91_CKGR_UCKR, tmp); -+ regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, AT91_PMC_UPLLEN, 0); - } - - static unsigned long clk_utmi_recalc_rate(struct clk_hw *hw, -@@ -93,10 +78,9 @@ - }; - - static struct clk * __init --at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq, -+at91_clk_register_utmi(struct regmap *regmap, - const char *name, const char *parent_name) - { -- int ret; - struct clk_utmi *utmi; - struct clk *clk = NULL; - struct clk_init_data init; -@@ -112,52 +96,36 @@ - init.flags = CLK_SET_RATE_GATE; - - utmi->hw.init = &init; -- utmi->pmc = pmc; -- utmi->irq = irq; -- init_waitqueue_head(&utmi->wait); -- irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN); -- ret = request_irq(utmi->irq, clk_utmi_irq_handler, -- IRQF_TRIGGER_HIGH, "clk-utmi", utmi); -- if (ret) { -- kfree(utmi); -- return ERR_PTR(ret); -- } -+ utmi->regmap = regmap; - - clk = clk_register(NULL, &utmi->hw); -- if (IS_ERR(clk)) { -- free_irq(utmi->irq, utmi); -+ if (IS_ERR(clk)) - kfree(utmi); -- } - - return clk; - } - --static void __init --of_at91_clk_utmi_setup(struct device_node *np, struct at91_pmc *pmc) -+static void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np) - { -- unsigned int irq; - struct clk *clk; - const char *parent_name; - const char *name = np->name; -+ struct regmap *regmap; - - parent_name = of_clk_get_parent_name(np, 0); - - of_property_read_string(np, "clock-output-names", &name); - -- irq = irq_of_parse_and_map(np, 0); -- if (!irq) -+ regmap = syscon_node_to_regmap(of_get_parent(np)); -+ if (IS_ERR(regmap)) - return; - -- clk = at91_clk_register_utmi(pmc, irq, name, parent_name); -+ clk = at91_clk_register_utmi(regmap, name, parent_name); - if (IS_ERR(clk)) - return; - - of_clk_add_provider(np, of_clk_src_simple_get, clk); - return; - } -- --void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np, -- struct at91_pmc *pmc) --{ -- of_at91_clk_utmi_setup(np, pmc); --} -+CLK_OF_DECLARE(at91sam9x5_clk_utmi, "atmel,at91sam9x5-clk-utmi", -+ of_at91sam9x5_clk_utmi_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.c linux-4.4.28/drivers/clk/at91/pmc.c ---- linux-4.4.28.orig/drivers/clk/at91/pmc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/pmc.c 2016-11-01 21:26:57.940288388 +0100 -@@ -12,36 +12,13 @@ - #include - #include - #include --#include --#include --#include --#include --#include --#include --#include -+#include -+#include - - #include - - #include "pmc.h" - --void __iomem *at91_pmc_base; --EXPORT_SYMBOL_GPL(at91_pmc_base); -- --void at91rm9200_idle(void) --{ -- /* -- * Disable the processor clock. The processor will be automatically -- * re-enabled by an interrupt or by a reset. -- */ -- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); --} -- --void at91sam9_idle(void) --{ -- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); -- cpu_do_idle(); --} -- - int of_at91_get_clk_range(struct device_node *np, const char *propname, - struct clk_range *range) - { -@@ -64,402 +41,3 @@ - return 0; - } - EXPORT_SYMBOL_GPL(of_at91_get_clk_range); -- --static void pmc_irq_mask(struct irq_data *d) --{ -- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); -- -- pmc_write(pmc, AT91_PMC_IDR, 1 << d->hwirq); --} -- --static void pmc_irq_unmask(struct irq_data *d) --{ -- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); -- -- pmc_write(pmc, AT91_PMC_IER, 1 << d->hwirq); --} -- --static int pmc_irq_set_type(struct irq_data *d, unsigned type) --{ -- if (type != IRQ_TYPE_LEVEL_HIGH) { -- pr_warn("PMC: type not supported (support only IRQ_TYPE_LEVEL_HIGH type)\n"); -- return -EINVAL; -- } -- -- return 0; --} -- --static void pmc_irq_suspend(struct irq_data *d) --{ -- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); -- -- pmc->imr = pmc_read(pmc, AT91_PMC_IMR); -- pmc_write(pmc, AT91_PMC_IDR, pmc->imr); --} -- --static void pmc_irq_resume(struct irq_data *d) --{ -- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); -- -- pmc_write(pmc, AT91_PMC_IER, pmc->imr); --} -- --static struct irq_chip pmc_irq = { -- .name = "PMC", -- .irq_disable = pmc_irq_mask, -- .irq_mask = pmc_irq_mask, -- .irq_unmask = pmc_irq_unmask, -- .irq_set_type = pmc_irq_set_type, -- .irq_suspend = pmc_irq_suspend, -- .irq_resume = pmc_irq_resume, --}; -- --static struct lock_class_key pmc_lock_class; -- --static int pmc_irq_map(struct irq_domain *h, unsigned int virq, -- irq_hw_number_t hw) --{ -- struct at91_pmc *pmc = h->host_data; -- -- irq_set_lockdep_class(virq, &pmc_lock_class); -- -- irq_set_chip_and_handler(virq, &pmc_irq, -- handle_level_irq); -- irq_set_chip_data(virq, pmc); -- -- return 0; --} -- --static int pmc_irq_domain_xlate(struct irq_domain *d, -- struct device_node *ctrlr, -- const u32 *intspec, unsigned int intsize, -- irq_hw_number_t *out_hwirq, -- unsigned int *out_type) --{ -- struct at91_pmc *pmc = d->host_data; -- const struct at91_pmc_caps *caps = pmc->caps; -- -- if (WARN_ON(intsize < 1)) -- return -EINVAL; -- -- *out_hwirq = intspec[0]; -- -- if (!(caps->available_irqs & (1 << *out_hwirq))) -- return -EINVAL; -- -- *out_type = IRQ_TYPE_LEVEL_HIGH; -- -- return 0; --} -- --static const struct irq_domain_ops pmc_irq_ops = { -- .map = pmc_irq_map, -- .xlate = pmc_irq_domain_xlate, --}; -- --static irqreturn_t pmc_irq_handler(int irq, void *data) --{ -- struct at91_pmc *pmc = (struct at91_pmc *)data; -- unsigned long sr; -- int n; -- -- sr = pmc_read(pmc, AT91_PMC_SR) & pmc_read(pmc, AT91_PMC_IMR); -- if (!sr) -- return IRQ_NONE; -- -- for_each_set_bit(n, &sr, BITS_PER_LONG) -- generic_handle_irq(irq_find_mapping(pmc->irqdomain, n)); -- -- return IRQ_HANDLED; --} -- --static const struct at91_pmc_caps at91rm9200_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | -- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | -- AT91_PMC_PCK3RDY, --}; -- --static const struct at91_pmc_caps at91sam9260_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | -- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY, --}; -- --static const struct at91_pmc_caps at91sam9g45_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | -- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY, --}; -- --static const struct at91_pmc_caps at91sam9n12_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | -- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS | -- AT91_PMC_MOSCRCS | AT91_PMC_CFDEV, --}; -- --static const struct at91_pmc_caps at91sam9x5_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | -- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS | -- AT91_PMC_MOSCRCS | AT91_PMC_CFDEV, --}; -- --static const struct at91_pmc_caps sama5d2_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | -- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | -- AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS | -- AT91_PMC_CFDEV | AT91_PMC_GCKRDY, --}; -- --static const struct at91_pmc_caps sama5d3_caps = { -- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | -- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | -- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | -- AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS | -- AT91_PMC_CFDEV, --}; -- --static struct at91_pmc *__init at91_pmc_init(struct device_node *np, -- void __iomem *regbase, int virq, -- const struct at91_pmc_caps *caps) --{ -- struct at91_pmc *pmc; -- -- if (!regbase || !virq || !caps) -- return NULL; -- -- at91_pmc_base = regbase; -- -- pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); -- if (!pmc) -- return NULL; -- -- spin_lock_init(&pmc->lock); -- pmc->regbase = regbase; -- pmc->virq = virq; -- pmc->caps = caps; -- -- pmc->irqdomain = irq_domain_add_linear(np, 32, &pmc_irq_ops, pmc); -- -- if (!pmc->irqdomain) -- goto out_free_pmc; -- -- pmc_write(pmc, AT91_PMC_IDR, 0xffffffff); -- if (request_irq(pmc->virq, pmc_irq_handler, -- IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc)) -- goto out_remove_irqdomain; -- -- return pmc; -- --out_remove_irqdomain: -- irq_domain_remove(pmc->irqdomain); --out_free_pmc: -- kfree(pmc); -- -- return NULL; --} -- --static const struct of_device_id pmc_clk_ids[] __initconst = { -- /* Slow oscillator */ -- { -- .compatible = "atmel,at91sam9260-clk-slow", -- .data = of_at91sam9260_clk_slow_setup, -- }, -- /* Main clock */ -- { -- .compatible = "atmel,at91rm9200-clk-main-osc", -- .data = of_at91rm9200_clk_main_osc_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-main-rc-osc", -- .data = of_at91sam9x5_clk_main_rc_osc_setup, -- }, -- { -- .compatible = "atmel,at91rm9200-clk-main", -- .data = of_at91rm9200_clk_main_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-main", -- .data = of_at91sam9x5_clk_main_setup, -- }, -- /* PLL clocks */ -- { -- .compatible = "atmel,at91rm9200-clk-pll", -- .data = of_at91rm9200_clk_pll_setup, -- }, -- { -- .compatible = "atmel,at91sam9g45-clk-pll", -- .data = of_at91sam9g45_clk_pll_setup, -- }, -- { -- .compatible = "atmel,at91sam9g20-clk-pllb", -- .data = of_at91sam9g20_clk_pllb_setup, -- }, -- { -- .compatible = "atmel,sama5d3-clk-pll", -- .data = of_sama5d3_clk_pll_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-plldiv", -- .data = of_at91sam9x5_clk_plldiv_setup, -- }, -- /* Master clock */ -- { -- .compatible = "atmel,at91rm9200-clk-master", -- .data = of_at91rm9200_clk_master_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-master", -- .data = of_at91sam9x5_clk_master_setup, -- }, -- /* System clocks */ -- { -- .compatible = "atmel,at91rm9200-clk-system", -- .data = of_at91rm9200_clk_sys_setup, -- }, -- /* Peripheral clocks */ -- { -- .compatible = "atmel,at91rm9200-clk-peripheral", -- .data = of_at91rm9200_clk_periph_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-peripheral", -- .data = of_at91sam9x5_clk_periph_setup, -- }, -- /* Programmable clocks */ -- { -- .compatible = "atmel,at91rm9200-clk-programmable", -- .data = of_at91rm9200_clk_prog_setup, -- }, -- { -- .compatible = "atmel,at91sam9g45-clk-programmable", -- .data = of_at91sam9g45_clk_prog_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-programmable", -- .data = of_at91sam9x5_clk_prog_setup, -- }, -- /* UTMI clock */ --#if defined(CONFIG_HAVE_AT91_UTMI) -- { -- .compatible = "atmel,at91sam9x5-clk-utmi", -- .data = of_at91sam9x5_clk_utmi_setup, -- }, --#endif -- /* USB clock */ --#if defined(CONFIG_HAVE_AT91_USB_CLK) -- { -- .compatible = "atmel,at91rm9200-clk-usb", -- .data = of_at91rm9200_clk_usb_setup, -- }, -- { -- .compatible = "atmel,at91sam9x5-clk-usb", -- .data = of_at91sam9x5_clk_usb_setup, -- }, -- { -- .compatible = "atmel,at91sam9n12-clk-usb", -- .data = of_at91sam9n12_clk_usb_setup, -- }, --#endif -- /* SMD clock */ --#if defined(CONFIG_HAVE_AT91_SMD) -- { -- .compatible = "atmel,at91sam9x5-clk-smd", -- .data = of_at91sam9x5_clk_smd_setup, -- }, --#endif --#if defined(CONFIG_HAVE_AT91_H32MX) -- { -- .compatible = "atmel,sama5d4-clk-h32mx", -- .data = of_sama5d4_clk_h32mx_setup, -- }, --#endif --#if defined(CONFIG_HAVE_AT91_GENERATED_CLK) -- { -- .compatible = "atmel,sama5d2-clk-generated", -- .data = of_sama5d2_clk_generated_setup, -- }, --#endif -- { /*sentinel*/ } --}; -- --static void __init of_at91_pmc_setup(struct device_node *np, -- const struct at91_pmc_caps *caps) --{ -- struct at91_pmc *pmc; -- struct device_node *childnp; -- void (*clk_setup)(struct device_node *, struct at91_pmc *); -- const struct of_device_id *clk_id; -- void __iomem *regbase = of_iomap(np, 0); -- int virq; -- -- if (!regbase) -- return; -- -- virq = irq_of_parse_and_map(np, 0); -- if (!virq) -- return; -- -- pmc = at91_pmc_init(np, regbase, virq, caps); -- if (!pmc) -- return; -- for_each_child_of_node(np, childnp) { -- clk_id = of_match_node(pmc_clk_ids, childnp); -- if (!clk_id) -- continue; -- clk_setup = clk_id->data; -- clk_setup(childnp, pmc); -- } --} -- --static void __init of_at91rm9200_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &at91rm9200_caps); --} --CLK_OF_DECLARE(at91rm9200_clk_pmc, "atmel,at91rm9200-pmc", -- of_at91rm9200_pmc_setup); -- --static void __init of_at91sam9260_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &at91sam9260_caps); --} --CLK_OF_DECLARE(at91sam9260_clk_pmc, "atmel,at91sam9260-pmc", -- of_at91sam9260_pmc_setup); -- --static void __init of_at91sam9g45_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &at91sam9g45_caps); --} --CLK_OF_DECLARE(at91sam9g45_clk_pmc, "atmel,at91sam9g45-pmc", -- of_at91sam9g45_pmc_setup); -- --static void __init of_at91sam9n12_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &at91sam9n12_caps); --} --CLK_OF_DECLARE(at91sam9n12_clk_pmc, "atmel,at91sam9n12-pmc", -- of_at91sam9n12_pmc_setup); -- --static void __init of_at91sam9x5_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &at91sam9x5_caps); --} --CLK_OF_DECLARE(at91sam9x5_clk_pmc, "atmel,at91sam9x5-pmc", -- of_at91sam9x5_pmc_setup); -- --static void __init of_sama5d2_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &sama5d2_caps); --} --CLK_OF_DECLARE(sama5d2_clk_pmc, "atmel,sama5d2-pmc", -- of_sama5d2_pmc_setup); -- --static void __init of_sama5d3_pmc_setup(struct device_node *np) --{ -- of_at91_pmc_setup(np, &sama5d3_caps); --} --CLK_OF_DECLARE(sama5d3_clk_pmc, "atmel,sama5d3-pmc", -- of_sama5d3_pmc_setup); -diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.h linux-4.4.28/drivers/clk/at91/pmc.h ---- linux-4.4.28.orig/drivers/clk/at91/pmc.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clk/at91/pmc.h 2016-11-01 21:26:57.944288652 +0100 -@@ -14,8 +14,11 @@ - - #include - #include -+#include - #include - -+extern spinlock_t pmc_pcr_lock; -+ - struct clk_range { - unsigned long min; - unsigned long max; -@@ -23,102 +26,7 @@ - - #define CLK_RANGE(MIN, MAX) {.min = MIN, .max = MAX,} - --struct at91_pmc_caps { -- u32 available_irqs; --}; -- --struct at91_pmc { -- void __iomem *regbase; -- int virq; -- spinlock_t lock; -- const struct at91_pmc_caps *caps; -- struct irq_domain *irqdomain; -- u32 imr; --}; -- --static inline void pmc_lock(struct at91_pmc *pmc) --{ -- spin_lock(&pmc->lock); --} -- --static inline void pmc_unlock(struct at91_pmc *pmc) --{ -- spin_unlock(&pmc->lock); --} -- --static inline u32 pmc_read(struct at91_pmc *pmc, int offset) --{ -- return readl(pmc->regbase + offset); --} -- --static inline void pmc_write(struct at91_pmc *pmc, int offset, u32 value) --{ -- writel(value, pmc->regbase + offset); --} -- - int of_at91_get_clk_range(struct device_node *np, const char *propname, - struct clk_range *range); - --void of_at91sam9260_clk_slow_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_main_osc_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91rm9200_clk_main_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_main_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9g45_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9g20_clk_pllb_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_sama5d3_clk_pll_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_plldiv_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_master_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_master_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_sys_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_periph_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_periph_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9g45_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_prog_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91sam9x5_clk_utmi_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91rm9200_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9x5_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc); --void of_at91sam9n12_clk_usb_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_at91sam9x5_clk_smd_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_sama5d4_clk_h32mx_setup(struct device_node *np, -- struct at91_pmc *pmc); -- --void of_sama5d2_clk_generated_setup(struct device_node *np, -- struct at91_pmc *pmc); -- - #endif /* __PMC_H_ */ -diff -Nur linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c linux-4.4.28/drivers/clocksource/tcb_clksrc.c ---- linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clocksource/tcb_clksrc.c 2016-11-01 21:26:57.948288905 +0100 -@@ -23,8 +23,7 @@ - * this 32 bit free-running counter. the second channel is not used. - * - * - The third channel may be used to provide a 16-bit clockevent -- * source, used in either periodic or oneshot mode. This runs -- * at 32 KiHZ, and can handle delays of up to two seconds. -+ * source, used in either periodic or oneshot mode. - * - * A boot clocksource and clockevent source are also currently needed, - * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so -@@ -74,6 +73,8 @@ - struct tc_clkevt_device { - struct clock_event_device clkevt; - struct clk *clk; -+ bool clk_enabled; -+ u32 freq; - void __iomem *regs; - }; - -@@ -82,15 +83,26 @@ - return container_of(clkevt, struct tc_clkevt_device, clkevt); - } - --/* For now, we always use the 32K clock ... this optimizes for NO_HZ, -- * because using one of the divided clocks would usually mean the -- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). -- * -- * A divided clock could be good for high resolution timers, since -- * 30.5 usec resolution can seem "low". -- */ - static u32 timer_clock; - -+static void tc_clk_disable(struct clock_event_device *d) -+{ -+ struct tc_clkevt_device *tcd = to_tc_clkevt(d); -+ -+ clk_disable(tcd->clk); -+ tcd->clk_enabled = false; -+} -+ -+static void tc_clk_enable(struct clock_event_device *d) -+{ -+ struct tc_clkevt_device *tcd = to_tc_clkevt(d); -+ -+ if (tcd->clk_enabled) -+ return; -+ clk_enable(tcd->clk); -+ tcd->clk_enabled = true; -+} -+ - static int tc_shutdown(struct clock_event_device *d) - { - struct tc_clkevt_device *tcd = to_tc_clkevt(d); -@@ -98,8 +110,14 @@ - - __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); - __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); -+ return 0; -+} -+ -+static int tc_shutdown_clk_off(struct clock_event_device *d) -+{ -+ tc_shutdown(d); - if (!clockevent_state_detached(d)) -- clk_disable(tcd->clk); -+ tc_clk_disable(d); - - return 0; - } -@@ -112,9 +130,9 @@ - if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) - tc_shutdown(d); - -- clk_enable(tcd->clk); -+ tc_clk_enable(d); - -- /* slow clock, count up to RC, then irq and stop */ -+ /* count up to RC, then irq and stop */ - __raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | - ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); - __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); -@@ -134,12 +152,12 @@ - /* By not making the gentime core emulate periodic mode on top - * of oneshot, we get lower overhead and improved accuracy. - */ -- clk_enable(tcd->clk); -+ tc_clk_enable(d); - -- /* slow clock, count up to RC, then irq and restart */ -+ /* count up to RC, then irq and restart */ - __raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, - regs + ATMEL_TC_REG(2, CMR)); -- __raw_writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); -+ __raw_writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); - - /* Enable clock and interrupts on RC compare */ - __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); -@@ -166,9 +184,13 @@ - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT, - /* Should be lower than at91rm9200's system timer */ -+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK - .rating = 125, -+#else -+ .rating = 200, -+#endif - .set_next_event = tc_next_event, -- .set_state_shutdown = tc_shutdown, -+ .set_state_shutdown = tc_shutdown_clk_off, - .set_state_periodic = tc_set_periodic, - .set_state_oneshot = tc_set_oneshot, - }, -@@ -188,8 +210,9 @@ - return IRQ_NONE; - } - --static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) -+static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) - { -+ unsigned divisor = atmel_tc_divisors[divisor_idx]; - int ret; - struct clk *t2_clk = tc->clk[2]; - int irq = tc->irq[2]; -@@ -210,7 +233,11 @@ - clkevt.regs = tc->regs; - clkevt.clk = t2_clk; - -- timer_clock = clk32k_divisor_idx; -+ timer_clock = divisor_idx; -+ if (!divisor) -+ clkevt.freq = 32768; -+ else -+ clkevt.freq = clk_get_rate(t2_clk) / divisor; - - clkevt.clkevt.cpumask = cpumask_of(0); - -@@ -221,7 +248,7 @@ - return ret; - } - -- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); -+ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); - - return ret; - } -@@ -358,7 +385,11 @@ - goto err_disable_t1; - - /* channel 2: periodic and oneshot timer support */ -+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK - ret = setup_clkevents(tc, clk32k_divisor_idx); -+#else -+ ret = setup_clkevents(tc, best_divisor_idx); -+#endif - if (ret) - goto err_unregister_clksrc; - -diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c linux-4.4.28/drivers/clocksource/timer-atmel-pit.c ---- linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clocksource/timer-atmel-pit.c 2016-11-01 21:26:57.952289162 +0100 -@@ -46,6 +46,7 @@ - u32 cycle; - u32 cnt; - unsigned int irq; -+ bool irq_requested; - struct clk *mck; - }; - -@@ -96,15 +97,29 @@ - - /* disable irq, leaving the clocksource active */ - pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN); -+ if (data->irq_requested) { -+ free_irq(data->irq, data); -+ data->irq_requested = false; -+ } - return 0; - } - -+static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id); - /* - * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) - */ - static int pit_clkevt_set_periodic(struct clock_event_device *dev) - { - struct pit_data *data = clkevt_to_pit_data(dev); -+ int ret; -+ -+ ret = request_irq(data->irq, at91sam926x_pit_interrupt, -+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, -+ "at91_tick", data); -+ if (ret) -+ panic(pr_fmt("Unable to setup IRQ\n")); -+ -+ data->irq_requested = true; - - /* update clocksource counter */ - data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR)); -@@ -181,7 +196,6 @@ - { - unsigned long pit_rate; - unsigned bits; -- int ret; - - /* - * Use our actual MCK to figure out how many MCK/16 ticks per -@@ -206,13 +220,6 @@ - data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; - clocksource_register_hz(&data->clksrc, pit_rate); - -- /* Set up irq handler */ -- ret = request_irq(data->irq, at91sam926x_pit_interrupt, -- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, -- "at91_tick", data); -- if (ret) -- panic(pr_fmt("Unable to setup IRQ\n")); -- - /* Set up and register clockevents */ - data->clkevt.name = "pit"; - data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC; -diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c linux-4.4.28/drivers/clocksource/timer-atmel-st.c ---- linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/clocksource/timer-atmel-st.c 2016-11-01 21:26:57.952289162 +0100 -@@ -115,18 +115,29 @@ - last_crtr = read_CRTR(); - } - -+static int atmel_st_irq; -+ - static int clkevt32k_shutdown(struct clock_event_device *evt) - { - clkdev32k_disable_and_flush_irq(); - irqmask = 0; - regmap_write(regmap_st, AT91_ST_IER, irqmask); -+ free_irq(atmel_st_irq, regmap_st); - return 0; - } - - static int clkevt32k_set_oneshot(struct clock_event_device *dev) - { -+ int ret; -+ - clkdev32k_disable_and_flush_irq(); - -+ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt, -+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, -+ "at91_tick", regmap_st); -+ if (ret) -+ panic(pr_fmt("Unable to setup IRQ\n")); -+ - /* - * ALM for oneshot irqs, set by next_event() - * before 32 seconds have passed. -@@ -139,8 +150,16 @@ - - static int clkevt32k_set_periodic(struct clock_event_device *dev) - { -+ int ret; -+ - clkdev32k_disable_and_flush_irq(); - -+ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt, -+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, -+ "at91_tick", regmap_st); -+ if (ret) -+ panic(pr_fmt("Unable to setup IRQ\n")); -+ - /* PIT for periodic irqs; fixed rate of 1/HZ */ - irqmask = AT91_ST_PITS; - regmap_write(regmap_st, AT91_ST_PIMR, timer_latch); -@@ -198,7 +217,7 @@ - { - struct clk *sclk; - unsigned int sclk_rate, val; -- int irq, ret; -+ int ret; - - regmap_st = syscon_node_to_regmap(node); - if (IS_ERR(regmap_st)) -@@ -210,17 +229,10 @@ - regmap_read(regmap_st, AT91_ST_SR, &val); - - /* Get the interrupts property */ -- irq = irq_of_parse_and_map(node, 0); -- if (!irq) -+ atmel_st_irq = irq_of_parse_and_map(node, 0); -+ if (!atmel_st_irq) - panic(pr_fmt("Unable to get IRQ from DT\n")); - -- /* Make IRQs happen for the system timer */ -- ret = request_irq(irq, at91rm9200_timer_interrupt, -- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, -- "at91_tick", regmap_st); -- if (ret) -- panic(pr_fmt("Unable to setup IRQ\n")); -- - sclk = of_clk_get(node, 0); - if (IS_ERR(sclk)) - panic(pr_fmt("Unable to get slow clock\n")); -diff -Nur linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 linux-4.4.28/drivers/cpufreq/Kconfig.x86 ---- linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/cpufreq/Kconfig.x86 2016-11-01 21:26:57.956289426 +0100 -@@ -123,7 +123,7 @@ - - config X86_POWERNOW_K8 - tristate "AMD Opteron/Athlon64 PowerNow!" -- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ -+ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE - help - This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. - Support for K10 and newer processors is now in acpi-cpufreq. -diff -Nur linux-4.4.28.orig/drivers/cpuidle/coupled.c linux-4.4.28/drivers/cpuidle/coupled.c ---- linux-4.4.28.orig/drivers/cpuidle/coupled.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/cpuidle/coupled.c 2016-11-01 21:26:57.960289679 +0100 -@@ -119,7 +119,6 @@ - - #define CPUIDLE_COUPLED_NOT_IDLE (-1) - --static DEFINE_MUTEX(cpuidle_coupled_lock); - static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); - - /* -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c ---- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-11-01 21:26:57.980290973 +0100 -@@ -1264,7 +1264,9 @@ - if (ret) - return ret; - -+#ifndef CONFIG_PREEMPT_RT_BASE - trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags); -+#endif - - i915_gem_execbuffer_move_to_active(vmas, params->request); - i915_gem_execbuffer_retire_commands(params); -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c ---- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-11-01 21:26:57.984291226 +0100 -@@ -39,7 +39,7 @@ - if (!mutex_is_locked(mutex)) - return false; - --#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) -+#if (defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)) && !defined(CONFIG_PREEMPT_RT_BASE) - return mutex->owner == task; - #else - /* Since UP may be pre-empted, we cannot assume that we own the lock */ -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c ---- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c 2016-11-01 21:26:58.000292256 +0100 -@@ -812,6 +812,7 @@ - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - - /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ -+ preempt_disable_rt(); - - /* Get optional system timestamp before query. */ - if (stime) -@@ -863,6 +864,7 @@ - *etime = ktime_get(); - - /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ -+ preempt_enable_rt(); - - spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); - -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c linux-4.4.28/drivers/gpu/drm/i915/intel_display.c ---- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/i915/intel_display.c 2016-11-01 21:26:58.040294841 +0100 -@@ -11400,7 +11400,7 @@ - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_unpin_work *work; - -- WARN_ON(!in_interrupt()); -+ WARN_ON_NONRT(!in_interrupt()); - - if (crtc == NULL) - return; -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c ---- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c 2016-11-01 21:26:58.056295867 +0100 -@@ -38,6 +38,7 @@ - #include "intel_drv.h" - #include - #include "i915_drv.h" -+#include - - static bool - format_is_yuv(uint32_t format) -@@ -64,6 +65,8 @@ - 1000 * adjusted_mode->crtc_htotal); - } - -+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); -+ - /** - * intel_pipe_update_start() - start update of a set of display registers - * @crtc: the crtc of which the registers are going to be updated -@@ -96,7 +99,7 @@ - min = vblank_start - usecs_to_scanlines(adjusted_mode, 100); - max = vblank_start - 1; - -- local_irq_disable(); -+ local_lock_irq(pipe_update_lock); - - if (min <= 0 || max <= 0) - return; -@@ -126,11 +129,11 @@ - break; - } - -- local_irq_enable(); -+ local_unlock_irq(pipe_update_lock); - - timeout = schedule_timeout(timeout); - -- local_irq_disable(); -+ local_lock_irq(pipe_update_lock); - } - - finish_wait(wq, &wait); -@@ -164,7 +167,7 @@ - - trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end); - -- local_irq_enable(); -+ local_unlock_irq(pipe_update_lock); - - if (crtc->debug.start_vbl_count && - crtc->debug.start_vbl_count != end_vbl_count) { -diff -Nur linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c ---- linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c 2016-11-01 21:26:58.068296641 +0100 -@@ -1862,6 +1862,7 @@ - struct radeon_device *rdev = dev->dev_private; - - /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ -+ preempt_disable_rt(); - - /* Get optional system timestamp before query. */ - if (stime) -@@ -1954,6 +1955,7 @@ - *etime = ktime_get(); - - /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ -+ preempt_enable_rt(); - - /* Decode into vertical and horizontal scanout position. */ - *vpos = position & 0x1fff; -diff -Nur linux-4.4.28.orig/drivers/hv/vmbus_drv.c linux-4.4.28/drivers/hv/vmbus_drv.c ---- linux-4.4.28.orig/drivers/hv/vmbus_drv.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/hv/vmbus_drv.c 2016-11-01 21:26:58.080297414 +0100 -@@ -820,7 +820,7 @@ - tasklet_schedule(&msg_dpc); - } - -- add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0); -+ add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0); - } - - -diff -Nur linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c linux-4.4.28/drivers/i2c/busses/i2c-omap.c ---- linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/i2c/busses/i2c-omap.c 2016-11-01 21:26:58.088297935 +0100 -@@ -995,15 +995,12 @@ - u16 mask; - u16 stat; - -- spin_lock(&omap->lock); -- mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); - stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG); -+ mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); - - if (stat & mask) - ret = IRQ_WAKE_THREAD; - -- spin_unlock(&omap->lock); -- - return ret; - } - -diff -Nur linux-4.4.28.orig/drivers/ide/alim15x3.c linux-4.4.28/drivers/ide/alim15x3.c ---- linux-4.4.28.orig/drivers/ide/alim15x3.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/alim15x3.c 2016-11-01 21:26:58.096298444 +0100 -@@ -234,7 +234,7 @@ - - isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL); - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - - if (m5229_revision < 0xC2) { - /* -@@ -325,7 +325,7 @@ - } - pci_dev_put(north); - pci_dev_put(isa_dev); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - return 0; - } - -diff -Nur linux-4.4.28.orig/drivers/ide/hpt366.c linux-4.4.28/drivers/ide/hpt366.c ---- linux-4.4.28.orig/drivers/ide/hpt366.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/hpt366.c 2016-11-01 21:26:58.100298709 +0100 -@@ -1241,7 +1241,7 @@ - - dma_old = inb(base + 2); - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - - dma_new = dma_old; - pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); -@@ -1252,7 +1252,7 @@ - if (dma_new != dma_old) - outb(dma_new, base + 2); - -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n", - hwif->name, base, base + 7); -diff -Nur linux-4.4.28.orig/drivers/ide/ide-io.c linux-4.4.28/drivers/ide/ide-io.c ---- linux-4.4.28.orig/drivers/ide/ide-io.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/ide-io.c 2016-11-01 21:26:58.108299218 +0100 -@@ -659,7 +659,7 @@ - /* disable_irq_nosync ?? */ - disable_irq(hwif->irq); - /* local CPU only, as if we were handling an interrupt */ -- local_irq_disable(); -+ local_irq_disable_nort(); - if (hwif->polling) { - startstop = handler(drive); - } else if (drive_is_ready(drive)) { -diff -Nur linux-4.4.28.orig/drivers/ide/ide-iops.c linux-4.4.28/drivers/ide/ide-iops.c ---- linux-4.4.28.orig/drivers/ide/ide-iops.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/ide-iops.c 2016-11-01 21:26:58.108299218 +0100 -@@ -129,12 +129,12 @@ - if ((stat & ATA_BUSY) == 0) - break; - -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - *rstat = stat; - return -EBUSY; - } - } -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - /* - * Allow status to settle, then read it again. -diff -Nur linux-4.4.28.orig/drivers/ide/ide-io-std.c linux-4.4.28/drivers/ide/ide-io-std.c ---- linux-4.4.28.orig/drivers/ide/ide-io-std.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/ide-io-std.c 2016-11-01 21:26:58.104298962 +0100 -@@ -175,7 +175,7 @@ - unsigned long uninitialized_var(flags); - - if ((io_32bit & 2) && !mmio) { -- local_irq_save(flags); -+ local_irq_save_nort(flags); - ata_vlb_sync(io_ports->nsect_addr); - } - -@@ -186,7 +186,7 @@ - insl(data_addr, buf, words); - - if ((io_32bit & 2) && !mmio) -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - if (((len + 1) & 3) < 2) - return; -@@ -219,7 +219,7 @@ - unsigned long uninitialized_var(flags); - - if ((io_32bit & 2) && !mmio) { -- local_irq_save(flags); -+ local_irq_save_nort(flags); - ata_vlb_sync(io_ports->nsect_addr); - } - -@@ -230,7 +230,7 @@ - outsl(data_addr, buf, words); - - if ((io_32bit & 2) && !mmio) -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - if (((len + 1) & 3) < 2) - return; -diff -Nur linux-4.4.28.orig/drivers/ide/ide-probe.c linux-4.4.28/drivers/ide/ide-probe.c ---- linux-4.4.28.orig/drivers/ide/ide-probe.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/ide-probe.c 2016-11-01 21:26:58.116299735 +0100 -@@ -196,10 +196,10 @@ - int bswap = 1; - - /* local CPU only; some systems need this */ -- local_irq_save(flags); -+ local_irq_save_nort(flags); - /* read 512 bytes of id info */ - hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - drive->dev_flags |= IDE_DFLAG_ID_READ; - #ifdef DEBUG -diff -Nur linux-4.4.28.orig/drivers/ide/ide-taskfile.c linux-4.4.28/drivers/ide/ide-taskfile.c ---- linux-4.4.28.orig/drivers/ide/ide-taskfile.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/ide/ide-taskfile.c 2016-11-01 21:26:58.116299735 +0100 -@@ -250,7 +250,7 @@ - - page_is_high = PageHighMem(page); - if (page_is_high) -- local_irq_save(flags); -+ local_irq_save_nort(flags); - - buf = kmap_atomic(page) + offset; - -@@ -271,7 +271,7 @@ - kunmap_atomic(buf); - - if (page_is_high) -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - len -= nr_bytes; - } -@@ -414,7 +414,7 @@ - } - - if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0) -- local_irq_disable(); -+ local_irq_disable_nort(); - - ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE); - -diff -Nur linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c ---- linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-11-01 21:26:58.124300256 +0100 -@@ -857,7 +857,7 @@ - - ipoib_dbg_mcast(priv, "restarting multicast task\n"); - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - netif_addr_lock(dev); - spin_lock(&priv->lock); - -@@ -939,7 +939,7 @@ - - spin_unlock(&priv->lock); - netif_addr_unlock(dev); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - /* - * make sure the in-flight joins have finished before we attempt -diff -Nur linux-4.4.28.orig/drivers/input/gameport/gameport.c linux-4.4.28/drivers/input/gameport/gameport.c ---- linux-4.4.28.orig/drivers/input/gameport/gameport.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/input/gameport/gameport.c 2016-11-01 21:26:58.132300765 +0100 -@@ -91,13 +91,13 @@ - tx = ~0; - - for (i = 0; i < 50; i++) { -- local_irq_save(flags); -+ local_irq_save_nort(flags); - t1 = ktime_get_ns(); - for (t = 0; t < 50; t++) - gameport_read(gameport); - t2 = ktime_get_ns(); - t3 = ktime_get_ns(); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - udelay(i * 10); - t = (t2 - t1) - (t3 - t2); - if (t < tx) -@@ -124,12 +124,12 @@ - tx = 1 << 30; - - for(i = 0; i < 50; i++) { -- local_irq_save(flags); -+ local_irq_save_nort(flags); - GET_TIME(t1); - for (t = 0; t < 50; t++) gameport_read(gameport); - GET_TIME(t2); - GET_TIME(t3); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - udelay(i * 10); - if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; - } -@@ -148,11 +148,11 @@ - tx = 1 << 30; - - for(i = 0; i < 50; i++) { -- local_irq_save(flags); -+ local_irq_save_nort(flags); - t1 = rdtsc(); - for (t = 0; t < 50; t++) gameport_read(gameport); - t2 = rdtsc(); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - udelay(i * 10); - if (t2 - t1 < tx) tx = t2 - t1; - } -diff -Nur linux-4.4.28.orig/drivers/iommu/amd_iommu.c linux-4.4.28/drivers/iommu/amd_iommu.c ---- linux-4.4.28.orig/drivers/iommu/amd_iommu.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/iommu/amd_iommu.c 2016-11-01 21:26:58.156302312 +0100 -@@ -2019,10 +2019,10 @@ - int ret; - - /* -- * Must be called with IRQs disabled. Warn here to detect early -- * when its not. -+ * Must be called with IRQs disabled on a non RT kernel. Warn here to -+ * detect early when its not. - */ -- WARN_ON(!irqs_disabled()); -+ WARN_ON_NONRT(!irqs_disabled()); - - /* lock domain */ - spin_lock(&domain->lock); -@@ -2185,10 +2185,10 @@ - struct protection_domain *domain; - - /* -- * Must be called with IRQs disabled. Warn here to detect early -- * when its not. -+ * Must be called with IRQs disabled on a non RT kernel. Warn here to -+ * detect early when its not. - */ -- WARN_ON(!irqs_disabled()); -+ WARN_ON_NONRT(!irqs_disabled()); - - if (WARN_ON(!dev_data->domain)) - return; -diff -Nur linux-4.4.28.orig/drivers/leds/trigger/Kconfig linux-4.4.28/drivers/leds/trigger/Kconfig ---- linux-4.4.28.orig/drivers/leds/trigger/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/leds/trigger/Kconfig 2016-11-01 21:26:58.168303087 +0100 -@@ -61,7 +61,7 @@ - - config LEDS_TRIGGER_CPU - bool "LED CPU Trigger" -- depends on LEDS_TRIGGERS -+ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE - help - This allows LEDs to be controlled by active CPUs. This shows - the active CPUs across an array of LEDs so you can see which -diff -Nur linux-4.4.28.orig/drivers/md/bcache/Kconfig linux-4.4.28/drivers/md/bcache/Kconfig ---- linux-4.4.28.orig/drivers/md/bcache/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/md/bcache/Kconfig 2016-11-01 21:26:58.172303343 +0100 -@@ -1,6 +1,7 @@ - - config BCACHE - tristate "Block device as cache" -+ depends on !PREEMPT_RT_FULL - ---help--- - Allows a block device to be used as cache for other devices; uses - a btree for indexing and the layout is optimized for SSDs. -diff -Nur linux-4.4.28.orig/drivers/md/dm.c linux-4.4.28/drivers/md/dm.c ---- linux-4.4.28.orig/drivers/md/dm.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/md/dm.c 2016-11-01 21:26:58.196304892 +0100 -@@ -2127,7 +2127,7 @@ - /* Establish tio->ti before queuing work (map_tio_request) */ - tio->ti = ti; - queue_kthread_work(&md->kworker, &tio->work); -- BUG_ON(!irqs_disabled()); -+ BUG_ON_NONRT(!irqs_disabled()); - } - - goto out; -diff -Nur linux-4.4.28.orig/drivers/md/raid5.c linux-4.4.28/drivers/md/raid5.c ---- linux-4.4.28.orig/drivers/md/raid5.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/md/raid5.c 2016-11-01 21:26:58.224306697 +0100 -@@ -1920,8 +1920,9 @@ - struct raid5_percpu *percpu; - unsigned long cpu; - -- cpu = get_cpu(); -+ cpu = get_cpu_light(); - percpu = per_cpu_ptr(conf->percpu, cpu); -+ spin_lock(&percpu->lock); - if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { - ops_run_biofill(sh); - overlap_clear++; -@@ -1977,7 +1978,8 @@ - if (test_and_clear_bit(R5_Overlap, &dev->flags)) - wake_up(&sh->raid_conf->wait_for_overlap); - } -- put_cpu(); -+ spin_unlock(&percpu->lock); -+ put_cpu_light(); - } - - static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) -@@ -6414,6 +6416,7 @@ - __func__, cpu); - break; - } -+ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); - } - put_online_cpus(); - -diff -Nur linux-4.4.28.orig/drivers/md/raid5.h linux-4.4.28/drivers/md/raid5.h ---- linux-4.4.28.orig/drivers/md/raid5.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/md/raid5.h 2016-11-01 21:26:58.236307469 +0100 -@@ -504,6 +504,7 @@ - int recovery_disabled; - /* per cpu variables */ - struct raid5_percpu { -+ spinlock_t lock; /* Protection for -RT */ - struct page *spare_page; /* Used when checking P/Q in raid6 */ - struct flex_array *scribble; /* space for constructing buffer - * lists and performing address -diff -Nur linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c ---- linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c 2016-11-01 21:26:58.244307986 +0100 -@@ -520,7 +520,7 @@ - bool stopped; - - spin_lock_irqsave(&pipe->irqlock, flags); -- stopped = pipe->state == VSP1_PIPELINE_STOPPED, -+ stopped = pipe->state == VSP1_PIPELINE_STOPPED; - spin_unlock_irqrestore(&pipe->irqlock, flags); - - return stopped; -diff -Nur linux-4.4.28.orig/drivers/misc/hwlat_detector.c linux-4.4.28/drivers/misc/hwlat_detector.c ---- linux-4.4.28.orig/drivers/misc/hwlat_detector.c 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/drivers/misc/hwlat_detector.c 2016-11-01 21:26:58.256308759 +0100 -@@ -0,0 +1,1240 @@ -+/* -+ * hwlat_detector.c - A simple Hardware Latency detector. -+ * -+ * Use this module to detect large system latencies induced by the behavior of -+ * certain underlying system hardware or firmware, independent of Linux itself. -+ * The code was developed originally to detect the presence of SMIs on Intel -+ * and AMD systems, although there is no dependency upon x86 herein. -+ * -+ * The classical example usage of this module is in detecting the presence of -+ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a -+ * somewhat special form of hardware interrupt spawned from earlier CPU debug -+ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge -+ * LPC (or other device) to generate a special interrupt under certain -+ * circumstances, for example, upon expiration of a special SMI timer device, -+ * due to certain external thermal readings, on certain I/O address accesses, -+ * and other situations. An SMI hits a special CPU pin, triggers a special -+ * SMI mode (complete with special memory map), and the OS is unaware. -+ * -+ * Although certain hardware-inducing latencies are necessary (for example, -+ * a modern system often requires an SMI handler for correct thermal control -+ * and remote management) they can wreak havoc upon any OS-level performance -+ * guarantees toward low-latency, especially when the OS is not even made -+ * aware of the presence of these interrupts. For this reason, we need a -+ * somewhat brute force mechanism to detect these interrupts. In this case, -+ * we do it by hogging all of the CPU(s) for configurable timer intervals, -+ * sampling the built-in CPU timer, looking for discontiguous readings. -+ * -+ * WARNING: This implementation necessarily introduces latencies. Therefore, -+ * you should NEVER use this module in a production environment -+ * requiring any kind of low-latency performance guarantee(s). -+ * -+ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. -+ * -+ * Includes useful feedback from Clark Williams -+ * -+ * This file is licensed under the terms of the GNU General Public -+ * License version 2. This program is licensed "as is" without any -+ * warranty of any kind, whether express or implied. -+ */ -+ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ -+#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ -+#define U64STR_SIZE 22 /* 20 digits max */ -+ -+#define VERSION "1.0.0" -+#define BANNER "hwlat_detector: " -+#define DRVNAME "hwlat_detector" -+#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ -+#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ -+#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ -+ -+/* Module metadata */ -+ -+MODULE_LICENSE("GPL"); -+MODULE_AUTHOR("Jon Masters "); -+MODULE_DESCRIPTION("A simple hardware latency detector"); -+MODULE_VERSION(VERSION); -+ -+/* Module parameters */ -+ -+static int debug; -+static int enabled; -+static int threshold; -+ -+module_param(debug, int, 0); /* enable debug */ -+module_param(enabled, int, 0); /* enable detector */ -+module_param(threshold, int, 0); /* latency threshold */ -+ -+/* Buffering and sampling */ -+ -+static struct ring_buffer *ring_buffer; /* sample buffer */ -+static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */ -+static unsigned long buf_size = BUF_SIZE_DEFAULT; -+static struct task_struct *kthread; /* sampling thread */ -+ -+/* DebugFS filesystem entries */ -+ -+static struct dentry *debug_dir; /* debugfs directory */ -+static struct dentry *debug_max; /* maximum TSC delta */ -+static struct dentry *debug_count; /* total detect count */ -+static struct dentry *debug_sample_width; /* sample width us */ -+static struct dentry *debug_sample_window; /* sample window us */ -+static struct dentry *debug_sample; /* raw samples us */ -+static struct dentry *debug_threshold; /* threshold us */ -+static struct dentry *debug_enable; /* enable/disable */ -+ -+/* Individual samples and global state */ -+ -+struct sample; /* latency sample */ -+struct data; /* Global state */ -+ -+/* Sampling functions */ -+static int __buffer_add_sample(struct sample *sample); -+static struct sample *buffer_get_sample(struct sample *sample); -+ -+/* Threading and state */ -+static int kthread_fn(void *unused); -+static int start_kthread(void); -+static int stop_kthread(void); -+static void __reset_stats(void); -+static int init_stats(void); -+ -+/* Debugfs interface */ -+static ssize_t simple_data_read(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos, const u64 *entry); -+static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, -+ size_t cnt, loff_t *ppos, u64 *entry); -+static int debug_sample_fopen(struct inode *inode, struct file *filp); -+static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos); -+static int debug_sample_release(struct inode *inode, struct file *filp); -+static int debug_enable_fopen(struct inode *inode, struct file *filp); -+static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos); -+static ssize_t debug_enable_fwrite(struct file *file, -+ const char __user *user_buffer, -+ size_t user_size, loff_t *offset); -+ -+/* Initialization functions */ -+static int init_debugfs(void); -+static void free_debugfs(void); -+static int detector_init(void); -+static void detector_exit(void); -+ -+/* Individual latency samples are stored here when detected and packed into -+ * the ring_buffer circular buffer, where they are overwritten when -+ * more than buf_size/sizeof(sample) samples are received. */ -+struct sample { -+ u64 seqnum; /* unique sequence */ -+ u64 duration; /* ktime delta */ -+ u64 outer_duration; /* ktime delta (outer loop) */ -+ struct timespec timestamp; /* wall time */ -+ unsigned long lost; -+}; -+ -+/* keep the global state somewhere. */ -+static struct data { -+ -+ struct mutex lock; /* protect changes */ -+ -+ u64 count; /* total since reset */ -+ u64 max_sample; /* max hardware latency */ -+ u64 threshold; /* sample threshold level */ -+ -+ u64 sample_window; /* total sampling window (on+off) */ -+ u64 sample_width; /* active sampling portion of window */ -+ -+ atomic_t sample_open; /* whether the sample file is open */ -+ -+ wait_queue_head_t wq; /* waitqeue for new sample values */ -+ -+} data; -+ -+/** -+ * __buffer_add_sample - add a new latency sample recording to the ring buffer -+ * @sample: The new latency sample value -+ * -+ * This receives a new latency sample and records it in a global ring buffer. -+ * No additional locking is used in this case. -+ */ -+static int __buffer_add_sample(struct sample *sample) -+{ -+ return ring_buffer_write(ring_buffer, -+ sizeof(struct sample), sample); -+} -+ -+/** -+ * buffer_get_sample - remove a hardware latency sample from the ring buffer -+ * @sample: Pre-allocated storage for the sample -+ * -+ * This retrieves a hardware latency sample from the global circular buffer -+ */ -+static struct sample *buffer_get_sample(struct sample *sample) -+{ -+ struct ring_buffer_event *e = NULL; -+ struct sample *s = NULL; -+ unsigned int cpu = 0; -+ -+ if (!sample) -+ return NULL; -+ -+ mutex_lock(&ring_buffer_mutex); -+ for_each_online_cpu(cpu) { -+ e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost); -+ if (e) -+ break; -+ } -+ -+ if (e) { -+ s = ring_buffer_event_data(e); -+ memcpy(sample, s, sizeof(struct sample)); -+ } else -+ sample = NULL; -+ mutex_unlock(&ring_buffer_mutex); -+ -+ return sample; -+} -+ -+#ifndef CONFIG_TRACING -+#define time_type ktime_t -+#define time_get() ktime_get() -+#define time_to_us(x) ktime_to_us(x) -+#define time_sub(a, b) ktime_sub(a, b) -+#define init_time(a, b) (a).tv64 = b -+#define time_u64(a) ((a).tv64) -+#else -+#define time_type u64 -+#define time_get() trace_clock_local() -+#define time_to_us(x) div_u64(x, 1000) -+#define time_sub(a, b) ((a) - (b)) -+#define init_time(a, b) (a = b) -+#define time_u64(a) a -+#endif -+/** -+ * get_sample - sample the CPU TSC and look for likely hardware latencies -+ * -+ * Used to repeatedly capture the CPU TSC (or similar), looking for potential -+ * hardware-induced latency. Called with interrupts disabled and with -+ * data.lock held. -+ */ -+static int get_sample(void) -+{ -+ time_type start, t1, t2, last_t2; -+ s64 diff, total = 0; -+ u64 sample = 0; -+ u64 outer_sample = 0; -+ int ret = -1; -+ -+ init_time(last_t2, 0); -+ start = time_get(); /* start timestamp */ -+ -+ do { -+ -+ t1 = time_get(); /* we'll look for a discontinuity */ -+ t2 = time_get(); -+ -+ if (time_u64(last_t2)) { -+ /* Check the delta from outer loop (t2 to next t1) */ -+ diff = time_to_us(time_sub(t1, last_t2)); -+ /* This shouldn't happen */ -+ if (diff < 0) { -+ pr_err(BANNER "time running backwards\n"); -+ goto out; -+ } -+ if (diff > outer_sample) -+ outer_sample = diff; -+ } -+ last_t2 = t2; -+ -+ total = time_to_us(time_sub(t2, start)); /* sample width */ -+ -+ /* This checks the inner loop (t1 to t2) */ -+ diff = time_to_us(time_sub(t2, t1)); /* current diff */ -+ -+ /* This shouldn't happen */ -+ if (diff < 0) { -+ pr_err(BANNER "time running backwards\n"); -+ goto out; -+ } -+ -+ if (diff > sample) -+ sample = diff; /* only want highest value */ -+ -+ } while (total <= data.sample_width); -+ -+ ret = 0; -+ -+ /* If we exceed the threshold value, we have found a hardware latency */ -+ if (sample > data.threshold || outer_sample > data.threshold) { -+ struct sample s; -+ -+ ret = 1; -+ -+ data.count++; -+ s.seqnum = data.count; -+ s.duration = sample; -+ s.outer_duration = outer_sample; -+ s.timestamp = CURRENT_TIME; -+ __buffer_add_sample(&s); -+ -+ /* Keep a running maximum ever recorded hardware latency */ -+ if (sample > data.max_sample) -+ data.max_sample = sample; -+ } -+ -+out: -+ return ret; -+} -+ -+/* -+ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread -+ * @unused: A required part of the kthread API. -+ * -+ * Used to periodically sample the CPU TSC via a call to get_sample. We -+ * disable interrupts, which does (intentionally) introduce latency since we -+ * need to ensure nothing else might be running (and thus pre-empting). -+ * Obviously this should never be used in production environments. -+ * -+ * Currently this runs on which ever CPU it was scheduled on, but most -+ * real-worald hardware latency situations occur across several CPUs, -+ * but we might later generalize this if we find there are any actualy -+ * systems with alternate SMI delivery or other hardware latencies. -+ */ -+static int kthread_fn(void *unused) -+{ -+ int ret; -+ u64 interval; -+ -+ while (!kthread_should_stop()) { -+ -+ mutex_lock(&data.lock); -+ -+ local_irq_disable(); -+ ret = get_sample(); -+ local_irq_enable(); -+ -+ if (ret > 0) -+ wake_up(&data.wq); /* wake up reader(s) */ -+ -+ interval = data.sample_window - data.sample_width; -+ do_div(interval, USEC_PER_MSEC); /* modifies interval value */ -+ -+ mutex_unlock(&data.lock); -+ -+ if (msleep_interruptible(interval)) -+ break; -+ } -+ -+ return 0; -+} -+ -+/** -+ * start_kthread - Kick off the hardware latency sampling/detector kthread -+ * -+ * This starts a kernel thread that will sit and sample the CPU timestamp -+ * counter (TSC or similar) and look for potential hardware latencies. -+ */ -+static int start_kthread(void) -+{ -+ kthread = kthread_run(kthread_fn, NULL, -+ DRVNAME); -+ if (IS_ERR(kthread)) { -+ pr_err(BANNER "could not start sampling thread\n"); -+ enabled = 0; -+ return -ENOMEM; -+ } -+ -+ return 0; -+} -+ -+/** -+ * stop_kthread - Inform the hardware latency samping/detector kthread to stop -+ * -+ * This kicks the running hardware latency sampling/detector kernel thread and -+ * tells it to stop sampling now. Use this on unload and at system shutdown. -+ */ -+static int stop_kthread(void) -+{ -+ int ret; -+ -+ ret = kthread_stop(kthread); -+ -+ return ret; -+} -+ -+/** -+ * __reset_stats - Reset statistics for the hardware latency detector -+ * -+ * We use data to store various statistics and global state. We call this -+ * function in order to reset those when "enable" is toggled on or off, and -+ * also at initialization. Should be called with data.lock held. -+ */ -+static void __reset_stats(void) -+{ -+ data.count = 0; -+ data.max_sample = 0; -+ ring_buffer_reset(ring_buffer); /* flush out old sample entries */ -+} -+ -+/** -+ * init_stats - Setup global state statistics for the hardware latency detector -+ * -+ * We use data to store various statistics and global state. We also use -+ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware -+ * induced system latencies. This function initializes these structures and -+ * allocates the global ring buffer also. -+ */ -+static int init_stats(void) -+{ -+ int ret = -ENOMEM; -+ -+ mutex_init(&data.lock); -+ init_waitqueue_head(&data.wq); -+ atomic_set(&data.sample_open, 0); -+ -+ ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS); -+ -+ if (WARN(!ring_buffer, KERN_ERR BANNER -+ "failed to allocate ring buffer!\n")) -+ goto out; -+ -+ __reset_stats(); -+ data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */ -+ data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ -+ data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ -+ -+ ret = 0; -+ -+out: -+ return ret; -+ -+} -+ -+/* -+ * simple_data_read - Wrapper read function for global state debugfs entries -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * @entry: The entry to read from -+ * -+ * This function provides a generic read implementation for the global state -+ * "data" structure debugfs filesystem entries. It would be nice to use -+ * simple_attr_read directly, but we need to make sure that the data.lock -+ * is held during the actual read. -+ */ -+static ssize_t simple_data_read(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos, const u64 *entry) -+{ -+ char buf[U64STR_SIZE]; -+ u64 val = 0; -+ int len = 0; -+ -+ memset(buf, 0, sizeof(buf)); -+ -+ if (!entry) -+ return -EFAULT; -+ -+ mutex_lock(&data.lock); -+ val = *entry; -+ mutex_unlock(&data.lock); -+ -+ len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val); -+ -+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); -+ -+} -+ -+/* -+ * simple_data_write - Wrapper write function for global state debugfs entries -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to write value from -+ * @cnt: The maximum number of bytes to write -+ * @ppos: The current "file" position -+ * @entry: The entry to write to -+ * -+ * This function provides a generic write implementation for the global state -+ * "data" structure debugfs filesystem entries. It would be nice to use -+ * simple_attr_write directly, but we need to make sure that the data.lock -+ * is held during the actual write. -+ */ -+static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, -+ size_t cnt, loff_t *ppos, u64 *entry) -+{ -+ char buf[U64STR_SIZE]; -+ int csize = min(cnt, sizeof(buf)); -+ u64 val = 0; -+ int err = 0; -+ -+ memset(buf, '\0', sizeof(buf)); -+ if (copy_from_user(buf, ubuf, csize)) -+ return -EFAULT; -+ -+ buf[U64STR_SIZE-1] = '\0'; /* just in case */ -+ err = kstrtoull(buf, 10, &val); -+ if (err) -+ return -EINVAL; -+ -+ mutex_lock(&data.lock); -+ *entry = val; -+ mutex_unlock(&data.lock); -+ -+ return csize; -+} -+ -+/** -+ * debug_count_fopen - Open function for "count" debugfs entry -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "count" debugfs -+ * interface to the hardware latency detector. -+ */ -+static int debug_count_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_count_fread - Read function for "count" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "count" debugfs -+ * interface to the hardware latency detector. Can be used to read the -+ * number of latency readings exceeding the configured threshold since -+ * the detector was last reset (e.g. by writing a zero into "count"). -+ */ -+static ssize_t debug_count_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ return simple_data_read(filp, ubuf, cnt, ppos, &data.count); -+} -+ -+/** -+ * debug_count_fwrite - Write function for "count" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "count" debugfs -+ * interface to the hardware latency detector. Can be used to write a -+ * desired value, especially to zero the total count. -+ */ -+static ssize_t debug_count_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ return simple_data_write(filp, ubuf, cnt, ppos, &data.count); -+} -+ -+/** -+ * debug_enable_fopen - Dummy open function for "enable" debugfs interface -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "enable" debugfs -+ * interface to the hardware latency detector. -+ */ -+static int debug_enable_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_enable_fread - Read function for "enable" debugfs interface -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "enable" debugfs -+ * interface to the hardware latency detector. Can be used to determine -+ * whether the detector is currently enabled ("0\n" or "1\n" returned). -+ */ -+static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ char buf[4]; -+ -+ if ((cnt < sizeof(buf)) || (*ppos)) -+ return 0; -+ -+ buf[0] = enabled ? '1' : '0'; -+ buf[1] = '\n'; -+ buf[2] = '\0'; -+ if (copy_to_user(ubuf, buf, strlen(buf))) -+ return -EFAULT; -+ return *ppos = strlen(buf); -+} -+ -+/** -+ * debug_enable_fwrite - Write function for "enable" debugfs interface -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "enable" debugfs -+ * interface to the hardware latency detector. Can be used to enable or -+ * disable the detector, which will have the side-effect of possibly -+ * also resetting the global stats and kicking off the measuring -+ * kthread (on an enable) or the converse (upon a disable). -+ */ -+static ssize_t debug_enable_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ char buf[4]; -+ int csize = min(cnt, sizeof(buf)); -+ long val = 0; -+ int err = 0; -+ -+ memset(buf, '\0', sizeof(buf)); -+ if (copy_from_user(buf, ubuf, csize)) -+ return -EFAULT; -+ -+ buf[sizeof(buf)-1] = '\0'; /* just in case */ -+ err = kstrtoul(buf, 10, &val); -+ if (err) -+ return -EINVAL; -+ -+ if (val) { -+ if (enabled) -+ goto unlock; -+ enabled = 1; -+ __reset_stats(); -+ if (start_kthread()) -+ return -EFAULT; -+ } else { -+ if (!enabled) -+ goto unlock; -+ enabled = 0; -+ err = stop_kthread(); -+ if (err) { -+ pr_err(BANNER "cannot stop kthread\n"); -+ return -EFAULT; -+ } -+ wake_up(&data.wq); /* reader(s) should return */ -+ } -+unlock: -+ return csize; -+} -+ -+/** -+ * debug_max_fopen - Open function for "max" debugfs entry -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "max" debugfs -+ * interface to the hardware latency detector. -+ */ -+static int debug_max_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_max_fread - Read function for "max" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "max" debugfs -+ * interface to the hardware latency detector. Can be used to determine -+ * the maximum latency value observed since it was last reset. -+ */ -+static ssize_t debug_max_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample); -+} -+ -+/** -+ * debug_max_fwrite - Write function for "max" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "max" debugfs -+ * interface to the hardware latency detector. Can be used to reset the -+ * maximum or set it to some other desired value - if, then, subsequent -+ * measurements exceed this value, the maximum will be updated. -+ */ -+static ssize_t debug_max_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample); -+} -+ -+ -+/** -+ * debug_sample_fopen - An open function for "sample" debugfs interface -+ * @inode: The in-kernel inode representation of this debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function handles opening the "sample" file within the hardware -+ * latency detector debugfs directory interface. This file is used to read -+ * raw samples from the global ring_buffer and allows the user to see a -+ * running latency history. Can be opened blocking or non-blocking, -+ * affecting whether it behaves as a buffer read pipe, or does not. -+ * Implements simple locking to prevent multiple simultaneous use. -+ */ -+static int debug_sample_fopen(struct inode *inode, struct file *filp) -+{ -+ if (!atomic_add_unless(&data.sample_open, 1, 1)) -+ return -EBUSY; -+ else -+ return 0; -+} -+ -+/** -+ * debug_sample_fread - A read function for "sample" debugfs interface -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that will contain the samples read -+ * @cnt: The maximum bytes to read from the debugfs "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function handles reading from the "sample" file within the hardware -+ * latency detector debugfs directory interface. This file is used to read -+ * raw samples from the global ring_buffer and allows the user to see a -+ * running latency history. By default this will block pending a new -+ * value written into the sample buffer, unless there are already a -+ * number of value(s) waiting in the buffer, or the sample file was -+ * previously opened in a non-blocking mode of operation. -+ */ -+static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ int len = 0; -+ char buf[64]; -+ struct sample *sample = NULL; -+ -+ if (!enabled) -+ return 0; -+ -+ sample = kzalloc(sizeof(struct sample), GFP_KERNEL); -+ if (!sample) -+ return -ENOMEM; -+ -+ while (!buffer_get_sample(sample)) { -+ -+ DEFINE_WAIT(wait); -+ -+ if (filp->f_flags & O_NONBLOCK) { -+ len = -EAGAIN; -+ goto out; -+ } -+ -+ prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE); -+ schedule(); -+ finish_wait(&data.wq, &wait); -+ -+ if (signal_pending(current)) { -+ len = -EINTR; -+ goto out; -+ } -+ -+ if (!enabled) { /* enable was toggled */ -+ len = 0; -+ goto out; -+ } -+ } -+ -+ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n", -+ sample->timestamp.tv_sec, -+ sample->timestamp.tv_nsec, -+ sample->duration, -+ sample->outer_duration); -+ -+ -+ /* handling partial reads is more trouble than it's worth */ -+ if (len > cnt) -+ goto out; -+ -+ if (copy_to_user(ubuf, buf, len)) -+ len = -EFAULT; -+ -+out: -+ kfree(sample); -+ return len; -+} -+ -+/** -+ * debug_sample_release - Release function for "sample" debugfs interface -+ * @inode: The in-kernel inode represenation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function completes the close of the debugfs interface "sample" file. -+ * Frees the sample_open "lock" so that other users may open the interface. -+ */ -+static int debug_sample_release(struct inode *inode, struct file *filp) -+{ -+ atomic_dec(&data.sample_open); -+ -+ return 0; -+} -+ -+/** -+ * debug_threshold_fopen - Open function for "threshold" debugfs entry -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "threshold" debugfs -+ * interface to the hardware latency detector. -+ */ -+static int debug_threshold_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_threshold_fread - Read function for "threshold" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "threshold" debugfs -+ * interface to the hardware latency detector. It can be used to determine -+ * the current threshold level at which a latency will be recorded in the -+ * global ring buffer, typically on the order of 10us. -+ */ -+static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold); -+} -+ -+/** -+ * debug_threshold_fwrite - Write function for "threshold" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "threshold" debugfs -+ * interface to the hardware latency detector. It can be used to configure -+ * the threshold level at which any subsequently detected latencies will -+ * be recorded into the global ring buffer. -+ */ -+static ssize_t debug_threshold_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ int ret; -+ -+ ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold); -+ -+ if (enabled) -+ wake_up_process(kthread); -+ -+ return ret; -+} -+ -+/** -+ * debug_width_fopen - Open function for "width" debugfs entry -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "width" debugfs -+ * interface to the hardware latency detector. -+ */ -+static int debug_width_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_width_fread - Read function for "width" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "width" debugfs -+ * interface to the hardware latency detector. It can be used to determine -+ * for how many us of the total window us we will actively sample for any -+ * hardware-induced latecy periods. Obviously, it is not possible to -+ * sample constantly and have the system respond to a sample reader, or, -+ * worse, without having the system appear to have gone out to lunch. -+ */ -+static ssize_t debug_width_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width); -+} -+ -+/** -+ * debug_width_fwrite - Write function for "width" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "width" debugfs -+ * interface to the hardware latency detector. It can be used to configure -+ * for how many us of the total window us we will actively sample for any -+ * hardware-induced latency periods. Obviously, it is not possible to -+ * sample constantly and have the system respond to a sample reader, or, -+ * worse, without having the system appear to have gone out to lunch. It -+ * is enforced that width is less that the total window size. -+ */ -+static ssize_t debug_width_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ char buf[U64STR_SIZE]; -+ int csize = min(cnt, sizeof(buf)); -+ u64 val = 0; -+ int err = 0; -+ -+ memset(buf, '\0', sizeof(buf)); -+ if (copy_from_user(buf, ubuf, csize)) -+ return -EFAULT; -+ -+ buf[U64STR_SIZE-1] = '\0'; /* just in case */ -+ err = kstrtoull(buf, 10, &val); -+ if (err) -+ return -EINVAL; -+ -+ mutex_lock(&data.lock); -+ if (val < data.sample_window) -+ data.sample_width = val; -+ else { -+ mutex_unlock(&data.lock); -+ return -EINVAL; -+ } -+ mutex_unlock(&data.lock); -+ -+ if (enabled) -+ wake_up_process(kthread); -+ -+ return csize; -+} -+ -+/** -+ * debug_window_fopen - Open function for "window" debugfs entry -+ * @inode: The in-kernel inode representation of the debugfs "file" -+ * @filp: The active open file structure for the debugfs "file" -+ * -+ * This function provides an open implementation for the "window" debugfs -+ * interface to the hardware latency detector. The window is the total time -+ * in us that will be considered one sample period. Conceptually, windows -+ * occur back-to-back and contain a sample width period during which -+ * actual sampling occurs. -+ */ -+static int debug_window_fopen(struct inode *inode, struct file *filp) -+{ -+ return 0; -+} -+ -+/** -+ * debug_window_fread - Read function for "window" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The userspace provided buffer to read value into -+ * @cnt: The maximum number of bytes to read -+ * @ppos: The current "file" position -+ * -+ * This function provides a read implementation for the "window" debugfs -+ * interface to the hardware latency detector. The window is the total time -+ * in us that will be considered one sample period. Conceptually, windows -+ * occur back-to-back and contain a sample width period during which -+ * actual sampling occurs. Can be used to read the total window size. -+ */ -+static ssize_t debug_window_fread(struct file *filp, char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window); -+} -+ -+/** -+ * debug_window_fwrite - Write function for "window" debugfs entry -+ * @filp: The active open file structure for the debugfs "file" -+ * @ubuf: The user buffer that contains the value to write -+ * @cnt: The maximum number of bytes to write to "file" -+ * @ppos: The current position in the debugfs "file" -+ * -+ * This function provides a write implementation for the "window" debufds -+ * interface to the hardware latency detetector. The window is the total time -+ * in us that will be considered one sample period. Conceptually, windows -+ * occur back-to-back and contain a sample width period during which -+ * actual sampling occurs. Can be used to write a new total window size. It -+ * is enfoced that any value written must be greater than the sample width -+ * size, or an error results. -+ */ -+static ssize_t debug_window_fwrite(struct file *filp, -+ const char __user *ubuf, -+ size_t cnt, -+ loff_t *ppos) -+{ -+ char buf[U64STR_SIZE]; -+ int csize = min(cnt, sizeof(buf)); -+ u64 val = 0; -+ int err = 0; -+ -+ memset(buf, '\0', sizeof(buf)); -+ if (copy_from_user(buf, ubuf, csize)) -+ return -EFAULT; -+ -+ buf[U64STR_SIZE-1] = '\0'; /* just in case */ -+ err = kstrtoull(buf, 10, &val); -+ if (err) -+ return -EINVAL; -+ -+ mutex_lock(&data.lock); -+ if (data.sample_width < val) -+ data.sample_window = val; -+ else { -+ mutex_unlock(&data.lock); -+ return -EINVAL; -+ } -+ mutex_unlock(&data.lock); -+ -+ return csize; -+} -+ -+/* -+ * Function pointers for the "count" debugfs file operations -+ */ -+static const struct file_operations count_fops = { -+ .open = debug_count_fopen, -+ .read = debug_count_fread, -+ .write = debug_count_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "enable" debugfs file operations -+ */ -+static const struct file_operations enable_fops = { -+ .open = debug_enable_fopen, -+ .read = debug_enable_fread, -+ .write = debug_enable_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "max" debugfs file operations -+ */ -+static const struct file_operations max_fops = { -+ .open = debug_max_fopen, -+ .read = debug_max_fread, -+ .write = debug_max_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "sample" debugfs file operations -+ */ -+static const struct file_operations sample_fops = { -+ .open = debug_sample_fopen, -+ .read = debug_sample_fread, -+ .release = debug_sample_release, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "threshold" debugfs file operations -+ */ -+static const struct file_operations threshold_fops = { -+ .open = debug_threshold_fopen, -+ .read = debug_threshold_fread, -+ .write = debug_threshold_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "width" debugfs file operations -+ */ -+static const struct file_operations width_fops = { -+ .open = debug_width_fopen, -+ .read = debug_width_fread, -+ .write = debug_width_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/* -+ * Function pointers for the "window" debugfs file operations -+ */ -+static const struct file_operations window_fops = { -+ .open = debug_window_fopen, -+ .read = debug_window_fread, -+ .write = debug_window_fwrite, -+ .owner = THIS_MODULE, -+}; -+ -+/** -+ * init_debugfs - A function to initialize the debugfs interface files -+ * -+ * This function creates entries in debugfs for "hwlat_detector", including -+ * files to read values from the detector, current samples, and the -+ * maximum sample that has been captured since the hardware latency -+ * dectector was started. -+ */ -+static int init_debugfs(void) -+{ -+ int ret = -ENOMEM; -+ -+ debug_dir = debugfs_create_dir(DRVNAME, NULL); -+ if (!debug_dir) -+ goto err_debug_dir; -+ -+ debug_sample = debugfs_create_file("sample", 0444, -+ debug_dir, NULL, -+ &sample_fops); -+ if (!debug_sample) -+ goto err_sample; -+ -+ debug_count = debugfs_create_file("count", 0444, -+ debug_dir, NULL, -+ &count_fops); -+ if (!debug_count) -+ goto err_count; -+ -+ debug_max = debugfs_create_file("max", 0444, -+ debug_dir, NULL, -+ &max_fops); -+ if (!debug_max) -+ goto err_max; -+ -+ debug_sample_window = debugfs_create_file("window", 0644, -+ debug_dir, NULL, -+ &window_fops); -+ if (!debug_sample_window) -+ goto err_window; -+ -+ debug_sample_width = debugfs_create_file("width", 0644, -+ debug_dir, NULL, -+ &width_fops); -+ if (!debug_sample_width) -+ goto err_width; -+ -+ debug_threshold = debugfs_create_file("threshold", 0644, -+ debug_dir, NULL, -+ &threshold_fops); -+ if (!debug_threshold) -+ goto err_threshold; -+ -+ debug_enable = debugfs_create_file("enable", 0644, -+ debug_dir, &enabled, -+ &enable_fops); -+ if (!debug_enable) -+ goto err_enable; -+ -+ else { -+ ret = 0; -+ goto out; -+ } -+ -+err_enable: -+ debugfs_remove(debug_threshold); -+err_threshold: -+ debugfs_remove(debug_sample_width); -+err_width: -+ debugfs_remove(debug_sample_window); -+err_window: -+ debugfs_remove(debug_max); -+err_max: -+ debugfs_remove(debug_count); -+err_count: -+ debugfs_remove(debug_sample); -+err_sample: -+ debugfs_remove(debug_dir); -+err_debug_dir: -+out: -+ return ret; -+} -+ -+/** -+ * free_debugfs - A function to cleanup the debugfs file interface -+ */ -+static void free_debugfs(void) -+{ -+ /* could also use a debugfs_remove_recursive */ -+ debugfs_remove(debug_enable); -+ debugfs_remove(debug_threshold); -+ debugfs_remove(debug_sample_width); -+ debugfs_remove(debug_sample_window); -+ debugfs_remove(debug_max); -+ debugfs_remove(debug_count); -+ debugfs_remove(debug_sample); -+ debugfs_remove(debug_dir); -+} -+ -+/** -+ * detector_init - Standard module initialization code -+ */ -+static int detector_init(void) -+{ -+ int ret = -ENOMEM; -+ -+ pr_info(BANNER "version %s\n", VERSION); -+ -+ ret = init_stats(); -+ if (ret) -+ goto out; -+ -+ ret = init_debugfs(); -+ if (ret) -+ goto err_stats; -+ -+ if (enabled) -+ ret = start_kthread(); -+ -+ goto out; -+ -+err_stats: -+ ring_buffer_free(ring_buffer); -+out: -+ return ret; -+ -+} -+ -+/** -+ * detector_exit - Standard module cleanup code -+ */ -+static void detector_exit(void) -+{ -+ int err; -+ -+ if (enabled) { -+ enabled = 0; -+ err = stop_kthread(); -+ if (err) -+ pr_err(BANNER "cannot stop kthread\n"); -+ } -+ -+ free_debugfs(); -+ ring_buffer_free(ring_buffer); /* free up the ring buffer */ -+ -+} -+ -+module_init(detector_init); -+module_exit(detector_exit); -diff -Nur linux-4.4.28.orig/drivers/misc/Kconfig linux-4.4.28/drivers/misc/Kconfig ---- linux-4.4.28.orig/drivers/misc/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/misc/Kconfig 2016-11-01 21:26:58.256308759 +0100 -@@ -54,6 +54,7 @@ - config ATMEL_TCLIB - bool "Atmel AT32/AT91 Timer/Counter Library" - depends on (AVR32 || ARCH_AT91) -+ default y if PREEMPT_RT_FULL - help - Select this if you want a library to allocate the Timer/Counter - blocks found on many Atmel processors. This facilitates using -@@ -69,8 +70,7 @@ - are combined to make a single 32-bit timer. - - When GENERIC_CLOCKEVENTS is defined, the third timer channel -- may be used as a clock event device supporting oneshot mode -- (delays of up to two seconds) based on the 32 KiHz clock. -+ may be used as a clock event device supporting oneshot mode. - - config ATMEL_TCB_CLKSRC_BLOCK - int -@@ -84,6 +84,15 @@ - TC can be used for other purposes, such as PWM generation and - interval timing. - -+config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK -+ bool "TC Block use 32 KiHz clock" -+ depends on ATMEL_TCB_CLKSRC -+ default y if !PREEMPT_RT_FULL -+ help -+ Select this to use 32 KiHz base clock rate as TC block clock -+ source for clock events. -+ -+ - config DUMMY_IRQ - tristate "Dummy IRQ handler" - default n -@@ -113,6 +122,35 @@ - for information on the specific driver level and support statement - for your IBM server. - -+config HWLAT_DETECTOR -+ tristate "Testing module to detect hardware-induced latencies" -+ depends on DEBUG_FS -+ depends on RING_BUFFER -+ default m -+ ---help--- -+ A simple hardware latency detector. Use this module to detect -+ large latencies introduced by the behavior of the underlying -+ system firmware external to Linux. We do this using periodic -+ use of stop_machine to grab all available CPUs and measure -+ for unexplainable gaps in the CPU timestamp counter(s). By -+ default, the module is not enabled until the "enable" file -+ within the "hwlat_detector" debugfs directory is toggled. -+ -+ This module is often used to detect SMI (System Management -+ Interrupts) on x86 systems, though is not x86 specific. To -+ this end, we default to using a sample window of 1 second, -+ during which we will sample for 0.5 seconds. If an SMI or -+ similar event occurs during that time, it is recorded -+ into an 8K samples global ring buffer until retreived. -+ -+ WARNING: This software should never be enabled (it can be built -+ but should not be turned on after it is loaded) in a production -+ environment where high latencies are a concern since the -+ sampling mechanism actually introduces latencies for -+ regular tasks while the CPU(s) are being held. -+ -+ If unsure, say N -+ - config PHANTOM - tristate "Sensable PHANToM (PCI)" - depends on PCI -diff -Nur linux-4.4.28.orig/drivers/misc/Makefile linux-4.4.28/drivers/misc/Makefile ---- linux-4.4.28.orig/drivers/misc/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/misc/Makefile 2016-11-01 21:26:58.256308759 +0100 -@@ -39,6 +39,7 @@ - obj-$(CONFIG_HMC6352) += hmc6352.o - obj-y += eeprom/ - obj-y += cb710/ -+obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o - obj-$(CONFIG_SPEAR13XX_PCIE_GADGET) += spear13xx_pcie_gadget.o - obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o - obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o -diff -Nur linux-4.4.28.orig/drivers/mmc/host/mmci.c linux-4.4.28/drivers/mmc/host/mmci.c ---- linux-4.4.28.orig/drivers/mmc/host/mmci.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/mmc/host/mmci.c 2016-11-01 21:26:58.268309533 +0100 -@@ -1155,15 +1155,12 @@ - struct sg_mapping_iter *sg_miter = &host->sg_miter; - struct variant_data *variant = host->variant; - void __iomem *base = host->base; -- unsigned long flags; - u32 status; - - status = readl(base + MMCISTATUS); - - dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status); - -- local_irq_save(flags); -- - do { - unsigned int remain, len; - char *buffer; -@@ -1203,8 +1200,6 @@ - - sg_miter_stop(sg_miter); - -- local_irq_restore(flags); -- - /* - * If we have less than the fifo 'half-full' threshold to transfer, - * trigger a PIO interrupt as soon as any data is available. -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c linux-4.4.28/drivers/net/ethernet/3com/3c59x.c ---- linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/3com/3c59x.c 2016-11-01 21:26:58.300311601 +0100 -@@ -842,9 +842,9 @@ - { - struct vortex_private *vp = netdev_priv(dev); - unsigned long flags; -- local_irq_save(flags); -+ local_irq_save_nort(flags); - (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - #endif - -@@ -1916,12 +1916,12 @@ - * Block interrupts because vortex_interrupt does a bare spin_lock() - */ - unsigned long flags; -- local_irq_save(flags); -+ local_irq_save_nort(flags); - if (vp->full_bus_master_tx) - boomerang_interrupt(dev->irq, dev); - else - vortex_interrupt(dev->irq, dev); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - } - -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c ---- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-11-01 21:26:58.324313148 +0100 -@@ -2221,11 +2221,7 @@ - } - - tpd_req = atl1c_cal_tpd_req(skb); -- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) { -- if (netif_msg_pktdata(adapter)) -- dev_info(&adapter->pdev->dev, "tx locked\n"); -- return NETDEV_TX_LOCKED; -- } -+ spin_lock_irqsave(&adapter->tx_lock, flags); - - if (atl1c_tpd_avail(adapter, type) < tpd_req) { - /* no enough descriptor, just stop queue */ -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c ---- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-11-01 21:26:58.336313921 +0100 -@@ -1880,8 +1880,7 @@ - return NETDEV_TX_OK; - } - tpd_req = atl1e_cal_tdp_req(skb); -- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) -- return NETDEV_TX_LOCKED; -+ spin_lock_irqsave(&adapter->tx_lock, flags); - - if (atl1e_tpd_avail(adapter) < tpd_req) { - /* no enough descriptor, just stop queue */ -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c ---- linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-11-01 21:26:58.348314695 +0100 -@@ -1664,8 +1664,7 @@ - struct cmdQ *q = &sge->cmdQ[qid]; - unsigned int credits, pidx, genbit, count, use_sched_skb = 0; - -- if (!spin_trylock(&q->lock)) -- return NETDEV_TX_LOCKED; -+ spin_lock(&q->lock); - - reclaim_completed_tx(sge, q); - -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c linux-4.4.28/drivers/net/ethernet/neterion/s2io.c ---- linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/neterion/s2io.c 2016-11-01 21:26:58.372316242 +0100 -@@ -4084,12 +4084,7 @@ - [skb->priority & (MAX_TX_FIFOS - 1)]; - fifo = &mac_control->fifos[queue]; - -- if (do_spin_lock) -- spin_lock_irqsave(&fifo->tx_lock, flags); -- else { -- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags))) -- return NETDEV_TX_LOCKED; -- } -+ spin_lock_irqsave(&fifo->tx_lock, flags); - - if (sp->config.multiq) { - if (__netif_subqueue_stopped(dev, fifo->fifo_no)) { -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c ---- linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-11-01 21:26:58.396317789 +0100 -@@ -2137,10 +2137,8 @@ - struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; - unsigned long flags; - -- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) { -- /* Collision - tell upper layer to requeue */ -- return NETDEV_TX_LOCKED; -- } -+ spin_lock_irqsave(&tx_ring->tx_lock, flags); -+ - if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) { - netif_stop_queue(netdev); - spin_unlock_irqrestore(&tx_ring->tx_lock, flags); -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c linux-4.4.28/drivers/net/ethernet/realtek/8139too.c ---- linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/realtek/8139too.c 2016-11-01 21:26:58.416319072 +0100 -@@ -2229,7 +2229,7 @@ - struct rtl8139_private *tp = netdev_priv(dev); - const int irq = tp->pci_dev->irq; - -- disable_irq(irq); -+ disable_irq_nosync(irq); - rtl8139_interrupt(irq, dev); - enable_irq(irq); - } -diff -Nur linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c ---- linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c 2016-11-01 21:26:58.436320363 +0100 -@@ -1629,13 +1629,8 @@ - unsigned long flags; - - ENTER; -- local_irq_save(flags); -- if (!spin_trylock(&priv->tx_lock)) { -- local_irq_restore(flags); -- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n", -- BDX_DRV_NAME, ndev->name); -- return NETDEV_TX_LOCKED; -- } -+ -+ spin_lock_irqsave(&priv->tx_lock, flags); - - /* build tx descriptor */ - BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */ -diff -Nur linux-4.4.28.orig/drivers/net/rionet.c linux-4.4.28/drivers/net/rionet.c ---- linux-4.4.28.orig/drivers/net/rionet.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/rionet.c 2016-11-01 21:26:58.448321136 +0100 -@@ -174,11 +174,7 @@ - unsigned long flags; - int add_num = 1; - -- local_irq_save(flags); -- if (!spin_trylock(&rnet->tx_lock)) { -- local_irq_restore(flags); -- return NETDEV_TX_LOCKED; -- } -+ spin_lock_irqsave(&rnet->tx_lock, flags); - - if (is_multicast_ether_addr(eth->h_dest)) - add_num = nets[rnet->mport->id].nact; -diff -Nur linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c ---- linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c 2016-11-01 21:26:58.460321910 +0100 -@@ -697,7 +697,7 @@ - while (!ctx->done.done && msecs--) - udelay(1000); - } else { -- wait_event_interruptible(ctx->done.wait, -+ swait_event_interruptible(ctx->done.wait, - ctx->done.done); - } - break; -diff -Nur linux-4.4.28.orig/drivers/pci/access.c linux-4.4.28/drivers/pci/access.c ---- linux-4.4.28.orig/drivers/pci/access.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/pci/access.c 2016-11-01 21:26:58.472322683 +0100 -@@ -561,7 +561,7 @@ - WARN_ON(!dev->block_cfg_access); - - dev->block_cfg_access = 0; -- wake_up_all(&pci_cfg_wait); -+ wake_up_all_locked(&pci_cfg_wait); - raw_spin_unlock_irqrestore(&pci_lock, flags); - } - EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); -diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c linux-4.4.28/drivers/scsi/fcoe/fcoe.c ---- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/scsi/fcoe/fcoe.c 2016-11-01 21:26:58.496324231 +0100 -@@ -1286,7 +1286,7 @@ - struct sk_buff *skb; - #ifdef CONFIG_SMP - struct fcoe_percpu_s *p0; -- unsigned targ_cpu = get_cpu(); -+ unsigned targ_cpu = get_cpu_light(); - #endif /* CONFIG_SMP */ - - FCOE_DBG("Destroying receive thread for CPU %d\n", cpu); -@@ -1342,7 +1342,7 @@ - kfree_skb(skb); - spin_unlock_bh(&p->fcoe_rx_list.lock); - } -- put_cpu(); -+ put_cpu_light(); - #else - /* - * This a non-SMP scenario where the singular Rx thread is -@@ -1566,11 +1566,11 @@ - static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) - { - struct fcoe_percpu_s *fps; -- int rc; -+ int rc, cpu = get_cpu_light(); - -- fps = &get_cpu_var(fcoe_percpu); -+ fps = &per_cpu(fcoe_percpu, cpu); - rc = fcoe_get_paged_crc_eof(skb, tlen, fps); -- put_cpu_var(fcoe_percpu); -+ put_cpu_light(); - - return rc; - } -@@ -1766,11 +1766,11 @@ - return 0; - } - -- stats = per_cpu_ptr(lport->stats, get_cpu()); -+ stats = per_cpu_ptr(lport->stats, get_cpu_light()); - stats->InvalidCRCCount++; - if (stats->InvalidCRCCount < 5) - printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); -- put_cpu(); -+ put_cpu_light(); - return -EINVAL; - } - -@@ -1814,7 +1814,7 @@ - */ - hp = (struct fcoe_hdr *) skb_network_header(skb); - -- stats = per_cpu_ptr(lport->stats, get_cpu()); -+ stats = per_cpu_ptr(lport->stats, get_cpu_light()); - if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { - if (stats->ErrorFrames < 5) - printk(KERN_WARNING "fcoe: FCoE version " -@@ -1846,13 +1846,13 @@ - goto drop; - - if (!fcoe_filter_frames(lport, fp)) { -- put_cpu(); -+ put_cpu_light(); - fc_exch_recv(lport, fp); - return; - } - drop: - stats->ErrorFrames++; -- put_cpu(); -+ put_cpu_light(); - kfree_skb(skb); - } - -diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c ---- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c 2016-11-01 21:26:58.516325525 +0100 -@@ -831,7 +831,7 @@ - - INIT_LIST_HEAD(&del_list); - -- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); -+ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); - - list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { - deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; -@@ -867,7 +867,7 @@ - sel_time = fcf->time; - } - } -- put_cpu(); -+ put_cpu_light(); - - list_for_each_entry_safe(fcf, next, &del_list, list) { - /* Removes fcf from current list */ -diff -Nur linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c linux-4.4.28/drivers/scsi/libfc/fc_exch.c ---- linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/scsi/libfc/fc_exch.c 2016-11-01 21:26:58.536326808 +0100 -@@ -814,10 +814,10 @@ - } - memset(ep, 0, sizeof(*ep)); - -- cpu = get_cpu(); -+ cpu = get_cpu_light(); - pool = per_cpu_ptr(mp->pool, cpu); - spin_lock_bh(&pool->lock); -- put_cpu(); -+ put_cpu_light(); - - /* peek cache of free slot */ - if (pool->left != FC_XID_UNKNOWN) { -diff -Nur linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c linux-4.4.28/drivers/scsi/libsas/sas_ata.c ---- linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/scsi/libsas/sas_ata.c 2016-11-01 21:26:58.548327581 +0100 -@@ -190,7 +190,7 @@ - /* TODO: audit callers to ensure they are ready for qc_issue to - * unconditionally re-enable interrupts - */ -- local_irq_save(flags); -+ local_irq_save_nort(flags); - spin_unlock(ap->lock); - - /* If the device fell off, no sense in issuing commands */ -@@ -255,7 +255,7 @@ - - out: - spin_lock(ap->lock); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - return ret; - } - -diff -Nur linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h ---- linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h 2016-11-01 21:26:58.560328355 +0100 -@@ -59,12 +59,12 @@ - { - unsigned long flags; - struct qla_hw_data *ha = rsp->hw; -- local_irq_save(flags); -+ local_irq_save_nort(flags); - if (IS_P3P_TYPE(ha)) - qla82xx_poll(0, rsp); - else - ha->isp_ops->intr_handler(0, rsp); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - - static inline uint8_t * -diff -Nur linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c ---- linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c 2016-11-01 21:26:58.572329128 +0100 -@@ -29,6 +29,7 @@ - #include - #include - #include -+#include - #include - #include - -@@ -352,7 +353,7 @@ - } - } - --static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) -+static void platform_thermal_notify_work(struct swork_event *event) - { - unsigned long flags; - int cpu = smp_processor_id(); -@@ -369,7 +370,7 @@ - pkg_work_scheduled[phy_id]) { - disable_pkg_thres_interrupt(); - spin_unlock_irqrestore(&pkg_work_lock, flags); -- return -EINVAL; -+ return; - } - pkg_work_scheduled[phy_id] = 1; - spin_unlock_irqrestore(&pkg_work_lock, flags); -@@ -378,9 +379,48 @@ - schedule_delayed_work_on(cpu, - &per_cpu(pkg_temp_thermal_threshold_work, cpu), - msecs_to_jiffies(notify_delay_ms)); -+} -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+static struct swork_event notify_work; -+ -+static int thermal_notify_work_init(void) -+{ -+ int err; -+ -+ err = swork_get(); -+ if (err) -+ return err; -+ -+ INIT_SWORK(¬ify_work, platform_thermal_notify_work); - return 0; - } - -+static void thermal_notify_work_cleanup(void) -+{ -+ swork_put(); -+} -+ -+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) -+{ -+ swork_queue(¬ify_work); -+ return 0; -+} -+ -+#else /* !CONFIG_PREEMPT_RT_FULL */ -+ -+static int thermal_notify_work_init(void) { return 0; } -+ -+static void thermal_notify_work_cleanup(void) { } -+ -+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) -+{ -+ platform_thermal_notify_work(NULL); -+ -+ return 0; -+} -+#endif /* CONFIG_PREEMPT_RT_FULL */ -+ - static int find_siblings_cpu(int cpu) - { - int i; -@@ -584,6 +624,9 @@ - if (!x86_match_cpu(pkg_temp_thermal_ids)) - return -ENODEV; - -+ if (!thermal_notify_work_init()) -+ return -ENODEV; -+ - spin_lock_init(&pkg_work_lock); - platform_thermal_package_notify = - pkg_temp_thermal_platform_thermal_notify; -@@ -608,7 +651,7 @@ - kfree(pkg_work_scheduled); - platform_thermal_package_notify = NULL; - platform_thermal_package_rate_control = NULL; -- -+ thermal_notify_work_cleanup(); - return -ENODEV; - } - -@@ -633,6 +676,7 @@ - mutex_unlock(&phy_dev_list_mutex); - platform_thermal_package_notify = NULL; - platform_thermal_package_rate_control = NULL; -+ thermal_notify_work_cleanup(); - for_each_online_cpu(i) - cancel_delayed_work_sync( - &per_cpu(pkg_temp_thermal_threshold_work, i)); -diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c linux-4.4.28/drivers/tty/serial/8250/8250_core.c ---- linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/tty/serial/8250/8250_core.c 2016-11-01 21:26:58.576329393 +0100 -@@ -58,7 +58,16 @@ - - static unsigned int skip_txen_test; /* force skip of txen test at init time */ - --#define PASS_LIMIT 512 -+/* -+ * On -rt we can have a more delays, and legitimately -+ * so - so don't drop work spuriously and spam the -+ * syslog: -+ */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define PASS_LIMIT 1000000 -+#else -+# define PASS_LIMIT 512 -+#endif - - #include - /* -diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c linux-4.4.28/drivers/tty/serial/8250/8250_port.c ---- linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/tty/serial/8250/8250_port.c 2016-11-01 21:26:58.596330676 +0100 -@@ -35,6 +35,7 @@ - #include - #include - #include -+#include - #include - #include - -@@ -2843,9 +2844,9 @@ - - serial8250_rpm_get(up); - -- if (port->sysrq) -+ if (port->sysrq || oops_in_progress) - locked = 0; -- else if (oops_in_progress) -+ else if (in_kdb_printk()) - locked = spin_trylock_irqsave(&port->lock, flags); - else - spin_lock_irqsave(&port->lock, flags); -diff -Nur linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c linux-4.4.28/drivers/tty/serial/amba-pl011.c ---- linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/tty/serial/amba-pl011.c 2016-11-01 21:26:58.608331449 +0100 -@@ -2067,13 +2067,19 @@ - - clk_enable(uap->clk); - -- local_irq_save(flags); -+ /* -+ * local_irq_save(flags); -+ * -+ * This local_irq_save() is nonsense. If we come in via sysrq -+ * handling then interrupts are already disabled. Aside of -+ * that the port.sysrq check is racy on SMP regardless. -+ */ - if (uap->port.sysrq) - locked = 0; - else if (oops_in_progress) -- locked = spin_trylock(&uap->port.lock); -+ locked = spin_trylock_irqsave(&uap->port.lock, flags); - else -- spin_lock(&uap->port.lock); -+ spin_lock_irqsave(&uap->port.lock, flags); - - /* - * First save the CR then disable the interrupts -@@ -2098,8 +2104,7 @@ - writew(old_cr, uap->port.membase + UART011_CR); - - if (locked) -- spin_unlock(&uap->port.lock); -- local_irq_restore(flags); -+ spin_unlock_irqrestore(&uap->port.lock, flags); - - clk_disable(uap->clk); - } -diff -Nur linux-4.4.28.orig/drivers/tty/serial/omap-serial.c linux-4.4.28/drivers/tty/serial/omap-serial.c ---- linux-4.4.28.orig/drivers/tty/serial/omap-serial.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/tty/serial/omap-serial.c 2016-11-01 21:26:58.620332223 +0100 -@@ -1257,13 +1257,10 @@ - - pm_runtime_get_sync(up->dev); - -- local_irq_save(flags); -- if (up->port.sysrq) -- locked = 0; -- else if (oops_in_progress) -- locked = spin_trylock(&up->port.lock); -+ if (up->port.sysrq || oops_in_progress) -+ locked = spin_trylock_irqsave(&up->port.lock, flags); - else -- spin_lock(&up->port.lock); -+ spin_lock_irqsave(&up->port.lock, flags); - - /* - * First save the IER then disable the interrupts -@@ -1292,8 +1289,7 @@ - pm_runtime_mark_last_busy(up->dev); - pm_runtime_put_autosuspend(up->dev); - if (locked) -- spin_unlock(&up->port.lock); -- local_irq_restore(flags); -+ spin_unlock_irqrestore(&up->port.lock, flags); - } - - static int __init -diff -Nur linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c linux-4.4.28/drivers/tty/serial/sc16is7xx.c ---- linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/tty/serial/sc16is7xx.c 2016-11-01 21:26:58.628332740 +0100 -@@ -1230,7 +1230,7 @@ - - /* Setup interrupt */ - ret = devm_request_irq(dev, irq, sc16is7xx_irq, -- IRQF_ONESHOT | flags, dev_name(dev), s); -+ flags, dev_name(dev), s); - if (!ret) - return 0; - -diff -Nur linux-4.4.28.orig/drivers/usb/core/hcd.c linux-4.4.28/drivers/usb/core/hcd.c ---- linux-4.4.28.orig/drivers/usb/core/hcd.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/usb/core/hcd.c 2016-11-01 21:26:58.648334034 +0100 -@@ -1735,9 +1735,9 @@ - * and no one may trigger the above deadlock situation when - * running complete() in tasklet. - */ -- local_irq_save(flags); -+ local_irq_save_nort(flags); - urb->complete(urb); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - - usb_anchor_resume_wakeups(anchor); - atomic_dec(&urb->use_count); -diff -Nur linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c linux-4.4.28/drivers/usb/gadget/function/f_fs.c ---- linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/usb/gadget/function/f_fs.c 2016-11-01 21:26:58.680336091 +0100 -@@ -1404,7 +1404,7 @@ - pr_info("%s(): freeing\n", __func__); - ffs_data_clear(ffs); - BUG_ON(waitqueue_active(&ffs->ev.waitq) || -- waitqueue_active(&ffs->ep0req_completion.wait)); -+ swait_active(&ffs->ep0req_completion.wait)); - kfree(ffs->dev_name); - kfree(ffs); - } -diff -Nur linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c linux-4.4.28/drivers/usb/gadget/legacy/inode.c ---- linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/usb/gadget/legacy/inode.c 2016-11-01 21:26:58.692336864 +0100 -@@ -345,7 +345,7 @@ - spin_unlock_irq (&epdata->dev->lock); - - if (likely (value == 0)) { -- value = wait_event_interruptible (done.wait, done.done); -+ value = swait_event_interruptible (done.wait, done.done); - if (value != 0) { - spin_lock_irq (&epdata->dev->lock); - if (likely (epdata->ep != NULL)) { -@@ -354,7 +354,7 @@ - usb_ep_dequeue (epdata->ep, epdata->req); - spin_unlock_irq (&epdata->dev->lock); - -- wait_event (done.wait, done.done); -+ swait_event (done.wait, done.done); - if (epdata->status == -ECONNRESET) - epdata->status = -EINTR; - } else { -diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c ---- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-11-01 21:26:58.704337638 +0100 -@@ -17,7 +17,9 @@ - #include - #include - #include -+#include - #include -+#include - #include - #include - #include -@@ -1888,20 +1890,15 @@ - #ifdef CONFIG_OF - static void at91sam9rl_toggle_bias(struct usba_udc *udc, int is_on) - { -- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); -- -- if (is_on) -- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); -- else -- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); -+ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, -+ is_on ? AT91_PMC_BIASEN : 0); - } - - static void at91sam9g45_pulse_bias(struct usba_udc *udc) - { -- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); -- -- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); -- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); -+ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, 0); -+ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, -+ AT91_PMC_BIASEN); - } - - static const struct usba_udc_errata at91sam9rl_errata = { -@@ -1938,6 +1935,9 @@ - return ERR_PTR(-EINVAL); - - udc->errata = match->data; -+ udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc"); -+ if (udc->errata && IS_ERR(udc->pmc)) -+ return ERR_CAST(udc->pmc); - - udc->num_ep = 0; - -diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h ---- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-11-01 21:26:58.704337638 +0100 -@@ -354,6 +354,8 @@ - struct dentry *debugfs_root; - struct dentry *debugfs_regs; - #endif -+ -+ struct regmap *pmc; - }; - - static inline struct usba_ep *to_usba_ep(struct usb_ep *ep) -diff -Nur linux-4.4.28.orig/fs/aio.c linux-4.4.28/fs/aio.c ---- linux-4.4.28.orig/fs/aio.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/aio.c 2016-11-01 21:26:58.716338411 +0100 -@@ -40,6 +40,7 @@ - #include - #include - #include -+#include - - #include - #include -@@ -115,7 +116,7 @@ - struct page **ring_pages; - long nr_pages; - -- struct work_struct free_work; -+ struct swork_event free_work; - - /* - * signals when all in-flight requests are done -@@ -258,6 +259,7 @@ - .mount = aio_mount, - .kill_sb = kill_anon_super, - }; -+ BUG_ON(swork_get()); - aio_mnt = kern_mount(&aio_fs); - if (IS_ERR(aio_mnt)) - panic("Failed to create aio fs mount."); -@@ -573,9 +575,9 @@ - return cancel(&kiocb->common); - } - --static void free_ioctx(struct work_struct *work) -+static void free_ioctx(struct swork_event *sev) - { -- struct kioctx *ctx = container_of(work, struct kioctx, free_work); -+ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); - - pr_debug("freeing %p\n", ctx); - -@@ -594,8 +596,8 @@ - if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) - complete(&ctx->rq_wait->comp); - -- INIT_WORK(&ctx->free_work, free_ioctx); -- schedule_work(&ctx->free_work); -+ INIT_SWORK(&ctx->free_work, free_ioctx); -+ swork_queue(&ctx->free_work); - } - - /* -@@ -603,9 +605,9 @@ - * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - - * now it's safe to cancel any that need to be. - */ --static void free_ioctx_users(struct percpu_ref *ref) -+static void free_ioctx_users_work(struct swork_event *sev) - { -- struct kioctx *ctx = container_of(ref, struct kioctx, users); -+ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); - struct aio_kiocb *req; - - spin_lock_irq(&ctx->ctx_lock); -@@ -624,6 +626,14 @@ - percpu_ref_put(&ctx->reqs); - } - -+static void free_ioctx_users(struct percpu_ref *ref) -+{ -+ struct kioctx *ctx = container_of(ref, struct kioctx, users); -+ -+ INIT_SWORK(&ctx->free_work, free_ioctx_users_work); -+ swork_queue(&ctx->free_work); -+} -+ - static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) - { - unsigned i, new_nr; -diff -Nur linux-4.4.28.orig/fs/autofs4/autofs_i.h linux-4.4.28/fs/autofs4/autofs_i.h ---- linux-4.4.28.orig/fs/autofs4/autofs_i.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/autofs4/autofs_i.h 2016-11-01 21:26:58.716338411 +0100 -@@ -34,6 +34,7 @@ - #include - #include - #include -+#include - #include - #include - -diff -Nur linux-4.4.28.orig/fs/autofs4/expire.c linux-4.4.28/fs/autofs4/expire.c ---- linux-4.4.28.orig/fs/autofs4/expire.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/autofs4/expire.c 2016-11-01 21:26:58.716338411 +0100 -@@ -150,7 +150,7 @@ - parent = p->d_parent; - if (!spin_trylock(&parent->d_lock)) { - spin_unlock(&p->d_lock); -- cpu_relax(); -+ cpu_chill(); - goto relock; - } - spin_unlock(&p->d_lock); -diff -Nur linux-4.4.28.orig/fs/buffer.c linux-4.4.28/fs/buffer.c ---- linux-4.4.28.orig/fs/buffer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/buffer.c 2016-11-01 21:26:58.716338411 +0100 -@@ -305,8 +305,7 @@ - * decide that the page is now completely done. - */ - first = page_buffers(page); -- local_irq_save(flags); -- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); -+ flags = bh_uptodate_lock_irqsave(first); - clear_buffer_async_read(bh); - unlock_buffer(bh); - tmp = bh; -@@ -319,8 +318,7 @@ - } - tmp = tmp->b_this_page; - } while (tmp != bh); -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -+ bh_uptodate_unlock_irqrestore(first, flags); - - /* - * If none of the buffers had errors and they are all -@@ -332,9 +330,7 @@ - return; - - still_busy: -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -- return; -+ bh_uptodate_unlock_irqrestore(first, flags); - } - - /* -@@ -362,8 +358,7 @@ - } - - first = page_buffers(page); -- local_irq_save(flags); -- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); -+ flags = bh_uptodate_lock_irqsave(first); - - clear_buffer_async_write(bh); - unlock_buffer(bh); -@@ -375,15 +370,12 @@ - } - tmp = tmp->b_this_page; - } -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -+ bh_uptodate_unlock_irqrestore(first, flags); - end_page_writeback(page); - return; - - still_busy: -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -- return; -+ bh_uptodate_unlock_irqrestore(first, flags); - } - EXPORT_SYMBOL(end_buffer_async_write); - -@@ -3325,6 +3317,7 @@ - struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); - if (ret) { - INIT_LIST_HEAD(&ret->b_assoc_buffers); -+ buffer_head_init_locks(ret); - preempt_disable(); - __this_cpu_inc(bh_accounting.nr); - recalc_bh_state(); -diff -Nur linux-4.4.28.orig/fs/dcache.c linux-4.4.28/fs/dcache.c ---- linux-4.4.28.orig/fs/dcache.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/dcache.c 2016-11-01 21:26:58.720338675 +0100 -@@ -19,6 +19,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -747,6 +748,8 @@ - */ - void dput(struct dentry *dentry) - { -+ struct dentry *parent; -+ - if (unlikely(!dentry)) - return; - -@@ -783,9 +786,18 @@ - return; - - kill_it: -- dentry = dentry_kill(dentry); -- if (dentry) { -- cond_resched(); -+ parent = dentry_kill(dentry); -+ if (parent) { -+ int r; -+ -+ if (parent == dentry) { -+ /* the task with the highest priority won't schedule */ -+ r = cond_resched(); -+ if (!r) -+ cpu_chill(); -+ } else { -+ dentry = parent; -+ } - goto repeat; - } - } -@@ -2394,7 +2406,7 @@ - if (dentry->d_lockref.count == 1) { - if (!spin_trylock(&inode->i_lock)) { - spin_unlock(&dentry->d_lock); -- cpu_relax(); -+ cpu_chill(); - goto again; - } - dentry->d_flags &= ~DCACHE_CANT_MOUNT; -diff -Nur linux-4.4.28.orig/fs/eventpoll.c linux-4.4.28/fs/eventpoll.c ---- linux-4.4.28.orig/fs/eventpoll.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/eventpoll.c 2016-11-01 21:26:58.720338675 +0100 -@@ -505,12 +505,12 @@ - */ - static void ep_poll_safewake(wait_queue_head_t *wq) - { -- int this_cpu = get_cpu(); -+ int this_cpu = get_cpu_light(); - - ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, - ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); - -- put_cpu(); -+ put_cpu_light(); - } - - static void ep_remove_wait_queue(struct eppoll_entry *pwq) -diff -Nur linux-4.4.28.orig/fs/exec.c linux-4.4.28/fs/exec.c ---- linux-4.4.28.orig/fs/exec.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/exec.c 2016-11-01 21:26:58.720338675 +0100 -@@ -865,12 +865,14 @@ - } - } - task_lock(tsk); -+ preempt_disable_rt(); - active_mm = tsk->active_mm; - tsk->mm = mm; - tsk->active_mm = mm; - activate_mm(active_mm, mm); - tsk->mm->vmacache_seqnum = 0; - vmacache_flush(tsk); -+ preempt_enable_rt(); - task_unlock(tsk); - if (old_mm) { - up_read(&old_mm->mmap_sem); -diff -Nur linux-4.4.28.orig/fs/f2fs/f2fs.h linux-4.4.28/fs/f2fs/f2fs.h ---- linux-4.4.28.orig/fs/f2fs/f2fs.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/f2fs/f2fs.h 2016-11-01 21:26:58.720338675 +0100 -@@ -24,7 +24,6 @@ - - #ifdef CONFIG_F2FS_CHECK_FS - #define f2fs_bug_on(sbi, condition) BUG_ON(condition) --#define f2fs_down_write(x, y) down_write_nest_lock(x, y) - #else - #define f2fs_bug_on(sbi, condition) \ - do { \ -@@ -33,7 +32,6 @@ - set_sbi_flag(sbi, SBI_NEED_FSCK); \ - } \ - } while (0) --#define f2fs_down_write(x, y) down_write(x) - #endif - - /* -@@ -959,7 +957,7 @@ - - static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) - { -- f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); -+ down_write(&sbi->cp_rwsem); - } - - static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) -diff -Nur linux-4.4.28.orig/fs/jbd2/checkpoint.c linux-4.4.28/fs/jbd2/checkpoint.c ---- linux-4.4.28.orig/fs/jbd2/checkpoint.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/jbd2/checkpoint.c 2016-11-01 21:26:58.720338675 +0100 -@@ -116,6 +116,8 @@ - nblocks = jbd2_space_needed(journal); - while (jbd2_log_space_left(journal) < nblocks) { - write_unlock(&journal->j_state_lock); -+ if (current->plug) -+ io_schedule(); - mutex_lock(&journal->j_checkpoint_mutex); - - /* -diff -Nur linux-4.4.28.orig/fs/namespace.c linux-4.4.28/fs/namespace.c ---- linux-4.4.28.orig/fs/namespace.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/namespace.c 2016-11-01 21:26:58.724338928 +0100 -@@ -14,6 +14,7 @@ - #include - #include - #include -+#include - #include - #include - #include /* init_rootfs */ -@@ -353,8 +354,11 @@ - * incremented count after it has set MNT_WRITE_HOLD. - */ - smp_mb(); -- while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) -- cpu_relax(); -+ while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { -+ preempt_enable(); -+ cpu_chill(); -+ preempt_disable(); -+ } - /* - * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will - * be set to match its requirements. So we must not load that until -diff -Nur linux-4.4.28.orig/fs/ntfs/aops.c linux-4.4.28/fs/ntfs/aops.c ---- linux-4.4.28.orig/fs/ntfs/aops.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/ntfs/aops.c 2016-11-01 21:26:58.724338928 +0100 -@@ -107,8 +107,7 @@ - "0x%llx.", (unsigned long long)bh->b_blocknr); - } - first = page_buffers(page); -- local_irq_save(flags); -- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); -+ flags = bh_uptodate_lock_irqsave(first); - clear_buffer_async_read(bh); - unlock_buffer(bh); - tmp = bh; -@@ -123,8 +122,7 @@ - } - tmp = tmp->b_this_page; - } while (tmp != bh); -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -+ bh_uptodate_unlock_irqrestore(first, flags); - /* - * If none of the buffers had errors then we can set the page uptodate, - * but we first have to perform the post read mst fixups, if the -@@ -145,13 +143,13 @@ - recs = PAGE_CACHE_SIZE / rec_size; - /* Should have been verified before we got here... */ - BUG_ON(!recs); -- local_irq_save(flags); -+ local_irq_save_nort(flags); - kaddr = kmap_atomic(page); - for (i = 0; i < recs; i++) - post_read_mst_fixup((NTFS_RECORD*)(kaddr + - i * rec_size), rec_size); - kunmap_atomic(kaddr); -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - flush_dcache_page(page); - if (likely(page_uptodate && !PageError(page))) - SetPageUptodate(page); -@@ -159,9 +157,7 @@ - unlock_page(page); - return; - still_busy: -- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); -- local_irq_restore(flags); -- return; -+ bh_uptodate_unlock_irqrestore(first, flags); - } - - /** -diff -Nur linux-4.4.28.orig/fs/timerfd.c linux-4.4.28/fs/timerfd.c ---- linux-4.4.28.orig/fs/timerfd.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/fs/timerfd.c 2016-11-01 21:26:58.724338928 +0100 -@@ -450,7 +450,10 @@ - break; - } - spin_unlock_irq(&ctx->wqh.lock); -- cpu_relax(); -+ if (isalarm(ctx)) -+ hrtimer_wait_for_timer(&ctx->t.alarm.timer); -+ else -+ hrtimer_wait_for_timer(&ctx->t.tmr); - } - - /* -diff -Nur linux-4.4.28.orig/include/acpi/platform/aclinux.h linux-4.4.28/include/acpi/platform/aclinux.h ---- linux-4.4.28.orig/include/acpi/platform/aclinux.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/acpi/platform/aclinux.h 2016-11-01 21:26:58.724338928 +0100 -@@ -127,6 +127,7 @@ - - #define acpi_cache_t struct kmem_cache - #define acpi_spinlock spinlock_t * -+#define acpi_raw_spinlock raw_spinlock_t * - #define acpi_cpu_flags unsigned long - - /* Use native linux version of acpi_os_allocate_zeroed */ -@@ -145,6 +146,20 @@ - #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id - #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock - -+#define acpi_os_create_raw_lock(__handle) \ -+({ \ -+ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ -+ \ -+ if (lock) { \ -+ *(__handle) = lock; \ -+ raw_spin_lock_init(*(__handle)); \ -+ } \ -+ lock ? AE_OK : AE_NO_MEMORY; \ -+ }) -+ -+#define acpi_os_delete_raw_lock(__handle) kfree(__handle) -+ -+ - /* - * OSL interfaces used by debugger/disassembler - */ -diff -Nur linux-4.4.28.orig/include/asm-generic/bug.h linux-4.4.28/include/asm-generic/bug.h ---- linux-4.4.28.orig/include/asm-generic/bug.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/asm-generic/bug.h 2016-11-01 21:26:58.724338928 +0100 -@@ -206,6 +206,20 @@ - # define WARN_ON_SMP(x) ({0;}) - #endif - -+#ifdef CONFIG_PREEMPT_RT_BASE -+# define BUG_ON_RT(c) BUG_ON(c) -+# define BUG_ON_NONRT(c) do { } while (0) -+# define WARN_ON_RT(condition) WARN_ON(condition) -+# define WARN_ON_NONRT(condition) do { } while (0) -+# define WARN_ON_ONCE_NONRT(condition) do { } while (0) -+#else -+# define BUG_ON_RT(c) do { } while (0) -+# define BUG_ON_NONRT(c) BUG_ON(c) -+# define WARN_ON_RT(condition) do { } while (0) -+# define WARN_ON_NONRT(condition) WARN_ON(condition) -+# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition) -+#endif -+ - #endif /* __ASSEMBLY__ */ - - #endif -diff -Nur linux-4.4.28.orig/include/asm-generic/preempt.h linux-4.4.28/include/asm-generic/preempt.h ---- linux-4.4.28.orig/include/asm-generic/preempt.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/asm-generic/preempt.h 2016-11-01 21:26:58.724338928 +0100 -@@ -7,10 +7,10 @@ - - static __always_inline int preempt_count(void) - { -- return current_thread_info()->preempt_count; -+ return READ_ONCE(current_thread_info()->preempt_count); - } - --static __always_inline int *preempt_count_ptr(void) -+static __always_inline volatile int *preempt_count_ptr(void) - { - return ¤t_thread_info()->preempt_count; - } -diff -Nur linux-4.4.28.orig/include/linux/blkdev.h linux-4.4.28/include/linux/blkdev.h ---- linux-4.4.28.orig/include/linux/blkdev.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/blkdev.h 2016-11-01 21:26:58.724338928 +0100 -@@ -89,6 +89,7 @@ - struct list_head queuelist; - union { - struct call_single_data csd; -+ struct work_struct work; - unsigned long fifo_time; - }; - -@@ -455,7 +456,7 @@ - struct throtl_data *td; - #endif - struct rcu_head rcu_head; -- wait_queue_head_t mq_freeze_wq; -+ struct swait_queue_head mq_freeze_wq; - struct percpu_ref q_usage_counter; - struct list_head all_q_node; - -diff -Nur linux-4.4.28.orig/include/linux/blk-mq.h linux-4.4.28/include/linux/blk-mq.h ---- linux-4.4.28.orig/include/linux/blk-mq.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/blk-mq.h 2016-11-01 21:26:58.724338928 +0100 -@@ -212,6 +212,7 @@ - - struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); - struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); -+void __blk_mq_complete_request_remote_work(struct work_struct *work); - - int blk_mq_request_started(struct request *rq); - void blk_mq_start_request(struct request *rq); -diff -Nur linux-4.4.28.orig/include/linux/bottom_half.h linux-4.4.28/include/linux/bottom_half.h ---- linux-4.4.28.orig/include/linux/bottom_half.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/bottom_half.h 2016-11-01 21:26:58.724338928 +0100 -@@ -3,6 +3,39 @@ - - #include - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ -+extern void __local_bh_disable(void); -+extern void _local_bh_enable(void); -+extern void __local_bh_enable(void); -+ -+static inline void local_bh_disable(void) -+{ -+ __local_bh_disable(); -+} -+ -+static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) -+{ -+ __local_bh_disable(); -+} -+ -+static inline void local_bh_enable(void) -+{ -+ __local_bh_enable(); -+} -+ -+static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) -+{ -+ __local_bh_enable(); -+} -+ -+static inline void local_bh_enable_ip(unsigned long ip) -+{ -+ __local_bh_enable(); -+} -+ -+#else -+ - #ifdef CONFIG_TRACE_IRQFLAGS - extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); - #else -@@ -30,5 +63,6 @@ - { - __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); - } -+#endif - - #endif /* _LINUX_BH_H */ -diff -Nur linux-4.4.28.orig/include/linux/buffer_head.h linux-4.4.28/include/linux/buffer_head.h ---- linux-4.4.28.orig/include/linux/buffer_head.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/buffer_head.h 2016-11-01 21:26:58.724338928 +0100 -@@ -75,8 +75,50 @@ - struct address_space *b_assoc_map; /* mapping this buffer is - associated with */ - atomic_t b_count; /* users using this buffer_head */ -+#ifdef CONFIG_PREEMPT_RT_BASE -+ spinlock_t b_uptodate_lock; -+#if IS_ENABLED(CONFIG_JBD2) -+ spinlock_t b_state_lock; -+ spinlock_t b_journal_head_lock; -+#endif -+#endif - }; - -+static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) -+{ -+ unsigned long flags; -+ -+#ifndef CONFIG_PREEMPT_RT_BASE -+ local_irq_save(flags); -+ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); -+#else -+ spin_lock_irqsave(&bh->b_uptodate_lock, flags); -+#endif -+ return flags; -+} -+ -+static inline void -+bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) -+{ -+#ifndef CONFIG_PREEMPT_RT_BASE -+ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); -+ local_irq_restore(flags); -+#else -+ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); -+#endif -+} -+ -+static inline void buffer_head_init_locks(struct buffer_head *bh) -+{ -+#ifdef CONFIG_PREEMPT_RT_BASE -+ spin_lock_init(&bh->b_uptodate_lock); -+#if IS_ENABLED(CONFIG_JBD2) -+ spin_lock_init(&bh->b_state_lock); -+ spin_lock_init(&bh->b_journal_head_lock); -+#endif -+#endif -+} -+ - /* - * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() - * and buffer_foo() functions. -diff -Nur linux-4.4.28.orig/include/linux/cgroup-defs.h linux-4.4.28/include/linux/cgroup-defs.h ---- linux-4.4.28.orig/include/linux/cgroup-defs.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/cgroup-defs.h 2016-11-01 21:26:58.728339185 +0100 -@@ -16,6 +16,7 @@ - #include - #include - #include -+#include - - #ifdef CONFIG_CGROUPS - -@@ -142,6 +143,7 @@ - /* percpu_ref killing and RCU release */ - struct rcu_head rcu_head; - struct work_struct destroy_work; -+ struct swork_event destroy_swork; - }; - - /* -diff -Nur linux-4.4.28.orig/include/linux/clk/at91_pmc.h linux-4.4.28/include/linux/clk/at91_pmc.h ---- linux-4.4.28.orig/include/linux/clk/at91_pmc.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/clk/at91_pmc.h 2016-11-01 21:26:58.728339185 +0100 -@@ -16,18 +16,6 @@ - #ifndef AT91_PMC_H - #define AT91_PMC_H - --#ifndef __ASSEMBLY__ --extern void __iomem *at91_pmc_base; -- --#define at91_pmc_read(field) \ -- readl_relaxed(at91_pmc_base + field) -- --#define at91_pmc_write(field, value) \ -- writel_relaxed(value, at91_pmc_base + field) --#else --.extern at91_pmc_base --#endif -- - #define AT91_PMC_SCER 0x00 /* System Clock Enable Register */ - #define AT91_PMC_SCDR 0x04 /* System Clock Disable Register */ - -diff -Nur linux-4.4.28.orig/include/linux/completion.h linux-4.4.28/include/linux/completion.h ---- linux-4.4.28.orig/include/linux/completion.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/completion.h 2016-11-01 21:26:58.728339185 +0100 -@@ -7,8 +7,7 @@ - * Atomic wait-for-completion handler data structures. - * See kernel/sched/completion.c for details. - */ -- --#include -+#include - - /* - * struct completion - structure used to maintain state for a "completion" -@@ -24,11 +23,11 @@ - */ - struct completion { - unsigned int done; -- wait_queue_head_t wait; -+ struct swait_queue_head wait; - }; - - #define COMPLETION_INITIALIZER(work) \ -- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } -+ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } - - #define COMPLETION_INITIALIZER_ONSTACK(work) \ - ({ init_completion(&work); work; }) -@@ -73,7 +72,7 @@ - static inline void init_completion(struct completion *x) - { - x->done = 0; -- init_waitqueue_head(&x->wait); -+ init_swait_queue_head(&x->wait); - } - - /** -diff -Nur linux-4.4.28.orig/include/linux/cpu.h linux-4.4.28/include/linux/cpu.h ---- linux-4.4.28.orig/include/linux/cpu.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/cpu.h 2016-11-01 21:26:58.728339185 +0100 -@@ -231,6 +231,8 @@ - extern void put_online_cpus(void); - extern void cpu_hotplug_disable(void); - extern void cpu_hotplug_enable(void); -+extern void pin_current_cpu(void); -+extern void unpin_current_cpu(void); - #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) - #define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri) - #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) -@@ -248,6 +250,8 @@ - #define put_online_cpus() do { } while (0) - #define cpu_hotplug_disable() do { } while (0) - #define cpu_hotplug_enable() do { } while (0) -+static inline void pin_current_cpu(void) { } -+static inline void unpin_current_cpu(void) { } - #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) - #define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) - /* These aren't inline functions due to a GCC bug. */ -diff -Nur linux-4.4.28.orig/include/linux/delay.h linux-4.4.28/include/linux/delay.h ---- linux-4.4.28.orig/include/linux/delay.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/delay.h 2016-11-01 21:26:58.728339185 +0100 -@@ -52,4 +52,10 @@ - msleep(seconds * 1000); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+extern void cpu_chill(void); -+#else -+# define cpu_chill() cpu_relax() -+#endif -+ - #endif /* defined(_LINUX_DELAY_H) */ -diff -Nur linux-4.4.28.orig/include/linux/ftrace.h linux-4.4.28/include/linux/ftrace.h ---- linux-4.4.28.orig/include/linux/ftrace.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/ftrace.h 2016-11-01 21:26:58.728339185 +0100 -@@ -694,6 +694,18 @@ - #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) - #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) - -+static inline unsigned long get_lock_parent_ip(void) -+{ -+ unsigned long addr = CALLER_ADDR0; -+ -+ if (!in_lock_functions(addr)) -+ return addr; -+ addr = CALLER_ADDR1; -+ if (!in_lock_functions(addr)) -+ return addr; -+ return CALLER_ADDR2; -+} -+ - #ifdef CONFIG_IRQSOFF_TRACER - extern void time_hardirqs_on(unsigned long a0, unsigned long a1); - extern void time_hardirqs_off(unsigned long a0, unsigned long a1); -diff -Nur linux-4.4.28.orig/include/linux/highmem.h linux-4.4.28/include/linux/highmem.h ---- linux-4.4.28.orig/include/linux/highmem.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/highmem.h 2016-11-01 21:26:58.728339185 +0100 -@@ -7,6 +7,7 @@ - #include - #include - #include -+#include - - #include - -@@ -65,7 +66,7 @@ - - static inline void *kmap_atomic(struct page *page) - { -- preempt_disable(); -+ preempt_disable_nort(); - pagefault_disable(); - return page_address(page); - } -@@ -74,7 +75,7 @@ - static inline void __kunmap_atomic(void *addr) - { - pagefault_enable(); -- preempt_enable(); -+ preempt_enable_nort(); - } - - #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) -@@ -86,32 +87,51 @@ - - #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) - -+#ifndef CONFIG_PREEMPT_RT_FULL - DECLARE_PER_CPU(int, __kmap_atomic_idx); -+#endif - - static inline int kmap_atomic_idx_push(void) - { -+#ifndef CONFIG_PREEMPT_RT_FULL - int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; - --#ifdef CONFIG_DEBUG_HIGHMEM -+# ifdef CONFIG_DEBUG_HIGHMEM - WARN_ON_ONCE(in_irq() && !irqs_disabled()); - BUG_ON(idx >= KM_TYPE_NR); --#endif -+# endif - return idx; -+#else -+ current->kmap_idx++; -+ BUG_ON(current->kmap_idx > KM_TYPE_NR); -+ return current->kmap_idx - 1; -+#endif - } - - static inline int kmap_atomic_idx(void) - { -+#ifndef CONFIG_PREEMPT_RT_FULL - return __this_cpu_read(__kmap_atomic_idx) - 1; -+#else -+ return current->kmap_idx - 1; -+#endif - } - - static inline void kmap_atomic_idx_pop(void) - { --#ifdef CONFIG_DEBUG_HIGHMEM -+#ifndef CONFIG_PREEMPT_RT_FULL -+# ifdef CONFIG_DEBUG_HIGHMEM - int idx = __this_cpu_dec_return(__kmap_atomic_idx); - - BUG_ON(idx < 0); --#else -+# else - __this_cpu_dec(__kmap_atomic_idx); -+# endif -+#else -+ current->kmap_idx--; -+# ifdef CONFIG_DEBUG_HIGHMEM -+ BUG_ON(current->kmap_idx < 0); -+# endif - #endif - } - -diff -Nur linux-4.4.28.orig/include/linux/hrtimer.h linux-4.4.28/include/linux/hrtimer.h ---- linux-4.4.28.orig/include/linux/hrtimer.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/hrtimer.h 2016-11-01 21:26:58.728339185 +0100 -@@ -87,6 +87,9 @@ - * @function: timer expiry callback function - * @base: pointer to the timer base (per cpu and per clock) - * @state: state information (See bit values above) -+ * @cb_entry: list entry to defer timers from hardirq context -+ * @irqsafe: timer can run in hardirq context -+ * @praecox: timer expiry time if expired at the time of programming - * @is_rel: Set if the timer was armed relative - * @start_pid: timer statistics field to store the pid of the task which - * started the timer -@@ -103,6 +106,11 @@ - enum hrtimer_restart (*function)(struct hrtimer *); - struct hrtimer_clock_base *base; - u8 state; -+ struct list_head cb_entry; -+ int irqsafe; -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ ktime_t praecox; -+#endif - u8 is_rel; - #ifdef CONFIG_TIMER_STATS - int start_pid; -@@ -123,11 +131,7 @@ - struct task_struct *task; - }; - --#ifdef CONFIG_64BIT - # define HRTIMER_CLOCK_BASE_ALIGN 64 --#else --# define HRTIMER_CLOCK_BASE_ALIGN 32 --#endif - - /** - * struct hrtimer_clock_base - the timer base for a specific clock -@@ -136,6 +140,7 @@ - * timer to a base on another cpu. - * @clockid: clock id for per_cpu support - * @active: red black tree root node for the active timers -+ * @expired: list head for deferred timers. - * @get_time: function to retrieve the current time of the clock - * @offset: offset of this clock to the monotonic base - */ -@@ -144,6 +149,7 @@ - int index; - clockid_t clockid; - struct timerqueue_head active; -+ struct list_head expired; - ktime_t (*get_time)(void); - ktime_t offset; - } __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN))); -@@ -187,6 +193,7 @@ - raw_spinlock_t lock; - seqcount_t seq; - struct hrtimer *running; -+ struct hrtimer *running_soft; - unsigned int cpu; - unsigned int active_bases; - unsigned int clock_was_set_seq; -@@ -203,6 +210,9 @@ - unsigned int nr_hangs; - unsigned int max_hang_time; - #endif -+#ifdef CONFIG_PREEMPT_RT_BASE -+ wait_queue_head_t wait; -+#endif - struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; - } ____cacheline_aligned; - -@@ -412,6 +422,13 @@ - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); - } - -+/* Softirq preemption could deadlock timer removal */ -+#ifdef CONFIG_PREEMPT_RT_BASE -+ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); -+#else -+# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) -+#endif -+ - /* Query timers: */ - extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); - -@@ -436,7 +453,7 @@ - * Helper function to check, whether the timer is running the callback - * function - */ --static inline int hrtimer_callback_running(struct hrtimer *timer) -+static inline int hrtimer_callback_running(const struct hrtimer *timer) - { - return timer->base->cpu_base->running == timer; - } -diff -Nur linux-4.4.28.orig/include/linux/idr.h linux-4.4.28/include/linux/idr.h ---- linux-4.4.28.orig/include/linux/idr.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/idr.h 2016-11-01 21:26:58.728339185 +0100 -@@ -95,10 +95,14 @@ - * Each idr_preload() should be matched with an invocation of this - * function. See idr_preload() for details. - */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+void idr_preload_end(void); -+#else - static inline void idr_preload_end(void) - { - preempt_enable(); - } -+#endif - - /** - * idr_find - return pointer for given id -diff -Nur linux-4.4.28.orig/include/linux/init_task.h linux-4.4.28/include/linux/init_task.h ---- linux-4.4.28.orig/include/linux/init_task.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/init_task.h 2016-11-01 21:26:58.728339185 +0100 -@@ -148,9 +148,15 @@ - # define INIT_PERF_EVENTS(tsk) - #endif - -+#ifdef CONFIG_PREEMPT_RT_BASE -+# define INIT_TIMER_LIST .posix_timer_list = NULL, -+#else -+# define INIT_TIMER_LIST -+#endif -+ - #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - # define INIT_VTIME(tsk) \ -- .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ -+ .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ - .vtime_snap = 0, \ - .vtime_snap_whence = VTIME_SYS, - #else -@@ -239,6 +245,7 @@ - .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ - .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ - .timer_slack_ns = 50000, /* 50 usec default slack */ \ -+ INIT_TIMER_LIST \ - .pids = { \ - [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ - [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ -diff -Nur linux-4.4.28.orig/include/linux/interrupt.h linux-4.4.28/include/linux/interrupt.h ---- linux-4.4.28.orig/include/linux/interrupt.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/interrupt.h 2016-11-01 21:26:58.728339185 +0100 -@@ -61,6 +61,7 @@ - * interrupt handler after suspending interrupts. For system - * wakeup devices users need to implement wakeup detection in - * their interrupt handlers. -+ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) - */ - #define IRQF_SHARED 0x00000080 - #define IRQF_PROBE_SHARED 0x00000100 -@@ -74,6 +75,7 @@ - #define IRQF_NO_THREAD 0x00010000 - #define IRQF_EARLY_RESUME 0x00020000 - #define IRQF_COND_SUSPEND 0x00040000 -+#define IRQF_NO_SOFTIRQ_CALL 0x00080000 - - #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) - -@@ -186,7 +188,7 @@ - #ifdef CONFIG_LOCKDEP - # define local_irq_enable_in_hardirq() do { } while (0) - #else --# define local_irq_enable_in_hardirq() local_irq_enable() -+# define local_irq_enable_in_hardirq() local_irq_enable_nort() - #endif - - extern void disable_irq_nosync(unsigned int irq); -@@ -206,6 +208,7 @@ - * @irq: Interrupt to which notification applies - * @kref: Reference count, for internal use - * @work: Work item, for internal use -+ * @list: List item for deferred callbacks - * @notify: Function to be called on change. This will be - * called in process context. - * @release: Function to be called on release. This will be -@@ -217,6 +220,7 @@ - unsigned int irq; - struct kref kref; - struct work_struct work; -+ struct list_head list; - void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); - void (*release)(struct kref *ref); - }; -@@ -379,9 +383,13 @@ - bool state); - - #ifdef CONFIG_IRQ_FORCED_THREADING -+# ifndef CONFIG_PREEMPT_RT_BASE - extern bool force_irqthreads; -+# else -+# define force_irqthreads (true) -+# endif - #else --#define force_irqthreads (0) -+#define force_irqthreads (false) - #endif - - #ifndef __ARCH_SET_SOFTIRQ_PENDING -@@ -438,9 +446,10 @@ - void (*action)(struct softirq_action *); - }; - -+#ifndef CONFIG_PREEMPT_RT_FULL - asmlinkage void do_softirq(void); - asmlinkage void __do_softirq(void); -- -+static inline void thread_do_softirq(void) { do_softirq(); } - #ifdef __ARCH_HAS_DO_SOFTIRQ - void do_softirq_own_stack(void); - #else -@@ -449,13 +458,25 @@ - __do_softirq(); - } - #endif -+#else -+extern void thread_do_softirq(void); -+#endif - - extern void open_softirq(int nr, void (*action)(struct softirq_action *)); - extern void softirq_init(void); - extern void __raise_softirq_irqoff(unsigned int nr); -+#ifdef CONFIG_PREEMPT_RT_FULL -+extern void __raise_softirq_irqoff_ksoft(unsigned int nr); -+#else -+static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) -+{ -+ __raise_softirq_irqoff(nr); -+} -+#endif - - extern void raise_softirq_irqoff(unsigned int nr); - extern void raise_softirq(unsigned int nr); -+extern void softirq_check_pending_idle(void); - - DECLARE_PER_CPU(struct task_struct *, ksoftirqd); - -@@ -477,8 +498,9 @@ - to be executed on some cpu at least once after this. - * If the tasklet is already scheduled, but its execution is still not - started, it will be executed only once. -- * If this tasklet is already running on another CPU (or schedule is called -- from tasklet itself), it is rescheduled for later. -+ * If this tasklet is already running on another CPU, it is rescheduled -+ for later. -+ * Schedule must not be called from the tasklet itself (a lockup occurs) - * Tasklet is strictly serialized wrt itself, but not - wrt another tasklets. If client needs some intertask synchronization, - he makes it with spinlocks. -@@ -503,27 +525,36 @@ - enum - { - TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ -- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ -+ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ -+ TASKLET_STATE_PENDING /* Tasklet is pending */ - }; - --#ifdef CONFIG_SMP -+#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) -+#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) -+#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) -+ -+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) - static inline int tasklet_trylock(struct tasklet_struct *t) - { - return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); - } - -+static inline int tasklet_tryunlock(struct tasklet_struct *t) -+{ -+ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; -+} -+ - static inline void tasklet_unlock(struct tasklet_struct *t) - { - smp_mb__before_atomic(); - clear_bit(TASKLET_STATE_RUN, &(t)->state); - } - --static inline void tasklet_unlock_wait(struct tasklet_struct *t) --{ -- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } --} -+extern void tasklet_unlock_wait(struct tasklet_struct *t); -+ - #else - #define tasklet_trylock(t) 1 -+#define tasklet_tryunlock(t) 1 - #define tasklet_unlock_wait(t) do { } while (0) - #define tasklet_unlock(t) do { } while (0) - #endif -@@ -572,12 +603,7 @@ - smp_mb(); - } - --static inline void tasklet_enable(struct tasklet_struct *t) --{ -- smp_mb__before_atomic(); -- atomic_dec(&t->count); --} -- -+extern void tasklet_enable(struct tasklet_struct *t); - extern void tasklet_kill(struct tasklet_struct *t); - extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); - extern void tasklet_init(struct tasklet_struct *t, -@@ -608,6 +634,12 @@ - tasklet_kill(&ttimer->tasklet); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+extern void softirq_early_init(void); -+#else -+static inline void softirq_early_init(void) { } -+#endif -+ - /* - * Autoprobing for irqs: - * -diff -Nur linux-4.4.28.orig/include/linux/irqdesc.h linux-4.4.28/include/linux/irqdesc.h ---- linux-4.4.28.orig/include/linux/irqdesc.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/irqdesc.h 2016-11-01 21:26:58.732339449 +0100 -@@ -61,6 +61,7 @@ - unsigned int irqs_unhandled; - atomic_t threads_handled; - int threads_handled_last; -+ u64 random_ip; - raw_spinlock_t lock; - struct cpumask *percpu_enabled; - #ifdef CONFIG_SMP -diff -Nur linux-4.4.28.orig/include/linux/irqflags.h linux-4.4.28/include/linux/irqflags.h ---- linux-4.4.28.orig/include/linux/irqflags.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/irqflags.h 2016-11-01 21:26:58.732339449 +0100 -@@ -25,8 +25,6 @@ - # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) - # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) - # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) --# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) --# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) - # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, - #else - # define trace_hardirqs_on() do { } while (0) -@@ -39,9 +37,15 @@ - # define trace_softirqs_enabled(p) 0 - # define trace_hardirq_enter() do { } while (0) - # define trace_hardirq_exit() do { } while (0) -+# define INIT_TRACE_IRQFLAGS -+#endif -+ -+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) -+# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) -+# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) -+#else - # define lockdep_softirq_enter() do { } while (0) - # define lockdep_softirq_exit() do { } while (0) --# define INIT_TRACE_IRQFLAGS - #endif - - #if defined(CONFIG_IRQSOFF_TRACER) || \ -@@ -148,4 +152,23 @@ - - #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) - -+/* -+ * local_irq* variants depending on RT/!RT -+ */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define local_irq_disable_nort() do { } while (0) -+# define local_irq_enable_nort() do { } while (0) -+# define local_irq_save_nort(flags) local_save_flags(flags) -+# define local_irq_restore_nort(flags) (void)(flags) -+# define local_irq_disable_rt() local_irq_disable() -+# define local_irq_enable_rt() local_irq_enable() -+#else -+# define local_irq_disable_nort() local_irq_disable() -+# define local_irq_enable_nort() local_irq_enable() -+# define local_irq_save_nort(flags) local_irq_save(flags) -+# define local_irq_restore_nort(flags) local_irq_restore(flags) -+# define local_irq_disable_rt() do { } while (0) -+# define local_irq_enable_rt() do { } while (0) -+#endif -+ - #endif -diff -Nur linux-4.4.28.orig/include/linux/irq.h linux-4.4.28/include/linux/irq.h ---- linux-4.4.28.orig/include/linux/irq.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/irq.h 2016-11-01 21:26:58.728339185 +0100 -@@ -72,6 +72,7 @@ - * IRQ_IS_POLLED - Always polled by another interrupt. Exclude - * it from the spurious interrupt detection - * mechanism and from core side polling. -+ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) - * IRQ_DISABLE_UNLAZY - Disable lazy irq disable - */ - enum { -@@ -99,13 +100,14 @@ - IRQ_PER_CPU_DEVID = (1 << 17), - IRQ_IS_POLLED = (1 << 18), - IRQ_DISABLE_UNLAZY = (1 << 19), -+ IRQ_NO_SOFTIRQ_CALL = (1 << 20), - }; - - #define IRQF_MODIFY_MASK \ - (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ - IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ - IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ -- IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) -+ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) - - #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) - -diff -Nur linux-4.4.28.orig/include/linux/irq_work.h linux-4.4.28/include/linux/irq_work.h ---- linux-4.4.28.orig/include/linux/irq_work.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/irq_work.h 2016-11-01 21:26:58.728339185 +0100 -@@ -16,6 +16,7 @@ - #define IRQ_WORK_BUSY 2UL - #define IRQ_WORK_FLAGS 3UL - #define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */ -+#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */ - - struct irq_work { - unsigned long flags; -@@ -51,4 +52,10 @@ - static inline void irq_work_run(void) { } - #endif - -+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) -+void irq_work_tick_soft(void); -+#else -+static inline void irq_work_tick_soft(void) { } -+#endif -+ - #endif /* _LINUX_IRQ_WORK_H */ -diff -Nur linux-4.4.28.orig/include/linux/jbd2.h linux-4.4.28/include/linux/jbd2.h ---- linux-4.4.28.orig/include/linux/jbd2.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/jbd2.h 2016-11-01 21:26:58.732339449 +0100 -@@ -352,32 +352,56 @@ - - static inline void jbd_lock_bh_state(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_lock(BH_State, &bh->b_state); -+#else -+ spin_lock(&bh->b_state_lock); -+#endif - } - - static inline int jbd_trylock_bh_state(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - return bit_spin_trylock(BH_State, &bh->b_state); -+#else -+ return spin_trylock(&bh->b_state_lock); -+#endif - } - - static inline int jbd_is_locked_bh_state(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - return bit_spin_is_locked(BH_State, &bh->b_state); -+#else -+ return spin_is_locked(&bh->b_state_lock); -+#endif - } - - static inline void jbd_unlock_bh_state(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_unlock(BH_State, &bh->b_state); -+#else -+ spin_unlock(&bh->b_state_lock); -+#endif - } - - static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_lock(BH_JournalHead, &bh->b_state); -+#else -+ spin_lock(&bh->b_journal_head_lock); -+#endif - } - - static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_unlock(BH_JournalHead, &bh->b_state); -+#else -+ spin_unlock(&bh->b_journal_head_lock); -+#endif - } - - #define J_ASSERT(assert) BUG_ON(!(assert)) -diff -Nur linux-4.4.28.orig/include/linux/kdb.h linux-4.4.28/include/linux/kdb.h ---- linux-4.4.28.orig/include/linux/kdb.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/kdb.h 2016-11-01 21:26:58.732339449 +0100 -@@ -167,6 +167,7 @@ - extern __printf(1, 2) int kdb_printf(const char *, ...); - typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); - -+#define in_kdb_printk() (kdb_trap_printk) - extern void kdb_init(int level); - - /* Access to kdb specific polling devices */ -@@ -201,6 +202,7 @@ - extern int kdb_unregister(char *); - #else /* ! CONFIG_KGDB_KDB */ - static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } -+#define in_kdb_printk() (0) - static inline void kdb_init(int level) {} - static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, - char *help, short minlen) { return 0; } -diff -Nur linux-4.4.28.orig/include/linux/kernel.h linux-4.4.28/include/linux/kernel.h ---- linux-4.4.28.orig/include/linux/kernel.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/kernel.h 2016-11-01 21:26:58.732339449 +0100 -@@ -188,6 +188,9 @@ - */ - # define might_sleep() \ - do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) -+ -+# define might_sleep_no_state_check() \ -+ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) - # define sched_annotate_sleep() (current->task_state_change = 0) - #else - static inline void ___might_sleep(const char *file, int line, -@@ -195,6 +198,7 @@ - static inline void __might_sleep(const char *file, int line, - int preempt_offset) { } - # define might_sleep() do { might_resched(); } while (0) -+# define might_sleep_no_state_check() do { might_resched(); } while (0) - # define sched_annotate_sleep() do { } while (0) - #endif - -@@ -255,6 +259,7 @@ - __printf(1, 2) - void panic(const char *fmt, ...) - __noreturn __cold; -+void nmi_panic(struct pt_regs *regs, const char *msg); - extern void oops_enter(void); - extern void oops_exit(void); - void print_oops_end_marker(void); -@@ -448,6 +453,14 @@ - extern bool crash_kexec_post_notifiers; - - /* -+ * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It -+ * holds a CPU number which is executing panic() currently. A value of -+ * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). -+ */ -+extern atomic_t panic_cpu; -+#define PANIC_CPU_INVALID -1 -+ -+/* - * Only to be used by arch init code. If the user over-wrote the default - * CONFIG_PANIC_TIMEOUT, honor it. - */ -@@ -475,6 +488,7 @@ - SYSTEM_HALT, - SYSTEM_POWER_OFF, - SYSTEM_RESTART, -+ SYSTEM_SUSPEND, - } system_state; - - #define TAINT_PROPRIETARY_MODULE 0 -diff -Nur linux-4.4.28.orig/include/linux/kvm_host.h linux-4.4.28/include/linux/kvm_host.h ---- linux-4.4.28.orig/include/linux/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/kvm_host.h 2016-11-01 21:26:58.732339449 +0100 -@@ -25,6 +25,7 @@ - #include - #include - #include -+#include - #include - - #include -@@ -243,7 +244,7 @@ - int fpu_active; - int guest_fpu_loaded, guest_xcr0_loaded; - unsigned char fpu_counter; -- wait_queue_head_t wq; -+ struct swait_queue_head wq; - struct pid *pid; - int sigset_active; - sigset_t sigset; -@@ -794,7 +795,7 @@ - } - #endif - --static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) -+static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) - { - #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; -diff -Nur linux-4.4.28.orig/include/linux/lglock.h linux-4.4.28/include/linux/lglock.h ---- linux-4.4.28.orig/include/linux/lglock.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/lglock.h 2016-11-01 21:26:58.732339449 +0100 -@@ -34,13 +34,30 @@ - #endif - - struct lglock { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ struct rt_mutex __percpu *lock; -+#else - arch_spinlock_t __percpu *lock; -+#endif - #ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lock_key; - struct lockdep_map lock_dep_map; - #endif - }; - -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define DEFINE_LGLOCK(name) \ -+ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ -+ = __RT_MUTEX_INITIALIZER( name ## _lock); \ -+ struct lglock name = { .lock = &name ## _lock } -+ -+# define DEFINE_STATIC_LGLOCK(name) \ -+ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ -+ = __RT_MUTEX_INITIALIZER( name ## _lock); \ -+ static struct lglock name = { .lock = &name ## _lock } -+ -+#else -+ - #define DEFINE_LGLOCK(name) \ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ -@@ -50,6 +67,7 @@ - static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ - = __ARCH_SPIN_LOCK_UNLOCKED; \ - static struct lglock name = { .lock = &name ## _lock } -+#endif - - void lg_lock_init(struct lglock *lg, char *name); - -@@ -64,6 +82,12 @@ - void lg_global_lock(struct lglock *lg); - void lg_global_unlock(struct lglock *lg); - -+#ifndef CONFIG_PREEMPT_RT_FULL -+#define lg_global_trylock_relax(name) lg_global_lock(name) -+#else -+void lg_global_trylock_relax(struct lglock *lg); -+#endif -+ - #else - /* When !CONFIG_SMP, map lglock to spinlock */ - #define lglock spinlock -diff -Nur linux-4.4.28.orig/include/linux/list_bl.h linux-4.4.28/include/linux/list_bl.h ---- linux-4.4.28.orig/include/linux/list_bl.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/list_bl.h 2016-11-01 21:26:58.732339449 +0100 -@@ -2,6 +2,7 @@ - #define _LINUX_LIST_BL_H - - #include -+#include - #include - - /* -@@ -32,13 +33,24 @@ - - struct hlist_bl_head { - struct hlist_bl_node *first; -+#ifdef CONFIG_PREEMPT_RT_BASE -+ raw_spinlock_t lock; -+#endif - }; - - struct hlist_bl_node { - struct hlist_bl_node *next, **pprev; - }; --#define INIT_HLIST_BL_HEAD(ptr) \ -- ((ptr)->first = NULL) -+ -+#ifdef CONFIG_PREEMPT_RT_BASE -+#define INIT_HLIST_BL_HEAD(h) \ -+do { \ -+ (h)->first = NULL; \ -+ raw_spin_lock_init(&(h)->lock); \ -+} while (0) -+#else -+#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL -+#endif - - static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) - { -@@ -118,12 +130,26 @@ - - static inline void hlist_bl_lock(struct hlist_bl_head *b) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - bit_spin_lock(0, (unsigned long *)b); -+#else -+ raw_spin_lock(&b->lock); -+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -+ __set_bit(0, (unsigned long *)b); -+#endif -+#endif - } - - static inline void hlist_bl_unlock(struct hlist_bl_head *b) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - __bit_spin_unlock(0, (unsigned long *)b); -+#else -+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) -+ __clear_bit(0, (unsigned long *)b); -+#endif -+ raw_spin_unlock(&b->lock); -+#endif - } - - static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) -diff -Nur linux-4.4.28.orig/include/linux/locallock.h linux-4.4.28/include/linux/locallock.h ---- linux-4.4.28.orig/include/linux/locallock.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/locallock.h 2016-11-01 21:26:58.732339449 +0100 -@@ -0,0 +1,276 @@ -+#ifndef _LINUX_LOCALLOCK_H -+#define _LINUX_LOCALLOCK_H -+ -+#include -+#include -+ -+#ifdef CONFIG_PREEMPT_RT_BASE -+ -+#ifdef CONFIG_DEBUG_SPINLOCK -+# define LL_WARN(cond) WARN_ON(cond) -+#else -+# define LL_WARN(cond) do { } while (0) -+#endif -+ -+/* -+ * per cpu lock based substitute for local_irq_*() -+ */ -+struct local_irq_lock { -+ spinlock_t lock; -+ struct task_struct *owner; -+ int nestcnt; -+ unsigned long flags; -+}; -+ -+#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ -+ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ -+ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } -+ -+#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ -+ DECLARE_PER_CPU(struct local_irq_lock, lvar) -+ -+#define local_irq_lock_init(lvar) \ -+ do { \ -+ int __cpu; \ -+ for_each_possible_cpu(__cpu) \ -+ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ -+ } while (0) -+ -+/* -+ * spin_lock|trylock|unlock_local flavour that does not migrate disable -+ * used for __local_lock|trylock|unlock where get_local_var/put_local_var -+ * already takes care of the migrate_disable/enable -+ * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. -+ */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define spin_lock_local(lock) rt_spin_lock__no_mg(lock) -+# define spin_trylock_local(lock) rt_spin_trylock__no_mg(lock) -+# define spin_unlock_local(lock) rt_spin_unlock__no_mg(lock) -+#else -+# define spin_lock_local(lock) spin_lock(lock) -+# define spin_trylock_local(lock) spin_trylock(lock) -+# define spin_unlock_local(lock) spin_unlock(lock) -+#endif -+ -+static inline void __local_lock(struct local_irq_lock *lv) -+{ -+ if (lv->owner != current) { -+ spin_lock_local(&lv->lock); -+ LL_WARN(lv->owner); -+ LL_WARN(lv->nestcnt); -+ lv->owner = current; -+ } -+ lv->nestcnt++; -+} -+ -+#define local_lock(lvar) \ -+ do { __local_lock(&get_local_var(lvar)); } while (0) -+ -+#define local_lock_on(lvar, cpu) \ -+ do { __local_lock(&per_cpu(lvar, cpu)); } while (0) -+ -+static inline int __local_trylock(struct local_irq_lock *lv) -+{ -+ if (lv->owner != current && spin_trylock_local(&lv->lock)) { -+ LL_WARN(lv->owner); -+ LL_WARN(lv->nestcnt); -+ lv->owner = current; -+ lv->nestcnt = 1; -+ return 1; -+ } -+ return 0; -+} -+ -+#define local_trylock(lvar) \ -+ ({ \ -+ int __locked; \ -+ __locked = __local_trylock(&get_local_var(lvar)); \ -+ if (!__locked) \ -+ put_local_var(lvar); \ -+ __locked; \ -+ }) -+ -+static inline void __local_unlock(struct local_irq_lock *lv) -+{ -+ LL_WARN(lv->nestcnt == 0); -+ LL_WARN(lv->owner != current); -+ if (--lv->nestcnt) -+ return; -+ -+ lv->owner = NULL; -+ spin_unlock_local(&lv->lock); -+} -+ -+#define local_unlock(lvar) \ -+ do { \ -+ __local_unlock(this_cpu_ptr(&lvar)); \ -+ put_local_var(lvar); \ -+ } while (0) -+ -+#define local_unlock_on(lvar, cpu) \ -+ do { __local_unlock(&per_cpu(lvar, cpu)); } while (0) -+ -+static inline void __local_lock_irq(struct local_irq_lock *lv) -+{ -+ spin_lock_irqsave(&lv->lock, lv->flags); -+ LL_WARN(lv->owner); -+ LL_WARN(lv->nestcnt); -+ lv->owner = current; -+ lv->nestcnt = 1; -+} -+ -+#define local_lock_irq(lvar) \ -+ do { __local_lock_irq(&get_local_var(lvar)); } while (0) -+ -+#define local_lock_irq_on(lvar, cpu) \ -+ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) -+ -+static inline void __local_unlock_irq(struct local_irq_lock *lv) -+{ -+ LL_WARN(!lv->nestcnt); -+ LL_WARN(lv->owner != current); -+ lv->owner = NULL; -+ lv->nestcnt = 0; -+ spin_unlock_irq(&lv->lock); -+} -+ -+#define local_unlock_irq(lvar) \ -+ do { \ -+ __local_unlock_irq(this_cpu_ptr(&lvar)); \ -+ put_local_var(lvar); \ -+ } while (0) -+ -+#define local_unlock_irq_on(lvar, cpu) \ -+ do { \ -+ __local_unlock_irq(&per_cpu(lvar, cpu)); \ -+ } while (0) -+ -+static inline int __local_lock_irqsave(struct local_irq_lock *lv) -+{ -+ if (lv->owner != current) { -+ __local_lock_irq(lv); -+ return 0; -+ } else { -+ lv->nestcnt++; -+ return 1; -+ } -+} -+ -+#define local_lock_irqsave(lvar, _flags) \ -+ do { \ -+ if (__local_lock_irqsave(&get_local_var(lvar))) \ -+ put_local_var(lvar); \ -+ _flags = __this_cpu_read(lvar.flags); \ -+ } while (0) -+ -+#define local_lock_irqsave_on(lvar, _flags, cpu) \ -+ do { \ -+ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ -+ _flags = per_cpu(lvar, cpu).flags; \ -+ } while (0) -+ -+static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, -+ unsigned long flags) -+{ -+ LL_WARN(!lv->nestcnt); -+ LL_WARN(lv->owner != current); -+ if (--lv->nestcnt) -+ return 0; -+ -+ lv->owner = NULL; -+ spin_unlock_irqrestore(&lv->lock, lv->flags); -+ return 1; -+} -+ -+#define local_unlock_irqrestore(lvar, flags) \ -+ do { \ -+ if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ -+ put_local_var(lvar); \ -+ } while (0) -+ -+#define local_unlock_irqrestore_on(lvar, flags, cpu) \ -+ do { \ -+ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ -+ } while (0) -+ -+#define local_spin_trylock_irq(lvar, lock) \ -+ ({ \ -+ int __locked; \ -+ local_lock_irq(lvar); \ -+ __locked = spin_trylock(lock); \ -+ if (!__locked) \ -+ local_unlock_irq(lvar); \ -+ __locked; \ -+ }) -+ -+#define local_spin_lock_irq(lvar, lock) \ -+ do { \ -+ local_lock_irq(lvar); \ -+ spin_lock(lock); \ -+ } while (0) -+ -+#define local_spin_unlock_irq(lvar, lock) \ -+ do { \ -+ spin_unlock(lock); \ -+ local_unlock_irq(lvar); \ -+ } while (0) -+ -+#define local_spin_lock_irqsave(lvar, lock, flags) \ -+ do { \ -+ local_lock_irqsave(lvar, flags); \ -+ spin_lock(lock); \ -+ } while (0) -+ -+#define local_spin_unlock_irqrestore(lvar, lock, flags) \ -+ do { \ -+ spin_unlock(lock); \ -+ local_unlock_irqrestore(lvar, flags); \ -+ } while (0) -+ -+#define get_locked_var(lvar, var) \ -+ (*({ \ -+ local_lock(lvar); \ -+ this_cpu_ptr(&var); \ -+ })) -+ -+#define put_locked_var(lvar, var) local_unlock(lvar); -+ -+#define local_lock_cpu(lvar) \ -+ ({ \ -+ local_lock(lvar); \ -+ smp_processor_id(); \ -+ }) -+ -+#define local_unlock_cpu(lvar) local_unlock(lvar) -+ -+#else /* PREEMPT_RT_BASE */ -+ -+#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar -+#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar -+ -+static inline void local_irq_lock_init(int lvar) { } -+ -+#define local_lock(lvar) preempt_disable() -+#define local_unlock(lvar) preempt_enable() -+#define local_lock_irq(lvar) local_irq_disable() -+#define local_unlock_irq(lvar) local_irq_enable() -+#define local_lock_irqsave(lvar, flags) local_irq_save(flags) -+#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) -+ -+#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) -+#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) -+#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) -+#define local_spin_lock_irqsave(lvar, lock, flags) \ -+ spin_lock_irqsave(lock, flags) -+#define local_spin_unlock_irqrestore(lvar, lock, flags) \ -+ spin_unlock_irqrestore(lock, flags) -+ -+#define get_locked_var(lvar, var) get_cpu_var(var) -+#define put_locked_var(lvar, var) put_cpu_var(var) -+ -+#define local_lock_cpu(lvar) get_cpu() -+#define local_unlock_cpu(lvar) put_cpu() -+ -+#endif -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/mm_types.h linux-4.4.28/include/linux/mm_types.h ---- linux-4.4.28.orig/include/linux/mm_types.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/mm_types.h 2016-11-01 21:26:58.732339449 +0100 -@@ -11,6 +11,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -504,6 +505,9 @@ - bool tlb_flush_pending; - #endif - struct uprobes_state uprobes_state; -+#ifdef CONFIG_PREEMPT_RT_BASE -+ struct rcu_head delayed_drop; -+#endif - #ifdef CONFIG_X86_INTEL_MPX - /* address of the bounds directory */ - void __user *bd_addr; -diff -Nur linux-4.4.28.orig/include/linux/mutex.h linux-4.4.28/include/linux/mutex.h ---- linux-4.4.28.orig/include/linux/mutex.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/mutex.h 2016-11-01 21:26:58.732339449 +0100 -@@ -19,6 +19,17 @@ - #include - #include - -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ -+ , .dep_map = { .name = #lockname } -+#else -+# define __DEP_MAP_MUTEX_INITIALIZER(lockname) -+#endif -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+# include -+#else -+ - /* - * Simple, straightforward mutexes with strict semantics: - * -@@ -99,13 +110,6 @@ - static inline void mutex_destroy(struct mutex *lock) {} - #endif - --#ifdef CONFIG_DEBUG_LOCK_ALLOC --# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ -- , .dep_map = { .name = #lockname } --#else --# define __DEP_MAP_MUTEX_INITIALIZER(lockname) --#endif -- - #define __MUTEX_INITIALIZER(lockname) \ - { .count = ATOMIC_INIT(1) \ - , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ -@@ -173,6 +177,8 @@ - extern int mutex_trylock(struct mutex *lock); - extern void mutex_unlock(struct mutex *lock); - -+#endif /* !PREEMPT_RT_FULL */ -+ - extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); - - #endif /* __LINUX_MUTEX_H */ -diff -Nur linux-4.4.28.orig/include/linux/mutex_rt.h linux-4.4.28/include/linux/mutex_rt.h ---- linux-4.4.28.orig/include/linux/mutex_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/mutex_rt.h 2016-11-01 21:26:58.732339449 +0100 -@@ -0,0 +1,84 @@ -+#ifndef __LINUX_MUTEX_RT_H -+#define __LINUX_MUTEX_RT_H -+ -+#ifndef __LINUX_MUTEX_H -+#error "Please include mutex.h" -+#endif -+ -+#include -+ -+/* FIXME: Just for __lockfunc */ -+#include -+ -+struct mutex { -+ struct rt_mutex lock; -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ struct lockdep_map dep_map; -+#endif -+}; -+ -+#define __MUTEX_INITIALIZER(mutexname) \ -+ { \ -+ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ -+ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ -+ } -+ -+#define DEFINE_MUTEX(mutexname) \ -+ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -+ -+extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); -+extern void __lockfunc _mutex_lock(struct mutex *lock); -+extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); -+extern int __lockfunc _mutex_lock_killable(struct mutex *lock); -+extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); -+extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); -+extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); -+extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); -+extern int __lockfunc _mutex_trylock(struct mutex *lock); -+extern void __lockfunc _mutex_unlock(struct mutex *lock); -+ -+#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) -+#define mutex_lock(l) _mutex_lock(l) -+#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) -+#define mutex_lock_killable(l) _mutex_lock_killable(l) -+#define mutex_trylock(l) _mutex_trylock(l) -+#define mutex_unlock(l) _mutex_unlock(l) -+#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) -+# define mutex_lock_interruptible_nested(l, s) \ -+ _mutex_lock_interruptible_nested(l, s) -+# define mutex_lock_killable_nested(l, s) \ -+ _mutex_lock_killable_nested(l, s) -+ -+# define mutex_lock_nest_lock(lock, nest_lock) \ -+do { \ -+ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ -+ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ -+} while (0) -+ -+#else -+# define mutex_lock_nested(l, s) _mutex_lock(l) -+# define mutex_lock_interruptible_nested(l, s) \ -+ _mutex_lock_interruptible(l) -+# define mutex_lock_killable_nested(l, s) \ -+ _mutex_lock_killable(l) -+# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) -+#endif -+ -+# define mutex_init(mutex) \ -+do { \ -+ static struct lock_class_key __key; \ -+ \ -+ rt_mutex_init(&(mutex)->lock); \ -+ __mutex_do_init((mutex), #mutex, &__key); \ -+} while (0) -+ -+# define __mutex_init(mutex, name, key) \ -+do { \ -+ rt_mutex_init(&(mutex)->lock); \ -+ __mutex_do_init((mutex), name, key); \ -+} while (0) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/netdevice.h linux-4.4.28/include/linux/netdevice.h ---- linux-4.4.28.orig/include/linux/netdevice.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/netdevice.h 2016-11-01 21:26:58.736339702 +0100 -@@ -2248,11 +2248,20 @@ - void synchronize_net(void); - int init_dummy_netdev(struct net_device *dev); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static inline int dev_recursion_level(void) -+{ -+ return current->xmit_recursion; -+} -+ -+#else -+ - DECLARE_PER_CPU(int, xmit_recursion); - static inline int dev_recursion_level(void) - { - return this_cpu_read(xmit_recursion); - } -+#endif - - struct net_device *dev_get_by_index(struct net *net, int ifindex); - struct net_device *__dev_get_by_index(struct net *net, int ifindex); -@@ -2563,6 +2572,7 @@ - unsigned int dropped; - struct sk_buff_head input_pkt_queue; - struct napi_struct backlog; -+ struct sk_buff_head tofree_queue; - - }; - -diff -Nur linux-4.4.28.orig/include/linux/netfilter/x_tables.h linux-4.4.28/include/linux/netfilter/x_tables.h ---- linux-4.4.28.orig/include/linux/netfilter/x_tables.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/netfilter/x_tables.h 2016-11-01 21:26:58.736339702 +0100 -@@ -4,6 +4,7 @@ - - #include - #include -+#include - #include - - /** -@@ -289,6 +290,8 @@ - */ - DECLARE_PER_CPU(seqcount_t, xt_recseq); - -+DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); -+ - /* xt_tee_enabled - true if x_tables needs to handle reentrancy - * - * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. -@@ -309,6 +312,9 @@ - { - unsigned int addend; - -+ /* RT protection */ -+ local_lock(xt_write_lock); -+ - /* - * Low order bit of sequence is set if we already - * called xt_write_recseq_begin(). -@@ -339,6 +345,7 @@ - /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ - smp_wmb(); - __this_cpu_add(xt_recseq.sequence, addend); -+ local_unlock(xt_write_lock); - } - - /* -diff -Nur linux-4.4.28.orig/include/linux/notifier.h linux-4.4.28/include/linux/notifier.h ---- linux-4.4.28.orig/include/linux/notifier.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/notifier.h 2016-11-01 21:26:58.736339702 +0100 -@@ -6,7 +6,7 @@ - * - * Alan Cox - */ -- -+ - #ifndef _LINUX_NOTIFIER_H - #define _LINUX_NOTIFIER_H - #include -@@ -42,9 +42,7 @@ - * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. - * As compensation, srcu_notifier_chain_unregister() is rather expensive. - * SRCU notifier chains should be used when the chain will be called very -- * often but notifier_blocks will seldom be removed. Also, SRCU notifier -- * chains are slightly more difficult to use because they require special -- * runtime initialization. -+ * often but notifier_blocks will seldom be removed. - */ - - typedef int (*notifier_fn_t)(struct notifier_block *nb, -@@ -88,7 +86,7 @@ - (name)->head = NULL; \ - } while (0) - --/* srcu_notifier_heads must be initialized and cleaned up dynamically */ -+/* srcu_notifier_heads must be cleaned up dynamically */ - extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); - #define srcu_cleanup_notifier_head(name) \ - cleanup_srcu_struct(&(name)->srcu); -@@ -101,7 +99,13 @@ - .head = NULL } - #define RAW_NOTIFIER_INIT(name) { \ - .head = NULL } --/* srcu_notifier_heads cannot be initialized statically */ -+ -+#define SRCU_NOTIFIER_INIT(name, pcpu) \ -+ { \ -+ .mutex = __MUTEX_INITIALIZER(name.mutex), \ -+ .head = NULL, \ -+ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ -+ } - - #define ATOMIC_NOTIFIER_HEAD(name) \ - struct atomic_notifier_head name = \ -@@ -113,6 +117,18 @@ - struct raw_notifier_head name = \ - RAW_NOTIFIER_INIT(name) - -+#define _SRCU_NOTIFIER_HEAD(name, mod) \ -+ static DEFINE_PER_CPU(struct srcu_struct_array, \ -+ name##_head_srcu_array); \ -+ mod struct srcu_notifier_head name = \ -+ SRCU_NOTIFIER_INIT(name, name##_head_srcu_array) -+ -+#define SRCU_NOTIFIER_HEAD(name) \ -+ _SRCU_NOTIFIER_HEAD(name, ) -+ -+#define SRCU_NOTIFIER_HEAD_STATIC(name) \ -+ _SRCU_NOTIFIER_HEAD(name, static) -+ - #ifdef __KERNEL__ - - extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, -@@ -182,12 +198,12 @@ - - /* - * Declared notifiers so far. I can imagine quite a few more chains -- * over time (eg laptop power reset chains, reboot chain (to clean -+ * over time (eg laptop power reset chains, reboot chain (to clean - * device units up), device [un]mount chain, module load/unload chain, -- * low memory chain, screenblank chain (for plug in modular screenblankers) -+ * low memory chain, screenblank chain (for plug in modular screenblankers) - * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... - */ -- -+ - /* CPU notfiers are defined in include/linux/cpu.h. */ - - /* netdevice notifiers are defined in include/linux/netdevice.h */ -diff -Nur linux-4.4.28.orig/include/linux/percpu.h linux-4.4.28/include/linux/percpu.h ---- linux-4.4.28.orig/include/linux/percpu.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/percpu.h 2016-11-01 21:26:58.736339702 +0100 -@@ -24,6 +24,35 @@ - PERCPU_MODULE_RESERVE) - #endif - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ -+#define get_local_var(var) (*({ \ -+ migrate_disable(); \ -+ this_cpu_ptr(&var); })) -+ -+#define put_local_var(var) do { \ -+ (void)&(var); \ -+ migrate_enable(); \ -+} while (0) -+ -+# define get_local_ptr(var) ({ \ -+ migrate_disable(); \ -+ this_cpu_ptr(var); }) -+ -+# define put_local_ptr(var) do { \ -+ (void)(var); \ -+ migrate_enable(); \ -+} while (0) -+ -+#else -+ -+#define get_local_var(var) get_cpu_var(var) -+#define put_local_var(var) put_cpu_var(var) -+#define get_local_ptr(var) get_cpu_ptr(var) -+#define put_local_ptr(var) put_cpu_ptr(var) -+ -+#endif -+ - /* minimum unit size, also is the maximum supported allocation size */ - #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) - -diff -Nur linux-4.4.28.orig/include/linux/pid.h linux-4.4.28/include/linux/pid.h ---- linux-4.4.28.orig/include/linux/pid.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/pid.h 2016-11-01 21:26:58.736339702 +0100 -@@ -2,6 +2,7 @@ - #define _LINUX_PID_H - - #include -+#include - - enum pid_type - { -diff -Nur linux-4.4.28.orig/include/linux/preempt.h linux-4.4.28/include/linux/preempt.h ---- linux-4.4.28.orig/include/linux/preempt.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/preempt.h 2016-11-01 21:26:58.736339702 +0100 -@@ -50,7 +50,11 @@ - #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) - #define NMI_OFFSET (1UL << NMI_SHIFT) - --#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) -+#ifndef CONFIG_PREEMPT_RT_FULL -+# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) -+#else -+# define SOFTIRQ_DISABLE_OFFSET (0) -+#endif - - /* We use the MSB mostly because its available */ - #define PREEMPT_NEED_RESCHED 0x80000000 -@@ -59,9 +63,15 @@ - #include - - #define hardirq_count() (preempt_count() & HARDIRQ_MASK) --#define softirq_count() (preempt_count() & SOFTIRQ_MASK) - #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ - | NMI_MASK)) -+#ifndef CONFIG_PREEMPT_RT_FULL -+# define softirq_count() (preempt_count() & SOFTIRQ_MASK) -+# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) -+#else -+# define softirq_count() (0UL) -+extern int in_serving_softirq(void); -+#endif - - /* - * Are we doing bottom half or hardware interrupt processing? -@@ -72,7 +82,6 @@ - #define in_irq() (hardirq_count()) - #define in_softirq() (softirq_count()) - #define in_interrupt() (irq_count()) --#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) - - /* - * Are we in NMI context? -@@ -91,7 +100,11 @@ - /* - * The preempt_count offset after spin_lock() - */ -+#if !defined(CONFIG_PREEMPT_RT_FULL) - #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET -+#else -+#define PREEMPT_LOCK_OFFSET 0 -+#endif - - /* - * The preempt_count offset needed for things like: -@@ -140,6 +153,20 @@ - #define preempt_count_inc() preempt_count_add(1) - #define preempt_count_dec() preempt_count_sub(1) - -+#ifdef CONFIG_PREEMPT_LAZY -+#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) -+#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) -+#define inc_preempt_lazy_count() add_preempt_lazy_count(1) -+#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) -+#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) -+#else -+#define add_preempt_lazy_count(val) do { } while (0) -+#define sub_preempt_lazy_count(val) do { } while (0) -+#define inc_preempt_lazy_count() do { } while (0) -+#define dec_preempt_lazy_count() do { } while (0) -+#define preempt_lazy_count() (0) -+#endif -+ - #ifdef CONFIG_PREEMPT_COUNT - - #define preempt_disable() \ -@@ -148,13 +175,25 @@ - barrier(); \ - } while (0) - -+#define preempt_lazy_disable() \ -+do { \ -+ inc_preempt_lazy_count(); \ -+ barrier(); \ -+} while (0) -+ - #define sched_preempt_enable_no_resched() \ - do { \ - barrier(); \ - preempt_count_dec(); \ - } while (0) - --#define preempt_enable_no_resched() sched_preempt_enable_no_resched() -+#ifdef CONFIG_PREEMPT_RT_BASE -+# define preempt_enable_no_resched() sched_preempt_enable_no_resched() -+# define preempt_check_resched_rt() preempt_check_resched() -+#else -+# define preempt_enable_no_resched() preempt_enable() -+# define preempt_check_resched_rt() barrier(); -+#endif - - #define preemptible() (preempt_count() == 0 && !irqs_disabled()) - -@@ -179,6 +218,13 @@ - __preempt_schedule(); \ - } while (0) - -+#define preempt_lazy_enable() \ -+do { \ -+ dec_preempt_lazy_count(); \ -+ barrier(); \ -+ preempt_check_resched(); \ -+} while (0) -+ - #else /* !CONFIG_PREEMPT */ - #define preempt_enable() \ - do { \ -@@ -224,6 +270,7 @@ - #define preempt_disable_notrace() barrier() - #define preempt_enable_no_resched_notrace() barrier() - #define preempt_enable_notrace() barrier() -+#define preempt_check_resched_rt() barrier() - #define preemptible() 0 - - #endif /* CONFIG_PREEMPT_COUNT */ -@@ -244,10 +291,31 @@ - } while (0) - #define preempt_fold_need_resched() \ - do { \ -- if (tif_need_resched()) \ -+ if (tif_need_resched_now()) \ - set_preempt_need_resched(); \ - } while (0) - -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define preempt_disable_rt() preempt_disable() -+# define preempt_enable_rt() preempt_enable() -+# define preempt_disable_nort() barrier() -+# define preempt_enable_nort() barrier() -+# ifdef CONFIG_SMP -+ extern void migrate_disable(void); -+ extern void migrate_enable(void); -+# else /* CONFIG_SMP */ -+# define migrate_disable() barrier() -+# define migrate_enable() barrier() -+# endif /* CONFIG_SMP */ -+#else -+# define preempt_disable_rt() barrier() -+# define preempt_enable_rt() barrier() -+# define preempt_disable_nort() preempt_disable() -+# define preempt_enable_nort() preempt_enable() -+# define migrate_disable() preempt_disable() -+# define migrate_enable() preempt_enable() -+#endif -+ - #ifdef CONFIG_PREEMPT_NOTIFIERS - - struct preempt_notifier; -diff -Nur linux-4.4.28.orig/include/linux/printk.h linux-4.4.28/include/linux/printk.h ---- linux-4.4.28.orig/include/linux/printk.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/printk.h 2016-11-01 21:26:58.736339702 +0100 -@@ -117,9 +117,11 @@ - #ifdef CONFIG_EARLY_PRINTK - extern asmlinkage __printf(1, 2) - void early_printk(const char *fmt, ...); -+extern void printk_kill(void); - #else - static inline __printf(1, 2) __cold - void early_printk(const char *s, ...) { } -+static inline void printk_kill(void) { } - #endif - - typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); -diff -Nur linux-4.4.28.orig/include/linux/radix-tree.h linux-4.4.28/include/linux/radix-tree.h ---- linux-4.4.28.orig/include/linux/radix-tree.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/radix-tree.h 2016-11-01 21:26:58.736339702 +0100 -@@ -277,8 +277,13 @@ - unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, - void ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items); -+#ifndef CONFIG_PREEMPT_RT_FULL - int radix_tree_preload(gfp_t gfp_mask); - int radix_tree_maybe_preload(gfp_t gfp_mask); -+#else -+static inline int radix_tree_preload(gfp_t gm) { return 0; } -+static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; } -+#endif - void radix_tree_init(void); - void *radix_tree_tag_set(struct radix_tree_root *root, - unsigned long index, unsigned int tag); -@@ -303,7 +308,7 @@ - - static inline void radix_tree_preload_end(void) - { -- preempt_enable(); -+ preempt_enable_nort(); - } - - /** -diff -Nur linux-4.4.28.orig/include/linux/random.h linux-4.4.28/include/linux/random.h ---- linux-4.4.28.orig/include/linux/random.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/random.h 2016-11-01 21:26:58.736339702 +0100 -@@ -20,7 +20,7 @@ - extern void add_device_randomness(const void *, unsigned int); - extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value); --extern void add_interrupt_randomness(int irq, int irq_flags); -+extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); - - extern void get_random_bytes(void *buf, int nbytes); - extern int add_random_ready_callback(struct random_ready_callback *rdy); -diff -Nur linux-4.4.28.orig/include/linux/rbtree.h linux-4.4.28/include/linux/rbtree.h ---- linux-4.4.28.orig/include/linux/rbtree.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rbtree.h 2016-11-01 21:26:58.736339702 +0100 -@@ -31,7 +31,6 @@ - - #include - #include --#include - - struct rb_node { - unsigned long __rb_parent_color; -@@ -86,14 +85,8 @@ - *rb_link = node; - } - --static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, -- struct rb_node **rb_link) --{ -- node->__rb_parent_color = (unsigned long)parent; -- node->rb_left = node->rb_right = NULL; -- -- rcu_assign_pointer(*rb_link, node); --} -+void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, -+ struct rb_node **rb_link); - - #define rb_entry_safe(ptr, type, member) \ - ({ typeof(ptr) ____ptr = (ptr); \ -diff -Nur linux-4.4.28.orig/include/linux/rcupdate.h linux-4.4.28/include/linux/rcupdate.h ---- linux-4.4.28.orig/include/linux/rcupdate.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rcupdate.h 2016-11-01 21:26:58.740339958 +0100 -@@ -169,6 +169,9 @@ - - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - -+#ifdef CONFIG_PREEMPT_RT_FULL -+#define call_rcu_bh call_rcu -+#else - /** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. -@@ -192,6 +195,7 @@ - */ - void call_rcu_bh(struct rcu_head *head, - rcu_callback_t func); -+#endif - - /** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. -@@ -292,6 +296,11 @@ - * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. - */ - #define rcu_preempt_depth() (current->rcu_read_lock_nesting) -+#ifndef CONFIG_PREEMPT_RT_FULL -+#define sched_rcu_preempt_depth() rcu_preempt_depth() -+#else -+static inline int sched_rcu_preempt_depth(void) { return 0; } -+#endif - - #else /* #ifdef CONFIG_PREEMPT_RCU */ - -@@ -317,6 +326,8 @@ - return 0; - } - -+#define sched_rcu_preempt_depth() rcu_preempt_depth() -+ - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - - /* Internal to kernel */ -@@ -489,7 +500,14 @@ - int debug_lockdep_rcu_enabled(void); - - int rcu_read_lock_held(void); -+#ifdef CONFIG_PREEMPT_RT_FULL -+static inline int rcu_read_lock_bh_held(void) -+{ -+ return rcu_read_lock_held(); -+} -+#else - int rcu_read_lock_bh_held(void); -+#endif - - /** - * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? -@@ -937,10 +955,14 @@ - static inline void rcu_read_lock_bh(void) - { - local_bh_disable(); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ rcu_read_lock(); -+#else - __acquire(RCU_BH); - rcu_lock_acquire(&rcu_bh_lock_map); - RCU_LOCKDEP_WARN(!rcu_is_watching(), - "rcu_read_lock_bh() used illegally while idle"); -+#endif - } - - /* -@@ -950,10 +972,14 @@ - */ - static inline void rcu_read_unlock_bh(void) - { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ rcu_read_unlock(); -+#else - RCU_LOCKDEP_WARN(!rcu_is_watching(), - "rcu_read_unlock_bh() used illegally while idle"); - rcu_lock_release(&rcu_bh_lock_map); - __release(RCU_BH); -+#endif - local_bh_enable(); - } - -diff -Nur linux-4.4.28.orig/include/linux/rcutree.h linux-4.4.28/include/linux/rcutree.h ---- linux-4.4.28.orig/include/linux/rcutree.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rcutree.h 2016-11-01 21:26:58.740339958 +0100 -@@ -44,7 +44,11 @@ - rcu_note_context_switch(); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define synchronize_rcu_bh synchronize_rcu -+#else - void synchronize_rcu_bh(void); -+#endif - void synchronize_sched_expedited(void); - void synchronize_rcu_expedited(void); - -@@ -72,7 +76,11 @@ - } - - void rcu_barrier(void); -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define rcu_barrier_bh rcu_barrier -+#else - void rcu_barrier_bh(void); -+#endif - void rcu_barrier_sched(void); - unsigned long get_state_synchronize_rcu(void); - void cond_synchronize_rcu(unsigned long oldstate); -@@ -85,12 +93,10 @@ - unsigned long rcu_batches_started_bh(void); - unsigned long rcu_batches_started_sched(void); - unsigned long rcu_batches_completed(void); --unsigned long rcu_batches_completed_bh(void); - unsigned long rcu_batches_completed_sched(void); - void show_rcu_gp_kthreads(void); - - void rcu_force_quiescent_state(void); --void rcu_bh_force_quiescent_state(void); - void rcu_sched_force_quiescent_state(void); - - void rcu_idle_enter(void); -@@ -105,6 +111,14 @@ - - bool rcu_is_watching(void); - -+#ifndef CONFIG_PREEMPT_RT_FULL -+void rcu_bh_force_quiescent_state(void); -+unsigned long rcu_batches_completed_bh(void); -+#else -+# define rcu_bh_force_quiescent_state rcu_force_quiescent_state -+# define rcu_batches_completed_bh rcu_batches_completed -+#endif -+ - void rcu_all_qs(void); - - #endif /* __LINUX_RCUTREE_H */ -diff -Nur linux-4.4.28.orig/include/linux/rtmutex.h linux-4.4.28/include/linux/rtmutex.h ---- linux-4.4.28.orig/include/linux/rtmutex.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rtmutex.h 2016-11-01 21:26:58.740339958 +0100 -@@ -13,11 +13,15 @@ - #define __LINUX_RT_MUTEX_H - - #include -+#include - #include --#include - - extern int max_lock_depth; /* for sysctl */ - -+#ifdef CONFIG_DEBUG_MUTEXES -+#include -+#endif -+ - /** - * The rt_mutex structure - * -@@ -31,8 +35,8 @@ - struct rb_root waiters; - struct rb_node *waiters_leftmost; - struct task_struct *owner; --#ifdef CONFIG_DEBUG_RT_MUTEXES - int save_state; -+#ifdef CONFIG_DEBUG_RT_MUTEXES - const char *name, *file; - int line; - void *magic; -@@ -55,22 +59,33 @@ - # define rt_mutex_debug_check_no_locks_held(task) do { } while (0) - #endif - -+# define rt_mutex_init(mutex) \ -+ do { \ -+ raw_spin_lock_init(&(mutex)->wait_lock); \ -+ __rt_mutex_init(mutex, #mutex); \ -+ } while (0) -+ - #ifdef CONFIG_DEBUG_RT_MUTEXES - # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ - , .name = #mutexname, .file = __FILE__, .line = __LINE__ --# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) - extern void rt_mutex_debug_task_free(struct task_struct *tsk); - #else - # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) --# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) - # define rt_mutex_debug_task_free(t) do { } while (0) - #endif - --#define __RT_MUTEX_INITIALIZER(mutexname) \ -- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ -+#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ -+ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .waiters = RB_ROOT \ - , .owner = NULL \ -- __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} -+ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) -+ -+#define __RT_MUTEX_INITIALIZER(mutexname) \ -+ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } -+ -+#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ -+ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ -+ , .save_state = 1 } - - #define DEFINE_RT_MUTEX(mutexname) \ - struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) -@@ -91,6 +106,7 @@ - - extern void rt_mutex_lock(struct rt_mutex *lock); - extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); -+extern int rt_mutex_lock_killable(struct rt_mutex *lock); - extern int rt_mutex_timed_lock(struct rt_mutex *lock, - struct hrtimer_sleeper *timeout); - -diff -Nur linux-4.4.28.orig/include/linux/rwlock_rt.h linux-4.4.28/include/linux/rwlock_rt.h ---- linux-4.4.28.orig/include/linux/rwlock_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/rwlock_rt.h 2016-11-01 21:26:58.740339958 +0100 -@@ -0,0 +1,99 @@ -+#ifndef __LINUX_RWLOCK_RT_H -+#define __LINUX_RWLOCK_RT_H -+ -+#ifndef __LINUX_SPINLOCK_H -+#error Do not include directly. Use spinlock.h -+#endif -+ -+#define rwlock_init(rwl) \ -+do { \ -+ static struct lock_class_key __key; \ -+ \ -+ rt_mutex_init(&(rwl)->lock); \ -+ __rt_rwlock_init(rwl, #rwl, &__key); \ -+} while (0) -+ -+extern void __lockfunc rt_write_lock(rwlock_t *rwlock); -+extern void __lockfunc rt_read_lock(rwlock_t *rwlock); -+extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); -+extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags); -+extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); -+extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); -+extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); -+extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock); -+extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock); -+extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); -+ -+#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) -+#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) -+ -+#define write_trylock_irqsave(lock, flags) \ -+ __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags)) -+ -+#define read_lock_irqsave(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ flags = rt_read_lock_irqsave(lock); \ -+ } while (0) -+ -+#define write_lock_irqsave(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ flags = rt_write_lock_irqsave(lock); \ -+ } while (0) -+ -+#define read_lock(lock) rt_read_lock(lock) -+ -+#define read_lock_bh(lock) \ -+ do { \ -+ local_bh_disable(); \ -+ rt_read_lock(lock); \ -+ } while (0) -+ -+#define read_lock_irq(lock) read_lock(lock) -+ -+#define write_lock(lock) rt_write_lock(lock) -+ -+#define write_lock_bh(lock) \ -+ do { \ -+ local_bh_disable(); \ -+ rt_write_lock(lock); \ -+ } while (0) -+ -+#define write_lock_irq(lock) write_lock(lock) -+ -+#define read_unlock(lock) rt_read_unlock(lock) -+ -+#define read_unlock_bh(lock) \ -+ do { \ -+ rt_read_unlock(lock); \ -+ local_bh_enable(); \ -+ } while (0) -+ -+#define read_unlock_irq(lock) read_unlock(lock) -+ -+#define write_unlock(lock) rt_write_unlock(lock) -+ -+#define write_unlock_bh(lock) \ -+ do { \ -+ rt_write_unlock(lock); \ -+ local_bh_enable(); \ -+ } while (0) -+ -+#define write_unlock_irq(lock) write_unlock(lock) -+ -+#define read_unlock_irqrestore(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ (void) flags; \ -+ rt_read_unlock(lock); \ -+ } while (0) -+ -+#define write_unlock_irqrestore(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ (void) flags; \ -+ rt_write_unlock(lock); \ -+ } while (0) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/rwlock_types.h linux-4.4.28/include/linux/rwlock_types.h ---- linux-4.4.28.orig/include/linux/rwlock_types.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rwlock_types.h 2016-11-01 21:26:58.740339958 +0100 -@@ -1,6 +1,10 @@ - #ifndef __LINUX_RWLOCK_TYPES_H - #define __LINUX_RWLOCK_TYPES_H - -+#if !defined(__LINUX_SPINLOCK_TYPES_H) -+# error "Do not include directly, include spinlock_types.h" -+#endif -+ - /* - * include/linux/rwlock_types.h - generic rwlock type definitions - * and initializers -@@ -43,6 +47,7 @@ - RW_DEP_MAP_INIT(lockname) } - #endif - --#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) -+#define DEFINE_RWLOCK(name) \ -+ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) - - #endif /* __LINUX_RWLOCK_TYPES_H */ -diff -Nur linux-4.4.28.orig/include/linux/rwlock_types_rt.h linux-4.4.28/include/linux/rwlock_types_rt.h ---- linux-4.4.28.orig/include/linux/rwlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/rwlock_types_rt.h 2016-11-01 21:26:58.740339958 +0100 -@@ -0,0 +1,33 @@ -+#ifndef __LINUX_RWLOCK_TYPES_RT_H -+#define __LINUX_RWLOCK_TYPES_RT_H -+ -+#ifndef __LINUX_SPINLOCK_TYPES_H -+#error "Do not include directly. Include spinlock_types.h instead" -+#endif -+ -+/* -+ * rwlocks - rtmutex which allows single reader recursion -+ */ -+typedef struct { -+ struct rt_mutex lock; -+ int read_depth; -+ unsigned int break_lock; -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ struct lockdep_map dep_map; -+#endif -+} rwlock_t; -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } -+#else -+# define RW_DEP_MAP_INIT(lockname) -+#endif -+ -+#define __RW_LOCK_UNLOCKED(name) \ -+ { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \ -+ RW_DEP_MAP_INIT(name) } -+ -+#define DEFINE_RWLOCK(name) \ -+ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/rwsem.h linux-4.4.28/include/linux/rwsem.h ---- linux-4.4.28.orig/include/linux/rwsem.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/rwsem.h 2016-11-01 21:26:58.740339958 +0100 -@@ -18,6 +18,10 @@ - #include - #endif - -+#ifdef CONFIG_PREEMPT_RT_FULL -+#include -+#else /* PREEMPT_RT_FULL */ -+ - struct rw_semaphore; - - #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK -@@ -177,4 +181,6 @@ - # define up_read_non_owner(sem) up_read(sem) - #endif - -+#endif /* !PREEMPT_RT_FULL */ -+ - #endif /* _LINUX_RWSEM_H */ -diff -Nur linux-4.4.28.orig/include/linux/rwsem_rt.h linux-4.4.28/include/linux/rwsem_rt.h ---- linux-4.4.28.orig/include/linux/rwsem_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/rwsem_rt.h 2016-11-01 21:26:58.740339958 +0100 -@@ -0,0 +1,152 @@ -+#ifndef _LINUX_RWSEM_RT_H -+#define _LINUX_RWSEM_RT_H -+ -+#ifndef _LINUX_RWSEM_H -+#error "Include rwsem.h" -+#endif -+ -+/* -+ * RW-semaphores are a spinlock plus a reader-depth count. -+ * -+ * Note that the semantics are different from the usual -+ * Linux rw-sems, in PREEMPT_RT mode we do not allow -+ * multiple readers to hold the lock at once, we only allow -+ * a read-lock owner to read-lock recursively. This is -+ * better for latency, makes the implementation inherently -+ * fair and makes it simpler as well. -+ */ -+ -+#include -+ -+struct rw_semaphore { -+ struct rt_mutex lock; -+ int read_depth; -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ struct lockdep_map dep_map; -+#endif -+}; -+ -+#define __RWSEM_INITIALIZER(name) \ -+ { .lock = __RT_MUTEX_INITIALIZER(name.lock), \ -+ RW_DEP_MAP_INIT(name) } -+ -+#define DECLARE_RWSEM(lockname) \ -+ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) -+ -+extern void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, -+ struct lock_class_key *key); -+ -+#define __rt_init_rwsem(sem, name, key) \ -+ do { \ -+ rt_mutex_init(&(sem)->lock); \ -+ __rt_rwsem_init((sem), (name), (key));\ -+ } while (0) -+ -+#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key) -+ -+# define rt_init_rwsem(sem) \ -+do { \ -+ static struct lock_class_key __key; \ -+ \ -+ __rt_init_rwsem((sem), #sem, &__key); \ -+} while (0) -+ -+extern void rt_down_write(struct rw_semaphore *rwsem); -+extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); -+extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); -+extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem, -+ struct lockdep_map *nest); -+extern void rt__down_read(struct rw_semaphore *rwsem); -+extern void rt_down_read(struct rw_semaphore *rwsem); -+extern int rt_down_write_trylock(struct rw_semaphore *rwsem); -+extern int rt__down_read_trylock(struct rw_semaphore *rwsem); -+extern int rt_down_read_trylock(struct rw_semaphore *rwsem); -+extern void __rt_up_read(struct rw_semaphore *rwsem); -+extern void rt_up_read(struct rw_semaphore *rwsem); -+extern void rt_up_write(struct rw_semaphore *rwsem); -+extern void rt_downgrade_write(struct rw_semaphore *rwsem); -+ -+#define init_rwsem(sem) rt_init_rwsem(sem) -+#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) -+ -+static inline int rwsem_is_contended(struct rw_semaphore *sem) -+{ -+ /* rt_mutex_has_waiters() */ -+ return !RB_EMPTY_ROOT(&sem->lock.waiters); -+} -+ -+static inline void __down_read(struct rw_semaphore *sem) -+{ -+ rt__down_read(sem); -+} -+ -+static inline void down_read(struct rw_semaphore *sem) -+{ -+ rt_down_read(sem); -+} -+ -+static inline int __down_read_trylock(struct rw_semaphore *sem) -+{ -+ return rt__down_read_trylock(sem); -+} -+ -+static inline int down_read_trylock(struct rw_semaphore *sem) -+{ -+ return rt_down_read_trylock(sem); -+} -+ -+static inline void down_write(struct rw_semaphore *sem) -+{ -+ rt_down_write(sem); -+} -+ -+static inline int down_write_trylock(struct rw_semaphore *sem) -+{ -+ return rt_down_write_trylock(sem); -+} -+ -+static inline void __up_read(struct rw_semaphore *sem) -+{ -+ __rt_up_read(sem); -+} -+ -+static inline void up_read(struct rw_semaphore *sem) -+{ -+ rt_up_read(sem); -+} -+ -+static inline void up_write(struct rw_semaphore *sem) -+{ -+ rt_up_write(sem); -+} -+ -+static inline void downgrade_write(struct rw_semaphore *sem) -+{ -+ rt_downgrade_write(sem); -+} -+ -+static inline void down_read_nested(struct rw_semaphore *sem, int subclass) -+{ -+ return rt_down_read_nested(sem, subclass); -+} -+ -+static inline void down_write_nested(struct rw_semaphore *sem, int subclass) -+{ -+ rt_down_write_nested(sem, subclass); -+} -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+static inline void down_write_nest_lock(struct rw_semaphore *sem, -+ struct rw_semaphore *nest_lock) -+{ -+ rt_down_write_nested_lock(sem, &nest_lock->dep_map); -+} -+ -+#else -+ -+static inline void down_write_nest_lock(struct rw_semaphore *sem, -+ struct rw_semaphore *nest_lock) -+{ -+ rt_down_write_nested_lock(sem, NULL); -+} -+#endif -+#endif -diff -Nur linux-4.4.28.orig/include/linux/sched.h linux-4.4.28/include/linux/sched.h ---- linux-4.4.28.orig/include/linux/sched.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/sched.h 2016-11-01 21:26:58.740339958 +0100 -@@ -26,6 +26,7 @@ - #include - #include - #include -+#include - - #include - #include -@@ -182,8 +183,6 @@ - static inline void update_cpu_load_nohz(void) { } - #endif - --extern unsigned long get_parent_ip(unsigned long addr); -- - extern void dump_cpu_task(int cpu); - - struct seq_file; -@@ -242,10 +241,7 @@ - TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ - __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) - --#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) - #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) --#define task_is_stopped_or_traced(task) \ -- ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) - #define task_contributes_to_load(task) \ - ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ - (task->flags & PF_FROZEN) == 0 && \ -@@ -311,6 +307,11 @@ - - #endif - -+#define __set_current_state_no_track(state_value) \ -+ do { current->state = (state_value); } while (0) -+#define set_current_state_no_track(state_value) \ -+ set_mb(current->state, (state_value)) -+ - /* Task command name length */ - #define TASK_COMM_LEN 16 - -@@ -970,8 +971,18 @@ - struct wake_q_head name = { WAKE_Q_TAIL, &name.first } - - extern void wake_q_add(struct wake_q_head *head, -- struct task_struct *task); --extern void wake_up_q(struct wake_q_head *head); -+ struct task_struct *task); -+extern void __wake_up_q(struct wake_q_head *head, bool sleeper); -+ -+static inline void wake_up_q(struct wake_q_head *head) -+{ -+ __wake_up_q(head, false); -+} -+ -+static inline void wake_up_q_sleeper(struct wake_q_head *head) -+{ -+ __wake_up_q(head, true); -+} - - /* - * sched-domains (multiprocessor balancing) declarations: -@@ -1379,6 +1390,7 @@ - - struct task_struct { - volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ -+ volatile long saved_state; /* saved state for "spinlock sleepers" */ - void *stack; - atomic_t usage; - unsigned int flags; /* per process flags, defined below */ -@@ -1415,6 +1427,12 @@ - #endif - - unsigned int policy; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ int migrate_disable; -+# ifdef CONFIG_SCHED_DEBUG -+ int migrate_disable_atomic; -+# endif -+#endif - int nr_cpus_allowed; - cpumask_t cpus_allowed; - -@@ -1522,11 +1540,14 @@ - cputime_t gtime; - struct prev_cputime prev_cputime; - #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -- seqlock_t vtime_seqlock; -+ seqcount_t vtime_seqcount; - unsigned long long vtime_snap; - enum { -- VTIME_SLEEPING = 0, -+ /* Task is sleeping or running in a CPU with VTIME inactive */ -+ VTIME_INACTIVE = 0, -+ /* Task runs in userspace in a CPU with VTIME active */ - VTIME_USER, -+ /* Task runs in kernelspace in a CPU with VTIME active */ - VTIME_SYS, - } vtime_snap_whence; - #endif -@@ -1538,6 +1559,9 @@ - - struct task_cputime cputime_expires; - struct list_head cpu_timers[3]; -+#ifdef CONFIG_PREEMPT_RT_BASE -+ struct task_struct *posix_timer_list; -+#endif - - /* process credentials */ - const struct cred __rcu *real_cred; /* objective and real subjective task -@@ -1568,10 +1592,15 @@ - /* signal handlers */ - struct signal_struct *signal; - struct sighand_struct *sighand; -+ struct sigqueue *sigqueue_cache; - - sigset_t blocked, real_blocked; - sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ - struct sigpending pending; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ /* TODO: move me into ->restart_block ? */ -+ struct siginfo forced_info; -+#endif - - unsigned long sas_ss_sp; - size_t sas_ss_size; -@@ -1795,6 +1824,12 @@ - unsigned long trace; - /* bitmask and counter of trace recursion */ - unsigned long trace_recursion; -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ u64 preempt_timestamp_hist; -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ long timer_offset; -+#endif -+#endif - #endif /* CONFIG_TRACING */ - #ifdef CONFIG_MEMCG - struct mem_cgroup *memcg_in_oom; -@@ -1811,9 +1846,23 @@ - unsigned int sequential_io; - unsigned int sequential_io_avg; - #endif -+#ifdef CONFIG_PREEMPT_RT_BASE -+ struct rcu_head put_rcu; -+ int softirq_nestcnt; -+ unsigned int softirqs_raised; -+#endif -+#ifdef CONFIG_PREEMPT_RT_FULL -+# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 -+ int kmap_idx; -+ pte_t kmap_pte[KM_TYPE_NR]; -+# endif -+#endif - #ifdef CONFIG_DEBUG_ATOMIC_SLEEP - unsigned long task_state_change; - #endif -+#ifdef CONFIG_PREEMPT_RT_FULL -+ int xmit_recursion; -+#endif - int pagefault_disabled; - /* CPU-specific state of this task */ - struct thread_struct thread; -@@ -1831,9 +1880,6 @@ - # define arch_task_struct_size (sizeof(struct task_struct)) - #endif - --/* Future-safe accessor for struct task_struct's cpus_allowed. */ --#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) -- - #define TNF_MIGRATED 0x01 - #define TNF_NO_GROUP 0x02 - #define TNF_SHARED 0x04 -@@ -2023,6 +2069,15 @@ - extern void free_task(struct task_struct *tsk); - #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) - -+#ifdef CONFIG_PREEMPT_RT_BASE -+extern void __put_task_struct_cb(struct rcu_head *rhp); -+ -+static inline void put_task_struct(struct task_struct *t) -+{ -+ if (atomic_dec_and_test(&t->usage)) -+ call_rcu(&t->put_rcu, __put_task_struct_cb); -+} -+#else - extern void __put_task_struct(struct task_struct *t); - - static inline void put_task_struct(struct task_struct *t) -@@ -2030,6 +2085,7 @@ - if (atomic_dec_and_test(&t->usage)) - __put_task_struct(t); - } -+#endif - - #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - extern void task_cputime(struct task_struct *t, -@@ -2068,6 +2124,7 @@ - /* - * Per process flags - */ -+#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ - #define PF_EXITING 0x00000004 /* getting shut down */ - #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ - #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ -@@ -2232,6 +2289,10 @@ - - extern int set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask); -+int migrate_me(void); -+void tell_sched_cpu_down_begin(int cpu); -+void tell_sched_cpu_down_done(int cpu); -+ - #else - static inline void do_set_cpus_allowed(struct task_struct *p, - const struct cpumask *new_mask) -@@ -2244,6 +2305,9 @@ - return -EINVAL; - return 0; - } -+static inline int migrate_me(void) { return 0; } -+static inline void tell_sched_cpu_down_begin(int cpu) { } -+static inline void tell_sched_cpu_down_done(int cpu) { } - #endif - - #ifdef CONFIG_NO_HZ_COMMON -@@ -2453,6 +2517,7 @@ - - extern int wake_up_state(struct task_struct *tsk, unsigned int state); - extern int wake_up_process(struct task_struct *tsk); -+extern int wake_up_lock_sleeper(struct task_struct * tsk); - extern void wake_up_new_task(struct task_struct *tsk); - #ifdef CONFIG_SMP - extern void kick_process(struct task_struct *tsk); -@@ -2576,12 +2641,24 @@ - - /* mmdrop drops the mm and the page tables */ - extern void __mmdrop(struct mm_struct *); -+ - static inline void mmdrop(struct mm_struct * mm) - { - if (unlikely(atomic_dec_and_test(&mm->mm_count))) - __mmdrop(mm); - } - -+#ifdef CONFIG_PREEMPT_RT_BASE -+extern void __mmdrop_delayed(struct rcu_head *rhp); -+static inline void mmdrop_delayed(struct mm_struct *mm) -+{ -+ if (atomic_dec_and_test(&mm->mm_count)) -+ call_rcu(&mm->delayed_drop, __mmdrop_delayed); -+} -+#else -+# define mmdrop_delayed(mm) mmdrop(mm) -+#endif -+ - /* mmput gets rid of the mappings and all user-space */ - extern void mmput(struct mm_struct *); - /* Grab a reference to a task's mm, if it is not already going away */ -@@ -2891,6 +2968,43 @@ - return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); - } - -+#ifdef CONFIG_PREEMPT_LAZY -+static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) -+{ -+ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); -+} -+ -+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) -+{ -+ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); -+} -+ -+static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) -+{ -+ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); -+} -+ -+static inline int need_resched_lazy(void) -+{ -+ return test_thread_flag(TIF_NEED_RESCHED_LAZY); -+} -+ -+static inline int need_resched_now(void) -+{ -+ return test_thread_flag(TIF_NEED_RESCHED); -+} -+ -+#else -+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } -+static inline int need_resched_lazy(void) { return 0; } -+ -+static inline int need_resched_now(void) -+{ -+ return test_thread_flag(TIF_NEED_RESCHED); -+} -+ -+#endif -+ - static inline int restart_syscall(void) - { - set_tsk_thread_flag(current, TIF_SIGPENDING); -@@ -2922,6 +3036,51 @@ - return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); - } - -+static inline bool __task_is_stopped_or_traced(struct task_struct *task) -+{ -+ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) -+ return true; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) -+ return true; -+#endif -+ return false; -+} -+ -+static inline bool task_is_stopped_or_traced(struct task_struct *task) -+{ -+ bool traced_stopped; -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ unsigned long flags; -+ -+ raw_spin_lock_irqsave(&task->pi_lock, flags); -+ traced_stopped = __task_is_stopped_or_traced(task); -+ raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+#else -+ traced_stopped = __task_is_stopped_or_traced(task); -+#endif -+ return traced_stopped; -+} -+ -+static inline bool task_is_traced(struct task_struct *task) -+{ -+ bool traced = false; -+ -+ if (task->state & __TASK_TRACED) -+ return true; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ /* in case the task is sleeping on tasklist_lock */ -+ raw_spin_lock_irq(&task->pi_lock); -+ if (task->state & __TASK_TRACED) -+ traced = true; -+ else if (task->saved_state & __TASK_TRACED) -+ traced = true; -+ raw_spin_unlock_irq(&task->pi_lock); -+#endif -+ return traced; -+} -+ - /* - * cond_resched() and cond_resched_lock(): latency reduction via - * explicit rescheduling in places that are safe. The return -@@ -2943,12 +3102,16 @@ - __cond_resched_lock(lock); \ - }) - -+#ifndef CONFIG_PREEMPT_RT_FULL - extern int __cond_resched_softirq(void); - - #define cond_resched_softirq() ({ \ - ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ - __cond_resched_softirq(); \ - }) -+#else -+# define cond_resched_softirq() cond_resched() -+#endif - - static inline void cond_resched_rcu(void) - { -@@ -3110,6 +3273,31 @@ - - #endif /* CONFIG_SMP */ - -+static inline int __migrate_disabled(struct task_struct *p) -+{ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ return p->migrate_disable; -+#else -+ return 0; -+#endif -+} -+ -+/* Future-safe accessor for struct task_struct's cpus_allowed. */ -+static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) -+{ -+ if (__migrate_disabled(p)) -+ return cpumask_of(task_cpu(p)); -+ -+ return &p->cpus_allowed; -+} -+ -+static inline int tsk_nr_cpus_allowed(struct task_struct *p) -+{ -+ if (__migrate_disabled(p)) -+ return 1; -+ return p->nr_cpus_allowed; -+} -+ - extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); - extern long sched_getaffinity(pid_t pid, struct cpumask *mask); - -diff -Nur linux-4.4.28.orig/include/linux/seqlock.h linux-4.4.28/include/linux/seqlock.h ---- linux-4.4.28.orig/include/linux/seqlock.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/seqlock.h 2016-11-01 21:26:58.744340223 +0100 -@@ -220,20 +220,30 @@ - return __read_seqcount_retry(s, start); - } - -- -- --static inline void raw_write_seqcount_begin(seqcount_t *s) -+static inline void __raw_write_seqcount_begin(seqcount_t *s) - { - s->sequence++; - smp_wmb(); - } - --static inline void raw_write_seqcount_end(seqcount_t *s) -+static inline void raw_write_seqcount_begin(seqcount_t *s) -+{ -+ preempt_disable_rt(); -+ __raw_write_seqcount_begin(s); -+} -+ -+static inline void __raw_write_seqcount_end(seqcount_t *s) - { - smp_wmb(); - s->sequence++; - } - -+static inline void raw_write_seqcount_end(seqcount_t *s) -+{ -+ __raw_write_seqcount_end(s); -+ preempt_enable_rt(); -+} -+ - /** - * raw_write_seqcount_barrier - do a seq write barrier - * @s: pointer to seqcount_t -@@ -425,10 +435,32 @@ - /* - * Read side functions for starting and finalizing a read side section. - */ -+#ifndef CONFIG_PREEMPT_RT_FULL - static inline unsigned read_seqbegin(const seqlock_t *sl) - { - return read_seqcount_begin(&sl->seqcount); - } -+#else -+/* -+ * Starvation safe read side for RT -+ */ -+static inline unsigned read_seqbegin(seqlock_t *sl) -+{ -+ unsigned ret; -+ -+repeat: -+ ret = ACCESS_ONCE(sl->seqcount.sequence); -+ if (unlikely(ret & 1)) { -+ /* -+ * Take the lock and let the writer proceed (i.e. evtl -+ * boost it), otherwise we could loop here forever. -+ */ -+ spin_unlock_wait(&sl->lock); -+ goto repeat; -+ } -+ return ret; -+} -+#endif - - static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) - { -@@ -443,36 +475,36 @@ - static inline void write_seqlock(seqlock_t *sl) - { - spin_lock(&sl->lock); -- write_seqcount_begin(&sl->seqcount); -+ __raw_write_seqcount_begin(&sl->seqcount); - } - - static inline void write_sequnlock(seqlock_t *sl) - { -- write_seqcount_end(&sl->seqcount); -+ __raw_write_seqcount_end(&sl->seqcount); - spin_unlock(&sl->lock); - } - - static inline void write_seqlock_bh(seqlock_t *sl) - { - spin_lock_bh(&sl->lock); -- write_seqcount_begin(&sl->seqcount); -+ __raw_write_seqcount_begin(&sl->seqcount); - } - - static inline void write_sequnlock_bh(seqlock_t *sl) - { -- write_seqcount_end(&sl->seqcount); -+ __raw_write_seqcount_end(&sl->seqcount); - spin_unlock_bh(&sl->lock); - } - - static inline void write_seqlock_irq(seqlock_t *sl) - { - spin_lock_irq(&sl->lock); -- write_seqcount_begin(&sl->seqcount); -+ __raw_write_seqcount_begin(&sl->seqcount); - } - - static inline void write_sequnlock_irq(seqlock_t *sl) - { -- write_seqcount_end(&sl->seqcount); -+ __raw_write_seqcount_end(&sl->seqcount); - spin_unlock_irq(&sl->lock); - } - -@@ -481,7 +513,7 @@ - unsigned long flags; - - spin_lock_irqsave(&sl->lock, flags); -- write_seqcount_begin(&sl->seqcount); -+ __raw_write_seqcount_begin(&sl->seqcount); - return flags; - } - -@@ -491,7 +523,7 @@ - static inline void - write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) - { -- write_seqcount_end(&sl->seqcount); -+ __raw_write_seqcount_end(&sl->seqcount); - spin_unlock_irqrestore(&sl->lock, flags); - } - -diff -Nur linux-4.4.28.orig/include/linux/signal.h linux-4.4.28/include/linux/signal.h ---- linux-4.4.28.orig/include/linux/signal.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/signal.h 2016-11-01 21:26:58.744340223 +0100 -@@ -233,6 +233,7 @@ - } - - extern void flush_sigqueue(struct sigpending *queue); -+extern void flush_task_sigqueue(struct task_struct *tsk); - - /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ - static inline int valid_signal(unsigned long sig) -diff -Nur linux-4.4.28.orig/include/linux/skbuff.h linux-4.4.28/include/linux/skbuff.h ---- linux-4.4.28.orig/include/linux/skbuff.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/skbuff.h 2016-11-01 21:26:58.744340223 +0100 -@@ -203,6 +203,7 @@ - - __u32 qlen; - spinlock_t lock; -+ raw_spinlock_t raw_lock; - }; - - struct sk_buff; -@@ -1465,6 +1466,12 @@ - __skb_queue_head_init(list); - } - -+static inline void skb_queue_head_init_raw(struct sk_buff_head *list) -+{ -+ raw_spin_lock_init(&list->raw_lock); -+ __skb_queue_head_init(list); -+} -+ - static inline void skb_queue_head_init_class(struct sk_buff_head *list, - struct lock_class_key *class) - { -diff -Nur linux-4.4.28.orig/include/linux/smp.h linux-4.4.28/include/linux/smp.h ---- linux-4.4.28.orig/include/linux/smp.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/smp.h 2016-11-01 21:26:58.744340223 +0100 -@@ -185,6 +185,9 @@ - #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) - #define put_cpu() preempt_enable() - -+#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) -+#define put_cpu_light() migrate_enable() -+ - /* - * Callback to arch code if there's nosmp or maxcpus=0 on the - * boot command line: -diff -Nur linux-4.4.28.orig/include/linux/spinlock_api_smp.h linux-4.4.28/include/linux/spinlock_api_smp.h ---- linux-4.4.28.orig/include/linux/spinlock_api_smp.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/spinlock_api_smp.h 2016-11-01 21:26:58.744340223 +0100 -@@ -189,6 +189,8 @@ - return 0; - } - --#include -+#ifndef CONFIG_PREEMPT_RT_FULL -+# include -+#endif - - #endif /* __LINUX_SPINLOCK_API_SMP_H */ -diff -Nur linux-4.4.28.orig/include/linux/spinlock.h linux-4.4.28/include/linux/spinlock.h ---- linux-4.4.28.orig/include/linux/spinlock.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/spinlock.h 2016-11-01 21:26:58.744340223 +0100 -@@ -271,7 +271,11 @@ - #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) - - /* Include rwlock functions */ --#include -+#ifdef CONFIG_PREEMPT_RT_FULL -+# include -+#else -+# include -+#endif - - /* - * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: -@@ -282,6 +286,10 @@ - # include - #endif - -+#ifdef CONFIG_PREEMPT_RT_FULL -+# include -+#else /* PREEMPT_RT_FULL */ -+ - /* - * Map the spin_lock functions to the raw variants for PREEMPT_RT=n - */ -@@ -347,6 +355,12 @@ - raw_spin_unlock(&lock->rlock); - } - -+static __always_inline int spin_unlock_no_deboost(spinlock_t *lock) -+{ -+ raw_spin_unlock(&lock->rlock); -+ return 0; -+} -+ - static __always_inline void spin_unlock_bh(spinlock_t *lock) - { - raw_spin_unlock_bh(&lock->rlock); -@@ -416,4 +430,6 @@ - #define atomic_dec_and_lock(atomic, lock) \ - __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) - -+#endif /* !PREEMPT_RT_FULL */ -+ - #endif /* __LINUX_SPINLOCK_H */ -diff -Nur linux-4.4.28.orig/include/linux/spinlock_rt.h linux-4.4.28/include/linux/spinlock_rt.h ---- linux-4.4.28.orig/include/linux/spinlock_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/spinlock_rt.h 2016-11-01 21:26:58.744340223 +0100 -@@ -0,0 +1,165 @@ -+#ifndef __LINUX_SPINLOCK_RT_H -+#define __LINUX_SPINLOCK_RT_H -+ -+#ifndef __LINUX_SPINLOCK_H -+#error Do not include directly. Use spinlock.h -+#endif -+ -+#include -+ -+extern void -+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); -+ -+#define spin_lock_init(slock) \ -+do { \ -+ static struct lock_class_key __key; \ -+ \ -+ rt_mutex_init(&(slock)->lock); \ -+ __rt_spin_lock_init(slock, #slock, &__key); \ -+} while (0) -+ -+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock); -+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock); -+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock); -+ -+extern void __lockfunc rt_spin_lock(spinlock_t *lock); -+extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); -+extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); -+extern void __lockfunc rt_spin_unlock(spinlock_t *lock); -+extern int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock); -+extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); -+extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); -+extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); -+extern int __lockfunc rt_spin_trylock(spinlock_t *lock); -+extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); -+ -+/* -+ * lockdep-less calls, for derived types like rwlock: -+ * (for trylock they can use rt_mutex_trylock() directly. -+ */ -+extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock); -+extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); -+extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); -+extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); -+ -+#define spin_lock(lock) rt_spin_lock(lock) -+ -+#define spin_lock_bh(lock) \ -+ do { \ -+ local_bh_disable(); \ -+ rt_spin_lock(lock); \ -+ } while (0) -+ -+#define spin_lock_irq(lock) spin_lock(lock) -+ -+#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) -+ -+#define spin_trylock(lock) \ -+({ \ -+ int __locked; \ -+ __locked = spin_do_trylock(lock); \ -+ __locked; \ -+}) -+ -+#ifdef CONFIG_LOCKDEP -+# define spin_lock_nested(lock, subclass) \ -+ do { \ -+ rt_spin_lock_nested(lock, subclass); \ -+ } while (0) -+ -+#define spin_lock_bh_nested(lock, subclass) \ -+ do { \ -+ local_bh_disable(); \ -+ rt_spin_lock_nested(lock, subclass); \ -+ } while (0) -+ -+# define spin_lock_irqsave_nested(lock, flags, subclass) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ flags = 0; \ -+ rt_spin_lock_nested(lock, subclass); \ -+ } while (0) -+#else -+# define spin_lock_nested(lock, subclass) spin_lock(lock) -+# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) -+ -+# define spin_lock_irqsave_nested(lock, flags, subclass) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ flags = 0; \ -+ spin_lock(lock); \ -+ } while (0) -+#endif -+ -+#define spin_lock_irqsave(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ flags = 0; \ -+ spin_lock(lock); \ -+ } while (0) -+ -+static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) -+{ -+ unsigned long flags = 0; -+#ifdef CONFIG_TRACE_IRQFLAGS -+ flags = rt_spin_lock_trace_flags(lock); -+#else -+ spin_lock(lock); /* lock_local */ -+#endif -+ return flags; -+} -+ -+/* FIXME: we need rt_spin_lock_nest_lock */ -+#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) -+ -+#define spin_unlock(lock) rt_spin_unlock(lock) -+#define spin_unlock_no_deboost(lock) rt_spin_unlock_no_deboost(lock) -+ -+#define spin_unlock_bh(lock) \ -+ do { \ -+ rt_spin_unlock(lock); \ -+ local_bh_enable(); \ -+ } while (0) -+ -+#define spin_unlock_irq(lock) spin_unlock(lock) -+ -+#define spin_unlock_irqrestore(lock, flags) \ -+ do { \ -+ typecheck(unsigned long, flags); \ -+ (void) flags; \ -+ spin_unlock(lock); \ -+ } while (0) -+ -+#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) -+#define spin_trylock_irq(lock) spin_trylock(lock) -+ -+#define spin_trylock_irqsave(lock, flags) \ -+ rt_spin_trylock_irqsave(lock, &(flags)) -+ -+#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) -+ -+#ifdef CONFIG_GENERIC_LOCKBREAK -+# define spin_is_contended(lock) ((lock)->break_lock) -+#else -+# define spin_is_contended(lock) (((void)(lock), 0)) -+#endif -+ -+static inline int spin_can_lock(spinlock_t *lock) -+{ -+ return !rt_mutex_is_locked(&lock->lock); -+} -+ -+static inline int spin_is_locked(spinlock_t *lock) -+{ -+ return rt_mutex_is_locked(&lock->lock); -+} -+ -+static inline void assert_spin_locked(spinlock_t *lock) -+{ -+ BUG_ON(!spin_is_locked(lock)); -+} -+ -+#define atomic_dec_and_lock(atomic, lock) \ -+ atomic_dec_and_spin_lock(atomic, lock) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/spinlock_types.h linux-4.4.28/include/linux/spinlock_types.h ---- linux-4.4.28.orig/include/linux/spinlock_types.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/spinlock_types.h 2016-11-01 21:26:58.744340223 +0100 -@@ -9,80 +9,15 @@ - * Released under the General Public License (GPL). - */ - --#if defined(CONFIG_SMP) --# include --#else --# include --#endif -- --#include -- --typedef struct raw_spinlock { -- arch_spinlock_t raw_lock; --#ifdef CONFIG_GENERIC_LOCKBREAK -- unsigned int break_lock; --#endif --#ifdef CONFIG_DEBUG_SPINLOCK -- unsigned int magic, owner_cpu; -- void *owner; --#endif --#ifdef CONFIG_DEBUG_LOCK_ALLOC -- struct lockdep_map dep_map; --#endif --} raw_spinlock_t; -- --#define SPINLOCK_MAGIC 0xdead4ead -- --#define SPINLOCK_OWNER_INIT ((void *)-1L) -- --#ifdef CONFIG_DEBUG_LOCK_ALLOC --# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } --#else --# define SPIN_DEP_MAP_INIT(lockname) --#endif -+#include - --#ifdef CONFIG_DEBUG_SPINLOCK --# define SPIN_DEBUG_INIT(lockname) \ -- .magic = SPINLOCK_MAGIC, \ -- .owner_cpu = -1, \ -- .owner = SPINLOCK_OWNER_INIT, -+#ifndef CONFIG_PREEMPT_RT_FULL -+# include -+# include - #else --# define SPIN_DEBUG_INIT(lockname) -+# include -+# include -+# include - #endif - --#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ -- { \ -- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ -- SPIN_DEBUG_INIT(lockname) \ -- SPIN_DEP_MAP_INIT(lockname) } -- --#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ -- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) -- --#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) -- --typedef struct spinlock { -- union { -- struct raw_spinlock rlock; -- --#ifdef CONFIG_DEBUG_LOCK_ALLOC --# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) -- struct { -- u8 __padding[LOCK_PADSIZE]; -- struct lockdep_map dep_map; -- }; --#endif -- }; --} spinlock_t; -- --#define __SPIN_LOCK_INITIALIZER(lockname) \ -- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } -- --#define __SPIN_LOCK_UNLOCKED(lockname) \ -- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) -- --#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) -- --#include -- - #endif /* __LINUX_SPINLOCK_TYPES_H */ -diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_nort.h linux-4.4.28/include/linux/spinlock_types_nort.h ---- linux-4.4.28.orig/include/linux/spinlock_types_nort.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/spinlock_types_nort.h 2016-11-01 21:26:58.744340223 +0100 -@@ -0,0 +1,33 @@ -+#ifndef __LINUX_SPINLOCK_TYPES_NORT_H -+#define __LINUX_SPINLOCK_TYPES_NORT_H -+ -+#ifndef __LINUX_SPINLOCK_TYPES_H -+#error "Do not include directly. Include spinlock_types.h instead" -+#endif -+ -+/* -+ * The non RT version maps spinlocks to raw_spinlocks -+ */ -+typedef struct spinlock { -+ union { -+ struct raw_spinlock rlock; -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) -+ struct { -+ u8 __padding[LOCK_PADSIZE]; -+ struct lockdep_map dep_map; -+ }; -+#endif -+ }; -+} spinlock_t; -+ -+#define __SPIN_LOCK_INITIALIZER(lockname) \ -+ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } -+ -+#define __SPIN_LOCK_UNLOCKED(lockname) \ -+ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) -+ -+#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_raw.h linux-4.4.28/include/linux/spinlock_types_raw.h ---- linux-4.4.28.orig/include/linux/spinlock_types_raw.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/spinlock_types_raw.h 2016-11-01 21:26:58.744340223 +0100 -@@ -0,0 +1,56 @@ -+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H -+#define __LINUX_SPINLOCK_TYPES_RAW_H -+ -+#if defined(CONFIG_SMP) -+# include -+#else -+# include -+#endif -+ -+#include -+ -+typedef struct raw_spinlock { -+ arch_spinlock_t raw_lock; -+#ifdef CONFIG_GENERIC_LOCKBREAK -+ unsigned int break_lock; -+#endif -+#ifdef CONFIG_DEBUG_SPINLOCK -+ unsigned int magic, owner_cpu; -+ void *owner; -+#endif -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ struct lockdep_map dep_map; -+#endif -+} raw_spinlock_t; -+ -+#define SPINLOCK_MAGIC 0xdead4ead -+ -+#define SPINLOCK_OWNER_INIT ((void *)-1L) -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } -+#else -+# define SPIN_DEP_MAP_INIT(lockname) -+#endif -+ -+#ifdef CONFIG_DEBUG_SPINLOCK -+# define SPIN_DEBUG_INIT(lockname) \ -+ .magic = SPINLOCK_MAGIC, \ -+ .owner_cpu = -1, \ -+ .owner = SPINLOCK_OWNER_INIT, -+#else -+# define SPIN_DEBUG_INIT(lockname) -+#endif -+ -+#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ -+ { \ -+ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ -+ SPIN_DEBUG_INIT(lockname) \ -+ SPIN_DEP_MAP_INIT(lockname) } -+ -+#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ -+ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) -+ -+#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_rt.h linux-4.4.28/include/linux/spinlock_types_rt.h ---- linux-4.4.28.orig/include/linux/spinlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/spinlock_types_rt.h 2016-11-01 21:26:58.744340223 +0100 -@@ -0,0 +1,51 @@ -+#ifndef __LINUX_SPINLOCK_TYPES_RT_H -+#define __LINUX_SPINLOCK_TYPES_RT_H -+ -+#ifndef __LINUX_SPINLOCK_TYPES_H -+#error "Do not include directly. Include spinlock_types.h instead" -+#endif -+ -+#include -+ -+/* -+ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: -+ */ -+typedef struct spinlock { -+ struct rt_mutex lock; -+ unsigned int break_lock; -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ struct lockdep_map dep_map; -+#endif -+} spinlock_t; -+ -+#ifdef CONFIG_DEBUG_RT_MUTEXES -+# define __RT_SPIN_INITIALIZER(name) \ -+ { \ -+ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ -+ .save_state = 1, \ -+ .file = __FILE__, \ -+ .line = __LINE__ , \ -+ } -+#else -+# define __RT_SPIN_INITIALIZER(name) \ -+ { \ -+ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ -+ .save_state = 1, \ -+ } -+#endif -+ -+/* -+.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) -+*/ -+ -+#define __SPIN_LOCK_UNLOCKED(name) \ -+ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ -+ SPIN_DEP_MAP_INIT(name) } -+ -+#define __DEFINE_SPINLOCK(name) \ -+ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) -+ -+#define DEFINE_SPINLOCK(name) \ -+ spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name) -+ -+#endif -diff -Nur linux-4.4.28.orig/include/linux/srcu.h linux-4.4.28/include/linux/srcu.h ---- linux-4.4.28.orig/include/linux/srcu.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/srcu.h 2016-11-01 21:26:58.744340223 +0100 -@@ -84,10 +84,10 @@ - - void process_srcu(struct work_struct *work); - --#define __SRCU_STRUCT_INIT(name) \ -+#define __SRCU_STRUCT_INIT(name, pcpu_name) \ - { \ - .completed = -300, \ -- .per_cpu_ref = &name##_srcu_array, \ -+ .per_cpu_ref = &pcpu_name, \ - .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ - .running = false, \ - .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ -@@ -104,7 +104,7 @@ - */ - #define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ -- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) -+ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array) - #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) - #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) - -diff -Nur linux-4.4.28.orig/include/linux/suspend.h linux-4.4.28/include/linux/suspend.h ---- linux-4.4.28.orig/include/linux/suspend.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/suspend.h 2016-11-01 21:26:58.748340476 +0100 -@@ -194,6 +194,12 @@ - void (*end)(void); - }; - -+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) -+extern bool pm_in_action; -+#else -+# define pm_in_action false -+#endif -+ - #ifdef CONFIG_SUSPEND - /** - * suspend_set_ops - set platform dependent suspend operations -diff -Nur linux-4.4.28.orig/include/linux/swait.h linux-4.4.28/include/linux/swait.h ---- linux-4.4.28.orig/include/linux/swait.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/swait.h 2016-11-01 21:26:58.748340476 +0100 -@@ -0,0 +1,173 @@ -+#ifndef _LINUX_SWAIT_H -+#define _LINUX_SWAIT_H -+ -+#include -+#include -+#include -+#include -+ -+/* -+ * Simple wait queues -+ * -+ * While these are very similar to the other/complex wait queues (wait.h) the -+ * most important difference is that the simple waitqueue allows for -+ * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold -+ * times. -+ * -+ * In order to make this so, we had to drop a fair number of features of the -+ * other waitqueue code; notably: -+ * -+ * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue; -+ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right -+ * sleeper state. -+ * -+ * - the exclusive mode; because this requires preserving the list order -+ * and this is hard. -+ * -+ * - custom wake functions; because you cannot give any guarantees about -+ * random code. -+ * -+ * As a side effect of this; the data structures are slimmer. -+ * -+ * One would recommend using this wait queue where possible. -+ */ -+ -+struct task_struct; -+ -+struct swait_queue_head { -+ raw_spinlock_t lock; -+ struct list_head task_list; -+}; -+ -+struct swait_queue { -+ struct task_struct *task; -+ struct list_head task_list; -+}; -+ -+#define __SWAITQUEUE_INITIALIZER(name) { \ -+ .task = current, \ -+ .task_list = LIST_HEAD_INIT((name).task_list), \ -+} -+ -+#define DECLARE_SWAITQUEUE(name) \ -+ struct swait_queue name = __SWAITQUEUE_INITIALIZER(name) -+ -+#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) { \ -+ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ -+ .task_list = LIST_HEAD_INIT((name).task_list), \ -+} -+ -+#define DECLARE_SWAIT_QUEUE_HEAD(name) \ -+ struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name) -+ -+extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name, -+ struct lock_class_key *key); -+ -+#define init_swait_queue_head(q) \ -+ do { \ -+ static struct lock_class_key __key; \ -+ __init_swait_queue_head((q), #q, &__key); \ -+ } while (0) -+ -+#ifdef CONFIG_LOCKDEP -+# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ -+ ({ init_swait_queue_head(&name); name; }) -+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ -+ struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) -+#else -+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ -+ DECLARE_SWAIT_QUEUE_HEAD(name) -+#endif -+ -+static inline int swait_active(struct swait_queue_head *q) -+{ -+ return !list_empty(&q->task_list); -+} -+ -+extern void swake_up(struct swait_queue_head *q); -+extern void swake_up_all(struct swait_queue_head *q); -+extern void swake_up_locked(struct swait_queue_head *q); -+extern void swake_up_all_locked(struct swait_queue_head *q); -+ -+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); -+extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); -+extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); -+ -+extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -+extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); -+ -+/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ -+#define ___swait_event(wq, condition, state, ret, cmd) \ -+({ \ -+ struct swait_queue __wait; \ -+ long __ret = ret; \ -+ \ -+ INIT_LIST_HEAD(&__wait.task_list); \ -+ for (;;) { \ -+ long __int = prepare_to_swait_event(&wq, &__wait, state);\ -+ \ -+ if (condition) \ -+ break; \ -+ \ -+ if (___wait_is_interruptible(state) && __int) { \ -+ __ret = __int; \ -+ break; \ -+ } \ -+ \ -+ cmd; \ -+ } \ -+ finish_swait(&wq, &__wait); \ -+ __ret; \ -+}) -+ -+#define __swait_event(wq, condition) \ -+ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ -+ schedule()) -+ -+#define swait_event(wq, condition) \ -+do { \ -+ if (condition) \ -+ break; \ -+ __swait_event(wq, condition); \ -+} while (0) -+ -+#define __swait_event_timeout(wq, condition, timeout) \ -+ ___swait_event(wq, ___wait_cond_timeout(condition), \ -+ TASK_UNINTERRUPTIBLE, timeout, \ -+ __ret = schedule_timeout(__ret)) -+ -+#define swait_event_timeout(wq, condition, timeout) \ -+({ \ -+ long __ret = timeout; \ -+ if (!___wait_cond_timeout(condition)) \ -+ __ret = __swait_event_timeout(wq, condition, timeout); \ -+ __ret; \ -+}) -+ -+#define __swait_event_interruptible(wq, condition) \ -+ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ -+ schedule()) -+ -+#define swait_event_interruptible(wq, condition) \ -+({ \ -+ int __ret = 0; \ -+ if (!(condition)) \ -+ __ret = __swait_event_interruptible(wq, condition); \ -+ __ret; \ -+}) -+ -+#define __swait_event_interruptible_timeout(wq, condition, timeout) \ -+ ___swait_event(wq, ___wait_cond_timeout(condition), \ -+ TASK_INTERRUPTIBLE, timeout, \ -+ __ret = schedule_timeout(__ret)) -+ -+#define swait_event_interruptible_timeout(wq, condition, timeout) \ -+({ \ -+ long __ret = timeout; \ -+ if (!___wait_cond_timeout(condition)) \ -+ __ret = __swait_event_interruptible_timeout(wq, \ -+ condition, timeout); \ -+ __ret; \ -+}) -+ -+#endif /* _LINUX_SWAIT_H */ -diff -Nur linux-4.4.28.orig/include/linux/swap.h linux-4.4.28/include/linux/swap.h ---- linux-4.4.28.orig/include/linux/swap.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/swap.h 2016-11-01 21:26:58.748340476 +0100 -@@ -11,6 +11,7 @@ - #include - #include - #include -+#include - #include - - struct notifier_block; -@@ -252,7 +253,8 @@ - void *workingset_eviction(struct address_space *mapping, struct page *page); - bool workingset_refault(void *shadow); - void workingset_activation(struct page *page); --extern struct list_lru workingset_shadow_nodes; -+extern struct list_lru __workingset_shadow_nodes; -+DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock); - - static inline unsigned int workingset_node_pages(struct radix_tree_node *node) - { -@@ -298,6 +300,7 @@ - - - /* linux/mm/swap.c */ -+DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); - extern void lru_cache_add(struct page *); - extern void lru_cache_add_anon(struct page *page); - extern void lru_cache_add_file(struct page *page); -diff -Nur linux-4.4.28.orig/include/linux/swork.h linux-4.4.28/include/linux/swork.h ---- linux-4.4.28.orig/include/linux/swork.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/linux/swork.h 2016-11-01 21:26:58.748340476 +0100 -@@ -0,0 +1,24 @@ -+#ifndef _LINUX_SWORK_H -+#define _LINUX_SWORK_H -+ -+#include -+ -+struct swork_event { -+ struct list_head item; -+ unsigned long flags; -+ void (*func)(struct swork_event *); -+}; -+ -+static inline void INIT_SWORK(struct swork_event *event, -+ void (*func)(struct swork_event *)) -+{ -+ event->flags = 0; -+ event->func = func; -+} -+ -+bool swork_queue(struct swork_event *sev); -+ -+int swork_get(void); -+void swork_put(void); -+ -+#endif /* _LINUX_SWORK_H */ -diff -Nur linux-4.4.28.orig/include/linux/thread_info.h linux-4.4.28/include/linux/thread_info.h ---- linux-4.4.28.orig/include/linux/thread_info.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/thread_info.h 2016-11-01 21:26:58.748340476 +0100 -@@ -102,7 +102,17 @@ - #define test_thread_flag(flag) \ - test_ti_thread_flag(current_thread_info(), flag) - --#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) -+#ifdef CONFIG_PREEMPT_LAZY -+#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ -+ test_thread_flag(TIF_NEED_RESCHED_LAZY)) -+#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) -+#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) -+ -+#else -+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) -+#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) -+#define tif_need_resched_lazy() 0 -+#endif - - #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK - /* -diff -Nur linux-4.4.28.orig/include/linux/timer.h linux-4.4.28/include/linux/timer.h ---- linux-4.4.28.orig/include/linux/timer.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/timer.h 2016-11-01 21:26:58.748340476 +0100 -@@ -225,7 +225,7 @@ - - extern int try_to_del_timer_sync(struct timer_list *timer); - --#ifdef CONFIG_SMP -+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) - extern int del_timer_sync(struct timer_list *timer); - #else - # define del_timer_sync(t) del_timer(t) -diff -Nur linux-4.4.28.orig/include/linux/trace_events.h linux-4.4.28/include/linux/trace_events.h ---- linux-4.4.28.orig/include/linux/trace_events.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/trace_events.h 2016-11-01 21:26:58.748340476 +0100 -@@ -66,6 +66,9 @@ - unsigned char flags; - unsigned char preempt_count; - int pid; -+ unsigned short migrate_disable; -+ unsigned short padding; -+ unsigned char preempt_lazy_count; - }; - - #define TRACE_EVENT_TYPE_MAX \ -diff -Nur linux-4.4.28.orig/include/linux/uaccess.h linux-4.4.28/include/linux/uaccess.h ---- linux-4.4.28.orig/include/linux/uaccess.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/uaccess.h 2016-11-01 21:26:58.748340476 +0100 -@@ -24,6 +24,7 @@ - */ - static inline void pagefault_disable(void) - { -+ migrate_disable(); - pagefault_disabled_inc(); - /* - * make sure to have issued the store before a pagefault -@@ -40,6 +41,7 @@ - */ - barrier(); - pagefault_disabled_dec(); -+ migrate_enable(); - } - - /* -diff -Nur linux-4.4.28.orig/include/linux/uprobes.h linux-4.4.28/include/linux/uprobes.h ---- linux-4.4.28.orig/include/linux/uprobes.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/uprobes.h 2016-11-01 21:26:58.748340476 +0100 -@@ -27,6 +27,7 @@ - #include - #include - #include -+#include - - struct vm_area_struct; - struct mm_struct; -diff -Nur linux-4.4.28.orig/include/linux/vmstat.h linux-4.4.28/include/linux/vmstat.h ---- linux-4.4.28.orig/include/linux/vmstat.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/vmstat.h 2016-11-01 21:26:58.748340476 +0100 -@@ -33,7 +33,9 @@ - */ - static inline void __count_vm_event(enum vm_event_item item) - { -+ preempt_disable_rt(); - raw_cpu_inc(vm_event_states.event[item]); -+ preempt_enable_rt(); - } - - static inline void count_vm_event(enum vm_event_item item) -@@ -43,7 +45,9 @@ - - static inline void __count_vm_events(enum vm_event_item item, long delta) - { -+ preempt_disable_rt(); - raw_cpu_add(vm_event_states.event[item], delta); -+ preempt_enable_rt(); - } - - static inline void count_vm_events(enum vm_event_item item, long delta) -diff -Nur linux-4.4.28.orig/include/linux/wait.h linux-4.4.28/include/linux/wait.h ---- linux-4.4.28.orig/include/linux/wait.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/linux/wait.h 2016-11-01 21:26:58.748340476 +0100 -@@ -8,6 +8,7 @@ - #include - #include - #include -+#include - - typedef struct __wait_queue wait_queue_t; - typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); -diff -Nur linux-4.4.28.orig/include/net/dst.h linux-4.4.28/include/net/dst.h ---- linux-4.4.28.orig/include/net/dst.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/net/dst.h 2016-11-01 21:26:58.748340476 +0100 -@@ -437,7 +437,7 @@ - static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, - struct sk_buff *skb) - { -- const struct hh_cache *hh; -+ struct hh_cache *hh; - - if (dst->pending_confirm) { - unsigned long now = jiffies; -diff -Nur linux-4.4.28.orig/include/net/neighbour.h linux-4.4.28/include/net/neighbour.h ---- linux-4.4.28.orig/include/net/neighbour.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/net/neighbour.h 2016-11-01 21:26:58.748340476 +0100 -@@ -446,7 +446,7 @@ - } - #endif - --static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) -+static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) - { - unsigned int seq; - int hh_len; -@@ -501,7 +501,7 @@ - - #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) - --static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, -+static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, - const struct net_device *dev) - { - unsigned int seq; -diff -Nur linux-4.4.28.orig/include/net/netns/ipv4.h linux-4.4.28/include/net/netns/ipv4.h ---- linux-4.4.28.orig/include/net/netns/ipv4.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/net/netns/ipv4.h 2016-11-01 21:26:58.748340476 +0100 -@@ -70,6 +70,7 @@ - - int sysctl_icmp_echo_ignore_all; - int sysctl_icmp_echo_ignore_broadcasts; -+ int sysctl_icmp_echo_sysrq; - int sysctl_icmp_ignore_bogus_error_responses; - int sysctl_icmp_ratelimit; - int sysctl_icmp_ratemask; -diff -Nur linux-4.4.28.orig/include/trace/events/hist.h linux-4.4.28/include/trace/events/hist.h ---- linux-4.4.28.orig/include/trace/events/hist.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/trace/events/hist.h 2016-11-01 21:26:58.748340476 +0100 -@@ -0,0 +1,73 @@ -+#undef TRACE_SYSTEM -+#define TRACE_SYSTEM hist -+ -+#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) -+#define _TRACE_HIST_H -+ -+#include "latency_hist.h" -+#include -+ -+#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) -+#define trace_preemptirqsoff_hist(a, b) -+#define trace_preemptirqsoff_hist_rcuidle(a, b) -+#else -+TRACE_EVENT(preemptirqsoff_hist, -+ -+ TP_PROTO(int reason, int starthist), -+ -+ TP_ARGS(reason, starthist), -+ -+ TP_STRUCT__entry( -+ __field(int, reason) -+ __field(int, starthist) -+ ), -+ -+ TP_fast_assign( -+ __entry->reason = reason; -+ __entry->starthist = starthist; -+ ), -+ -+ TP_printk("reason=%s starthist=%s", getaction(__entry->reason), -+ __entry->starthist ? "start" : "stop") -+); -+#endif -+ -+#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST -+#define trace_hrtimer_interrupt(a, b, c, d) -+#else -+TRACE_EVENT(hrtimer_interrupt, -+ -+ TP_PROTO(int cpu, long long offset, struct task_struct *curr, -+ struct task_struct *task), -+ -+ TP_ARGS(cpu, offset, curr, task), -+ -+ TP_STRUCT__entry( -+ __field(int, cpu) -+ __field(long long, offset) -+ __array(char, ccomm, TASK_COMM_LEN) -+ __field(int, cprio) -+ __array(char, tcomm, TASK_COMM_LEN) -+ __field(int, tprio) -+ ), -+ -+ TP_fast_assign( -+ __entry->cpu = cpu; -+ __entry->offset = offset; -+ memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); -+ __entry->cprio = curr->prio; -+ memcpy(__entry->tcomm, task != NULL ? task->comm : "", -+ task != NULL ? TASK_COMM_LEN : 7); -+ __entry->tprio = task != NULL ? task->prio : -1; -+ ), -+ -+ TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", -+ __entry->cpu, __entry->offset, __entry->ccomm, -+ __entry->cprio, __entry->tcomm, __entry->tprio) -+); -+#endif -+ -+#endif /* _TRACE_HIST_H */ -+ -+/* This part must be outside protection */ -+#include -diff -Nur linux-4.4.28.orig/include/trace/events/latency_hist.h linux-4.4.28/include/trace/events/latency_hist.h ---- linux-4.4.28.orig/include/trace/events/latency_hist.h 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/include/trace/events/latency_hist.h 2016-11-01 21:26:58.752340732 +0100 -@@ -0,0 +1,29 @@ -+#ifndef _LATENCY_HIST_H -+#define _LATENCY_HIST_H -+ -+enum hist_action { -+ IRQS_ON, -+ PREEMPT_ON, -+ TRACE_STOP, -+ IRQS_OFF, -+ PREEMPT_OFF, -+ TRACE_START, -+}; -+ -+static char *actions[] = { -+ "IRQS_ON", -+ "PREEMPT_ON", -+ "TRACE_STOP", -+ "IRQS_OFF", -+ "PREEMPT_OFF", -+ "TRACE_START", -+}; -+ -+static inline char *getaction(int action) -+{ -+ if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) -+ return actions[action]; -+ return "unknown"; -+} -+ -+#endif /* _LATENCY_HIST_H */ -diff -Nur linux-4.4.28.orig/include/trace/events/writeback.h linux-4.4.28/include/trace/events/writeback.h ---- linux-4.4.28.orig/include/trace/events/writeback.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/include/trace/events/writeback.h 2016-11-01 21:26:58.752340732 +0100 -@@ -134,58 +134,28 @@ - #ifdef CREATE_TRACE_POINTS - #ifdef CONFIG_CGROUP_WRITEBACK - --static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) -+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) - { -- return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1; -+ return wb->memcg_css->cgroup->kn->ino; - } - --static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) --{ -- struct cgroup *cgrp = wb->memcg_css->cgroup; -- char *path; -- -- path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1); -- WARN_ON_ONCE(path != buf); --} -- --static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) --{ -- if (wbc->wb) -- return __trace_wb_cgroup_size(wbc->wb); -- else -- return 2; --} -- --static inline void __trace_wbc_assign_cgroup(char *buf, -- struct writeback_control *wbc) -+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) - { - if (wbc->wb) -- __trace_wb_assign_cgroup(buf, wbc->wb); -+ return __trace_wb_assign_cgroup(wbc->wb); - else -- strcpy(buf, "/"); -+ return -1U; - } -- - #else /* CONFIG_CGROUP_WRITEBACK */ - --static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) --{ -- return 2; --} -- --static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) --{ -- strcpy(buf, "/"); --} -- --static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) -+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) - { -- return 2; -+ return -1U; - } - --static inline void __trace_wbc_assign_cgroup(char *buf, -- struct writeback_control *wbc) -+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) - { -- strcpy(buf, "/"); -+ return -1U; - } - - #endif /* CONFIG_CGROUP_WRITEBACK */ -@@ -201,7 +171,7 @@ - __array(char, name, 32) - __field(unsigned long, ino) - __field(int, sync_mode) -- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -209,14 +179,14 @@ - dev_name(inode_to_bdi(inode)->dev), 32); - __entry->ino = inode->i_ino; - __entry->sync_mode = wbc->sync_mode; -- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); -+ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); - ), - -- TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s", -+ TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u", - __entry->name, - __entry->ino, - __entry->sync_mode, -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -@@ -246,7 +216,7 @@ - __field(int, range_cyclic) - __field(int, for_background) - __field(int, reason) -- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) -+ __field(unsigned int, cgroup_ino) - ), - TP_fast_assign( - strncpy(__entry->name, -@@ -258,10 +228,10 @@ - __entry->range_cyclic = work->range_cyclic; - __entry->for_background = work->for_background; - __entry->reason = work->reason; -- __trace_wb_assign_cgroup(__get_str(cgroup), wb); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - ), - TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " -- "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s", -+ "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u", - __entry->name, - MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), - __entry->nr_pages, -@@ -270,7 +240,7 @@ - __entry->range_cyclic, - __entry->for_background, - __print_symbolic(__entry->reason, WB_WORK_REASON), -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - #define DEFINE_WRITEBACK_WORK_EVENT(name) \ -@@ -300,15 +270,15 @@ - TP_ARGS(wb), - TP_STRUCT__entry( - __array(char, name, 32) -- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) -+ __field(unsigned int, cgroup_ino) - ), - TP_fast_assign( - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); -- __trace_wb_assign_cgroup(__get_str(cgroup), wb); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - ), -- TP_printk("bdi %s: cgroup=%s", -+ TP_printk("bdi %s: cgroup_ino=%u", - __entry->name, -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - #define DEFINE_WRITEBACK_EVENT(name) \ -@@ -347,7 +317,7 @@ - __field(int, range_cyclic) - __field(long, range_start) - __field(long, range_end) -- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -361,12 +331,12 @@ - __entry->range_cyclic = wbc->range_cyclic; - __entry->range_start = (long)wbc->range_start; - __entry->range_end = (long)wbc->range_end; -- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); -+ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); - ), - - TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " - "bgrd=%d reclm=%d cyclic=%d " -- "start=0x%lx end=0x%lx cgroup=%s", -+ "start=0x%lx end=0x%lx cgroup_ino=%u", - __entry->name, - __entry->nr_to_write, - __entry->pages_skipped, -@@ -377,7 +347,7 @@ - __entry->range_cyclic, - __entry->range_start, - __entry->range_end, -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ) - -@@ -398,7 +368,7 @@ - __field(long, age) - __field(int, moved) - __field(int, reason) -- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) -+ __field(unsigned int, cgroup_ino) - ), - TP_fast_assign( - unsigned long *older_than_this = work->older_than_this; -@@ -408,15 +378,15 @@ - (jiffies - *older_than_this) * 1000 / HZ : -1; - __entry->moved = moved; - __entry->reason = work->reason; -- __trace_wb_assign_cgroup(__get_str(cgroup), wb); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - ), -- TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s", -+ TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u", - __entry->name, - __entry->older, /* older_than_this in jiffies */ - __entry->age, /* older_than_this in relative milliseconds */ - __entry->moved, - __print_symbolic(__entry->reason, WB_WORK_REASON), -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -@@ -484,7 +454,7 @@ - __field(unsigned long, dirty_ratelimit) - __field(unsigned long, task_ratelimit) - __field(unsigned long, balanced_dirty_ratelimit) -- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -496,13 +466,13 @@ - __entry->task_ratelimit = KBps(task_ratelimit); - __entry->balanced_dirty_ratelimit = - KBps(wb->balanced_dirty_ratelimit); -- __trace_wb_assign_cgroup(__get_str(cgroup), wb); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - ), - - TP_printk("bdi %s: " - "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " - "dirty_ratelimit=%lu task_ratelimit=%lu " -- "balanced_dirty_ratelimit=%lu cgroup=%s", -+ "balanced_dirty_ratelimit=%lu cgroup_ino=%u", - __entry->bdi, - __entry->write_bw, /* write bandwidth */ - __entry->avg_write_bw, /* avg write bandwidth */ -@@ -510,7 +480,7 @@ - __entry->dirty_ratelimit, /* base ratelimit */ - __entry->task_ratelimit, /* ratelimit with position control */ - __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -@@ -548,7 +518,7 @@ - __field( long, pause) - __field(unsigned long, period) - __field( long, think) -- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -571,7 +541,7 @@ - __entry->period = period * 1000 / HZ; - __entry->pause = pause * 1000 / HZ; - __entry->paused = (jiffies - start_time) * 1000 / HZ; -- __trace_wb_assign_cgroup(__get_str(cgroup), wb); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - ), - - -@@ -580,7 +550,7 @@ - "bdi_setpoint=%lu bdi_dirty=%lu " - "dirty_ratelimit=%lu task_ratelimit=%lu " - "dirtied=%u dirtied_pause=%u " -- "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s", -+ "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u", - __entry->bdi, - __entry->limit, - __entry->setpoint, -@@ -595,7 +565,7 @@ - __entry->pause, /* ms */ - __entry->period, /* ms */ - __entry->think, /* ms */ -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -@@ -609,8 +579,7 @@ - __field(unsigned long, ino) - __field(unsigned long, state) - __field(unsigned long, dirtied_when) -- __dynamic_array(char, cgroup, -- __trace_wb_cgroup_size(inode_to_wb(inode))) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -619,16 +588,16 @@ - __entry->ino = inode->i_ino; - __entry->state = inode->i_state; - __entry->dirtied_when = inode->dirtied_when; -- __trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode)); -+ __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); - ), - -- TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s", -+ TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u", - __entry->name, - __entry->ino, - show_inode_state(__entry->state), - __entry->dirtied_when, - (jiffies - __entry->dirtied_when) / HZ, -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -@@ -684,7 +653,7 @@ - __field(unsigned long, writeback_index) - __field(long, nr_to_write) - __field(unsigned long, wrote) -- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) -+ __field(unsigned int, cgroup_ino) - ), - - TP_fast_assign( -@@ -696,11 +665,11 @@ - __entry->writeback_index = inode->i_mapping->writeback_index; - __entry->nr_to_write = nr_to_write; - __entry->wrote = nr_to_write - wbc->nr_to_write; -- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); -+ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); - ), - - TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " -- "index=%lu to_write=%ld wrote=%lu cgroup=%s", -+ "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u", - __entry->name, - __entry->ino, - show_inode_state(__entry->state), -@@ -709,7 +678,7 @@ - __entry->writeback_index, - __entry->nr_to_write, - __entry->wrote, -- __get_str(cgroup) -+ __entry->cgroup_ino - ) - ); - -diff -Nur linux-4.4.28.orig/init/Kconfig linux-4.4.28/init/Kconfig ---- linux-4.4.28.orig/init/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/init/Kconfig 2016-11-01 21:26:58.752340732 +0100 -@@ -498,7 +498,7 @@ - - config RCU_EXPERT - bool "Make expert-level adjustments to RCU configuration" -- default n -+ default y if PREEMPT_RT_FULL - help - This option needs to be enabled if you wish to make - expert-level adjustments to RCU configuration. By default, -@@ -614,7 +614,7 @@ - - config RCU_FAST_NO_HZ - bool "Accelerate last non-dyntick-idle CPU's grace periods" -- depends on NO_HZ_COMMON && SMP && RCU_EXPERT -+ depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL - default n - help - This option permits CPUs to enter dynticks-idle state even if -@@ -641,7 +641,7 @@ - config RCU_BOOST - bool "Enable RCU priority boosting" - depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT -- default n -+ default y if PREEMPT_RT_FULL - help - This option boosts the priority of preempted RCU readers that - block the current preemptible RCU grace period for too long. -@@ -1106,6 +1106,7 @@ - config RT_GROUP_SCHED - bool "Group scheduling for SCHED_RR/FIFO" - depends on CGROUP_SCHED -+ depends on !PREEMPT_RT_FULL - default n - help - This feature lets you explicitly allocate real CPU bandwidth -@@ -1719,6 +1720,7 @@ - - config SLAB - bool "SLAB" -+ depends on !PREEMPT_RT_FULL - help - The regular slab allocator that is established and known to work - well in all environments. It organizes cache hot objects in -@@ -1737,6 +1739,7 @@ - config SLOB - depends on EXPERT - bool "SLOB (Simple Allocator)" -+ depends on !PREEMPT_RT_FULL - help - SLOB replaces the stock allocator with a drastically simpler - allocator. SLOB is generally more space efficient but -@@ -1746,7 +1749,7 @@ - - config SLUB_CPU_PARTIAL - default y -- depends on SLUB && SMP -+ depends on SLUB && SMP && !PREEMPT_RT_FULL - bool "SLUB per cpu partial cache" - help - Per cpu partial caches accellerate objects allocation and freeing -diff -Nur linux-4.4.28.orig/init/main.c linux-4.4.28/init/main.c ---- linux-4.4.28.orig/init/main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/init/main.c 2016-11-01 21:26:58.752340732 +0100 -@@ -530,6 +530,7 @@ - setup_command_line(command_line); - setup_nr_cpu_ids(); - setup_per_cpu_areas(); -+ softirq_early_init(); - smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ - - build_all_zonelists(NULL, NULL); -diff -Nur linux-4.4.28.orig/init/Makefile linux-4.4.28/init/Makefile ---- linux-4.4.28.orig/init/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/init/Makefile 2016-11-01 21:26:58.752340732 +0100 -@@ -33,4 +33,4 @@ - include/generated/compile.h: FORCE - @$($(quiet)chk_compile.h) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ -- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" -+ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" -diff -Nur linux-4.4.28.orig/ipc/msg.c linux-4.4.28/ipc/msg.c ---- linux-4.4.28.orig/ipc/msg.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/ipc/msg.c 2016-11-01 21:26:58.752340732 +0100 -@@ -183,20 +183,14 @@ - } - } - --static void expunge_all(struct msg_queue *msq, int res) -+static void expunge_all(struct msg_queue *msq, int res, -+ struct wake_q_head *wake_q) - { - struct msg_receiver *msr, *t; - - list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { -- msr->r_msg = NULL; /* initialize expunge ordering */ -- wake_up_process(msr->r_tsk); -- /* -- * Ensure that the wakeup is visible before setting r_msg as -- * the receiving end depends on it: either spinning on a nil, -- * or dealing with -EAGAIN cases. See lockless receive part 1 -- * and 2 in do_msgrcv(). -- */ -- smp_wmb(); /* barrier (B) */ -+ -+ wake_q_add(wake_q, msr->r_tsk); - msr->r_msg = ERR_PTR(res); - } - } -@@ -213,11 +207,13 @@ - { - struct msg_msg *msg, *t; - struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); -+ WAKE_Q(wake_q); - -- expunge_all(msq, -EIDRM); -+ expunge_all(msq, -EIDRM, &wake_q); - ss_wakeup(&msq->q_senders, 1); - msg_rmid(ns, msq); - ipc_unlock_object(&msq->q_perm); -+ wake_up_q(&wake_q); - rcu_read_unlock(); - - list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { -@@ -342,6 +338,7 @@ - struct kern_ipc_perm *ipcp; - struct msqid64_ds uninitialized_var(msqid64); - struct msg_queue *msq; -+ WAKE_Q(wake_q); - int err; - - if (cmd == IPC_SET) { -@@ -389,7 +386,7 @@ - /* sleeping receivers might be excluded by - * stricter permissions. - */ -- expunge_all(msq, -EAGAIN); -+ expunge_all(msq, -EAGAIN, &wake_q); - /* sleeping senders might be able to send - * due to a larger queue size. - */ -@@ -402,6 +399,7 @@ - - out_unlock0: - ipc_unlock_object(&msq->q_perm); -+ wake_up_q(&wake_q); - out_unlock1: - rcu_read_unlock(); - out_up: -@@ -566,7 +564,8 @@ - return 0; - } - --static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) -+static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, -+ struct wake_q_head *wake_q) - { - struct msg_receiver *msr, *t; - -@@ -577,27 +576,13 @@ - - list_del(&msr->r_list); - if (msr->r_maxsize < msg->m_ts) { -- /* initialize pipelined send ordering */ -- msr->r_msg = NULL; -- wake_up_process(msr->r_tsk); -- /* barrier (B) see barrier comment below */ -- smp_wmb(); -+ wake_q_add(wake_q, msr->r_tsk); - msr->r_msg = ERR_PTR(-E2BIG); - } else { -- msr->r_msg = NULL; - msq->q_lrpid = task_pid_vnr(msr->r_tsk); - msq->q_rtime = get_seconds(); -- wake_up_process(msr->r_tsk); -- /* -- * Ensure that the wakeup is visible before -- * setting r_msg, as the receiving can otherwise -- * exit - once r_msg is set, the receiver can -- * continue. See lockless receive part 1 and 2 -- * in do_msgrcv(). Barrier (B). -- */ -- smp_wmb(); -+ wake_q_add(wake_q, msr->r_tsk); - msr->r_msg = msg; -- - return 1; - } - } -@@ -613,6 +598,7 @@ - struct msg_msg *msg; - int err; - struct ipc_namespace *ns; -+ WAKE_Q(wake_q); - - ns = current->nsproxy->ipc_ns; - -@@ -698,7 +684,7 @@ - msq->q_lspid = task_tgid_vnr(current); - msq->q_stime = get_seconds(); - -- if (!pipelined_send(msq, msg)) { -+ if (!pipelined_send(msq, msg, &wake_q)) { - /* no one is waiting for this message, enqueue it */ - list_add_tail(&msg->m_list, &msq->q_messages); - msq->q_cbytes += msgsz; -@@ -712,6 +698,7 @@ - - out_unlock0: - ipc_unlock_object(&msq->q_perm); -+ wake_up_q(&wake_q); - out_unlock1: - rcu_read_unlock(); - if (msg != NULL) -@@ -932,57 +919,25 @@ - rcu_read_lock(); - - /* Lockless receive, part 2: -- * Wait until pipelined_send or expunge_all are outside of -- * wake_up_process(). There is a race with exit(), see -- * ipc/mqueue.c for the details. The correct serialization -- * ensures that a receiver cannot continue without the wakeup -- * being visibible _before_ setting r_msg: -+ * The work in pipelined_send() and expunge_all(): -+ * - Set pointer to message -+ * - Queue the receiver task for later wakeup -+ * - Wake up the process after the lock is dropped. - * -- * CPU 0 CPU 1 -- * -- * smp_rmb(); (A) <-- pair -. -- * r_msg> | msr->r_msg = NULL; -- * | wake_up_process(); -- * `------> smp_wmb(); (B) -- * msr->r_msg = msg; -- * -- * Where (A) orders the message value read and where (B) orders -- * the write to the r_msg -- done in both pipelined_send and -- * expunge_all. -+ * Should the process wake up before this wakeup (due to a -+ * signal) it will either see the message and continue … - */ -- for (;;) { -- /* -- * Pairs with writer barrier in pipelined_send -- * or expunge_all. -- */ -- smp_rmb(); /* barrier (A) */ -- msg = (struct msg_msg *)msr_d.r_msg; -- if (msg) -- break; - -- /* -- * The cpu_relax() call is a compiler barrier -- * which forces everything in this loop to be -- * re-loaded. -- */ -- cpu_relax(); -- } -- -- /* Lockless receive, part 3: -- * If there is a message or an error then accept it without -- * locking. -- */ -+ msg = (struct msg_msg *)msr_d.r_msg; - if (msg != ERR_PTR(-EAGAIN)) - goto out_unlock1; - -- /* Lockless receive, part 3: -- * Acquire the queue spinlock. -- */ -+ /* -+ * … or see -EAGAIN, acquire the lock to check the message -+ * again. -+ */ - ipc_lock_object(&msq->q_perm); - -- /* Lockless receive, part 4: -- * Repeat test after acquiring the spinlock. -- */ - msg = (struct msg_msg *)msr_d.r_msg; - if (msg != ERR_PTR(-EAGAIN)) - goto out_unlock0; -diff -Nur linux-4.4.28.orig/ipc/sem.c linux-4.4.28/ipc/sem.c ---- linux-4.4.28.orig/ipc/sem.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/ipc/sem.c 2016-11-01 21:26:58.756340996 +0100 -@@ -708,6 +708,13 @@ - static void wake_up_sem_queue_prepare(struct list_head *pt, - struct sem_queue *q, int error) - { -+#ifdef CONFIG_PREEMPT_RT_BASE -+ struct task_struct *p = q->sleeper; -+ get_task_struct(p); -+ q->status = error; -+ wake_up_process(p); -+ put_task_struct(p); -+#else - if (list_empty(pt)) { - /* - * Hold preempt off so that we don't get preempted and have the -@@ -719,6 +726,7 @@ - q->pid = error; - - list_add_tail(&q->list, pt); -+#endif - } - - /** -@@ -732,6 +740,7 @@ - */ - static void wake_up_sem_queue_do(struct list_head *pt) - { -+#ifndef CONFIG_PREEMPT_RT_BASE - struct sem_queue *q, *t; - int did_something; - -@@ -744,6 +753,7 @@ - } - if (did_something) - preempt_enable(); -+#endif - } - - static void unlink_queue(struct sem_array *sma, struct sem_queue *q) -diff -Nur linux-4.4.28.orig/kernel/cgroup.c linux-4.4.28/kernel/cgroup.c ---- linux-4.4.28.orig/kernel/cgroup.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/cgroup.c 2016-11-01 21:26:58.756340996 +0100 -@@ -4737,10 +4737,10 @@ - queue_work(cgroup_destroy_wq, &css->destroy_work); - } - --static void css_release_work_fn(struct work_struct *work) -+static void css_release_work_fn(struct swork_event *sev) - { - struct cgroup_subsys_state *css = -- container_of(work, struct cgroup_subsys_state, destroy_work); -+ container_of(sev, struct cgroup_subsys_state, destroy_swork); - struct cgroup_subsys *ss = css->ss; - struct cgroup *cgrp = css->cgroup; - -@@ -4779,8 +4779,8 @@ - struct cgroup_subsys_state *css = - container_of(ref, struct cgroup_subsys_state, refcnt); - -- INIT_WORK(&css->destroy_work, css_release_work_fn); -- queue_work(cgroup_destroy_wq, &css->destroy_work); -+ INIT_SWORK(&css->destroy_swork, css_release_work_fn); -+ swork_queue(&css->destroy_swork); - } - - static void init_and_link_css(struct cgroup_subsys_state *css, -@@ -5397,6 +5397,7 @@ - */ - cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); - BUG_ON(!cgroup_destroy_wq); -+ BUG_ON(swork_get()); - - /* - * Used to destroy pidlists and separate to serve as flush domain. -diff -Nur linux-4.4.28.orig/kernel/cpu.c linux-4.4.28/kernel/cpu.c ---- linux-4.4.28.orig/kernel/cpu.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/cpu.c 2016-11-01 21:26:58.756340996 +0100 -@@ -75,8 +75,8 @@ - #endif - } cpu_hotplug = { - .active_writer = NULL, -- .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), - .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), -+ .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), - #ifdef CONFIG_DEBUG_LOCK_ALLOC - .dep_map = {.name = "cpu_hotplug.lock" }, - #endif -@@ -89,6 +89,289 @@ - #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) - #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) - -+/** -+ * hotplug_pcp - per cpu hotplug descriptor -+ * @unplug: set when pin_current_cpu() needs to sync tasks -+ * @sync_tsk: the task that waits for tasks to finish pinned sections -+ * @refcount: counter of tasks in pinned sections -+ * @grab_lock: set when the tasks entering pinned sections should wait -+ * @synced: notifier for @sync_tsk to tell cpu_down it's finished -+ * @mutex: the mutex to make tasks wait (used when @grab_lock is true) -+ * @mutex_init: zero if the mutex hasn't been initialized yet. -+ * -+ * Although @unplug and @sync_tsk may point to the same task, the @unplug -+ * is used as a flag and still exists after @sync_tsk has exited and -+ * @sync_tsk set to NULL. -+ */ -+struct hotplug_pcp { -+ struct task_struct *unplug; -+ struct task_struct *sync_tsk; -+ int refcount; -+ int grab_lock; -+ struct completion synced; -+ struct completion unplug_wait; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ /* -+ * Note, on PREEMPT_RT, the hotplug lock must save the state of -+ * the task, otherwise the mutex will cause the task to fail -+ * to sleep when required. (Because it's called from migrate_disable()) -+ * -+ * The spinlock_t on PREEMPT_RT is a mutex that saves the task's -+ * state. -+ */ -+ spinlock_t lock; -+#else -+ struct mutex mutex; -+#endif -+ int mutex_init; -+}; -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+# define hotplug_lock(hp) rt_spin_lock__no_mg(&(hp)->lock) -+# define hotplug_unlock(hp) rt_spin_unlock__no_mg(&(hp)->lock) -+#else -+# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) -+# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) -+#endif -+ -+static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); -+ -+/** -+ * pin_current_cpu - Prevent the current cpu from being unplugged -+ * -+ * Lightweight version of get_online_cpus() to prevent cpu from being -+ * unplugged when code runs in a migration disabled region. -+ * -+ * Must be called with preemption disabled (preempt_count = 1)! -+ */ -+void pin_current_cpu(void) -+{ -+ struct hotplug_pcp *hp; -+ int force = 0; -+ -+retry: -+ hp = this_cpu_ptr(&hotplug_pcp); -+ -+ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || -+ hp->unplug == current) { -+ hp->refcount++; -+ return; -+ } -+ if (hp->grab_lock) { -+ preempt_enable(); -+ hotplug_lock(hp); -+ hotplug_unlock(hp); -+ } else { -+ preempt_enable(); -+ /* -+ * Try to push this task off of this CPU. -+ */ -+ if (!migrate_me()) { -+ preempt_disable(); -+ hp = this_cpu_ptr(&hotplug_pcp); -+ if (!hp->grab_lock) { -+ /* -+ * Just let it continue it's already pinned -+ * or about to sleep. -+ */ -+ force = 1; -+ goto retry; -+ } -+ preempt_enable(); -+ } -+ } -+ preempt_disable(); -+ goto retry; -+} -+ -+/** -+ * unpin_current_cpu - Allow unplug of current cpu -+ * -+ * Must be called with preemption or interrupts disabled! -+ */ -+void unpin_current_cpu(void) -+{ -+ struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); -+ -+ WARN_ON(hp->refcount <= 0); -+ -+ /* This is safe. sync_unplug_thread is pinned to this cpu */ -+ if (!--hp->refcount && hp->unplug && hp->unplug != current) -+ wake_up_process(hp->unplug); -+} -+ -+static void wait_for_pinned_cpus(struct hotplug_pcp *hp) -+{ -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ while (hp->refcount) { -+ schedule_preempt_disabled(); -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ } -+} -+ -+static int sync_unplug_thread(void *data) -+{ -+ struct hotplug_pcp *hp = data; -+ -+ wait_for_completion(&hp->unplug_wait); -+ preempt_disable(); -+ hp->unplug = current; -+ wait_for_pinned_cpus(hp); -+ -+ /* -+ * This thread will synchronize the cpu_down() with threads -+ * that have pinned the CPU. When the pinned CPU count reaches -+ * zero, we inform the cpu_down code to continue to the next step. -+ */ -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ preempt_enable(); -+ complete(&hp->synced); -+ -+ /* -+ * If all succeeds, the next step will need tasks to wait till -+ * the CPU is offline before continuing. To do this, the grab_lock -+ * is set and tasks going into pin_current_cpu() will block on the -+ * mutex. But we still need to wait for those that are already in -+ * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() -+ * will kick this thread out. -+ */ -+ while (!hp->grab_lock && !kthread_should_stop()) { -+ schedule(); -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ } -+ -+ /* Make sure grab_lock is seen before we see a stale completion */ -+ smp_mb(); -+ -+ /* -+ * Now just before cpu_down() enters stop machine, we need to make -+ * sure all tasks that are in pinned CPU sections are out, and new -+ * tasks will now grab the lock, keeping them from entering pinned -+ * CPU sections. -+ */ -+ if (!kthread_should_stop()) { -+ preempt_disable(); -+ wait_for_pinned_cpus(hp); -+ preempt_enable(); -+ complete(&hp->synced); -+ } -+ -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ while (!kthread_should_stop()) { -+ schedule(); -+ set_current_state(TASK_UNINTERRUPTIBLE); -+ } -+ set_current_state(TASK_RUNNING); -+ -+ /* -+ * Force this thread off this CPU as it's going down and -+ * we don't want any more work on this CPU. -+ */ -+ current->flags &= ~PF_NO_SETAFFINITY; -+ set_cpus_allowed_ptr(current, cpu_present_mask); -+ migrate_me(); -+ return 0; -+} -+ -+static void __cpu_unplug_sync(struct hotplug_pcp *hp) -+{ -+ wake_up_process(hp->sync_tsk); -+ wait_for_completion(&hp->synced); -+} -+ -+static void __cpu_unplug_wait(unsigned int cpu) -+{ -+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); -+ -+ complete(&hp->unplug_wait); -+ wait_for_completion(&hp->synced); -+} -+ -+/* -+ * Start the sync_unplug_thread on the target cpu and wait for it to -+ * complete. -+ */ -+static int cpu_unplug_begin(unsigned int cpu) -+{ -+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); -+ int err; -+ -+ /* Protected by cpu_hotplug.lock */ -+ if (!hp->mutex_init) { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ spin_lock_init(&hp->lock); -+#else -+ mutex_init(&hp->mutex); -+#endif -+ hp->mutex_init = 1; -+ } -+ -+ /* Inform the scheduler to migrate tasks off this CPU */ -+ tell_sched_cpu_down_begin(cpu); -+ -+ init_completion(&hp->synced); -+ init_completion(&hp->unplug_wait); -+ -+ hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); -+ if (IS_ERR(hp->sync_tsk)) { -+ err = PTR_ERR(hp->sync_tsk); -+ hp->sync_tsk = NULL; -+ return err; -+ } -+ kthread_bind(hp->sync_tsk, cpu); -+ -+ /* -+ * Wait for tasks to get out of the pinned sections, -+ * it's still OK if new tasks enter. Some CPU notifiers will -+ * wait for tasks that are going to enter these sections and -+ * we must not have them block. -+ */ -+ wake_up_process(hp->sync_tsk); -+ return 0; -+} -+ -+static void cpu_unplug_sync(unsigned int cpu) -+{ -+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); -+ -+ init_completion(&hp->synced); -+ /* The completion needs to be initialzied before setting grab_lock */ -+ smp_wmb(); -+ -+ /* Grab the mutex before setting grab_lock */ -+ hotplug_lock(hp); -+ hp->grab_lock = 1; -+ -+ /* -+ * The CPU notifiers have been completed. -+ * Wait for tasks to get out of pinned CPU sections and have new -+ * tasks block until the CPU is completely down. -+ */ -+ __cpu_unplug_sync(hp); -+ -+ /* All done with the sync thread */ -+ kthread_stop(hp->sync_tsk); -+ hp->sync_tsk = NULL; -+} -+ -+static void cpu_unplug_done(unsigned int cpu) -+{ -+ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); -+ -+ hp->unplug = NULL; -+ /* Let all tasks know cpu unplug is finished before cleaning up */ -+ smp_wmb(); -+ -+ if (hp->sync_tsk) -+ kthread_stop(hp->sync_tsk); -+ -+ if (hp->grab_lock) { -+ hotplug_unlock(hp); -+ /* protected by cpu_hotplug.lock */ -+ hp->grab_lock = 0; -+ } -+ tell_sched_cpu_down_done(cpu); -+} - - void get_online_cpus(void) - { -@@ -338,13 +621,15 @@ - /* Requires cpu_add_remove_lock to be held */ - static int _cpu_down(unsigned int cpu, int tasks_frozen) - { -- int err, nr_calls = 0; -+ int mycpu, err, nr_calls = 0; - void *hcpu = (void *)(long)cpu; - unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; - struct take_cpu_down_param tcd_param = { - .mod = mod, - .hcpu = hcpu, - }; -+ cpumask_var_t cpumask; -+ cpumask_var_t cpumask_org; - - if (num_online_cpus() == 1) - return -EBUSY; -@@ -352,7 +637,34 @@ - if (!cpu_online(cpu)) - return -EINVAL; - -+ /* Move the downtaker off the unplug cpu */ -+ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) -+ return -ENOMEM; -+ if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { -+ free_cpumask_var(cpumask); -+ return -ENOMEM; -+ } -+ -+ cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); -+ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); -+ set_cpus_allowed_ptr(current, cpumask); -+ free_cpumask_var(cpumask); -+ migrate_disable(); -+ mycpu = smp_processor_id(); -+ if (mycpu == cpu) { -+ printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); -+ migrate_enable(); -+ err = -EBUSY; -+ goto restore_cpus; -+ } -+ migrate_enable(); -+ - cpu_hotplug_begin(); -+ err = cpu_unplug_begin(cpu); -+ if (err) { -+ printk("cpu_unplug_begin(%d) failed\n", cpu); -+ goto out_cancel; -+ } - - err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); - if (err) { -@@ -378,8 +690,12 @@ - else - synchronize_rcu(); - -+ __cpu_unplug_wait(cpu); - smpboot_park_threads(cpu); - -+ /* Notifiers are done. Don't let any more tasks pin this CPU. */ -+ cpu_unplug_sync(cpu); -+ - /* - * Prevent irq alloc/free while the dying cpu reorganizes the - * interrupt affinities. -@@ -424,9 +740,14 @@ - check_for_tasks(cpu); - - out_release: -+ cpu_unplug_done(cpu); -+out_cancel: - cpu_hotplug_done(); - if (!err) - cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); -+restore_cpus: -+ set_cpus_allowed_ptr(current, cpumask_org); -+ free_cpumask_var(cpumask_org); - return err; - } - -diff -Nur linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c linux-4.4.28/kernel/debug/kdb/kdb_io.c ---- linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/debug/kdb/kdb_io.c 2016-11-01 21:26:58.756340996 +0100 -@@ -554,7 +554,6 @@ - int linecount; - int colcount; - int logging, saved_loglevel = 0; -- int saved_trap_printk; - int got_printf_lock = 0; - int retlen = 0; - int fnd, len; -@@ -565,8 +564,6 @@ - unsigned long uninitialized_var(flags); - - preempt_disable(); -- saved_trap_printk = kdb_trap_printk; -- kdb_trap_printk = 0; - - /* Serialize kdb_printf if multiple cpus try to write at once. - * But if any cpu goes recursive in kdb, just print the output, -@@ -855,7 +852,6 @@ - } else { - __release(kdb_printf_lock); - } -- kdb_trap_printk = saved_trap_printk; - preempt_enable(); - return retlen; - } -@@ -865,9 +861,11 @@ - va_list ap; - int r; - -+ kdb_trap_printk++; - va_start(ap, fmt); - r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); - va_end(ap); -+ kdb_trap_printk--; - - return r; - } -diff -Nur linux-4.4.28.orig/kernel/events/core.c linux-4.4.28/kernel/events/core.c ---- linux-4.4.28.orig/kernel/events/core.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/events/core.c 2016-11-01 21:26:58.760341249 +0100 -@@ -802,6 +802,7 @@ - raw_spin_lock_init(&cpuctx->hrtimer_lock); - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - timer->function = perf_mux_hrtimer_handler; -+ timer->irqsafe = 1; - } - - static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) -@@ -7240,6 +7241,7 @@ - - hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hwc->hrtimer.function = perf_swevent_hrtimer; -+ hwc->hrtimer.irqsafe = 1; - - /* - * Since hrtimers have a fixed rate, we can do a static freq->period -diff -Nur linux-4.4.28.orig/kernel/exit.c linux-4.4.28/kernel/exit.c ---- linux-4.4.28.orig/kernel/exit.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/exit.c 2016-11-01 21:26:58.760341249 +0100 -@@ -144,7 +144,7 @@ - * Do this under ->siglock, we can race with another thread - * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. - */ -- flush_sigqueue(&tsk->pending); -+ flush_task_sigqueue(tsk); - tsk->sighand = NULL; - spin_unlock(&sighand->siglock); - -diff -Nur linux-4.4.28.orig/kernel/fork.c linux-4.4.28/kernel/fork.c ---- linux-4.4.28.orig/kernel/fork.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/fork.c 2016-11-01 21:26:58.764341506 +0100 -@@ -108,7 +108,7 @@ - - DEFINE_PER_CPU(unsigned long, process_counts) = 0; - --__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ -+DEFINE_RWLOCK(tasklist_lock); /* outer */ - - #ifdef CONFIG_PROVE_RCU - int lockdep_tasklist_lock_is_held(void) -@@ -244,7 +244,9 @@ - if (atomic_dec_and_test(&sig->sigcnt)) - free_signal_struct(sig); - } -- -+#ifdef CONFIG_PREEMPT_RT_BASE -+static -+#endif - void __put_task_struct(struct task_struct *tsk) - { - WARN_ON(!tsk->exit_state); -@@ -261,7 +263,18 @@ - if (!profile_handoff_task(tsk)) - free_task(tsk); - } -+#ifndef CONFIG_PREEMPT_RT_BASE - EXPORT_SYMBOL_GPL(__put_task_struct); -+#else -+void __put_task_struct_cb(struct rcu_head *rhp) -+{ -+ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); -+ -+ __put_task_struct(tsk); -+ -+} -+EXPORT_SYMBOL_GPL(__put_task_struct_cb); -+#endif - - void __init __weak arch_task_cache_init(void) { } - -@@ -689,6 +702,19 @@ - } - EXPORT_SYMBOL_GPL(__mmdrop); - -+#ifdef CONFIG_PREEMPT_RT_BASE -+/* -+ * RCU callback for delayed mm drop. Not strictly rcu, but we don't -+ * want another facility to make this work. -+ */ -+void __mmdrop_delayed(struct rcu_head *rhp) -+{ -+ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); -+ -+ __mmdrop(mm); -+} -+#endif -+ - /* - * Decrement the use count and release all resources for an mm. - */ -@@ -1239,6 +1265,9 @@ - */ - static void posix_cpu_timers_init(struct task_struct *tsk) - { -+#ifdef CONFIG_PREEMPT_RT_BASE -+ tsk->posix_timer_list = NULL; -+#endif - tsk->cputime_expires.prof_exp = 0; - tsk->cputime_expires.virt_exp = 0; - tsk->cputime_expires.sched_exp = 0; -@@ -1364,15 +1393,16 @@ - spin_lock_init(&p->alloc_lock); - - init_sigpending(&p->pending); -+ p->sigqueue_cache = NULL; - - p->utime = p->stime = p->gtime = 0; - p->utimescaled = p->stimescaled = 0; - prev_cputime_init(&p->prev_cputime); - - #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -- seqlock_init(&p->vtime_seqlock); -+ seqcount_init(&p->vtime_seqcount); - p->vtime_snap = 0; -- p->vtime_snap_whence = VTIME_SLEEPING; -+ p->vtime_snap_whence = VTIME_INACTIVE; - #endif - - #if defined(SPLIT_RSS_COUNTING) -diff -Nur linux-4.4.28.orig/kernel/futex.c linux-4.4.28/kernel/futex.c ---- linux-4.4.28.orig/kernel/futex.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/futex.c 2016-11-01 21:26:58.764341506 +0100 -@@ -815,7 +815,9 @@ - * task still owns the PI-state: - */ - if (head->next != next) { -+ raw_spin_unlock_irq(&curr->pi_lock); - spin_unlock(&hb->lock); -+ raw_spin_lock_irq(&curr->pi_lock); - continue; - } - -@@ -1210,6 +1212,7 @@ - struct futex_pi_state *pi_state = this->pi_state; - u32 uninitialized_var(curval), newval; - WAKE_Q(wake_q); -+ WAKE_Q(wake_sleeper_q); - bool deboost; - int ret = 0; - -@@ -1223,7 +1226,7 @@ - if (pi_state->owner != current) - return -EINVAL; - -- raw_spin_lock(&pi_state->pi_mutex.wait_lock); -+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); - new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); - - /* -@@ -1259,24 +1262,25 @@ - ret = -EINVAL; - } - if (ret) { -- raw_spin_unlock(&pi_state->pi_mutex.wait_lock); -+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - return ret; - } - -- raw_spin_lock_irq(&pi_state->owner->pi_lock); -+ raw_spin_lock(&pi_state->owner->pi_lock); - WARN_ON(list_empty(&pi_state->list)); - list_del_init(&pi_state->list); -- raw_spin_unlock_irq(&pi_state->owner->pi_lock); -+ raw_spin_unlock(&pi_state->owner->pi_lock); - -- raw_spin_lock_irq(&new_owner->pi_lock); -+ raw_spin_lock(&new_owner->pi_lock); - WARN_ON(!list_empty(&pi_state->list)); - list_add(&pi_state->list, &new_owner->pi_state_list); - pi_state->owner = new_owner; -- raw_spin_unlock_irq(&new_owner->pi_lock); -+ raw_spin_unlock(&new_owner->pi_lock); - -- raw_spin_unlock(&pi_state->pi_mutex.wait_lock); -+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); - -- deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); -+ deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, -+ &wake_sleeper_q); - - /* - * First unlock HB so the waiter does not spin on it once he got woken -@@ -1284,8 +1288,9 @@ - * deboost first (and lose our higher priority), then the task might get - * scheduled away before the wake up can take place. - */ -- spin_unlock(&hb->lock); -+ deboost |= spin_unlock_no_deboost(&hb->lock); - wake_up_q(&wake_q); -+ wake_up_q_sleeper(&wake_sleeper_q); - if (deboost) - rt_mutex_adjust_prio(current); - -@@ -1822,6 +1827,16 @@ - requeue_pi_wake_futex(this, &key2, hb2); - drop_count++; - continue; -+ } else if (ret == -EAGAIN) { -+ /* -+ * Waiter was woken by timeout or -+ * signal and has set pi_blocked_on to -+ * PI_WAKEUP_INPROGRESS before we -+ * tried to enqueue it on the rtmutex. -+ */ -+ this->pi_state = NULL; -+ free_pi_state(pi_state); -+ continue; - } else if (ret) { - /* -EDEADLK */ - this->pi_state = NULL; -@@ -2139,11 +2154,11 @@ - * we returned due to timeout or signal without taking the - * rt_mutex. Too late. - */ -- raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); -+ raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); - owner = rt_mutex_owner(&q->pi_state->pi_mutex); - if (!owner) - owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); -- raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); -+ raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); - ret = fixup_pi_state_owner(uaddr, q, owner); - goto out; - } -@@ -2691,7 +2706,7 @@ - struct hrtimer_sleeper timeout, *to = NULL; - struct rt_mutex_waiter rt_waiter; - struct rt_mutex *pi_mutex = NULL; -- struct futex_hash_bucket *hb; -+ struct futex_hash_bucket *hb, *hb2; - union futex_key key2 = FUTEX_KEY_INIT; - struct futex_q q = futex_q_init; - int res, ret; -@@ -2716,10 +2731,7 @@ - * The waiter is allocated on our stack, manipulated by the requeue - * code while we sleep on uaddr. - */ -- debug_rt_mutex_init_waiter(&rt_waiter); -- RB_CLEAR_NODE(&rt_waiter.pi_tree_entry); -- RB_CLEAR_NODE(&rt_waiter.tree_entry); -- rt_waiter.task = NULL; -+ rt_mutex_init_waiter(&rt_waiter, false); - - ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); - if (unlikely(ret != 0)) -@@ -2750,20 +2762,55 @@ - /* Queue the futex_q, drop the hb lock, wait for wakeup. */ - futex_wait_queue_me(hb, &q, to); - -- spin_lock(&hb->lock); -- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); -- spin_unlock(&hb->lock); -- if (ret) -- goto out_put_keys; -+ /* -+ * On RT we must avoid races with requeue and trying to block -+ * on two mutexes (hb->lock and uaddr2's rtmutex) by -+ * serializing access to pi_blocked_on with pi_lock. -+ */ -+ raw_spin_lock_irq(¤t->pi_lock); -+ if (current->pi_blocked_on) { -+ /* -+ * We have been requeued or are in the process of -+ * being requeued. -+ */ -+ raw_spin_unlock_irq(¤t->pi_lock); -+ } else { -+ /* -+ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS -+ * prevents a concurrent requeue from moving us to the -+ * uaddr2 rtmutex. After that we can safely acquire -+ * (and possibly block on) hb->lock. -+ */ -+ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; -+ raw_spin_unlock_irq(¤t->pi_lock); -+ -+ spin_lock(&hb->lock); -+ -+ /* -+ * Clean up pi_blocked_on. We might leak it otherwise -+ * when we succeeded with the hb->lock in the fast -+ * path. -+ */ -+ raw_spin_lock_irq(¤t->pi_lock); -+ current->pi_blocked_on = NULL; -+ raw_spin_unlock_irq(¤t->pi_lock); -+ -+ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); -+ spin_unlock(&hb->lock); -+ if (ret) -+ goto out_put_keys; -+ } - - /* -- * In order for us to be here, we know our q.key == key2, and since -- * we took the hb->lock above, we also know that futex_requeue() has -- * completed and we no longer have to concern ourselves with a wakeup -- * race with the atomic proxy lock acquisition by the requeue code. The -- * futex_requeue dropped our key1 reference and incremented our key2 -- * reference count. -+ * In order to be here, we have either been requeued, are in -+ * the process of being requeued, or requeue successfully -+ * acquired uaddr2 on our behalf. If pi_blocked_on was -+ * non-null above, we may be racing with a requeue. Do not -+ * rely on q->lock_ptr to be hb2->lock until after blocking on -+ * hb->lock or hb2->lock. The futex_requeue dropped our key1 -+ * reference and incremented our key2 reference count. - */ -+ hb2 = hash_futex(&key2); - - /* Check if the requeue code acquired the second futex for us. */ - if (!q.rt_waiter) { -@@ -2772,14 +2819,15 @@ - * did a lock-steal - fix up the PI-state in that case. - */ - if (q.pi_state && (q.pi_state->owner != current)) { -- spin_lock(q.lock_ptr); -+ spin_lock(&hb2->lock); -+ BUG_ON(&hb2->lock != q.lock_ptr); - ret = fixup_pi_state_owner(uaddr2, &q, current); - /* - * Drop the reference to the pi state which - * the requeue_pi() code acquired for us. - */ - free_pi_state(q.pi_state); -- spin_unlock(q.lock_ptr); -+ spin_unlock(&hb2->lock); - } - } else { - /* -@@ -2792,7 +2840,8 @@ - ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); - debug_rt_mutex_free_waiter(&rt_waiter); - -- spin_lock(q.lock_ptr); -+ spin_lock(&hb2->lock); -+ BUG_ON(&hb2->lock != q.lock_ptr); - /* - * Fixup the pi_state owner and possibly acquire the lock if we - * haven't already. -diff -Nur linux-4.4.28.orig/kernel/irq/handle.c linux-4.4.28/kernel/irq/handle.c ---- linux-4.4.28.orig/kernel/irq/handle.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq/handle.c 2016-11-01 21:26:58.764341506 +0100 -@@ -134,6 +134,8 @@ - - irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) - { -+ struct pt_regs *regs = get_irq_regs(); -+ u64 ip = regs ? instruction_pointer(regs) : 0; - irqreturn_t retval = IRQ_NONE; - unsigned int flags = 0, irq = desc->irq_data.irq; - struct irqaction *action = desc->action; -@@ -176,7 +178,11 @@ - action = action->next; - } - -- add_interrupt_randomness(irq, flags); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ desc->random_ip = ip; -+#else -+ add_interrupt_randomness(irq, flags, ip); -+#endif - - if (!noirqdebug) - note_interrupt(desc, retval); -diff -Nur linux-4.4.28.orig/kernel/irq/irqdesc.c linux-4.4.28/kernel/irq/irqdesc.c ---- linux-4.4.28.orig/kernel/irq/irqdesc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq/irqdesc.c 2016-11-01 21:26:58.764341506 +0100 -@@ -24,10 +24,27 @@ - static struct lock_class_key irq_desc_lock_class; - - #if defined(CONFIG_SMP) -+static int __init irq_affinity_setup(char *str) -+{ -+ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); -+ cpulist_parse(str, irq_default_affinity); -+ /* -+ * Set at least the boot cpu. We don't want to end up with -+ * bugreports caused by random comandline masks -+ */ -+ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); -+ return 1; -+} -+__setup("irqaffinity=", irq_affinity_setup); -+ - static void __init init_irq_default_affinity(void) - { -- alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); -- cpumask_setall(irq_default_affinity); -+#ifdef CONFIG_CPUMASK_OFFSTACK -+ if (!irq_default_affinity) -+ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); -+#endif -+ if (cpumask_empty(irq_default_affinity)) -+ cpumask_setall(irq_default_affinity); - } - #else - static void __init init_irq_default_affinity(void) -diff -Nur linux-4.4.28.orig/kernel/irq/manage.c linux-4.4.28/kernel/irq/manage.c ---- linux-4.4.28.orig/kernel/irq/manage.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq/manage.c 2016-11-01 21:26:58.764341506 +0100 -@@ -22,6 +22,7 @@ - #include "internals.h" - - #ifdef CONFIG_IRQ_FORCED_THREADING -+# ifndef CONFIG_PREEMPT_RT_BASE - __read_mostly bool force_irqthreads; - - static int __init setup_forced_irqthreads(char *arg) -@@ -30,6 +31,7 @@ - return 0; - } - early_param("threadirqs", setup_forced_irqthreads); -+# endif - #endif - - static void __synchronize_hardirq(struct irq_desc *desc) -@@ -181,6 +183,62 @@ - irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } - #endif - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static void _irq_affinity_notify(struct irq_affinity_notify *notify); -+static struct task_struct *set_affinity_helper; -+static LIST_HEAD(affinity_list); -+static DEFINE_RAW_SPINLOCK(affinity_list_lock); -+ -+static int set_affinity_thread(void *unused) -+{ -+ while (1) { -+ struct irq_affinity_notify *notify; -+ int empty; -+ -+ set_current_state(TASK_INTERRUPTIBLE); -+ -+ raw_spin_lock_irq(&affinity_list_lock); -+ empty = list_empty(&affinity_list); -+ raw_spin_unlock_irq(&affinity_list_lock); -+ -+ if (empty) -+ schedule(); -+ if (kthread_should_stop()) -+ break; -+ set_current_state(TASK_RUNNING); -+try_next: -+ notify = NULL; -+ -+ raw_spin_lock_irq(&affinity_list_lock); -+ if (!list_empty(&affinity_list)) { -+ notify = list_first_entry(&affinity_list, -+ struct irq_affinity_notify, list); -+ list_del_init(¬ify->list); -+ } -+ raw_spin_unlock_irq(&affinity_list_lock); -+ -+ if (!notify) -+ continue; -+ _irq_affinity_notify(notify); -+ goto try_next; -+ } -+ return 0; -+} -+ -+static void init_helper_thread(void) -+{ -+ if (set_affinity_helper) -+ return; -+ set_affinity_helper = kthread_run(set_affinity_thread, NULL, -+ "affinity-cb"); -+ WARN_ON(IS_ERR(set_affinity_helper)); -+} -+#else -+ -+static inline void init_helper_thread(void) { } -+ -+#endif -+ - int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) - { -@@ -220,7 +278,17 @@ - - if (desc->affinity_notify) { - kref_get(&desc->affinity_notify->kref); -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ raw_spin_lock(&affinity_list_lock); -+ if (list_empty(&desc->affinity_notify->list)) -+ list_add_tail(&affinity_list, -+ &desc->affinity_notify->list); -+ raw_spin_unlock(&affinity_list_lock); -+ wake_up_process(set_affinity_helper); -+#else - schedule_work(&desc->affinity_notify->work); -+#endif - } - irqd_set(data, IRQD_AFFINITY_SET); - -@@ -258,10 +326,8 @@ - } - EXPORT_SYMBOL_GPL(irq_set_affinity_hint); - --static void irq_affinity_notify(struct work_struct *work) -+static void _irq_affinity_notify(struct irq_affinity_notify *notify) - { -- struct irq_affinity_notify *notify = -- container_of(work, struct irq_affinity_notify, work); - struct irq_desc *desc = irq_to_desc(notify->irq); - cpumask_var_t cpumask; - unsigned long flags; -@@ -283,6 +349,13 @@ - kref_put(¬ify->kref, notify->release); - } - -+static void irq_affinity_notify(struct work_struct *work) -+{ -+ struct irq_affinity_notify *notify = -+ container_of(work, struct irq_affinity_notify, work); -+ _irq_affinity_notify(notify); -+} -+ - /** - * irq_set_affinity_notifier - control notification of IRQ affinity changes - * @irq: Interrupt for which to enable/disable notification -@@ -312,6 +385,8 @@ - notify->irq = irq; - kref_init(¬ify->kref); - INIT_WORK(¬ify->work, irq_affinity_notify); -+ INIT_LIST_HEAD(¬ify->list); -+ init_helper_thread(); - } - - raw_spin_lock_irqsave(&desc->lock, flags); -@@ -865,7 +940,15 @@ - local_bh_disable(); - ret = action->thread_fn(action->irq, action->dev_id); - irq_finalize_oneshot(desc, action); -- local_bh_enable(); -+ /* -+ * Interrupts which have real time requirements can be set up -+ * to avoid softirq processing in the thread handler. This is -+ * safe as these interrupts do not raise soft interrupts. -+ */ -+ if (irq_settings_no_softirq_call(desc)) -+ _local_bh_enable(); -+ else -+ local_bh_enable(); - return ret; - } - -@@ -962,6 +1045,12 @@ - if (action_ret == IRQ_WAKE_THREAD) - irq_wake_secondary(desc, action); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ migrate_disable(); -+ add_interrupt_randomness(action->irq, 0, -+ desc->random_ip ^ (unsigned long) action); -+ migrate_enable(); -+#endif - wake_threads_waitq(desc); - } - -@@ -1315,6 +1404,9 @@ - irqd_set(&desc->irq_data, IRQD_NO_BALANCING); - } - -+ if (new->flags & IRQF_NO_SOFTIRQ_CALL) -+ irq_settings_set_no_softirq_call(desc); -+ - /* Set default affinity mask once everything is setup */ - setup_affinity(desc, mask); - -@@ -1968,7 +2060,7 @@ - * This call sets the internal irqchip state of an interrupt, - * depending on the value of @which. - * -- * This function should be called with preemption disabled if the -+ * This function should be called with migration disabled if the - * interrupt controller has per-cpu registers. - */ - int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, -diff -Nur linux-4.4.28.orig/kernel/irq/settings.h linux-4.4.28/kernel/irq/settings.h ---- linux-4.4.28.orig/kernel/irq/settings.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq/settings.h 2016-11-01 21:26:58.764341506 +0100 -@@ -16,6 +16,7 @@ - _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, - _IRQ_IS_POLLED = IRQ_IS_POLLED, - _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, -+ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, - _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, - }; - -@@ -30,6 +31,7 @@ - #define IRQ_PER_CPU_DEVID GOT_YOU_MORON - #define IRQ_IS_POLLED GOT_YOU_MORON - #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON -+#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON - #undef IRQF_MODIFY_MASK - #define IRQF_MODIFY_MASK GOT_YOU_MORON - -@@ -40,6 +42,16 @@ - desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); - } - -+static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) -+{ -+ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; -+} -+ -+static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) -+{ -+ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; -+} -+ - static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) - { - return desc->status_use_accessors & _IRQ_PER_CPU; -diff -Nur linux-4.4.28.orig/kernel/irq/spurious.c linux-4.4.28/kernel/irq/spurious.c ---- linux-4.4.28.orig/kernel/irq/spurious.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq/spurious.c 2016-11-01 21:26:58.764341506 +0100 -@@ -444,6 +444,10 @@ - - static int __init irqfixup_setup(char *str) - { -+#ifdef CONFIG_PREEMPT_RT_BASE -+ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); -+ return 1; -+#endif - irqfixup = 1; - printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); - printk(KERN_WARNING "This may impact system performance.\n"); -@@ -456,6 +460,10 @@ - - static int __init irqpoll_setup(char *str) - { -+#ifdef CONFIG_PREEMPT_RT_BASE -+ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); -+ return 1; -+#endif - irqfixup = 2; - printk(KERN_WARNING "Misrouted IRQ fixup and polling support " - "enabled\n"); -diff -Nur linux-4.4.28.orig/kernel/irq_work.c linux-4.4.28/kernel/irq_work.c ---- linux-4.4.28.orig/kernel/irq_work.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/irq_work.c 2016-11-01 21:26:58.768341770 +0100 -@@ -17,6 +17,7 @@ - #include - #include - #include -+#include - #include - - -@@ -65,6 +66,8 @@ - */ - bool irq_work_queue_on(struct irq_work *work, int cpu) - { -+ struct llist_head *list; -+ - /* All work should have been flushed before going offline */ - WARN_ON_ONCE(cpu_is_offline(cpu)); - -@@ -75,7 +78,12 @@ - if (!irq_work_claim(work)) - return false; - -- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) -+ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) -+ list = &per_cpu(lazy_list, cpu); -+ else -+ list = &per_cpu(raised_list, cpu); -+ -+ if (llist_add(&work->llnode, list)) - arch_send_call_function_single_ipi(cpu); - - return true; -@@ -86,6 +94,9 @@ - /* Enqueue the irq work @work on the current CPU */ - bool irq_work_queue(struct irq_work *work) - { -+ struct llist_head *list; -+ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); -+ - /* Only queue if not already pending */ - if (!irq_work_claim(work)) - return false; -@@ -93,13 +104,15 @@ - /* Queue the entry and raise the IPI if needed. */ - preempt_disable(); - -- /* If the work is "lazy", handle it from next tick if any */ -- if (work->flags & IRQ_WORK_LAZY) { -- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && -- tick_nohz_tick_stopped()) -- arch_irq_work_raise(); -- } else { -- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) -+ lazy_work = work->flags & IRQ_WORK_LAZY; -+ -+ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) -+ list = this_cpu_ptr(&lazy_list); -+ else -+ list = this_cpu_ptr(&raised_list); -+ -+ if (llist_add(&work->llnode, list)) { -+ if (!lazy_work || tick_nohz_tick_stopped()) - arch_irq_work_raise(); - } - -@@ -116,9 +129,8 @@ - raised = this_cpu_ptr(&raised_list); - lazy = this_cpu_ptr(&lazy_list); - -- if (llist_empty(raised) || arch_irq_work_has_interrupt()) -- if (llist_empty(lazy)) -- return false; -+ if (llist_empty(raised) && llist_empty(lazy)) -+ return false; - - /* All work should have been flushed before going offline */ - WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); -@@ -132,7 +144,7 @@ - struct irq_work *work; - struct llist_node *llnode; - -- BUG_ON(!irqs_disabled()); -+ BUG_ON_NONRT(!irqs_disabled()); - - if (llist_empty(list)) - return; -@@ -169,7 +181,16 @@ - void irq_work_run(void) - { - irq_work_run_list(this_cpu_ptr(&raised_list)); -- irq_work_run_list(this_cpu_ptr(&lazy_list)); -+ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { -+ /* -+ * NOTE: we raise softirq via IPI for safety, -+ * and execute in irq_work_tick() to move the -+ * overhead from hard to soft irq context. -+ */ -+ if (!llist_empty(this_cpu_ptr(&lazy_list))) -+ raise_softirq(TIMER_SOFTIRQ); -+ } else -+ irq_work_run_list(this_cpu_ptr(&lazy_list)); - } - EXPORT_SYMBOL_GPL(irq_work_run); - -@@ -179,8 +200,17 @@ - - if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) - irq_work_run_list(raised); -+ -+ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) -+ irq_work_run_list(this_cpu_ptr(&lazy_list)); -+} -+ -+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) -+void irq_work_tick_soft(void) -+{ - irq_work_run_list(this_cpu_ptr(&lazy_list)); - } -+#endif - - /* - * Synchronize against the irq_work @entry, ensures the entry is not -diff -Nur linux-4.4.28.orig/kernel/Kconfig.locks linux-4.4.28/kernel/Kconfig.locks ---- linux-4.4.28.orig/kernel/Kconfig.locks 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/Kconfig.locks 2016-11-01 21:26:58.756340996 +0100 -@@ -225,11 +225,11 @@ - - config MUTEX_SPIN_ON_OWNER - def_bool y -- depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW -+ depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL - - config RWSEM_SPIN_ON_OWNER - def_bool y -- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW -+ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL - - config LOCK_SPIN_ON_OWNER - def_bool y -diff -Nur linux-4.4.28.orig/kernel/Kconfig.preempt linux-4.4.28/kernel/Kconfig.preempt ---- linux-4.4.28.orig/kernel/Kconfig.preempt 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/Kconfig.preempt 2016-11-01 21:26:58.756340996 +0100 -@@ -1,3 +1,16 @@ -+config PREEMPT -+ bool -+ select PREEMPT_COUNT -+ -+config PREEMPT_RT_BASE -+ bool -+ select PREEMPT -+ -+config HAVE_PREEMPT_LAZY -+ bool -+ -+config PREEMPT_LAZY -+ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL - - choice - prompt "Preemption Model" -@@ -33,9 +46,9 @@ - - Select this if you are building a kernel for a desktop system. - --config PREEMPT -+config PREEMPT__LL - bool "Preemptible Kernel (Low-Latency Desktop)" -- select PREEMPT_COUNT -+ select PREEMPT - select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK - help - This option reduces the latency of the kernel by making -@@ -52,6 +65,22 @@ - embedded system with latency requirements in the milliseconds - range. - -+config PREEMPT_RTB -+ bool "Preemptible Kernel (Basic RT)" -+ select PREEMPT_RT_BASE -+ help -+ This option is basically the same as (Low-Latency Desktop) but -+ enables changes which are preliminary for the full preemptible -+ RT kernel. -+ -+config PREEMPT_RT_FULL -+ bool "Fully Preemptible Kernel (RT)" -+ depends on IRQ_FORCED_THREADING -+ select PREEMPT_RT_BASE -+ select PREEMPT_RCU -+ help -+ All and everything -+ - endchoice - - config PREEMPT_COUNT -diff -Nur linux-4.4.28.orig/kernel/ksysfs.c linux-4.4.28/kernel/ksysfs.c ---- linux-4.4.28.orig/kernel/ksysfs.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/ksysfs.c 2016-11-01 21:26:58.768341770 +0100 -@@ -136,6 +136,15 @@ - - #endif /* CONFIG_KEXEC_CORE */ - -+#if defined(CONFIG_PREEMPT_RT_FULL) -+static ssize_t realtime_show(struct kobject *kobj, -+ struct kobj_attribute *attr, char *buf) -+{ -+ return sprintf(buf, "%d\n", 1); -+} -+KERNEL_ATTR_RO(realtime); -+#endif -+ - /* whether file capabilities are enabled */ - static ssize_t fscaps_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -@@ -203,6 +212,9 @@ - &vmcoreinfo_attr.attr, - #endif - &rcu_expedited_attr.attr, -+#ifdef CONFIG_PREEMPT_RT_FULL -+ &realtime_attr.attr, -+#endif - NULL - }; - -diff -Nur linux-4.4.28.orig/kernel/locking/lglock.c linux-4.4.28/kernel/locking/lglock.c ---- linux-4.4.28.orig/kernel/locking/lglock.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/lglock.c 2016-11-01 21:26:58.768341770 +0100 -@@ -4,6 +4,15 @@ - #include - #include - -+#ifndef CONFIG_PREEMPT_RT_FULL -+# define lg_lock_ptr arch_spinlock_t -+# define lg_do_lock(l) arch_spin_lock(l) -+# define lg_do_unlock(l) arch_spin_unlock(l) -+#else -+# define lg_lock_ptr struct rt_mutex -+# define lg_do_lock(l) __rt_spin_lock__no_mg(l) -+# define lg_do_unlock(l) __rt_spin_unlock(l) -+#endif - /* - * Note there is no uninit, so lglocks cannot be defined in - * modules (but it's fine to use them from there) -@@ -12,51 +21,60 @@ - - void lg_lock_init(struct lglock *lg, char *name) - { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ int i; -+ -+ for_each_possible_cpu(i) { -+ struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); -+ -+ rt_mutex_init(lock); -+ } -+#endif - LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); - } - EXPORT_SYMBOL(lg_lock_init); - - void lg_local_lock(struct lglock *lg) - { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - -- preempt_disable(); -+ migrate_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = this_cpu_ptr(lg->lock); -- arch_spin_lock(lock); -+ lg_do_lock(lock); - } - EXPORT_SYMBOL(lg_local_lock); - - void lg_local_unlock(struct lglock *lg) - { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = this_cpu_ptr(lg->lock); -- arch_spin_unlock(lock); -- preempt_enable(); -+ lg_do_unlock(lock); -+ migrate_enable(); - } - EXPORT_SYMBOL(lg_local_unlock); - - void lg_local_lock_cpu(struct lglock *lg, int cpu) - { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - -- preempt_disable(); -+ preempt_disable_nort(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); -- arch_spin_lock(lock); -+ lg_do_lock(lock); - } - EXPORT_SYMBOL(lg_local_lock_cpu); - - void lg_local_unlock_cpu(struct lglock *lg, int cpu) - { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); -- arch_spin_unlock(lock); -- preempt_enable(); -+ lg_do_unlock(lock); -+ preempt_enable_nort(); - } - EXPORT_SYMBOL(lg_local_unlock_cpu); - -@@ -68,30 +86,30 @@ - if (cpu2 < cpu1) - swap(cpu1, cpu2); - -- preempt_disable(); -+ preempt_disable_nort(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); -- arch_spin_lock(per_cpu_ptr(lg->lock, cpu1)); -- arch_spin_lock(per_cpu_ptr(lg->lock, cpu2)); -+ lg_do_lock(per_cpu_ptr(lg->lock, cpu1)); -+ lg_do_lock(per_cpu_ptr(lg->lock, cpu2)); - } - - void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2) - { - lock_release(&lg->lock_dep_map, 1, _RET_IP_); -- arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1)); -- arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2)); -- preempt_enable(); -+ lg_do_unlock(per_cpu_ptr(lg->lock, cpu1)); -+ lg_do_unlock(per_cpu_ptr(lg->lock, cpu2)); -+ preempt_enable_nort(); - } - - void lg_global_lock(struct lglock *lg) - { - int i; - -- preempt_disable(); -+ preempt_disable_nort(); - lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - for_each_possible_cpu(i) { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - lock = per_cpu_ptr(lg->lock, i); -- arch_spin_lock(lock); -+ lg_do_lock(lock); - } - } - EXPORT_SYMBOL(lg_global_lock); -@@ -102,10 +120,35 @@ - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - for_each_possible_cpu(i) { -- arch_spinlock_t *lock; -+ lg_lock_ptr *lock; - lock = per_cpu_ptr(lg->lock, i); -- arch_spin_unlock(lock); -+ lg_do_unlock(lock); - } -- preempt_enable(); -+ preempt_enable_nort(); - } - EXPORT_SYMBOL(lg_global_unlock); -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * HACK: If you use this, you get to keep the pieces. -+ * Used in queue_stop_cpus_work() when stop machinery -+ * is called from inactive CPU, so we can't schedule. -+ */ -+# define lg_do_trylock_relax(l) \ -+ do { \ -+ while (!__rt_spin_trylock(l)) \ -+ cpu_relax(); \ -+ } while (0) -+ -+void lg_global_trylock_relax(struct lglock *lg) -+{ -+ int i; -+ -+ lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); -+ for_each_possible_cpu(i) { -+ lg_lock_ptr *lock; -+ lock = per_cpu_ptr(lg->lock, i); -+ lg_do_trylock_relax(lock); -+ } -+} -+#endif -diff -Nur linux-4.4.28.orig/kernel/locking/lockdep.c linux-4.4.28/kernel/locking/lockdep.c ---- linux-4.4.28.orig/kernel/locking/lockdep.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/lockdep.c 2016-11-01 21:26:58.768341770 +0100 -@@ -3525,6 +3525,7 @@ - } - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * We dont accurately track softirq state in e.g. - * hardirq contexts (such as on 4KSTACKS), so only -@@ -3539,6 +3540,7 @@ - DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); - } - } -+#endif - - if (!debug_locks) - print_irqtrace_events(current); -diff -Nur linux-4.4.28.orig/kernel/locking/locktorture.c linux-4.4.28/kernel/locking/locktorture.c ---- linux-4.4.28.orig/kernel/locking/locktorture.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/locktorture.c 2016-11-01 21:26:58.768341770 +0100 -@@ -26,7 +26,6 @@ - #include - #include - #include --#include - #include - #include - #include -diff -Nur linux-4.4.28.orig/kernel/locking/Makefile linux-4.4.28/kernel/locking/Makefile ---- linux-4.4.28.orig/kernel/locking/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/Makefile 2016-11-01 21:26:58.768341770 +0100 -@@ -1,5 +1,5 @@ - --obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o -+obj-y += semaphore.o percpu-rwsem.o - - ifdef CONFIG_FUNCTION_TRACER - CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) -@@ -8,7 +8,11 @@ - CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) - endif - -+ifneq ($(CONFIG_PREEMPT_RT_FULL),y) -+obj-y += mutex.o - obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o -+obj-y += rwsem.o -+endif - obj-$(CONFIG_LOCKDEP) += lockdep.o - ifeq ($(CONFIG_PROC_FS),y) - obj-$(CONFIG_LOCKDEP) += lockdep_proc.o -@@ -22,7 +26,10 @@ - obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o - obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o - obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o -+ifneq ($(CONFIG_PREEMPT_RT_FULL),y) - obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o - obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o -+endif -+obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o - obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o - obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o -diff -Nur linux-4.4.28.orig/kernel/locking/rt.c linux-4.4.28/kernel/locking/rt.c ---- linux-4.4.28.orig/kernel/locking/rt.c 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/kernel/locking/rt.c 2016-11-01 21:26:58.768341770 +0100 -@@ -0,0 +1,474 @@ -+/* -+ * kernel/rt.c -+ * -+ * Real-Time Preemption Support -+ * -+ * started by Ingo Molnar: -+ * -+ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar -+ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner -+ * -+ * historic credit for proving that Linux spinlocks can be implemented via -+ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow -+ * and others) who prototyped it on 2.4 and did lots of comparative -+ * research and analysis; TimeSys, for proving that you can implement a -+ * fully preemptible kernel via the use of IRQ threading and mutexes; -+ * Bill Huey for persuasively arguing on lkml that the mutex model is the -+ * right one; and to MontaVista, who ported pmutexes to 2.6. -+ * -+ * This code is a from-scratch implementation and is not based on pmutexes, -+ * but the idea of converting spinlocks to mutexes is used here too. -+ * -+ * lock debugging, locking tree, deadlock detection: -+ * -+ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey -+ * Released under the General Public License (GPL). -+ * -+ * Includes portions of the generic R/W semaphore implementation from: -+ * -+ * Copyright (c) 2001 David Howells (dhowells@redhat.com). -+ * - Derived partially from idea by Andrea Arcangeli -+ * - Derived also from comments by Linus -+ * -+ * Pending ownership of locks and ownership stealing: -+ * -+ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt -+ * -+ * (also by Steven Rostedt) -+ * - Converted single pi_lock to individual task locks. -+ * -+ * By Esben Nielsen: -+ * Doing priority inheritance with help of the scheduler. -+ * -+ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner -+ * - major rework based on Esben Nielsens initial patch -+ * - replaced thread_info references by task_struct refs -+ * - removed task->pending_owner dependency -+ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks -+ * in the scheduler return path as discussed with Steven Rostedt -+ * -+ * Copyright (C) 2006, Kihon Technologies Inc. -+ * Steven Rostedt -+ * - debugged and patched Thomas Gleixner's rework. -+ * - added back the cmpxchg to the rework. -+ * - turned atomic require back on for SMP. -+ */ -+ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#include "rtmutex_common.h" -+ -+/* -+ * struct mutex functions -+ */ -+void __mutex_do_init(struct mutex *mutex, const char *name, -+ struct lock_class_key *key) -+{ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ /* -+ * Make sure we are not reinitializing a held lock: -+ */ -+ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); -+ lockdep_init_map(&mutex->dep_map, name, key, 0); -+#endif -+ mutex->lock.save_state = 0; -+} -+EXPORT_SYMBOL(__mutex_do_init); -+ -+void __lockfunc _mutex_lock(struct mutex *lock) -+{ -+ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); -+ rt_mutex_lock(&lock->lock); -+} -+EXPORT_SYMBOL(_mutex_lock); -+ -+int __lockfunc _mutex_lock_interruptible(struct mutex *lock) -+{ -+ int ret; -+ -+ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); -+ ret = rt_mutex_lock_interruptible(&lock->lock); -+ if (ret) -+ mutex_release(&lock->dep_map, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(_mutex_lock_interruptible); -+ -+int __lockfunc _mutex_lock_killable(struct mutex *lock) -+{ -+ int ret; -+ -+ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); -+ ret = rt_mutex_lock_killable(&lock->lock); -+ if (ret) -+ mutex_release(&lock->dep_map, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(_mutex_lock_killable); -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) -+{ -+ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); -+ rt_mutex_lock(&lock->lock); -+} -+EXPORT_SYMBOL(_mutex_lock_nested); -+ -+void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) -+{ -+ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); -+ rt_mutex_lock(&lock->lock); -+} -+EXPORT_SYMBOL(_mutex_lock_nest_lock); -+ -+int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) -+{ -+ int ret; -+ -+ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); -+ ret = rt_mutex_lock_interruptible(&lock->lock); -+ if (ret) -+ mutex_release(&lock->dep_map, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(_mutex_lock_interruptible_nested); -+ -+int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) -+{ -+ int ret; -+ -+ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); -+ ret = rt_mutex_lock_killable(&lock->lock); -+ if (ret) -+ mutex_release(&lock->dep_map, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(_mutex_lock_killable_nested); -+#endif -+ -+int __lockfunc _mutex_trylock(struct mutex *lock) -+{ -+ int ret = rt_mutex_trylock(&lock->lock); -+ -+ if (ret) -+ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); -+ -+ return ret; -+} -+EXPORT_SYMBOL(_mutex_trylock); -+ -+void __lockfunc _mutex_unlock(struct mutex *lock) -+{ -+ mutex_release(&lock->dep_map, 1, _RET_IP_); -+ rt_mutex_unlock(&lock->lock); -+} -+EXPORT_SYMBOL(_mutex_unlock); -+ -+/* -+ * rwlock_t functions -+ */ -+int __lockfunc rt_write_trylock(rwlock_t *rwlock) -+{ -+ int ret; -+ -+ migrate_disable(); -+ ret = rt_mutex_trylock(&rwlock->lock); -+ if (ret) -+ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); -+ else -+ migrate_enable(); -+ -+ return ret; -+} -+EXPORT_SYMBOL(rt_write_trylock); -+ -+int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) -+{ -+ int ret; -+ -+ *flags = 0; -+ ret = rt_write_trylock(rwlock); -+ return ret; -+} -+EXPORT_SYMBOL(rt_write_trylock_irqsave); -+ -+int __lockfunc rt_read_trylock(rwlock_t *rwlock) -+{ -+ struct rt_mutex *lock = &rwlock->lock; -+ int ret = 1; -+ -+ /* -+ * recursive read locks succeed when current owns the lock, -+ * but not when read_depth == 0 which means that the lock is -+ * write locked. -+ */ -+ if (rt_mutex_owner(lock) != current) { -+ migrate_disable(); -+ ret = rt_mutex_trylock(lock); -+ if (ret) -+ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); -+ else -+ migrate_enable(); -+ -+ } else if (!rwlock->read_depth) { -+ ret = 0; -+ } -+ -+ if (ret) -+ rwlock->read_depth++; -+ -+ return ret; -+} -+EXPORT_SYMBOL(rt_read_trylock); -+ -+void __lockfunc rt_write_lock(rwlock_t *rwlock) -+{ -+ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); -+ __rt_spin_lock(&rwlock->lock); -+} -+EXPORT_SYMBOL(rt_write_lock); -+ -+void __lockfunc rt_read_lock(rwlock_t *rwlock) -+{ -+ struct rt_mutex *lock = &rwlock->lock; -+ -+ -+ /* -+ * recursive read locks succeed when current owns the lock -+ */ -+ if (rt_mutex_owner(lock) != current) { -+ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); -+ __rt_spin_lock(lock); -+ } -+ rwlock->read_depth++; -+} -+ -+EXPORT_SYMBOL(rt_read_lock); -+ -+void __lockfunc rt_write_unlock(rwlock_t *rwlock) -+{ -+ /* NOTE: we always pass in '1' for nested, for simplicity */ -+ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); -+ __rt_spin_unlock(&rwlock->lock); -+ migrate_enable(); -+} -+EXPORT_SYMBOL(rt_write_unlock); -+ -+void __lockfunc rt_read_unlock(rwlock_t *rwlock) -+{ -+ /* Release the lock only when read_depth is down to 0 */ -+ if (--rwlock->read_depth == 0) { -+ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); -+ __rt_spin_unlock(&rwlock->lock); -+ migrate_enable(); -+ } -+} -+EXPORT_SYMBOL(rt_read_unlock); -+ -+unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) -+{ -+ rt_write_lock(rwlock); -+ -+ return 0; -+} -+EXPORT_SYMBOL(rt_write_lock_irqsave); -+ -+unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) -+{ -+ rt_read_lock(rwlock); -+ -+ return 0; -+} -+EXPORT_SYMBOL(rt_read_lock_irqsave); -+ -+void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) -+{ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ /* -+ * Make sure we are not reinitializing a held lock: -+ */ -+ debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); -+ lockdep_init_map(&rwlock->dep_map, name, key, 0); -+#endif -+ rwlock->lock.save_state = 1; -+ rwlock->read_depth = 0; -+} -+EXPORT_SYMBOL(__rt_rwlock_init); -+ -+/* -+ * rw_semaphores -+ */ -+ -+void rt_up_write(struct rw_semaphore *rwsem) -+{ -+ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); -+ rt_mutex_unlock(&rwsem->lock); -+} -+EXPORT_SYMBOL(rt_up_write); -+ -+void __rt_up_read(struct rw_semaphore *rwsem) -+{ -+ if (--rwsem->read_depth == 0) -+ rt_mutex_unlock(&rwsem->lock); -+} -+ -+void rt_up_read(struct rw_semaphore *rwsem) -+{ -+ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); -+ __rt_up_read(rwsem); -+} -+EXPORT_SYMBOL(rt_up_read); -+ -+/* -+ * downgrade a write lock into a read lock -+ * - just wake up any readers at the front of the queue -+ */ -+void rt_downgrade_write(struct rw_semaphore *rwsem) -+{ -+ BUG_ON(rt_mutex_owner(&rwsem->lock) != current); -+ rwsem->read_depth = 1; -+} -+EXPORT_SYMBOL(rt_downgrade_write); -+ -+int rt_down_write_trylock(struct rw_semaphore *rwsem) -+{ -+ int ret = rt_mutex_trylock(&rwsem->lock); -+ -+ if (ret) -+ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(rt_down_write_trylock); -+ -+void rt_down_write(struct rw_semaphore *rwsem) -+{ -+ rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); -+ rt_mutex_lock(&rwsem->lock); -+} -+EXPORT_SYMBOL(rt_down_write); -+ -+void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) -+{ -+ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); -+ rt_mutex_lock(&rwsem->lock); -+} -+EXPORT_SYMBOL(rt_down_write_nested); -+ -+void rt_down_write_nested_lock(struct rw_semaphore *rwsem, -+ struct lockdep_map *nest) -+{ -+ rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); -+ rt_mutex_lock(&rwsem->lock); -+} -+EXPORT_SYMBOL(rt_down_write_nested_lock); -+ -+int rt__down_read_trylock(struct rw_semaphore *rwsem) -+{ -+ struct rt_mutex *lock = &rwsem->lock; -+ int ret = 1; -+ -+ /* -+ * recursive read locks succeed when current owns the rwsem, -+ * but not when read_depth == 0 which means that the rwsem is -+ * write locked. -+ */ -+ if (rt_mutex_owner(lock) != current) -+ ret = rt_mutex_trylock(&rwsem->lock); -+ else if (!rwsem->read_depth) -+ ret = 0; -+ -+ if (ret) -+ rwsem->read_depth++; -+ return ret; -+ -+} -+ -+int rt_down_read_trylock(struct rw_semaphore *rwsem) -+{ -+ int ret; -+ -+ ret = rt__down_read_trylock(rwsem); -+ if (ret) -+ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); -+ -+ return ret; -+} -+EXPORT_SYMBOL(rt_down_read_trylock); -+ -+void rt__down_read(struct rw_semaphore *rwsem) -+{ -+ struct rt_mutex *lock = &rwsem->lock; -+ -+ if (rt_mutex_owner(lock) != current) -+ rt_mutex_lock(&rwsem->lock); -+ rwsem->read_depth++; -+} -+EXPORT_SYMBOL(rt__down_read); -+ -+static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) -+{ -+ rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); -+ rt__down_read(rwsem); -+} -+ -+void rt_down_read(struct rw_semaphore *rwsem) -+{ -+ __rt_down_read(rwsem, 0); -+} -+EXPORT_SYMBOL(rt_down_read); -+ -+void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) -+{ -+ __rt_down_read(rwsem, subclass); -+} -+EXPORT_SYMBOL(rt_down_read_nested); -+ -+void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, -+ struct lock_class_key *key) -+{ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ /* -+ * Make sure we are not reinitializing a held lock: -+ */ -+ debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); -+ lockdep_init_map(&rwsem->dep_map, name, key, 0); -+#endif -+ rwsem->read_depth = 0; -+ rwsem->lock.save_state = 0; -+} -+EXPORT_SYMBOL(__rt_rwsem_init); -+ -+/** -+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 -+ * @cnt: the atomic which we are to dec -+ * @lock: the mutex to return holding if we dec to 0 -+ * -+ * return true and hold lock if we dec to 0, return false otherwise -+ */ -+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) -+{ -+ /* dec if we can't possibly hit 0 */ -+ if (atomic_add_unless(cnt, -1, 1)) -+ return 0; -+ /* we might hit 0, so take the lock */ -+ mutex_lock(lock); -+ if (!atomic_dec_and_test(cnt)) { -+ /* when we actually did the dec, we didn't hit 0 */ -+ mutex_unlock(lock); -+ return 0; -+ } -+ /* we hit 0, and we hold the lock */ -+ return 1; -+} -+EXPORT_SYMBOL(atomic_dec_and_mutex_lock); -diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex.c linux-4.4.28/kernel/locking/rtmutex.c ---- linux-4.4.28.orig/kernel/locking/rtmutex.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/rtmutex.c 2016-11-01 21:26:58.772342023 +0100 -@@ -7,6 +7,11 @@ - * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner - * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt - * Copyright (C) 2006 Esben Nielsen -+ * Adaptive Spinlocks: -+ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, -+ * and Peter Morreale, -+ * Adaptive Spinlocks simplification: -+ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt - * - * See Documentation/locking/rt-mutex-design.txt for details. - */ -@@ -16,6 +21,7 @@ - #include - #include - #include -+#include - - #include "rtmutex_common.h" - -@@ -69,6 +75,12 @@ - clear_rt_mutex_waiters(lock); - } - -+static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) -+{ -+ return waiter && waiter != PI_WAKEUP_INPROGRESS && -+ waiter != PI_REQUEUE_INPROGRESS; -+} -+ - /* - * We can speed up the acquire/release, if there's no debugging state to be - * set up. -@@ -99,13 +111,14 @@ - * 2) Drop lock->wait_lock - * 3) Try to unlock the lock with cmpxchg - */ --static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) -+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, -+ unsigned long flags) - __releases(lock->wait_lock) - { - struct task_struct *owner = rt_mutex_owner(lock); - - clear_rt_mutex_waiters(lock); -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - /* - * If a new waiter comes in between the unlock and the cmpxchg - * we have two situations: -@@ -147,11 +160,12 @@ - /* - * Simple slow path only version: lock->owner is protected by lock->wait_lock. - */ --static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) -+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, -+ unsigned long flags) - __releases(lock->wait_lock) - { - lock->owner = NULL; -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - return true; - } - #endif -@@ -348,6 +362,14 @@ - return debug_rt_mutex_detect_deadlock(waiter, chwalk); - } - -+static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) -+{ -+ if (waiter->savestate) -+ wake_up_lock_sleeper(waiter->task); -+ else -+ wake_up_process(waiter->task); -+} -+ - /* - * Max number of times we'll walk the boosting chain: - */ -@@ -355,7 +377,8 @@ - - static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) - { -- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; -+ return rt_mutex_real_waiter(p->pi_blocked_on) ? -+ p->pi_blocked_on->lock : NULL; - } - - /* -@@ -433,7 +456,6 @@ - int ret = 0, depth = 0; - struct rt_mutex *lock; - bool detect_deadlock; -- unsigned long flags; - bool requeue = true; - - detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); -@@ -476,7 +498,7 @@ - /* - * [1] Task cannot go away as we did a get_task() before ! - */ -- raw_spin_lock_irqsave(&task->pi_lock, flags); -+ raw_spin_lock_irq(&task->pi_lock); - - /* - * [2] Get the waiter on which @task is blocked on. -@@ -492,7 +514,7 @@ - * reached or the state of the chain has changed while we - * dropped the locks. - */ -- if (!waiter) -+ if (!rt_mutex_real_waiter(waiter)) - goto out_unlock_pi; - - /* -@@ -560,7 +582,7 @@ - * operations. - */ - if (!raw_spin_trylock(&lock->wait_lock)) { -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock_irq(&task->pi_lock); - cpu_relax(); - goto retry; - } -@@ -591,7 +613,7 @@ - /* - * No requeue[7] here. Just release @task [8] - */ -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock(&task->pi_lock); - put_task_struct(task); - - /* -@@ -599,14 +621,14 @@ - * If there is no owner of the lock, end of chain. - */ - if (!rt_mutex_owner(lock)) { -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - return 0; - } - - /* [10] Grab the next task, i.e. owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); -- raw_spin_lock_irqsave(&task->pi_lock, flags); -+ raw_spin_lock(&task->pi_lock); - - /* - * No requeue [11] here. We just do deadlock detection. -@@ -621,8 +643,8 @@ - top_waiter = rt_mutex_top_waiter(lock); - - /* [13] Drop locks */ -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock(&task->pi_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - /* If owner is not blocked, end of chain. */ - if (!next_lock) -@@ -643,7 +665,7 @@ - rt_mutex_enqueue(lock, waiter); - - /* [8] Release the task */ -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock(&task->pi_lock); - put_task_struct(task); - - /* -@@ -654,21 +676,24 @@ - * follow here. This is the end of the chain we are walking. - */ - if (!rt_mutex_owner(lock)) { -+ struct rt_mutex_waiter *lock_top_waiter; -+ - /* - * If the requeue [7] above changed the top waiter, - * then we need to wake the new top waiter up to try - * to get the lock. - */ -- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) -- wake_up_process(rt_mutex_top_waiter(lock)->task); -- raw_spin_unlock(&lock->wait_lock); -+ lock_top_waiter = rt_mutex_top_waiter(lock); -+ if (prerequeue_top_waiter != lock_top_waiter) -+ rt_mutex_wake_waiter(lock_top_waiter); -+ raw_spin_unlock_irq(&lock->wait_lock); - return 0; - } - - /* [10] Grab the next task, i.e. the owner of @lock */ - task = rt_mutex_owner(lock); - get_task_struct(task); -- raw_spin_lock_irqsave(&task->pi_lock, flags); -+ raw_spin_lock(&task->pi_lock); - - /* [11] requeue the pi waiters if necessary */ - if (waiter == rt_mutex_top_waiter(lock)) { -@@ -722,8 +747,8 @@ - top_waiter = rt_mutex_top_waiter(lock); - - /* [13] Drop the locks */ -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock(&task->pi_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - /* - * Make the actual exit decisions [12], based on the stored -@@ -746,28 +771,46 @@ - goto again; - - out_unlock_pi: -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock_irq(&task->pi_lock); - out_put_task: - put_task_struct(task); - - return ret; - } - -+ -+#define STEAL_NORMAL 0 -+#define STEAL_LATERAL 1 -+ -+/* -+ * Note that RT tasks are excluded from lateral-steals to prevent the -+ * introduction of an unbounded latency -+ */ -+static inline int lock_is_stealable(struct task_struct *task, -+ struct task_struct *pendowner, int mode) -+{ -+ if (mode == STEAL_NORMAL || rt_task(task)) { -+ if (task->prio >= pendowner->prio) -+ return 0; -+ } else if (task->prio > pendowner->prio) -+ return 0; -+ return 1; -+} -+ - /* - * Try to take an rt-mutex - * -- * Must be called with lock->wait_lock held. -+ * Must be called with lock->wait_lock held and interrupts disabled - * - * @lock: The lock to be acquired. - * @task: The task which wants to acquire the lock - * @waiter: The waiter that is queued to the lock's wait tree if the - * callsite called task_blocked_on_lock(), otherwise NULL - */ --static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, -- struct rt_mutex_waiter *waiter) -+static int __try_to_take_rt_mutex(struct rt_mutex *lock, -+ struct task_struct *task, -+ struct rt_mutex_waiter *waiter, int mode) - { -- unsigned long flags; -- - /* - * Before testing whether we can acquire @lock, we set the - * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all -@@ -803,8 +846,10 @@ - * If waiter is not the highest priority waiter of - * @lock, give up. - */ -- if (waiter != rt_mutex_top_waiter(lock)) -+ if (waiter != rt_mutex_top_waiter(lock)) { -+ /* XXX lock_is_stealable() ? */ - return 0; -+ } - - /* - * We can acquire the lock. Remove the waiter from the -@@ -822,14 +867,10 @@ - * not need to be dequeued. - */ - if (rt_mutex_has_waiters(lock)) { -- /* -- * If @task->prio is greater than or equal to -- * the top waiter priority (kernel view), -- * @task lost. -- */ -- if (task->prio >= rt_mutex_top_waiter(lock)->prio) -- return 0; -+ struct task_struct *pown = rt_mutex_top_waiter(lock)->task; - -+ if (task != pown && !lock_is_stealable(task, pown, mode)) -+ return 0; - /* - * The current top waiter stays enqueued. We - * don't have to change anything in the lock -@@ -852,7 +893,7 @@ - * case, but conditionals are more expensive than a redundant - * store. - */ -- raw_spin_lock_irqsave(&task->pi_lock, flags); -+ raw_spin_lock(&task->pi_lock); - task->pi_blocked_on = NULL; - /* - * Finish the lock acquisition. @task is the new owner. If -@@ -861,7 +902,7 @@ - */ - if (rt_mutex_has_waiters(lock)) - rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock(&task->pi_lock); - - takeit: - /* We got the lock. */ -@@ -878,12 +919,444 @@ - return 1; - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * preemptible spin_lock functions: -+ */ -+static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, -+ void (*slowfn)(struct rt_mutex *lock, -+ bool mg_off), -+ bool do_mig_dis) -+{ -+ might_sleep_no_state_check(); -+ -+ if (do_mig_dis) -+ migrate_disable(); -+ -+ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) -+ rt_mutex_deadlock_account_lock(lock, current); -+ else -+ slowfn(lock, do_mig_dis); -+} -+ -+static inline int rt_spin_lock_fastunlock(struct rt_mutex *lock, -+ int (*slowfn)(struct rt_mutex *lock)) -+{ -+ if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { -+ rt_mutex_deadlock_account_unlock(current); -+ return 0; -+ } -+ return slowfn(lock); -+} -+#ifdef CONFIG_SMP -+/* -+ * Note that owner is a speculative pointer and dereferencing relies -+ * on rcu_read_lock() and the check against the lock owner. -+ */ -+static int adaptive_wait(struct rt_mutex *lock, -+ struct task_struct *owner) -+{ -+ int res = 0; -+ -+ rcu_read_lock(); -+ for (;;) { -+ if (owner != rt_mutex_owner(lock)) -+ break; -+ /* -+ * Ensure that owner->on_cpu is dereferenced _after_ -+ * checking the above to be valid. -+ */ -+ barrier(); -+ if (!owner->on_cpu) { -+ res = 1; -+ break; -+ } -+ cpu_relax(); -+ } -+ rcu_read_unlock(); -+ return res; -+} -+#else -+static int adaptive_wait(struct rt_mutex *lock, -+ struct task_struct *orig_owner) -+{ -+ return 1; -+} -+#endif -+ -+static int task_blocks_on_rt_mutex(struct rt_mutex *lock, -+ struct rt_mutex_waiter *waiter, -+ struct task_struct *task, -+ enum rtmutex_chainwalk chwalk); -+/* -+ * Slow path lock function spin_lock style: this variant is very -+ * careful not to miss any non-lock wakeups. -+ * -+ * We store the current state under p->pi_lock in p->saved_state and -+ * the try_to_wake_up() code handles this accordingly. -+ */ -+static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock, -+ bool mg_off) -+{ -+ struct task_struct *lock_owner, *self = current; -+ struct rt_mutex_waiter waiter, *top_waiter; -+ unsigned long flags; -+ int ret; -+ -+ rt_mutex_init_waiter(&waiter, true); -+ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); -+ -+ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ return; -+ } -+ -+ BUG_ON(rt_mutex_owner(lock) == self); -+ -+ /* -+ * We save whatever state the task is in and we'll restore it -+ * after acquiring the lock taking real wakeups into account -+ * as well. We are serialized via pi_lock against wakeups. See -+ * try_to_wake_up(). -+ */ -+ raw_spin_lock(&self->pi_lock); -+ self->saved_state = self->state; -+ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); -+ raw_spin_unlock(&self->pi_lock); -+ -+ ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK); -+ BUG_ON(ret); -+ -+ for (;;) { -+ /* Try to acquire the lock again. */ -+ if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) -+ break; -+ -+ top_waiter = rt_mutex_top_waiter(lock); -+ lock_owner = rt_mutex_owner(lock); -+ -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ -+ debug_rt_mutex_print_deadlock(&waiter); -+ -+ if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) { -+ if (mg_off) -+ migrate_enable(); -+ schedule(); -+ if (mg_off) -+ migrate_disable(); -+ } -+ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); -+ -+ raw_spin_lock(&self->pi_lock); -+ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); -+ raw_spin_unlock(&self->pi_lock); -+ } -+ -+ /* -+ * Restore the task state to current->saved_state. We set it -+ * to the original state above and the try_to_wake_up() code -+ * has possibly updated it when a real (non-rtmutex) wakeup -+ * happened while we were blocked. Clear saved_state so -+ * try_to_wakeup() does not get confused. -+ */ -+ raw_spin_lock(&self->pi_lock); -+ __set_current_state_no_track(self->saved_state); -+ self->saved_state = TASK_RUNNING; -+ raw_spin_unlock(&self->pi_lock); -+ -+ /* -+ * try_to_take_rt_mutex() sets the waiter bit -+ * unconditionally. We might have to fix that up: -+ */ -+ fixup_rt_mutex_waiters(lock); -+ -+ BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); -+ BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry)); -+ -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ -+ debug_rt_mutex_free_waiter(&waiter); -+} -+ -+static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, -+ struct wake_q_head *wake_sleeper_q, -+ struct rt_mutex *lock); -+/* -+ * Slow path to release a rt_mutex spin_lock style -+ */ -+static int noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) -+{ -+ unsigned long flags; -+ WAKE_Q(wake_q); -+ WAKE_Q(wake_sleeper_q); -+ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); -+ -+ debug_rt_mutex_unlock(lock); -+ -+ rt_mutex_deadlock_account_unlock(current); -+ -+ if (!rt_mutex_has_waiters(lock)) { -+ lock->owner = NULL; -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ return 0; -+ } -+ -+ mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock); -+ -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ wake_up_q(&wake_q); -+ wake_up_q_sleeper(&wake_sleeper_q); -+ -+ /* Undo pi boosting.when necessary */ -+ rt_mutex_adjust_prio(current); -+ return 0; -+} -+ -+static int noinline __sched rt_spin_lock_slowunlock_no_deboost(struct rt_mutex *lock) -+{ -+ unsigned long flags; -+ WAKE_Q(wake_q); -+ WAKE_Q(wake_sleeper_q); -+ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); -+ -+ debug_rt_mutex_unlock(lock); -+ -+ rt_mutex_deadlock_account_unlock(current); -+ -+ if (!rt_mutex_has_waiters(lock)) { -+ lock->owner = NULL; -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ return 0; -+ } -+ -+ mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock); -+ -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); -+ wake_up_q(&wake_q); -+ wake_up_q_sleeper(&wake_sleeper_q); -+ return 1; -+} -+ -+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock) -+{ -+ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, false); -+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); -+} -+EXPORT_SYMBOL(rt_spin_lock__no_mg); -+ -+void __lockfunc rt_spin_lock(spinlock_t *lock) -+{ -+ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true); -+ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); -+} -+EXPORT_SYMBOL(rt_spin_lock); -+ -+void __lockfunc __rt_spin_lock(struct rt_mutex *lock) -+{ -+ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, true); -+} -+EXPORT_SYMBOL(__rt_spin_lock); -+ -+void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock) -+{ -+ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, false); -+} -+EXPORT_SYMBOL(__rt_spin_lock__no_mg); -+ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) -+{ -+ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); -+ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true); -+} -+EXPORT_SYMBOL(rt_spin_lock_nested); -+#endif -+ -+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock) -+{ -+ /* NOTE: we always pass in '1' for nested, for simplicity */ -+ spin_release(&lock->dep_map, 1, _RET_IP_); -+ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); -+} -+EXPORT_SYMBOL(rt_spin_unlock__no_mg); -+ -+void __lockfunc rt_spin_unlock(spinlock_t *lock) -+{ -+ /* NOTE: we always pass in '1' for nested, for simplicity */ -+ spin_release(&lock->dep_map, 1, _RET_IP_); -+ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); -+ migrate_enable(); -+} -+EXPORT_SYMBOL(rt_spin_unlock); -+ -+int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock) -+{ -+ int ret; -+ -+ /* NOTE: we always pass in '1' for nested, for simplicity */ -+ spin_release(&lock->dep_map, 1, _RET_IP_); -+ ret = rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_no_deboost); -+ migrate_enable(); -+ return ret; -+} -+ -+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) -+{ -+ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); -+} -+EXPORT_SYMBOL(__rt_spin_unlock); -+ -+/* -+ * Wait for the lock to get unlocked: instead of polling for an unlock -+ * (like raw spinlocks do), we lock and unlock, to force the kernel to -+ * schedule if there's contention: -+ */ -+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) -+{ -+ spin_lock(lock); -+ spin_unlock(lock); -+} -+EXPORT_SYMBOL(rt_spin_unlock_wait); -+ -+int __lockfunc __rt_spin_trylock(struct rt_mutex *lock) -+{ -+ return rt_mutex_trylock(lock); -+} -+ -+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock) -+{ -+ int ret; -+ -+ ret = rt_mutex_trylock(&lock->lock); -+ if (ret) -+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); -+ return ret; -+} -+EXPORT_SYMBOL(rt_spin_trylock__no_mg); -+ -+int __lockfunc rt_spin_trylock(spinlock_t *lock) -+{ -+ int ret; -+ -+ migrate_disable(); -+ ret = rt_mutex_trylock(&lock->lock); -+ if (ret) -+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); -+ else -+ migrate_enable(); -+ return ret; -+} -+EXPORT_SYMBOL(rt_spin_trylock); -+ -+int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) -+{ -+ int ret; -+ -+ local_bh_disable(); -+ ret = rt_mutex_trylock(&lock->lock); -+ if (ret) { -+ migrate_disable(); -+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); -+ } else -+ local_bh_enable(); -+ return ret; -+} -+EXPORT_SYMBOL(rt_spin_trylock_bh); -+ -+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) -+{ -+ int ret; -+ -+ *flags = 0; -+ ret = rt_mutex_trylock(&lock->lock); -+ if (ret) { -+ migrate_disable(); -+ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); -+ } -+ return ret; -+} -+EXPORT_SYMBOL(rt_spin_trylock_irqsave); -+ -+int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) -+{ -+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ -+ if (atomic_add_unless(atomic, -1, 1)) -+ return 0; -+ rt_spin_lock(lock); -+ if (atomic_dec_and_test(atomic)) -+ return 1; -+ rt_spin_unlock(lock); -+ return 0; -+} -+EXPORT_SYMBOL(atomic_dec_and_spin_lock); -+ -+ void -+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) -+{ -+#ifdef CONFIG_DEBUG_LOCK_ALLOC -+ /* -+ * Make sure we are not reinitializing a held lock: -+ */ -+ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); -+ lockdep_init_map(&lock->dep_map, name, key, 0); -+#endif -+} -+EXPORT_SYMBOL(__rt_spin_lock_init); -+ -+#endif /* PREEMPT_RT_FULL */ -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ static inline int __sched -+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) -+{ -+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); -+ struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); -+ -+ if (!hold_ctx) -+ return 0; -+ -+ if (unlikely(ctx == hold_ctx)) -+ return -EALREADY; -+ -+ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && -+ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { -+#ifdef CONFIG_DEBUG_MUTEXES -+ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); -+ ctx->contending_lock = ww; -+#endif -+ return -EDEADLK; -+ } -+ -+ return 0; -+} -+#else -+ static inline int __sched -+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) -+{ -+ BUG(); -+ return 0; -+} -+ -+#endif -+ -+static inline int -+try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, -+ struct rt_mutex_waiter *waiter) -+{ -+ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); -+} -+ - /* - * Task blocks on lock. - * - * Prepare waiter and propagate pi chain - * -- * This must be called with lock->wait_lock held. -+ * This must be called with lock->wait_lock held and interrupts disabled - */ - static int task_blocks_on_rt_mutex(struct rt_mutex *lock, - struct rt_mutex_waiter *waiter, -@@ -894,7 +1367,6 @@ - struct rt_mutex_waiter *top_waiter = waiter; - struct rt_mutex *next_lock; - int chain_walk = 0, res; -- unsigned long flags; - - /* - * Early deadlock detection. We really don't want the task to -@@ -908,7 +1380,24 @@ - if (owner == task) - return -EDEADLK; - -- raw_spin_lock_irqsave(&task->pi_lock, flags); -+ raw_spin_lock(&task->pi_lock); -+ -+ /* -+ * In the case of futex requeue PI, this will be a proxy -+ * lock. The task will wake unaware that it is enqueueed on -+ * this lock. Avoid blocking on two locks and corrupting -+ * pi_blocked_on via the PI_WAKEUP_INPROGRESS -+ * flag. futex_wait_requeue_pi() sets this when it wakes up -+ * before requeue (due to a signal or timeout). Do not enqueue -+ * the task if PI_WAKEUP_INPROGRESS is set. -+ */ -+ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { -+ raw_spin_unlock(&task->pi_lock); -+ return -EAGAIN; -+ } -+ -+ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); -+ - __rt_mutex_adjust_prio(task); - waiter->task = task; - waiter->lock = lock; -@@ -921,18 +1410,18 @@ - - task->pi_blocked_on = waiter; - -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); -+ raw_spin_unlock(&task->pi_lock); - - if (!owner) - return 0; - -- raw_spin_lock_irqsave(&owner->pi_lock, flags); -+ raw_spin_lock(&owner->pi_lock); - if (waiter == rt_mutex_top_waiter(lock)) { - rt_mutex_dequeue_pi(owner, top_waiter); - rt_mutex_enqueue_pi(owner, waiter); - - __rt_mutex_adjust_prio(owner); -- if (owner->pi_blocked_on) -+ if (rt_mutex_real_waiter(owner->pi_blocked_on)) - chain_walk = 1; - } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { - chain_walk = 1; -@@ -941,7 +1430,7 @@ - /* Store the lock on which owner is blocked or NULL */ - next_lock = task_blocked_on_lock(owner); - -- raw_spin_unlock_irqrestore(&owner->pi_lock, flags); -+ raw_spin_unlock(&owner->pi_lock); - /* - * Even if full deadlock detection is on, if the owner is not - * blocked itself, we can avoid finding this out in the chain -@@ -957,12 +1446,12 @@ - */ - get_task_struct(owner); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, - next_lock, waiter, task); - -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irq(&lock->wait_lock); - - return res; - } -@@ -971,15 +1460,15 @@ - * Remove the top waiter from the current tasks pi waiter tree and - * queue it up. - * -- * Called with lock->wait_lock held. -+ * Called with lock->wait_lock held and interrupts disabled. - */ - static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, -+ struct wake_q_head *wake_sleeper_q, - struct rt_mutex *lock) - { - struct rt_mutex_waiter *waiter; -- unsigned long flags; - -- raw_spin_lock_irqsave(¤t->pi_lock, flags); -+ raw_spin_lock(¤t->pi_lock); - - waiter = rt_mutex_top_waiter(lock); - -@@ -1001,15 +1490,18 @@ - */ - lock->owner = (void *) RT_MUTEX_HAS_WAITERS; - -- raw_spin_unlock_irqrestore(¤t->pi_lock, flags); -+ raw_spin_unlock(¤t->pi_lock); - -- wake_q_add(wake_q, waiter->task); -+ if (waiter->savestate) -+ wake_q_add(wake_sleeper_q, waiter->task); -+ else -+ wake_q_add(wake_q, waiter->task); - } - - /* - * Remove a waiter from a lock and give up - * -- * Must be called with lock->wait_lock held and -+ * Must be called with lock->wait_lock held and interrupts disabled. I must - * have just failed to try_to_take_rt_mutex(). - */ - static void remove_waiter(struct rt_mutex *lock, -@@ -1017,13 +1509,12 @@ - { - bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); - struct task_struct *owner = rt_mutex_owner(lock); -- struct rt_mutex *next_lock; -- unsigned long flags; -+ struct rt_mutex *next_lock = NULL; - -- raw_spin_lock_irqsave(¤t->pi_lock, flags); -+ raw_spin_lock(¤t->pi_lock); - rt_mutex_dequeue(lock, waiter); - current->pi_blocked_on = NULL; -- raw_spin_unlock_irqrestore(¤t->pi_lock, flags); -+ raw_spin_unlock(¤t->pi_lock); - - /* - * Only update priority if the waiter was the highest priority -@@ -1032,7 +1523,7 @@ - if (!owner || !is_top_waiter) - return; - -- raw_spin_lock_irqsave(&owner->pi_lock, flags); -+ raw_spin_lock(&owner->pi_lock); - - rt_mutex_dequeue_pi(owner, waiter); - -@@ -1042,9 +1533,10 @@ - __rt_mutex_adjust_prio(owner); - - /* Store the lock on which owner is blocked or NULL */ -- next_lock = task_blocked_on_lock(owner); -+ if (rt_mutex_real_waiter(owner->pi_blocked_on)) -+ next_lock = task_blocked_on_lock(owner); - -- raw_spin_unlock_irqrestore(&owner->pi_lock, flags); -+ raw_spin_unlock(&owner->pi_lock); - - /* - * Don't walk the chain, if the owner task is not blocked -@@ -1056,12 +1548,12 @@ - /* gets dropped in rt_mutex_adjust_prio_chain()! */ - get_task_struct(owner); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, - next_lock, NULL, current); - -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irq(&lock->wait_lock); - } - - /* -@@ -1078,17 +1570,17 @@ - raw_spin_lock_irqsave(&task->pi_lock, flags); - - waiter = task->pi_blocked_on; -- if (!waiter || (waiter->prio == task->prio && -+ if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio && - !dl_prio(task->prio))) { - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - return; - } - next_lock = waiter->lock; -- raw_spin_unlock_irqrestore(&task->pi_lock, flags); - - /* gets dropped in rt_mutex_adjust_prio_chain()! */ - get_task_struct(task); - -+ raw_spin_unlock_irqrestore(&task->pi_lock, flags); - rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, - next_lock, NULL, task); - } -@@ -1097,16 +1589,17 @@ - * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop - * @lock: the rt_mutex to take - * @state: the state the task should block in (TASK_INTERRUPTIBLE -- * or TASK_UNINTERRUPTIBLE) -+ * or TASK_UNINTERRUPTIBLE) - * @timeout: the pre-initialized and started timer, or NULL for none - * @waiter: the pre-initialized rt_mutex_waiter - * -- * lock->wait_lock must be held by the caller. -+ * Must be called with lock->wait_lock held and interrupts disabled - */ - static int __sched - __rt_mutex_slowlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, -- struct rt_mutex_waiter *waiter) -+ struct rt_mutex_waiter *waiter, -+ struct ww_acquire_ctx *ww_ctx) - { - int ret = 0; - -@@ -1129,13 +1622,19 @@ - break; - } - -- raw_spin_unlock(&lock->wait_lock); -+ if (ww_ctx && ww_ctx->acquired > 0) { -+ ret = __mutex_lock_check_stamp(lock, ww_ctx); -+ if (ret) -+ break; -+ } -+ -+ raw_spin_unlock_irq(&lock->wait_lock); - - debug_rt_mutex_print_deadlock(waiter); - - schedule(); - -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irq(&lock->wait_lock); - set_current_state(state); - } - -@@ -1163,26 +1662,112 @@ - } - } - -+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, -+ struct ww_acquire_ctx *ww_ctx) -+{ -+#ifdef CONFIG_DEBUG_MUTEXES -+ /* -+ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, -+ * but released with a normal mutex_unlock in this call. -+ * -+ * This should never happen, always use ww_mutex_unlock. -+ */ -+ DEBUG_LOCKS_WARN_ON(ww->ctx); -+ -+ /* -+ * Not quite done after calling ww_acquire_done() ? -+ */ -+ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); -+ -+ if (ww_ctx->contending_lock) { -+ /* -+ * After -EDEADLK you tried to -+ * acquire a different ww_mutex? Bad! -+ */ -+ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); -+ -+ /* -+ * You called ww_mutex_lock after receiving -EDEADLK, -+ * but 'forgot' to unlock everything else first? -+ */ -+ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); -+ ww_ctx->contending_lock = NULL; -+ } -+ -+ /* -+ * Naughty, using a different class will lead to undefined behavior! -+ */ -+ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); -+#endif -+ ww_ctx->acquired++; -+} -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+static void ww_mutex_account_lock(struct rt_mutex *lock, -+ struct ww_acquire_ctx *ww_ctx) -+{ -+ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); -+ struct rt_mutex_waiter *waiter, *n; -+ -+ /* -+ * This branch gets optimized out for the common case, -+ * and is only important for ww_mutex_lock. -+ */ -+ ww_mutex_lock_acquired(ww, ww_ctx); -+ ww->ctx = ww_ctx; -+ -+ /* -+ * Give any possible sleeping processes the chance to wake up, -+ * so they can recheck if they have to back off. -+ */ -+ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters, -+ tree_entry) { -+ /* XXX debug rt mutex waiter wakeup */ -+ -+ BUG_ON(waiter->lock != lock); -+ rt_mutex_wake_waiter(waiter); -+ } -+} -+ -+#else -+ -+static void ww_mutex_account_lock(struct rt_mutex *lock, -+ struct ww_acquire_ctx *ww_ctx) -+{ -+ BUG(); -+} -+#endif -+ - /* - * Slow path lock function: - */ - static int __sched - rt_mutex_slowlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, -- enum rtmutex_chainwalk chwalk) -+ enum rtmutex_chainwalk chwalk, -+ struct ww_acquire_ctx *ww_ctx) - { - struct rt_mutex_waiter waiter; -+ unsigned long flags; - int ret = 0; - -- debug_rt_mutex_init_waiter(&waiter); -- RB_CLEAR_NODE(&waiter.pi_tree_entry); -- RB_CLEAR_NODE(&waiter.tree_entry); -+ rt_mutex_init_waiter(&waiter, false); - -- raw_spin_lock(&lock->wait_lock); -+ /* -+ * Technically we could use raw_spin_[un]lock_irq() here, but this can -+ * be called in early boot if the cmpxchg() fast path is disabled -+ * (debug, no architecture support). In this case we will acquire the -+ * rtmutex with lock->wait_lock held. But we cannot unconditionally -+ * enable interrupts in that early boot case. So we need to use the -+ * irqsave/restore variants. -+ */ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); - - /* Try to acquire the lock again: */ - if (try_to_take_rt_mutex(lock, current, NULL)) { -- raw_spin_unlock(&lock->wait_lock); -+ if (ww_ctx) -+ ww_mutex_account_lock(lock, ww_ctx); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - return 0; - } - -@@ -1196,13 +1781,23 @@ - - if (likely(!ret)) - /* sleep on the mutex */ -- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); -+ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, -+ ww_ctx); -+ else if (ww_ctx) { -+ /* ww_mutex received EDEADLK, let it become EALREADY */ -+ ret = __mutex_lock_check_stamp(lock, ww_ctx); -+ BUG_ON(!ret); -+ } - - if (unlikely(ret)) { - __set_current_state(TASK_RUNNING); - if (rt_mutex_has_waiters(lock)) - remove_waiter(lock, &waiter); -- rt_mutex_handle_deadlock(ret, chwalk, &waiter); -+ /* ww_mutex want to report EDEADLK/EALREADY, let them */ -+ if (!ww_ctx) -+ rt_mutex_handle_deadlock(ret, chwalk, &waiter); -+ } else if (ww_ctx) { -+ ww_mutex_account_lock(lock, ww_ctx); - } - - /* -@@ -1211,7 +1806,7 @@ - */ - fixup_rt_mutex_waiters(lock); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - /* Remove pending timer: */ - if (unlikely(timeout)) -@@ -1227,6 +1822,7 @@ - */ - static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) - { -+ unsigned long flags; - int ret; - - /* -@@ -1238,10 +1834,10 @@ - return 0; - - /* -- * The mutex has currently no owner. Lock the wait lock and -- * try to acquire the lock. -+ * The mutex has currently no owner. Lock the wait lock and try to -+ * acquire the lock. We use irqsave here to support early boot calls. - */ -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); - - ret = try_to_take_rt_mutex(lock, current, NULL); - -@@ -1251,7 +1847,7 @@ - */ - fixup_rt_mutex_waiters(lock); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - return ret; - } -@@ -1261,9 +1857,13 @@ - * Return whether the current task needs to undo a potential priority boosting. - */ - static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, -- struct wake_q_head *wake_q) -+ struct wake_q_head *wake_q, -+ struct wake_q_head *wake_sleeper_q) - { -- raw_spin_lock(&lock->wait_lock); -+ unsigned long flags; -+ -+ /* irqsave required to support early boot calls */ -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); - - debug_rt_mutex_unlock(lock); - -@@ -1302,10 +1902,10 @@ - */ - while (!rt_mutex_has_waiters(lock)) { - /* Drops lock->wait_lock ! */ -- if (unlock_rt_mutex_safe(lock) == true) -+ if (unlock_rt_mutex_safe(lock, flags) == true) - return false; - /* Relock the rtmutex and try again */ -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irqsave(&lock->wait_lock, flags); - } - - /* -@@ -1314,9 +1914,9 @@ - * - * Queue the next waiter for wakeup once we release the wait_lock. - */ -- mark_wakeup_next_waiter(wake_q, lock); -+ mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); - - /* check PI boosting */ - return true; -@@ -1330,31 +1930,36 @@ - */ - static inline int - rt_mutex_fastlock(struct rt_mutex *lock, int state, -+ struct ww_acquire_ctx *ww_ctx, - int (*slowfn)(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, -- enum rtmutex_chainwalk chwalk)) -+ enum rtmutex_chainwalk chwalk, -+ struct ww_acquire_ctx *ww_ctx)) - { - if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); - return 0; - } else -- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); -+ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, -+ ww_ctx); - } - - static inline int - rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, - enum rtmutex_chainwalk chwalk, -+ struct ww_acquire_ctx *ww_ctx, - int (*slowfn)(struct rt_mutex *lock, int state, - struct hrtimer_sleeper *timeout, -- enum rtmutex_chainwalk chwalk)) -+ enum rtmutex_chainwalk chwalk, -+ struct ww_acquire_ctx *ww_ctx)) - { - if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { - rt_mutex_deadlock_account_lock(lock, current); - return 0; - } else -- return slowfn(lock, state, timeout, chwalk); -+ return slowfn(lock, state, timeout, chwalk, ww_ctx); - } - - static inline int -@@ -1371,17 +1976,20 @@ - static inline void - rt_mutex_fastunlock(struct rt_mutex *lock, - bool (*slowfn)(struct rt_mutex *lock, -- struct wake_q_head *wqh)) -+ struct wake_q_head *wqh, -+ struct wake_q_head *wq_sleeper)) - { - WAKE_Q(wake_q); -+ WAKE_Q(wake_sleeper_q); - - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { - rt_mutex_deadlock_account_unlock(current); - - } else { -- bool deboost = slowfn(lock, &wake_q); -+ bool deboost = slowfn(lock, &wake_q, &wake_sleeper_q); - - wake_up_q(&wake_q); -+ wake_up_q_sleeper(&wake_sleeper_q); - - /* Undo pi boosting if necessary: */ - if (deboost) -@@ -1398,7 +2006,7 @@ - { - might_sleep(); - -- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); -+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock); - } - EXPORT_SYMBOL_GPL(rt_mutex_lock); - -@@ -1415,7 +2023,7 @@ - { - might_sleep(); - -- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); -+ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock); - } - EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); - -@@ -1428,11 +2036,30 @@ - might_sleep(); - - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, -- RT_MUTEX_FULL_CHAINWALK, -+ RT_MUTEX_FULL_CHAINWALK, NULL, - rt_mutex_slowlock); - } - - /** -+ * rt_mutex_lock_killable - lock a rt_mutex killable -+ * -+ * @lock: the rt_mutex to be locked -+ * @detect_deadlock: deadlock detection on/off -+ * -+ * Returns: -+ * 0 on success -+ * -EINTR when interrupted by a signal -+ * -EDEADLK when the lock would deadlock (when deadlock detection is on) -+ */ -+int __sched rt_mutex_lock_killable(struct rt_mutex *lock) -+{ -+ might_sleep(); -+ -+ return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock); -+} -+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); -+ -+/** - * rt_mutex_timed_lock - lock a rt_mutex interruptible - * the timeout structure is provided - * by the caller -@@ -1452,6 +2079,7 @@ - - return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, - RT_MUTEX_MIN_CHAINWALK, -+ NULL, - rt_mutex_slowlock); - } - EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); -@@ -1469,7 +2097,11 @@ - */ - int __sched rt_mutex_trylock(struct rt_mutex *lock) - { -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (WARN_ON_ONCE(in_irq() || in_nmi())) -+#else - if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq())) -+#endif - return 0; - - return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); -@@ -1495,13 +2127,14 @@ - * required or not. - */ - bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, -- struct wake_q_head *wqh) -+ struct wake_q_head *wqh, -+ struct wake_q_head *wq_sleeper) - { - if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { - rt_mutex_deadlock_account_unlock(current); - return false; - } -- return rt_mutex_slowunlock(lock, wqh); -+ return rt_mutex_slowunlock(lock, wqh, wq_sleeper); - } - - /** -@@ -1534,13 +2167,12 @@ - void __rt_mutex_init(struct rt_mutex *lock, const char *name) - { - lock->owner = NULL; -- raw_spin_lock_init(&lock->wait_lock); - lock->waiters = RB_ROOT; - lock->waiters_leftmost = NULL; - - debug_rt_mutex_init(lock, name); - } --EXPORT_SYMBOL_GPL(__rt_mutex_init); -+EXPORT_SYMBOL(__rt_mutex_init); - - /** - * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a -@@ -1555,7 +2187,7 @@ - void rt_mutex_init_proxy_locked(struct rt_mutex *lock, - struct task_struct *proxy_owner) - { -- __rt_mutex_init(lock, NULL); -+ rt_mutex_init(lock); - debug_rt_mutex_proxy_lock(lock, proxy_owner); - rt_mutex_set_owner(lock, proxy_owner); - rt_mutex_deadlock_account_lock(lock, proxy_owner); -@@ -1596,13 +2228,42 @@ - { - int ret; - -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irq(&lock->wait_lock); - - if (try_to_take_rt_mutex(lock, task, NULL)) { -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - return 1; - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ /* -+ * In PREEMPT_RT there's an added race. -+ * If the task, that we are about to requeue, times out, -+ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue -+ * to skip this task. But right after the task sets -+ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then -+ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. -+ * This will replace the PI_WAKEUP_INPROGRESS with the actual -+ * lock that it blocks on. We *must not* place this task -+ * on this proxy lock in that case. -+ * -+ * To prevent this race, we first take the task's pi_lock -+ * and check if it has updated its pi_blocked_on. If it has, -+ * we assume that it woke up and we return -EAGAIN. -+ * Otherwise, we set the task's pi_blocked_on to -+ * PI_REQUEUE_INPROGRESS, so that if the task is waking up -+ * it will know that we are in the process of requeuing it. -+ */ -+ raw_spin_lock(&task->pi_lock); -+ if (task->pi_blocked_on) { -+ raw_spin_unlock(&task->pi_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); -+ return -EAGAIN; -+ } -+ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; -+ raw_spin_unlock(&task->pi_lock); -+#endif -+ - /* We enforce deadlock detection for futexes */ - ret = task_blocks_on_rt_mutex(lock, waiter, task, - RT_MUTEX_FULL_CHAINWALK); -@@ -1617,10 +2278,10 @@ - ret = 0; - } - -- if (unlikely(ret)) -+ if (ret && rt_mutex_has_waiters(lock)) - remove_waiter(lock, waiter); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - debug_rt_mutex_print_deadlock(waiter); - -@@ -1668,12 +2329,12 @@ - { - int ret; - -- raw_spin_lock(&lock->wait_lock); -+ raw_spin_lock_irq(&lock->wait_lock); - - set_current_state(TASK_INTERRUPTIBLE); - - /* sleep on the mutex */ -- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); -+ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); - - if (unlikely(ret)) - remove_waiter(lock, waiter); -@@ -1684,7 +2345,93 @@ - */ - fixup_rt_mutex_waiters(lock); - -- raw_spin_unlock(&lock->wait_lock); -+ raw_spin_unlock_irq(&lock->wait_lock); - - return ret; - } -+ -+static inline int -+ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -+{ -+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH -+ unsigned tmp; -+ -+ if (ctx->deadlock_inject_countdown-- == 0) { -+ tmp = ctx->deadlock_inject_interval; -+ if (tmp > UINT_MAX/4) -+ tmp = UINT_MAX; -+ else -+ tmp = tmp*2 + tmp + tmp/2; -+ -+ ctx->deadlock_inject_interval = tmp; -+ ctx->deadlock_inject_countdown = tmp; -+ ctx->contending_lock = lock; -+ -+ ww_mutex_unlock(lock); -+ -+ return -EDEADLK; -+ } -+#endif -+ -+ return 0; -+} -+ -+#ifdef CONFIG_PREEMPT_RT_FULL -+int __sched -+__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) -+{ -+ int ret; -+ -+ might_sleep(); -+ -+ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); -+ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); -+ if (ret) -+ mutex_release(&lock->base.dep_map, 1, _RET_IP_); -+ else if (!ret && ww_ctx->acquired > 1) -+ return ww_mutex_deadlock_injection(lock, ww_ctx); -+ -+ return ret; -+} -+EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); -+ -+int __sched -+__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) -+{ -+ int ret; -+ -+ might_sleep(); -+ -+ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); -+ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); -+ if (ret) -+ mutex_release(&lock->base.dep_map, 1, _RET_IP_); -+ else if (!ret && ww_ctx->acquired > 1) -+ return ww_mutex_deadlock_injection(lock, ww_ctx); -+ -+ return ret; -+} -+EXPORT_SYMBOL_GPL(__ww_mutex_lock); -+ -+void __sched ww_mutex_unlock(struct ww_mutex *lock) -+{ -+ int nest = !!lock->ctx; -+ -+ /* -+ * The unlocking fastpath is the 0->1 transition from 'locked' -+ * into 'unlocked' state: -+ */ -+ if (nest) { -+#ifdef CONFIG_DEBUG_MUTEXES -+ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); -+#endif -+ if (lock->ctx->acquired > 0) -+ lock->ctx->acquired--; -+ lock->ctx = NULL; -+ } -+ -+ mutex_release(&lock->base.dep_map, nest, _RET_IP_); -+ rt_mutex_unlock(&lock->base.lock); -+} -+EXPORT_SYMBOL(ww_mutex_unlock); -+#endif -diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex_common.h linux-4.4.28/kernel/locking/rtmutex_common.h ---- linux-4.4.28.orig/kernel/locking/rtmutex_common.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/rtmutex_common.h 2016-11-01 21:26:58.772342023 +0100 -@@ -27,6 +27,7 @@ - struct rb_node pi_tree_entry; - struct task_struct *task; - struct rt_mutex *lock; -+ bool savestate; - #ifdef CONFIG_DEBUG_RT_MUTEXES - unsigned long ip; - struct pid *deadlock_task_pid; -@@ -97,6 +98,9 @@ - /* - * PI-futex support (proxy locking functions, etc.): - */ -+#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) -+#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) -+ - extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); - extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, - struct task_struct *proxy_owner); -@@ -110,7 +114,8 @@ - struct rt_mutex_waiter *waiter); - extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); - extern bool rt_mutex_futex_unlock(struct rt_mutex *lock, -- struct wake_q_head *wqh); -+ struct wake_q_head *wqh, -+ struct wake_q_head *wq_sleeper); - extern void rt_mutex_adjust_prio(struct task_struct *task); - - #ifdef CONFIG_DEBUG_RT_MUTEXES -@@ -119,4 +124,14 @@ - # include "rtmutex.h" - #endif - -+static inline void -+rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) -+{ -+ debug_rt_mutex_init_waiter(waiter); -+ waiter->task = NULL; -+ waiter->savestate = savestate; -+ RB_CLEAR_NODE(&waiter->pi_tree_entry); -+ RB_CLEAR_NODE(&waiter->tree_entry); -+} -+ - #endif -diff -Nur linux-4.4.28.orig/kernel/locking/spinlock.c linux-4.4.28/kernel/locking/spinlock.c ---- linux-4.4.28.orig/kernel/locking/spinlock.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/spinlock.c 2016-11-01 21:26:58.772342023 +0100 -@@ -124,8 +124,11 @@ - * __[spin|read|write]_lock_bh() - */ - BUILD_LOCK_OPS(spin, raw_spinlock); -+ -+#ifndef CONFIG_PREEMPT_RT_FULL - BUILD_LOCK_OPS(read, rwlock); - BUILD_LOCK_OPS(write, rwlock); -+#endif - - #endif - -@@ -209,6 +212,8 @@ - EXPORT_SYMBOL(_raw_spin_unlock_bh); - #endif - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - #ifndef CONFIG_INLINE_READ_TRYLOCK - int __lockfunc _raw_read_trylock(rwlock_t *lock) - { -@@ -353,6 +358,8 @@ - EXPORT_SYMBOL(_raw_write_unlock_bh); - #endif - -+#endif /* !PREEMPT_RT_FULL */ -+ - #ifdef CONFIG_DEBUG_LOCK_ALLOC - - void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) -diff -Nur linux-4.4.28.orig/kernel/locking/spinlock_debug.c linux-4.4.28/kernel/locking/spinlock_debug.c ---- linux-4.4.28.orig/kernel/locking/spinlock_debug.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/locking/spinlock_debug.c 2016-11-01 21:26:58.772342023 +0100 -@@ -31,6 +31,7 @@ - - EXPORT_SYMBOL(__raw_spin_lock_init); - -+#ifndef CONFIG_PREEMPT_RT_FULL - void __rwlock_init(rwlock_t *lock, const char *name, - struct lock_class_key *key) - { -@@ -48,6 +49,7 @@ - } - - EXPORT_SYMBOL(__rwlock_init); -+#endif - - static void spin_dump(raw_spinlock_t *lock, const char *msg) - { -@@ -159,6 +161,7 @@ - arch_spin_unlock(&lock->raw_lock); - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - static void rwlock_bug(rwlock_t *lock, const char *msg) - { - if (!debug_locks_off()) -@@ -300,3 +303,5 @@ - debug_write_unlock(lock); - arch_write_unlock(&lock->raw_lock); - } -+ -+#endif -diff -Nur linux-4.4.28.orig/kernel/panic.c linux-4.4.28/kernel/panic.c ---- linux-4.4.28.orig/kernel/panic.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/panic.c 2016-11-01 21:26:58.772342023 +0100 -@@ -61,6 +61,37 @@ - cpu_relax(); - } - -+/* -+ * Stop ourselves in NMI context if another CPU has already panicked. Arch code -+ * may override this to prepare for crash dumping, e.g. save regs info. -+ */ -+void __weak nmi_panic_self_stop(struct pt_regs *regs) -+{ -+ panic_smp_self_stop(); -+} -+ -+atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); -+ -+/* -+ * A variant of panic() called from NMI context. We return if we've already -+ * panicked on this CPU. If another CPU already panicked, loop in -+ * nmi_panic_self_stop() which can provide architecture dependent code such -+ * as saving register state for crash dump. -+ */ -+void nmi_panic(struct pt_regs *regs, const char *msg) -+{ -+ int old_cpu, cpu; -+ -+ cpu = raw_smp_processor_id(); -+ old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); -+ -+ if (old_cpu == PANIC_CPU_INVALID) -+ panic("%s", msg); -+ else if (old_cpu != cpu) -+ nmi_panic_self_stop(regs); -+} -+EXPORT_SYMBOL(nmi_panic); -+ - /** - * panic - halt the system - * @fmt: The text string to print -@@ -71,17 +102,17 @@ - */ - void panic(const char *fmt, ...) - { -- static DEFINE_SPINLOCK(panic_lock); - static char buf[1024]; - va_list args; - long i, i_next = 0; - int state = 0; -+ int old_cpu, this_cpu; - - /* - * Disable local interrupts. This will prevent panic_smp_self_stop - * from deadlocking the first cpu that invokes the panic, since - * there is nothing to prevent an interrupt handler (that runs -- * after the panic_lock is acquired) from invoking panic again. -+ * after setting panic_cpu) from invoking panic() again. - */ - local_irq_disable(); - -@@ -94,8 +125,16 @@ - * multiple parallel invocations of panic, all other CPUs either - * stop themself or will wait until they are stopped by the 1st CPU - * with smp_send_stop(). -+ * -+ * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which -+ * comes here, so go ahead. -+ * `old_cpu == this_cpu' means we came from nmi_panic() which sets -+ * panic_cpu to this CPU. In this case, this is also the 1st CPU. - */ -- if (!spin_trylock(&panic_lock)) -+ this_cpu = raw_smp_processor_id(); -+ old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); -+ -+ if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu) - panic_smp_self_stop(); - - console_verbose(); -@@ -400,9 +439,11 @@ - - static int init_oops_id(void) - { -+#ifndef CONFIG_PREEMPT_RT_FULL - if (!oops_id) - get_random_bytes(&oops_id, sizeof(oops_id)); - else -+#endif - oops_id++; - - return 0; -diff -Nur linux-4.4.28.orig/kernel/power/hibernate.c linux-4.4.28/kernel/power/hibernate.c ---- linux-4.4.28.orig/kernel/power/hibernate.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/power/hibernate.c 2016-11-01 21:26:58.772342023 +0100 -@@ -285,6 +285,8 @@ - - local_irq_disable(); - -+ system_state = SYSTEM_SUSPEND; -+ - error = syscore_suspend(); - if (error) { - printk(KERN_ERR "PM: Some system devices failed to power down, " -@@ -314,6 +316,7 @@ - syscore_resume(); - - Enable_irqs: -+ system_state = SYSTEM_RUNNING; - local_irq_enable(); - - Enable_cpus: -@@ -438,6 +441,7 @@ - goto Enable_cpus; - - local_irq_disable(); -+ system_state = SYSTEM_SUSPEND; - - error = syscore_suspend(); - if (error) -@@ -471,6 +475,7 @@ - syscore_resume(); - - Enable_irqs: -+ system_state = SYSTEM_RUNNING; - local_irq_enable(); - - Enable_cpus: -@@ -556,6 +561,7 @@ - goto Enable_cpus; - - local_irq_disable(); -+ system_state = SYSTEM_SUSPEND; - syscore_suspend(); - if (pm_wakeup_pending()) { - error = -EAGAIN; -@@ -568,6 +574,7 @@ - - Power_up: - syscore_resume(); -+ system_state = SYSTEM_RUNNING; - local_irq_enable(); - - Enable_cpus: -@@ -642,6 +649,10 @@ - cpu_relax(); - } - -+#ifndef CONFIG_SUSPEND -+bool pm_in_action; -+#endif -+ - /** - * hibernate - Carry out system hibernation, including saving the image. - */ -@@ -654,6 +665,8 @@ - return -EPERM; - } - -+ pm_in_action = true; -+ - lock_system_sleep(); - /* The snapshot device should not be opened while we're running */ - if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { -@@ -719,6 +732,7 @@ - atomic_inc(&snapshot_device_available); - Unlock: - unlock_system_sleep(); -+ pm_in_action = false; - return error; - } - -diff -Nur linux-4.4.28.orig/kernel/power/suspend.c linux-4.4.28/kernel/power/suspend.c ---- linux-4.4.28.orig/kernel/power/suspend.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/power/suspend.c 2016-11-01 21:26:58.772342023 +0100 -@@ -359,6 +359,8 @@ - arch_suspend_disable_irqs(); - BUG_ON(!irqs_disabled()); - -+ system_state = SYSTEM_SUSPEND; -+ - error = syscore_suspend(); - if (!error) { - *wakeup = pm_wakeup_pending(); -@@ -375,6 +377,8 @@ - syscore_resume(); - } - -+ system_state = SYSTEM_RUNNING; -+ - arch_suspend_enable_irqs(); - BUG_ON(irqs_disabled()); - -@@ -518,6 +522,8 @@ - return error; - } - -+bool pm_in_action; -+ - /** - * pm_suspend - Externally visible function for suspending the system. - * @state: System sleep state to enter. -@@ -532,6 +538,8 @@ - if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) - return -EINVAL; - -+ pm_in_action = true; -+ - error = enter_state(state); - if (error) { - suspend_stats.fail++; -@@ -539,6 +547,7 @@ - } else { - suspend_stats.success++; - } -+ pm_in_action = false; - return error; - } - EXPORT_SYMBOL(pm_suspend); -diff -Nur linux-4.4.28.orig/kernel/printk/printk.c linux-4.4.28/kernel/printk/printk.c ---- linux-4.4.28.orig/kernel/printk/printk.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/printk/printk.c 2016-11-01 21:26:58.776342279 +0100 -@@ -241,6 +241,65 @@ - */ - static DEFINE_RAW_SPINLOCK(logbuf_lock); - -+#ifdef CONFIG_EARLY_PRINTK -+struct console *early_console; -+ -+static void early_vprintk(const char *fmt, va_list ap) -+{ -+ if (early_console) { -+ char buf[512]; -+ int n = vscnprintf(buf, sizeof(buf), fmt, ap); -+ -+ early_console->write(early_console, buf, n); -+ } -+} -+ -+asmlinkage void early_printk(const char *fmt, ...) -+{ -+ va_list ap; -+ -+ va_start(ap, fmt); -+ early_vprintk(fmt, ap); -+ va_end(ap); -+} -+ -+/* -+ * This is independent of any log levels - a global -+ * kill switch that turns off all of printk. -+ * -+ * Used by the NMI watchdog if early-printk is enabled. -+ */ -+static bool __read_mostly printk_killswitch; -+ -+static int __init force_early_printk_setup(char *str) -+{ -+ printk_killswitch = true; -+ return 0; -+} -+early_param("force_early_printk", force_early_printk_setup); -+ -+void printk_kill(void) -+{ -+ printk_killswitch = true; -+} -+ -+#ifdef CONFIG_PRINTK -+static int forced_early_printk(const char *fmt, va_list ap) -+{ -+ if (!printk_killswitch) -+ return 0; -+ early_vprintk(fmt, ap); -+ return 1; -+} -+#endif -+ -+#else -+static inline int forced_early_printk(const char *fmt, va_list ap) -+{ -+ return 0; -+} -+#endif -+ - #ifdef CONFIG_PRINTK - DECLARE_WAIT_QUEUE_HEAD(log_wait); - /* the next printk record to read by syslog(READ) or /proc/kmsg */ -@@ -1203,6 +1262,7 @@ - { - char *text; - int len = 0; -+ int attempts = 0; - - text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); - if (!text) -@@ -1214,7 +1274,14 @@ - u64 seq; - u32 idx; - enum log_flags prev; -- -+ int num_msg; -+try_again: -+ attempts++; -+ if (attempts > 10) { -+ len = -EBUSY; -+ goto out; -+ } -+ num_msg = 0; - if (clear_seq < log_first_seq) { - /* messages are gone, move to first available one */ - clear_seq = log_first_seq; -@@ -1235,6 +1302,14 @@ - prev = msg->flags; - idx = log_next(idx); - seq++; -+ num_msg++; -+ if (num_msg > 5) { -+ num_msg = 0; -+ raw_spin_unlock_irq(&logbuf_lock); -+ raw_spin_lock_irq(&logbuf_lock); -+ if (clear_seq < log_first_seq) -+ goto try_again; -+ } - } - - /* move first record forward until length fits into the buffer */ -@@ -1248,6 +1323,14 @@ - prev = msg->flags; - idx = log_next(idx); - seq++; -+ num_msg++; -+ if (num_msg > 5) { -+ num_msg = 0; -+ raw_spin_unlock_irq(&logbuf_lock); -+ raw_spin_lock_irq(&logbuf_lock); -+ if (clear_seq < log_first_seq) -+ goto try_again; -+ } - } - - /* last message fitting into this dump */ -@@ -1288,6 +1371,7 @@ - clear_seq = log_next_seq; - clear_idx = log_next_idx; - } -+out: - raw_spin_unlock_irq(&logbuf_lock); - - kfree(text); -@@ -1443,6 +1527,12 @@ - if (!console_drivers) - return; - -+ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { -+ if (in_irq() || in_nmi()) -+ return; -+ } -+ -+ migrate_disable(); - for_each_console(con) { - if (exclusive_console && con != exclusive_console) - continue; -@@ -1458,6 +1548,7 @@ - else - con->write(con, text, len); - } -+ migrate_enable(); - } - - /* -@@ -1518,6 +1609,15 @@ - static int console_trylock_for_printk(void) - { - unsigned int cpu = smp_processor_id(); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ int lock = !early_boot_irqs_disabled && (preempt_count() == 0) && -+ !irqs_disabled(); -+#else -+ int lock = 1; -+#endif -+ -+ if (!lock) -+ return 0; - - if (!console_trylock()) - return 0; -@@ -1672,6 +1772,13 @@ - /* cpu currently holding logbuf_lock in this function */ - static unsigned int logbuf_cpu = UINT_MAX; - -+ /* -+ * Fall back to early_printk if a debugging subsystem has -+ * killed printk output -+ */ -+ if (unlikely(forced_early_printk(fmt, args))) -+ return 1; -+ - if (level == LOGLEVEL_SCHED) { - level = LOGLEVEL_DEFAULT; - in_sched = true; -@@ -1813,8 +1920,7 @@ - * console_sem which would prevent anyone from printing to - * console - */ -- preempt_disable(); -- -+ migrate_disable(); - /* - * Try to acquire and then immediately release the console - * semaphore. The release will print out buffers and wake up -@@ -1822,7 +1928,7 @@ - */ - if (console_trylock_for_printk()) - console_unlock(); -- preempt_enable(); -+ migrate_enable(); - lockdep_on(); - } - -@@ -1961,26 +2067,6 @@ - - #endif /* CONFIG_PRINTK */ - --#ifdef CONFIG_EARLY_PRINTK --struct console *early_console; -- --asmlinkage __visible void early_printk(const char *fmt, ...) --{ -- va_list ap; -- char buf[512]; -- int n; -- -- if (!early_console) -- return; -- -- va_start(ap, fmt); -- n = vscnprintf(buf, sizeof(buf), fmt, ap); -- va_end(ap); -- -- early_console->write(early_console, buf, n); --} --#endif -- - static int __add_preferred_console(char *name, int idx, char *options, - char *brl_options) - { -@@ -2202,11 +2288,16 @@ - goto out; - - len = cont_print_text(text, size); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ raw_spin_unlock_irqrestore(&logbuf_lock, flags); -+ call_console_drivers(cont.level, NULL, 0, text, len); -+#else - raw_spin_unlock(&logbuf_lock); - stop_critical_timings(); - call_console_drivers(cont.level, NULL, 0, text, len); - start_critical_timings(); - local_irq_restore(flags); -+#endif - return; - out: - raw_spin_unlock_irqrestore(&logbuf_lock, flags); -@@ -2316,13 +2407,17 @@ - console_idx = log_next(console_idx); - console_seq++; - console_prev = msg->flags; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ raw_spin_unlock_irqrestore(&logbuf_lock, flags); -+ call_console_drivers(level, ext_text, ext_len, text, len); -+#else - raw_spin_unlock(&logbuf_lock); - - stop_critical_timings(); /* don't trace print latency */ - call_console_drivers(level, ext_text, ext_len, text, len); - start_critical_timings(); - local_irq_restore(flags); -- -+#endif - if (do_cond_resched) - cond_resched(); - } -@@ -2374,6 +2469,11 @@ - { - struct console *c; - -+ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { -+ if (in_irq() || in_nmi()) -+ return; -+ } -+ - /* - * console_unblank can no longer be called in interrupt context unless - * oops_in_progress is set to 1.. -diff -Nur linux-4.4.28.orig/kernel/ptrace.c linux-4.4.28/kernel/ptrace.c ---- linux-4.4.28.orig/kernel/ptrace.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/ptrace.c 2016-11-01 21:26:58.776342279 +0100 -@@ -129,7 +129,14 @@ - - spin_lock_irq(&task->sighand->siglock); - if (task_is_traced(task) && !__fatal_signal_pending(task)) { -- task->state = __TASK_TRACED; -+ unsigned long flags; -+ -+ raw_spin_lock_irqsave(&task->pi_lock, flags); -+ if (task->state & __TASK_TRACED) -+ task->state = __TASK_TRACED; -+ else -+ task->saved_state = __TASK_TRACED; -+ raw_spin_unlock_irqrestore(&task->pi_lock, flags); - ret = true; - } - spin_unlock_irq(&task->sighand->siglock); -diff -Nur linux-4.4.28.orig/kernel/rcu/rcutorture.c linux-4.4.28/kernel/rcu/rcutorture.c ---- linux-4.4.28.orig/kernel/rcu/rcutorture.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/rcu/rcutorture.c 2016-11-01 21:26:58.776342279 +0100 -@@ -390,6 +390,7 @@ - .name = "rcu" - }; - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * Definitions for rcu_bh torture testing. - */ -@@ -429,6 +430,12 @@ - .name = "rcu_bh" - }; - -+#else -+static struct rcu_torture_ops rcu_bh_ops = { -+ .ttype = INVALID_RCU_FLAVOR, -+}; -+#endif -+ - /* - * Don't even think about trying any of these in real life!!! - * The names includes "busted", and they really means it! -diff -Nur linux-4.4.28.orig/kernel/rcu/tree.c linux-4.4.28/kernel/rcu/tree.c ---- linux-4.4.28.orig/kernel/rcu/tree.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/rcu/tree.c 2016-11-01 21:26:58.780342543 +0100 -@@ -56,6 +56,11 @@ - #include - #include - #include -+#include -+#include -+#include -+#include -+#include "../time/tick-internal.h" - - #include "tree.h" - #include "rcu.h" -@@ -266,6 +271,19 @@ - } - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static void rcu_preempt_qs(void); -+ -+void rcu_bh_qs(void) -+{ -+ unsigned long flags; -+ -+ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ -+ local_irq_save(flags); -+ rcu_preempt_qs(); -+ local_irq_restore(flags); -+} -+#else - void rcu_bh_qs(void) - { - if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { -@@ -275,6 +293,7 @@ - __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); - } - } -+#endif - - static DEFINE_PER_CPU(int, rcu_sched_qs_mask); - -@@ -435,11 +454,13 @@ - /* - * Return the number of RCU BH batches started thus far for debug & stats. - */ -+#ifndef CONFIG_PREEMPT_RT_FULL - unsigned long rcu_batches_started_bh(void) - { - return rcu_bh_state.gpnum; - } - EXPORT_SYMBOL_GPL(rcu_batches_started_bh); -+#endif - - /* - * Return the number of RCU batches completed thus far for debug & stats. -@@ -459,6 +480,7 @@ - } - EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * Return the number of RCU BH batches completed thus far for debug & stats. - */ -@@ -486,6 +508,13 @@ - } - EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); - -+#else -+void rcu_force_quiescent_state(void) -+{ -+} -+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); -+#endif -+ - /* - * Force a quiescent state for RCU-sched. - */ -@@ -536,9 +565,11 @@ - case RCU_FLAVOR: - rsp = rcu_state_p; - break; -+#ifndef CONFIG_PREEMPT_RT_FULL - case RCU_BH_FLAVOR: - rsp = &rcu_bh_state; - break; -+#endif - case RCU_SCHED_FLAVOR: - rsp = &rcu_sched_state; - break; -@@ -1590,7 +1621,6 @@ - int needmore; - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - -- rcu_nocb_gp_cleanup(rsp, rnp); - rnp->need_future_gp[c & 0x1] = 0; - needmore = rnp->need_future_gp[(c + 1) & 0x1]; - trace_rcu_future_gp(rnp, rdp, c, -@@ -1611,7 +1641,7 @@ - !READ_ONCE(rsp->gp_flags) || - !rsp->gp_kthread) - return; -- wake_up(&rsp->gp_wq); -+ swake_up(&rsp->gp_wq); - } - - /* -@@ -1991,6 +2021,7 @@ - int nocb = 0; - struct rcu_data *rdp; - struct rcu_node *rnp = rcu_get_root(rsp); -+ struct swait_queue_head *sq; - - WRITE_ONCE(rsp->gp_activity, jiffies); - raw_spin_lock_irq(&rnp->lock); -@@ -2029,7 +2060,9 @@ - needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; - /* smp_mb() provided by prior unlock-lock pair. */ - nocb += rcu_future_gp_cleanup(rsp, rnp); -+ sq = rcu_nocb_gp_get(rnp); - raw_spin_unlock_irq(&rnp->lock); -+ rcu_nocb_gp_cleanup(sq); - cond_resched_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - rcu_gp_slow(rsp, gp_cleanup_delay); -@@ -2076,7 +2109,7 @@ - READ_ONCE(rsp->gpnum), - TPS("reqwait")); - rsp->gp_state = RCU_GP_WAIT_GPS; -- wait_event_interruptible(rsp->gp_wq, -+ swait_event_interruptible(rsp->gp_wq, - READ_ONCE(rsp->gp_flags) & - RCU_GP_FLAG_INIT); - rsp->gp_state = RCU_GP_DONE_GPS; -@@ -2106,7 +2139,7 @@ - READ_ONCE(rsp->gpnum), - TPS("fqswait")); - rsp->gp_state = RCU_GP_WAIT_FQS; -- ret = wait_event_interruptible_timeout(rsp->gp_wq, -+ ret = swait_event_interruptible_timeout(rsp->gp_wq, - rcu_gp_fqs_check_wake(rsp, &gf), j); - rsp->gp_state = RCU_GP_DOING_FQS; - /* Locking provides needed memory barriers. */ -@@ -2230,7 +2263,7 @@ - WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); -- rcu_gp_kthread_wake(rsp); -+ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ - } - - /* -@@ -2891,7 +2924,7 @@ - } - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore(&rnp_old->lock, flags); -- rcu_gp_kthread_wake(rsp); -+ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ - } - - /* -@@ -2934,18 +2967,17 @@ - /* - * Do RCU core processing for the current CPU. - */ --static void rcu_process_callbacks(struct softirq_action *unused) -+static void rcu_process_callbacks(void) - { - struct rcu_state *rsp; - - if (cpu_is_offline(smp_processor_id())) - return; -- trace_rcu_utilization(TPS("Start RCU core")); - for_each_rcu_flavor(rsp) - __rcu_process_callbacks(rsp); -- trace_rcu_utilization(TPS("End RCU core")); - } - -+static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); - /* - * Schedule RCU callback invocation. If the specified type of RCU - * does not support RCU priority boosting, just do a direct call, -@@ -2957,18 +2989,105 @@ - { - if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) - return; -- if (likely(!rsp->boost)) { -- rcu_do_batch(rsp, rdp); -+ rcu_do_batch(rsp, rdp); -+} -+ -+static void rcu_wake_cond(struct task_struct *t, int status) -+{ -+ /* -+ * If the thread is yielding, only wake it when this -+ * is invoked from idle -+ */ -+ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) -+ wake_up_process(t); -+} -+ -+/* -+ * Wake up this CPU's rcuc kthread to do RCU core processing. -+ */ -+static void invoke_rcu_core(void) -+{ -+ unsigned long flags; -+ struct task_struct *t; -+ -+ if (!cpu_online(smp_processor_id())) - return; -+ local_irq_save(flags); -+ __this_cpu_write(rcu_cpu_has_work, 1); -+ t = __this_cpu_read(rcu_cpu_kthread_task); -+ if (t != NULL && current != t) -+ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); -+ local_irq_restore(flags); -+} -+ -+static void rcu_cpu_kthread_park(unsigned int cpu) -+{ -+ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; -+} -+ -+static int rcu_cpu_kthread_should_run(unsigned int cpu) -+{ -+ return __this_cpu_read(rcu_cpu_has_work); -+} -+ -+/* -+ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the -+ * RCU softirq used in flavors and configurations of RCU that do not -+ * support RCU priority boosting. -+ */ -+static void rcu_cpu_kthread(unsigned int cpu) -+{ -+ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); -+ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); -+ int spincnt; -+ -+ for (spincnt = 0; spincnt < 10; spincnt++) { -+ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); -+ local_bh_disable(); -+ *statusp = RCU_KTHREAD_RUNNING; -+ this_cpu_inc(rcu_cpu_kthread_loops); -+ local_irq_disable(); -+ work = *workp; -+ *workp = 0; -+ local_irq_enable(); -+ if (work) -+ rcu_process_callbacks(); -+ local_bh_enable(); -+ if (*workp == 0) { -+ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); -+ *statusp = RCU_KTHREAD_WAITING; -+ return; -+ } - } -- invoke_rcu_callbacks_kthread(); -+ *statusp = RCU_KTHREAD_YIELDING; -+ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); -+ schedule_timeout_interruptible(2); -+ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); -+ *statusp = RCU_KTHREAD_WAITING; - } - --static void invoke_rcu_core(void) -+static struct smp_hotplug_thread rcu_cpu_thread_spec = { -+ .store = &rcu_cpu_kthread_task, -+ .thread_should_run = rcu_cpu_kthread_should_run, -+ .thread_fn = rcu_cpu_kthread, -+ .thread_comm = "rcuc/%u", -+ .setup = rcu_cpu_kthread_setup, -+ .park = rcu_cpu_kthread_park, -+}; -+ -+/* -+ * Spawn per-CPU RCU core processing kthreads. -+ */ -+static int __init rcu_spawn_core_kthreads(void) - { -- if (cpu_online(smp_processor_id())) -- raise_softirq(RCU_SOFTIRQ); -+ int cpu; -+ -+ for_each_possible_cpu(cpu) -+ per_cpu(rcu_cpu_has_work, cpu) = 0; -+ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); -+ return 0; - } -+early_initcall(rcu_spawn_core_kthreads); - - /* - * Handle any core-RCU processing required by a call_rcu() invocation. -@@ -3114,6 +3233,7 @@ - } - EXPORT_SYMBOL_GPL(call_rcu_sched); - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * Queue an RCU callback for invocation after a quicker grace period. - */ -@@ -3122,6 +3242,7 @@ - __call_rcu(head, func, &rcu_bh_state, -1, 0); - } - EXPORT_SYMBOL_GPL(call_rcu_bh); -+#endif - - /* - * Queue an RCU callback for lazy invocation after a grace period. -@@ -3213,6 +3334,7 @@ - } - EXPORT_SYMBOL_GPL(synchronize_sched); - -+#ifndef CONFIG_PREEMPT_RT_FULL - /** - * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. - * -@@ -3239,6 +3361,7 @@ - wait_rcu_gp(call_rcu_bh); - } - EXPORT_SYMBOL_GPL(synchronize_rcu_bh); -+#endif - - /** - * get_state_synchronize_rcu - Snapshot current RCU state -@@ -3524,7 +3647,7 @@ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (wake) { - smp_mb(); /* EGP done before wake_up(). */ -- wake_up(&rsp->expedited_wq); -+ swake_up(&rsp->expedited_wq); - } - break; - } -@@ -3781,7 +3904,7 @@ - jiffies_start = jiffies; - - for (;;) { -- ret = wait_event_interruptible_timeout( -+ ret = swait_event_timeout( - rsp->expedited_wq, - sync_rcu_preempt_exp_done(rnp_root), - jiffies_stall); -@@ -3789,7 +3912,7 @@ - return; - if (ret < 0) { - /* Hit a signal, disable CPU stall warnings. */ -- wait_event(rsp->expedited_wq, -+ swait_event(rsp->expedited_wq, - sync_rcu_preempt_exp_done(rnp_root)); - return; - } -@@ -4101,6 +4224,7 @@ - mutex_unlock(&rsp->barrier_mutex); - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - /** - * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. - */ -@@ -4109,6 +4233,7 @@ - _rcu_barrier(&rcu_bh_state); - } - EXPORT_SYMBOL_GPL(rcu_barrier_bh); -+#endif - - /** - * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. -@@ -4455,8 +4580,8 @@ - } - } - -- init_waitqueue_head(&rsp->gp_wq); -- init_waitqueue_head(&rsp->expedited_wq); -+ init_swait_queue_head(&rsp->gp_wq); -+ init_swait_queue_head(&rsp->expedited_wq); - rnp = rsp->level[rcu_num_lvls - 1]; - for_each_possible_cpu(i) { - while (i > rnp->grphi) -@@ -4576,12 +4701,13 @@ - - rcu_bootup_announce(); - rcu_init_geometry(); -+#ifndef CONFIG_PREEMPT_RT_FULL - rcu_init_one(&rcu_bh_state, &rcu_bh_data); -+#endif - rcu_init_one(&rcu_sched_state, &rcu_sched_data); - if (dump_tree) - rcu_dump_rcu_node_tree(&rcu_sched_state); - __rcu_init_preempt(); -- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); - - /* - * We don't need protection against CPU-hotplug here because -diff -Nur linux-4.4.28.orig/kernel/rcu/tree.h linux-4.4.28/kernel/rcu/tree.h ---- linux-4.4.28.orig/kernel/rcu/tree.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/rcu/tree.h 2016-11-01 21:26:58.780342543 +0100 -@@ -27,6 +27,7 @@ - #include - #include - #include -+#include - #include - - /* -@@ -241,7 +242,7 @@ - /* Refused to boost: not sure why, though. */ - /* This can happen due to race conditions. */ - #ifdef CONFIG_RCU_NOCB_CPU -- wait_queue_head_t nocb_gp_wq[2]; -+ struct swait_queue_head nocb_gp_wq[2]; - /* Place for rcu_nocb_kthread() to wait GP. */ - #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - int need_future_gp[2]; -@@ -393,7 +394,7 @@ - atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ - struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ - struct rcu_head **nocb_follower_tail; -- wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ -+ struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ - struct task_struct *nocb_kthread; - int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ - -@@ -472,7 +473,7 @@ - unsigned long gpnum; /* Current gp number. */ - unsigned long completed; /* # of last completed gp. */ - struct task_struct *gp_kthread; /* Task for grace periods. */ -- wait_queue_head_t gp_wq; /* Where GP task waits. */ -+ struct swait_queue_head gp_wq; /* Where GP task waits. */ - short gp_flags; /* Commands for GP task. */ - short gp_state; /* GP kthread sleep state. */ - -@@ -504,7 +505,7 @@ - atomic_long_t expedited_workdone3; /* # done by others #3. */ - atomic_long_t expedited_normal; /* # fallbacks to normal. */ - atomic_t expedited_need_qs; /* # CPUs left to check in. */ -- wait_queue_head_t expedited_wq; /* Wait for check-ins. */ -+ struct swait_queue_head expedited_wq; /* Wait for check-ins. */ - int ncpus_snap; /* # CPUs seen last time. */ - - unsigned long jiffies_force_qs; /* Time at which to invoke */ -@@ -556,18 +557,18 @@ - */ - extern struct rcu_state rcu_sched_state; - -+#ifndef CONFIG_PREEMPT_RT_FULL - extern struct rcu_state rcu_bh_state; -+#endif - - #ifdef CONFIG_PREEMPT_RCU - extern struct rcu_state rcu_preempt_state; - #endif /* #ifdef CONFIG_PREEMPT_RCU */ - --#ifdef CONFIG_RCU_BOOST - DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); - DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); - DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); - DECLARE_PER_CPU(char, rcu_cpu_has_work); --#endif /* #ifdef CONFIG_RCU_BOOST */ - - #ifndef RCU_TREE_NONCORE - -@@ -587,10 +588,9 @@ - static void __init __rcu_init_preempt(void); - static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); - static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); --static void invoke_rcu_callbacks_kthread(void); - static bool rcu_is_callbacks_kthread(void); -+static void rcu_cpu_kthread_setup(unsigned int cpu); - #ifdef CONFIG_RCU_BOOST --static void rcu_preempt_do_callbacks(void); - static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp); - #endif /* #ifdef CONFIG_RCU_BOOST */ -@@ -607,7 +607,8 @@ - static void increment_cpu_stall_ticks(void); - static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); - static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); --static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); -+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); -+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); - static void rcu_init_one_nocb(struct rcu_node *rnp); - static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, - bool lazy, unsigned long flags); -diff -Nur linux-4.4.28.orig/kernel/rcu/tree_plugin.h linux-4.4.28/kernel/rcu/tree_plugin.h ---- linux-4.4.28.orig/kernel/rcu/tree_plugin.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/rcu/tree_plugin.h 2016-11-01 21:26:58.780342543 +0100 -@@ -24,25 +24,10 @@ - * Paul E. McKenney - */ - --#include --#include --#include --#include --#include "../time/tick-internal.h" -- - #ifdef CONFIG_RCU_BOOST - - #include "../locking/rtmutex_common.h" - --/* -- * Control variables for per-CPU and per-rcu_node kthreads. These -- * handle all flavors of RCU. -- */ --static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); --DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); --DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); --DEFINE_PER_CPU(char, rcu_cpu_has_work); -- - #else /* #ifdef CONFIG_RCU_BOOST */ - - /* -@@ -55,6 +40,14 @@ - - #endif /* #else #ifdef CONFIG_RCU_BOOST */ - -+/* -+ * Control variables for per-CPU and per-rcu_node kthreads. These -+ * handle all flavors of RCU. -+ */ -+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); -+DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); -+DEFINE_PER_CPU(char, rcu_cpu_has_work); -+ - #ifdef CONFIG_RCU_NOCB_CPU - static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ - static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ -@@ -432,7 +425,7 @@ - } - - /* Hardware IRQ handlers cannot block, complain if they get here. */ -- if (in_irq() || in_serving_softirq()) { -+ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { - lockdep_rcu_suspicious(__FILE__, __LINE__, - "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); - pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", -@@ -645,15 +638,6 @@ - t->rcu_read_unlock_special.b.need_qs = true; - } - --#ifdef CONFIG_RCU_BOOST -- --static void rcu_preempt_do_callbacks(void) --{ -- rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p)); --} -- --#endif /* #ifdef CONFIG_RCU_BOOST */ -- - /* - * Queue a preemptible-RCU callback for invocation after a grace period. - */ -@@ -930,6 +914,19 @@ - - #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - -+/* -+ * If boosting, set rcuc kthreads to realtime priority. -+ */ -+static void rcu_cpu_kthread_setup(unsigned int cpu) -+{ -+#ifdef CONFIG_RCU_BOOST -+ struct sched_param sp; -+ -+ sp.sched_priority = kthread_prio; -+ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); -+#endif /* #ifdef CONFIG_RCU_BOOST */ -+} -+ - #ifdef CONFIG_RCU_BOOST - - #include "../locking/rtmutex_common.h" -@@ -961,16 +958,6 @@ - - #endif /* #else #ifdef CONFIG_RCU_TRACE */ - --static void rcu_wake_cond(struct task_struct *t, int status) --{ -- /* -- * If the thread is yielding, only wake it when this -- * is invoked from idle -- */ -- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) -- wake_up_process(t); --} -- - /* - * Carry out RCU priority boosting on the task indicated by ->exp_tasks - * or ->boost_tasks, advancing the pointer to the next task in the -@@ -1115,23 +1102,6 @@ - } - - /* -- * Wake up the per-CPU kthread to invoke RCU callbacks. -- */ --static void invoke_rcu_callbacks_kthread(void) --{ -- unsigned long flags; -- -- local_irq_save(flags); -- __this_cpu_write(rcu_cpu_has_work, 1); -- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && -- current != __this_cpu_read(rcu_cpu_kthread_task)) { -- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), -- __this_cpu_read(rcu_cpu_kthread_status)); -- } -- local_irq_restore(flags); --} -- --/* - * Is the current CPU running the RCU-callbacks kthread? - * Caller must have preemption disabled. - */ -@@ -1186,67 +1156,6 @@ - return 0; - } - --static void rcu_kthread_do_work(void) --{ -- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); -- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); -- rcu_preempt_do_callbacks(); --} -- --static void rcu_cpu_kthread_setup(unsigned int cpu) --{ -- struct sched_param sp; -- -- sp.sched_priority = kthread_prio; -- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); --} -- --static void rcu_cpu_kthread_park(unsigned int cpu) --{ -- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; --} -- --static int rcu_cpu_kthread_should_run(unsigned int cpu) --{ -- return __this_cpu_read(rcu_cpu_has_work); --} -- --/* -- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the -- * RCU softirq used in flavors and configurations of RCU that do not -- * support RCU priority boosting. -- */ --static void rcu_cpu_kthread(unsigned int cpu) --{ -- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); -- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); -- int spincnt; -- -- for (spincnt = 0; spincnt < 10; spincnt++) { -- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); -- local_bh_disable(); -- *statusp = RCU_KTHREAD_RUNNING; -- this_cpu_inc(rcu_cpu_kthread_loops); -- local_irq_disable(); -- work = *workp; -- *workp = 0; -- local_irq_enable(); -- if (work) -- rcu_kthread_do_work(); -- local_bh_enable(); -- if (*workp == 0) { -- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); -- *statusp = RCU_KTHREAD_WAITING; -- return; -- } -- } -- *statusp = RCU_KTHREAD_YIELDING; -- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); -- schedule_timeout_interruptible(2); -- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); -- *statusp = RCU_KTHREAD_WAITING; --} -- - /* - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still -@@ -1276,26 +1185,12 @@ - free_cpumask_var(cm); - } - --static struct smp_hotplug_thread rcu_cpu_thread_spec = { -- .store = &rcu_cpu_kthread_task, -- .thread_should_run = rcu_cpu_kthread_should_run, -- .thread_fn = rcu_cpu_kthread, -- .thread_comm = "rcuc/%u", -- .setup = rcu_cpu_kthread_setup, -- .park = rcu_cpu_kthread_park, --}; -- - /* - * Spawn boost kthreads -- called as soon as the scheduler is running. - */ - static void __init rcu_spawn_boost_kthreads(void) - { - struct rcu_node *rnp; -- int cpu; -- -- for_each_possible_cpu(cpu) -- per_cpu(rcu_cpu_has_work, cpu) = 0; -- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); - rcu_for_each_leaf_node(rcu_state_p, rnp) - (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); - } -@@ -1318,11 +1213,6 @@ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - } - --static void invoke_rcu_callbacks_kthread(void) --{ -- WARN_ON_ONCE(1); --} -- - static bool rcu_is_callbacks_kthread(void) - { - return false; -@@ -1346,7 +1236,7 @@ - - #endif /* #else #ifdef CONFIG_RCU_BOOST */ - --#if !defined(CONFIG_RCU_FAST_NO_HZ) -+#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) - - /* - * Check to see if any future RCU-related work will need to be done -@@ -1363,7 +1253,9 @@ - return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) - ? 0 : rcu_cpu_has_callbacks(NULL); - } -+#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ - -+#if !defined(CONFIG_RCU_FAST_NO_HZ) - /* - * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up - * after it. -@@ -1459,6 +1351,8 @@ - return cbs_ready; - } - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - /* - * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready - * to invoke. If the CPU has callbacks, try to advance them. Tell the -@@ -1504,6 +1398,7 @@ - *nextevt = basemono + dj * TICK_NSEC; - return 0; - } -+#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ - - /* - * Prepare a CPU for idle from an RCU perspective. The first major task -@@ -1822,9 +1717,9 @@ - * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended - * grace period. - */ --static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) -+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) - { -- wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); -+ swake_up_all(sq); - } - - /* -@@ -1840,10 +1735,15 @@ - rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; - } - -+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) -+{ -+ return &rnp->nocb_gp_wq[rnp->completed & 0x1]; -+} -+ - static void rcu_init_one_nocb(struct rcu_node *rnp) - { -- init_waitqueue_head(&rnp->nocb_gp_wq[0]); -- init_waitqueue_head(&rnp->nocb_gp_wq[1]); -+ init_swait_queue_head(&rnp->nocb_gp_wq[0]); -+ init_swait_queue_head(&rnp->nocb_gp_wq[1]); - } - - #ifndef CONFIG_RCU_NOCB_CPU_ALL -@@ -1868,7 +1768,7 @@ - if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { - /* Prior smp_mb__after_atomic() orders against prior enqueue. */ - WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); -- wake_up(&rdp_leader->nocb_wq); -+ swake_up(&rdp_leader->nocb_wq); - } - } - -@@ -2081,7 +1981,7 @@ - */ - trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); - for (;;) { -- wait_event_interruptible( -+ swait_event_interruptible( - rnp->nocb_gp_wq[c & 0x1], - (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); - if (likely(d)) -@@ -2109,7 +2009,7 @@ - /* Wait for callbacks to appear. */ - if (!rcu_nocb_poll) { - trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); -- wait_event_interruptible(my_rdp->nocb_wq, -+ swait_event_interruptible(my_rdp->nocb_wq, - !READ_ONCE(my_rdp->nocb_leader_sleep)); - /* Memory barrier handled by smp_mb() calls below and repoll. */ - } else if (firsttime) { -@@ -2184,7 +2084,7 @@ - * List was empty, wake up the follower. - * Memory barriers supplied by atomic_long_add(). - */ -- wake_up(&rdp->nocb_wq); -+ swake_up(&rdp->nocb_wq); - } - } - -@@ -2205,7 +2105,7 @@ - if (!rcu_nocb_poll) { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, - "FollowerSleep"); -- wait_event_interruptible(rdp->nocb_wq, -+ swait_event_interruptible(rdp->nocb_wq, - READ_ONCE(rdp->nocb_follower_head)); - } else if (firsttime) { - /* Don't drown trace log with "Poll"! */ -@@ -2364,7 +2264,7 @@ - static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) - { - rdp->nocb_tail = &rdp->nocb_head; -- init_waitqueue_head(&rdp->nocb_wq); -+ init_swait_queue_head(&rdp->nocb_wq); - rdp->nocb_follower_tail = &rdp->nocb_follower_head; - } - -@@ -2514,7 +2414,7 @@ - return false; - } - --static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) -+static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) - { - } - -@@ -2522,6 +2422,11 @@ - { - } - -+static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) -+{ -+ return NULL; -+} -+ - static void rcu_init_one_nocb(struct rcu_node *rnp) - { - } -diff -Nur linux-4.4.28.orig/kernel/rcu/update.c linux-4.4.28/kernel/rcu/update.c ---- linux-4.4.28.orig/kernel/rcu/update.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/rcu/update.c 2016-11-01 21:26:58.780342543 +0100 -@@ -276,6 +276,7 @@ - } - EXPORT_SYMBOL_GPL(rcu_read_lock_held); - -+#ifndef CONFIG_PREEMPT_RT_FULL - /** - * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? - * -@@ -302,6 +303,7 @@ - return in_softirq() || irqs_disabled(); - } - EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); -+#endif - - #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - -diff -Nur linux-4.4.28.orig/kernel/relay.c linux-4.4.28/kernel/relay.c ---- linux-4.4.28.orig/kernel/relay.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/relay.c 2016-11-01 21:26:58.780342543 +0100 -@@ -336,6 +336,10 @@ - { - struct rchan_buf *buf = (struct rchan_buf *)data; - wake_up_interruptible(&buf->read_wait); -+ /* -+ * Stupid polling for now: -+ */ -+ mod_timer(&buf->timer, jiffies + 1); - } - - /** -@@ -353,6 +357,7 @@ - init_waitqueue_head(&buf->read_wait); - kref_init(&buf->kref); - setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); -+ mod_timer(&buf->timer, jiffies + 1); - } else - del_timer_sync(&buf->timer); - -@@ -736,15 +741,6 @@ - else - buf->early_bytes += buf->chan->subbuf_size - - buf->padding[old_subbuf]; -- smp_mb(); -- if (waitqueue_active(&buf->read_wait)) -- /* -- * Calling wake_up_interruptible() from here -- * will deadlock if we happen to be logging -- * from the scheduler (trying to re-grab -- * rq->lock), so defer it. -- */ -- mod_timer(&buf->timer, jiffies + 1); - } - - old = buf->data; -diff -Nur linux-4.4.28.orig/kernel/sched/completion.c linux-4.4.28/kernel/sched/completion.c ---- linux-4.4.28.orig/kernel/sched/completion.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/completion.c 2016-11-01 21:26:58.780342543 +0100 -@@ -30,10 +30,10 @@ - { - unsigned long flags; - -- spin_lock_irqsave(&x->wait.lock, flags); -+ raw_spin_lock_irqsave(&x->wait.lock, flags); - x->done++; -- __wake_up_locked(&x->wait, TASK_NORMAL, 1); -- spin_unlock_irqrestore(&x->wait.lock, flags); -+ swake_up_locked(&x->wait); -+ raw_spin_unlock_irqrestore(&x->wait.lock, flags); - } - EXPORT_SYMBOL(complete); - -@@ -50,10 +50,10 @@ - { - unsigned long flags; - -- spin_lock_irqsave(&x->wait.lock, flags); -+ raw_spin_lock_irqsave(&x->wait.lock, flags); - x->done += UINT_MAX/2; -- __wake_up_locked(&x->wait, TASK_NORMAL, 0); -- spin_unlock_irqrestore(&x->wait.lock, flags); -+ swake_up_all_locked(&x->wait); -+ raw_spin_unlock_irqrestore(&x->wait.lock, flags); - } - EXPORT_SYMBOL(complete_all); - -@@ -62,20 +62,20 @@ - long (*action)(long), long timeout, int state) - { - if (!x->done) { -- DECLARE_WAITQUEUE(wait, current); -+ DECLARE_SWAITQUEUE(wait); - -- __add_wait_queue_tail_exclusive(&x->wait, &wait); -+ __prepare_to_swait(&x->wait, &wait); - do { - if (signal_pending_state(state, current)) { - timeout = -ERESTARTSYS; - break; - } - __set_current_state(state); -- spin_unlock_irq(&x->wait.lock); -+ raw_spin_unlock_irq(&x->wait.lock); - timeout = action(timeout); -- spin_lock_irq(&x->wait.lock); -+ raw_spin_lock_irq(&x->wait.lock); - } while (!x->done && timeout); -- __remove_wait_queue(&x->wait, &wait); -+ __finish_swait(&x->wait, &wait); - if (!x->done) - return timeout; - } -@@ -89,9 +89,9 @@ - { - might_sleep(); - -- spin_lock_irq(&x->wait.lock); -+ raw_spin_lock_irq(&x->wait.lock); - timeout = do_wait_for_common(x, action, timeout, state); -- spin_unlock_irq(&x->wait.lock); -+ raw_spin_unlock_irq(&x->wait.lock); - return timeout; - } - -@@ -277,12 +277,12 @@ - if (!READ_ONCE(x->done)) - return 0; - -- spin_lock_irqsave(&x->wait.lock, flags); -+ raw_spin_lock_irqsave(&x->wait.lock, flags); - if (!x->done) - ret = 0; - else - x->done--; -- spin_unlock_irqrestore(&x->wait.lock, flags); -+ raw_spin_unlock_irqrestore(&x->wait.lock, flags); - return ret; - } - EXPORT_SYMBOL(try_wait_for_completion); -@@ -311,7 +311,7 @@ - * after it's acquired the lock. - */ - smp_rmb(); -- spin_unlock_wait(&x->wait.lock); -+ raw_spin_unlock_wait(&x->wait.lock); - return true; - } - EXPORT_SYMBOL(completion_done); -diff -Nur linux-4.4.28.orig/kernel/sched/core.c linux-4.4.28/kernel/sched/core.c ---- linux-4.4.28.orig/kernel/sched/core.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/core.c 2016-11-01 21:26:58.784342796 +0100 -@@ -260,7 +260,11 @@ - * Number of tasks to iterate in a single balance run. - * Limited because this is done with IRQs disabled. - */ -+#ifndef CONFIG_PREEMPT_RT_FULL - const_debug unsigned int sysctl_sched_nr_migrate = 32; -+#else -+const_debug unsigned int sysctl_sched_nr_migrate = 8; -+#endif - - /* - * period over which we average the RT time consumption, measured -@@ -438,6 +442,7 @@ - - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - rq->hrtick_timer.function = hrtick; -+ rq->hrtick_timer.irqsafe = 1; - } - #else /* CONFIG_SCHED_HRTICK */ - static inline void hrtick_clear(struct rq *rq) -@@ -542,7 +547,7 @@ - head->lastp = &node->next; - } - --void wake_up_q(struct wake_q_head *head) -+void __wake_up_q(struct wake_q_head *head, bool sleeper) - { - struct wake_q_node *node = head->first; - -@@ -559,7 +564,10 @@ - * wake_up_process() implies a wmb() to pair with the queueing - * in wake_q_add() so as not to miss wakeups. - */ -- wake_up_process(task); -+ if (sleeper) -+ wake_up_lock_sleeper(task); -+ else -+ wake_up_process(task); - put_task_struct(task); - } - } -@@ -595,6 +603,38 @@ - trace_sched_wake_idle_without_ipi(cpu); - } - -+#ifdef CONFIG_PREEMPT_LAZY -+void resched_curr_lazy(struct rq *rq) -+{ -+ struct task_struct *curr = rq->curr; -+ int cpu; -+ -+ if (!sched_feat(PREEMPT_LAZY)) { -+ resched_curr(rq); -+ return; -+ } -+ -+ lockdep_assert_held(&rq->lock); -+ -+ if (test_tsk_need_resched(curr)) -+ return; -+ -+ if (test_tsk_need_resched_lazy(curr)) -+ return; -+ -+ set_tsk_need_resched_lazy(curr); -+ -+ cpu = cpu_of(rq); -+ if (cpu == smp_processor_id()) -+ return; -+ -+ /* NEED_RESCHED_LAZY must be visible before we test polling */ -+ smp_mb(); -+ if (!tsk_is_polling(curr)) -+ smp_send_reschedule(cpu); -+} -+#endif -+ - void resched_cpu(int cpu) - { - struct rq *rq = cpu_rq(cpu); -@@ -618,11 +658,14 @@ - */ - int get_nohz_timer_target(void) - { -- int i, cpu = smp_processor_id(); -+ int i, cpu; - struct sched_domain *sd; - -+ preempt_disable_rt(); -+ cpu = smp_processor_id(); -+ - if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) -- return cpu; -+ goto preempt_en_rt; - - rcu_read_lock(); - for_each_domain(cpu, sd) { -@@ -641,6 +684,8 @@ - cpu = housekeeping_any_cpu(); - unlock: - rcu_read_unlock(); -+preempt_en_rt: -+ preempt_enable_rt(); - return cpu; - } - /* -@@ -1174,6 +1219,11 @@ - - lockdep_assert_held(&p->pi_lock); - -+ if (__migrate_disabled(p)) { -+ cpumask_copy(&p->cpus_allowed, new_mask); -+ return; -+ } -+ - queued = task_on_rq_queued(p); - running = task_current(rq, p); - -@@ -1196,6 +1246,84 @@ - enqueue_task(rq, p, ENQUEUE_RESTORE); - } - -+static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); -+static DEFINE_MUTEX(sched_down_mutex); -+static cpumask_t sched_down_cpumask; -+ -+void tell_sched_cpu_down_begin(int cpu) -+{ -+ mutex_lock(&sched_down_mutex); -+ cpumask_set_cpu(cpu, &sched_down_cpumask); -+ mutex_unlock(&sched_down_mutex); -+} -+ -+void tell_sched_cpu_down_done(int cpu) -+{ -+ mutex_lock(&sched_down_mutex); -+ cpumask_clear_cpu(cpu, &sched_down_cpumask); -+ mutex_unlock(&sched_down_mutex); -+} -+ -+/** -+ * migrate_me - try to move the current task off this cpu -+ * -+ * Used by the pin_current_cpu() code to try to get tasks -+ * to move off the current CPU as it is going down. -+ * It will only move the task if the task isn't pinned to -+ * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) -+ * and the task has to be in a RUNNING state. Otherwise the -+ * movement of the task will wake it up (change its state -+ * to running) when the task did not expect it. -+ * -+ * Returns 1 if it succeeded in moving the current task -+ * 0 otherwise. -+ */ -+int migrate_me(void) -+{ -+ struct task_struct *p = current; -+ struct migration_arg arg; -+ struct cpumask *cpumask; -+ struct cpumask *mask; -+ unsigned long flags; -+ unsigned int dest_cpu; -+ struct rq *rq; -+ -+ /* -+ * We can not migrate tasks bounded to a CPU or tasks not -+ * running. The movement of the task will wake it up. -+ */ -+ if (p->flags & PF_NO_SETAFFINITY || p->state) -+ return 0; -+ -+ mutex_lock(&sched_down_mutex); -+ rq = task_rq_lock(p, &flags); -+ -+ cpumask = this_cpu_ptr(&sched_cpumasks); -+ mask = &p->cpus_allowed; -+ -+ cpumask_andnot(cpumask, mask, &sched_down_cpumask); -+ -+ if (!cpumask_weight(cpumask)) { -+ /* It's only on this CPU? */ -+ task_rq_unlock(rq, p, &flags); -+ mutex_unlock(&sched_down_mutex); -+ return 0; -+ } -+ -+ dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); -+ -+ arg.task = p; -+ arg.dest_cpu = dest_cpu; -+ -+ task_rq_unlock(rq, p, &flags); -+ -+ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); -+ tlb_migrate_finish(p->mm); -+ mutex_unlock(&sched_down_mutex); -+ -+ return 1; -+} -+ - /* - * Change a given task's CPU affinity. Migrate the thread to a - * proper CPU and schedule it away if the CPU it's executing on -@@ -1235,7 +1363,7 @@ - do_set_cpus_allowed(p, new_mask); - - /* Can the task run on the task's current CPU? If so, we're done */ -- if (cpumask_test_cpu(task_cpu(p), new_mask)) -+ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) - goto out; - - dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); -@@ -1411,6 +1539,18 @@ - return ret; - } - -+static bool check_task_state(struct task_struct *p, long match_state) -+{ -+ bool match = false; -+ -+ raw_spin_lock_irq(&p->pi_lock); -+ if (p->state == match_state || p->saved_state == match_state) -+ match = true; -+ raw_spin_unlock_irq(&p->pi_lock); -+ -+ return match; -+} -+ - /* - * wait_task_inactive - wait for a thread to unschedule. - * -@@ -1455,7 +1595,7 @@ - * is actually now running somewhere else! - */ - while (task_running(rq, p)) { -- if (match_state && unlikely(p->state != match_state)) -+ if (match_state && !check_task_state(p, match_state)) - return 0; - cpu_relax(); - } -@@ -1470,7 +1610,8 @@ - running = task_running(rq, p); - queued = task_on_rq_queued(p); - ncsw = 0; -- if (!match_state || p->state == match_state) -+ if (!match_state || p->state == match_state || -+ p->saved_state == match_state) - ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, p, &flags); - -@@ -1627,7 +1768,7 @@ - { - lockdep_assert_held(&p->pi_lock); - -- if (p->nr_cpus_allowed > 1) -+ if (tsk_nr_cpus_allowed(p) > 1) - cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); - - /* -@@ -1707,10 +1848,6 @@ - { - activate_task(rq, p, en_flags); - p->on_rq = TASK_ON_RQ_QUEUED; -- -- /* if a worker is waking up, notify workqueue */ -- if (p->flags & PF_WQ_WORKER) -- wq_worker_waking_up(p, cpu_of(rq)); - } - - /* -@@ -1937,8 +2074,27 @@ - */ - smp_mb__before_spinlock(); - raw_spin_lock_irqsave(&p->pi_lock, flags); -- if (!(p->state & state)) -+ if (!(p->state & state)) { -+ /* -+ * The task might be running due to a spinlock sleeper -+ * wakeup. Check the saved state and set it to running -+ * if the wakeup condition is true. -+ */ -+ if (!(wake_flags & WF_LOCK_SLEEPER)) { -+ if (p->saved_state & state) { -+ p->saved_state = TASK_RUNNING; -+ success = 1; -+ } -+ } - goto out; -+ } -+ -+ /* -+ * If this is a regular wakeup, then we can unconditionally -+ * clear the saved state of a "lock sleeper". -+ */ -+ if (!(wake_flags & WF_LOCK_SLEEPER)) -+ p->saved_state = TASK_RUNNING; - - trace_sched_waking(p); - -@@ -2030,52 +2186,6 @@ - } - - /** -- * try_to_wake_up_local - try to wake up a local task with rq lock held -- * @p: the thread to be awakened -- * -- * Put @p on the run-queue if it's not already there. The caller must -- * ensure that this_rq() is locked, @p is bound to this_rq() and not -- * the current task. -- */ --static void try_to_wake_up_local(struct task_struct *p) --{ -- struct rq *rq = task_rq(p); -- -- if (WARN_ON_ONCE(rq != this_rq()) || -- WARN_ON_ONCE(p == current)) -- return; -- -- lockdep_assert_held(&rq->lock); -- -- if (!raw_spin_trylock(&p->pi_lock)) { -- /* -- * This is OK, because current is on_cpu, which avoids it being -- * picked for load-balance and preemption/IRQs are still -- * disabled avoiding further scheduler activity on it and we've -- * not yet picked a replacement task. -- */ -- lockdep_unpin_lock(&rq->lock); -- raw_spin_unlock(&rq->lock); -- raw_spin_lock(&p->pi_lock); -- raw_spin_lock(&rq->lock); -- lockdep_pin_lock(&rq->lock); -- } -- -- if (!(p->state & TASK_NORMAL)) -- goto out; -- -- trace_sched_waking(p); -- -- if (!task_on_rq_queued(p)) -- ttwu_activate(rq, p, ENQUEUE_WAKEUP); -- -- ttwu_do_wakeup(rq, p, 0); -- ttwu_stat(p, smp_processor_id(), 0); --out: -- raw_spin_unlock(&p->pi_lock); --} -- --/** - * wake_up_process - Wake up a specific process - * @p: The process to be woken up. - * -@@ -2093,6 +2203,18 @@ - } - EXPORT_SYMBOL(wake_up_process); - -+/** -+ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" -+ * @p: The process to be woken up. -+ * -+ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate -+ * the nature of the wakeup. -+ */ -+int wake_up_lock_sleeper(struct task_struct *p) -+{ -+ return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); -+} -+ - int wake_up_state(struct task_struct *p, unsigned int state) - { - return try_to_wake_up(p, state, 0); -@@ -2279,6 +2401,9 @@ - p->on_cpu = 0; - #endif - init_task_preempt_count(p); -+#ifdef CONFIG_HAVE_PREEMPT_LAZY -+ task_thread_info(p)->preempt_lazy_count = 0; -+#endif - #ifdef CONFIG_SMP - plist_node_init(&p->pushable_tasks, MAX_PRIO); - RB_CLEAR_NODE(&p->pushable_dl_tasks); -@@ -2603,8 +2728,12 @@ - finish_arch_post_lock_switch(); - - fire_sched_in_preempt_notifiers(current); -+ /* -+ * We use mmdrop_delayed() here so we don't have to do the -+ * full __mmdrop() when we are the last user. -+ */ - if (mm) -- mmdrop(mm); -+ mmdrop_delayed(mm); - if (unlikely(prev_state == TASK_DEAD)) { - if (prev->sched_class->task_dead) - prev->sched_class->task_dead(prev); -@@ -2935,16 +3064,6 @@ - } - #endif - --notrace unsigned long get_parent_ip(unsigned long addr) --{ -- if (in_lock_functions(addr)) { -- addr = CALLER_ADDR2; -- if (in_lock_functions(addr)) -- addr = CALLER_ADDR3; -- } -- return addr; --} -- - #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_PREEMPT_TRACER)) - -@@ -2966,7 +3085,7 @@ - PREEMPT_MASK - 10); - #endif - if (preempt_count() == val) { -- unsigned long ip = get_parent_ip(CALLER_ADDR1); -+ unsigned long ip = get_lock_parent_ip(); - #ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = ip; - #endif -@@ -2993,7 +3112,7 @@ - #endif - - if (preempt_count() == val) -- trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); -+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); - __preempt_count_sub(val); - } - EXPORT_SYMBOL(preempt_count_sub); -@@ -3048,6 +3167,77 @@ - schedstat_inc(this_rq(), sched_count); - } - -+#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) -+ -+void migrate_disable(void) -+{ -+ struct task_struct *p = current; -+ -+ if (in_atomic() || irqs_disabled()) { -+#ifdef CONFIG_SCHED_DEBUG -+ p->migrate_disable_atomic++; -+#endif -+ return; -+ } -+ -+#ifdef CONFIG_SCHED_DEBUG -+ if (unlikely(p->migrate_disable_atomic)) { -+ tracing_off(); -+ WARN_ON_ONCE(1); -+ } -+#endif -+ -+ if (p->migrate_disable) { -+ p->migrate_disable++; -+ return; -+ } -+ -+ preempt_disable(); -+ preempt_lazy_disable(); -+ pin_current_cpu(); -+ p->migrate_disable = 1; -+ preempt_enable(); -+} -+EXPORT_SYMBOL(migrate_disable); -+ -+void migrate_enable(void) -+{ -+ struct task_struct *p = current; -+ -+ if (in_atomic() || irqs_disabled()) { -+#ifdef CONFIG_SCHED_DEBUG -+ p->migrate_disable_atomic--; -+#endif -+ return; -+ } -+ -+#ifdef CONFIG_SCHED_DEBUG -+ if (unlikely(p->migrate_disable_atomic)) { -+ tracing_off(); -+ WARN_ON_ONCE(1); -+ } -+#endif -+ WARN_ON_ONCE(p->migrate_disable <= 0); -+ -+ if (p->migrate_disable > 1) { -+ p->migrate_disable--; -+ return; -+ } -+ -+ preempt_disable(); -+ /* -+ * Clearing migrate_disable causes tsk_cpus_allowed to -+ * show the tasks original cpu affinity. -+ */ -+ p->migrate_disable = 0; -+ -+ unpin_current_cpu(); -+ preempt_enable(); -+ preempt_lazy_enable(); -+} -+EXPORT_SYMBOL(migrate_enable); -+#endif -+ - /* - * Pick up the highest-prio task: - */ -@@ -3172,19 +3362,6 @@ - } else { - deactivate_task(rq, prev, DEQUEUE_SLEEP); - prev->on_rq = 0; -- -- /* -- * If a worker went to sleep, notify and ask workqueue -- * whether it wants to wake up a task to maintain -- * concurrency. -- */ -- if (prev->flags & PF_WQ_WORKER) { -- struct task_struct *to_wakeup; -- -- to_wakeup = wq_worker_sleeping(prev, cpu); -- if (to_wakeup) -- try_to_wake_up_local(to_wakeup); -- } - } - switch_count = &prev->nvcsw; - } -@@ -3194,6 +3371,7 @@ - - next = pick_next_task(rq, prev); - clear_tsk_need_resched(prev); -+ clear_tsk_need_resched_lazy(prev); - clear_preempt_need_resched(); - rq->clock_skip_update = 0; - -@@ -3215,9 +3393,20 @@ - - static inline void sched_submit_work(struct task_struct *tsk) - { -- if (!tsk->state || tsk_is_pi_blocked(tsk)) -+ if (!tsk->state) - return; - /* -+ * If a worker went to sleep, notify and ask workqueue whether -+ * it wants to wake up a task to maintain concurrency. -+ */ -+ if (tsk->flags & PF_WQ_WORKER) -+ wq_worker_sleeping(tsk); -+ -+ -+ if (tsk_is_pi_blocked(tsk)) -+ return; -+ -+ /* - * If we are going to sleep and we have plugged IO queued, - * make sure to submit it to avoid deadlocks. - */ -@@ -3225,6 +3414,12 @@ - blk_schedule_flush_plug(tsk); - } - -+static void sched_update_worker(struct task_struct *tsk) -+{ -+ if (tsk->flags & PF_WQ_WORKER) -+ wq_worker_running(tsk); -+} -+ - asmlinkage __visible void __sched schedule(void) - { - struct task_struct *tsk = current; -@@ -3235,6 +3430,7 @@ - __schedule(false); - sched_preempt_enable_no_resched(); - } while (need_resched()); -+ sched_update_worker(tsk); - } - EXPORT_SYMBOL(schedule); - -@@ -3283,6 +3479,30 @@ - } while (need_resched()); - } - -+#ifdef CONFIG_PREEMPT_LAZY -+/* -+ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is -+ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as -+ * preempt_lazy_count counter >0. -+ */ -+static __always_inline int preemptible_lazy(void) -+{ -+ if (test_thread_flag(TIF_NEED_RESCHED)) -+ return 1; -+ if (current_thread_info()->preempt_lazy_count) -+ return 0; -+ return 1; -+} -+ -+#else -+ -+static inline int preemptible_lazy(void) -+{ -+ return 1; -+} -+ -+#endif -+ - #ifdef CONFIG_PREEMPT - /* - * this is the entry point to schedule() from in-kernel preemption -@@ -3297,6 +3517,8 @@ - */ - if (likely(!preemptible())) - return; -+ if (!preemptible_lazy()) -+ return; - - preempt_schedule_common(); - } -@@ -3323,6 +3545,8 @@ - - if (likely(!preemptible())) - return; -+ if (!preemptible_lazy()) -+ return; - - do { - preempt_disable_notrace(); -@@ -3332,7 +3556,16 @@ - * an infinite recursion. - */ - prev_ctx = exception_enter(); -+ /* -+ * The add/subtract must not be traced by the function -+ * tracer. But we still want to account for the -+ * preempt off latency tracer. Since the _notrace versions -+ * of add/subtract skip the accounting for latency tracer -+ * we must force it manually. -+ */ -+ start_critical_timings(); - __schedule(true); -+ stop_critical_timings(); - exception_exit(prev_ctx); - - preempt_enable_no_resched_notrace(); -@@ -4676,6 +4909,7 @@ - } - EXPORT_SYMBOL(__cond_resched_lock); - -+#ifndef CONFIG_PREEMPT_RT_FULL - int __sched __cond_resched_softirq(void) - { - BUG_ON(!in_softirq()); -@@ -4689,6 +4923,7 @@ - return 0; - } - EXPORT_SYMBOL(__cond_resched_softirq); -+#endif - - /** - * yield - yield the current processor to other threads. -@@ -5055,7 +5290,9 @@ - - /* Set the preempt count _outside_ the spinlocks! */ - init_idle_preempt_count(idle, cpu); -- -+#ifdef CONFIG_HAVE_PREEMPT_LAZY -+ task_thread_info(idle)->preempt_lazy_count = 0; -+#endif - /* - * The idle tasks have their own, simple scheduling class: - */ -@@ -5196,6 +5433,8 @@ - #endif /* CONFIG_NUMA_BALANCING */ - - #ifdef CONFIG_HOTPLUG_CPU -+static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); -+ - /* - * Ensures that the idle task is using init_mm right before its cpu goes - * offline. -@@ -5210,7 +5449,11 @@ - switch_mm(mm, &init_mm, current); - finish_arch_post_lock_switch(); - } -- mmdrop(mm); -+ /* -+ * Defer the cleanup to an alive cpu. On RT we can neither -+ * call mmdrop() nor mmdrop_delayed() from here. -+ */ -+ per_cpu(idle_last_mm, smp_processor_id()) = mm; - } - - /* -@@ -5583,6 +5826,10 @@ - - case CPU_DEAD: - calc_load_migrate(rq); -+ if (per_cpu(idle_last_mm, cpu)) { -+ mmdrop(per_cpu(idle_last_mm, cpu)); -+ per_cpu(idle_last_mm, cpu) = NULL; -+ } - break; - #endif - } -@@ -7566,7 +7813,7 @@ - #ifdef CONFIG_DEBUG_ATOMIC_SLEEP - static inline int preempt_count_equals(int preempt_offset) - { -- int nested = preempt_count() + rcu_preempt_depth(); -+ int nested = preempt_count() + sched_rcu_preempt_depth(); - - return (nested == preempt_offset); - } -diff -Nur linux-4.4.28.orig/kernel/sched/cpudeadline.c linux-4.4.28/kernel/sched/cpudeadline.c ---- linux-4.4.28.orig/kernel/sched/cpudeadline.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/cpudeadline.c 2016-11-01 21:26:58.784342796 +0100 -@@ -103,10 +103,10 @@ - const struct sched_dl_entity *dl_se = &p->dl; - - if (later_mask && -- cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { -+ cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) { - best_cpu = cpumask_any(later_mask); - goto out; -- } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && -+ } else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) && - dl_time_before(dl_se->deadline, cp->elements[0].dl)) { - best_cpu = cpudl_maximum(cp); - if (later_mask) -diff -Nur linux-4.4.28.orig/kernel/sched/cpupri.c linux-4.4.28/kernel/sched/cpupri.c ---- linux-4.4.28.orig/kernel/sched/cpupri.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/cpupri.c 2016-11-01 21:26:58.784342796 +0100 -@@ -103,11 +103,11 @@ - if (skip) - continue; - -- if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) -+ if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids) - continue; - - if (lowest_mask) { -- cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); -+ cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask); - - /* - * We have to ensure that we have at least one bit -diff -Nur linux-4.4.28.orig/kernel/sched/cputime.c linux-4.4.28/kernel/sched/cputime.c ---- linux-4.4.28.orig/kernel/sched/cputime.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/cputime.c 2016-11-01 21:26:58.788343053 +0100 -@@ -685,7 +685,7 @@ - { - unsigned long long delta = vtime_delta(tsk); - -- WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); -+ WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); - tsk->vtime_snap += delta; - - /* CHECKME: always safe to convert nsecs to cputime? */ -@@ -701,37 +701,37 @@ - - void vtime_account_system(struct task_struct *tsk) - { -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - - void vtime_gen_account_irq_exit(struct task_struct *tsk) - { -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); - if (context_tracking_in_user()) - tsk->vtime_snap_whence = VTIME_USER; -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - - void vtime_account_user(struct task_struct *tsk) - { - cputime_t delta_cpu; - -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - delta_cpu = get_vtime_delta(tsk); - tsk->vtime_snap_whence = VTIME_SYS; - account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - - void vtime_user_enter(struct task_struct *tsk) - { -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); - tsk->vtime_snap_whence = VTIME_USER; -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - - void vtime_guest_enter(struct task_struct *tsk) -@@ -743,19 +743,19 @@ - * synchronization against the reader (task_gtime()) - * that can thus safely catch up with a tickless delta. - */ -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); - current->flags |= PF_VCPU; -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - EXPORT_SYMBOL_GPL(vtime_guest_enter); - - void vtime_guest_exit(struct task_struct *tsk) - { -- write_seqlock(&tsk->vtime_seqlock); -+ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); - current->flags &= ~PF_VCPU; -- write_sequnlock(&tsk->vtime_seqlock); -+ write_seqcount_end(&tsk->vtime_seqcount); - } - EXPORT_SYMBOL_GPL(vtime_guest_exit); - -@@ -768,24 +768,26 @@ - - void arch_vtime_task_switch(struct task_struct *prev) - { -- write_seqlock(&prev->vtime_seqlock); -- prev->vtime_snap_whence = VTIME_SLEEPING; -- write_sequnlock(&prev->vtime_seqlock); -+ write_seqcount_begin(&prev->vtime_seqcount); -+ prev->vtime_snap_whence = VTIME_INACTIVE; -+ write_seqcount_end(&prev->vtime_seqcount); - -- write_seqlock(¤t->vtime_seqlock); -+ write_seqcount_begin(¤t->vtime_seqcount); - current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock_cpu(smp_processor_id()); -- write_sequnlock(¤t->vtime_seqlock); -+ write_seqcount_end(¤t->vtime_seqcount); - } - - void vtime_init_idle(struct task_struct *t, int cpu) - { - unsigned long flags; - -- write_seqlock_irqsave(&t->vtime_seqlock, flags); -+ local_irq_save(flags); -+ write_seqcount_begin(&t->vtime_seqcount); - t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock_cpu(cpu); -- write_sequnlock_irqrestore(&t->vtime_seqlock, flags); -+ write_seqcount_end(&t->vtime_seqcount); -+ local_irq_restore(flags); - } - - cputime_t task_gtime(struct task_struct *t) -@@ -797,13 +799,13 @@ - return t->gtime; - - do { -- seq = read_seqbegin(&t->vtime_seqlock); -+ seq = read_seqcount_begin(&t->vtime_seqcount); - - gtime = t->gtime; - if (t->flags & PF_VCPU) - gtime += vtime_delta(t); - -- } while (read_seqretry(&t->vtime_seqlock, seq)); -+ } while (read_seqcount_retry(&t->vtime_seqcount, seq)); - - return gtime; - } -@@ -826,7 +828,7 @@ - *udelta = 0; - *sdelta = 0; - -- seq = read_seqbegin(&t->vtime_seqlock); -+ seq = read_seqcount_begin(&t->vtime_seqcount); - - if (u_dst) - *u_dst = *u_src; -@@ -834,7 +836,7 @@ - *s_dst = *s_src; - - /* Task is sleeping, nothing to add */ -- if (t->vtime_snap_whence == VTIME_SLEEPING || -+ if (t->vtime_snap_whence == VTIME_INACTIVE || - is_idle_task(t)) - continue; - -@@ -850,7 +852,7 @@ - if (t->vtime_snap_whence == VTIME_SYS) - *sdelta = delta; - } -- } while (read_seqretry(&t->vtime_seqlock, seq)); -+ } while (read_seqcount_retry(&t->vtime_seqcount, seq)); - } - - -diff -Nur linux-4.4.28.orig/kernel/sched/deadline.c linux-4.4.28/kernel/sched/deadline.c ---- linux-4.4.28.orig/kernel/sched/deadline.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/deadline.c 2016-11-01 21:26:58.788343053 +0100 -@@ -134,7 +134,7 @@ - { - struct task_struct *p = dl_task_of(dl_se); - -- if (p->nr_cpus_allowed > 1) -+ if (tsk_nr_cpus_allowed(p) > 1) - dl_rq->dl_nr_migratory++; - - update_dl_migration(dl_rq); -@@ -144,7 +144,7 @@ - { - struct task_struct *p = dl_task_of(dl_se); - -- if (p->nr_cpus_allowed > 1) -+ if (tsk_nr_cpus_allowed(p) > 1) - dl_rq->dl_nr_migratory--; - - update_dl_migration(dl_rq); -@@ -697,6 +697,7 @@ - - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - timer->function = dl_task_timer; -+ timer->irqsafe = 1; - } - - static -@@ -989,7 +990,7 @@ - - enqueue_dl_entity(&p->dl, pi_se, flags); - -- if (!task_current(rq, p) && p->nr_cpus_allowed > 1) -+ if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) - enqueue_pushable_dl_task(rq, p); - } - -@@ -1067,9 +1068,9 @@ - * try to make it stay here, it might be important. - */ - if (unlikely(dl_task(curr)) && -- (curr->nr_cpus_allowed < 2 || -+ (tsk_nr_cpus_allowed(curr) < 2 || - !dl_entity_preempt(&p->dl, &curr->dl)) && -- (p->nr_cpus_allowed > 1)) { -+ (tsk_nr_cpus_allowed(p) > 1)) { - int target = find_later_rq(p); - - if (target != -1 && -@@ -1090,7 +1091,7 @@ - * Current can't be migrated, useless to reschedule, - * let's hope p can move out. - */ -- if (rq->curr->nr_cpus_allowed == 1 || -+ if (tsk_nr_cpus_allowed(rq->curr) == 1 || - cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) - return; - -@@ -1098,7 +1099,7 @@ - * p is migratable, so let's not schedule it and - * see if it is pushed or pulled somewhere else. - */ -- if (p->nr_cpus_allowed != 1 && -+ if (tsk_nr_cpus_allowed(p) != 1 && - cpudl_find(&rq->rd->cpudl, p, NULL) != -1) - return; - -@@ -1212,7 +1213,7 @@ - { - update_curr_dl(rq); - -- if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) -+ if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1) - enqueue_pushable_dl_task(rq, p); - } - -@@ -1335,7 +1336,7 @@ - if (unlikely(!later_mask)) - return -1; - -- if (task->nr_cpus_allowed == 1) -+ if (tsk_nr_cpus_allowed(task) == 1) - return -1; - - /* -@@ -1441,7 +1442,7 @@ - if (double_lock_balance(rq, later_rq)) { - if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, -- &task->cpus_allowed) || -+ tsk_cpus_allowed(task)) || - task_running(rq, task) || - !task_on_rq_queued(task))) { - double_unlock_balance(rq, later_rq); -@@ -1480,7 +1481,7 @@ - - BUG_ON(rq->cpu != task_cpu(p)); - BUG_ON(task_current(rq, p)); -- BUG_ON(p->nr_cpus_allowed <= 1); -+ BUG_ON(tsk_nr_cpus_allowed(p) <= 1); - - BUG_ON(!task_on_rq_queued(p)); - BUG_ON(!dl_task(p)); -@@ -1519,7 +1520,7 @@ - */ - if (dl_task(rq->curr) && - dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && -- rq->curr->nr_cpus_allowed > 1) { -+ tsk_nr_cpus_allowed(rq->curr) > 1) { - resched_curr(rq); - return 0; - } -@@ -1666,9 +1667,9 @@ - { - if (!task_running(rq, p) && - !test_tsk_need_resched(rq->curr) && -- p->nr_cpus_allowed > 1 && -+ tsk_nr_cpus_allowed(p) > 1 && - dl_task(rq->curr) && -- (rq->curr->nr_cpus_allowed < 2 || -+ (tsk_nr_cpus_allowed(rq->curr) < 2 || - !dl_entity_preempt(&p->dl, &rq->curr->dl))) { - push_dl_tasks(rq); - } -@@ -1769,7 +1770,7 @@ - { - if (task_on_rq_queued(p) && rq->curr != p) { - #ifdef CONFIG_SMP -- if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) -+ if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) - queue_push_tasks(rq); - #else - if (dl_task(rq->curr)) -diff -Nur linux-4.4.28.orig/kernel/sched/debug.c linux-4.4.28/kernel/sched/debug.c ---- linux-4.4.28.orig/kernel/sched/debug.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/debug.c 2016-11-01 21:26:58.788343053 +0100 -@@ -251,6 +251,9 @@ - P(rt_throttled); - PN(rt_time); - PN(rt_runtime); -+#ifdef CONFIG_SMP -+ P(rt_nr_migratory); -+#endif - - #undef PN - #undef P -@@ -635,6 +638,10 @@ - #endif - P(policy); - P(prio); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ P(migrate_disable); -+#endif -+ P(nr_cpus_allowed); - #undef PN - #undef __PN - #undef P -diff -Nur linux-4.4.28.orig/kernel/sched/fair.c linux-4.4.28/kernel/sched/fair.c ---- linux-4.4.28.orig/kernel/sched/fair.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/fair.c 2016-11-01 21:26:58.792343317 +0100 -@@ -3166,7 +3166,7 @@ - ideal_runtime = sched_slice(cfs_rq, curr); - delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - if (delta_exec > ideal_runtime) { -- resched_curr(rq_of(cfs_rq)); -+ resched_curr_lazy(rq_of(cfs_rq)); - /* - * The current task ran long enough, ensure it doesn't get - * re-elected due to buddy favours. -@@ -3190,7 +3190,7 @@ - return; - - if (delta > ideal_runtime) -- resched_curr(rq_of(cfs_rq)); -+ resched_curr_lazy(rq_of(cfs_rq)); - } - - static void -@@ -3330,7 +3330,7 @@ - * validating it and just reschedule. - */ - if (queued) { -- resched_curr(rq_of(cfs_rq)); -+ resched_curr_lazy(rq_of(cfs_rq)); - return; - } - /* -@@ -3512,7 +3512,7 @@ - * hierarchy can be throttled - */ - if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) -- resched_curr(rq_of(cfs_rq)); -+ resched_curr_lazy(rq_of(cfs_rq)); - } - - static __always_inline -@@ -4124,7 +4124,7 @@ - - if (delta < 0) { - if (rq->curr == p) -- resched_curr(rq); -+ resched_curr_lazy(rq); - return; - } - hrtick_start(rq, delta); -@@ -5213,7 +5213,7 @@ - return; - - preempt: -- resched_curr(rq); -+ resched_curr_lazy(rq); - /* - * Only set the backward buddy when the current task is still - * on the rq. This can happen when a wakeup gets interleaved -@@ -7964,7 +7964,7 @@ - * 'current' within the tree based on its new key value. - */ - swap(curr->vruntime, se->vruntime); -- resched_curr(rq); -+ resched_curr_lazy(rq); - } - - se->vruntime -= cfs_rq->min_vruntime; -@@ -7989,7 +7989,7 @@ - */ - if (rq->curr == p) { - if (p->prio > oldprio) -- resched_curr(rq); -+ resched_curr_lazy(rq); - } else - check_preempt_curr(rq, p, 0); - } -diff -Nur linux-4.4.28.orig/kernel/sched/features.h linux-4.4.28/kernel/sched/features.h ---- linux-4.4.28.orig/kernel/sched/features.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/features.h 2016-11-01 21:26:58.792343317 +0100 -@@ -45,11 +45,19 @@ - */ - SCHED_FEAT(NONTASK_CAPACITY, true) - -+#ifdef CONFIG_PREEMPT_RT_FULL -+SCHED_FEAT(TTWU_QUEUE, false) -+# ifdef CONFIG_PREEMPT_LAZY -+SCHED_FEAT(PREEMPT_LAZY, true) -+# endif -+#else -+ - /* - * Queue remote wakeups on the target CPU and process them - * using the scheduler IPI. Reduces rq->lock contention/bounces. - */ - SCHED_FEAT(TTWU_QUEUE, true) -+#endif - - #ifdef HAVE_RT_PUSH_IPI - /* -diff -Nur linux-4.4.28.orig/kernel/sched/Makefile linux-4.4.28/kernel/sched/Makefile ---- linux-4.4.28.orig/kernel/sched/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/Makefile 2016-11-01 21:26:58.780342543 +0100 -@@ -13,7 +13,7 @@ - - obj-y += core.o loadavg.o clock.o cputime.o - obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o --obj-y += wait.o completion.o idle.o -+obj-y += wait.o swait.o swork.o completion.o idle.o - obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o - obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o - obj-$(CONFIG_SCHEDSTATS) += stats.o -diff -Nur linux-4.4.28.orig/kernel/sched/rt.c linux-4.4.28/kernel/sched/rt.c ---- linux-4.4.28.orig/kernel/sched/rt.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/rt.c 2016-11-01 21:26:58.792343317 +0100 -@@ -47,6 +47,7 @@ - - hrtimer_init(&rt_b->rt_period_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); -+ rt_b->rt_period_timer.irqsafe = 1; - rt_b->rt_period_timer.function = sched_rt_period_timer; - } - -@@ -93,6 +94,7 @@ - rt_rq->push_cpu = nr_cpu_ids; - raw_spin_lock_init(&rt_rq->push_lock); - init_irq_work(&rt_rq->push_work, push_irq_work_func); -+ rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ; - #endif - #endif /* CONFIG_SMP */ - /* We start is dequeued state, because no RT tasks are queued */ -@@ -326,7 +328,7 @@ - rt_rq = &rq_of_rt_rq(rt_rq)->rt; - - rt_rq->rt_nr_total++; -- if (p->nr_cpus_allowed > 1) -+ if (tsk_nr_cpus_allowed(p) > 1) - rt_rq->rt_nr_migratory++; - - update_rt_migration(rt_rq); -@@ -343,7 +345,7 @@ - rt_rq = &rq_of_rt_rq(rt_rq)->rt; - - rt_rq->rt_nr_total--; -- if (p->nr_cpus_allowed > 1) -+ if (tsk_nr_cpus_allowed(p) > 1) - rt_rq->rt_nr_migratory--; - - update_rt_migration(rt_rq); -@@ -1262,7 +1264,7 @@ - - enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); - -- if (!task_current(rq, p) && p->nr_cpus_allowed > 1) -+ if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) - enqueue_pushable_task(rq, p); - } - -@@ -1351,7 +1353,7 @@ - * will have to sort it out. - */ - if (curr && unlikely(rt_task(curr)) && -- (curr->nr_cpus_allowed < 2 || -+ (tsk_nr_cpus_allowed(curr) < 2 || - curr->prio <= p->prio)) { - int target = find_lowest_rq(p); - -@@ -1375,7 +1377,7 @@ - * Current can't be migrated, useless to reschedule, - * let's hope p can move out. - */ -- if (rq->curr->nr_cpus_allowed == 1 || -+ if (tsk_nr_cpus_allowed(rq->curr) == 1 || - !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) - return; - -@@ -1383,7 +1385,7 @@ - * p is migratable, so let's not schedule it and - * see if it is pushed or pulled somewhere else. - */ -- if (p->nr_cpus_allowed != 1 -+ if (tsk_nr_cpus_allowed(p) != 1 - && cpupri_find(&rq->rd->cpupri, p, NULL)) - return; - -@@ -1517,7 +1519,7 @@ - * The previous task needs to be made eligible for pushing - * if it is still active - */ -- if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) -+ if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1) - enqueue_pushable_task(rq, p); - } - -@@ -1567,7 +1569,7 @@ - if (unlikely(!lowest_mask)) - return -1; - -- if (task->nr_cpus_allowed == 1) -+ if (tsk_nr_cpus_allowed(task) == 1) - return -1; /* No other targets possible */ - - if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) -@@ -1699,7 +1701,7 @@ - - BUG_ON(rq->cpu != task_cpu(p)); - BUG_ON(task_current(rq, p)); -- BUG_ON(p->nr_cpus_allowed <= 1); -+ BUG_ON(tsk_nr_cpus_allowed(p) <= 1); - - BUG_ON(!task_on_rq_queued(p)); - BUG_ON(!rt_task(p)); -@@ -2059,9 +2061,9 @@ - { - if (!task_running(rq, p) && - !test_tsk_need_resched(rq->curr) && -- p->nr_cpus_allowed > 1 && -+ tsk_nr_cpus_allowed(p) > 1 && - (dl_task(rq->curr) || rt_task(rq->curr)) && -- (rq->curr->nr_cpus_allowed < 2 || -+ (tsk_nr_cpus_allowed(rq->curr) < 2 || - rq->curr->prio <= p->prio)) - push_rt_tasks(rq); - } -@@ -2134,7 +2136,7 @@ - */ - if (task_on_rq_queued(p) && rq->curr != p) { - #ifdef CONFIG_SMP -- if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) -+ if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) - queue_push_tasks(rq); - #else - if (p->prio < rq->curr->prio) -diff -Nur linux-4.4.28.orig/kernel/sched/sched.h linux-4.4.28/kernel/sched/sched.h ---- linux-4.4.28.orig/kernel/sched/sched.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/sched/sched.h 2016-11-01 21:26:58.792343317 +0100 -@@ -1100,6 +1100,7 @@ - #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ - #define WF_FORK 0x02 /* child wakeup after fork */ - #define WF_MIGRATED 0x4 /* internal use, task got migrated */ -+#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ - - /* - * To aid in avoiding the subversion of "niceness" due to uneven distribution -@@ -1299,6 +1300,15 @@ - extern void resched_curr(struct rq *rq); - extern void resched_cpu(int cpu); - -+#ifdef CONFIG_PREEMPT_LAZY -+extern void resched_curr_lazy(struct rq *rq); -+#else -+static inline void resched_curr_lazy(struct rq *rq) -+{ -+ resched_curr(rq); -+} -+#endif -+ - extern struct rt_bandwidth def_rt_bandwidth; - extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); - -diff -Nur linux-4.4.28.orig/kernel/sched/swait.c linux-4.4.28/kernel/sched/swait.c ---- linux-4.4.28.orig/kernel/sched/swait.c 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/kernel/sched/swait.c 2016-11-01 21:26:58.792343317 +0100 -@@ -0,0 +1,143 @@ -+#include -+#include -+#include -+ -+void __init_swait_queue_head(struct swait_queue_head *q, const char *name, -+ struct lock_class_key *key) -+{ -+ raw_spin_lock_init(&q->lock); -+ lockdep_set_class_and_name(&q->lock, key, name); -+ INIT_LIST_HEAD(&q->task_list); -+} -+EXPORT_SYMBOL(__init_swait_queue_head); -+ -+/* -+ * The thing about the wake_up_state() return value; I think we can ignore it. -+ * -+ * If for some reason it would return 0, that means the previously waiting -+ * task is already running, so it will observe condition true (or has already). -+ */ -+void swake_up_locked(struct swait_queue_head *q) -+{ -+ struct swait_queue *curr; -+ -+ if (list_empty(&q->task_list)) -+ return; -+ -+ curr = list_first_entry(&q->task_list, typeof(*curr), task_list); -+ wake_up_process(curr->task); -+ list_del_init(&curr->task_list); -+} -+EXPORT_SYMBOL(swake_up_locked); -+ -+void swake_up_all_locked(struct swait_queue_head *q) -+{ -+ struct swait_queue *curr; -+ int wakes = 0; -+ -+ while (!list_empty(&q->task_list)) { -+ -+ curr = list_first_entry(&q->task_list, typeof(*curr), -+ task_list); -+ wake_up_process(curr->task); -+ list_del_init(&curr->task_list); -+ wakes++; -+ } -+ if (pm_in_action) -+ return; -+ WARN(wakes > 2, "complate_all() with %d waiters\n", wakes); -+} -+EXPORT_SYMBOL(swake_up_all_locked); -+ -+void swake_up(struct swait_queue_head *q) -+{ -+ unsigned long flags; -+ -+ if (!swait_active(q)) -+ return; -+ -+ raw_spin_lock_irqsave(&q->lock, flags); -+ swake_up_locked(q); -+ raw_spin_unlock_irqrestore(&q->lock, flags); -+} -+EXPORT_SYMBOL(swake_up); -+ -+/* -+ * Does not allow usage from IRQ disabled, since we must be able to -+ * release IRQs to guarantee bounded hold time. -+ */ -+void swake_up_all(struct swait_queue_head *q) -+{ -+ struct swait_queue *curr; -+ LIST_HEAD(tmp); -+ -+ if (!swait_active(q)) -+ return; -+ -+ raw_spin_lock_irq(&q->lock); -+ list_splice_init(&q->task_list, &tmp); -+ while (!list_empty(&tmp)) { -+ curr = list_first_entry(&tmp, typeof(*curr), task_list); -+ -+ wake_up_state(curr->task, TASK_NORMAL); -+ list_del_init(&curr->task_list); -+ -+ if (list_empty(&tmp)) -+ break; -+ -+ raw_spin_unlock_irq(&q->lock); -+ raw_spin_lock_irq(&q->lock); -+ } -+ raw_spin_unlock_irq(&q->lock); -+} -+EXPORT_SYMBOL(swake_up_all); -+ -+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) -+{ -+ wait->task = current; -+ if (list_empty(&wait->task_list)) -+ list_add(&wait->task_list, &q->task_list); -+} -+ -+void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) -+{ -+ unsigned long flags; -+ -+ raw_spin_lock_irqsave(&q->lock, flags); -+ __prepare_to_swait(q, wait); -+ set_current_state(state); -+ raw_spin_unlock_irqrestore(&q->lock, flags); -+} -+EXPORT_SYMBOL(prepare_to_swait); -+ -+long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) -+{ -+ if (signal_pending_state(state, current)) -+ return -ERESTARTSYS; -+ -+ prepare_to_swait(q, wait, state); -+ -+ return 0; -+} -+EXPORT_SYMBOL(prepare_to_swait_event); -+ -+void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait) -+{ -+ __set_current_state(TASK_RUNNING); -+ if (!list_empty(&wait->task_list)) -+ list_del_init(&wait->task_list); -+} -+ -+void finish_swait(struct swait_queue_head *q, struct swait_queue *wait) -+{ -+ unsigned long flags; -+ -+ __set_current_state(TASK_RUNNING); -+ -+ if (!list_empty_careful(&wait->task_list)) { -+ raw_spin_lock_irqsave(&q->lock, flags); -+ list_del_init(&wait->task_list); -+ raw_spin_unlock_irqrestore(&q->lock, flags); -+ } -+} -+EXPORT_SYMBOL(finish_swait); -diff -Nur linux-4.4.28.orig/kernel/sched/swork.c linux-4.4.28/kernel/sched/swork.c ---- linux-4.4.28.orig/kernel/sched/swork.c 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/kernel/sched/swork.c 2016-11-01 21:26:58.792343317 +0100 -@@ -0,0 +1,173 @@ -+/* -+ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de -+ * -+ * Provides a framework for enqueuing callbacks from irq context -+ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. -+ */ -+ -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#define SWORK_EVENT_PENDING (1 << 0) -+ -+static DEFINE_MUTEX(worker_mutex); -+static struct sworker *glob_worker; -+ -+struct sworker { -+ struct list_head events; -+ struct swait_queue_head wq; -+ -+ raw_spinlock_t lock; -+ -+ struct task_struct *task; -+ int refs; -+}; -+ -+static bool swork_readable(struct sworker *worker) -+{ -+ bool r; -+ -+ if (kthread_should_stop()) -+ return true; -+ -+ raw_spin_lock_irq(&worker->lock); -+ r = !list_empty(&worker->events); -+ raw_spin_unlock_irq(&worker->lock); -+ -+ return r; -+} -+ -+static int swork_kthread(void *arg) -+{ -+ struct sworker *worker = arg; -+ -+ for (;;) { -+ swait_event_interruptible(worker->wq, -+ swork_readable(worker)); -+ if (kthread_should_stop()) -+ break; -+ -+ raw_spin_lock_irq(&worker->lock); -+ while (!list_empty(&worker->events)) { -+ struct swork_event *sev; -+ -+ sev = list_first_entry(&worker->events, -+ struct swork_event, item); -+ list_del(&sev->item); -+ raw_spin_unlock_irq(&worker->lock); -+ -+ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, -+ &sev->flags)); -+ sev->func(sev); -+ raw_spin_lock_irq(&worker->lock); -+ } -+ raw_spin_unlock_irq(&worker->lock); -+ } -+ return 0; -+} -+ -+static struct sworker *swork_create(void) -+{ -+ struct sworker *worker; -+ -+ worker = kzalloc(sizeof(*worker), GFP_KERNEL); -+ if (!worker) -+ return ERR_PTR(-ENOMEM); -+ -+ INIT_LIST_HEAD(&worker->events); -+ raw_spin_lock_init(&worker->lock); -+ init_swait_queue_head(&worker->wq); -+ -+ worker->task = kthread_run(swork_kthread, worker, "kswork"); -+ if (IS_ERR(worker->task)) { -+ kfree(worker); -+ return ERR_PTR(-ENOMEM); -+ } -+ -+ return worker; -+} -+ -+static void swork_destroy(struct sworker *worker) -+{ -+ kthread_stop(worker->task); -+ -+ WARN_ON(!list_empty(&worker->events)); -+ kfree(worker); -+} -+ -+/** -+ * swork_queue - queue swork -+ * -+ * Returns %false if @work was already on a queue, %true otherwise. -+ * -+ * The work is queued and processed on a random CPU -+ */ -+bool swork_queue(struct swork_event *sev) -+{ -+ unsigned long flags; -+ -+ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) -+ return false; -+ -+ raw_spin_lock_irqsave(&glob_worker->lock, flags); -+ list_add_tail(&sev->item, &glob_worker->events); -+ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); -+ -+ swake_up(&glob_worker->wq); -+ return true; -+} -+EXPORT_SYMBOL_GPL(swork_queue); -+ -+/** -+ * swork_get - get an instance of the sworker -+ * -+ * Returns an negative error code if the initialization if the worker did not -+ * work, %0 otherwise. -+ * -+ */ -+int swork_get(void) -+{ -+ struct sworker *worker; -+ -+ mutex_lock(&worker_mutex); -+ if (!glob_worker) { -+ worker = swork_create(); -+ if (IS_ERR(worker)) { -+ mutex_unlock(&worker_mutex); -+ return -ENOMEM; -+ } -+ -+ glob_worker = worker; -+ } -+ -+ glob_worker->refs++; -+ mutex_unlock(&worker_mutex); -+ -+ return 0; -+} -+EXPORT_SYMBOL_GPL(swork_get); -+ -+/** -+ * swork_put - puts an instance of the sworker -+ * -+ * Will destroy the sworker thread. This function must not be called until all -+ * queued events have been completed. -+ */ -+void swork_put(void) -+{ -+ mutex_lock(&worker_mutex); -+ -+ glob_worker->refs--; -+ if (glob_worker->refs > 0) -+ goto out; -+ -+ swork_destroy(glob_worker); -+ glob_worker = NULL; -+out: -+ mutex_unlock(&worker_mutex); -+} -+EXPORT_SYMBOL_GPL(swork_put); -diff -Nur linux-4.4.28.orig/kernel/signal.c linux-4.4.28/kernel/signal.c ---- linux-4.4.28.orig/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/signal.c 2016-11-01 21:26:58.796343570 +0100 -@@ -14,6 +14,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -352,13 +353,30 @@ - return false; - } - -+static inline struct sigqueue *get_task_cache(struct task_struct *t) -+{ -+ struct sigqueue *q = t->sigqueue_cache; -+ -+ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) -+ return NULL; -+ return q; -+} -+ -+static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) -+{ -+ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) -+ return 0; -+ return 1; -+} -+ - /* - * allocate a new signal queue record - * - this may be called without locks if and only if t == current, otherwise an - * appropriate lock must be held to stop the target task from exiting - */ - static struct sigqueue * --__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) -+__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, -+ int override_rlimit, int fromslab) - { - struct sigqueue *q = NULL; - struct user_struct *user; -@@ -375,7 +393,10 @@ - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { -- q = kmem_cache_alloc(sigqueue_cachep, flags); -+ if (!fromslab) -+ q = get_task_cache(t); -+ if (!q) -+ q = kmem_cache_alloc(sigqueue_cachep, flags); - } else { - print_dropped_signal(sig); - } -@@ -392,6 +413,13 @@ - return q; - } - -+static struct sigqueue * -+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, -+ int override_rlimit) -+{ -+ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); -+} -+ - static void __sigqueue_free(struct sigqueue *q) - { - if (q->flags & SIGQUEUE_PREALLOC) -@@ -401,6 +429,21 @@ - kmem_cache_free(sigqueue_cachep, q); - } - -+static void sigqueue_free_current(struct sigqueue *q) -+{ -+ struct user_struct *up; -+ -+ if (q->flags & SIGQUEUE_PREALLOC) -+ return; -+ -+ up = q->user; -+ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { -+ atomic_dec(&up->sigpending); -+ free_uid(up); -+ } else -+ __sigqueue_free(q); -+} -+ - void flush_sigqueue(struct sigpending *queue) - { - struct sigqueue *q; -@@ -414,6 +457,21 @@ - } - - /* -+ * Called from __exit_signal. Flush tsk->pending and -+ * tsk->sigqueue_cache -+ */ -+void flush_task_sigqueue(struct task_struct *tsk) -+{ -+ struct sigqueue *q; -+ -+ flush_sigqueue(&tsk->pending); -+ -+ q = get_task_cache(tsk); -+ if (q) -+ kmem_cache_free(sigqueue_cachep, q); -+} -+ -+/* - * Flush all pending signals for this kthread. - */ - void flush_signals(struct task_struct *t) -@@ -525,7 +583,7 @@ - still_pending: - list_del_init(&first->list); - copy_siginfo(info, &first->info); -- __sigqueue_free(first); -+ sigqueue_free_current(first); - } else { - /* - * Ok, it wasn't in the queue. This must be -@@ -560,6 +618,8 @@ - { - int signr; - -+ WARN_ON_ONCE(tsk != current); -+ - /* We only dequeue private signals from ourselves, we don't let - * signalfd steal them - */ -@@ -1156,8 +1216,8 @@ - * We don't want to have recursive SIGSEGV's etc, for example, - * that is why we also clear SIGNAL_UNKILLABLE. - */ --int --force_sig_info(int sig, struct siginfo *info, struct task_struct *t) -+static int -+do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) - { - unsigned long int flags; - int ret, blocked, ignored; -@@ -1182,6 +1242,39 @@ - return ret; - } - -+int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) -+{ -+/* -+ * On some archs, PREEMPT_RT has to delay sending a signal from a trap -+ * since it can not enable preemption, and the signal code's spin_locks -+ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will -+ * send the signal on exit of the trap. -+ */ -+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND -+ if (in_atomic()) { -+ if (WARN_ON_ONCE(t != current)) -+ return 0; -+ if (WARN_ON_ONCE(t->forced_info.si_signo)) -+ return 0; -+ -+ if (is_si_special(info)) { -+ WARN_ON_ONCE(info != SEND_SIG_PRIV); -+ t->forced_info.si_signo = sig; -+ t->forced_info.si_errno = 0; -+ t->forced_info.si_code = SI_KERNEL; -+ t->forced_info.si_pid = 0; -+ t->forced_info.si_uid = 0; -+ } else { -+ t->forced_info = *info; -+ } -+ -+ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); -+ return 0; -+ } -+#endif -+ return do_force_sig_info(sig, info, t); -+} -+ - /* - * Nuke all other threads in the group. - */ -@@ -1216,12 +1309,12 @@ - * Disable interrupts early to avoid deadlocks. - * See rcu_read_unlock() comment header for details. - */ -- local_irq_save(*flags); -+ local_irq_save_nort(*flags); - rcu_read_lock(); - sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) { - rcu_read_unlock(); -- local_irq_restore(*flags); -+ local_irq_restore_nort(*flags); - break; - } - /* -@@ -1242,7 +1335,7 @@ - } - spin_unlock(&sighand->siglock); - rcu_read_unlock(); -- local_irq_restore(*flags); -+ local_irq_restore_nort(*flags); - } - - return sighand; -@@ -1485,7 +1578,8 @@ - */ - struct sigqueue *sigqueue_alloc(void) - { -- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); -+ /* Preallocated sigqueue objects always from the slabcache ! */ -+ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); - - if (q) - q->flags |= SIGQUEUE_PREALLOC; -@@ -1846,15 +1940,7 @@ - if (gstop_done && ptrace_reparented(current)) - do_notify_parent_cldstop(current, false, why); - -- /* -- * Don't want to allow preemption here, because -- * sys_ptrace() needs this task to be inactive. -- * -- * XXX: implement read_unlock_no_resched(). -- */ -- preempt_disable(); - read_unlock(&tasklist_lock); -- preempt_enable_no_resched(); - freezable_schedule(); - } else { - /* -diff -Nur linux-4.4.28.orig/kernel/softirq.c linux-4.4.28/kernel/softirq.c ---- linux-4.4.28.orig/kernel/softirq.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/softirq.c 2016-11-01 21:26:58.796343570 +0100 -@@ -21,10 +21,12 @@ - #include - #include - #include -+#include - #include - #include - #include - #include -+#include - #include - - #define CREATE_TRACE_POINTS -@@ -56,12 +58,108 @@ - static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; - - DEFINE_PER_CPU(struct task_struct *, ksoftirqd); -+#ifdef CONFIG_PREEMPT_RT_FULL -+#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) -+DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); -+#endif - - const char * const softirq_to_name[NR_SOFTIRQS] = { - "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", - "TASKLET", "SCHED", "HRTIMER", "RCU" - }; - -+#ifdef CONFIG_NO_HZ_COMMON -+# ifdef CONFIG_PREEMPT_RT_FULL -+ -+struct softirq_runner { -+ struct task_struct *runner[NR_SOFTIRQS]; -+}; -+ -+static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); -+ -+static inline void softirq_set_runner(unsigned int sirq) -+{ -+ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); -+ -+ sr->runner[sirq] = current; -+} -+ -+static inline void softirq_clr_runner(unsigned int sirq) -+{ -+ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); -+ -+ sr->runner[sirq] = NULL; -+} -+ -+/* -+ * On preempt-rt a softirq running context might be blocked on a -+ * lock. There might be no other runnable task on this CPU because the -+ * lock owner runs on some other CPU. So we have to go into idle with -+ * the pending bit set. Therefor we need to check this otherwise we -+ * warn about false positives which confuses users and defeats the -+ * whole purpose of this test. -+ * -+ * This code is called with interrupts disabled. -+ */ -+void softirq_check_pending_idle(void) -+{ -+ static int rate_limit; -+ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); -+ u32 warnpending; -+ int i; -+ -+ if (rate_limit >= 10) -+ return; -+ -+ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; -+ for (i = 0; i < NR_SOFTIRQS; i++) { -+ struct task_struct *tsk = sr->runner[i]; -+ -+ /* -+ * The wakeup code in rtmutex.c wakes up the task -+ * _before_ it sets pi_blocked_on to NULL under -+ * tsk->pi_lock. So we need to check for both: state -+ * and pi_blocked_on. -+ */ -+ if (tsk) { -+ raw_spin_lock(&tsk->pi_lock); -+ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { -+ /* Clear all bits pending in that task */ -+ warnpending &= ~(tsk->softirqs_raised); -+ warnpending &= ~(1 << i); -+ } -+ raw_spin_unlock(&tsk->pi_lock); -+ } -+ } -+ -+ if (warnpending) { -+ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", -+ warnpending); -+ rate_limit++; -+ } -+} -+# else -+/* -+ * On !PREEMPT_RT we just printk rate limited: -+ */ -+void softirq_check_pending_idle(void) -+{ -+ static int rate_limit; -+ -+ if (rate_limit < 10 && -+ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { -+ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", -+ local_softirq_pending()); -+ rate_limit++; -+ } -+} -+# endif -+ -+#else /* !CONFIG_NO_HZ_COMMON */ -+static inline void softirq_set_runner(unsigned int sirq) { } -+static inline void softirq_clr_runner(unsigned int sirq) { } -+#endif -+ - /* - * we cannot loop indefinitely here to avoid userspace starvation, - * but we also don't want to introduce a worst case 1/HZ latency -@@ -77,6 +175,79 @@ - wake_up_process(tsk); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static void wakeup_timer_softirqd(void) -+{ -+ /* Interrupts are disabled: no need to stop preemption */ -+ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); -+ -+ if (tsk && tsk->state != TASK_RUNNING) -+ wake_up_process(tsk); -+} -+#endif -+ -+static void handle_softirq(unsigned int vec_nr) -+{ -+ struct softirq_action *h = softirq_vec + vec_nr; -+ int prev_count; -+ -+ prev_count = preempt_count(); -+ -+ kstat_incr_softirqs_this_cpu(vec_nr); -+ -+ trace_softirq_entry(vec_nr); -+ h->action(h); -+ trace_softirq_exit(vec_nr); -+ if (unlikely(prev_count != preempt_count())) { -+ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", -+ vec_nr, softirq_to_name[vec_nr], h->action, -+ prev_count, preempt_count()); -+ preempt_count_set(prev_count); -+ } -+} -+ -+#ifndef CONFIG_PREEMPT_RT_FULL -+static inline int ksoftirqd_softirq_pending(void) -+{ -+ return local_softirq_pending(); -+} -+ -+static void handle_pending_softirqs(u32 pending) -+{ -+ struct softirq_action *h = softirq_vec; -+ int softirq_bit; -+ -+ local_irq_enable(); -+ -+ h = softirq_vec; -+ -+ while ((softirq_bit = ffs(pending))) { -+ unsigned int vec_nr; -+ -+ h += softirq_bit - 1; -+ vec_nr = h - softirq_vec; -+ handle_softirq(vec_nr); -+ -+ h++; -+ pending >>= softirq_bit; -+ } -+ -+ rcu_bh_qs(); -+ local_irq_disable(); -+} -+ -+static void run_ksoftirqd(unsigned int cpu) -+{ -+ local_irq_disable(); -+ if (ksoftirqd_softirq_pending()) { -+ __do_softirq(); -+ local_irq_enable(); -+ cond_resched_rcu_qs(); -+ return; -+ } -+ local_irq_enable(); -+} -+ - /* - * preempt_count and SOFTIRQ_OFFSET usage: - * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving -@@ -116,9 +287,9 @@ - - if (preempt_count() == cnt) { - #ifdef CONFIG_DEBUG_PREEMPT -- current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); -+ current->preempt_disable_ip = get_lock_parent_ip(); - #endif -- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); -+ trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); - } - } - EXPORT_SYMBOL(__local_bh_disable_ip); -@@ -232,10 +403,8 @@ - unsigned long end = jiffies + MAX_SOFTIRQ_TIME; - unsigned long old_flags = current->flags; - int max_restart = MAX_SOFTIRQ_RESTART; -- struct softirq_action *h; - bool in_hardirq; - __u32 pending; -- int softirq_bit; - - /* - * Mask out PF_MEMALLOC s current task context is borrowed for the -@@ -254,36 +423,7 @@ - /* Reset the pending bitmask before enabling irqs */ - set_softirq_pending(0); - -- local_irq_enable(); -- -- h = softirq_vec; -- -- while ((softirq_bit = ffs(pending))) { -- unsigned int vec_nr; -- int prev_count; -- -- h += softirq_bit - 1; -- -- vec_nr = h - softirq_vec; -- prev_count = preempt_count(); -- -- kstat_incr_softirqs_this_cpu(vec_nr); -- -- trace_softirq_entry(vec_nr); -- h->action(h); -- trace_softirq_exit(vec_nr); -- if (unlikely(prev_count != preempt_count())) { -- pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", -- vec_nr, softirq_to_name[vec_nr], h->action, -- prev_count, preempt_count()); -- preempt_count_set(prev_count); -- } -- h++; -- pending >>= softirq_bit; -- } -- -- rcu_bh_qs(); -- local_irq_disable(); -+ handle_pending_softirqs(pending); - - pending = local_softirq_pending(); - if (pending) { -@@ -320,6 +460,310 @@ - } - - /* -+ * This function must run with irqs disabled! -+ */ -+void raise_softirq_irqoff(unsigned int nr) -+{ -+ __raise_softirq_irqoff(nr); -+ -+ /* -+ * If we're in an interrupt or softirq, we're done -+ * (this also catches softirq-disabled code). We will -+ * actually run the softirq once we return from -+ * the irq or softirq. -+ * -+ * Otherwise we wake up ksoftirqd to make sure we -+ * schedule the softirq soon. -+ */ -+ if (!in_interrupt()) -+ wakeup_softirqd(); -+} -+ -+void __raise_softirq_irqoff(unsigned int nr) -+{ -+ trace_softirq_raise(nr); -+ or_softirq_pending(1UL << nr); -+} -+ -+static inline void local_bh_disable_nort(void) { local_bh_disable(); } -+static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } -+static void ksoftirqd_set_sched_params(unsigned int cpu) { } -+ -+#else /* !PREEMPT_RT_FULL */ -+ -+/* -+ * On RT we serialize softirq execution with a cpu local lock per softirq -+ */ -+static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); -+ -+void __init softirq_early_init(void) -+{ -+ int i; -+ -+ for (i = 0; i < NR_SOFTIRQS; i++) -+ local_irq_lock_init(local_softirq_locks[i]); -+} -+ -+static void lock_softirq(int which) -+{ -+ local_lock(local_softirq_locks[which]); -+} -+ -+static void unlock_softirq(int which) -+{ -+ local_unlock(local_softirq_locks[which]); -+} -+ -+static void do_single_softirq(int which) -+{ -+ unsigned long old_flags = current->flags; -+ -+ current->flags &= ~PF_MEMALLOC; -+ vtime_account_irq_enter(current); -+ current->flags |= PF_IN_SOFTIRQ; -+ lockdep_softirq_enter(); -+ local_irq_enable(); -+ handle_softirq(which); -+ local_irq_disable(); -+ lockdep_softirq_exit(); -+ current->flags &= ~PF_IN_SOFTIRQ; -+ vtime_account_irq_enter(current); -+ tsk_restore_flags(current, old_flags, PF_MEMALLOC); -+} -+ -+/* -+ * Called with interrupts disabled. Process softirqs which were raised -+ * in current context (or on behalf of ksoftirqd). -+ */ -+static void do_current_softirqs(void) -+{ -+ while (current->softirqs_raised) { -+ int i = __ffs(current->softirqs_raised); -+ unsigned int pending, mask = (1U << i); -+ -+ current->softirqs_raised &= ~mask; -+ local_irq_enable(); -+ -+ /* -+ * If the lock is contended, we boost the owner to -+ * process the softirq or leave the critical section -+ * now. -+ */ -+ lock_softirq(i); -+ local_irq_disable(); -+ softirq_set_runner(i); -+ /* -+ * Check with the local_softirq_pending() bits, -+ * whether we need to process this still or if someone -+ * else took care of it. -+ */ -+ pending = local_softirq_pending(); -+ if (pending & mask) { -+ set_softirq_pending(pending & ~mask); -+ do_single_softirq(i); -+ } -+ softirq_clr_runner(i); -+ WARN_ON(current->softirq_nestcnt != 1); -+ local_irq_enable(); -+ unlock_softirq(i); -+ local_irq_disable(); -+ } -+} -+ -+void __local_bh_disable(void) -+{ -+ if (++current->softirq_nestcnt == 1) -+ migrate_disable(); -+} -+EXPORT_SYMBOL(__local_bh_disable); -+ -+void __local_bh_enable(void) -+{ -+ if (WARN_ON(current->softirq_nestcnt == 0)) -+ return; -+ -+ local_irq_disable(); -+ if (current->softirq_nestcnt == 1 && current->softirqs_raised) -+ do_current_softirqs(); -+ local_irq_enable(); -+ -+ if (--current->softirq_nestcnt == 0) -+ migrate_enable(); -+} -+EXPORT_SYMBOL(__local_bh_enable); -+ -+void _local_bh_enable(void) -+{ -+ if (WARN_ON(current->softirq_nestcnt == 0)) -+ return; -+ if (--current->softirq_nestcnt == 0) -+ migrate_enable(); -+} -+EXPORT_SYMBOL(_local_bh_enable); -+ -+int in_serving_softirq(void) -+{ -+ return current->flags & PF_IN_SOFTIRQ; -+} -+EXPORT_SYMBOL(in_serving_softirq); -+ -+/* Called with preemption disabled */ -+static void run_ksoftirqd(unsigned int cpu) -+{ -+ local_irq_disable(); -+ current->softirq_nestcnt++; -+ -+ do_current_softirqs(); -+ current->softirq_nestcnt--; -+ local_irq_enable(); -+ cond_resched_rcu_qs(); -+} -+ -+/* -+ * Called from netif_rx_ni(). Preemption enabled, but migration -+ * disabled. So the cpu can't go away under us. -+ */ -+void thread_do_softirq(void) -+{ -+ if (!in_serving_softirq() && current->softirqs_raised) { -+ current->softirq_nestcnt++; -+ do_current_softirqs(); -+ current->softirq_nestcnt--; -+ } -+} -+ -+static void do_raise_softirq_irqoff(unsigned int nr) -+{ -+ unsigned int mask; -+ -+ mask = 1UL << nr; -+ -+ trace_softirq_raise(nr); -+ or_softirq_pending(mask); -+ -+ /* -+ * If we are not in a hard interrupt and inside a bh disabled -+ * region, we simply raise the flag on current. local_bh_enable() -+ * will make sure that the softirq is executed. Otherwise we -+ * delegate it to ksoftirqd. -+ */ -+ if (!in_irq() && current->softirq_nestcnt) -+ current->softirqs_raised |= mask; -+ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) -+ return; -+ -+ if (mask & TIMER_SOFTIRQS) -+ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; -+ else -+ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; -+} -+ -+static void wakeup_proper_softirq(unsigned int nr) -+{ -+ if ((1UL << nr) & TIMER_SOFTIRQS) -+ wakeup_timer_softirqd(); -+ else -+ wakeup_softirqd(); -+} -+ -+ -+void __raise_softirq_irqoff(unsigned int nr) -+{ -+ do_raise_softirq_irqoff(nr); -+ if (!in_irq() && !current->softirq_nestcnt) -+ wakeup_proper_softirq(nr); -+} -+ -+/* -+ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd -+ */ -+void __raise_softirq_irqoff_ksoft(unsigned int nr) -+{ -+ unsigned int mask; -+ -+ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || -+ !__this_cpu_read(ktimer_softirqd))) -+ return; -+ mask = 1UL << nr; -+ -+ trace_softirq_raise(nr); -+ or_softirq_pending(mask); -+ if (mask & TIMER_SOFTIRQS) -+ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; -+ else -+ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; -+ wakeup_proper_softirq(nr); -+} -+ -+/* -+ * This function must run with irqs disabled! -+ */ -+void raise_softirq_irqoff(unsigned int nr) -+{ -+ do_raise_softirq_irqoff(nr); -+ -+ /* -+ * If we're in an hard interrupt we let irq return code deal -+ * with the wakeup of ksoftirqd. -+ */ -+ if (in_irq()) -+ return; -+ /* -+ * If we are in thread context but outside of a bh disabled -+ * region, we need to wake ksoftirqd as well. -+ * -+ * CHECKME: Some of the places which do that could be wrapped -+ * into local_bh_disable/enable pairs. Though it's unclear -+ * whether this is worth the effort. To find those places just -+ * raise a WARN() if the condition is met. -+ */ -+ if (!current->softirq_nestcnt) -+ wakeup_proper_softirq(nr); -+} -+ -+static inline int ksoftirqd_softirq_pending(void) -+{ -+ return current->softirqs_raised; -+} -+ -+static inline void local_bh_disable_nort(void) { } -+static inline void _local_bh_enable_nort(void) { } -+ -+static inline void ksoftirqd_set_sched_params(unsigned int cpu) -+{ -+ /* Take over all but timer pending softirqs when starting */ -+ local_irq_disable(); -+ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; -+ local_irq_enable(); -+} -+ -+static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) -+{ -+ struct sched_param param = { .sched_priority = 1 }; -+ -+ sched_setscheduler(current, SCHED_FIFO, ¶m); -+ -+ /* Take over timer pending softirqs when starting */ -+ local_irq_disable(); -+ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; -+ local_irq_enable(); -+} -+ -+static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, -+ bool online) -+{ -+ struct sched_param param = { .sched_priority = 0 }; -+ -+ sched_setscheduler(current, SCHED_NORMAL, ¶m); -+} -+ -+static int ktimer_softirqd_should_run(unsigned int cpu) -+{ -+ return current->softirqs_raised; -+} -+ -+#endif /* PREEMPT_RT_FULL */ -+/* - * Enter an interrupt context. - */ - void irq_enter(void) -@@ -330,9 +774,9 @@ - * Prevent raise_softirq from needlessly waking up ksoftirqd - * here, as softirq will be serviced on return from interrupt. - */ -- local_bh_disable(); -+ local_bh_disable_nort(); - tick_irq_enter(); -- _local_bh_enable(); -+ _local_bh_enable_nort(); - } - - __irq_enter(); -@@ -340,6 +784,7 @@ - - static inline void invoke_softirq(void) - { -+#ifndef CONFIG_PREEMPT_RT_FULL - if (!force_irqthreads) { - #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK - /* -@@ -359,6 +804,18 @@ - } else { - wakeup_softirqd(); - } -+#else /* PREEMPT_RT_FULL */ -+ unsigned long flags; -+ -+ local_irq_save(flags); -+ if (__this_cpu_read(ksoftirqd) && -+ __this_cpu_read(ksoftirqd)->softirqs_raised) -+ wakeup_softirqd(); -+ if (__this_cpu_read(ktimer_softirqd) && -+ __this_cpu_read(ktimer_softirqd)->softirqs_raised) -+ wakeup_timer_softirqd(); -+ local_irq_restore(flags); -+#endif - } - - static inline void tick_irq_exit(void) -@@ -395,26 +852,6 @@ - trace_hardirq_exit(); /* must be last! */ - } - --/* -- * This function must run with irqs disabled! -- */ --inline void raise_softirq_irqoff(unsigned int nr) --{ -- __raise_softirq_irqoff(nr); -- -- /* -- * If we're in an interrupt or softirq, we're done -- * (this also catches softirq-disabled code). We will -- * actually run the softirq once we return from -- * the irq or softirq. -- * -- * Otherwise we wake up ksoftirqd to make sure we -- * schedule the softirq soon. -- */ -- if (!in_interrupt()) -- wakeup_softirqd(); --} -- - void raise_softirq(unsigned int nr) - { - unsigned long flags; -@@ -424,12 +861,6 @@ - local_irq_restore(flags); - } - --void __raise_softirq_irqoff(unsigned int nr) --{ -- trace_softirq_raise(nr); -- or_softirq_pending(1UL << nr); --} -- - void open_softirq(int nr, void (*action)(struct softirq_action *)) - { - softirq_vec[nr].action = action; -@@ -446,15 +877,45 @@ - static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); - static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); - -+static void inline -+__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) -+{ -+ if (tasklet_trylock(t)) { -+again: -+ /* We may have been preempted before tasklet_trylock -+ * and __tasklet_action may have already run. -+ * So double check the sched bit while the takslet -+ * is locked before adding it to the list. -+ */ -+ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { -+ t->next = NULL; -+ *head->tail = t; -+ head->tail = &(t->next); -+ raise_softirq_irqoff(nr); -+ tasklet_unlock(t); -+ } else { -+ /* This is subtle. If we hit the corner case above -+ * It is possible that we get preempted right here, -+ * and another task has successfully called -+ * tasklet_schedule(), then this function, and -+ * failed on the trylock. Thus we must be sure -+ * before releasing the tasklet lock, that the -+ * SCHED_BIT is clear. Otherwise the tasklet -+ * may get its SCHED_BIT set, but not added to the -+ * list -+ */ -+ if (!tasklet_tryunlock(t)) -+ goto again; -+ } -+ } -+} -+ - void __tasklet_schedule(struct tasklet_struct *t) - { - unsigned long flags; - - local_irq_save(flags); -- t->next = NULL; -- *__this_cpu_read(tasklet_vec.tail) = t; -- __this_cpu_write(tasklet_vec.tail, &(t->next)); -- raise_softirq_irqoff(TASKLET_SOFTIRQ); -+ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); - local_irq_restore(flags); - } - EXPORT_SYMBOL(__tasklet_schedule); -@@ -464,10 +925,7 @@ - unsigned long flags; - - local_irq_save(flags); -- t->next = NULL; -- *__this_cpu_read(tasklet_hi_vec.tail) = t; -- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); -- raise_softirq_irqoff(HI_SOFTIRQ); -+ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); - local_irq_restore(flags); - } - EXPORT_SYMBOL(__tasklet_hi_schedule); -@@ -476,82 +934,122 @@ - { - BUG_ON(!irqs_disabled()); - -- t->next = __this_cpu_read(tasklet_hi_vec.head); -- __this_cpu_write(tasklet_hi_vec.head, t); -- __raise_softirq_irqoff(HI_SOFTIRQ); -+ __tasklet_hi_schedule(t); - } - EXPORT_SYMBOL(__tasklet_hi_schedule_first); - --static void tasklet_action(struct softirq_action *a) -+void tasklet_enable(struct tasklet_struct *t) - { -- struct tasklet_struct *list; -+ if (!atomic_dec_and_test(&t->count)) -+ return; -+ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) -+ tasklet_schedule(t); -+} -+EXPORT_SYMBOL(tasklet_enable); - -- local_irq_disable(); -- list = __this_cpu_read(tasklet_vec.head); -- __this_cpu_write(tasklet_vec.head, NULL); -- __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); -- local_irq_enable(); -+static void __tasklet_action(struct softirq_action *a, -+ struct tasklet_struct *list) -+{ -+ int loops = 1000000; - - while (list) { - struct tasklet_struct *t = list; - - list = list->next; - -- if (tasklet_trylock(t)) { -- if (!atomic_read(&t->count)) { -- if (!test_and_clear_bit(TASKLET_STATE_SCHED, -- &t->state)) -- BUG(); -- t->func(t->data); -- tasklet_unlock(t); -- continue; -- } -- tasklet_unlock(t); -+ /* -+ * Should always succeed - after a tasklist got on the -+ * list (after getting the SCHED bit set from 0 to 1), -+ * nothing but the tasklet softirq it got queued to can -+ * lock it: -+ */ -+ if (!tasklet_trylock(t)) { -+ WARN_ON(1); -+ continue; - } - -- local_irq_disable(); - t->next = NULL; -- *__this_cpu_read(tasklet_vec.tail) = t; -- __this_cpu_write(tasklet_vec.tail, &(t->next)); -- __raise_softirq_irqoff(TASKLET_SOFTIRQ); -- local_irq_enable(); -+ -+ /* -+ * If we cannot handle the tasklet because it's disabled, -+ * mark it as pending. tasklet_enable() will later -+ * re-schedule the tasklet. -+ */ -+ if (unlikely(atomic_read(&t->count))) { -+out_disabled: -+ /* implicit unlock: */ -+ wmb(); -+ t->state = TASKLET_STATEF_PENDING; -+ continue; -+ } -+ -+ /* -+ * After this point on the tasklet might be rescheduled -+ * on another CPU, but it can only be added to another -+ * CPU's tasklet list if we unlock the tasklet (which we -+ * dont do yet). -+ */ -+ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) -+ WARN_ON(1); -+ -+again: -+ t->func(t->data); -+ -+ /* -+ * Try to unlock the tasklet. We must use cmpxchg, because -+ * another CPU might have scheduled or disabled the tasklet. -+ * We only allow the STATE_RUN -> 0 transition here. -+ */ -+ while (!tasklet_tryunlock(t)) { -+ /* -+ * If it got disabled meanwhile, bail out: -+ */ -+ if (atomic_read(&t->count)) -+ goto out_disabled; -+ /* -+ * If it got scheduled meanwhile, re-execute -+ * the tasklet function: -+ */ -+ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) -+ goto again; -+ if (!--loops) { -+ printk("hm, tasklet state: %08lx\n", t->state); -+ WARN_ON(1); -+ tasklet_unlock(t); -+ break; -+ } -+ } - } - } - -+static void tasklet_action(struct softirq_action *a) -+{ -+ struct tasklet_struct *list; -+ -+ local_irq_disable(); -+ -+ list = __this_cpu_read(tasklet_vec.head); -+ __this_cpu_write(tasklet_vec.head, NULL); -+ __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); -+ -+ local_irq_enable(); -+ -+ __tasklet_action(a, list); -+} -+ - static void tasklet_hi_action(struct softirq_action *a) - { - struct tasklet_struct *list; - - local_irq_disable(); -+ - list = __this_cpu_read(tasklet_hi_vec.head); - __this_cpu_write(tasklet_hi_vec.head, NULL); - __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head)); -- local_irq_enable(); - -- while (list) { -- struct tasklet_struct *t = list; -- -- list = list->next; -- -- if (tasklet_trylock(t)) { -- if (!atomic_read(&t->count)) { -- if (!test_and_clear_bit(TASKLET_STATE_SCHED, -- &t->state)) -- BUG(); -- t->func(t->data); -- tasklet_unlock(t); -- continue; -- } -- tasklet_unlock(t); -- } -+ local_irq_enable(); - -- local_irq_disable(); -- t->next = NULL; -- *__this_cpu_read(tasklet_hi_vec.tail) = t; -- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); -- __raise_softirq_irqoff(HI_SOFTIRQ); -- local_irq_enable(); -- } -+ __tasklet_action(a, list); - } - - void tasklet_init(struct tasklet_struct *t, -@@ -572,7 +1070,7 @@ - - while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { - do { -- yield(); -+ msleep(1); - } while (test_bit(TASKLET_STATE_SCHED, &t->state)); - } - tasklet_unlock_wait(t); -@@ -646,25 +1144,26 @@ - open_softirq(HI_SOFTIRQ, tasklet_hi_action); - } - --static int ksoftirqd_should_run(unsigned int cpu) --{ -- return local_softirq_pending(); --} -- --static void run_ksoftirqd(unsigned int cpu) -+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) -+void tasklet_unlock_wait(struct tasklet_struct *t) - { -- local_irq_disable(); -- if (local_softirq_pending()) { -+ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { - /* -- * We can safely run softirq on inline stack, as we are not deep -- * in the task stack here. -+ * Hack for now to avoid this busy-loop: - */ -- __do_softirq(); -- local_irq_enable(); -- cond_resched_rcu_qs(); -- return; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ msleep(1); -+#else -+ barrier(); -+#endif - } -- local_irq_enable(); -+} -+EXPORT_SYMBOL(tasklet_unlock_wait); -+#endif -+ -+static int ksoftirqd_should_run(unsigned int cpu) -+{ -+ return ksoftirqd_softirq_pending(); - } - - #ifdef CONFIG_HOTPLUG_CPU -@@ -746,16 +1245,31 @@ - - static struct smp_hotplug_thread softirq_threads = { - .store = &ksoftirqd, -+ .setup = ksoftirqd_set_sched_params, - .thread_should_run = ksoftirqd_should_run, - .thread_fn = run_ksoftirqd, - .thread_comm = "ksoftirqd/%u", - }; - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static struct smp_hotplug_thread softirq_timer_threads = { -+ .store = &ktimer_softirqd, -+ .setup = ktimer_softirqd_set_sched_params, -+ .cleanup = ktimer_softirqd_clr_sched_params, -+ .thread_should_run = ktimer_softirqd_should_run, -+ .thread_fn = run_ksoftirqd, -+ .thread_comm = "ktimersoftd/%u", -+}; -+#endif -+ - static __init int spawn_ksoftirqd(void) - { - register_cpu_notifier(&cpu_nfb); - - BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); -+#endif - - return 0; - } -diff -Nur linux-4.4.28.orig/kernel/stop_machine.c linux-4.4.28/kernel/stop_machine.c ---- linux-4.4.28.orig/kernel/stop_machine.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/stop_machine.c 2016-11-01 21:26:58.796343570 +0100 -@@ -37,7 +37,7 @@ - struct cpu_stopper { - struct task_struct *thread; - -- spinlock_t lock; -+ raw_spinlock_t lock; - bool enabled; /* is this stopper enabled? */ - struct list_head works; /* list of pending works */ - -@@ -86,12 +86,12 @@ - struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - unsigned long flags; - -- spin_lock_irqsave(&stopper->lock, flags); -+ raw_spin_lock_irqsave(&stopper->lock, flags); - if (stopper->enabled) - __cpu_stop_queue_work(stopper, work); - else - cpu_stop_signal_done(work->done, false); -- spin_unlock_irqrestore(&stopper->lock, flags); -+ raw_spin_unlock_irqrestore(&stopper->lock, flags); - } - - /** -@@ -224,8 +224,8 @@ - int err; - - lg_double_lock(&stop_cpus_lock, cpu1, cpu2); -- spin_lock_irq(&stopper1->lock); -- spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); -+ raw_spin_lock_irq(&stopper1->lock); -+ raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); - - err = -ENOENT; - if (!stopper1->enabled || !stopper2->enabled) -@@ -235,8 +235,8 @@ - __cpu_stop_queue_work(stopper1, work1); - __cpu_stop_queue_work(stopper2, work2); - unlock: -- spin_unlock(&stopper2->lock); -- spin_unlock_irq(&stopper1->lock); -+ raw_spin_unlock(&stopper2->lock); -+ raw_spin_unlock_irq(&stopper1->lock); - lg_double_unlock(&stop_cpus_lock, cpu1, cpu2); - - return err; -@@ -258,7 +258,7 @@ - struct cpu_stop_work work1, work2; - struct multi_stop_data msdata; - -- preempt_disable(); -+ preempt_disable_nort(); - msdata = (struct multi_stop_data){ - .fn = fn, - .data = arg, -@@ -278,11 +278,11 @@ - if (cpu1 > cpu2) - swap(cpu1, cpu2); - if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) { -- preempt_enable(); -+ preempt_enable_nort(); - return -ENOENT; - } - -- preempt_enable(); -+ preempt_enable_nort(); - - wait_for_completion(&done.completion); - -@@ -315,17 +315,20 @@ - - static void queue_stop_cpus_work(const struct cpumask *cpumask, - cpu_stop_fn_t fn, void *arg, -- struct cpu_stop_done *done) -+ struct cpu_stop_done *done, bool inactive) - { - struct cpu_stop_work *work; - unsigned int cpu; - - /* -- * Disable preemption while queueing to avoid getting -- * preempted by a stopper which might wait for other stoppers -- * to enter @fn which can lead to deadlock. -+ * Make sure that all work is queued on all cpus before -+ * any of the cpus can execute it. - */ -- lg_global_lock(&stop_cpus_lock); -+ if (!inactive) -+ lg_global_lock(&stop_cpus_lock); -+ else -+ lg_global_trylock_relax(&stop_cpus_lock); -+ - for_each_cpu(cpu, cpumask) { - work = &per_cpu(cpu_stopper.stop_work, cpu); - work->fn = fn; -@@ -342,7 +345,7 @@ - struct cpu_stop_done done; - - cpu_stop_init_done(&done, cpumask_weight(cpumask)); -- queue_stop_cpus_work(cpumask, fn, arg, &done); -+ queue_stop_cpus_work(cpumask, fn, arg, &done, false); - wait_for_completion(&done.completion); - return done.executed ? done.ret : -ENOENT; - } -@@ -422,9 +425,9 @@ - unsigned long flags; - int run; - -- spin_lock_irqsave(&stopper->lock, flags); -+ raw_spin_lock_irqsave(&stopper->lock, flags); - run = !list_empty(&stopper->works); -- spin_unlock_irqrestore(&stopper->lock, flags); -+ raw_spin_unlock_irqrestore(&stopper->lock, flags); - return run; - } - -@@ -436,13 +439,13 @@ - - repeat: - work = NULL; -- spin_lock_irq(&stopper->lock); -+ raw_spin_lock_irq(&stopper->lock); - if (!list_empty(&stopper->works)) { - work = list_first_entry(&stopper->works, - struct cpu_stop_work, list); - list_del_init(&work->list); - } -- spin_unlock_irq(&stopper->lock); -+ raw_spin_unlock_irq(&stopper->lock); - - if (work) { - cpu_stop_fn_t fn = work->fn; -@@ -450,6 +453,16 @@ - struct cpu_stop_done *done = work->done; - char ksym_buf[KSYM_NAME_LEN] __maybe_unused; - -+ /* -+ * Wait until the stopper finished scheduling on all -+ * cpus -+ */ -+ lg_global_lock(&stop_cpus_lock); -+ /* -+ * Let other cpu threads continue as well -+ */ -+ lg_global_unlock(&stop_cpus_lock); -+ - /* cpu stop callbacks are not allowed to sleep */ - preempt_disable(); - -@@ -520,10 +533,12 @@ - for_each_possible_cpu(cpu) { - struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - -- spin_lock_init(&stopper->lock); -+ raw_spin_lock_init(&stopper->lock); - INIT_LIST_HEAD(&stopper->works); - } - -+ lg_lock_init(&stop_cpus_lock, "stop_cpus_lock"); -+ - BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); - stop_machine_unpark(raw_smp_processor_id()); - stop_machine_initialized = true; -@@ -620,7 +635,7 @@ - set_state(&msdata, MULTI_STOP_PREPARE); - cpu_stop_init_done(&done, num_active_cpus()); - queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, -- &done); -+ &done, true); - ret = multi_cpu_stop(&msdata); - - /* Busy wait for completion. */ -diff -Nur linux-4.4.28.orig/kernel/time/hrtimer.c linux-4.4.28/kernel/time/hrtimer.c ---- linux-4.4.28.orig/kernel/time/hrtimer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/hrtimer.c 2016-11-01 21:26:58.796343570 +0100 -@@ -48,11 +48,13 @@ - #include - #include - #include -+#include - #include - - #include - - #include -+#include - - #include "tick-internal.h" - -@@ -717,6 +719,44 @@ - - static DECLARE_WORK(hrtimer_work, clock_was_set_work); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * RT can not call schedule_work from real interrupt context. -+ * Need to make a thread to do the real work. -+ */ -+static struct task_struct *clock_set_delay_thread; -+static bool do_clock_set_delay; -+ -+static int run_clock_set_delay(void *ignore) -+{ -+ while (!kthread_should_stop()) { -+ set_current_state(TASK_INTERRUPTIBLE); -+ if (do_clock_set_delay) { -+ do_clock_set_delay = false; -+ schedule_work(&hrtimer_work); -+ } -+ schedule(); -+ } -+ __set_current_state(TASK_RUNNING); -+ return 0; -+} -+ -+void clock_was_set_delayed(void) -+{ -+ do_clock_set_delay = true; -+ /* Make visible before waking up process */ -+ smp_wmb(); -+ wake_up_process(clock_set_delay_thread); -+} -+ -+static __init int create_clock_set_delay_thread(void) -+{ -+ clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); -+ BUG_ON(!clock_set_delay_thread); -+ return 0; -+} -+early_initcall(create_clock_set_delay_thread); -+#else /* PREEMPT_RT_FULL */ - /* - * Called from timekeeping and resume code to reprogramm the hrtimer - * interrupt device on all cpus. -@@ -725,6 +765,7 @@ - { - schedule_work(&hrtimer_work); - } -+#endif - - #else - -@@ -734,11 +775,8 @@ - static inline void hrtimer_switch_to_hres(void) { } - static inline void - hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } --static inline int hrtimer_reprogram(struct hrtimer *timer, -- struct hrtimer_clock_base *base) --{ -- return 0; --} -+static inline void hrtimer_reprogram(struct hrtimer *timer, -+ struct hrtimer_clock_base *base) { } - static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } - static inline void retrigger_next_event(void *arg) { } - -@@ -870,6 +908,32 @@ - } - EXPORT_SYMBOL_GPL(hrtimer_forward); - -+#ifdef CONFIG_PREEMPT_RT_BASE -+# define wake_up_timer_waiters(b) wake_up(&(b)->wait) -+ -+/** -+ * hrtimer_wait_for_timer - Wait for a running timer -+ * -+ * @timer: timer to wait for -+ * -+ * The function waits in case the timers callback function is -+ * currently executed on the waitqueue of the timer base. The -+ * waitqueue is woken up after the timer callback function has -+ * finished execution. -+ */ -+void hrtimer_wait_for_timer(const struct hrtimer *timer) -+{ -+ struct hrtimer_clock_base *base = timer->base; -+ -+ if (base && base->cpu_base && !timer->irqsafe) -+ wait_event(base->cpu_base->wait, -+ !(hrtimer_callback_running(timer))); -+} -+ -+#else -+# define wake_up_timer_waiters(b) do { } while (0) -+#endif -+ - /* - * enqueue_hrtimer - internal function to (re)start a timer - * -@@ -911,6 +975,11 @@ - if (!(state & HRTIMER_STATE_ENQUEUED)) - return; - -+ if (unlikely(!list_empty(&timer->cb_entry))) { -+ list_del_init(&timer->cb_entry); -+ return; -+ } -+ - if (!timerqueue_del(&base->active, &timer->node)) - cpu_base->active_bases &= ~(1 << base->index); - -@@ -1006,7 +1075,16 @@ - new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); - - timer_stats_hrtimer_set_start_info(timer); -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ { -+ ktime_t now = new_base->get_time(); - -+ if (ktime_to_ns(tim) < ktime_to_ns(now)) -+ timer->praecox = now; -+ else -+ timer->praecox = ktime_set(0, 0); -+ } -+#endif - leftmost = enqueue_hrtimer(timer, new_base); - if (!leftmost) - goto unlock; -@@ -1078,7 +1156,7 @@ - - if (ret >= 0) - return ret; -- cpu_relax(); -+ hrtimer_wait_for_timer(timer); - } - } - EXPORT_SYMBOL_GPL(hrtimer_cancel); -@@ -1142,6 +1220,7 @@ - - base = hrtimer_clockid_to_base(clock_id); - timer->base = &cpu_base->clock_base[base]; -+ INIT_LIST_HEAD(&timer->cb_entry); - timerqueue_init(&timer->node); - - #ifdef CONFIG_TIMER_STATS -@@ -1182,6 +1261,7 @@ - seq = raw_read_seqcount_begin(&cpu_base->seq); - - if (timer->state != HRTIMER_STATE_INACTIVE || -+ cpu_base->running_soft == timer || - cpu_base->running == timer) - return true; - -@@ -1280,10 +1360,112 @@ - cpu_base->running = NULL; - } - -+#ifdef CONFIG_PREEMPT_RT_BASE -+static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, -+ struct hrtimer_clock_base *base) -+{ -+ int leftmost; -+ -+ if (restart != HRTIMER_NORESTART && -+ !(timer->state & HRTIMER_STATE_ENQUEUED)) { -+ -+ leftmost = enqueue_hrtimer(timer, base); -+ if (!leftmost) -+ return; -+#ifdef CONFIG_HIGH_RES_TIMERS -+ if (!hrtimer_is_hres_active(timer)) { -+ /* -+ * Kick to reschedule the next tick to handle the new timer -+ * on dynticks target. -+ */ -+ if (base->cpu_base->nohz_active) -+ wake_up_nohz_cpu(base->cpu_base->cpu); -+ } else { -+ -+ hrtimer_reprogram(timer, base); -+ } -+#endif -+ } -+} -+ -+/* -+ * The changes in mainline which removed the callback modes from -+ * hrtimer are not yet working with -rt. The non wakeup_process() -+ * based callbacks which involve sleeping locks need to be treated -+ * seperately. -+ */ -+static void hrtimer_rt_run_pending(void) -+{ -+ enum hrtimer_restart (*fn)(struct hrtimer *); -+ struct hrtimer_cpu_base *cpu_base; -+ struct hrtimer_clock_base *base; -+ struct hrtimer *timer; -+ int index, restart; -+ -+ local_irq_disable(); -+ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); -+ -+ raw_spin_lock(&cpu_base->lock); -+ -+ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { -+ base = &cpu_base->clock_base[index]; -+ -+ while (!list_empty(&base->expired)) { -+ timer = list_first_entry(&base->expired, -+ struct hrtimer, cb_entry); -+ -+ /* -+ * Same as the above __run_hrtimer function -+ * just we run with interrupts enabled. -+ */ -+ debug_deactivate(timer); -+ cpu_base->running_soft = timer; -+ raw_write_seqcount_barrier(&cpu_base->seq); -+ -+ __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); -+ timer_stats_account_hrtimer(timer); -+ fn = timer->function; -+ -+ raw_spin_unlock_irq(&cpu_base->lock); -+ restart = fn(timer); -+ raw_spin_lock_irq(&cpu_base->lock); -+ -+ hrtimer_rt_reprogram(restart, timer, base); -+ raw_write_seqcount_barrier(&cpu_base->seq); -+ -+ WARN_ON_ONCE(cpu_base->running_soft != timer); -+ cpu_base->running_soft = NULL; -+ } -+ } -+ -+ raw_spin_unlock_irq(&cpu_base->lock); -+ -+ wake_up_timer_waiters(cpu_base); -+} -+ -+static int hrtimer_rt_defer(struct hrtimer *timer) -+{ -+ if (timer->irqsafe) -+ return 0; -+ -+ __remove_hrtimer(timer, timer->base, timer->state, 0); -+ list_add_tail(&timer->cb_entry, &timer->base->expired); -+ return 1; -+} -+ -+#else -+ -+static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } -+ -+#endif -+ -+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); -+ - static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now) - { - struct hrtimer_clock_base *base = cpu_base->clock_base; - unsigned int active = cpu_base->active_bases; -+ int raise = 0; - - for (; active; base++, active >>= 1) { - struct timerqueue_node *node; -@@ -1299,6 +1481,15 @@ - - timer = container_of(node, struct hrtimer, node); - -+ trace_hrtimer_interrupt(raw_smp_processor_id(), -+ ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? -+ timer->praecox : hrtimer_get_expires(timer), -+ basenow)), -+ current, -+ timer->function == hrtimer_wakeup ? -+ container_of(timer, struct hrtimer_sleeper, -+ timer)->task : NULL); -+ - /* - * The immediate goal for using the softexpires is - * minimizing wakeups, not running timers at the -@@ -1314,9 +1505,14 @@ - if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) - break; - -- __run_hrtimer(cpu_base, base, timer, &basenow); -+ if (!hrtimer_rt_defer(timer)) -+ __run_hrtimer(cpu_base, base, timer, &basenow); -+ else -+ raise = 1; - } - } -+ if (raise) -+ raise_softirq_irqoff(HRTIMER_SOFTIRQ); - } - - #ifdef CONFIG_HIGH_RES_TIMERS -@@ -1479,16 +1675,18 @@ - void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) - { - sl->timer.function = hrtimer_wakeup; -+ sl->timer.irqsafe = 1; - sl->task = task; - } - EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); - --static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) -+static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, -+ unsigned long state) - { - hrtimer_init_sleeper(t, current); - - do { -- set_current_state(TASK_INTERRUPTIBLE); -+ set_current_state(state); - hrtimer_start_expires(&t->timer, mode); - - if (likely(t->task)) -@@ -1530,7 +1728,8 @@ - HRTIMER_MODE_ABS); - hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); - -- if (do_nanosleep(&t, HRTIMER_MODE_ABS)) -+ /* cpu_chill() does not care about restart state. */ -+ if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) - goto out; - - rmtp = restart->nanosleep.rmtp; -@@ -1547,8 +1746,10 @@ - return ret; - } - --long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, -- const enum hrtimer_mode mode, const clockid_t clockid) -+static long -+__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, -+ const enum hrtimer_mode mode, const clockid_t clockid, -+ unsigned long state) - { - struct restart_block *restart; - struct hrtimer_sleeper t; -@@ -1561,7 +1762,7 @@ - - hrtimer_init_on_stack(&t.timer, clockid, mode); - hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); -- if (do_nanosleep(&t, mode)) -+ if (do_nanosleep(&t, mode, state)) - goto out; - - /* Absolute timers do not update the rmtp value and restart: */ -@@ -1588,6 +1789,12 @@ - return ret; - } - -+long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, -+ const enum hrtimer_mode mode, const clockid_t clockid) -+{ -+ return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); -+} -+ - SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, - struct timespec __user *, rmtp) - { -@@ -1602,6 +1809,26 @@ - return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * Sleep for 1 ms in hope whoever holds what we want will let it go. -+ */ -+void cpu_chill(void) -+{ -+ struct timespec tu = { -+ .tv_nsec = NSEC_PER_MSEC, -+ }; -+ unsigned int freeze_flag = current->flags & PF_NOFREEZE; -+ -+ current->flags |= PF_NOFREEZE; -+ __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, -+ TASK_UNINTERRUPTIBLE); -+ if (!freeze_flag) -+ current->flags &= ~PF_NOFREEZE; -+} -+EXPORT_SYMBOL(cpu_chill); -+#endif -+ - /* - * Functions related to boot-time initialization: - */ -@@ -1613,10 +1840,14 @@ - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { - cpu_base->clock_base[i].cpu_base = cpu_base; - timerqueue_init_head(&cpu_base->clock_base[i].active); -+ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); - } - - cpu_base->cpu = cpu; - hrtimer_init_hres(cpu_base); -+#ifdef CONFIG_PREEMPT_RT_BASE -+ init_waitqueue_head(&cpu_base->wait); -+#endif - } - - #ifdef CONFIG_HOTPLUG_CPU -@@ -1714,11 +1945,21 @@ - .notifier_call = hrtimer_cpu_notify, - }; - -+#ifdef CONFIG_PREEMPT_RT_BASE -+static void run_hrtimer_softirq(struct softirq_action *h) -+{ -+ hrtimer_rt_run_pending(); -+} -+#endif -+ - void __init hrtimers_init(void) - { - hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); - register_cpu_notifier(&hrtimers_nb); -+#ifdef CONFIG_PREEMPT_RT_BASE -+ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); -+#endif - } - - /** -diff -Nur linux-4.4.28.orig/kernel/time/itimer.c linux-4.4.28/kernel/time/itimer.c ---- linux-4.4.28.orig/kernel/time/itimer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/itimer.c 2016-11-01 21:26:58.796343570 +0100 -@@ -213,6 +213,7 @@ - /* We are sharing ->siglock with it_real_fn() */ - if (hrtimer_try_to_cancel(timer) < 0) { - spin_unlock_irq(&tsk->sighand->siglock); -+ hrtimer_wait_for_timer(&tsk->signal->real_timer); - goto again; - } - expires = timeval_to_ktime(value->it_value); -diff -Nur linux-4.4.28.orig/kernel/time/jiffies.c linux-4.4.28/kernel/time/jiffies.c ---- linux-4.4.28.orig/kernel/time/jiffies.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/jiffies.c 2016-11-01 21:26:58.796343570 +0100 -@@ -74,7 +74,8 @@ - .max_cycles = 10, - }; - --__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); -+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); -+__cacheline_aligned_in_smp seqcount_t jiffies_seq; - - #if (BITS_PER_LONG < 64) - u64 get_jiffies_64(void) -@@ -83,9 +84,9 @@ - u64 ret; - - do { -- seq = read_seqbegin(&jiffies_lock); -+ seq = read_seqcount_begin(&jiffies_seq); - ret = jiffies_64; -- } while (read_seqretry(&jiffies_lock, seq)); -+ } while (read_seqcount_retry(&jiffies_seq, seq)); - return ret; - } - EXPORT_SYMBOL(get_jiffies_64); -diff -Nur linux-4.4.28.orig/kernel/time/ntp.c linux-4.4.28/kernel/time/ntp.c ---- linux-4.4.28.orig/kernel/time/ntp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/ntp.c 2016-11-01 21:26:58.796343570 +0100 -@@ -10,6 +10,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -562,10 +563,52 @@ - &sync_cmos_work, timespec64_to_jiffies(&next)); - } - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * RT can not call schedule_delayed_work from real interrupt context. -+ * Need to make a thread to do the real work. -+ */ -+static struct task_struct *cmos_delay_thread; -+static bool do_cmos_delay; -+ -+static int run_cmos_delay(void *ignore) -+{ -+ while (!kthread_should_stop()) { -+ set_current_state(TASK_INTERRUPTIBLE); -+ if (do_cmos_delay) { -+ do_cmos_delay = false; -+ queue_delayed_work(system_power_efficient_wq, -+ &sync_cmos_work, 0); -+ } -+ schedule(); -+ } -+ __set_current_state(TASK_RUNNING); -+ return 0; -+} -+ -+void ntp_notify_cmos_timer(void) -+{ -+ do_cmos_delay = true; -+ /* Make visible before waking up process */ -+ smp_wmb(); -+ wake_up_process(cmos_delay_thread); -+} -+ -+static __init int create_cmos_delay_thread(void) -+{ -+ cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); -+ BUG_ON(!cmos_delay_thread); -+ return 0; -+} -+early_initcall(create_cmos_delay_thread); -+ -+#else -+ - void ntp_notify_cmos_timer(void) - { - queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); - } -+#endif /* CONFIG_PREEMPT_RT_FULL */ - - #else - void ntp_notify_cmos_timer(void) { } -diff -Nur linux-4.4.28.orig/kernel/time/posix-cpu-timers.c linux-4.4.28/kernel/time/posix-cpu-timers.c ---- linux-4.4.28.orig/kernel/time/posix-cpu-timers.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/posix-cpu-timers.c 2016-11-01 21:26:58.800343826 +0100 -@@ -3,6 +3,7 @@ - */ - - #include -+#include - #include - #include - #include -@@ -650,7 +651,7 @@ - /* - * Disarm any old timer after extracting its expiry time. - */ -- WARN_ON_ONCE(!irqs_disabled()); -+ WARN_ON_ONCE_NONRT(!irqs_disabled()); - - ret = 0; - old_incr = timer->it.cpu.incr; -@@ -1092,7 +1093,7 @@ - /* - * Now re-arm for the new expiry time. - */ -- WARN_ON_ONCE(!irqs_disabled()); -+ WARN_ON_ONCE_NONRT(!irqs_disabled()); - arm_timer(timer); - unlock_task_sighand(p, &flags); - -@@ -1183,13 +1184,13 @@ - * already updated our counts. We need to check if any timers fire now. - * Interrupts are disabled. - */ --void run_posix_cpu_timers(struct task_struct *tsk) -+static void __run_posix_cpu_timers(struct task_struct *tsk) - { - LIST_HEAD(firing); - struct k_itimer *timer, *next; - unsigned long flags; - -- WARN_ON_ONCE(!irqs_disabled()); -+ WARN_ON_ONCE_NONRT(!irqs_disabled()); - - /* - * The fast path checks that there are no expired thread or thread -@@ -1243,6 +1244,190 @@ - } - } - -+#ifdef CONFIG_PREEMPT_RT_BASE -+#include -+#include -+DEFINE_PER_CPU(struct task_struct *, posix_timer_task); -+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); -+ -+static int posix_cpu_timers_thread(void *data) -+{ -+ int cpu = (long)data; -+ -+ BUG_ON(per_cpu(posix_timer_task,cpu) != current); -+ -+ while (!kthread_should_stop()) { -+ struct task_struct *tsk = NULL; -+ struct task_struct *next = NULL; -+ -+ if (cpu_is_offline(cpu)) -+ goto wait_to_die; -+ -+ /* grab task list */ -+ raw_local_irq_disable(); -+ tsk = per_cpu(posix_timer_tasklist, cpu); -+ per_cpu(posix_timer_tasklist, cpu) = NULL; -+ raw_local_irq_enable(); -+ -+ /* its possible the list is empty, just return */ -+ if (!tsk) { -+ set_current_state(TASK_INTERRUPTIBLE); -+ schedule(); -+ __set_current_state(TASK_RUNNING); -+ continue; -+ } -+ -+ /* Process task list */ -+ while (1) { -+ /* save next */ -+ next = tsk->posix_timer_list; -+ -+ /* run the task timers, clear its ptr and -+ * unreference it -+ */ -+ __run_posix_cpu_timers(tsk); -+ tsk->posix_timer_list = NULL; -+ put_task_struct(tsk); -+ -+ /* check if this is the last on the list */ -+ if (next == tsk) -+ break; -+ tsk = next; -+ } -+ } -+ return 0; -+ -+wait_to_die: -+ /* Wait for kthread_stop */ -+ set_current_state(TASK_INTERRUPTIBLE); -+ while (!kthread_should_stop()) { -+ schedule(); -+ set_current_state(TASK_INTERRUPTIBLE); -+ } -+ __set_current_state(TASK_RUNNING); -+ return 0; -+} -+ -+static inline int __fastpath_timer_check(struct task_struct *tsk) -+{ -+ /* tsk == current, ensure it is safe to use ->signal/sighand */ -+ if (unlikely(tsk->exit_state)) -+ return 0; -+ -+ if (!task_cputime_zero(&tsk->cputime_expires)) -+ return 1; -+ -+ if (!task_cputime_zero(&tsk->signal->cputime_expires)) -+ return 1; -+ -+ return 0; -+} -+ -+void run_posix_cpu_timers(struct task_struct *tsk) -+{ -+ unsigned long cpu = smp_processor_id(); -+ struct task_struct *tasklist; -+ -+ BUG_ON(!irqs_disabled()); -+ if(!per_cpu(posix_timer_task, cpu)) -+ return; -+ /* get per-cpu references */ -+ tasklist = per_cpu(posix_timer_tasklist, cpu); -+ -+ /* check to see if we're already queued */ -+ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { -+ get_task_struct(tsk); -+ if (tasklist) { -+ tsk->posix_timer_list = tasklist; -+ } else { -+ /* -+ * The list is terminated by a self-pointing -+ * task_struct -+ */ -+ tsk->posix_timer_list = tsk; -+ } -+ per_cpu(posix_timer_tasklist, cpu) = tsk; -+ -+ wake_up_process(per_cpu(posix_timer_task, cpu)); -+ } -+} -+ -+/* -+ * posix_cpu_thread_call - callback that gets triggered when a CPU is added. -+ * Here we can start up the necessary migration thread for the new CPU. -+ */ -+static int posix_cpu_thread_call(struct notifier_block *nfb, -+ unsigned long action, void *hcpu) -+{ -+ int cpu = (long)hcpu; -+ struct task_struct *p; -+ struct sched_param param; -+ -+ switch (action) { -+ case CPU_UP_PREPARE: -+ p = kthread_create(posix_cpu_timers_thread, hcpu, -+ "posixcputmr/%d",cpu); -+ if (IS_ERR(p)) -+ return NOTIFY_BAD; -+ p->flags |= PF_NOFREEZE; -+ kthread_bind(p, cpu); -+ /* Must be high prio to avoid getting starved */ -+ param.sched_priority = MAX_RT_PRIO-1; -+ sched_setscheduler(p, SCHED_FIFO, ¶m); -+ per_cpu(posix_timer_task,cpu) = p; -+ break; -+ case CPU_ONLINE: -+ /* Strictly unneccessary, as first user will wake it. */ -+ wake_up_process(per_cpu(posix_timer_task,cpu)); -+ break; -+#ifdef CONFIG_HOTPLUG_CPU -+ case CPU_UP_CANCELED: -+ /* Unbind it from offline cpu so it can run. Fall thru. */ -+ kthread_bind(per_cpu(posix_timer_task, cpu), -+ cpumask_any(cpu_online_mask)); -+ kthread_stop(per_cpu(posix_timer_task,cpu)); -+ per_cpu(posix_timer_task,cpu) = NULL; -+ break; -+ case CPU_DEAD: -+ kthread_stop(per_cpu(posix_timer_task,cpu)); -+ per_cpu(posix_timer_task,cpu) = NULL; -+ break; -+#endif -+ } -+ return NOTIFY_OK; -+} -+ -+/* Register at highest priority so that task migration (migrate_all_tasks) -+ * happens before everything else. -+ */ -+static struct notifier_block posix_cpu_thread_notifier = { -+ .notifier_call = posix_cpu_thread_call, -+ .priority = 10 -+}; -+ -+static int __init posix_cpu_thread_init(void) -+{ -+ void *hcpu = (void *)(long)smp_processor_id(); -+ /* Start one for boot CPU. */ -+ unsigned long cpu; -+ -+ /* init the per-cpu posix_timer_tasklets */ -+ for_each_possible_cpu(cpu) -+ per_cpu(posix_timer_tasklist, cpu) = NULL; -+ -+ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); -+ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); -+ register_cpu_notifier(&posix_cpu_thread_notifier); -+ return 0; -+} -+early_initcall(posix_cpu_thread_init); -+#else /* CONFIG_PREEMPT_RT_BASE */ -+void run_posix_cpu_timers(struct task_struct *tsk) -+{ -+ __run_posix_cpu_timers(tsk); -+} -+#endif /* CONFIG_PREEMPT_RT_BASE */ -+ - /* - * Set one of the process-wide special case CPU timers or RLIMIT_CPU. - * The tsk->sighand->siglock must be held by the caller. -diff -Nur linux-4.4.28.orig/kernel/time/posix-timers.c linux-4.4.28/kernel/time/posix-timers.c ---- linux-4.4.28.orig/kernel/time/posix-timers.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/posix-timers.c 2016-11-01 21:26:58.800343826 +0100 -@@ -506,6 +506,7 @@ - static struct pid *good_sigevent(sigevent_t * event) - { - struct task_struct *rtn = current->group_leader; -+ int sig = event->sigev_signo; - - if ((event->sigev_notify & SIGEV_THREAD_ID ) && - (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || -@@ -514,7 +515,8 @@ - return NULL; - - if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && -- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) -+ (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || -+ sig_kernel_coredump(sig))) - return NULL; - - return task_pid(rtn); -@@ -826,6 +828,20 @@ - return overrun; - } - -+/* -+ * Protected by RCU! -+ */ -+static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) -+{ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (kc->timer_set == common_timer_set) -+ hrtimer_wait_for_timer(&timr->it.real.timer); -+ else -+ /* FIXME: Whacky hack for posix-cpu-timers */ -+ schedule_timeout(1); -+#endif -+} -+ - /* Set a POSIX.1b interval timer. */ - /* timr->it_lock is taken. */ - static int -@@ -903,6 +919,7 @@ - if (!timr) - return -EINVAL; - -+ rcu_read_lock(); - kc = clockid_to_kclock(timr->it_clock); - if (WARN_ON_ONCE(!kc || !kc->timer_set)) - error = -EINVAL; -@@ -911,9 +928,12 @@ - - unlock_timer(timr, flag); - if (error == TIMER_RETRY) { -+ timer_wait_for_callback(kc, timr); - rtn = NULL; // We already got the old time... -+ rcu_read_unlock(); - goto retry; - } -+ rcu_read_unlock(); - - if (old_setting && !error && - copy_to_user(old_setting, &old_spec, sizeof (old_spec))) -@@ -951,10 +971,15 @@ - if (!timer) - return -EINVAL; - -+ rcu_read_lock(); - if (timer_delete_hook(timer) == TIMER_RETRY) { - unlock_timer(timer, flags); -+ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), -+ timer); -+ rcu_read_unlock(); - goto retry_delete; - } -+ rcu_read_unlock(); - - spin_lock(¤t->sighand->siglock); - list_del(&timer->list); -@@ -980,8 +1005,18 @@ - retry_delete: - spin_lock_irqsave(&timer->it_lock, flags); - -+ /* On RT we can race with a deletion */ -+ if (!timer->it_signal) { -+ unlock_timer(timer, flags); -+ return; -+ } -+ - if (timer_delete_hook(timer) == TIMER_RETRY) { -+ rcu_read_lock(); - unlock_timer(timer, flags); -+ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), -+ timer); -+ rcu_read_unlock(); - goto retry_delete; - } - list_del(&timer->list); -diff -Nur linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c ---- linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c 2016-11-01 21:26:58.800343826 +0100 -@@ -106,5 +106,6 @@ - { - hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - bctimer.function = bc_handler; -+ bctimer.irqsafe = true; - clockevents_register_device(&ce_broadcast_hrtimer); - } -diff -Nur linux-4.4.28.orig/kernel/time/tick-common.c linux-4.4.28/kernel/time/tick-common.c ---- linux-4.4.28.orig/kernel/time/tick-common.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/tick-common.c 2016-11-01 21:26:58.800343826 +0100 -@@ -79,13 +79,15 @@ - static void tick_periodic(int cpu) - { - if (tick_do_timer_cpu == cpu) { -- write_seqlock(&jiffies_lock); -+ raw_spin_lock(&jiffies_lock); -+ write_seqcount_begin(&jiffies_seq); - - /* Keep track of the next tick event */ - tick_next_period = ktime_add(tick_next_period, tick_period); - - do_timer(1); -- write_sequnlock(&jiffies_lock); -+ write_seqcount_end(&jiffies_seq); -+ raw_spin_unlock(&jiffies_lock); - update_wall_time(); - } - -@@ -157,9 +159,9 @@ - ktime_t next; - - do { -- seq = read_seqbegin(&jiffies_lock); -+ seq = read_seqcount_begin(&jiffies_seq); - next = tick_next_period; -- } while (read_seqretry(&jiffies_lock, seq)); -+ } while (read_seqcount_retry(&jiffies_seq, seq)); - - clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); - -diff -Nur linux-4.4.28.orig/kernel/time/tick-sched.c linux-4.4.28/kernel/time/tick-sched.c ---- linux-4.4.28.orig/kernel/time/tick-sched.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/tick-sched.c 2016-11-01 21:26:58.800343826 +0100 -@@ -62,7 +62,8 @@ - return; - - /* Reevalute with jiffies_lock held */ -- write_seqlock(&jiffies_lock); -+ raw_spin_lock(&jiffies_lock); -+ write_seqcount_begin(&jiffies_seq); - - delta = ktime_sub(now, last_jiffies_update); - if (delta.tv64 >= tick_period.tv64) { -@@ -85,10 +86,12 @@ - /* Keep the tick_next_period variable up to date */ - tick_next_period = ktime_add(last_jiffies_update, tick_period); - } else { -- write_sequnlock(&jiffies_lock); -+ write_seqcount_end(&jiffies_seq); -+ raw_spin_unlock(&jiffies_lock); - return; - } -- write_sequnlock(&jiffies_lock); -+ write_seqcount_end(&jiffies_seq); -+ raw_spin_unlock(&jiffies_lock); - update_wall_time(); - } - -@@ -99,12 +102,14 @@ - { - ktime_t period; - -- write_seqlock(&jiffies_lock); -+ raw_spin_lock(&jiffies_lock); -+ write_seqcount_begin(&jiffies_seq); - /* Did we start the jiffies update yet ? */ - if (last_jiffies_update.tv64 == 0) - last_jiffies_update = tick_next_period; - period = last_jiffies_update; -- write_sequnlock(&jiffies_lock); -+ write_seqcount_end(&jiffies_seq); -+ raw_spin_unlock(&jiffies_lock); - return period; - } - -@@ -176,6 +181,11 @@ - return false; - } - -+ if (!arch_irq_work_has_interrupt()) { -+ trace_tick_stop(0, "missing irq work interrupt\n"); -+ return false; -+ } -+ - /* sched_clock_tick() needs us? */ - #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK - /* -@@ -204,6 +214,7 @@ - - static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { - .func = nohz_full_kick_work_func, -+ .flags = IRQ_WORK_HARD_IRQ, - }; - - /* -@@ -578,10 +589,10 @@ - - /* Read jiffies and the time when jiffies were updated last */ - do { -- seq = read_seqbegin(&jiffies_lock); -+ seq = read_seqcount_begin(&jiffies_seq); - basemono = last_jiffies_update.tv64; - basejiff = jiffies; -- } while (read_seqretry(&jiffies_lock, seq)); -+ } while (read_seqcount_retry(&jiffies_seq, seq)); - ts->last_jiffies = basejiff; - - if (rcu_needs_cpu(basemono, &next_rcu) || -@@ -753,14 +764,7 @@ - return false; - - if (unlikely(local_softirq_pending() && cpu_online(cpu))) { -- static int ratelimit; -- -- if (ratelimit < 10 && -- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { -- pr_warn("NOHZ: local_softirq_pending %02x\n", -- (unsigned int) local_softirq_pending()); -- ratelimit++; -- } -+ softirq_check_pending_idle(); - return false; - } - -@@ -1100,6 +1104,7 @@ - * Emulate tick processing via per-CPU hrtimers: - */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); -+ ts->sched_timer.irqsafe = 1; - ts->sched_timer.function = tick_sched_timer; - - /* Get the next period (per cpu) */ -diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.c linux-4.4.28/kernel/time/timekeeping.c ---- linux-4.4.28.orig/kernel/time/timekeeping.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/timekeeping.c 2016-11-01 21:26:58.800343826 +0100 -@@ -2070,8 +2070,10 @@ - */ - void xtime_update(unsigned long ticks) - { -- write_seqlock(&jiffies_lock); -+ raw_spin_lock(&jiffies_lock); -+ write_seqcount_begin(&jiffies_seq); - do_timer(ticks); -- write_sequnlock(&jiffies_lock); -+ write_seqcount_end(&jiffies_seq); -+ raw_spin_unlock(&jiffies_lock); - update_wall_time(); - } -diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.h linux-4.4.28/kernel/time/timekeeping.h ---- linux-4.4.28.orig/kernel/time/timekeeping.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/timekeeping.h 2016-11-01 21:26:58.800343826 +0100 -@@ -19,7 +19,8 @@ - extern void do_timer(unsigned long ticks); - extern void update_wall_time(void); - --extern seqlock_t jiffies_lock; -+extern raw_spinlock_t jiffies_lock; -+extern seqcount_t jiffies_seq; - - #define CS_NAME_LEN 32 - -diff -Nur linux-4.4.28.orig/kernel/time/timer.c linux-4.4.28/kernel/time/timer.c ---- linux-4.4.28.orig/kernel/time/timer.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/time/timer.c 2016-11-01 21:26:58.804344090 +0100 -@@ -80,6 +80,9 @@ - struct tvec_base { - spinlock_t lock; - struct timer_list *running_timer; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ wait_queue_head_t wait_for_running_timer; -+#endif - unsigned long timer_jiffies; - unsigned long next_timer; - unsigned long active_timers; -@@ -777,6 +780,39 @@ - cpu_relax(); - } - } -+#ifdef CONFIG_PREEMPT_RT_FULL -+static inline struct tvec_base *switch_timer_base(struct timer_list *timer, -+ struct tvec_base *old, -+ struct tvec_base *new) -+{ -+ /* -+ * We cannot do the below because we might be preempted and -+ * then the preempter would see NULL and loop forever. -+ */ -+ if (spin_trylock(&new->lock)) { -+ WRITE_ONCE(timer->flags, -+ (timer->flags & ~TIMER_BASEMASK) | new->cpu); -+ spin_unlock(&old->lock); -+ return new; -+ } -+ return old; -+} -+ -+#else -+static inline struct tvec_base *switch_timer_base(struct timer_list *timer, -+ struct tvec_base *old, -+ struct tvec_base *new) -+{ -+ /* See the comment in lock_timer_base() */ -+ timer->flags |= TIMER_MIGRATING; -+ -+ spin_unlock(&old->lock); -+ spin_lock(&new->lock); -+ WRITE_ONCE(timer->flags, -+ (timer->flags & ~TIMER_BASEMASK) | new->cpu); -+ return new; -+} -+#endif - - static inline int - __mod_timer(struct timer_list *timer, unsigned long expires, -@@ -807,16 +843,8 @@ - * handler yet has not finished. This also guarantees that - * the timer is serialized wrt itself. - */ -- if (likely(base->running_timer != timer)) { -- /* See the comment in lock_timer_base() */ -- timer->flags |= TIMER_MIGRATING; -- -- spin_unlock(&base->lock); -- base = new_base; -- spin_lock(&base->lock); -- WRITE_ONCE(timer->flags, -- (timer->flags & ~TIMER_BASEMASK) | base->cpu); -- } -+ if (likely(base->running_timer != timer)) -+ base = switch_timer_base(timer, base, new_base); - } - - timer->expires = expires; -@@ -1006,6 +1034,33 @@ - } - EXPORT_SYMBOL_GPL(add_timer_on); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * Wait for a running timer -+ */ -+static void wait_for_running_timer(struct timer_list *timer) -+{ -+ struct tvec_base *base; -+ u32 tf = timer->flags; -+ -+ if (tf & TIMER_MIGRATING) -+ return; -+ -+ base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK); -+ wait_event(base->wait_for_running_timer, -+ base->running_timer != timer); -+} -+ -+# define wakeup_timer_waiters(b) wake_up_all(&(b)->wait_for_running_timer) -+#else -+static inline void wait_for_running_timer(struct timer_list *timer) -+{ -+ cpu_relax(); -+} -+ -+# define wakeup_timer_waiters(b) do { } while (0) -+#endif -+ - /** - * del_timer - deactive a timer. - * @timer: the timer to be deactivated -@@ -1063,7 +1118,7 @@ - } - EXPORT_SYMBOL(try_to_del_timer_sync); - --#ifdef CONFIG_SMP -+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) - /** - * del_timer_sync - deactivate a timer and wait for the handler to finish. - * @timer: the timer to be deactivated -@@ -1123,7 +1178,7 @@ - int ret = try_to_del_timer_sync(timer); - if (ret >= 0) - return ret; -- cpu_relax(); -+ wait_for_running_timer(timer); - } - } - EXPORT_SYMBOL(del_timer_sync); -@@ -1248,16 +1303,18 @@ - if (irqsafe) { - spin_unlock(&base->lock); - call_timer_fn(timer, fn, data); -+ base->running_timer = NULL; - spin_lock(&base->lock); - } else { - spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn, data); -+ base->running_timer = NULL; - spin_lock_irq(&base->lock); - } - } - } -- base->running_timer = NULL; - spin_unlock_irq(&base->lock); -+ wakeup_timer_waiters(base); - } - - #ifdef CONFIG_NO_HZ_COMMON -@@ -1390,6 +1447,14 @@ - if (cpu_is_offline(smp_processor_id())) - return expires; - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ /* -+ * On PREEMPT_RT we cannot sleep here. As a result we can't take -+ * the base lock to check when the next timer is pending and so -+ * we assume the next jiffy. -+ */ -+ return basem + TICK_NSEC; -+#endif - spin_lock(&base->lock); - if (base->active_timers) { - if (time_before_eq(base->next_timer, base->timer_jiffies)) -@@ -1416,13 +1481,13 @@ - - /* Note: this timer irq context must be accounted for as well. */ - account_process_tick(p, user_tick); -+ scheduler_tick(); - run_local_timers(); - rcu_check_callbacks(user_tick); --#ifdef CONFIG_IRQ_WORK -+#if defined(CONFIG_IRQ_WORK) - if (in_irq()) - irq_work_tick(); - #endif -- scheduler_tick(); - run_posix_cpu_timers(p); - } - -@@ -1433,6 +1498,8 @@ - { - struct tvec_base *base = this_cpu_ptr(&tvec_bases); - -+ irq_work_tick_soft(); -+ - if (time_after_eq(jiffies, base->timer_jiffies)) - __run_timers(base); - } -@@ -1589,7 +1656,7 @@ - - BUG_ON(cpu_online(cpu)); - old_base = per_cpu_ptr(&tvec_bases, cpu); -- new_base = get_cpu_ptr(&tvec_bases); -+ new_base = get_local_ptr(&tvec_bases); - /* - * The caller is globally serialized and nobody else - * takes two locks at once, deadlock is not possible. -@@ -1613,7 +1680,7 @@ - - spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); -- put_cpu_ptr(&tvec_bases); -+ put_local_ptr(&tvec_bases); - } - - static int timer_cpu_notify(struct notifier_block *self, -@@ -1645,6 +1712,9 @@ - - base->cpu = cpu; - spin_lock_init(&base->lock); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ init_waitqueue_head(&base->wait_for_running_timer); -+#endif - - base->timer_jiffies = jiffies; - base->next_timer = base->timer_jiffies; -diff -Nur linux-4.4.28.orig/kernel/trace/Kconfig linux-4.4.28/kernel/trace/Kconfig ---- linux-4.4.28.orig/kernel/trace/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/Kconfig 2016-11-01 21:26:58.804344090 +0100 -@@ -187,6 +187,24 @@ - enabled. This option and the preempt-off timing option can be - used together or separately.) - -+config INTERRUPT_OFF_HIST -+ bool "Interrupts-off Latency Histogram" -+ depends on IRQSOFF_TRACER -+ help -+ This option generates continuously updated histograms (one per cpu) -+ of the duration of time periods with interrupts disabled. The -+ histograms are disabled by default. To enable them, write a non-zero -+ number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff -+ -+ If PREEMPT_OFF_HIST is also selected, additional histograms (one -+ per cpu) are generated that accumulate the duration of time periods -+ when both interrupts and preemption are disabled. The histogram data -+ will be located in the debug file system at -+ -+ /sys/kernel/debug/tracing/latency_hist/irqsoff -+ - config PREEMPT_TRACER - bool "Preemption-off Latency Tracer" - default n -@@ -211,6 +229,24 @@ - enabled. This option and the irqs-off timing option can be - used together or separately.) - -+config PREEMPT_OFF_HIST -+ bool "Preemption-off Latency Histogram" -+ depends on PREEMPT_TRACER -+ help -+ This option generates continuously updated histograms (one per cpu) -+ of the duration of time periods with preemption disabled. The -+ histograms are disabled by default. To enable them, write a non-zero -+ number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff -+ -+ If INTERRUPT_OFF_HIST is also selected, additional histograms (one -+ per cpu) are generated that accumulate the duration of time periods -+ when both interrupts and preemption are disabled. The histogram data -+ will be located in the debug file system at -+ -+ /sys/kernel/debug/tracing/latency_hist/preemptoff -+ - config SCHED_TRACER - bool "Scheduling Latency Tracer" - select GENERIC_TRACER -@@ -221,6 +257,74 @@ - This tracer tracks the latency of the highest priority task - to be scheduled in, starting from the point it has woken up. - -+config WAKEUP_LATENCY_HIST -+ bool "Scheduling Latency Histogram" -+ depends on SCHED_TRACER -+ help -+ This option generates continuously updated histograms (one per cpu) -+ of the scheduling latency of the highest priority task. -+ The histograms are disabled by default. To enable them, write a -+ non-zero number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/wakeup -+ -+ Two different algorithms are used, one to determine the latency of -+ processes that exclusively use the highest priority of the system and -+ another one to determine the latency of processes that share the -+ highest system priority with other processes. The former is used to -+ improve hardware and system software, the latter to optimize the -+ priority design of a given system. The histogram data will be -+ located in the debug file system at -+ -+ /sys/kernel/debug/tracing/latency_hist/wakeup -+ -+ and -+ -+ /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio -+ -+ If both Scheduling Latency Histogram and Missed Timer Offsets -+ Histogram are selected, additional histogram data will be collected -+ that contain, in addition to the wakeup latency, the timer latency, in -+ case the wakeup was triggered by an expired timer. These histograms -+ are available in the -+ -+ /sys/kernel/debug/tracing/latency_hist/timerandwakeup -+ -+ directory. They reflect the apparent interrupt and scheduling latency -+ and are best suitable to determine the worst-case latency of a given -+ system. To enable these histograms, write a non-zero number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup -+ -+config MISSED_TIMER_OFFSETS_HIST -+ depends on HIGH_RES_TIMERS -+ select GENERIC_TRACER -+ bool "Missed Timer Offsets Histogram" -+ help -+ Generate a histogram of missed timer offsets in microseconds. The -+ histograms are disabled by default. To enable them, write a non-zero -+ number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets -+ -+ The histogram data will be located in the debug file system at -+ -+ /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets -+ -+ If both Scheduling Latency Histogram and Missed Timer Offsets -+ Histogram are selected, additional histogram data will be collected -+ that contain, in addition to the wakeup latency, the timer latency, in -+ case the wakeup was triggered by an expired timer. These histograms -+ are available in the -+ -+ /sys/kernel/debug/tracing/latency_hist/timerandwakeup -+ -+ directory. They reflect the apparent interrupt and scheduling latency -+ and are best suitable to determine the worst-case latency of a given -+ system. To enable these histograms, write a non-zero number to -+ -+ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup -+ - config ENABLE_DEFAULT_TRACERS - bool "Trace process context switches and events" - depends on !GENERIC_TRACER -diff -Nur linux-4.4.28.orig/kernel/trace/latency_hist.c linux-4.4.28/kernel/trace/latency_hist.c ---- linux-4.4.28.orig/kernel/trace/latency_hist.c 1970-01-01 01:00:00.000000000 +0100 -+++ linux-4.4.28/kernel/trace/latency_hist.c 2016-11-01 21:26:58.804344090 +0100 -@@ -0,0 +1,1178 @@ -+/* -+ * kernel/trace/latency_hist.c -+ * -+ * Add support for histograms of preemption-off latency and -+ * interrupt-off latency and wakeup latency, it depends on -+ * Real-Time Preemption Support. -+ * -+ * Copyright (C) 2005 MontaVista Software, Inc. -+ * Yi Yang -+ * -+ * Converted to work with the new latency tracer. -+ * Copyright (C) 2008 Red Hat, Inc. -+ * Steven Rostedt -+ * -+ */ -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+#include -+ -+#include "trace.h" -+#include -+ -+#define NSECS_PER_USECS 1000L -+ -+#define CREATE_TRACE_POINTS -+#include -+ -+enum { -+ IRQSOFF_LATENCY = 0, -+ PREEMPTOFF_LATENCY, -+ PREEMPTIRQSOFF_LATENCY, -+ WAKEUP_LATENCY, -+ WAKEUP_LATENCY_SHAREDPRIO, -+ MISSED_TIMER_OFFSETS, -+ TIMERANDWAKEUP_LATENCY, -+ MAX_LATENCY_TYPE, -+}; -+ -+#define MAX_ENTRY_NUM 10240 -+ -+struct hist_data { -+ atomic_t hist_mode; /* 0 log, 1 don't log */ -+ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ -+ long min_lat; -+ long max_lat; -+ unsigned long long below_hist_bound_samples; -+ unsigned long long above_hist_bound_samples; -+ long long accumulate_lat; -+ unsigned long long total_samples; -+ unsigned long long hist_array[MAX_ENTRY_NUM]; -+}; -+ -+struct enable_data { -+ int latency_type; -+ int enabled; -+}; -+ -+static char *latency_hist_dir_root = "latency_hist"; -+ -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); -+static char *irqsoff_hist_dir = "irqsoff"; -+static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); -+static DEFINE_PER_CPU(int, hist_irqsoff_counting); -+#endif -+ -+#ifdef CONFIG_PREEMPT_OFF_HIST -+static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); -+static char *preemptoff_hist_dir = "preemptoff"; -+static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); -+static DEFINE_PER_CPU(int, hist_preemptoff_counting); -+#endif -+ -+#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) -+static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); -+static char *preemptirqsoff_hist_dir = "preemptirqsoff"; -+static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); -+static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); -+#endif -+ -+#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) -+static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); -+static struct enable_data preemptirqsoff_enabled_data = { -+ .latency_type = PREEMPTIRQSOFF_LATENCY, -+ .enabled = 0, -+}; -+#endif -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+struct maxlatproc_data { -+ char comm[FIELD_SIZEOF(struct task_struct, comm)]; -+ char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; -+ int pid; -+ int current_pid; -+ int prio; -+ int current_prio; -+ long latency; -+ long timeroffset; -+ cycle_t timestamp; -+}; -+#endif -+ -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); -+static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); -+static char *wakeup_latency_hist_dir = "wakeup"; -+static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; -+static notrace void probe_wakeup_latency_hist_start(void *v, -+ struct task_struct *p); -+static notrace void probe_wakeup_latency_hist_stop(void *v, -+ bool preempt, struct task_struct *prev, struct task_struct *next); -+static notrace void probe_sched_migrate_task(void *, -+ struct task_struct *task, int cpu); -+static struct enable_data wakeup_latency_enabled_data = { -+ .latency_type = WAKEUP_LATENCY, -+ .enabled = 0, -+}; -+static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); -+static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); -+static DEFINE_PER_CPU(struct task_struct *, wakeup_task); -+static DEFINE_PER_CPU(int, wakeup_sharedprio); -+static unsigned long wakeup_pid; -+#endif -+ -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); -+static char *missed_timer_offsets_dir = "missed_timer_offsets"; -+static notrace void probe_hrtimer_interrupt(void *v, int cpu, -+ long long offset, struct task_struct *curr, struct task_struct *task); -+static struct enable_data missed_timer_offsets_enabled_data = { -+ .latency_type = MISSED_TIMER_OFFSETS, -+ .enabled = 0, -+}; -+static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); -+static unsigned long missed_timer_offsets_pid; -+#endif -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); -+static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; -+static struct enable_data timerandwakeup_enabled_data = { -+ .latency_type = TIMERANDWAKEUP_LATENCY, -+ .enabled = 0, -+}; -+static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); -+#endif -+ -+void notrace latency_hist(int latency_type, int cpu, long latency, -+ long timeroffset, cycle_t stop, -+ struct task_struct *p) -+{ -+ struct hist_data *my_hist; -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ struct maxlatproc_data *mp = NULL; -+#endif -+ -+ if (!cpu_possible(cpu) || latency_type < 0 || -+ latency_type >= MAX_LATENCY_TYPE) -+ return; -+ -+ switch (latency_type) { -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ case IRQSOFF_LATENCY: -+ my_hist = &per_cpu(irqsoff_hist, cpu); -+ break; -+#endif -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ case PREEMPTOFF_LATENCY: -+ my_hist = &per_cpu(preemptoff_hist, cpu); -+ break; -+#endif -+#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) -+ case PREEMPTIRQSOFF_LATENCY: -+ my_hist = &per_cpu(preemptirqsoff_hist, cpu); -+ break; -+#endif -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ case WAKEUP_LATENCY: -+ my_hist = &per_cpu(wakeup_latency_hist, cpu); -+ mp = &per_cpu(wakeup_maxlatproc, cpu); -+ break; -+ case WAKEUP_LATENCY_SHAREDPRIO: -+ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); -+ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); -+ break; -+#endif -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ case MISSED_TIMER_OFFSETS: -+ my_hist = &per_cpu(missed_timer_offsets, cpu); -+ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); -+ break; -+#endif -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ case TIMERANDWAKEUP_LATENCY: -+ my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); -+ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); -+ break; -+#endif -+ -+ default: -+ return; -+ } -+ -+ latency += my_hist->offset; -+ -+ if (atomic_read(&my_hist->hist_mode) == 0) -+ return; -+ -+ if (latency < 0 || latency >= MAX_ENTRY_NUM) { -+ if (latency < 0) -+ my_hist->below_hist_bound_samples++; -+ else -+ my_hist->above_hist_bound_samples++; -+ } else -+ my_hist->hist_array[latency]++; -+ -+ if (unlikely(latency > my_hist->max_lat || -+ my_hist->min_lat == LONG_MAX)) { -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ if (latency_type == WAKEUP_LATENCY || -+ latency_type == WAKEUP_LATENCY_SHAREDPRIO || -+ latency_type == MISSED_TIMER_OFFSETS || -+ latency_type == TIMERANDWAKEUP_LATENCY) { -+ strncpy(mp->comm, p->comm, sizeof(mp->comm)); -+ strncpy(mp->current_comm, current->comm, -+ sizeof(mp->current_comm)); -+ mp->pid = task_pid_nr(p); -+ mp->current_pid = task_pid_nr(current); -+ mp->prio = p->prio; -+ mp->current_prio = current->prio; -+ mp->latency = latency; -+ mp->timeroffset = timeroffset; -+ mp->timestamp = stop; -+ } -+#endif -+ my_hist->max_lat = latency; -+ } -+ if (unlikely(latency < my_hist->min_lat)) -+ my_hist->min_lat = latency; -+ my_hist->total_samples++; -+ my_hist->accumulate_lat += latency; -+} -+ -+static void *l_start(struct seq_file *m, loff_t *pos) -+{ -+ loff_t *index_ptr = NULL; -+ loff_t index = *pos; -+ struct hist_data *my_hist = m->private; -+ -+ if (index == 0) { -+ char minstr[32], avgstr[32], maxstr[32]; -+ -+ atomic_dec(&my_hist->hist_mode); -+ -+ if (likely(my_hist->total_samples)) { -+ long avg = (long) div64_s64(my_hist->accumulate_lat, -+ my_hist->total_samples); -+ snprintf(minstr, sizeof(minstr), "%ld", -+ my_hist->min_lat - my_hist->offset); -+ snprintf(avgstr, sizeof(avgstr), "%ld", -+ avg - my_hist->offset); -+ snprintf(maxstr, sizeof(maxstr), "%ld", -+ my_hist->max_lat - my_hist->offset); -+ } else { -+ strcpy(minstr, ""); -+ strcpy(avgstr, minstr); -+ strcpy(maxstr, minstr); -+ } -+ -+ seq_printf(m, "#Minimum latency: %s microseconds\n" -+ "#Average latency: %s microseconds\n" -+ "#Maximum latency: %s microseconds\n" -+ "#Total samples: %llu\n" -+ "#There are %llu samples lower than %ld" -+ " microseconds.\n" -+ "#There are %llu samples greater or equal" -+ " than %ld microseconds.\n" -+ "#usecs\t%16s\n", -+ minstr, avgstr, maxstr, -+ my_hist->total_samples, -+ my_hist->below_hist_bound_samples, -+ -my_hist->offset, -+ my_hist->above_hist_bound_samples, -+ MAX_ENTRY_NUM - my_hist->offset, -+ "samples"); -+ } -+ if (index < MAX_ENTRY_NUM) { -+ index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); -+ if (index_ptr) -+ *index_ptr = index; -+ } -+ -+ return index_ptr; -+} -+ -+static void *l_next(struct seq_file *m, void *p, loff_t *pos) -+{ -+ loff_t *index_ptr = p; -+ struct hist_data *my_hist = m->private; -+ -+ if (++*pos >= MAX_ENTRY_NUM) { -+ atomic_inc(&my_hist->hist_mode); -+ return NULL; -+ } -+ *index_ptr = *pos; -+ return index_ptr; -+} -+ -+static void l_stop(struct seq_file *m, void *p) -+{ -+ kfree(p); -+} -+ -+static int l_show(struct seq_file *m, void *p) -+{ -+ int index = *(loff_t *) p; -+ struct hist_data *my_hist = m->private; -+ -+ seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, -+ my_hist->hist_array[index]); -+ return 0; -+} -+ -+static const struct seq_operations latency_hist_seq_op = { -+ .start = l_start, -+ .next = l_next, -+ .stop = l_stop, -+ .show = l_show -+}; -+ -+static int latency_hist_open(struct inode *inode, struct file *file) -+{ -+ int ret; -+ -+ ret = seq_open(file, &latency_hist_seq_op); -+ if (!ret) { -+ struct seq_file *seq = file->private_data; -+ seq->private = inode->i_private; -+ } -+ return ret; -+} -+ -+static const struct file_operations latency_hist_fops = { -+ .open = latency_hist_open, -+ .read = seq_read, -+ .llseek = seq_lseek, -+ .release = seq_release, -+}; -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+static void clear_maxlatprocdata(struct maxlatproc_data *mp) -+{ -+ mp->comm[0] = mp->current_comm[0] = '\0'; -+ mp->prio = mp->current_prio = mp->pid = mp->current_pid = -+ mp->latency = mp->timeroffset = -1; -+ mp->timestamp = 0; -+} -+#endif -+ -+static void hist_reset(struct hist_data *hist) -+{ -+ atomic_dec(&hist->hist_mode); -+ -+ memset(hist->hist_array, 0, sizeof(hist->hist_array)); -+ hist->below_hist_bound_samples = 0ULL; -+ hist->above_hist_bound_samples = 0ULL; -+ hist->min_lat = LONG_MAX; -+ hist->max_lat = LONG_MIN; -+ hist->total_samples = 0ULL; -+ hist->accumulate_lat = 0LL; -+ -+ atomic_inc(&hist->hist_mode); -+} -+ -+static ssize_t -+latency_hist_reset(struct file *file, const char __user *a, -+ size_t size, loff_t *off) -+{ -+ int cpu; -+ struct hist_data *hist = NULL; -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ struct maxlatproc_data *mp = NULL; -+#endif -+ off_t latency_type = (off_t) file->private_data; -+ -+ for_each_online_cpu(cpu) { -+ -+ switch (latency_type) { -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ case PREEMPTOFF_LATENCY: -+ hist = &per_cpu(preemptoff_hist, cpu); -+ break; -+#endif -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ case IRQSOFF_LATENCY: -+ hist = &per_cpu(irqsoff_hist, cpu); -+ break; -+#endif -+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) -+ case PREEMPTIRQSOFF_LATENCY: -+ hist = &per_cpu(preemptirqsoff_hist, cpu); -+ break; -+#endif -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ case WAKEUP_LATENCY: -+ hist = &per_cpu(wakeup_latency_hist, cpu); -+ mp = &per_cpu(wakeup_maxlatproc, cpu); -+ break; -+ case WAKEUP_LATENCY_SHAREDPRIO: -+ hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); -+ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); -+ break; -+#endif -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ case MISSED_TIMER_OFFSETS: -+ hist = &per_cpu(missed_timer_offsets, cpu); -+ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); -+ break; -+#endif -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ case TIMERANDWAKEUP_LATENCY: -+ hist = &per_cpu(timerandwakeup_latency_hist, cpu); -+ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); -+ break; -+#endif -+ } -+ -+ hist_reset(hist); -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ if (latency_type == WAKEUP_LATENCY || -+ latency_type == WAKEUP_LATENCY_SHAREDPRIO || -+ latency_type == MISSED_TIMER_OFFSETS || -+ latency_type == TIMERANDWAKEUP_LATENCY) -+ clear_maxlatprocdata(mp); -+#endif -+ } -+ -+ return size; -+} -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+static ssize_t -+show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) -+{ -+ char buf[64]; -+ int r; -+ unsigned long *this_pid = file->private_data; -+ -+ r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); -+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -+} -+ -+static ssize_t do_pid(struct file *file, const char __user *ubuf, -+ size_t cnt, loff_t *ppos) -+{ -+ char buf[64]; -+ unsigned long pid; -+ unsigned long *this_pid = file->private_data; -+ -+ if (cnt >= sizeof(buf)) -+ return -EINVAL; -+ -+ if (copy_from_user(&buf, ubuf, cnt)) -+ return -EFAULT; -+ -+ buf[cnt] = '\0'; -+ -+ if (kstrtoul(buf, 10, &pid)) -+ return -EINVAL; -+ -+ *this_pid = pid; -+ -+ return cnt; -+} -+#endif -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+static ssize_t -+show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) -+{ -+ int r; -+ struct maxlatproc_data *mp = file->private_data; -+ int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); -+ unsigned long long t; -+ unsigned long usecs, secs; -+ char *buf; -+ -+ if (mp->pid == -1 || mp->current_pid == -1) { -+ buf = "(none)\n"; -+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, -+ strlen(buf)); -+ } -+ -+ buf = kmalloc(strmaxlen, GFP_KERNEL); -+ if (buf == NULL) -+ return -ENOMEM; -+ -+ t = ns2usecs(mp->timestamp); -+ usecs = do_div(t, USEC_PER_SEC); -+ secs = (unsigned long) t; -+ r = snprintf(buf, strmaxlen, -+ "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, -+ MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, -+ mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, -+ secs, usecs); -+ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -+ kfree(buf); -+ return r; -+} -+#endif -+ -+static ssize_t -+show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) -+{ -+ char buf[64]; -+ struct enable_data *ed = file->private_data; -+ int r; -+ -+ r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); -+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -+} -+ -+static ssize_t -+do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) -+{ -+ char buf[64]; -+ long enable; -+ struct enable_data *ed = file->private_data; -+ -+ if (cnt >= sizeof(buf)) -+ return -EINVAL; -+ -+ if (copy_from_user(&buf, ubuf, cnt)) -+ return -EFAULT; -+ -+ buf[cnt] = 0; -+ -+ if (kstrtoul(buf, 10, &enable)) -+ return -EINVAL; -+ -+ if ((enable && ed->enabled) || (!enable && !ed->enabled)) -+ return cnt; -+ -+ if (enable) { -+ int ret; -+ -+ switch (ed->latency_type) { -+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) -+ case PREEMPTIRQSOFF_LATENCY: -+ ret = register_trace_preemptirqsoff_hist( -+ probe_preemptirqsoff_hist, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_preemptirqsoff_hist " -+ "to trace_preemptirqsoff_hist\n"); -+ return ret; -+ } -+ break; -+#endif -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ case WAKEUP_LATENCY: -+ ret = register_trace_sched_wakeup( -+ probe_wakeup_latency_hist_start, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_wakeup_latency_hist_start " -+ "to trace_sched_wakeup\n"); -+ return ret; -+ } -+ ret = register_trace_sched_wakeup_new( -+ probe_wakeup_latency_hist_start, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_wakeup_latency_hist_start " -+ "to trace_sched_wakeup_new\n"); -+ unregister_trace_sched_wakeup( -+ probe_wakeup_latency_hist_start, NULL); -+ return ret; -+ } -+ ret = register_trace_sched_switch( -+ probe_wakeup_latency_hist_stop, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_wakeup_latency_hist_stop " -+ "to trace_sched_switch\n"); -+ unregister_trace_sched_wakeup( -+ probe_wakeup_latency_hist_start, NULL); -+ unregister_trace_sched_wakeup_new( -+ probe_wakeup_latency_hist_start, NULL); -+ return ret; -+ } -+ ret = register_trace_sched_migrate_task( -+ probe_sched_migrate_task, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_sched_migrate_task " -+ "to trace_sched_migrate_task\n"); -+ unregister_trace_sched_wakeup( -+ probe_wakeup_latency_hist_start, NULL); -+ unregister_trace_sched_wakeup_new( -+ probe_wakeup_latency_hist_start, NULL); -+ unregister_trace_sched_switch( -+ probe_wakeup_latency_hist_stop, NULL); -+ return ret; -+ } -+ break; -+#endif -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ case MISSED_TIMER_OFFSETS: -+ ret = register_trace_hrtimer_interrupt( -+ probe_hrtimer_interrupt, NULL); -+ if (ret) { -+ pr_info("wakeup trace: Couldn't assign " -+ "probe_hrtimer_interrupt " -+ "to trace_hrtimer_interrupt\n"); -+ return ret; -+ } -+ break; -+#endif -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ case TIMERANDWAKEUP_LATENCY: -+ if (!wakeup_latency_enabled_data.enabled || -+ !missed_timer_offsets_enabled_data.enabled) -+ return -EINVAL; -+ break; -+#endif -+ default: -+ break; -+ } -+ } else { -+ switch (ed->latency_type) { -+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) -+ case PREEMPTIRQSOFF_LATENCY: -+ { -+ int cpu; -+ -+ unregister_trace_preemptirqsoff_hist( -+ probe_preemptirqsoff_hist, NULL); -+ for_each_online_cpu(cpu) { -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ per_cpu(hist_irqsoff_counting, -+ cpu) = 0; -+#endif -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ per_cpu(hist_preemptoff_counting, -+ cpu) = 0; -+#endif -+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) -+ per_cpu(hist_preemptirqsoff_counting, -+ cpu) = 0; -+#endif -+ } -+ } -+ break; -+#endif -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ case WAKEUP_LATENCY: -+ { -+ int cpu; -+ -+ unregister_trace_sched_wakeup( -+ probe_wakeup_latency_hist_start, NULL); -+ unregister_trace_sched_wakeup_new( -+ probe_wakeup_latency_hist_start, NULL); -+ unregister_trace_sched_switch( -+ probe_wakeup_latency_hist_stop, NULL); -+ unregister_trace_sched_migrate_task( -+ probe_sched_migrate_task, NULL); -+ -+ for_each_online_cpu(cpu) { -+ per_cpu(wakeup_task, cpu) = NULL; -+ per_cpu(wakeup_sharedprio, cpu) = 0; -+ } -+ } -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ timerandwakeup_enabled_data.enabled = 0; -+#endif -+ break; -+#endif -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ case MISSED_TIMER_OFFSETS: -+ unregister_trace_hrtimer_interrupt( -+ probe_hrtimer_interrupt, NULL); -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ timerandwakeup_enabled_data.enabled = 0; -+#endif -+ break; -+#endif -+ default: -+ break; -+ } -+ } -+ ed->enabled = enable; -+ return cnt; -+} -+ -+static const struct file_operations latency_hist_reset_fops = { -+ .open = tracing_open_generic, -+ .write = latency_hist_reset, -+}; -+ -+static const struct file_operations enable_fops = { -+ .open = tracing_open_generic, -+ .read = show_enable, -+ .write = do_enable, -+}; -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+static const struct file_operations pid_fops = { -+ .open = tracing_open_generic, -+ .read = show_pid, -+ .write = do_pid, -+}; -+ -+static const struct file_operations maxlatproc_fops = { -+ .open = tracing_open_generic, -+ .read = show_maxlatproc, -+}; -+#endif -+ -+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) -+static notrace void probe_preemptirqsoff_hist(void *v, int reason, -+ int starthist) -+{ -+ int cpu = raw_smp_processor_id(); -+ int time_set = 0; -+ -+ if (starthist) { -+ cycle_t uninitialized_var(start); -+ -+ if (!preempt_count() && !irqs_disabled()) -+ return; -+ -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ if ((reason == IRQS_OFF || reason == TRACE_START) && -+ !per_cpu(hist_irqsoff_counting, cpu)) { -+ per_cpu(hist_irqsoff_counting, cpu) = 1; -+ start = ftrace_now(cpu); -+ time_set++; -+ per_cpu(hist_irqsoff_start, cpu) = start; -+ } -+#endif -+ -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ if ((reason == PREEMPT_OFF || reason == TRACE_START) && -+ !per_cpu(hist_preemptoff_counting, cpu)) { -+ per_cpu(hist_preemptoff_counting, cpu) = 1; -+ if (!(time_set++)) -+ start = ftrace_now(cpu); -+ per_cpu(hist_preemptoff_start, cpu) = start; -+ } -+#endif -+ -+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) -+ if (per_cpu(hist_irqsoff_counting, cpu) && -+ per_cpu(hist_preemptoff_counting, cpu) && -+ !per_cpu(hist_preemptirqsoff_counting, cpu)) { -+ per_cpu(hist_preemptirqsoff_counting, cpu) = 1; -+ if (!time_set) -+ start = ftrace_now(cpu); -+ per_cpu(hist_preemptirqsoff_start, cpu) = start; -+ } -+#endif -+ } else { -+ cycle_t uninitialized_var(stop); -+ -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ if ((reason == IRQS_ON || reason == TRACE_STOP) && -+ per_cpu(hist_irqsoff_counting, cpu)) { -+ cycle_t start = per_cpu(hist_irqsoff_start, cpu); -+ -+ stop = ftrace_now(cpu); -+ time_set++; -+ if (start) { -+ long latency = ((long) (stop - start)) / -+ NSECS_PER_USECS; -+ -+ latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, -+ stop, NULL); -+ } -+ per_cpu(hist_irqsoff_counting, cpu) = 0; -+ } -+#endif -+ -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ if ((reason == PREEMPT_ON || reason == TRACE_STOP) && -+ per_cpu(hist_preemptoff_counting, cpu)) { -+ cycle_t start = per_cpu(hist_preemptoff_start, cpu); -+ -+ if (!(time_set++)) -+ stop = ftrace_now(cpu); -+ if (start) { -+ long latency = ((long) (stop - start)) / -+ NSECS_PER_USECS; -+ -+ latency_hist(PREEMPTOFF_LATENCY, cpu, latency, -+ 0, stop, NULL); -+ } -+ per_cpu(hist_preemptoff_counting, cpu) = 0; -+ } -+#endif -+ -+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) -+ if ((!per_cpu(hist_irqsoff_counting, cpu) || -+ !per_cpu(hist_preemptoff_counting, cpu)) && -+ per_cpu(hist_preemptirqsoff_counting, cpu)) { -+ cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); -+ -+ if (!time_set) -+ stop = ftrace_now(cpu); -+ if (start) { -+ long latency = ((long) (stop - start)) / -+ NSECS_PER_USECS; -+ -+ latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, -+ latency, 0, stop, NULL); -+ } -+ per_cpu(hist_preemptirqsoff_counting, cpu) = 0; -+ } -+#endif -+ } -+} -+#endif -+ -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+static DEFINE_RAW_SPINLOCK(wakeup_lock); -+static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, -+ int cpu) -+{ -+ int old_cpu = task_cpu(task); -+ -+ if (cpu != old_cpu) { -+ unsigned long flags; -+ struct task_struct *cpu_wakeup_task; -+ -+ raw_spin_lock_irqsave(&wakeup_lock, flags); -+ -+ cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); -+ if (task == cpu_wakeup_task) { -+ put_task_struct(cpu_wakeup_task); -+ per_cpu(wakeup_task, old_cpu) = NULL; -+ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; -+ get_task_struct(cpu_wakeup_task); -+ } -+ -+ raw_spin_unlock_irqrestore(&wakeup_lock, flags); -+ } -+} -+ -+static notrace void probe_wakeup_latency_hist_start(void *v, -+ struct task_struct *p) -+{ -+ unsigned long flags; -+ struct task_struct *curr = current; -+ int cpu = task_cpu(p); -+ struct task_struct *cpu_wakeup_task; -+ -+ raw_spin_lock_irqsave(&wakeup_lock, flags); -+ -+ cpu_wakeup_task = per_cpu(wakeup_task, cpu); -+ -+ if (wakeup_pid) { -+ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || -+ p->prio == curr->prio) -+ per_cpu(wakeup_sharedprio, cpu) = 1; -+ if (likely(wakeup_pid != task_pid_nr(p))) -+ goto out; -+ } else { -+ if (likely(!rt_task(p)) || -+ (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || -+ p->prio > curr->prio) -+ goto out; -+ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || -+ p->prio == curr->prio) -+ per_cpu(wakeup_sharedprio, cpu) = 1; -+ } -+ -+ if (cpu_wakeup_task) -+ put_task_struct(cpu_wakeup_task); -+ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; -+ get_task_struct(cpu_wakeup_task); -+ cpu_wakeup_task->preempt_timestamp_hist = -+ ftrace_now(raw_smp_processor_id()); -+out: -+ raw_spin_unlock_irqrestore(&wakeup_lock, flags); -+} -+ -+static notrace void probe_wakeup_latency_hist_stop(void *v, -+ bool preempt, struct task_struct *prev, struct task_struct *next) -+{ -+ unsigned long flags; -+ int cpu = task_cpu(next); -+ long latency; -+ cycle_t stop; -+ struct task_struct *cpu_wakeup_task; -+ -+ raw_spin_lock_irqsave(&wakeup_lock, flags); -+ -+ cpu_wakeup_task = per_cpu(wakeup_task, cpu); -+ -+ if (cpu_wakeup_task == NULL) -+ goto out; -+ -+ /* Already running? */ -+ if (unlikely(current == cpu_wakeup_task)) -+ goto out_reset; -+ -+ if (next != cpu_wakeup_task) { -+ if (next->prio < cpu_wakeup_task->prio) -+ goto out_reset; -+ -+ if (next->prio == cpu_wakeup_task->prio) -+ per_cpu(wakeup_sharedprio, cpu) = 1; -+ -+ goto out; -+ } -+ -+ if (current->prio == cpu_wakeup_task->prio) -+ per_cpu(wakeup_sharedprio, cpu) = 1; -+ -+ /* -+ * The task we are waiting for is about to be switched to. -+ * Calculate latency and store it in histogram. -+ */ -+ stop = ftrace_now(raw_smp_processor_id()); -+ -+ latency = ((long) (stop - next->preempt_timestamp_hist)) / -+ NSECS_PER_USECS; -+ -+ if (per_cpu(wakeup_sharedprio, cpu)) { -+ latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, -+ next); -+ per_cpu(wakeup_sharedprio, cpu) = 0; -+ } else { -+ latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ if (timerandwakeup_enabled_data.enabled) { -+ latency_hist(TIMERANDWAKEUP_LATENCY, cpu, -+ next->timer_offset + latency, next->timer_offset, -+ stop, next); -+ } -+#endif -+ } -+ -+out_reset: -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ next->timer_offset = 0; -+#endif -+ put_task_struct(cpu_wakeup_task); -+ per_cpu(wakeup_task, cpu) = NULL; -+out: -+ raw_spin_unlock_irqrestore(&wakeup_lock, flags); -+} -+#endif -+ -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+static notrace void probe_hrtimer_interrupt(void *v, int cpu, -+ long long latency_ns, struct task_struct *curr, -+ struct task_struct *task) -+{ -+ if (latency_ns <= 0 && task != NULL && rt_task(task) && -+ (task->prio < curr->prio || -+ (task->prio == curr->prio && -+ !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { -+ long latency; -+ cycle_t now; -+ -+ if (missed_timer_offsets_pid) { -+ if (likely(missed_timer_offsets_pid != -+ task_pid_nr(task))) -+ return; -+ } -+ -+ now = ftrace_now(cpu); -+ latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); -+ latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, -+ task); -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ task->timer_offset = latency; -+#endif -+ } -+} -+#endif -+ -+static __init int latency_hist_init(void) -+{ -+ struct dentry *latency_hist_root = NULL; -+ struct dentry *dentry; -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ struct dentry *dentry_sharedprio; -+#endif -+ struct dentry *entry; -+ struct dentry *enable_root; -+ int i = 0; -+ struct hist_data *my_hist; -+ char name[64]; -+ char *cpufmt = "CPU%d"; -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ char *cpufmt_maxlatproc = "max_latency-CPU%d"; -+ struct maxlatproc_data *mp = NULL; -+#endif -+ -+ dentry = tracing_init_dentry(); -+ latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); -+ enable_root = debugfs_create_dir("enable", latency_hist_root); -+ -+#ifdef CONFIG_INTERRUPT_OFF_HIST -+ dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(irqsoff_hist, i), &latency_hist_fops); -+ my_hist = &per_cpu(irqsoff_hist, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ } -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); -+#endif -+ -+#ifdef CONFIG_PREEMPT_OFF_HIST -+ dentry = debugfs_create_dir(preemptoff_hist_dir, -+ latency_hist_root); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(preemptoff_hist, i), &latency_hist_fops); -+ my_hist = &per_cpu(preemptoff_hist, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ } -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); -+#endif -+ -+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) -+ dentry = debugfs_create_dir(preemptirqsoff_hist_dir, -+ latency_hist_root); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); -+ my_hist = &per_cpu(preemptirqsoff_hist, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ } -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); -+#endif -+ -+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) -+ entry = debugfs_create_file("preemptirqsoff", 0644, -+ enable_root, (void *)&preemptirqsoff_enabled_data, -+ &enable_fops); -+#endif -+ -+#ifdef CONFIG_WAKEUP_LATENCY_HIST -+ dentry = debugfs_create_dir(wakeup_latency_hist_dir, -+ latency_hist_root); -+ dentry_sharedprio = debugfs_create_dir( -+ wakeup_latency_hist_dir_sharedprio, dentry); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(wakeup_latency_hist, i), -+ &latency_hist_fops); -+ my_hist = &per_cpu(wakeup_latency_hist, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ -+ entry = debugfs_create_file(name, 0444, dentry_sharedprio, -+ &per_cpu(wakeup_latency_hist_sharedprio, i), -+ &latency_hist_fops); -+ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ -+ sprintf(name, cpufmt_maxlatproc, i); -+ -+ mp = &per_cpu(wakeup_maxlatproc, i); -+ entry = debugfs_create_file(name, 0444, dentry, mp, -+ &maxlatproc_fops); -+ clear_maxlatprocdata(mp); -+ -+ mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); -+ entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, -+ &maxlatproc_fops); -+ clear_maxlatprocdata(mp); -+ } -+ entry = debugfs_create_file("pid", 0644, dentry, -+ (void *)&wakeup_pid, &pid_fops); -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); -+ entry = debugfs_create_file("reset", 0644, dentry_sharedprio, -+ (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); -+ entry = debugfs_create_file("wakeup", 0644, -+ enable_root, (void *)&wakeup_latency_enabled_data, -+ &enable_fops); -+#endif -+ -+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST -+ dentry = debugfs_create_dir(missed_timer_offsets_dir, -+ latency_hist_root); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(missed_timer_offsets, i), &latency_hist_fops); -+ my_hist = &per_cpu(missed_timer_offsets, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ -+ sprintf(name, cpufmt_maxlatproc, i); -+ mp = &per_cpu(missed_timer_offsets_maxlatproc, i); -+ entry = debugfs_create_file(name, 0444, dentry, mp, -+ &maxlatproc_fops); -+ clear_maxlatprocdata(mp); -+ } -+ entry = debugfs_create_file("pid", 0644, dentry, -+ (void *)&missed_timer_offsets_pid, &pid_fops); -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); -+ entry = debugfs_create_file("missed_timer_offsets", 0644, -+ enable_root, (void *)&missed_timer_offsets_enabled_data, -+ &enable_fops); -+#endif -+ -+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ -+ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) -+ dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, -+ latency_hist_root); -+ for_each_possible_cpu(i) { -+ sprintf(name, cpufmt, i); -+ entry = debugfs_create_file(name, 0444, dentry, -+ &per_cpu(timerandwakeup_latency_hist, i), -+ &latency_hist_fops); -+ my_hist = &per_cpu(timerandwakeup_latency_hist, i); -+ atomic_set(&my_hist->hist_mode, 1); -+ my_hist->min_lat = LONG_MAX; -+ -+ sprintf(name, cpufmt_maxlatproc, i); -+ mp = &per_cpu(timerandwakeup_maxlatproc, i); -+ entry = debugfs_create_file(name, 0444, dentry, mp, -+ &maxlatproc_fops); -+ clear_maxlatprocdata(mp); -+ } -+ entry = debugfs_create_file("reset", 0644, dentry, -+ (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); -+ entry = debugfs_create_file("timerandwakeup", 0644, -+ enable_root, (void *)&timerandwakeup_enabled_data, -+ &enable_fops); -+#endif -+ return 0; -+} -+ -+device_initcall(latency_hist_init); -diff -Nur linux-4.4.28.orig/kernel/trace/Makefile linux-4.4.28/kernel/trace/Makefile ---- linux-4.4.28.orig/kernel/trace/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/Makefile 2016-11-01 21:26:58.804344090 +0100 -@@ -40,6 +40,10 @@ - obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o - obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o - obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o -+obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o -+obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o -+obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o -+obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o - obj-$(CONFIG_NOP_TRACER) += trace_nop.o - obj-$(CONFIG_STACK_TRACER) += trace_stack.o - obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o -diff -Nur linux-4.4.28.orig/kernel/trace/trace.c linux-4.4.28/kernel/trace/trace.c ---- linux-4.4.28.orig/kernel/trace/trace.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/trace.c 2016-11-01 21:26:58.808344343 +0100 -@@ -1652,6 +1652,7 @@ - struct task_struct *tsk = current; - - entry->preempt_count = pc & 0xff; -+ entry->preempt_lazy_count = preempt_lazy_count(); - entry->pid = (tsk) ? tsk->pid : 0; - entry->flags = - #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT -@@ -1661,8 +1662,11 @@ - #endif - ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | - ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | -- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | -+ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | -+ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | - (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); -+ -+ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; - } - EXPORT_SYMBOL_GPL(tracing_generic_entry_update); - -@@ -2555,14 +2559,17 @@ - - static void print_lat_help_header(struct seq_file *m) - { -- seq_puts(m, "# _------=> CPU# \n" -- "# / _-----=> irqs-off \n" -- "# | / _----=> need-resched \n" -- "# || / _---=> hardirq/softirq \n" -- "# ||| / _--=> preempt-depth \n" -- "# |||| / delay \n" -- "# cmd pid ||||| time | caller \n" -- "# \\ / ||||| \\ | / \n"); -+ seq_puts(m, "# _--------=> CPU# \n" -+ "# / _-------=> irqs-off \n" -+ "# | / _------=> need-resched \n" -+ "# || / _-----=> need-resched_lazy \n" -+ "# ||| / _----=> hardirq/softirq \n" -+ "# |||| / _---=> preempt-depth \n" -+ "# ||||| / _--=> preempt-lazy-depth\n" -+ "# |||||| / _-=> migrate-disable \n" -+ "# ||||||| / delay \n" -+ "# cmd pid |||||||| time | caller \n" -+ "# \\ / |||||||| \\ | / \n"); - } - - static void print_event_info(struct trace_buffer *buf, struct seq_file *m) -@@ -2588,11 +2595,14 @@ - print_event_info(buf, m); - seq_puts(m, "# _-----=> irqs-off\n" - "# / _----=> need-resched\n" -- "# | / _---=> hardirq/softirq\n" -- "# || / _--=> preempt-depth\n" -- "# ||| / delay\n" -- "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n" -- "# | | | |||| | |\n"); -+ "# |/ _-----=> need-resched_lazy\n" -+ "# || / _---=> hardirq/softirq\n" -+ "# ||| / _--=> preempt-depth\n" -+ "# |||| / _-=> preempt-lazy-depth\n" -+ "# ||||| / _-=> migrate-disable \n" -+ "# |||||| / delay\n" -+ "# TASK-PID CPU# ||||||| TIMESTAMP FUNCTION\n" -+ "# | | | ||||||| | |\n"); - } - - void -diff -Nur linux-4.4.28.orig/kernel/trace/trace_events.c linux-4.4.28/kernel/trace/trace_events.c ---- linux-4.4.28.orig/kernel/trace/trace_events.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/trace_events.c 2016-11-01 21:26:58.808344343 +0100 -@@ -188,6 +188,8 @@ - __common_field(unsigned char, flags); - __common_field(unsigned char, preempt_count); - __common_field(int, pid); -+ __common_field(unsigned short, migrate_disable); -+ __common_field(unsigned short, padding); - - return ret; - } -@@ -244,6 +246,14 @@ - - local_save_flags(fbuffer->flags); - fbuffer->pc = preempt_count(); -+ /* -+ * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables -+ * preemption (adding one to the preempt_count). Since we are -+ * interested in the preempt_count at the time the tracepoint was -+ * hit, we need to subtract one to offset the increment. -+ */ -+ if (IS_ENABLED(CONFIG_PREEMPT)) -+ fbuffer->pc--; - fbuffer->trace_file = trace_file; - - fbuffer->event = -diff -Nur linux-4.4.28.orig/kernel/trace/trace.h linux-4.4.28/kernel/trace/trace.h ---- linux-4.4.28.orig/kernel/trace/trace.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/trace.h 2016-11-01 21:26:58.808344343 +0100 -@@ -117,6 +117,7 @@ - * NEED_RESCHED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler -+ * NEED_RESCHED_LAZY - lazy reschedule is requested - */ - enum trace_flag_type { - TRACE_FLAG_IRQS_OFF = 0x01, -@@ -125,6 +126,7 @@ - TRACE_FLAG_HARDIRQ = 0x08, - TRACE_FLAG_SOFTIRQ = 0x10, - TRACE_FLAG_PREEMPT_RESCHED = 0x20, -+ TRACE_FLAG_NEED_RESCHED_LAZY = 0x40, - }; - - #define TRACE_BUF_SIZE 1024 -diff -Nur linux-4.4.28.orig/kernel/trace/trace_irqsoff.c linux-4.4.28/kernel/trace/trace_irqsoff.c ---- linux-4.4.28.orig/kernel/trace/trace_irqsoff.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/trace_irqsoff.c 2016-11-01 21:26:58.808344343 +0100 -@@ -13,6 +13,7 @@ - #include - #include - #include -+#include - - #include "trace.h" - -@@ -424,11 +425,13 @@ - { - if (preempt_trace() || irq_trace()) - start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); -+ trace_preemptirqsoff_hist_rcuidle(TRACE_START, 1); - } - EXPORT_SYMBOL_GPL(start_critical_timings); - - void stop_critical_timings(void) - { -+ trace_preemptirqsoff_hist_rcuidle(TRACE_STOP, 0); - if (preempt_trace() || irq_trace()) - stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); - } -@@ -438,6 +441,7 @@ - #ifdef CONFIG_PROVE_LOCKING - void time_hardirqs_on(unsigned long a0, unsigned long a1) - { -+ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0); - if (!preempt_trace() && irq_trace()) - stop_critical_timing(a0, a1); - } -@@ -446,6 +450,7 @@ - { - if (!preempt_trace() && irq_trace()) - start_critical_timing(a0, a1); -+ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1); - } - - #else /* !CONFIG_PROVE_LOCKING */ -@@ -471,6 +476,7 @@ - */ - void trace_hardirqs_on(void) - { -+ trace_preemptirqsoff_hist(IRQS_ON, 0); - if (!preempt_trace() && irq_trace()) - stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); - } -@@ -480,11 +486,13 @@ - { - if (!preempt_trace() && irq_trace()) - start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); -+ trace_preemptirqsoff_hist(IRQS_OFF, 1); - } - EXPORT_SYMBOL(trace_hardirqs_off); - - __visible void trace_hardirqs_on_caller(unsigned long caller_addr) - { -+ trace_preemptirqsoff_hist(IRQS_ON, 0); - if (!preempt_trace() && irq_trace()) - stop_critical_timing(CALLER_ADDR0, caller_addr); - } -@@ -494,6 +502,7 @@ - { - if (!preempt_trace() && irq_trace()) - start_critical_timing(CALLER_ADDR0, caller_addr); -+ trace_preemptirqsoff_hist(IRQS_OFF, 1); - } - EXPORT_SYMBOL(trace_hardirqs_off_caller); - -@@ -503,12 +512,14 @@ - #ifdef CONFIG_PREEMPT_TRACER - void trace_preempt_on(unsigned long a0, unsigned long a1) - { -+ trace_preemptirqsoff_hist(PREEMPT_ON, 0); - if (preempt_trace() && !irq_trace()) - stop_critical_timing(a0, a1); - } - - void trace_preempt_off(unsigned long a0, unsigned long a1) - { -+ trace_preemptirqsoff_hist(PREEMPT_ON, 1); - if (preempt_trace() && !irq_trace()) - start_critical_timing(a0, a1); - } -diff -Nur linux-4.4.28.orig/kernel/trace/trace_output.c linux-4.4.28/kernel/trace/trace_output.c ---- linux-4.4.28.orig/kernel/trace/trace_output.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/trace/trace_output.c 2016-11-01 21:26:58.808344343 +0100 -@@ -386,6 +386,7 @@ - { - char hardsoft_irq; - char need_resched; -+ char need_resched_lazy; - char irqs_off; - int hardirq; - int softirq; -@@ -413,6 +414,8 @@ - need_resched = '.'; - break; - } -+ need_resched_lazy = -+ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; - - hardsoft_irq = - (hardirq && softirq) ? 'H' : -@@ -420,14 +423,25 @@ - softirq ? 's' : - '.'; - -- trace_seq_printf(s, "%c%c%c", -- irqs_off, need_resched, hardsoft_irq); -+ trace_seq_printf(s, "%c%c%c%c", -+ irqs_off, need_resched, need_resched_lazy, -+ hardsoft_irq); - - if (entry->preempt_count) - trace_seq_printf(s, "%x", entry->preempt_count); - else - trace_seq_putc(s, '.'); - -+ if (entry->preempt_lazy_count) -+ trace_seq_printf(s, "%x", entry->preempt_lazy_count); -+ else -+ trace_seq_putc(s, '.'); -+ -+ if (entry->migrate_disable) -+ trace_seq_printf(s, "%x", entry->migrate_disable); -+ else -+ trace_seq_putc(s, '.'); -+ - return !trace_seq_has_overflowed(s); - } - -diff -Nur linux-4.4.28.orig/kernel/user.c linux-4.4.28/kernel/user.c ---- linux-4.4.28.orig/kernel/user.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/user.c 2016-11-01 21:26:58.808344343 +0100 -@@ -161,11 +161,11 @@ - if (!up) - return; - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) - free_user(up, flags); - else -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - - struct user_struct *alloc_uid(kuid_t uid) -diff -Nur linux-4.4.28.orig/kernel/watchdog.c linux-4.4.28/kernel/watchdog.c ---- linux-4.4.28.orig/kernel/watchdog.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/watchdog.c 2016-11-01 21:26:58.808344343 +0100 -@@ -299,6 +299,8 @@ - - #ifdef CONFIG_HARDLOCKUP_DETECTOR - -+static DEFINE_RAW_SPINLOCK(watchdog_output_lock); -+ - static struct perf_event_attr wd_hw_attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, -@@ -333,6 +335,13 @@ - /* only print hardlockups once */ - if (__this_cpu_read(hard_watchdog_warn) == true) - return; -+ /* -+ * If early-printk is enabled then make sure we do not -+ * lock up in printk() and kill console logging: -+ */ -+ printk_kill(); -+ -+ raw_spin_lock(&watchdog_output_lock); - - pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); - print_modules(); -@@ -350,8 +359,9 @@ - !test_and_set_bit(0, &hardlockup_allcpu_dumped)) - trigger_allbutself_cpu_backtrace(); - -+ raw_spin_unlock(&watchdog_output_lock); - if (hardlockup_panic) -- panic("Hard LOCKUP"); -+ nmi_panic(regs, "Hard LOCKUP"); - - __this_cpu_write(hard_watchdog_warn, true); - return; -@@ -497,6 +507,7 @@ - /* kick off the timer for the hardlockup detector */ - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; -+ hrtimer->irqsafe = 1; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); -diff -Nur linux-4.4.28.orig/kernel/workqueue.c linux-4.4.28/kernel/workqueue.c ---- linux-4.4.28.orig/kernel/workqueue.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/workqueue.c 2016-11-01 21:26:58.812344600 +0100 -@@ -48,6 +48,8 @@ - #include - #include - #include -+#include -+#include - - #include "workqueue_internal.h" - -@@ -121,11 +123,16 @@ - * cpu or grabbing pool->lock is enough for read access. If - * POOL_DISASSOCIATED is set, it's identical to L. - * -+ * On RT we need the extra protection via rt_lock_idle_list() for -+ * the list manipulations against read access from -+ * wq_worker_sleeping(). All other places are nicely serialized via -+ * pool->lock. -+ * - * A: pool->attach_mutex protected. - * - * PL: wq_pool_mutex protected. - * -- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. -+ * PR: wq_pool_mutex protected for writes. RCU protected for reads. - * - * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. - * -@@ -134,7 +141,7 @@ - * - * WQ: wq->mutex protected. - * -- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. -+ * WR: wq->mutex protected for writes. RCU protected for reads. - * - * MD: wq_mayday_lock protected. - */ -@@ -183,7 +190,7 @@ - atomic_t nr_running ____cacheline_aligned_in_smp; - - /* -- * Destruction of pool is sched-RCU protected to allow dereferences -+ * Destruction of pool is RCU protected to allow dereferences - * from get_work_pool(). - */ - struct rcu_head rcu; -@@ -212,7 +219,7 @@ - /* - * Release of unbound pwq is punted to system_wq. See put_pwq() - * and pwq_unbound_release_workfn() for details. pool_workqueue -- * itself is also sched-RCU protected so that the first pwq can be -+ * itself is also RCU protected so that the first pwq can be - * determined without grabbing wq->mutex. - */ - struct work_struct unbound_release_work; -@@ -331,6 +338,8 @@ - struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; - EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); - -+static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); -+ - static int worker_thread(void *__worker); - static void workqueue_sysfs_unregister(struct workqueue_struct *wq); - -@@ -338,20 +347,20 @@ - #include - - #define assert_rcu_or_pool_mutex() \ -- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ -+ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ - !lockdep_is_held(&wq_pool_mutex), \ -- "sched RCU or wq_pool_mutex should be held") -+ "RCU or wq_pool_mutex should be held") - - #define assert_rcu_or_wq_mutex(wq) \ -- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ -+ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ - !lockdep_is_held(&wq->mutex), \ -- "sched RCU or wq->mutex should be held") -+ "RCU or wq->mutex should be held") - - #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ -- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ -+ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ - !lockdep_is_held(&wq->mutex) && \ - !lockdep_is_held(&wq_pool_mutex), \ -- "sched RCU, wq->mutex or wq_pool_mutex should be held") -+ "RCU, wq->mutex or wq_pool_mutex should be held") - - #define for_each_cpu_worker_pool(pool, cpu) \ - for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ -@@ -363,7 +372,7 @@ - * @pool: iteration cursor - * @pi: integer used for iteration - * -- * This must be called either with wq_pool_mutex held or sched RCU read -+ * This must be called either with wq_pool_mutex held or RCU read - * locked. If the pool needs to be used beyond the locking in effect, the - * caller is responsible for guaranteeing that the pool stays online. - * -@@ -395,7 +404,7 @@ - * @pwq: iteration cursor - * @wq: the target workqueue - * -- * This must be called either with wq->mutex held or sched RCU read locked. -+ * This must be called either with wq->mutex held or RCU read locked. - * If the pwq needs to be used beyond the locking in effect, the caller is - * responsible for guaranteeing that the pwq stays online. - * -@@ -407,6 +416,31 @@ - if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ - else - -+#ifdef CONFIG_PREEMPT_RT_BASE -+static inline void rt_lock_idle_list(struct worker_pool *pool) -+{ -+ preempt_disable(); -+} -+static inline void rt_unlock_idle_list(struct worker_pool *pool) -+{ -+ preempt_enable(); -+} -+static inline void sched_lock_idle_list(struct worker_pool *pool) { } -+static inline void sched_unlock_idle_list(struct worker_pool *pool) { } -+#else -+static inline void rt_lock_idle_list(struct worker_pool *pool) { } -+static inline void rt_unlock_idle_list(struct worker_pool *pool) { } -+static inline void sched_lock_idle_list(struct worker_pool *pool) -+{ -+ spin_lock_irq(&pool->lock); -+} -+static inline void sched_unlock_idle_list(struct worker_pool *pool) -+{ -+ spin_unlock_irq(&pool->lock); -+} -+#endif -+ -+ - #ifdef CONFIG_DEBUG_OBJECTS_WORK - - static struct debug_obj_descr work_debug_descr; -@@ -557,7 +591,7 @@ - * @wq: the target workqueue - * @node: the node ID - * -- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU -+ * This must be called with any of wq_pool_mutex, wq->mutex or RCU - * read locked. - * If the pwq needs to be used beyond the locking in effect, the caller is - * responsible for guaranteeing that the pwq stays online. -@@ -701,8 +735,8 @@ - * @work: the work item of interest - * - * Pools are created and destroyed under wq_pool_mutex, and allows read -- * access under sched-RCU read lock. As such, this function should be -- * called under wq_pool_mutex or with preemption disabled. -+ * access under RCU read lock. As such, this function should be -+ * called under wq_pool_mutex or inside of a rcu_read_lock() region. - * - * All fields of the returned pool are accessible as long as the above - * mentioned locking is in effect. If the returned pool needs to be used -@@ -839,51 +873,44 @@ - */ - static void wake_up_worker(struct worker_pool *pool) - { -- struct worker *worker = first_idle_worker(pool); -+ struct worker *worker; -+ -+ rt_lock_idle_list(pool); -+ -+ worker = first_idle_worker(pool); - - if (likely(worker)) - wake_up_process(worker->task); -+ -+ rt_unlock_idle_list(pool); - } - - /** -- * wq_worker_waking_up - a worker is waking up -- * @task: task waking up -- * @cpu: CPU @task is waking up to -+ * wq_worker_running - a worker is running again -+ * @task: task returning from sleep - * -- * This function is called during try_to_wake_up() when a worker is -- * being awoken. -- * -- * CONTEXT: -- * spin_lock_irq(rq->lock) -+ * This function is called when a worker returns from schedule() - */ --void wq_worker_waking_up(struct task_struct *task, int cpu) -+void wq_worker_running(struct task_struct *task) - { - struct worker *worker = kthread_data(task); - -- if (!(worker->flags & WORKER_NOT_RUNNING)) { -- WARN_ON_ONCE(worker->pool->cpu != cpu); -+ if (!worker->sleeping) -+ return; -+ if (!(worker->flags & WORKER_NOT_RUNNING)) - atomic_inc(&worker->pool->nr_running); -- } -+ worker->sleeping = 0; - } - - /** - * wq_worker_sleeping - a worker is going to sleep - * @task: task going to sleep -- * @cpu: CPU in question, must be the current CPU number -- * -- * This function is called during schedule() when a busy worker is -- * going to sleep. Worker on the same cpu can be woken up by -- * returning pointer to its task. -- * -- * CONTEXT: -- * spin_lock_irq(rq->lock) -- * -- * Return: -- * Worker task on @cpu to wake up, %NULL if none. -+ * This function is called from schedule() when a busy worker is -+ * going to sleep. - */ --struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) -+void wq_worker_sleeping(struct task_struct *task) - { -- struct worker *worker = kthread_data(task), *to_wakeup = NULL; -+ struct worker *worker = kthread_data(task); - struct worker_pool *pool; - - /* -@@ -892,29 +919,26 @@ - * checking NOT_RUNNING. - */ - if (worker->flags & WORKER_NOT_RUNNING) -- return NULL; -+ return; - - pool = worker->pool; - -- /* this can only happen on the local cpu */ -- if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) -- return NULL; -+ if (WARN_ON_ONCE(worker->sleeping)) -+ return; -+ -+ worker->sleeping = 1; - - /* - * The counterpart of the following dec_and_test, implied mb, - * worklist not empty test sequence is in insert_work(). - * Please read comment there. -- * -- * NOT_RUNNING is clear. This means that we're bound to and -- * running on the local cpu w/ rq lock held and preemption -- * disabled, which in turn means that none else could be -- * manipulating idle_list, so dereferencing idle_list without pool -- * lock is safe. - */ - if (atomic_dec_and_test(&pool->nr_running) && -- !list_empty(&pool->worklist)) -- to_wakeup = first_idle_worker(pool); -- return to_wakeup ? to_wakeup->task : NULL; -+ !list_empty(&pool->worklist)) { -+ sched_lock_idle_list(pool); -+ wake_up_worker(pool); -+ sched_unlock_idle_list(pool); -+ } - } - - /** -@@ -1108,12 +1132,12 @@ - { - if (pwq) { - /* -- * As both pwqs and pools are sched-RCU protected, the -+ * As both pwqs and pools are RCU protected, the - * following lock operations are safe. - */ -- spin_lock_irq(&pwq->pool->lock); -+ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); - put_pwq(pwq); -- spin_unlock_irq(&pwq->pool->lock); -+ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); - } - } - -@@ -1215,7 +1239,7 @@ - struct worker_pool *pool; - struct pool_workqueue *pwq; - -- local_irq_save(*flags); -+ local_lock_irqsave(pendingb_lock, *flags); - - /* try to steal the timer if it exists */ - if (is_dwork) { -@@ -1234,6 +1258,7 @@ - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) - return 0; - -+ rcu_read_lock(); - /* - * The queueing is in progress, or it is already queued. Try to - * steal it from ->worklist without clearing WORK_STRUCT_PENDING. -@@ -1272,14 +1297,16 @@ - set_work_pool_and_keep_pending(work, pool->id); - - spin_unlock(&pool->lock); -+ rcu_read_unlock(); - return 1; - } - spin_unlock(&pool->lock); - fail: -- local_irq_restore(*flags); -+ rcu_read_unlock(); -+ local_unlock_irqrestore(pendingb_lock, *flags); - if (work_is_canceling(work)) - return -ENOENT; -- cpu_relax(); -+ cpu_chill(); - return -EAGAIN; - } - -@@ -1348,7 +1375,7 @@ - * queued or lose PENDING. Grabbing PENDING and queueing should - * happen with IRQ disabled. - */ -- WARN_ON_ONCE(!irqs_disabled()); -+ WARN_ON_ONCE_NONRT(!irqs_disabled()); - - debug_work_activate(work); - -@@ -1356,6 +1383,8 @@ - if (unlikely(wq->flags & __WQ_DRAINING) && - WARN_ON_ONCE(!is_chained_work(wq))) - return; -+ -+ rcu_read_lock(); - retry: - if (req_cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); -@@ -1412,10 +1441,8 @@ - /* pwq determined, queue */ - trace_workqueue_queue_work(req_cpu, pwq, work); - -- if (WARN_ON(!list_empty(&work->entry))) { -- spin_unlock(&pwq->pool->lock); -- return; -- } -+ if (WARN_ON(!list_empty(&work->entry))) -+ goto out; - - pwq->nr_in_flight[pwq->work_color]++; - work_flags = work_color_to_flags(pwq->work_color); -@@ -1431,7 +1458,9 @@ - - insert_work(pwq, work, worklist, work_flags); - -+out: - spin_unlock(&pwq->pool->lock); -+ rcu_read_unlock(); - } - - /** -@@ -1451,14 +1480,14 @@ - bool ret = false; - unsigned long flags; - -- local_irq_save(flags); -+ local_lock_irqsave(pendingb_lock,flags); - - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - __queue_work(cpu, wq, work); - ret = true; - } - -- local_irq_restore(flags); -+ local_unlock_irqrestore(pendingb_lock, flags); - return ret; - } - EXPORT_SYMBOL(queue_work_on); -@@ -1525,14 +1554,14 @@ - unsigned long flags; - - /* read the comment in __queue_work() */ -- local_irq_save(flags); -+ local_lock_irqsave(pendingb_lock, flags); - - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - __queue_delayed_work(cpu, wq, dwork, delay); - ret = true; - } - -- local_irq_restore(flags); -+ local_unlock_irqrestore(pendingb_lock, flags); - return ret; - } - EXPORT_SYMBOL(queue_delayed_work_on); -@@ -1567,7 +1596,7 @@ - - if (likely(ret >= 0)) { - __queue_delayed_work(cpu, wq, dwork, delay); -- local_irq_restore(flags); -+ local_unlock_irqrestore(pendingb_lock, flags); - } - - /* -ENOENT from try_to_grab_pending() becomes %true */ -@@ -1600,7 +1629,9 @@ - worker->last_active = jiffies; - - /* idle_list is LIFO */ -+ rt_lock_idle_list(pool); - list_add(&worker->entry, &pool->idle_list); -+ rt_unlock_idle_list(pool); - - if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) - mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); -@@ -1633,7 +1664,9 @@ - return; - worker_clr_flags(worker, WORKER_IDLE); - pool->nr_idle--; -+ rt_lock_idle_list(pool); - list_del_init(&worker->entry); -+ rt_unlock_idle_list(pool); - } - - static struct worker *alloc_worker(int node) -@@ -1799,7 +1832,9 @@ - pool->nr_workers--; - pool->nr_idle--; - -+ rt_lock_idle_list(pool); - list_del_init(&worker->entry); -+ rt_unlock_idle_list(pool); - worker->flags |= WORKER_DIE; - wake_up_process(worker->task); - } -@@ -2716,14 +2751,14 @@ - - might_sleep(); - -- local_irq_disable(); -+ rcu_read_lock(); - pool = get_work_pool(work); - if (!pool) { -- local_irq_enable(); -+ rcu_read_unlock(); - return false; - } - -- spin_lock(&pool->lock); -+ spin_lock_irq(&pool->lock); - /* see the comment in try_to_grab_pending() with the same code */ - pwq = get_work_pwq(work); - if (pwq) { -@@ -2750,10 +2785,11 @@ - else - lock_map_acquire_read(&pwq->wq->lockdep_map); - lock_map_release(&pwq->wq->lockdep_map); -- -+ rcu_read_unlock(); - return true; - already_gone: - spin_unlock_irq(&pool->lock); -+ rcu_read_unlock(); - return false; - } - -@@ -2840,7 +2876,7 @@ - - /* tell other tasks trying to grab @work to back off */ - mark_work_canceling(work); -- local_irq_restore(flags); -+ local_unlock_irqrestore(pendingb_lock, flags); - - flush_work(work); - clear_work_data(work); -@@ -2895,10 +2931,10 @@ - */ - bool flush_delayed_work(struct delayed_work *dwork) - { -- local_irq_disable(); -+ local_lock_irq(pendingb_lock); - if (del_timer_sync(&dwork->timer)) - __queue_work(dwork->cpu, dwork->wq, &dwork->work); -- local_irq_enable(); -+ local_unlock_irq(pendingb_lock); - return flush_work(&dwork->work); - } - EXPORT_SYMBOL(flush_delayed_work); -@@ -2933,7 +2969,7 @@ - - set_work_pool_and_clear_pending(&dwork->work, - get_work_pool_id(&dwork->work)); -- local_irq_restore(flags); -+ local_unlock_irqrestore(pendingb_lock, flags); - return ret; - } - EXPORT_SYMBOL(cancel_delayed_work); -@@ -3161,7 +3197,7 @@ - * put_unbound_pool - put a worker_pool - * @pool: worker_pool to put - * -- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU -+ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU - * safe manner. get_unbound_pool() calls this function on its failure path - * and this function should be able to release pools which went through, - * successfully or not, init_worker_pool(). -@@ -3215,8 +3251,8 @@ - del_timer_sync(&pool->idle_timer); - del_timer_sync(&pool->mayday_timer); - -- /* sched-RCU protected to allow dereferences from get_work_pool() */ -- call_rcu_sched(&pool->rcu, rcu_free_pool); -+ /* RCU protected to allow dereferences from get_work_pool() */ -+ call_rcu(&pool->rcu, rcu_free_pool); - } - - /** -@@ -3323,14 +3359,14 @@ - put_unbound_pool(pool); - mutex_unlock(&wq_pool_mutex); - -- call_rcu_sched(&pwq->rcu, rcu_free_pwq); -+ call_rcu(&pwq->rcu, rcu_free_pwq); - - /* - * If we're the last pwq going away, @wq is already dead and no one - * is gonna access it anymore. Schedule RCU free. - */ - if (is_last) -- call_rcu_sched(&wq->rcu, rcu_free_wq); -+ call_rcu(&wq->rcu, rcu_free_wq); - } - - /** -@@ -3983,7 +4019,7 @@ - * The base ref is never dropped on per-cpu pwqs. Directly - * schedule RCU free. - */ -- call_rcu_sched(&wq->rcu, rcu_free_wq); -+ call_rcu(&wq->rcu, rcu_free_wq); - } else { - /* - * We're the sole accessor of @wq at this point. Directly -@@ -4076,7 +4112,8 @@ - struct pool_workqueue *pwq; - bool ret; - -- rcu_read_lock_sched(); -+ rcu_read_lock(); -+ preempt_disable(); - - if (cpu == WORK_CPU_UNBOUND) - cpu = smp_processor_id(); -@@ -4087,7 +4124,8 @@ - pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); - - ret = !list_empty(&pwq->delayed_works); -- rcu_read_unlock_sched(); -+ preempt_enable(); -+ rcu_read_unlock(); - - return ret; - } -@@ -4113,15 +4151,15 @@ - if (work_pending(work)) - ret |= WORK_BUSY_PENDING; - -- local_irq_save(flags); -+ rcu_read_lock(); - pool = get_work_pool(work); - if (pool) { -- spin_lock(&pool->lock); -+ spin_lock_irqsave(&pool->lock, flags); - if (find_worker_executing_work(pool, work)) - ret |= WORK_BUSY_RUNNING; -- spin_unlock(&pool->lock); -+ spin_unlock_irqrestore(&pool->lock, flags); - } -- local_irq_restore(flags); -+ rcu_read_unlock(); - - return ret; - } -@@ -4310,7 +4348,7 @@ - unsigned long flags; - int pi; - -- rcu_read_lock_sched(); -+ rcu_read_lock(); - - pr_info("Showing busy workqueues and worker pools:\n"); - -@@ -4361,7 +4399,7 @@ - spin_unlock_irqrestore(&pool->lock, flags); - } - -- rcu_read_unlock_sched(); -+ rcu_read_unlock(); - } - - /* -@@ -4722,16 +4760,16 @@ - * nr_active is monotonically decreasing. It's safe - * to peek without lock. - */ -- rcu_read_lock_sched(); -+ rcu_read_lock(); - for_each_pwq(pwq, wq) { - WARN_ON_ONCE(pwq->nr_active < 0); - if (pwq->nr_active) { - busy = true; -- rcu_read_unlock_sched(); -+ rcu_read_unlock(); - goto out_unlock; - } - } -- rcu_read_unlock_sched(); -+ rcu_read_unlock(); - } - out_unlock: - mutex_unlock(&wq_pool_mutex); -@@ -4921,7 +4959,8 @@ - const char *delim = ""; - int node, written = 0; - -- rcu_read_lock_sched(); -+ get_online_cpus(); -+ rcu_read_lock(); - for_each_node(node) { - written += scnprintf(buf + written, PAGE_SIZE - written, - "%s%d:%d", delim, node, -@@ -4929,7 +4968,8 @@ - delim = " "; - } - written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); -- rcu_read_unlock_sched(); -+ rcu_read_unlock(); -+ put_online_cpus(); - - return written; - } -diff -Nur linux-4.4.28.orig/kernel/workqueue_internal.h linux-4.4.28/kernel/workqueue_internal.h ---- linux-4.4.28.orig/kernel/workqueue_internal.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/kernel/workqueue_internal.h 2016-11-01 21:26:58.812344600 +0100 -@@ -43,6 +43,7 @@ - unsigned long last_active; /* L: last active timestamp */ - unsigned int flags; /* X: flags */ - int id; /* I: worker id */ -+ int sleeping; /* None */ - - /* - * Opaque string set with work_set_desc(). Printed out with task -@@ -68,7 +69,7 @@ - * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. - */ --void wq_worker_waking_up(struct task_struct *task, int cpu); --struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); -+void wq_worker_running(struct task_struct *task); -+void wq_worker_sleeping(struct task_struct *task); - - #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ -diff -Nur linux-4.4.28.orig/lib/debugobjects.c linux-4.4.28/lib/debugobjects.c ---- linux-4.4.28.orig/lib/debugobjects.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/debugobjects.c 2016-11-01 21:26:58.812344600 +0100 -@@ -309,7 +309,10 @@ - struct debug_obj *obj; - unsigned long flags; - -- fill_pool(); -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (preempt_count() == 0 && !irqs_disabled()) -+#endif -+ fill_pool(); - - db = get_bucket((unsigned long) addr); - -diff -Nur linux-4.4.28.orig/lib/idr.c linux-4.4.28/lib/idr.c ---- linux-4.4.28.orig/lib/idr.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/idr.c 2016-11-01 21:26:58.812344600 +0100 -@@ -30,6 +30,7 @@ - #include - #include - #include -+#include - - #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) - #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) -@@ -45,6 +46,37 @@ - static DEFINE_PER_CPU(int, idr_preload_cnt); - static DEFINE_SPINLOCK(simple_ida_lock); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+static DEFINE_LOCAL_IRQ_LOCK(idr_lock); -+ -+static inline void idr_preload_lock(void) -+{ -+ local_lock(idr_lock); -+} -+ -+static inline void idr_preload_unlock(void) -+{ -+ local_unlock(idr_lock); -+} -+ -+void idr_preload_end(void) -+{ -+ idr_preload_unlock(); -+} -+EXPORT_SYMBOL(idr_preload_end); -+#else -+static inline void idr_preload_lock(void) -+{ -+ preempt_disable(); -+} -+ -+static inline void idr_preload_unlock(void) -+{ -+ preempt_enable(); -+} -+#endif -+ -+ - /* the maximum ID which can be allocated given idr->layers */ - static int idr_max(int layers) - { -@@ -115,14 +147,14 @@ - * context. See idr_preload() for details. - */ - if (!in_interrupt()) { -- preempt_disable(); -+ idr_preload_lock(); - new = __this_cpu_read(idr_preload_head); - if (new) { - __this_cpu_write(idr_preload_head, new->ary[0]); - __this_cpu_dec(idr_preload_cnt); - new->ary[0] = NULL; - } -- preempt_enable(); -+ idr_preload_unlock(); - if (new) - return new; - } -@@ -366,7 +398,6 @@ - idr_mark_full(pa, id); - } - -- - /** - * idr_preload - preload for idr_alloc() - * @gfp_mask: allocation mask to use for preloading -@@ -401,7 +432,7 @@ - WARN_ON_ONCE(in_interrupt()); - might_sleep_if(gfpflags_allow_blocking(gfp_mask)); - -- preempt_disable(); -+ idr_preload_lock(); - - /* - * idr_alloc() is likely to succeed w/o full idr_layer buffer and -@@ -413,9 +444,9 @@ - while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { - struct idr_layer *new; - -- preempt_enable(); -+ idr_preload_unlock(); - new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); -- preempt_disable(); -+ idr_preload_lock(); - if (!new) - break; - -diff -Nur linux-4.4.28.orig/lib/Kconfig linux-4.4.28/lib/Kconfig ---- linux-4.4.28.orig/lib/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/Kconfig 2016-11-01 21:26:58.812344600 +0100 -@@ -397,6 +397,7 @@ - - config CPUMASK_OFFSTACK - bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS -+ depends on !PREEMPT_RT_FULL - help - Use dynamic allocation for cpumask_var_t, instead of putting - them on the stack. This is a bit more expensive, but avoids -diff -Nur linux-4.4.28.orig/lib/locking-selftest.c linux-4.4.28/lib/locking-selftest.c ---- linux-4.4.28.orig/lib/locking-selftest.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/locking-selftest.c 2016-11-01 21:26:58.816344864 +0100 -@@ -590,6 +590,8 @@ - #include "locking-selftest-spin-hardirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - #include "locking-selftest-rlock-hardirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) - -@@ -605,9 +607,12 @@ - #include "locking-selftest-wlock-softirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) - -+#endif -+ - #undef E1 - #undef E2 - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * Enabling hardirqs with a softirq-safe lock held: - */ -@@ -640,6 +645,8 @@ - #undef E1 - #undef E2 - -+#endif -+ - /* - * Enabling irqs with an irq-safe lock held: - */ -@@ -663,6 +670,8 @@ - #include "locking-selftest-spin-hardirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - #include "locking-selftest-rlock-hardirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) - -@@ -678,6 +687,8 @@ - #include "locking-selftest-wlock-softirq.h" - GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) - -+#endif -+ - #undef E1 - #undef E2 - -@@ -709,6 +720,8 @@ - #include "locking-selftest-spin-hardirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - #include "locking-selftest-rlock-hardirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) - -@@ -724,6 +737,8 @@ - #include "locking-selftest-wlock-softirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) - -+#endif -+ - #undef E1 - #undef E2 - #undef E3 -@@ -757,6 +772,8 @@ - #include "locking-selftest-spin-hardirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - #include "locking-selftest-rlock-hardirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) - -@@ -772,10 +789,14 @@ - #include "locking-selftest-wlock-softirq.h" - GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) - -+#endif -+ - #undef E1 - #undef E2 - #undef E3 - -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - /* - * read-lock / write-lock irq inversion. - * -@@ -838,6 +859,10 @@ - #undef E2 - #undef E3 - -+#endif -+ -+#ifndef CONFIG_PREEMPT_RT_FULL -+ - /* - * read-lock / write-lock recursion that is actually safe. - */ -@@ -876,6 +901,8 @@ - #undef E2 - #undef E3 - -+#endif -+ - /* - * read-lock / write-lock recursion that is unsafe. - */ -@@ -1858,6 +1885,7 @@ - - printk(" --------------------------------------------------------------------------\n"); - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * irq-context testcases: - */ -@@ -1870,6 +1898,28 @@ - - DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); - // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); -+#else -+ /* On -rt, we only do hardirq context test for raw spinlock */ -+ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); -+ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); -+ -+ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); -+ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); -+ -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); -+ -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); -+ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); -+#endif - - ww_tests(); - -diff -Nur linux-4.4.28.orig/lib/percpu_ida.c linux-4.4.28/lib/percpu_ida.c ---- linux-4.4.28.orig/lib/percpu_ida.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/percpu_ida.c 2016-11-01 21:26:58.816344864 +0100 -@@ -26,6 +26,9 @@ - #include - #include - #include -+#include -+ -+static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock); - - struct percpu_ida_cpu { - /* -@@ -148,13 +151,13 @@ - unsigned long flags; - int tag; - -- local_irq_save(flags); -+ local_lock_irqsave(irq_off_lock, flags); - tags = this_cpu_ptr(pool->tag_cpu); - - /* Fastpath */ - tag = alloc_local_tag(tags); - if (likely(tag >= 0)) { -- local_irq_restore(flags); -+ local_unlock_irqrestore(irq_off_lock, flags); - return tag; - } - -@@ -173,6 +176,7 @@ - - if (!tags->nr_free) - alloc_global_tags(pool, tags); -+ - if (!tags->nr_free) - steal_tags(pool, tags); - -@@ -184,7 +188,7 @@ - } - - spin_unlock(&pool->lock); -- local_irq_restore(flags); -+ local_unlock_irqrestore(irq_off_lock, flags); - - if (tag >= 0 || state == TASK_RUNNING) - break; -@@ -196,7 +200,7 @@ - - schedule(); - -- local_irq_save(flags); -+ local_lock_irqsave(irq_off_lock, flags); - tags = this_cpu_ptr(pool->tag_cpu); - } - if (state != TASK_RUNNING) -@@ -221,7 +225,7 @@ - - BUG_ON(tag >= pool->nr_tags); - -- local_irq_save(flags); -+ local_lock_irqsave(irq_off_lock, flags); - tags = this_cpu_ptr(pool->tag_cpu); - - spin_lock(&tags->lock); -@@ -253,7 +257,7 @@ - spin_unlock(&pool->lock); - } - -- local_irq_restore(flags); -+ local_unlock_irqrestore(irq_off_lock, flags); - } - EXPORT_SYMBOL_GPL(percpu_ida_free); - -@@ -345,7 +349,7 @@ - struct percpu_ida_cpu *remote; - unsigned cpu, i, err = 0; - -- local_irq_save(flags); -+ local_lock_irqsave(irq_off_lock, flags); - for_each_possible_cpu(cpu) { - remote = per_cpu_ptr(pool->tag_cpu, cpu); - spin_lock(&remote->lock); -@@ -367,7 +371,7 @@ - } - spin_unlock(&pool->lock); - out: -- local_irq_restore(flags); -+ local_unlock_irqrestore(irq_off_lock, flags); - return err; - } - EXPORT_SYMBOL_GPL(percpu_ida_for_each_free); -diff -Nur linux-4.4.28.orig/lib/radix-tree.c linux-4.4.28/lib/radix-tree.c ---- linux-4.4.28.orig/lib/radix-tree.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/radix-tree.c 2016-11-01 21:26:58.816344864 +0100 -@@ -196,13 +196,14 @@ - * succeed in getting a node here (and never reach - * kmem_cache_alloc) - */ -- rtp = this_cpu_ptr(&radix_tree_preloads); -+ rtp = &get_cpu_var(radix_tree_preloads); - if (rtp->nr) { - ret = rtp->nodes; - rtp->nodes = ret->private_data; - ret->private_data = NULL; - rtp->nr--; - } -+ put_cpu_var(radix_tree_preloads); - /* - * Update the allocation stack trace as this is more useful - * for debugging. -@@ -242,6 +243,7 @@ - call_rcu(&node->rcu_head, radix_tree_node_rcu_free); - } - -+#ifndef CONFIG_PREEMPT_RT_FULL - /* - * Load up this CPU's radix_tree_node buffer with sufficient objects to - * ensure that the addition of a single element in the tree cannot fail. On -@@ -310,6 +312,7 @@ - return 0; - } - EXPORT_SYMBOL(radix_tree_maybe_preload); -+#endif - - /* - * Return the maximum key which can be store into a -diff -Nur linux-4.4.28.orig/lib/rbtree.c linux-4.4.28/lib/rbtree.c ---- linux-4.4.28.orig/lib/rbtree.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/rbtree.c 2016-11-01 21:26:58.816344864 +0100 -@@ -23,6 +23,7 @@ - - #include - #include -+#include - - /* - * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree -@@ -590,3 +591,13 @@ - return rb_left_deepest_node(root->rb_node); - } - EXPORT_SYMBOL(rb_first_postorder); -+ -+void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, -+ struct rb_node **rb_link) -+{ -+ node->__rb_parent_color = (unsigned long)parent; -+ node->rb_left = node->rb_right = NULL; -+ -+ rcu_assign_pointer(*rb_link, node); -+} -+EXPORT_SYMBOL(rb_link_node_rcu); -diff -Nur linux-4.4.28.orig/lib/scatterlist.c linux-4.4.28/lib/scatterlist.c ---- linux-4.4.28.orig/lib/scatterlist.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/scatterlist.c 2016-11-01 21:26:58.816344864 +0100 -@@ -620,7 +620,7 @@ - flush_kernel_dcache_page(miter->page); - - if (miter->__flags & SG_MITER_ATOMIC) { -- WARN_ON_ONCE(preemptible()); -+ WARN_ON_ONCE(!pagefault_disabled()); - kunmap_atomic(miter->addr); - } else - kunmap(miter->page); -@@ -664,7 +664,7 @@ - if (!sg_miter_skip(&miter, skip)) - return false; - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - - while (sg_miter_next(&miter) && offset < buflen) { - unsigned int len; -@@ -681,7 +681,7 @@ - - sg_miter_stop(&miter); - -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - return offset; - } - EXPORT_SYMBOL(sg_copy_buffer); -diff -Nur linux-4.4.28.orig/lib/smp_processor_id.c linux-4.4.28/lib/smp_processor_id.c ---- linux-4.4.28.orig/lib/smp_processor_id.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/lib/smp_processor_id.c 2016-11-01 21:26:58.816344864 +0100 -@@ -39,8 +39,9 @@ - if (!printk_ratelimit()) - goto out_enable; - -- printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", -- what1, what2, preempt_count() - 1, current->comm, current->pid); -+ printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x %08x] code: %s/%d\n", -+ what1, what2, preempt_count() - 1, __migrate_disabled(current), -+ current->comm, current->pid); - - print_symbol("caller is %s\n", (long)__builtin_return_address(0)); - dump_stack(); -diff -Nur linux-4.4.28.orig/Makefile linux-4.4.28/Makefile ---- linux-4.4.28.orig/Makefile 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/Makefile 2016-11-01 21:26:56.688207681 +0100 -@@ -394,7 +394,7 @@ - KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ - -fno-strict-aliasing -fno-common \ - -Werror-implicit-function-declaration \ -- -Wno-format-security \ -+ -Wno-format-security -fno-PIE \ - -std=gnu89 - - KBUILD_AFLAGS_KERNEL := -@@ -783,6 +783,9 @@ - # Prohibit date/time macros, which would make the build non-deterministic - KBUILD_CFLAGS += $(call cc-option,-Werror=date-time) - -+# enforce correct pointer usage -+KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) -+ - # use the deterministic mode of AR if available - KBUILD_ARFLAGS := $(call ar-option,D) - -diff -Nur linux-4.4.28.orig/mm/backing-dev.c linux-4.4.28/mm/backing-dev.c ---- linux-4.4.28.orig/mm/backing-dev.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/backing-dev.c 2016-11-01 21:26:58.816344864 +0100 -@@ -457,9 +457,9 @@ - { - unsigned long flags; - -- local_irq_save(flags); -+ local_irq_save_nort(flags); - if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - return; - } - -diff -Nur linux-4.4.28.orig/mm/compaction.c linux-4.4.28/mm/compaction.c ---- linux-4.4.28.orig/mm/compaction.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/compaction.c 2016-11-01 21:26:58.816344864 +0100 -@@ -1430,10 +1430,12 @@ - cc->migrate_pfn & ~((1UL << cc->order) - 1); - - if (cc->last_migrated_pfn < current_block_start) { -- cpu = get_cpu(); -+ cpu = get_cpu_light(); -+ local_lock_irq(swapvec_lock); - lru_add_drain_cpu(cpu); -+ local_unlock_irq(swapvec_lock); - drain_local_pages(zone); -- put_cpu(); -+ put_cpu_light(); - /* No more flushing until we migrate again */ - cc->last_migrated_pfn = 0; - } -diff -Nur linux-4.4.28.orig/mm/filemap.c linux-4.4.28/mm/filemap.c ---- linux-4.4.28.orig/mm/filemap.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/filemap.c 2016-11-01 21:29:56.667809032 +0100 -@@ -144,9 +144,12 @@ - * node->private_list is protected by - * mapping->tree_lock. - */ -- if (!list_empty(&node->private_list)) -- list_lru_del(&workingset_shadow_nodes, -- &node->private_list); -+ if (!list_empty(&node->private_list)) { -+ local_lock(workingset_shadow_lock); -+ list_lru_del(&__workingset_shadow_nodes, -+ &node->private_list); -+ local_unlock(workingset_shadow_lock); -+ } - } - return 0; - } -@@ -218,7 +221,9 @@ - if (!workingset_node_pages(node) && - list_empty(&node->private_list)) { - node->private_data = mapping; -- list_lru_add(&workingset_shadow_nodes, &node->private_list); -+ local_lock(workingset_shadow_lock); -+ list_lru_add(&__workingset_shadow_nodes, &node->private_list); -+ local_unlock(workingset_shadow_lock); - } - } - -diff -Nur linux-4.4.28.orig/mm/highmem.c linux-4.4.28/mm/highmem.c ---- linux-4.4.28.orig/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/highmem.c 2016-11-01 21:26:58.820345117 +0100 -@@ -29,10 +29,11 @@ - #include - #include - -- -+#ifndef CONFIG_PREEMPT_RT_FULL - #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) - DEFINE_PER_CPU(int, __kmap_atomic_idx); - #endif -+#endif - - /* - * Virtual_count is not a pure "count". -@@ -107,8 +108,9 @@ - unsigned long totalhigh_pages __read_mostly; - EXPORT_SYMBOL(totalhigh_pages); - -- -+#ifndef CONFIG_PREEMPT_RT_FULL - EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); -+#endif - - unsigned int nr_free_highpages (void) - { -diff -Nur linux-4.4.28.orig/mm/Kconfig linux-4.4.28/mm/Kconfig ---- linux-4.4.28.orig/mm/Kconfig 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/Kconfig 2016-11-01 21:26:58.816344864 +0100 -@@ -392,7 +392,7 @@ - - config TRANSPARENT_HUGEPAGE - bool "Transparent Hugepage Support" -- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE -+ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL - select COMPACTION - help - Transparent Hugepages allows the kernel to use huge pages and -diff -Nur linux-4.4.28.orig/mm/memcontrol.c linux-4.4.28/mm/memcontrol.c ---- linux-4.4.28.orig/mm/memcontrol.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/memcontrol.c 2016-11-01 21:26:58.820345117 +0100 -@@ -67,6 +67,8 @@ - #include - #include - #include -+#include -+ - #include "slab.h" - - #include -@@ -87,6 +89,7 @@ - #define do_swap_account 0 - #endif - -+static DEFINE_LOCAL_IRQ_LOCK(event_lock); - static const char * const mem_cgroup_stat_names[] = { - "cache", - "rss", -@@ -1922,14 +1925,17 @@ - */ - static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) - { -- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); -+ struct memcg_stock_pcp *stock; -+ int cpu = get_cpu_light(); -+ -+ stock = &per_cpu(memcg_stock, cpu); - - if (stock->cached != memcg) { /* reset if necessary */ - drain_stock(stock); - stock->cached = memcg; - } - stock->nr_pages += nr_pages; -- put_cpu_var(memcg_stock); -+ put_cpu_light(); - } - - /* -@@ -1945,7 +1951,7 @@ - return; - /* Notify other cpus that system-wide "drain" is running */ - get_online_cpus(); -- curcpu = get_cpu(); -+ curcpu = get_cpu_light(); - for_each_online_cpu(cpu) { - struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); - struct mem_cgroup *memcg; -@@ -1962,7 +1968,7 @@ - schedule_work_on(cpu, &stock->work); - } - } -- put_cpu(); -+ put_cpu_light(); - put_online_cpus(); - mutex_unlock(&percpu_charge_mutex); - } -@@ -4700,12 +4706,12 @@ - - ret = 0; - -- local_irq_disable(); -+ local_lock_irq(event_lock); - mem_cgroup_charge_statistics(to, page, nr_pages); - memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); - memcg_check_events(from, page); -- local_irq_enable(); -+ local_unlock_irq(event_lock); - out_unlock: - unlock_page(page); - out: -@@ -5495,10 +5501,10 @@ - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - -- local_irq_disable(); -+ local_lock_irq(event_lock); - mem_cgroup_charge_statistics(memcg, page, nr_pages); - memcg_check_events(memcg, page); -- local_irq_enable(); -+ local_unlock_irq(event_lock); - - if (do_swap_account && PageSwapCache(page)) { - swp_entry_t entry = { .val = page_private(page) }; -@@ -5554,14 +5560,14 @@ - memcg_oom_recover(memcg); - } - -- local_irq_save(flags); -+ local_lock_irqsave(event_lock, flags); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); - __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); - __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); - __this_cpu_add(memcg->stat->nr_page_events, nr_pages); - memcg_check_events(memcg, dummy_page); -- local_irq_restore(flags); -+ local_unlock_irqrestore(event_lock, flags); - - if (!mem_cgroup_is_root(memcg)) - css_put_many(&memcg->css, nr_pages); -@@ -5753,6 +5759,7 @@ - { - struct mem_cgroup *memcg, *swap_memcg; - unsigned short oldid; -+ unsigned long flags; - - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); -@@ -5793,12 +5800,16 @@ - * important here to have the interrupts disabled because it is the - * only synchronisation we have for udpating the per-CPU variables. - */ -+ local_lock_irqsave(event_lock, flags); -+#ifndef CONFIG_PREEMPT_RT_BASE - VM_BUG_ON(!irqs_disabled()); -+#endif - mem_cgroup_charge_statistics(memcg, page, -1); - memcg_check_events(memcg, page); - - if (!mem_cgroup_is_root(memcg)) - css_put(&memcg->css); -+ local_unlock_irqrestore(event_lock, flags); - } - - /** -diff -Nur linux-4.4.28.orig/mm/mmu_context.c linux-4.4.28/mm/mmu_context.c ---- linux-4.4.28.orig/mm/mmu_context.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/mmu_context.c 2016-11-01 21:26:58.820345117 +0100 -@@ -23,6 +23,7 @@ - struct task_struct *tsk = current; - - task_lock(tsk); -+ preempt_disable_rt(); - active_mm = tsk->active_mm; - if (active_mm != mm) { - atomic_inc(&mm->mm_count); -@@ -30,6 +31,7 @@ - } - tsk->mm = mm; - switch_mm(active_mm, mm, tsk); -+ preempt_enable_rt(); - task_unlock(tsk); - #ifdef finish_arch_post_lock_switch - finish_arch_post_lock_switch(); -diff -Nur linux-4.4.28.orig/mm/page_alloc.c linux-4.4.28/mm/page_alloc.c ---- linux-4.4.28.orig/mm/page_alloc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/page_alloc.c 2016-11-01 21:26:58.824345373 +0100 -@@ -60,6 +60,7 @@ - #include - #include - #include -+#include - #include - #include - -@@ -264,6 +265,18 @@ - EXPORT_SYMBOL(nr_online_nodes); - #endif - -+static DEFINE_LOCAL_IRQ_LOCK(pa_lock); -+ -+#ifdef CONFIG_PREEMPT_RT_BASE -+# define cpu_lock_irqsave(cpu, flags) \ -+ local_lock_irqsave_on(pa_lock, flags, cpu) -+# define cpu_unlock_irqrestore(cpu, flags) \ -+ local_unlock_irqrestore_on(pa_lock, flags, cpu) -+#else -+# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) -+# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) -+#endif -+ - int page_group_by_mobility_disabled __read_mostly; - - #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -@@ -786,7 +799,7 @@ - } - - /* -- * Frees a number of pages from the PCP lists -+ * Frees a number of pages which have been collected from the pcp lists. - * Assumes all pages on list are in same zone, and of same order. - * count is the number of pages to free. - * -@@ -797,18 +810,53 @@ - * pinned" detection logic. - */ - static void free_pcppages_bulk(struct zone *zone, int count, -- struct per_cpu_pages *pcp) -+ struct list_head *list) - { -- int migratetype = 0; -- int batch_free = 0; - int to_free = count; - unsigned long nr_scanned; -+ unsigned long flags; -+ -+ spin_lock_irqsave(&zone->lock, flags); - -- spin_lock(&zone->lock); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); - if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); - -+ while (!list_empty(list)) { -+ struct page *page = list_first_entry(list, struct page, lru); -+ int mt; /* migratetype of the to-be-freed page */ -+ -+ /* must delete as __free_one_page list manipulates */ -+ list_del(&page->lru); -+ -+ mt = get_pcppage_migratetype(page); -+ /* MIGRATE_ISOLATE page should not go to pcplists */ -+ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); -+ /* Pageblock could have been isolated meanwhile */ -+ if (unlikely(has_isolate_pageblock(zone))) -+ mt = get_pageblock_migratetype(page); -+ -+ __free_one_page(page, page_to_pfn(page), zone, 0, mt); -+ trace_mm_page_pcpu_drain(page, 0, mt); -+ to_free--; -+ } -+ WARN_ON(to_free != 0); -+ spin_unlock_irqrestore(&zone->lock, flags); -+} -+ -+/* -+ * Moves a number of pages from the PCP lists to free list which -+ * is freed outside of the locked region. -+ * -+ * Assumes all pages on list are in same zone, and of same order. -+ * count is the number of pages to free. -+ */ -+static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, -+ struct list_head *dst) -+{ -+ int migratetype = 0; -+ int batch_free = 0; -+ - while (to_free) { - struct page *page; - struct list_head *list; -@@ -824,7 +872,7 @@ - batch_free++; - if (++migratetype == MIGRATE_PCPTYPES) - migratetype = 0; -- list = &pcp->lists[migratetype]; -+ list = &src->lists[migratetype]; - } while (list_empty(list)); - - /* This is the only non-empty list. Free them all. */ -@@ -832,24 +880,12 @@ - batch_free = to_free; - - do { -- int mt; /* migratetype of the to-be-freed page */ -- -- page = list_entry(list->prev, struct page, lru); -- /* must delete as __free_one_page list manipulates */ -+ page = list_last_entry(list, struct page, lru); - list_del(&page->lru); - -- mt = get_pcppage_migratetype(page); -- /* MIGRATE_ISOLATE page should not go to pcplists */ -- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); -- /* Pageblock could have been isolated meanwhile */ -- if (unlikely(has_isolate_pageblock(zone))) -- mt = get_pageblock_migratetype(page); -- -- __free_one_page(page, page_to_pfn(page), zone, 0, mt); -- trace_mm_page_pcpu_drain(page, 0, mt); -+ list_add(&page->lru, dst); - } while (--to_free && --batch_free && !list_empty(list)); - } -- spin_unlock(&zone->lock); - } - - static void free_one_page(struct zone *zone, -@@ -858,7 +894,9 @@ - int migratetype) - { - unsigned long nr_scanned; -- spin_lock(&zone->lock); -+ unsigned long flags; -+ -+ spin_lock_irqsave(&zone->lock, flags); - nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); - if (nr_scanned) - __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); -@@ -868,7 +906,7 @@ - migratetype = get_pfnblock_migratetype(page, pfn); - } - __free_one_page(page, pfn, zone, order, migratetype); -- spin_unlock(&zone->lock); -+ spin_unlock_irqrestore(&zone->lock, flags); - } - - static int free_tail_pages_check(struct page *head_page, struct page *page) -@@ -1019,10 +1057,10 @@ - return; - - migratetype = get_pfnblock_migratetype(page, pfn); -- local_irq_save(flags); -+ local_lock_irqsave(pa_lock, flags); - __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype); -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); - } - - static void __init __free_pages_boot_core(struct page *page, -@@ -1879,16 +1917,18 @@ - void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) - { - unsigned long flags; -+ LIST_HEAD(dst); - int to_drain, batch; - -- local_irq_save(flags); -+ local_lock_irqsave(pa_lock, flags); - batch = READ_ONCE(pcp->batch); - to_drain = min(pcp->count, batch); - if (to_drain > 0) { -- free_pcppages_bulk(zone, to_drain, pcp); -+ isolate_pcp_pages(to_drain, pcp, &dst); - pcp->count -= to_drain; - } -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); -+ free_pcppages_bulk(zone, to_drain, &dst); - } - #endif - -@@ -1904,16 +1944,21 @@ - unsigned long flags; - struct per_cpu_pageset *pset; - struct per_cpu_pages *pcp; -+ LIST_HEAD(dst); -+ int count; - -- local_irq_save(flags); -+ cpu_lock_irqsave(cpu, flags); - pset = per_cpu_ptr(zone->pageset, cpu); - - pcp = &pset->pcp; -- if (pcp->count) { -- free_pcppages_bulk(zone, pcp->count, pcp); -+ count = pcp->count; -+ if (count) { -+ isolate_pcp_pages(count, pcp, &dst); - pcp->count = 0; - } -- local_irq_restore(flags); -+ cpu_unlock_irqrestore(cpu, flags); -+ if (count) -+ free_pcppages_bulk(zone, count, &dst); - } - - /* -@@ -1999,8 +2044,17 @@ - else - cpumask_clear_cpu(cpu, &cpus_with_pcps); - } -+#ifndef CONFIG_PREEMPT_RT_BASE - on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages, - zone, 1); -+#else -+ for_each_cpu(cpu, &cpus_with_pcps) { -+ if (zone) -+ drain_pages_zone(cpu, zone); -+ else -+ drain_pages(cpu); -+ } -+#endif - } - - #ifdef CONFIG_HIBERNATION -@@ -2056,7 +2110,7 @@ - - migratetype = get_pfnblock_migratetype(page, pfn); - set_pcppage_migratetype(page, migratetype); -- local_irq_save(flags); -+ local_lock_irqsave(pa_lock, flags); - __count_vm_event(PGFREE); - - /* -@@ -2082,12 +2136,17 @@ - pcp->count++; - if (pcp->count >= pcp->high) { - unsigned long batch = READ_ONCE(pcp->batch); -- free_pcppages_bulk(zone, batch, pcp); -+ LIST_HEAD(dst); -+ -+ isolate_pcp_pages(batch, pcp, &dst); - pcp->count -= batch; -+ local_unlock_irqrestore(pa_lock, flags); -+ free_pcppages_bulk(zone, batch, &dst); -+ return; - } - - out: -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); - } - - /* -@@ -2222,7 +2281,7 @@ - struct per_cpu_pages *pcp; - struct list_head *list; - -- local_irq_save(flags); -+ local_lock_irqsave(pa_lock, flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - if (list_empty(list)) { -@@ -2254,7 +2313,7 @@ - */ - WARN_ON_ONCE(order > 1); - } -- spin_lock_irqsave(&zone->lock, flags); -+ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); - - page = NULL; - if (alloc_flags & ALLOC_HARDER) { -@@ -2264,11 +2323,13 @@ - } - if (!page) - page = __rmqueue(zone, order, migratetype, gfp_flags); -- spin_unlock(&zone->lock); -- if (!page) -+ if (!page) { -+ spin_unlock(&zone->lock); - goto failed; -+ } - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); -+ spin_unlock(&zone->lock); - } - - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); -@@ -2278,13 +2339,13 @@ - - __count_zone_vm_events(PGALLOC, zone, 1 << order); - zone_statistics(preferred_zone, zone, gfp_flags); -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); - - VM_BUG_ON_PAGE(bad_range(zone, page), page); - return page; - - failed: -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); - return NULL; - } - -@@ -5950,6 +6011,7 @@ - void __init page_alloc_init(void) - { - hotcpu_notifier(page_alloc_cpu_notify, 0); -+ local_irq_lock_init(pa_lock); - } - - /* -@@ -6844,7 +6906,7 @@ - struct per_cpu_pageset *pset; - - /* avoid races with drain_pages() */ -- local_irq_save(flags); -+ local_lock_irqsave(pa_lock, flags); - if (zone->pageset != &boot_pageset) { - for_each_online_cpu(cpu) { - pset = per_cpu_ptr(zone->pageset, cpu); -@@ -6853,7 +6915,7 @@ - free_percpu(zone->pageset); - zone->pageset = &boot_pageset; - } -- local_irq_restore(flags); -+ local_unlock_irqrestore(pa_lock, flags); - } - - #ifdef CONFIG_MEMORY_HOTREMOVE -diff -Nur linux-4.4.28.orig/mm/slab.h linux-4.4.28/mm/slab.h ---- linux-4.4.28.orig/mm/slab.h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/slab.h 2016-11-01 21:26:58.824345373 +0100 -@@ -324,7 +324,11 @@ - * The slab lists for all objects. - */ - struct kmem_cache_node { -+#ifdef CONFIG_SLUB -+ raw_spinlock_t list_lock; -+#else - spinlock_t list_lock; -+#endif - - #ifdef CONFIG_SLAB - struct list_head slabs_partial; /* partial list first, better asm code */ -diff -Nur linux-4.4.28.orig/mm/slub.c linux-4.4.28/mm/slub.c ---- linux-4.4.28.orig/mm/slub.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/slub.c 2016-11-01 21:26:58.828345638 +0100 -@@ -1075,7 +1075,7 @@ - void *object = head; - int cnt = 0; - -- spin_lock_irqsave(&n->list_lock, *flags); -+ raw_spin_lock_irqsave(&n->list_lock, *flags); - slab_lock(page); - - if (!check_slab(s, page)) -@@ -1136,7 +1136,7 @@ - - fail: - slab_unlock(page); -- spin_unlock_irqrestore(&n->list_lock, *flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, *flags); - slab_fix(s, "Object at 0x%p not freed", object); - return NULL; - } -@@ -1263,6 +1263,12 @@ - - #endif /* CONFIG_SLUB_DEBUG */ - -+struct slub_free_list { -+ raw_spinlock_t lock; -+ struct list_head list; -+}; -+static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); -+ - /* - * Hooks for other subsystems that check memory allocations. In a typical - * production configuration these hooks all should produce no code at all. -@@ -1399,10 +1405,17 @@ - gfp_t alloc_gfp; - void *start, *p; - int idx, order; -+ bool enableirqs = false; - - flags &= gfp_allowed_mask; - - if (gfpflags_allow_blocking(flags)) -+ enableirqs = true; -+#ifdef CONFIG_PREEMPT_RT_FULL -+ if (system_state == SYSTEM_RUNNING) -+ enableirqs = true; -+#endif -+ if (enableirqs) - local_irq_enable(); - - flags |= s->allocflags; -@@ -1473,7 +1486,7 @@ - page->frozen = 1; - - out: -- if (gfpflags_allow_blocking(flags)) -+ if (enableirqs) - local_irq_disable(); - if (!page) - return NULL; -@@ -1529,6 +1542,16 @@ - __free_kmem_pages(page, order); - } - -+static void free_delayed(struct list_head *h) -+{ -+ while(!list_empty(h)) { -+ struct page *page = list_first_entry(h, struct page, lru); -+ -+ list_del(&page->lru); -+ __free_slab(page->slab_cache, page); -+ } -+} -+ - #define need_reserve_slab_rcu \ - (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) - -@@ -1560,6 +1583,12 @@ - } - - call_rcu(head, rcu_free_slab); -+ } else if (irqs_disabled()) { -+ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); -+ -+ raw_spin_lock(&f->lock); -+ list_add(&page->lru, &f->list); -+ raw_spin_unlock(&f->lock); - } else - __free_slab(s, page); - } -@@ -1673,7 +1702,7 @@ - if (!n || !n->nr_partial) - return NULL; - -- spin_lock(&n->list_lock); -+ raw_spin_lock(&n->list_lock); - list_for_each_entry_safe(page, page2, &n->partial, lru) { - void *t; - -@@ -1698,7 +1727,7 @@ - break; - - } -- spin_unlock(&n->list_lock); -+ raw_spin_unlock(&n->list_lock); - return object; - } - -@@ -1944,7 +1973,7 @@ - * that acquire_slab() will see a slab page that - * is frozen - */ -- spin_lock(&n->list_lock); -+ raw_spin_lock(&n->list_lock); - } - } else { - m = M_FULL; -@@ -1955,7 +1984,7 @@ - * slabs from diagnostic functions will not see - * any frozen slabs. - */ -- spin_lock(&n->list_lock); -+ raw_spin_lock(&n->list_lock); - } - } - -@@ -1990,7 +2019,7 @@ - goto redo; - - if (lock) -- spin_unlock(&n->list_lock); -+ raw_spin_unlock(&n->list_lock); - - if (m == M_FREE) { - stat(s, DEACTIVATE_EMPTY); -@@ -2022,10 +2051,10 @@ - n2 = get_node(s, page_to_nid(page)); - if (n != n2) { - if (n) -- spin_unlock(&n->list_lock); -+ raw_spin_unlock(&n->list_lock); - - n = n2; -- spin_lock(&n->list_lock); -+ raw_spin_lock(&n->list_lock); - } - - do { -@@ -2054,7 +2083,7 @@ - } - - if (n) -- spin_unlock(&n->list_lock); -+ raw_spin_unlock(&n->list_lock); - - while (discard_page) { - page = discard_page; -@@ -2093,14 +2122,21 @@ - pobjects = oldpage->pobjects; - pages = oldpage->pages; - if (drain && pobjects > s->cpu_partial) { -+ struct slub_free_list *f; - unsigned long flags; -+ LIST_HEAD(tofree); - /* - * partial array is full. Move the existing - * set to the per node partial list. - */ - local_irq_save(flags); - unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); -+ f = this_cpu_ptr(&slub_free_list); -+ raw_spin_lock(&f->lock); -+ list_splice_init(&f->list, &tofree); -+ raw_spin_unlock(&f->lock); - local_irq_restore(flags); -+ free_delayed(&tofree); - oldpage = NULL; - pobjects = 0; - pages = 0; -@@ -2172,7 +2208,22 @@ - - static void flush_all(struct kmem_cache *s) - { -+ LIST_HEAD(tofree); -+ int cpu; -+ - on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); -+ for_each_online_cpu(cpu) { -+ struct slub_free_list *f; -+ -+ if (!has_cpu_slab(cpu, s)) -+ continue; -+ -+ f = &per_cpu(slub_free_list, cpu); -+ raw_spin_lock_irq(&f->lock); -+ list_splice_init(&f->list, &tofree); -+ raw_spin_unlock_irq(&f->lock); -+ free_delayed(&tofree); -+ } - } - - /* -@@ -2208,10 +2259,10 @@ - unsigned long x = 0; - struct page *page; - -- spin_lock_irqsave(&n->list_lock, flags); -+ raw_spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, lru) - x += get_count(page); -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - return x; - } - #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ -@@ -2349,8 +2400,10 @@ - * already disabled (which is the case for bulk allocation). - */ - static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, -- unsigned long addr, struct kmem_cache_cpu *c) -+ unsigned long addr, struct kmem_cache_cpu *c, -+ struct list_head *to_free) - { -+ struct slub_free_list *f; - void *freelist; - struct page *page; - -@@ -2410,6 +2463,13 @@ - VM_BUG_ON(!c->page->frozen); - c->freelist = get_freepointer(s, freelist); - c->tid = next_tid(c->tid); -+ -+out: -+ f = this_cpu_ptr(&slub_free_list); -+ raw_spin_lock(&f->lock); -+ list_splice_init(&f->list, to_free); -+ raw_spin_unlock(&f->lock); -+ - return freelist; - - new_slab: -@@ -2441,7 +2501,7 @@ - deactivate_slab(s, page, get_freepointer(s, freelist)); - c->page = NULL; - c->freelist = NULL; -- return freelist; -+ goto out; - } - - /* -@@ -2453,6 +2513,7 @@ - { - void *p; - unsigned long flags; -+ LIST_HEAD(tofree); - - local_irq_save(flags); - #ifdef CONFIG_PREEMPT -@@ -2464,8 +2525,9 @@ - c = this_cpu_ptr(s->cpu_slab); - #endif - -- p = ___slab_alloc(s, gfpflags, node, addr, c); -+ p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree); - local_irq_restore(flags); -+ free_delayed(&tofree); - return p; - } - -@@ -2652,7 +2714,7 @@ - - do { - if (unlikely(n)) { -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - n = NULL; - } - prior = page->freelist; -@@ -2684,7 +2746,7 @@ - * Otherwise the list_lock will synchronize with - * other processors updating the list of slabs. - */ -- spin_lock_irqsave(&n->list_lock, flags); -+ raw_spin_lock_irqsave(&n->list_lock, flags); - - } - } -@@ -2726,7 +2788,7 @@ - add_partial(n, page, DEACTIVATE_TO_TAIL); - stat(s, FREE_ADD_PARTIAL); - } -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - return; - - slab_empty: -@@ -2741,7 +2803,7 @@ - remove_full(s, n, page); - } - -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - stat(s, FREE_SLAB); - discard_slab(s, page); - } -@@ -2913,6 +2975,7 @@ - void **p) - { - struct kmem_cache_cpu *c; -+ LIST_HEAD(to_free); - int i; - - /* memcg and kmem_cache debug support */ -@@ -2936,7 +2999,7 @@ - * of re-populating per CPU c->freelist - */ - p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, -- _RET_IP_, c); -+ _RET_IP_, c, &to_free); - if (unlikely(!p[i])) - goto error; - -@@ -2948,6 +3011,7 @@ - } - c->tid = next_tid(c->tid); - local_irq_enable(); -+ free_delayed(&to_free); - - /* Clear memory outside IRQ disabled fastpath loop */ - if (unlikely(flags & __GFP_ZERO)) { -@@ -3095,7 +3159,7 @@ - init_kmem_cache_node(struct kmem_cache_node *n) - { - n->nr_partial = 0; -- spin_lock_init(&n->list_lock); -+ raw_spin_lock_init(&n->list_lock); - INIT_LIST_HEAD(&n->partial); - #ifdef CONFIG_SLUB_DEBUG - atomic_long_set(&n->nr_slabs, 0); -@@ -3677,7 +3741,7 @@ - for (i = 0; i < SHRINK_PROMOTE_MAX; i++) - INIT_LIST_HEAD(promote + i); - -- spin_lock_irqsave(&n->list_lock, flags); -+ raw_spin_lock_irqsave(&n->list_lock, flags); - - /* - * Build lists of slabs to discard or promote. -@@ -3708,7 +3772,7 @@ - for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) - list_splice(promote + i, &n->partial); - -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - - /* Release empty slabs */ - list_for_each_entry_safe(page, t, &discard, lru) -@@ -3884,6 +3948,12 @@ - { - static __initdata struct kmem_cache boot_kmem_cache, - boot_kmem_cache_node; -+ int cpu; -+ -+ for_each_possible_cpu(cpu) { -+ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); -+ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); -+ } - - if (debug_guardpage_minorder()) - slub_max_order = 0; -@@ -4127,7 +4197,7 @@ - struct page *page; - unsigned long flags; - -- spin_lock_irqsave(&n->list_lock, flags); -+ raw_spin_lock_irqsave(&n->list_lock, flags); - - list_for_each_entry(page, &n->partial, lru) { - validate_slab_slab(s, page, map); -@@ -4149,7 +4219,7 @@ - s->name, count, atomic_long_read(&n->nr_slabs)); - - out: -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - return count; - } - -@@ -4337,12 +4407,12 @@ - if (!atomic_long_read(&n->nr_slabs)) - continue; - -- spin_lock_irqsave(&n->list_lock, flags); -+ raw_spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, lru) - process_slab(&t, s, page, alloc, map); - list_for_each_entry(page, &n->full, lru) - process_slab(&t, s, page, alloc, map); -- spin_unlock_irqrestore(&n->list_lock, flags); -+ raw_spin_unlock_irqrestore(&n->list_lock, flags); - } - - for (i = 0; i < t.count; i++) { -diff -Nur linux-4.4.28.orig/mm/swap.c linux-4.4.28/mm/swap.c ---- linux-4.4.28.orig/mm/swap.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/swap.c 2016-11-01 21:26:58.828345638 +0100 -@@ -31,6 +31,7 @@ - #include - #include - #include -+#include - #include - #include - -@@ -46,6 +47,9 @@ - static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); - static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); - -+static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); -+DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); -+ - /* - * This path almost never happens for VM activity - pages are normally - * freed via pagevecs. But it gets used by networking. -@@ -481,11 +485,11 @@ - unsigned long flags; - - page_cache_get(page); -- local_irq_save(flags); -+ local_lock_irqsave(rotate_lock, flags); - pvec = this_cpu_ptr(&lru_rotate_pvecs); - if (!pagevec_add(pvec, page)) - pagevec_move_tail(pvec); -- local_irq_restore(flags); -+ local_unlock_irqrestore(rotate_lock, flags); - } - } - -@@ -536,12 +540,13 @@ - void activate_page(struct page *page) - { - if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { -- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); -+ struct pagevec *pvec = &get_locked_var(swapvec_lock, -+ activate_page_pvecs); - - page_cache_get(page); - if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, __activate_page, NULL); -- put_cpu_var(activate_page_pvecs); -+ put_locked_var(swapvec_lock, activate_page_pvecs); - } - } - -@@ -567,7 +572,7 @@ - - static void __lru_cache_activate_page(struct page *page) - { -- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); -+ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); - int i; - - /* -@@ -589,7 +594,7 @@ - } - } - -- put_cpu_var(lru_add_pvec); -+ put_locked_var(swapvec_lock, lru_add_pvec); - } - - /* -@@ -630,13 +635,13 @@ - - static void __lru_cache_add(struct page *page) - { -- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); -+ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); - - page_cache_get(page); - if (!pagevec_space(pvec)) - __pagevec_lru_add(pvec); - pagevec_add(pvec, page); -- put_cpu_var(lru_add_pvec); -+ put_locked_var(swapvec_lock, lru_add_pvec); - } - - /** -@@ -816,9 +821,15 @@ - unsigned long flags; - - /* No harm done if a racing interrupt already did this */ -- local_irq_save(flags); -+#ifdef CONFIG_PREEMPT_RT_BASE -+ local_lock_irqsave_on(rotate_lock, flags, cpu); -+ pagevec_move_tail(pvec); -+ local_unlock_irqrestore_on(rotate_lock, flags, cpu); -+#else -+ local_lock_irqsave(rotate_lock, flags); - pagevec_move_tail(pvec); -- local_irq_restore(flags); -+ local_unlock_irqrestore(rotate_lock, flags); -+#endif - } - - pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); -@@ -846,26 +857,47 @@ - return; - - if (likely(get_page_unless_zero(page))) { -- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); -+ struct pagevec *pvec = &get_locked_var(swapvec_lock, -+ lru_deactivate_file_pvecs); - - if (!pagevec_add(pvec, page)) - pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); -- put_cpu_var(lru_deactivate_file_pvecs); -+ put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); - } - } - - void lru_add_drain(void) - { -- lru_add_drain_cpu(get_cpu()); -- put_cpu(); -+ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); -+ local_unlock_cpu(swapvec_lock); - } - -+ -+#ifdef CONFIG_PREEMPT_RT_BASE -+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) -+{ -+ local_lock_on(swapvec_lock, cpu); -+ lru_add_drain_cpu(cpu); -+ local_unlock_on(swapvec_lock, cpu); -+} -+ -+#else -+ - static void lru_add_drain_per_cpu(struct work_struct *dummy) - { - lru_add_drain(); - } - - static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); -+static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) -+{ -+ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); -+ -+ INIT_WORK(work, lru_add_drain_per_cpu); -+ schedule_work_on(cpu, work); -+ cpumask_set_cpu(cpu, has_work); -+} -+#endif - - void lru_add_drain_all(void) - { -@@ -878,20 +910,17 @@ - cpumask_clear(&has_work); - - for_each_online_cpu(cpu) { -- struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); -- - if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || - pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || - pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || -- need_activate_page_drain(cpu)) { -- INIT_WORK(work, lru_add_drain_per_cpu); -- schedule_work_on(cpu, work); -- cpumask_set_cpu(cpu, &has_work); -- } -+ need_activate_page_drain(cpu)) -+ remote_lru_add_drain(cpu, &has_work); - } - -+#ifndef CONFIG_PREEMPT_RT_BASE - for_each_cpu(cpu, &has_work) - flush_work(&per_cpu(lru_add_drain_work, cpu)); -+#endif - - put_online_cpus(); - mutex_unlock(&lock); -diff -Nur linux-4.4.28.orig/mm/truncate.c linux-4.4.28/mm/truncate.c ---- linux-4.4.28.orig/mm/truncate.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/truncate.c 2016-11-01 21:26:58.828345638 +0100 -@@ -56,8 +56,11 @@ - * protected by mapping->tree_lock. - */ - if (!workingset_node_shadows(node) && -- !list_empty(&node->private_list)) -- list_lru_del(&workingset_shadow_nodes, &node->private_list); -+ !list_empty(&node->private_list)) { -+ local_lock(workingset_shadow_lock); -+ list_lru_del(&__workingset_shadow_nodes, &node->private_list); -+ local_unlock(workingset_shadow_lock); -+ } - __radix_tree_delete_node(&mapping->page_tree, node); - unlock: - spin_unlock_irq(&mapping->tree_lock); -diff -Nur linux-4.4.28.orig/mm/vmalloc.c linux-4.4.28/mm/vmalloc.c ---- linux-4.4.28.orig/mm/vmalloc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/vmalloc.c 2016-11-01 21:26:58.828345638 +0100 -@@ -821,7 +821,7 @@ - struct vmap_block *vb; - struct vmap_area *va; - unsigned long vb_idx; -- int node, err; -+ int node, err, cpu; - void *vaddr; - - node = numa_node_id(); -@@ -864,11 +864,12 @@ - BUG_ON(err); - radix_tree_preload_end(); - -- vbq = &get_cpu_var(vmap_block_queue); -+ cpu = get_cpu_light(); -+ vbq = this_cpu_ptr(&vmap_block_queue); - spin_lock(&vbq->lock); - list_add_tail_rcu(&vb->free_list, &vbq->free); - spin_unlock(&vbq->lock); -- put_cpu_var(vmap_block_queue); -+ put_cpu_light(); - - return vaddr; - } -@@ -937,6 +938,7 @@ - struct vmap_block *vb; - void *vaddr = NULL; - unsigned int order; -+ int cpu; - - BUG_ON(offset_in_page(size)); - BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); -@@ -951,7 +953,8 @@ - order = get_order(size); - - rcu_read_lock(); -- vbq = &get_cpu_var(vmap_block_queue); -+ cpu = get_cpu_light(); -+ vbq = this_cpu_ptr(&vmap_block_queue); - list_for_each_entry_rcu(vb, &vbq->free, free_list) { - unsigned long pages_off; - -@@ -974,7 +977,7 @@ - break; - } - -- put_cpu_var(vmap_block_queue); -+ put_cpu_light(); - rcu_read_unlock(); - - /* Allocate new block if nothing was found */ -diff -Nur linux-4.4.28.orig/mm/vmstat.c linux-4.4.28/mm/vmstat.c ---- linux-4.4.28.orig/mm/vmstat.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/vmstat.c 2016-11-01 21:26:58.828345638 +0100 -@@ -226,6 +226,7 @@ - long x; - long t; - -+ preempt_disable_rt(); - x = delta + __this_cpu_read(*p); - - t = __this_cpu_read(pcp->stat_threshold); -@@ -235,6 +236,7 @@ - x = 0; - } - __this_cpu_write(*p, x); -+ preempt_enable_rt(); - } - EXPORT_SYMBOL(__mod_zone_page_state); - -@@ -267,6 +269,7 @@ - s8 __percpu *p = pcp->vm_stat_diff + item; - s8 v, t; - -+ preempt_disable_rt(); - v = __this_cpu_inc_return(*p); - t = __this_cpu_read(pcp->stat_threshold); - if (unlikely(v > t)) { -@@ -275,6 +278,7 @@ - zone_page_state_add(v + overstep, zone, item); - __this_cpu_write(*p, -overstep); - } -+ preempt_enable_rt(); - } - - void __inc_zone_page_state(struct page *page, enum zone_stat_item item) -@@ -289,6 +293,7 @@ - s8 __percpu *p = pcp->vm_stat_diff + item; - s8 v, t; - -+ preempt_disable_rt(); - v = __this_cpu_dec_return(*p); - t = __this_cpu_read(pcp->stat_threshold); - if (unlikely(v < - t)) { -@@ -297,6 +302,7 @@ - zone_page_state_add(v - overstep, zone, item); - __this_cpu_write(*p, overstep); - } -+ preempt_enable_rt(); - } - - void __dec_zone_page_state(struct page *page, enum zone_stat_item item) -diff -Nur linux-4.4.28.orig/mm/workingset.c linux-4.4.28/mm/workingset.c ---- linux-4.4.28.orig/mm/workingset.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/workingset.c 2016-11-01 21:26:58.832345891 +0100 -@@ -264,7 +264,8 @@ - * point where they would still be useful. - */ - --struct list_lru workingset_shadow_nodes; -+struct list_lru __workingset_shadow_nodes; -+DEFINE_LOCAL_IRQ_LOCK(workingset_shadow_lock); - - static unsigned long count_shadow_nodes(struct shrinker *shrinker, - struct shrink_control *sc) -@@ -274,9 +275,9 @@ - unsigned long pages; - - /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ -- local_irq_disable(); -- shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); -- local_irq_enable(); -+ local_lock_irq(workingset_shadow_lock); -+ shadow_nodes = list_lru_shrink_count(&__workingset_shadow_nodes, sc); -+ local_unlock_irq(workingset_shadow_lock); - - pages = node_present_pages(sc->nid); - /* -@@ -361,9 +362,9 @@ - spin_unlock(&mapping->tree_lock); - ret = LRU_REMOVED_RETRY; - out: -- local_irq_enable(); -+ local_unlock_irq(workingset_shadow_lock); - cond_resched(); -- local_irq_disable(); -+ local_lock_irq(workingset_shadow_lock); - spin_lock(lru_lock); - return ret; - } -@@ -374,10 +375,10 @@ - unsigned long ret; - - /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ -- local_irq_disable(); -- ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc, -+ local_lock_irq(workingset_shadow_lock); -+ ret = list_lru_shrink_walk(&__workingset_shadow_nodes, sc, - shadow_lru_isolate, NULL); -- local_irq_enable(); -+ local_unlock_irq(workingset_shadow_lock); - return ret; - } - -@@ -398,7 +399,7 @@ - { - int ret; - -- ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); -+ ret = list_lru_init_key(&__workingset_shadow_nodes, &shadow_nodes_key); - if (ret) - goto err; - ret = register_shrinker(&workingset_shadow_shrinker); -@@ -406,7 +407,7 @@ - goto err_list_lru; - return 0; - err_list_lru: -- list_lru_destroy(&workingset_shadow_nodes); -+ list_lru_destroy(&__workingset_shadow_nodes); - err: - return ret; - } -diff -Nur linux-4.4.28.orig/mm/zsmalloc.c linux-4.4.28/mm/zsmalloc.c ---- linux-4.4.28.orig/mm/zsmalloc.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/mm/zsmalloc.c 2016-11-01 21:26:58.832345891 +0100 -@@ -64,6 +64,7 @@ - #include - #include - #include -+#include - - /* - * This must be power of 2 and greater than of equal to sizeof(link_free). -@@ -403,6 +404,7 @@ - - /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ - static DEFINE_PER_CPU(struct mapping_area, zs_map_area); -+static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); - - static int is_first_page(struct page *page) - { -@@ -1289,7 +1291,7 @@ - class = pool->size_class[class_idx]; - off = obj_idx_to_offset(page, obj_idx, class->size); - -- area = &get_cpu_var(zs_map_area); -+ area = &get_locked_var(zs_map_area_lock, zs_map_area); - area->vm_mm = mm; - if (off + class->size <= PAGE_SIZE) { - /* this object is contained entirely within a page */ -@@ -1342,7 +1344,7 @@ - - __zs_unmap_object(area, pages, off, class->size); - } -- put_cpu_var(zs_map_area); -+ put_locked_var(zs_map_area_lock, zs_map_area); - unpin_tag(handle); - } - EXPORT_SYMBOL_GPL(zs_unmap_object); -diff -Nur linux-4.4.28.orig/net/core/dev.c linux-4.4.28/net/core/dev.c ---- linux-4.4.28.orig/net/core/dev.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/core/dev.c 2016-11-01 21:26:58.836346147 +0100 -@@ -186,6 +186,7 @@ - static DEFINE_HASHTABLE(napi_hash, 8); - - static seqcount_t devnet_rename_seq; -+static DEFINE_MUTEX(devnet_rename_mutex); - - static inline void dev_base_seq_inc(struct net *net) - { -@@ -207,14 +208,14 @@ - static inline void rps_lock(struct softnet_data *sd) - { - #ifdef CONFIG_RPS -- spin_lock(&sd->input_pkt_queue.lock); -+ raw_spin_lock(&sd->input_pkt_queue.raw_lock); - #endif - } - - static inline void rps_unlock(struct softnet_data *sd) - { - #ifdef CONFIG_RPS -- spin_unlock(&sd->input_pkt_queue.lock); -+ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); - #endif - } - -@@ -884,7 +885,8 @@ - strcpy(name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) { -- cond_resched(); -+ mutex_lock(&devnet_rename_mutex); -+ mutex_unlock(&devnet_rename_mutex); - goto retry; - } - -@@ -1153,20 +1155,17 @@ - if (dev->flags & IFF_UP) - return -EBUSY; - -- write_seqcount_begin(&devnet_rename_seq); -+ mutex_lock(&devnet_rename_mutex); -+ __raw_write_seqcount_begin(&devnet_rename_seq); - -- if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { -- write_seqcount_end(&devnet_rename_seq); -- return 0; -- } -+ if (strncmp(newname, dev->name, IFNAMSIZ) == 0) -+ goto outunlock; - - memcpy(oldname, dev->name, IFNAMSIZ); - - err = dev_get_valid_name(net, dev, newname); -- if (err < 0) { -- write_seqcount_end(&devnet_rename_seq); -- return err; -- } -+ if (err < 0) -+ goto outunlock; - - if (oldname[0] && !strchr(oldname, '%')) - netdev_info(dev, "renamed from %s\n", oldname); -@@ -1179,11 +1178,12 @@ - if (ret) { - memcpy(dev->name, oldname, IFNAMSIZ); - dev->name_assign_type = old_assign_type; -- write_seqcount_end(&devnet_rename_seq); -- return ret; -+ err = ret; -+ goto outunlock; - } - -- write_seqcount_end(&devnet_rename_seq); -+ __raw_write_seqcount_end(&devnet_rename_seq); -+ mutex_unlock(&devnet_rename_mutex); - - netdev_adjacent_rename_links(dev, oldname); - -@@ -1204,7 +1204,8 @@ - /* err >= 0 after dev_alloc_name() or stores the first errno */ - if (err >= 0) { - err = ret; -- write_seqcount_begin(&devnet_rename_seq); -+ mutex_lock(&devnet_rename_mutex); -+ __raw_write_seqcount_begin(&devnet_rename_seq); - memcpy(dev->name, oldname, IFNAMSIZ); - memcpy(oldname, newname, IFNAMSIZ); - dev->name_assign_type = old_assign_type; -@@ -1217,6 +1218,11 @@ - } - - return err; -+ -+outunlock: -+ __raw_write_seqcount_end(&devnet_rename_seq); -+ mutex_unlock(&devnet_rename_mutex); -+ return err; - } - - /** -@@ -2246,6 +2252,7 @@ - sd->output_queue_tailp = &q->next_sched; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - - void __netif_schedule(struct Qdisc *q) -@@ -2327,6 +2334,7 @@ - __this_cpu_write(softnet_data.completion_queue, skb); - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - EXPORT_SYMBOL(__dev_kfree_skb_irq); - -@@ -2883,7 +2891,11 @@ - * This permits __QDISC___STATE_RUNNING owner to get the lock more - * often and dequeue packets faster. - */ -+#ifdef CONFIG_PREEMPT_RT_FULL -+ contended = true; -+#else - contended = qdisc_is_running(q); -+#endif - if (unlikely(contended)) - spin_lock(&q->busylock); - -@@ -2943,9 +2955,44 @@ - #define skb_update_prio(skb) - #endif - -+#ifdef CONFIG_PREEMPT_RT_FULL -+ -+static inline int xmit_rec_read(void) -+{ -+ return current->xmit_recursion; -+} -+ -+static inline void xmit_rec_inc(void) -+{ -+ current->xmit_recursion++; -+} -+ -+static inline void xmit_rec_dec(void) -+{ -+ current->xmit_recursion--; -+} -+ -+#else -+ - DEFINE_PER_CPU(int, xmit_recursion); - EXPORT_SYMBOL(xmit_recursion); - -+static inline int xmit_rec_read(void) -+{ -+ return __this_cpu_read(xmit_recursion); -+} -+ -+static inline void xmit_rec_inc(void) -+{ -+ __this_cpu_inc(xmit_recursion); -+} -+ -+static inline void xmit_rec_dec(void) -+{ -+ __this_cpu_dec(xmit_recursion); -+} -+#endif -+ - #define RECURSION_LIMIT 10 - - /** -@@ -3138,7 +3185,7 @@ - - if (txq->xmit_lock_owner != cpu) { - -- if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) -+ if (xmit_rec_read() > RECURSION_LIMIT) - goto recursion_alert; - - skb = validate_xmit_skb(skb, dev); -@@ -3148,9 +3195,9 @@ - HARD_TX_LOCK(dev, txq, cpu); - - if (!netif_xmit_stopped(txq)) { -- __this_cpu_inc(xmit_recursion); -+ xmit_rec_inc(); - skb = dev_hard_start_xmit(skb, dev, txq, &rc); -- __this_cpu_dec(xmit_recursion); -+ xmit_rec_dec(); - if (dev_xmit_complete(rc)) { - HARD_TX_UNLOCK(dev, txq); - goto out; -@@ -3524,6 +3571,7 @@ - rps_unlock(sd); - - local_irq_restore(flags); -+ preempt_check_resched_rt(); - - atomic_long_inc(&skb->dev->rx_dropped); - kfree_skb(skb); -@@ -3542,7 +3590,7 @@ - struct rps_dev_flow voidflow, *rflow = &voidflow; - int cpu; - -- preempt_disable(); -+ migrate_disable(); - rcu_read_lock(); - - cpu = get_rps_cpu(skb->dev, skb, &rflow); -@@ -3552,13 +3600,13 @@ - ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); - - rcu_read_unlock(); -- preempt_enable(); -+ migrate_enable(); - } else - #endif - { - unsigned int qtail; -- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); -- put_cpu(); -+ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); -+ put_cpu_light(); - } - return ret; - } -@@ -3592,16 +3640,44 @@ - - trace_netif_rx_ni_entry(skb); - -- preempt_disable(); -+ local_bh_disable(); - err = netif_rx_internal(skb); -- if (local_softirq_pending()) -- do_softirq(); -- preempt_enable(); -+ local_bh_enable(); - - return err; - } - EXPORT_SYMBOL(netif_rx_ni); - -+#ifdef CONFIG_PREEMPT_RT_FULL -+/* -+ * RT runs ksoftirqd as a real time thread and the root_lock is a -+ * "sleeping spinlock". If the trylock fails then we can go into an -+ * infinite loop when ksoftirqd preempted the task which actually -+ * holds the lock, because we requeue q and raise NET_TX softirq -+ * causing ksoftirqd to loop forever. -+ * -+ * It's safe to use spin_lock on RT here as softirqs run in thread -+ * context and cannot deadlock against the thread which is holding -+ * root_lock. -+ * -+ * On !RT the trylock might fail, but there we bail out from the -+ * softirq loop after 10 attempts which we can't do on RT. And the -+ * task holding root_lock cannot be preempted, so the only downside of -+ * that trylock is that we need 10 loops to decide that we should have -+ * given up in the first one :) -+ */ -+static inline int take_root_lock(spinlock_t *lock) -+{ -+ spin_lock(lock); -+ return 1; -+} -+#else -+static inline int take_root_lock(spinlock_t *lock) -+{ -+ return spin_trylock(lock); -+} -+#endif -+ - static void net_tx_action(struct softirq_action *h) - { - struct softnet_data *sd = this_cpu_ptr(&softnet_data); -@@ -3643,7 +3719,7 @@ - head = head->next_sched; - - root_lock = qdisc_lock(q); -- if (spin_trylock(root_lock)) { -+ if (take_root_lock(root_lock)) { - smp_mb__before_atomic(); - clear_bit(__QDISC_STATE_SCHED, - &q->state); -@@ -4065,7 +4141,7 @@ - skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { - if (skb->dev == dev) { - __skb_unlink(skb, &sd->input_pkt_queue); -- kfree_skb(skb); -+ __skb_queue_tail(&sd->tofree_queue, skb); - input_queue_head_incr(sd); - } - } -@@ -4074,10 +4150,13 @@ - skb_queue_walk_safe(&sd->process_queue, skb, tmp) { - if (skb->dev == dev) { - __skb_unlink(skb, &sd->process_queue); -- kfree_skb(skb); -+ __skb_queue_tail(&sd->tofree_queue, skb); - input_queue_head_incr(sd); - } - } -+ -+ if (!skb_queue_empty(&sd->tofree_queue)) -+ raise_softirq_irqoff(NET_RX_SOFTIRQ); - } - - static int napi_gro_complete(struct sk_buff *skb) -@@ -4531,6 +4610,7 @@ - sd->rps_ipi_list = NULL; - - local_irq_enable(); -+ preempt_check_resched_rt(); - - /* Send pending IPI's to kick RPS processing on remote cpus. */ - while (remsd) { -@@ -4544,6 +4624,7 @@ - } else - #endif - local_irq_enable(); -+ preempt_check_resched_rt(); - } - - static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) -@@ -4625,6 +4706,7 @@ - local_irq_save(flags); - ____napi_schedule(this_cpu_ptr(&softnet_data), n); - local_irq_restore(flags); -+ preempt_check_resched_rt(); - } - EXPORT_SYMBOL(__napi_schedule); - -@@ -4901,7 +4983,7 @@ - list_splice_tail(&repoll, &list); - list_splice(&list, &sd->poll_list); - if (!list_empty(&sd->poll_list)) -- __raise_softirq_irqoff(NET_RX_SOFTIRQ); -+ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); - - net_rps_action_and_irq_enable(sd); - } -@@ -7234,7 +7316,7 @@ - void synchronize_net(void) - { - might_sleep(); -- if (rtnl_is_locked()) -+ if (rtnl_is_locked() && !IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) - synchronize_rcu_expedited(); - else - synchronize_rcu(); -@@ -7475,16 +7557,20 @@ - - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_enable(); -+ preempt_check_resched_rt(); - - /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx_ni(skb); - input_queue_head_incr(oldsd); - } -- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { -+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx_ni(skb); - input_queue_head_incr(oldsd); - } -+ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { -+ kfree_skb(skb); -+ } - - return NOTIFY_OK; - } -@@ -7786,8 +7872,9 @@ - for_each_possible_cpu(i) { - struct softnet_data *sd = &per_cpu(softnet_data, i); - -- skb_queue_head_init(&sd->input_pkt_queue); -- skb_queue_head_init(&sd->process_queue); -+ skb_queue_head_init_raw(&sd->input_pkt_queue); -+ skb_queue_head_init_raw(&sd->process_queue); -+ skb_queue_head_init_raw(&sd->tofree_queue); - INIT_LIST_HEAD(&sd->poll_list); - sd->output_queue_tailp = &sd->output_queue; - #ifdef CONFIG_RPS -diff -Nur linux-4.4.28.orig/net/core/skbuff.c linux-4.4.28/net/core/skbuff.c ---- linux-4.4.28.orig/net/core/skbuff.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/core/skbuff.c 2016-11-01 21:26:58.836346147 +0100 -@@ -63,6 +63,7 @@ - #include - #include - #include -+#include - - #include - #include -@@ -351,6 +352,8 @@ - - static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); - static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache); -+static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); -+static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); - - static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) - { -@@ -358,10 +361,10 @@ - unsigned long flags; - void *data; - -- local_irq_save(flags); -+ local_lock_irqsave(netdev_alloc_lock, flags); - nc = this_cpu_ptr(&netdev_alloc_cache); - data = __alloc_page_frag(nc, fragsz, gfp_mask); -- local_irq_restore(flags); -+ local_unlock_irqrestore(netdev_alloc_lock, flags); - return data; - } - -@@ -380,9 +383,13 @@ - - static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) - { -- struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); -+ struct page_frag_cache *nc; -+ void *data; - -- return __alloc_page_frag(nc, fragsz, gfp_mask); -+ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); -+ data = __alloc_page_frag(nc, fragsz, gfp_mask); -+ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); -+ return data; - } - - void *napi_alloc_frag(unsigned int fragsz) -@@ -429,13 +436,13 @@ - if (sk_memalloc_socks()) - gfp_mask |= __GFP_MEMALLOC; - -- local_irq_save(flags); -+ local_lock_irqsave(netdev_alloc_lock, flags); - - nc = this_cpu_ptr(&netdev_alloc_cache); - data = __alloc_page_frag(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; - -- local_irq_restore(flags); -+ local_unlock_irqrestore(netdev_alloc_lock, flags); - - if (unlikely(!data)) - return NULL; -@@ -476,9 +483,10 @@ - struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, - gfp_t gfp_mask) - { -- struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); -+ struct page_frag_cache *nc; - struct sk_buff *skb; - void *data; -+ bool pfmemalloc; - - len += NET_SKB_PAD + NET_IP_ALIGN; - -@@ -496,7 +504,11 @@ - if (sk_memalloc_socks()) - gfp_mask |= __GFP_MEMALLOC; - -+ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); - data = __alloc_page_frag(nc, len, gfp_mask); -+ pfmemalloc = nc->pfmemalloc; -+ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); -+ - if (unlikely(!data)) - return NULL; - -@@ -507,7 +519,7 @@ - } - - /* use OR instead of assignment to avoid clearing of bits in mask */ -- if (nc->pfmemalloc) -+ if (pfmemalloc) - skb->pfmemalloc = 1; - skb->head_frag = 1; - -diff -Nur linux-4.4.28.orig/net/core/sock.c linux-4.4.28/net/core/sock.c ---- linux-4.4.28.orig/net/core/sock.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/core/sock.c 2016-11-01 21:26:58.836346147 +0100 -@@ -2435,12 +2435,11 @@ - if (sk->sk_lock.owned) - __lock_sock(sk); - sk->sk_lock.owned = 1; -- spin_unlock(&sk->sk_lock.slock); -+ spin_unlock_bh(&sk->sk_lock.slock); - /* - * The sk_lock has mutex_lock() semantics here: - */ - mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); -- local_bh_enable(); - } - EXPORT_SYMBOL(lock_sock_nested); - -diff -Nur linux-4.4.28.orig/net/ipv4/icmp.c linux-4.4.28/net/ipv4/icmp.c ---- linux-4.4.28.orig/net/ipv4/icmp.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/ipv4/icmp.c 2016-11-01 21:26:58.836346147 +0100 -@@ -69,6 +69,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -77,6 +78,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -204,6 +206,8 @@ - * - * On SMP we have one ICMP socket per-cpu. - */ -+static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); -+ - static struct sock *icmp_sk(struct net *net) - { - return *this_cpu_ptr(net->ipv4.icmp_sk); -@@ -215,12 +219,14 @@ - - local_bh_disable(); - -+ local_lock(icmp_sk_lock); - sk = icmp_sk(net); - - if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { - /* This can happen if the output path signals a - * dst_link_failure() for an outgoing ICMP packet. - */ -+ local_unlock(icmp_sk_lock); - local_bh_enable(); - return NULL; - } -@@ -230,6 +236,7 @@ - static inline void icmp_xmit_unlock(struct sock *sk) - { - spin_unlock_bh(&sk->sk_lock.slock); -+ local_unlock(icmp_sk_lock); - } - - int sysctl_icmp_msgs_per_sec __read_mostly = 1000; -@@ -358,6 +365,7 @@ - struct sock *sk; - struct sk_buff *skb; - -+ local_lock(icmp_sk_lock); - sk = icmp_sk(dev_net((*rt)->dst.dev)); - if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, - icmp_param->data_len+icmp_param->head_len, -@@ -380,6 +388,7 @@ - skb->ip_summed = CHECKSUM_NONE; - ip_push_pending_frames(sk, fl4); - } -+ local_unlock(icmp_sk_lock); - } - - /* -@@ -891,6 +900,30 @@ - } - - /* -+ * 32bit and 64bit have different timestamp length, so we check for -+ * the cookie at offset 20 and verify it is repeated at offset 50 -+ */ -+#define CO_POS0 20 -+#define CO_POS1 50 -+#define CO_SIZE sizeof(int) -+#define ICMP_SYSRQ_SIZE 57 -+ -+/* -+ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie -+ * pattern and if it matches send the next byte as a trigger to sysrq. -+ */ -+static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) -+{ -+ int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); -+ char *p = skb->data; -+ -+ if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && -+ !memcmp(&cookie, p + CO_POS1, CO_SIZE) && -+ p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) -+ handle_sysrq(p[CO_POS0 + CO_SIZE]); -+} -+ -+/* - * Handle ICMP_ECHO ("ping") requests. - * - * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo -@@ -917,6 +950,11 @@ - icmp_param.data_len = skb->len; - icmp_param.head_len = sizeof(struct icmphdr); - icmp_reply(&icmp_param, skb); -+ -+ if (skb->len == ICMP_SYSRQ_SIZE && -+ net->ipv4.sysctl_icmp_echo_sysrq) { -+ icmp_check_sysrq(net, skb); -+ } - } - /* should there be an ICMP stat for ignored echos? */ - return true; -diff -Nur linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c linux-4.4.28/net/ipv4/sysctl_net_ipv4.c ---- linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/ipv4/sysctl_net_ipv4.c 2016-11-01 21:26:58.836346147 +0100 -@@ -818,6 +818,13 @@ - .proc_handler = proc_dointvec - }, - { -+ .procname = "icmp_echo_sysrq", -+ .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec -+ }, -+ { - .procname = "icmp_ignore_bogus_error_responses", - .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, - .maxlen = sizeof(int), -diff -Nur linux-4.4.28.orig/net/ipv4/tcp_ipv4.c linux-4.4.28/net/ipv4/tcp_ipv4.c ---- linux-4.4.28.orig/net/ipv4/tcp_ipv4.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/ipv4/tcp_ipv4.c 2016-11-01 21:26:58.840346411 +0100 -@@ -62,6 +62,7 @@ - #include - #include - #include -+#include - - #include - #include -@@ -566,6 +567,7 @@ - } - EXPORT_SYMBOL(tcp_v4_send_check); - -+static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); - /* - * This routine will send an RST to the other tcp. - * -@@ -687,10 +689,13 @@ - arg.bound_dev_if = sk->sk_bound_dev_if; - - arg.tos = ip_hdr(skb)->tos; -+ -+ local_lock(tcp_sk_lock); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), - skb, &TCP_SKB_CB(skb)->header.h4.opt, - ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, - &arg, arg.iov[0].iov_len); -+ local_unlock(tcp_sk_lock); - - TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); -@@ -772,10 +777,12 @@ - if (oif) - arg.bound_dev_if = oif; - arg.tos = tos; -+ local_lock(tcp_sk_lock); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), - skb, &TCP_SKB_CB(skb)->header.h4.opt, - ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, - &arg, arg.iov[0].iov_len); -+ local_unlock(tcp_sk_lock); - - TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); - } -diff -Nur linux-4.4.28.orig/net/mac80211/rx.c linux-4.4.28/net/mac80211/rx.c ---- linux-4.4.28.orig/net/mac80211/rx.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/mac80211/rx.c 2016-11-01 21:26:58.840346411 +0100 -@@ -3574,7 +3574,7 @@ - struct ieee80211_supported_band *sband; - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - -- WARN_ON_ONCE(softirq_count() == 0); -+ WARN_ON_ONCE_NONRT(softirq_count() == 0); - - if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) - goto drop; -diff -Nur linux-4.4.28.orig/net/netfilter/core.c linux-4.4.28/net/netfilter/core.c ---- linux-4.4.28.orig/net/netfilter/core.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/netfilter/core.c 2016-11-01 21:26:58.840346411 +0100 -@@ -22,11 +22,17 @@ - #include - #include - #include -+#include - #include - #include - - #include "nf_internals.h" - -+#ifdef CONFIG_PREEMPT_RT_BASE -+DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); -+EXPORT_PER_CPU_SYMBOL(xt_write_lock); -+#endif -+ - static DEFINE_MUTEX(afinfo_mutex); - - const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; -diff -Nur linux-4.4.28.orig/net/packet/af_packet.c linux-4.4.28/net/packet/af_packet.c ---- linux-4.4.28.orig/net/packet/af_packet.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/packet/af_packet.c 2016-11-01 21:26:58.844346664 +0100 -@@ -63,6 +63,7 @@ - #include - #include - #include -+#include - #include - #include - #include -@@ -695,7 +696,7 @@ - if (BLOCK_NUM_PKTS(pbd)) { - while (atomic_read(&pkc->blk_fill_in_prog)) { - /* Waiting for skb_copy_bits to finish... */ -- cpu_relax(); -+ cpu_chill(); - } - } - -@@ -957,7 +958,7 @@ - if (!(status & TP_STATUS_BLK_TMO)) { - while (atomic_read(&pkc->blk_fill_in_prog)) { - /* Waiting for skb_copy_bits to finish... */ -- cpu_relax(); -+ cpu_chill(); - } - } - prb_close_block(pkc, pbd, po, status); -diff -Nur linux-4.4.28.orig/net/rds/ib_rdma.c linux-4.4.28/net/rds/ib_rdma.c ---- linux-4.4.28.orig/net/rds/ib_rdma.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/rds/ib_rdma.c 2016-11-01 21:26:58.844346664 +0100 -@@ -34,6 +34,7 @@ - #include - #include - #include -+#include - - #include "rds.h" - #include "ib.h" -@@ -313,7 +314,7 @@ - for_each_online_cpu(cpu) { - flag = &per_cpu(clean_list_grace, cpu); - while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) -- cpu_relax(); -+ cpu_chill(); - } - } - -diff -Nur linux-4.4.28.orig/net/sched/sch_generic.c linux-4.4.28/net/sched/sch_generic.c ---- linux-4.4.28.orig/net/sched/sch_generic.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/sched/sch_generic.c 2016-11-01 21:26:58.844346664 +0100 -@@ -893,7 +893,7 @@ - /* Wait for outstanding qdisc_run calls. */ - list_for_each_entry(dev, head, close_list) - while (some_qdisc_is_busy(dev)) -- yield(); -+ msleep(1); - } - - void dev_deactivate(struct net_device *dev) -diff -Nur linux-4.4.28.orig/net/sunrpc/svc_xprt.c linux-4.4.28/net/sunrpc/svc_xprt.c ---- linux-4.4.28.orig/net/sunrpc/svc_xprt.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/net/sunrpc/svc_xprt.c 2016-11-01 21:26:58.844346664 +0100 -@@ -340,7 +340,7 @@ - goto out; - } - -- cpu = get_cpu(); -+ cpu = get_cpu_light(); - pool = svc_pool_for_cpu(xprt->xpt_server, cpu); - - atomic_long_inc(&pool->sp_stats.packets); -@@ -376,7 +376,7 @@ - - atomic_long_inc(&pool->sp_stats.threads_woken); - wake_up_process(rqstp->rq_task); -- put_cpu(); -+ put_cpu_light(); - goto out; - } - rcu_read_unlock(); -@@ -397,7 +397,7 @@ - goto redo_search; - } - rqstp = NULL; -- put_cpu(); -+ put_cpu_light(); - out: - trace_svc_xprt_do_enqueue(xprt, rqstp); - } -diff -Nur linux-4.4.28.orig/scripts/mkcompile_h linux-4.4.28/scripts/mkcompile_h ---- linux-4.4.28.orig/scripts/mkcompile_h 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/scripts/mkcompile_h 2016-11-01 21:26:58.844346664 +0100 -@@ -4,7 +4,8 @@ - ARCH=$2 - SMP=$3 - PREEMPT=$4 --CC=$5 -+RT=$5 -+CC=$6 - - vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } - -@@ -57,6 +58,7 @@ - CONFIG_FLAGS="" - if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi - if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi -+if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi - UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" - - # Truncate to maximum length -diff -Nur linux-4.4.28.orig/sound/core/pcm_native.c linux-4.4.28/sound/core/pcm_native.c ---- linux-4.4.28.orig/sound/core/pcm_native.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/sound/core/pcm_native.c 2016-11-01 21:26:58.844346664 +0100 -@@ -135,7 +135,7 @@ - void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream) - { - if (!substream->pcm->nonatomic) -- local_irq_disable(); -+ local_irq_disable_nort(); - snd_pcm_stream_lock(substream); - } - EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq); -@@ -150,7 +150,7 @@ - { - snd_pcm_stream_unlock(substream); - if (!substream->pcm->nonatomic) -- local_irq_enable(); -+ local_irq_enable_nort(); - } - EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq); - -@@ -158,7 +158,7 @@ - { - unsigned long flags = 0; - if (!substream->pcm->nonatomic) -- local_irq_save(flags); -+ local_irq_save_nort(flags); - snd_pcm_stream_lock(substream); - return flags; - } -@@ -176,7 +176,7 @@ - { - snd_pcm_stream_unlock(substream); - if (!substream->pcm->nonatomic) -- local_irq_restore(flags); -+ local_irq_restore_nort(flags); - } - EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore); - -diff -Nur linux-4.4.28.orig/virt/kvm/async_pf.c linux-4.4.28/virt/kvm/async_pf.c ---- linux-4.4.28.orig/virt/kvm/async_pf.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/virt/kvm/async_pf.c 2016-11-01 21:26:58.844346664 +0100 -@@ -98,8 +98,8 @@ - * This memory barrier pairs with prepare_to_wait's set_current_state() - */ - smp_mb(); -- if (waitqueue_active(&vcpu->wq)) -- wake_up_interruptible(&vcpu->wq); -+ if (swait_active(&vcpu->wq)) -+ swake_up(&vcpu->wq); - - mmput(mm); - kvm_put_kvm(vcpu->kvm); -diff -Nur linux-4.4.28.orig/virt/kvm/kvm_main.c linux-4.4.28/virt/kvm/kvm_main.c ---- linux-4.4.28.orig/virt/kvm/kvm_main.c 2016-10-28 09:53:25.000000000 +0200 -+++ linux-4.4.28/virt/kvm/kvm_main.c 2016-11-01 21:26:58.848346921 +0100 -@@ -228,8 +228,7 @@ - vcpu->kvm = kvm; - vcpu->vcpu_id = id; - vcpu->pid = NULL; -- vcpu->halt_poll_ns = 0; -- init_waitqueue_head(&vcpu->wq); -+ init_swait_queue_head(&vcpu->wq); - kvm_async_pf_vcpu_init(vcpu); - - vcpu->pre_pcpu = -1; -@@ -2005,7 +2004,7 @@ - void kvm_vcpu_block(struct kvm_vcpu *vcpu) - { - ktime_t start, cur; -- DEFINE_WAIT(wait); -+ DECLARE_SWAITQUEUE(wait); - bool waited = false; - u64 block_ns; - -@@ -2030,7 +2029,7 @@ - kvm_arch_vcpu_blocking(vcpu); - - for (;;) { -- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); -+ prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); - - if (kvm_vcpu_check_block(vcpu) < 0) - break; -@@ -2039,7 +2038,7 @@ - schedule(); - } - -- finish_wait(&vcpu->wq, &wait); -+ finish_swait(&vcpu->wq, &wait); - cur = ktime_get(); - - kvm_arch_vcpu_unblocking(vcpu); -@@ -2071,11 +2070,11 @@ - { - int me; - int cpu = vcpu->cpu; -- wait_queue_head_t *wqp; -+ struct swait_queue_head *wqp; - - wqp = kvm_arch_vcpu_wq(vcpu); -- if (waitqueue_active(wqp)) { -- wake_up_interruptible(wqp); -+ if (swait_active(wqp)) { -+ swake_up(wqp); - ++vcpu->stat.halt_wakeup; - } - -@@ -2176,7 +2175,7 @@ - continue; - if (vcpu == me) - continue; -- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) -+ if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) - continue; - if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) - continue; diff --git a/target/linux/patches/4.4.28/revert-sparc.patch b/target/linux/patches/4.4.28/revert-sparc.patch deleted file mode 100644 index 296be0e4a..000000000 --- a/target/linux/patches/4.4.28/revert-sparc.patch +++ /dev/null @@ -1,319 +0,0 @@ -From fff1ade5bd7576b053b6bbc9c9b72c2572092c06 Mon Sep 17 00:00:00 2001 -From: Waldemar Brodkorb -Date: Wed, 6 Jul 2016 08:16:59 +0200 -Subject: [PATCH] Revert "sparc: Harden signal return frame checks." - -This reverts commit 1fda90c39d8ef6acbedfd3cd9bd710a5bcc490c3. - -Signed-off-by: Waldemar Brodkorb ---- - arch/sparc/kernel/signal32.c | 46 ++++++++++++++-------------------------- - arch/sparc/kernel/signal_32.c | 41 +++++++++++++---------------------- - arch/sparc/kernel/signal_64.c | 31 ++++++++++----------------- - arch/sparc/kernel/sigutil_32.c | 9 +------- - arch/sparc/kernel/sigutil_64.c | 10 ++------- - 5 files changed, 45 insertions(+), 92 deletions(-) - -diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c -index 77655f0..4eed773 100644 ---- a/arch/sparc/kernel/signal32.c -+++ b/arch/sparc/kernel/signal32.c -@@ -138,24 +138,12 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) - return 0; - } - --/* Checks if the fp is valid. We always build signal frames which are -- * 16-byte aligned, therefore we can always enforce that the restore -- * frame has that property as well. -- */ --static bool invalid_frame_pointer(void __user *fp, int fplen) --{ -- if ((((unsigned long) fp) & 15) || -- ((unsigned long)fp) > 0x100000000ULL - fplen) -- return true; -- return false; --} -- - void do_sigreturn32(struct pt_regs *regs) - { - struct signal_frame32 __user *sf; - compat_uptr_t fpu_save; - compat_uptr_t rwin_save; -- unsigned int psr, ufp; -+ unsigned int psr; - unsigned pc, npc; - sigset_t set; - compat_sigset_t seta; -@@ -170,16 +158,11 @@ void do_sigreturn32(struct pt_regs *regs) - sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP]; - - /* 1. Make sure we are not getting garbage from the user */ -- if (invalid_frame_pointer(sf, sizeof(*sf))) -- goto segv; -- -- if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) -- goto segv; -- -- if (ufp & 0x7) -+ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || -+ (((unsigned long) sf) & 3)) - goto segv; - -- if (__get_user(pc, &sf->info.si_regs.pc) || -+ if (get_user(pc, &sf->info.si_regs.pc) || - __get_user(npc, &sf->info.si_regs.npc)) - goto segv; - -@@ -244,7 +227,7 @@ segv: - asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) - { - struct rt_signal_frame32 __user *sf; -- unsigned int psr, pc, npc, ufp; -+ unsigned int psr, pc, npc; - compat_uptr_t fpu_save; - compat_uptr_t rwin_save; - sigset_t set; -@@ -259,16 +242,11 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) - sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP]; - - /* 1. Make sure we are not getting garbage from the user */ -- if (invalid_frame_pointer(sf, sizeof(*sf))) -+ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || -+ (((unsigned long) sf) & 3)) - goto segv; - -- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) -- goto segv; -- -- if (ufp & 0x7) -- goto segv; -- -- if (__get_user(pc, &sf->regs.pc) || -+ if (get_user(pc, &sf->regs.pc) || - __get_user(npc, &sf->regs.npc)) - goto segv; - -@@ -329,6 +307,14 @@ segv: - force_sig(SIGSEGV, current); - } - -+/* Checks if the fp is valid */ -+static int invalid_frame_pointer(void __user *fp, int fplen) -+{ -+ if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen) -+ return 1; -+ return 0; -+} -+ - static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) - { - unsigned long sp; -diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c -index c3c12ef..52aa5e4 100644 ---- a/arch/sparc/kernel/signal_32.c -+++ b/arch/sparc/kernel/signal_32.c -@@ -60,22 +60,10 @@ struct rt_signal_frame { - #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) - #define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7))) - --/* Checks if the fp is valid. We always build signal frames which are -- * 16-byte aligned, therefore we can always enforce that the restore -- * frame has that property as well. -- */ --static inline bool invalid_frame_pointer(void __user *fp, int fplen) --{ -- if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen)) -- return true; -- -- return false; --} -- - asmlinkage void do_sigreturn(struct pt_regs *regs) - { -- unsigned long up_psr, pc, npc, ufp; - struct signal_frame __user *sf; -+ unsigned long up_psr, pc, npc; - sigset_t set; - __siginfo_fpu_t __user *fpu_save; - __siginfo_rwin_t __user *rwin_save; -@@ -89,13 +77,10 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) - sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; - - /* 1. Make sure we are not getting garbage from the user */ -- if (!invalid_frame_pointer(sf, sizeof(*sf))) -- goto segv_and_exit; -- -- if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) -+ if (!access_ok(VERIFY_READ, sf, sizeof(*sf))) - goto segv_and_exit; - -- if (ufp & 0x7) -+ if (((unsigned long) sf) & 3) - goto segv_and_exit; - - err = __get_user(pc, &sf->info.si_regs.pc); -@@ -142,7 +127,7 @@ segv_and_exit: - asmlinkage void do_rt_sigreturn(struct pt_regs *regs) - { - struct rt_signal_frame __user *sf; -- unsigned int psr, pc, npc, ufp; -+ unsigned int psr, pc, npc; - __siginfo_fpu_t __user *fpu_save; - __siginfo_rwin_t __user *rwin_save; - sigset_t set; -@@ -150,13 +135,8 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) - - synchronize_user_stack(); - sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; -- if (!invalid_frame_pointer(sf, sizeof(*sf))) -- goto segv; -- -- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) -- goto segv; -- -- if (ufp & 0x7) -+ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || -+ (((unsigned long) sf) & 0x03)) - goto segv; - - err = __get_user(pc, &sf->regs.pc); -@@ -198,6 +178,15 @@ segv: - force_sig(SIGSEGV, current); - } - -+/* Checks if the fp is valid */ -+static inline int invalid_frame_pointer(void __user *fp, int fplen) -+{ -+ if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen)) -+ return 1; -+ -+ return 0; -+} -+ - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) - { - unsigned long sp = regs->u_regs[UREG_FP]; -diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c -index 5ee930c..39aaec1 100644 ---- a/arch/sparc/kernel/signal_64.c -+++ b/arch/sparc/kernel/signal_64.c -@@ -234,17 +234,6 @@ do_sigsegv: - goto out; - } - --/* Checks if the fp is valid. We always build rt signal frames which -- * are 16-byte aligned, therefore we can always enforce that the -- * restore frame has that property as well. -- */ --static bool invalid_frame_pointer(void __user *fp) --{ -- if (((unsigned long) fp) & 15) -- return true; -- return false; --} -- - struct rt_signal_frame { - struct sparc_stackf ss; - siginfo_t info; -@@ -257,8 +246,8 @@ struct rt_signal_frame { - - void do_rt_sigreturn(struct pt_regs *regs) - { -- unsigned long tpc, tnpc, tstate, ufp; - struct rt_signal_frame __user *sf; -+ unsigned long tpc, tnpc, tstate; - __siginfo_fpu_t __user *fpu_save; - __siginfo_rwin_t __user *rwin_save; - sigset_t set; -@@ -272,16 +261,10 @@ void do_rt_sigreturn(struct pt_regs *regs) - (regs->u_regs [UREG_FP] + STACK_BIAS); - - /* 1. Make sure we are not getting garbage from the user */ -- if (invalid_frame_pointer(sf)) -- goto segv; -- -- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) -+ if (((unsigned long) sf) & 3) - goto segv; - -- if ((ufp + STACK_BIAS) & 0x7) -- goto segv; -- -- err = __get_user(tpc, &sf->regs.tpc); -+ err = get_user(tpc, &sf->regs.tpc); - err |= __get_user(tnpc, &sf->regs.tnpc); - if (test_thread_flag(TIF_32BIT)) { - tpc &= 0xffffffff; -@@ -325,6 +308,14 @@ segv: - force_sig(SIGSEGV, current); - } - -+/* Checks if the fp is valid */ -+static int invalid_frame_pointer(void __user *fp) -+{ -+ if (((unsigned long) fp) & 15) -+ return 1; -+ return 0; -+} -+ - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) - { - unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; -diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c -index e5fe8ce..0f6eebe 100644 ---- a/arch/sparc/kernel/sigutil_32.c -+++ b/arch/sparc/kernel/sigutil_32.c -@@ -48,10 +48,6 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) - int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) - { - int err; -- -- if (((unsigned long) fpu) & 3) -- return -EFAULT; -- - #ifdef CONFIG_SMP - if (test_tsk_thread_flag(current, TIF_USEDFPU)) - regs->psr &= ~PSR_EF; -@@ -101,10 +97,7 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) - struct thread_info *t = current_thread_info(); - int i, wsaved, err; - -- if (((unsigned long) rp) & 3) -- return -EFAULT; -- -- get_user(wsaved, &rp->wsaved); -+ __get_user(wsaved, &rp->wsaved); - if (wsaved > NSWINS) - return -EFAULT; - -diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c -index 36aadcb..387834a 100644 ---- a/arch/sparc/kernel/sigutil_64.c -+++ b/arch/sparc/kernel/sigutil_64.c -@@ -37,10 +37,7 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) - unsigned long fprs; - int err; - -- if (((unsigned long) fpu) & 7) -- return -EFAULT; -- -- err = get_user(fprs, &fpu->si_fprs); -+ err = __get_user(fprs, &fpu->si_fprs); - fprs_write(0); - regs->tstate &= ~TSTATE_PEF; - if (fprs & FPRS_DL) -@@ -75,10 +72,7 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) - struct thread_info *t = current_thread_info(); - int i, wsaved, err; - -- if (((unsigned long) rp) & 7) -- return -EFAULT; -- -- get_user(wsaved, &rp->wsaved); -+ __get_user(wsaved, &rp->wsaved); - if (wsaved > NSWINS) - return -EFAULT; - --- -1.7.10.4 - diff --git a/target/linux/patches/4.4.28/startup.patch b/target/linux/patches/4.4.28/startup.patch deleted file mode 100644 index e54ac19a6..000000000 --- a/target/linux/patches/4.4.28/startup.patch +++ /dev/null @@ -1,34 +0,0 @@ -diff -Nur linux-4.4.6.orig/init/initramfs.c linux-4.4.6/init/initramfs.c ---- linux-4.4.6.orig/init/initramfs.c 2016-03-16 16:43:17.000000000 +0100 -+++ linux-4.4.6/init/initramfs.c 2016-03-27 14:15:43.931044532 +0200 -@@ -653,6 +653,9 @@ - */ - load_default_modules(); - } -+#ifdef CONFIG_DEVTMPFS_MOUNT -+ devtmpfs_mount("dev"); -+#endif - return 0; - } - rootfs_initcall(populate_rootfs); -diff -Nur linux-4.4.6.orig/init/main.c linux-4.4.6/init/main.c ---- linux-4.4.6.orig/init/main.c 2016-03-16 16:43:17.000000000 +0100 -+++ linux-4.4.6/init/main.c 2016-03-27 14:15:43.935044783 +0200 -@@ -1011,6 +1011,8 @@ - if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) - pr_err("Warning: unable to open an initial console.\n"); - -+ printk(KERN_WARNING "Starting Linux (built with OpenADK).\n"); -+ - (void) sys_dup(0); - (void) sys_dup(0); - /* -@@ -1019,7 +1021,7 @@ - */ - - if (!ramdisk_execute_command) -- ramdisk_execute_command = "/init"; -+ ramdisk_execute_command = "/sbin/init"; - - if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) { - ramdisk_execute_command = NULL; diff --git a/target/linux/patches/4.4.28/use-libgcc-for-sh.patch b/target/linux/patches/4.4.28/use-libgcc-for-sh.patch deleted file mode 100644 index 6420219b0..000000000 --- a/target/linux/patches/4.4.28/use-libgcc-for-sh.patch +++ /dev/null @@ -1,29 +0,0 @@ -diff -Nur linux-4.1.13.orig/arch/sh/Makefile linux-4.1.13/arch/sh/Makefile ---- linux-4.1.13.orig/arch/sh/Makefile 2015-11-09 23:34:10.000000000 +0100 -+++ linux-4.1.13/arch/sh/Makefile 2015-12-06 19:59:31.000000000 +0100 -@@ -200,7 +206,9 @@ - KBUILD_CFLAGS += -fasynchronous-unwind-tables - endif - --libs-$(CONFIG_SUPERH32) := arch/sh/lib/ $(libs-y) -+LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libgcc.a) -+ -+libs-$(CONFIG_SUPERH32) := arch/sh/lib/ $(libs-y) $(LIBGCC) - libs-$(CONFIG_SUPERH64) := arch/sh/lib64/ $(libs-y) - - BOOT_TARGETS = uImage uImage.bz2 uImage.gz uImage.lzma uImage.xz uImage.lzo \ -diff -Nur linux-4.1.13.orig/arch/sh/lib/Makefile linux-4.1.13/arch/sh/lib/Makefile ---- linux-4.1.13.orig/arch/sh/lib/Makefile 2015-11-09 23:34:10.000000000 +0100 -+++ linux-4.1.13/arch/sh/lib/Makefile 2015-12-06 19:59:14.000000000 +0100 -@@ -5,11 +5,6 @@ - lib-y = delay.o memmove.o memchr.o \ - checksum.o strlen.o div64.o div64-generic.o - --# Extracted from libgcc --obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ -- ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \ -- udiv_qrnnd.o -- - udivsi3-y := udivsi3_i4i-Os.o - - ifneq ($(CONFIG_CC_OPTIMIZE_FOR_SIZE),y) diff --git a/target/linux/patches/4.4.28/versatile-nommu.patch b/target/linux/patches/4.4.28/versatile-nommu.patch deleted file mode 100644 index 96140b30c..000000000 --- a/target/linux/patches/4.4.28/versatile-nommu.patch +++ /dev/null @@ -1,16 +0,0 @@ -diff -Nur linux-4.4.17.orig/arch/arm/mach-versatile/include/mach/hardware.h linux-4.4.17/arch/arm/mach-versatile/include/mach/hardware.h ---- linux-4.4.17.orig/arch/arm/mach-versatile/include/mach/hardware.h 2016-08-10 11:49:43.000000000 +0200 -+++ linux-4.4.17/arch/arm/mach-versatile/include/mach/hardware.h 2016-08-25 23:19:03.691716292 +0200 -@@ -30,8 +30,12 @@ - #define VERSATILE_PCI_VIRT_BASE (void __iomem *)0xe8000000ul - #define VERSATILE_PCI_CFG_VIRT_BASE (void __iomem *)0xe9000000ul - -+#ifdef CONFIG_MMU - /* macro to get at MMIO space when running virtually */ - #define IO_ADDRESS(x) (((x) & 0x0fffffff) + (((x) >> 4) & 0x0f000000) + 0xf0000000) -+#else -+#define IO_ADDRESS(x) (x) -+#endif - - #define __io_address(n) ((void __iomem __force *)IO_ADDRESS(n)) - diff --git a/target/linux/patches/4.4.30/coldfire-sighandler.patch b/target/linux/patches/4.4.30/coldfire-sighandler.patch new file mode 100644 index 000000000..c52a4e228 --- /dev/null +++ b/target/linux/patches/4.4.30/coldfire-sighandler.patch @@ -0,0 +1,100 @@ +From a95517992a37488c0bc8b629c47c570e580e407d Mon Sep 17 00:00:00 2001 +From: Greg Ungerer +Date: Mon, 15 Feb 2016 16:36:29 +1000 +Subject: m68k: Use conventional function parameters for do_sigreturn + +Create conventional stack parameters for the calls to do_sigreturn and +do_rt_sigreturn. The current C code for do_sigreturn and do_rt_sigreturn +dig into the stack to create local pointers to the saved switch stack +and the pt_regs structs. + +The motivation for this change is a problem with non-MMU targets that +have broken signal return paths on newer versions of gcc. It appears as +though gcc has determined that the pointers into the saved stack structs, +and the saved structs themselves, are function parameters and updates to +them will be lost on function return, so they are optimized away. This +results in large parts of restore_sigcontext() and mangle_kernel_stack() +functions being removed. Of course this results in non-functional code +causing kernel oops. This problem has been observed with gcc version +5.2 and 5.3, and probably exists in earlier versions as well. + +Using conventional stack parameter pointers passed to these functions has +the advantage of the code here not needing to know the exact details of +how the underlying entry handler layed these structs out on the stack. +So the rather ugly pointer setup casting and arg referencing can be +removed. + +The resulting code after this change is a few bytes larger (due to the +overhead of creating the stack args and their tear down). Not being hot +paths I don't think this is too much of a problem here. + +An alternative solution is to put a barrier() in the do_sigreturn() code, +but this doesn't feel quite as clean as this solution. + +This change has been compile tested on all defconfigs, and run tested on +Atari (through aranym), ColdFire with MMU (M5407EVB) and ColdFire with +no-MMU (QEMU and M5208EVB). + +Signed-off-by: Greg Ungerer +Acked-by: Andreas Schwab +Signed-off-by: Geert Uytterhoeven +--- + arch/m68k/kernel/entry.S | 6 ++++++ + arch/m68k/kernel/signal.c | 8 ++------ + 2 files changed, 8 insertions(+), 6 deletions(-) + +diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S +index b54ac7a..97cd3ea 100644 +--- a/arch/m68k/kernel/entry.S ++++ b/arch/m68k/kernel/entry.S +@@ -71,13 +71,19 @@ ENTRY(__sys_vfork) + + ENTRY(sys_sigreturn) + SAVE_SWITCH_STACK ++ movel %sp,%sp@- | switch_stack pointer ++ pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + jbsr do_sigreturn ++ addql #8,%sp + RESTORE_SWITCH_STACK + rts + + ENTRY(sys_rt_sigreturn) + SAVE_SWITCH_STACK ++ movel %sp,%sp@- | switch_stack pointer ++ pea %sp@(SWITCH_STACK_SIZE+4) | pt_regs pointer + jbsr do_rt_sigreturn ++ addql #8,%sp + RESTORE_SWITCH_STACK + rts + +diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c +index af1c4f3..2dcee3a 100644 +--- a/arch/m68k/kernel/signal.c ++++ b/arch/m68k/kernel/signal.c +@@ -737,10 +737,8 @@ badframe: + return 1; + } + +-asmlinkage int do_sigreturn(unsigned long __unused) ++asmlinkage int do_sigreturn(struct pt_regs *regs, struct switch_stack *sw) + { +- struct switch_stack *sw = (struct switch_stack *) &__unused; +- struct pt_regs *regs = (struct pt_regs *) (sw + 1); + unsigned long usp = rdusp(); + struct sigframe __user *frame = (struct sigframe __user *)(usp - 4); + sigset_t set; +@@ -764,10 +762,8 @@ badframe: + return 0; + } + +-asmlinkage int do_rt_sigreturn(unsigned long __unused) ++asmlinkage int do_rt_sigreturn(struct pt_regs *regs, struct switch_stack *sw) + { +- struct switch_stack *sw = (struct switch_stack *) &__unused; +- struct pt_regs *regs = (struct pt_regs *) (sw + 1); + unsigned long usp = rdusp(); + struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(usp - 4); + sigset_t set; +-- +cgit v0.12 + diff --git a/target/linux/patches/4.4.30/crisv32.patch b/target/linux/patches/4.4.30/crisv32.patch new file mode 100644 index 000000000..cb9b0d028 --- /dev/null +++ b/target/linux/patches/4.4.30/crisv32.patch @@ -0,0 +1,33 @@ +diff -Nur linux-4.4.13.orig/arch/cris/arch-v32/mm/intmem.c linux-4.4.13/arch/cris/arch-v32/mm/intmem.c +--- linux-4.4.13.orig/arch/cris/arch-v32/mm/intmem.c 2016-06-08 03:14:51.000000000 +0200 ++++ linux-4.4.13/arch/cris/arch-v32/mm/intmem.c 2016-06-21 20:40:18.919361891 +0200 +@@ -113,14 +113,14 @@ + + allocation->status = STATUS_FREE; + /* Join with prev and/or next if also free */ +- if ((prev != &intmem_allocations) && ++ if ((&prev->entry != &intmem_allocations) && + (prev->status == STATUS_FREE)) { + prev->size += allocation->size; + list_del(&allocation->entry); + kfree(allocation); + allocation = prev; + } +- if ((next != &intmem_allocations) && ++ if ((&next->entry != &intmem_allocations) && + (next->status == STATUS_FREE)) { + allocation->size += next->size; + list_del(&next->entry); +@@ -145,5 +145,11 @@ + (unsigned long)intmem_virtual + MEM_INTMEM_START + + RESERVED_SIZE); + } +-device_initcall(crisv32_intmem_init); + ++static int __init crisv32_intmem_setup(void) ++{ ++ crisv32_intmem_init(); ++ ++ return 0; ++} ++device_initcall(crisv32_intmem_setup); diff --git a/target/linux/patches/4.4.30/crisv32_ethernet_driver.patch b/target/linux/patches/4.4.30/crisv32_ethernet_driver.patch new file mode 100644 index 000000000..0cef202fc --- /dev/null +++ b/target/linux/patches/4.4.30/crisv32_ethernet_driver.patch @@ -0,0 +1,4048 @@ +diff -Nur linux-4.7.3.orig/arch/cris/arch-v32/drivers/Kconfig linux-4.7.3/arch/cris/arch-v32/drivers/Kconfig +--- linux-4.7.3.orig/arch/cris/arch-v32/drivers/Kconfig 2016-09-07 08:35:12.000000000 +0200 ++++ linux-4.7.3/arch/cris/arch-v32/drivers/Kconfig 2016-09-13 01:47:09.507717605 +0200 +@@ -8,9 +8,18 @@ + This option enables the ETRAX FS built-in 10/100Mbit Ethernet + controller. + ++config ETRAX_HAVE_PHY ++ bool "PHY present" ++ default y ++ help ++ Search and use the first PHY available on the MDIO bus. Fail ++ if none is found. Say Y here if you are not in a switched ++ environment (single port device). ++ + config ETRAX_NO_PHY + bool "PHY not present" + depends on ETRAX_ETHERNET ++ default n + help + This option disables all MDIO communication with an ethernet + transceiver connected to the MII interface. This option shall +@@ -18,6 +27,70 @@ + switch. This option should normally be disabled. If enabled, + speed and duplex will be locked to 100 Mbit and full duplex. + ++config ETRAX_PHY_FALLBACK ++ bool "Fixed PHY fallback" ++ depends on ETRAX_ETHERNET ++ default n ++ help ++ If no PHY is found on the MDIO bus, fall back on a fixed ++ 100/Full fixed PHY. Say Y here if you need dynamic PHY ++ presence detection (switch connection where some but not ++ all ports have integrated PHYs), otherwise say N. ++ ++config ETRAX_ETHERNET_IFACE0 ++ depends on ETRAX_ETHERNET ++ bool "Enable network interface 0" ++ ++config ETRAX_ETHERNET_IFACE1 ++ depends on (ETRAX_ETHERNET && ETRAXFS) ++ bool "Enable network interface 1 (uses DMA6 and DMA7)" ++ ++choice ++ prompt "Eth0 led group" ++ depends on ETRAX_ETHERNET_IFACE0 ++ default ETRAX_ETH0_USE_LEDGRP0 ++ ++config ETRAX_ETH0_USE_LEDGRP0 ++ bool "Use LED grp 0" ++ depends on ETRAX_NBR_LED_GRP_ONE || ETRAX_NBR_LED_GRP_TWO ++ help ++ Use LED grp 0 for eth0 ++ ++config ETRAX_ETH0_USE_LEDGRP1 ++ bool "Use LED grp 1" ++ depends on ETRAX_NBR_LED_GRP_TWO ++ help ++ Use LED grp 1 for eth0 ++ ++config ETRAX_ETH0_USE_LEDGRPNULL ++ bool "Use no LEDs for eth0" ++ help ++ Use no LEDs for eth0 ++endchoice ++ ++choice ++ prompt "Eth1 led group" ++ depends on ETRAX_ETHERNET_IFACE1 ++ default ETRAX_ETH1_USE_LEDGRP1 ++ ++config ETRAX_ETH1_USE_LEDGRP0 ++ bool "Use LED grp 0" ++ depends on ETRAX_NBR_LED_GRP_ONE || ETRAX_NBR_LED_GRP_TWO ++ help ++ Use LED grp 0 for eth1 ++ ++config ETRAX_ETH1_USE_LEDGRP1 ++ bool "Use LED grp 1" ++ depends on ETRAX_NBR_LED_GRP_TWO ++ help ++ Use LED grp 1 for eth1 ++ ++config ETRAX_ETH1_USE_LEDGRPNULL ++ bool "Use no LEDs for eth1" ++ help ++ Use no LEDs for eth1 ++endchoice ++ + config ETRAXFS_SERIAL + bool "Serial-port support" + depends on ETRAX_ARCH_V32 +diff -Nur linux-4.7.3.orig/arch/cris/include/arch-v32/arch/hwregs/eth_defs.h linux-4.7.3/arch/cris/include/arch-v32/arch/hwregs/eth_defs.h +--- linux-4.7.3.orig/arch/cris/include/arch-v32/arch/hwregs/eth_defs.h 2016-09-07 08:35:12.000000000 +0200 ++++ linux-4.7.3/arch/cris/include/arch-v32/arch/hwregs/eth_defs.h 2016-09-13 01:47:09.527718381 +0200 +@@ -2,69 +2,64 @@ + #define __eth_defs_h + + /* +- * This file is autogenerated from +- * file: eth.r +- * id: eth_regs.r,v 1.16 2005/05/20 15:41:22 perz Exp +- * last modfied: Mon Jan 9 06:06:41 2006 +- * +- * by /n/asic/design/tools/rdesc/rdes2c eth.r +- * id: $Id: eth_defs.h,v 1.7 2006/01/26 13:45:30 karljope Exp $ +- * Any changes here will be lost. +- * +- * -*- buffer-read-only: t -*- ++ * Note: Previously this was autogenerated code from the hardware ++ * implementation. However, to enable the same file to be used ++ * for both ARTPEC-3 and ETRAX FS this file is now hand-edited. ++ * Be careful. + */ ++ + /* Main access macros */ + #ifndef REG_RD + #define REG_RD( scope, inst, reg ) \ +- REG_READ( reg_##scope##_##reg, \ +- (inst) + REG_RD_ADDR_##scope##_##reg ) ++ REG_READ( reg_##scope##_##reg, \ ++ (inst) + REG_RD_ADDR_##scope##_##reg ) + #endif + + #ifndef REG_WR + #define REG_WR( scope, inst, reg, val ) \ +- REG_WRITE( reg_##scope##_##reg, \ +- (inst) + REG_WR_ADDR_##scope##_##reg, (val) ) ++ REG_WRITE( reg_##scope##_##reg, \ ++ (inst) + REG_WR_ADDR_##scope##_##reg, (val) ) + #endif + + #ifndef REG_RD_VECT + #define REG_RD_VECT( scope, inst, reg, index ) \ +- REG_READ( reg_##scope##_##reg, \ +- (inst) + REG_RD_ADDR_##scope##_##reg + \ +- (index) * STRIDE_##scope##_##reg ) ++ REG_READ( reg_##scope##_##reg, \ ++ (inst) + REG_RD_ADDR_##scope##_##reg + \ ++ (index) * STRIDE_##scope##_##reg ) + #endif + + #ifndef REG_WR_VECT + #define REG_WR_VECT( scope, inst, reg, index, val ) \ +- REG_WRITE( reg_##scope##_##reg, \ +- (inst) + REG_WR_ADDR_##scope##_##reg + \ +- (index) * STRIDE_##scope##_##reg, (val) ) ++ REG_WRITE( reg_##scope##_##reg, \ ++ (inst) + REG_WR_ADDR_##scope##_##reg + \ ++ (index) * STRIDE_##scope##_##reg, (val) ) + #endif + + #ifndef REG_RD_INT + #define REG_RD_INT( scope, inst, reg ) \ +- REG_READ( int, (inst) + REG_RD_ADDR_##scope##_##reg ) ++ REG_READ( int, (inst) + REG_RD_ADDR_##scope##_##reg ) + #endif + + #ifndef REG_WR_INT + #define REG_WR_INT( scope, inst, reg, val ) \ +- REG_WRITE( int, (inst) + REG_WR_ADDR_##scope##_##reg, (val) ) ++ REG_WRITE( int, (inst) + REG_WR_ADDR_##scope##_##reg, (val) ) + #endif + + #ifndef REG_RD_INT_VECT + #define REG_RD_INT_VECT( scope, inst, reg, index ) \ +- REG_READ( int, (inst) + REG_RD_ADDR_##scope##_##reg + \ +- (index) * STRIDE_##scope##_##reg ) ++ REG_READ( int, (inst) + REG_RD_ADDR_##scope##_##reg + \ ++ (index) * STRIDE_##scope##_##reg ) + #endif + + #ifndef REG_WR_INT_VECT + #define REG_WR_INT_VECT( scope, inst, reg, index, val ) \ +- REG_WRITE( int, (inst) + REG_WR_ADDR_##scope##_##reg + \ +- (index) * STRIDE_##scope##_##reg, (val) ) ++ REG_WRITE( int, (inst) + REG_WR_ADDR_##scope##_##reg + \ ++ (index) * STRIDE_##scope##_##reg, (val) ) + #endif + + #ifndef REG_TYPE_CONV + #define REG_TYPE_CONV( type, orgtype, val ) \ +- ( { union { orgtype o; type n; } r; r.o = val; r.n; } ) ++ ( { union { orgtype o; type n; } r; r.o = val; r.n; } ) + #endif + + #ifndef reg_page_size +@@ -73,306 +68,332 @@ + + #ifndef REG_ADDR + #define REG_ADDR( scope, inst, reg ) \ +- ( (inst) + REG_RD_ADDR_##scope##_##reg ) ++ ( (inst) + REG_RD_ADDR_##scope##_##reg ) + #endif + + #ifndef REG_ADDR_VECT + #define REG_ADDR_VECT( scope, inst, reg, index ) \ +- ( (inst) + REG_RD_ADDR_##scope##_##reg + \ +- (index) * STRIDE_##scope##_##reg ) ++ ( (inst) + REG_RD_ADDR_##scope##_##reg + \ ++ (index) * STRIDE_##scope##_##reg ) + #endif + + /* C-code for register scope eth */ + + /* Register rw_ma0_lo, scope eth, type rw */ + typedef struct { +- unsigned int addr : 32; ++ unsigned int addr : 32; + } reg_eth_rw_ma0_lo; + #define REG_RD_ADDR_eth_rw_ma0_lo 0 + #define REG_WR_ADDR_eth_rw_ma0_lo 0 + + /* Register rw_ma0_hi, scope eth, type rw */ + typedef struct { +- unsigned int addr : 16; +- unsigned int dummy1 : 16; ++ unsigned int addr : 16; ++ unsigned int dummy1 : 16; + } reg_eth_rw_ma0_hi; + #define REG_RD_ADDR_eth_rw_ma0_hi 4 + #define REG_WR_ADDR_eth_rw_ma0_hi 4 + + /* Register rw_ma1_lo, scope eth, type rw */ + typedef struct { +- unsigned int addr : 32; ++ unsigned int addr : 32; + } reg_eth_rw_ma1_lo; + #define REG_RD_ADDR_eth_rw_ma1_lo 8 + #define REG_WR_ADDR_eth_rw_ma1_lo 8 + + /* Register rw_ma1_hi, scope eth, type rw */ + typedef struct { +- unsigned int addr : 16; +- unsigned int dummy1 : 16; ++ unsigned int addr : 16; ++ unsigned int dummy1 : 16; + } reg_eth_rw_ma1_hi; + #define REG_RD_ADDR_eth_rw_ma1_hi 12 + #define REG_WR_ADDR_eth_rw_ma1_hi 12 + + /* Register rw_ga_lo, scope eth, type rw */ + typedef struct { +- unsigned int tbl : 32; ++ unsigned int table : 32; + } reg_eth_rw_ga_lo; + #define REG_RD_ADDR_eth_rw_ga_lo 16 + #define REG_WR_ADDR_eth_rw_ga_lo 16 + + /* Register rw_ga_hi, scope eth, type rw */ + typedef struct { +- unsigned int tbl : 32; ++ unsigned int table : 32; + } reg_eth_rw_ga_hi; + #define REG_RD_ADDR_eth_rw_ga_hi 20 + #define REG_WR_ADDR_eth_rw_ga_hi 20 + + /* Register rw_gen_ctrl, scope eth, type rw */ + typedef struct { +- unsigned int en : 1; +- unsigned int phy : 2; +- unsigned int protocol : 1; +- unsigned int loopback : 1; +- unsigned int flow_ctrl : 1; +- unsigned int gtxclk_out : 1; +- unsigned int phyrst_n : 1; +- unsigned int dummy1 : 24; ++ unsigned int en : 1; ++ unsigned int phy : 2; ++ unsigned int protocol : 1; ++ unsigned int loopback : 1; ++ unsigned int flow_ctrl : 1; ++ unsigned int gtxclk_out : 1; ++ unsigned int phyrst_n : 1; ++ unsigned int dummy1 : 24; + } reg_eth_rw_gen_ctrl; + #define REG_RD_ADDR_eth_rw_gen_ctrl 24 + #define REG_WR_ADDR_eth_rw_gen_ctrl 24 + + /* Register rw_rec_ctrl, scope eth, type rw */ + typedef struct { +- unsigned int ma0 : 1; +- unsigned int ma1 : 1; +- unsigned int individual : 1; +- unsigned int broadcast : 1; +- unsigned int undersize : 1; +- unsigned int oversize : 1; +- unsigned int bad_crc : 1; +- unsigned int duplex : 1; +- unsigned int max_size : 16; +- unsigned int dummy1 : 8; ++ unsigned int ma0 : 1; ++ unsigned int ma1 : 1; ++ unsigned int individual : 1; ++ unsigned int broadcast : 1; ++ unsigned int undersize : 1; ++ unsigned int oversize : 1; ++ unsigned int bad_crc : 1; ++ unsigned int duplex : 1; ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ unsigned int max_size : 16; ++ unsigned int dummy1 : 8; ++#else ++ unsigned int max_size : 1; ++ unsigned int dummy1 : 23; ++#endif + } reg_eth_rw_rec_ctrl; + #define REG_RD_ADDR_eth_rw_rec_ctrl 28 + #define REG_WR_ADDR_eth_rw_rec_ctrl 28 + + /* Register rw_tr_ctrl, scope eth, type rw */ + typedef struct { +- unsigned int crc : 1; +- unsigned int pad : 1; +- unsigned int retry : 1; +- unsigned int ignore_col : 1; +- unsigned int cancel : 1; +- unsigned int hsh_delay : 1; +- unsigned int ignore_crs : 1; +- unsigned int carrier_ext : 1; +- unsigned int dummy1 : 24; ++ unsigned int crc : 1; ++ unsigned int pad : 1; ++ unsigned int retry : 1; ++ unsigned int ignore_col : 1; ++ unsigned int cancel : 1; ++ unsigned int hsh_delay : 1; ++ unsigned int ignore_crs : 1; ++ unsigned int carrier_ext : 1; ++ unsigned int dummy1 : 24; + } reg_eth_rw_tr_ctrl; + #define REG_RD_ADDR_eth_rw_tr_ctrl 32 + #define REG_WR_ADDR_eth_rw_tr_ctrl 32 + + /* Register rw_clr_err, scope eth, type rw */ + typedef struct { +- unsigned int clr : 1; +- unsigned int dummy1 : 31; ++ unsigned int clr : 1; ++ unsigned int dummy1 : 31; + } reg_eth_rw_clr_err; + #define REG_RD_ADDR_eth_rw_clr_err 36 + #define REG_WR_ADDR_eth_rw_clr_err 36 + + /* Register rw_mgm_ctrl, scope eth, type rw */ + typedef struct { +- unsigned int mdio : 1; +- unsigned int mdoe : 1; +- unsigned int mdc : 1; +- unsigned int dummy1 : 29; ++ unsigned int mdio : 1; ++ unsigned int mdoe : 1; ++ unsigned int mdc : 1; ++ unsigned int phyclk : 1; ++ unsigned int txdata : 4; ++ unsigned int txen : 1; ++ unsigned int dummy1 : 23; + } reg_eth_rw_mgm_ctrl; + #define REG_RD_ADDR_eth_rw_mgm_ctrl 40 + #define REG_WR_ADDR_eth_rw_mgm_ctrl 40 + + /* Register r_stat, scope eth, type r */ + typedef struct { +- unsigned int mdio : 1; +- unsigned int exc_col : 1; +- unsigned int urun : 1; +- unsigned int clk_125 : 1; +- unsigned int dummy1 : 28; ++ unsigned int mdio : 1; ++ unsigned int exc_col : 1; ++ unsigned int urun : 1; ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ unsigned int clk_125 : 1; ++#else ++ unsigned int phyclk : 1; ++#endif ++ unsigned int txdata : 4; ++ unsigned int txen : 1; ++ unsigned int col : 1; ++ unsigned int crs : 1; ++ unsigned int txclk : 1; ++ unsigned int rxdata : 4; ++ unsigned int rxer : 1; ++ unsigned int rxdv : 1; ++ unsigned int rxclk : 1; ++ unsigned int dummy1 : 13; + } reg_eth_r_stat; + #define REG_RD_ADDR_eth_r_stat 44 + + /* Register rs_rec_cnt, scope eth, type rs */ + typedef struct { +- unsigned int crc_err : 8; +- unsigned int align_err : 8; +- unsigned int oversize : 8; +- unsigned int congestion : 8; ++ unsigned int crc_err : 8; ++ unsigned int align_err : 8; ++ unsigned int oversize : 8; ++ unsigned int congestion : 8; + } reg_eth_rs_rec_cnt; + #define REG_RD_ADDR_eth_rs_rec_cnt 48 + + /* Register r_rec_cnt, scope eth, type r */ + typedef struct { +- unsigned int crc_err : 8; +- unsigned int align_err : 8; +- unsigned int oversize : 8; +- unsigned int congestion : 8; ++ unsigned int crc_err : 8; ++ unsigned int align_err : 8; ++ unsigned int oversize : 8; ++ unsigned int congestion : 8; + } reg_eth_r_rec_cnt; + #define REG_RD_ADDR_eth_r_rec_cnt 52 + + /* Register rs_tr_cnt, scope eth, type rs */ + typedef struct { +- unsigned int single_col : 8; +- unsigned int mult_col : 8; +- unsigned int late_col : 8; +- unsigned int deferred : 8; ++ unsigned int single_col : 8; ++ unsigned int mult_col : 8; ++ unsigned int late_col : 8; ++ unsigned int deferred : 8; + } reg_eth_rs_tr_cnt; + #define REG_RD_ADDR_eth_rs_tr_cnt 56 + + /* Register r_tr_cnt, scope eth, type r */ + typedef struct { +- unsigned int single_col : 8; +- unsigned int mult_col : 8; +- unsigned int late_col : 8; +- unsigned int deferred : 8; ++ unsigned int single_col : 8; ++ unsigned int mult_col : 8; ++ unsigned int late_col : 8; ++ unsigned int deferred : 8; + } reg_eth_r_tr_cnt; + #define REG_RD_ADDR_eth_r_tr_cnt 60 + + /* Register rs_phy_cnt, scope eth, type rs */ + typedef struct { +- unsigned int carrier_loss : 8; +- unsigned int sqe_err : 8; +- unsigned int dummy1 : 16; ++ unsigned int carrier_loss : 8; ++ unsigned int sqe_err : 8; ++ unsigned int dummy1 : 16; + } reg_eth_rs_phy_cnt; + #define REG_RD_ADDR_eth_rs_phy_cnt 64 + + /* Register r_phy_cnt, scope eth, type r */ + typedef struct { +- unsigned int carrier_loss : 8; +- unsigned int sqe_err : 8; +- unsigned int dummy1 : 16; ++ unsigned int carrier_loss : 8; ++ unsigned int sqe_err : 8; ++ unsigned int dummy1 : 16; + } reg_eth_r_phy_cnt; + #define REG_RD_ADDR_eth_r_phy_cnt 68 + + /* Register rw_test_ctrl, scope eth, type rw */ + typedef struct { +- unsigned int snmp_inc : 1; +- unsigned int snmp : 1; +- unsigned int backoff : 1; +- unsigned int dummy1 : 29; ++ unsigned int snmp_inc : 1; ++ unsigned int snmp : 1; ++ unsigned int backoff : 1; ++ unsigned int dummy1 : 29; + } reg_eth_rw_test_ctrl; + #define REG_RD_ADDR_eth_rw_test_ctrl 72 + #define REG_WR_ADDR_eth_rw_test_ctrl 72 + + /* Register rw_intr_mask, scope eth, type rw */ + typedef struct { +- unsigned int crc : 1; +- unsigned int align : 1; +- unsigned int oversize : 1; +- unsigned int congestion : 1; +- unsigned int single_col : 1; +- unsigned int mult_col : 1; +- unsigned int late_col : 1; +- unsigned int deferred : 1; +- unsigned int carrier_loss : 1; +- unsigned int sqe_test_err : 1; +- unsigned int orun : 1; +- unsigned int urun : 1; +- unsigned int exc_col : 1; +- unsigned int mdio : 1; +- unsigned int dummy1 : 18; ++ unsigned int crc : 1; ++ unsigned int align : 1; ++ unsigned int oversize : 1; ++ unsigned int congestion : 1; ++ unsigned int single_col : 1; ++ unsigned int mult_col : 1; ++ unsigned int late_col : 1; ++ unsigned int deferred : 1; ++ unsigned int carrier_loss : 1; ++ unsigned int sqe_test_err : 1; ++ unsigned int orun : 1; ++ unsigned int urun : 1; ++ unsigned int exc_col : 1; ++ unsigned int mdio : 1; ++ unsigned int dummy1 : 18; + } reg_eth_rw_intr_mask; + #define REG_RD_ADDR_eth_rw_intr_mask 76 + #define REG_WR_ADDR_eth_rw_intr_mask 76 + + /* Register rw_ack_intr, scope eth, type rw */ + typedef struct { +- unsigned int crc : 1; +- unsigned int align : 1; +- unsigned int oversize : 1; +- unsigned int congestion : 1; +- unsigned int single_col : 1; +- unsigned int mult_col : 1; +- unsigned int late_col : 1; +- unsigned int deferred : 1; +- unsigned int carrier_loss : 1; +- unsigned int sqe_test_err : 1; +- unsigned int orun : 1; +- unsigned int urun : 1; +- unsigned int exc_col : 1; +- unsigned int mdio : 1; +- unsigned int dummy1 : 18; ++ unsigned int crc : 1; ++ unsigned int align : 1; ++ unsigned int oversize : 1; ++ unsigned int congestion : 1; ++ unsigned int single_col : 1; ++ unsigned int mult_col : 1; ++ unsigned int late_col : 1; ++ unsigned int deferred : 1; ++ unsigned int carrier_loss : 1; ++ unsigned int sqe_test_err : 1; ++ unsigned int orun : 1; ++ unsigned int urun : 1; ++ unsigned int exc_col : 1; ++ unsigned int mdio : 1; ++ unsigned int dummy1 : 18; + } reg_eth_rw_ack_intr; + #define REG_RD_ADDR_eth_rw_ack_intr 80 + #define REG_WR_ADDR_eth_rw_ack_intr 80 + + /* Register r_intr, scope eth, type r */ + typedef struct { +- unsigned int crc : 1; +- unsigned int align : 1; +- unsigned int oversize : 1; +- unsigned int congestion : 1; +- unsigned int single_col : 1; +- unsigned int mult_col : 1; +- unsigned int late_col : 1; +- unsigned int deferred : 1; +- unsigned int carrier_loss : 1; +- unsigned int sqe_test_err : 1; +- unsigned int orun : 1; +- unsigned int urun : 1; +- unsigned int exc_col : 1; +- unsigned int mdio : 1; +- unsigned int dummy1 : 18; ++ unsigned int crc : 1; ++ unsigned int align : 1; ++ unsigned int oversize : 1; ++ unsigned int congestion : 1; ++ unsigned int single_col : 1; ++ unsigned int mult_col : 1; ++ unsigned int late_col : 1; ++ unsigned int deferred : 1; ++ unsigned int carrier_loss : 1; ++ unsigned int sqe_test_err : 1; ++ unsigned int orun : 1; ++ unsigned int urun : 1; ++ unsigned int exc_col : 1; ++ unsigned int mdio : 1; ++ unsigned int dummy1 : 18; + } reg_eth_r_intr; + #define REG_RD_ADDR_eth_r_intr 84 + + /* Register r_masked_intr, scope eth, type r */ + typedef struct { +- unsigned int crc : 1; +- unsigned int align : 1; +- unsigned int oversize : 1; +- unsigned int congestion : 1; +- unsigned int single_col : 1; +- unsigned int mult_col : 1; +- unsigned int late_col : 1; +- unsigned int deferred : 1; +- unsigned int carrier_loss : 1; +- unsigned int sqe_test_err : 1; +- unsigned int orun : 1; +- unsigned int urun : 1; +- unsigned int exc_col : 1; +- unsigned int mdio : 1; +- unsigned int dummy1 : 18; ++ unsigned int crc : 1; ++ unsigned int align : 1; ++ unsigned int oversize : 1; ++ unsigned int congestion : 1; ++ unsigned int single_col : 1; ++ unsigned int mult_col : 1; ++ unsigned int late_col : 1; ++ unsigned int deferred : 1; ++ unsigned int carrier_loss : 1; ++ unsigned int sqe_test_err : 1; ++ unsigned int orun : 1; ++ unsigned int urun : 1; ++ unsigned int exc_col : 1; ++ unsigned int mdio : 1; ++ unsigned int dummy1 : 18; + } reg_eth_r_masked_intr; + #define REG_RD_ADDR_eth_r_masked_intr 88 + +- + /* Constants */ + enum { +- regk_eth_discard = 0x00000000, +- regk_eth_ether = 0x00000000, +- regk_eth_full = 0x00000001, +- regk_eth_gmii = 0x00000003, +- regk_eth_gtxclk = 0x00000001, +- regk_eth_half = 0x00000000, +- regk_eth_hsh = 0x00000001, +- regk_eth_mii = 0x00000001, +- regk_eth_mii_arec = 0x00000002, +- regk_eth_mii_clk = 0x00000000, +- regk_eth_no = 0x00000000, +- regk_eth_phyrst = 0x00000000, +- regk_eth_rec = 0x00000001, +- regk_eth_rw_ga_hi_default = 0x00000000, +- regk_eth_rw_ga_lo_default = 0x00000000, +- regk_eth_rw_gen_ctrl_default = 0x00000000, +- regk_eth_rw_intr_mask_default = 0x00000000, +- regk_eth_rw_ma0_hi_default = 0x00000000, +- regk_eth_rw_ma0_lo_default = 0x00000000, +- regk_eth_rw_ma1_hi_default = 0x00000000, +- regk_eth_rw_ma1_lo_default = 0x00000000, +- regk_eth_rw_mgm_ctrl_default = 0x00000000, +- regk_eth_rw_test_ctrl_default = 0x00000000, +- regk_eth_size1518 = 0x000005ee, +- regk_eth_size1522 = 0x000005f2, +- regk_eth_yes = 0x00000001 ++ regk_eth_discard = 0x00000000, ++ regk_eth_ether = 0x00000000, ++ regk_eth_full = 0x00000001, ++ regk_eth_gmii = 0x00000003, ++ regk_eth_gtxclk = 0x00000001, ++ regk_eth_half = 0x00000000, ++ regk_eth_hsh = 0x00000001, ++ regk_eth_mii = 0x00000001, ++ regk_eth_mii_arec = 0x00000002, ++ regk_eth_mii_clk = 0x00000000, ++ regk_eth_no = 0x00000000, ++ regk_eth_phyrst = 0x00000000, ++ regk_eth_rec = 0x00000001, ++ regk_eth_rw_ga_hi_default = 0x00000000, ++ regk_eth_rw_ga_lo_default = 0x00000000, ++ regk_eth_rw_gen_ctrl_default = 0x00000000, ++ regk_eth_rw_intr_mask_default = 0x00000000, ++ regk_eth_rw_ma0_hi_default = 0x00000000, ++ regk_eth_rw_ma0_lo_default = 0x00000000, ++ regk_eth_rw_ma1_hi_default = 0x00000000, ++ regk_eth_rw_ma1_lo_default = 0x00000000, ++ regk_eth_rw_mgm_ctrl_default = 0x00000000, ++ regk_eth_rw_test_ctrl_default = 0x00000000, ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ regk_eth_size1518 = 0x000005ee, ++ regk_eth_size1522 = 0x000005f2, ++#else ++ regk_eth_size1518 = 0x00000000, ++ regk_eth_size1522 = 0x00000001, ++#endif ++ regk_eth_yes = 0x00000001 + }; ++ + #endif /* __eth_defs_h */ +diff -Nur linux-4.7.3.orig/drivers/net/cris/eth_v32.c linux-4.7.3/drivers/net/cris/eth_v32.c +--- linux-4.7.3.orig/drivers/net/cris/eth_v32.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.7.3/drivers/net/cris/eth_v32.c 2016-09-13 01:48:05.953910422 +0200 +@@ -0,0 +1,3060 @@ ++/* ++ * Driver for the ETRAX FS/Artpec-3 network controller. ++ * ++ * Copyright (c) 2003-2008 Axis Communications AB. ++ * ++ * TODO: ++ * * Decrease the amount of code running with interrupts disabled. ++ * * Rework the error handling so that we do not need to touch the tx ++ * ring from the error interrupts. When done, we should be able to ++ * do tx completition from the NAPI loop without disabling interrupts. ++ * * Remove the gigabit code. It's probably never going to be used. ++ */ ++ ++#include ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include ++#include ++#include ++#include ++#include ++ ++#include /* CRIS_LED_* I/O functions */ ++#include ++#include ++#include ++#include ++#include ++#ifdef CONFIG_ETRAXFS ++#include ++#else ++#include ++#endif ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "eth_v32.h" ++ ++#ifndef CONFIG_ETRAXFS ++#define ETH0_INTR_VECT ETH_INTR_VECT ++#define ETH1_INTR_VECT ETH_INTR_VECT ++#define regi_eth0 regi_eth ++#define regi_eth1 regi_ ++#endif ++ ++#define DEBUG(x) ++#define GET_BIT(bit,val) (((val) >> (bit)) & 0x01) ++ ++#if defined(CONFIG_ETRAX_HAVE_PHY) || defined(CONFIG_ETRAX_PHY_FALLBACK) ++#define RESET_PHY 1 ++#else ++#define RESET_PHY 0 ++#endif ++ ++enum { ++ HAVE_PHY, ++ NO_PHY, ++ FALLBACK_PHY, ++}; ++#if defined(CONFIG_ETRAX_PHY_FALLBACK) ++#define PHY_MODE (FALLBACK_PHY) ++#elif defined(CONFIG_ETRAX_NO_PHY) ++#define PHY_MODE (NO_PHY) ++#elif defined(CONFIG_ETRAX_HAVE_PHY) ++#define PHY_MODE (HAVE_PHY) ++#else ++#error Unknown PHY behaviour ++#endif ++ ++static struct { ++ const char str[ETH_GSTRING_LEN]; ++} const ethtool_stats_keys[] = { ++ { "tx_dma_restarts" }, ++ { "tx_mac_resets" }, ++ { "rx_dma_restarts" }, ++ { "rx_dma_timeouts" }, ++ { " dropped_rx" } ++}; ++ ++static void crisv32_eth_check_speed(unsigned long idev); ++static void crisv32_eth_check_duplex(unsigned long idev); ++static void update_rx_stats(struct crisv32_ethernet_local *np); ++static void update_tx_stats(struct crisv32_ethernet_local *np); ++static int crisv32_eth_poll(struct napi_struct *napi, int budget); ++static void crisv32_eth_setup_controller(struct net_device *dev); ++static int crisv32_eth_request_irqdma(struct net_device *dev); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++static void ++crisv32_eth_restart_rx_dma(struct net_device* dev, ++ struct crisv32_ethernet_local *np); ++#endif ++#if 0 ++static void crisv32_ethernet_bug(struct net_device *dev); ++#endif ++ ++/* ++ * The name of the card. Is used for messages and in the requests for ++ * io regions, irqs and dma channels. ++ */ ++#ifdef CONFIG_ETRAXFS ++static const char cardname[] = "ETRAX FS built-in ethernet controller"; ++#else ++static const char cardname[] = "ARTPEC-3 built-in ethernet controller"; ++#endif ++ ++/* Some chipset needs special care. */ ++#ifndef CONFIG_ETRAX_NO_PHY ++struct transceiver_ops transceivers[] = { ++ {0x1018, broadcom_check_speed, broadcom_check_duplex}, ++ {0x50EF, broadcom_check_speed, broadcom_check_duplex}, ++ /* TDK 2120 and TDK 2120C */ ++ {0xC039, tdk_check_speed, tdk_check_duplex}, ++ {0x039C, tdk_check_speed, tdk_check_duplex}, ++ /* Intel LXT972A*/ ++ {0x04de, intel_check_speed, intel_check_duplex}, ++ /* National Semiconductor DP83865 */ ++ {0x0017, national_check_speed, national_check_duplex}, ++ /* Vitesse VCS8641 */ ++ {0x01c1, vitesse_check_speed, vitesse_check_duplex}, ++ /* Davicom DM9161 */ ++ {0x606E, davicom_check_speed, davicom_check_duplex}, ++ /* Generic, must be last. */ ++ {0x0000, generic_check_speed, generic_check_duplex} ++}; ++#endif ++ ++static struct net_device *crisv32_dev[2]; ++static struct crisv32_eth_leds *crisv32_leds[3]; ++ ++/* Default MAC address for interface 0. ++ * The real one will be set later. */ ++static struct sockaddr default_mac_iface0 = ++ {0, {0x00, 0x40, 0x8C, 0xCD, 0x00, 0x00}}; ++ ++#ifdef CONFIG_CPU_FREQ ++static int ++crisv32_ethernet_freq_notifier(struct notifier_block *nb, unsigned long val, ++ void *data); ++ ++static struct notifier_block crisv32_ethernet_freq_notifier_block = { ++ .notifier_call = crisv32_ethernet_freq_notifier ++}; ++#endif ++ ++static void receive_timeout(unsigned long arg); ++static void receive_timeout_work(struct work_struct* work); ++static void transmit_timeout(unsigned long arg); ++ ++/* ++ * mask in and out tx/rx interrupts. ++ */ ++static inline void crisv32_disable_tx_ints(struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_intr_mask intr_mask_tx = { .data = regk_dma_no }; ++ REG_WR(dma, np->dma_out_inst, rw_intr_mask, intr_mask_tx); ++} ++ ++static inline void crisv32_enable_tx_ints(struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_intr_mask intr_mask_tx = { .data = regk_dma_yes }; ++ REG_WR(dma, np->dma_out_inst, rw_intr_mask, intr_mask_tx); ++} ++ ++static inline void crisv32_disable_rx_ints(struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_intr_mask intr_mask_rx = { .in_eop = regk_dma_no }; ++ REG_WR(dma, np->dma_in_inst, rw_intr_mask, intr_mask_rx); ++} ++ ++static inline void crisv32_enable_rx_ints(struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_intr_mask intr_mask_rx = { .in_eop = regk_dma_yes }; ++ REG_WR(dma, np->dma_in_inst, rw_intr_mask, intr_mask_rx); ++} ++ ++static inline void crisv32_disable_eth_ints(struct crisv32_ethernet_local *np) ++{ ++ int intr_mask_nw = 0x0; ++ REG_WR_INT(eth, np->eth_inst, rw_intr_mask, intr_mask_nw); ++} ++ ++static inline void crisv32_enable_eth_ints(struct crisv32_ethernet_local *np) ++{ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ /* For Artpec-3 we use overrun to workaround voodoo TR 87 */ ++ int intr_mask_nw = 0x1c00; ++#else ++ int intr_mask_nw = 0x1800; ++#endif ++ REG_WR_INT(eth, np->eth_inst, rw_intr_mask, intr_mask_nw); ++} ++ ++static inline int crisv32_eth_gigabit(struct crisv32_ethernet_local *np) ++{ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ return np->gigabit_mode; ++#else ++ return 0; ++#endif ++} ++ ++static inline void crisv32_eth_set_gigabit(struct crisv32_ethernet_local *np, ++ int g) ++{ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ np->gigabit_mode = g; ++#endif ++} ++ ++/* start/stop receiver */ ++static inline void crisv32_start_receiver(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rw_rec_ctrl rec_ctrl; ++ ++ rec_ctrl = REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.ma0 = regk_eth_yes; ++ rec_ctrl.broadcast = regk_eth_rec; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++} ++ ++static inline void crisv32_stop_receiver(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rw_rec_ctrl rec_ctrl; ++ ++ rec_ctrl = REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.ma0 = regk_eth_no; ++ rec_ctrl.broadcast = regk_eth_discard; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++} ++ ++static inline void crisv32_eth_reset(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rw_gen_ctrl gen_ctrl = { 0 }; ++ ++ gen_ctrl = REG_RD(eth, np->eth_inst, rw_gen_ctrl); ++ gen_ctrl.en = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++ gen_ctrl.en = regk_eth_yes; ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++} ++ ++static void crisv32_eth_tx_cancel_frame(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rw_tr_ctrl tr_ctrl; ++ ++ /* Cancel any pending transmits. This should bring us to the ++ excessive collisions state but it doesn't always do it. */ ++ tr_ctrl = REG_RD(eth, np->eth_inst, rw_tr_ctrl); ++ tr_ctrl.cancel = 1; ++ REG_WR(eth, np->eth_inst, rw_tr_ctrl, tr_ctrl); ++ tr_ctrl.cancel = 0; ++ REG_WR(eth, np->eth_inst, rw_tr_ctrl, tr_ctrl); ++} ++ ++/* ++ * Hack to disconnect/reconnect the dma from the ethernet block while we reset ++ * things. TODO: verify that we don't need to disconnect out channels and ++ * remove that code. ++ * ++ * ARTPEC-3 has only a single ethernet block so np->eth_inst is always eth0. ++ * The strmux values are named slightly different, redefine to avoid #ifdefs ++ * in the code blocks. For artpec3 only regk_strmux_eth0 and channel 0/1 ++ * should be used. ++ */ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++#define regk_strmux_eth0 regk_strmux_eth ++#define regk_strmux_eth1 regk_strmux_eth ++#endif ++static inline void ++crisv32_disconnect_eth_tx_dma(struct crisv32_ethernet_local *np) ++{ ++ reg_strmux_rw_cfg strmux_cfg; ++ ++ strmux_cfg = REG_RD(strmux, regi_strmux, rw_cfg); ++ if (np->eth_inst == regi_eth0) ++ strmux_cfg.dma0 = regk_strmux_off; ++ else ++ strmux_cfg.dma6 = regk_strmux_off; ++ REG_WR(strmux, regi_strmux, rw_cfg, strmux_cfg); ++} ++ ++static inline void crisv32_connect_eth_tx_dma(struct crisv32_ethernet_local *np) ++{ ++ reg_strmux_rw_cfg strmux_cfg; ++ ++ strmux_cfg = REG_RD(strmux, regi_strmux, rw_cfg); ++ if (np->eth_inst == regi_eth0) ++ strmux_cfg.dma0 = regk_strmux_eth0; ++ else ++ strmux_cfg.dma6 = regk_strmux_eth1; ++ REG_WR(strmux, regi_strmux, rw_cfg, strmux_cfg); ++} ++ ++static inline void ++crisv32_disconnect_eth_rx_dma(struct crisv32_ethernet_local *np) ++{ ++ reg_strmux_rw_cfg strmux_cfg; ++ ++ strmux_cfg = REG_RD(strmux, regi_strmux, rw_cfg); ++ if (np->eth_inst == regi_eth0) ++ strmux_cfg.dma1 = regk_strmux_off; ++ else ++ strmux_cfg.dma7 = regk_strmux_off; ++ REG_WR(strmux, regi_strmux, rw_cfg, strmux_cfg); ++} ++ ++static inline void crisv32_connect_eth_rx_dma(struct crisv32_ethernet_local *np) ++{ ++ reg_strmux_rw_cfg strmux_cfg; ++ ++ strmux_cfg = REG_RD(strmux, regi_strmux, rw_cfg); ++ if (np->eth_inst == regi_eth0) ++ strmux_cfg.dma1 = regk_strmux_eth0; ++ else ++ strmux_cfg.dma7 = regk_strmux_eth1; ++ REG_WR(strmux, regi_strmux, rw_cfg, strmux_cfg); ++} ++ ++static int dma_wait_busy(int inst, int timeout) ++{ ++ reg_dma_rw_stream_cmd dma_sc; ++ ++ do { ++ dma_sc = REG_RD(dma, inst, rw_stream_cmd); ++ } while (timeout-- > 0 && dma_sc.busy); ++ return dma_sc.busy; ++} ++ ++static int __init crisv32_eth_request_irqdma(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ /* Allocate IRQs and DMAs. */ ++ if (np->eth_inst == regi_eth0) { ++ if (request_irq(DMA0_INTR_VECT, crisv32tx_eth_interrupt, ++ 0, "Ethernet TX", dev)) { ++ return -EAGAIN; ++ } ++ ++ if (request_irq(DMA1_INTR_VECT, crisv32rx_eth_interrupt, ++ 0, "Ethernet RX", dev)) ++ goto err0_1; ++ ++ if (crisv32_request_dma(0, cardname, DMA_VERBOSE_ON_ERROR, ++ 12500000, dma_eth0)) ++ goto err0_2; ++ ++ if (crisv32_request_dma(1, cardname, DMA_VERBOSE_ON_ERROR, ++ 12500000, dma_eth0)) ++ goto err0_3; ++ ++ if (request_irq(ETH0_INTR_VECT, crisv32nw_eth_interrupt, 0, ++ cardname, dev)) { ++ crisv32_free_dma(1); ++err0_3: ++ crisv32_free_dma(0); ++err0_2: ++ free_irq(DMA1_INTR_VECT, dev); ++err0_1: ++ free_irq(DMA0_INTR_VECT, dev); ++ return -EAGAIN; ++ } ++ } else { ++ if (request_irq(DMA6_INTR_VECT, crisv32tx_eth_interrupt, ++ 0, cardname, dev)) ++ return -EAGAIN; ++ ++ if (request_irq(DMA7_INTR_VECT, crisv32rx_eth_interrupt, ++ 0, cardname, dev)) ++ goto err1_1; ++ ++ if (crisv32_request_dma(6, cardname, DMA_VERBOSE_ON_ERROR, ++ 0, dma_eth1)) ++ goto err1_2; ++ ++ if (crisv32_request_dma(7, cardname, DMA_VERBOSE_ON_ERROR, ++ 0, dma_eth1)) ++ goto err1_3; ++ ++ if (request_irq(ETH1_INTR_VECT, crisv32nw_eth_interrupt, 0, ++ cardname, dev)) { ++ crisv32_free_dma(7); ++err1_3: ++ crisv32_free_dma(6); ++err1_2: ++ free_irq(DMA7_INTR_VECT, dev); ++err1_1: ++ free_irq(DMA6_INTR_VECT, dev); ++ return -EAGAIN; ++ } ++ } ++ return 0; ++} ++ ++static int __init crisv32_eth_init_phy(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ struct timer_list timer_init = TIMER_INITIALIZER(NULL, 0, 0); ++ ++ if (RESET_PHY) { ++#ifdef CONFIG_ETRAXFS ++ reg_config_rw_pad_ctrl pad_ctrl; ++ pad_ctrl = REG_RD(config, regi_config, rw_pad_ctrl); ++ pad_ctrl.phyrst_n = 0; ++ REG_WR(config, regi_config, rw_pad_ctrl, pad_ctrl); ++ ++ udelay(500); /* RESET_LEN */ ++ ++ pad_ctrl.phyrst_n = 1; ++ REG_WR(config, regi_config, rw_pad_ctrl, pad_ctrl); ++#else ++ reg_eth_rw_gen_ctrl gen_ctrl = REG_RD(eth, np->eth_inst, rw_gen_ctrl); ++ gen_ctrl.phyrst_n = 0; ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++ ++ udelay(500); /* RESET_LEN */ ++ ++ gen_ctrl.phyrst_n = 1; ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++#endif ++ ++ udelay(200); /* RESET_WAIT */ ++ } ++ ++ switch (PHY_MODE) { ++ case FALLBACK_PHY: ++ /* Fall back on using fixed iff there is no PHY on */ ++ /* the MDIO bus */ ++ np->fixed_phy = crisv32_eth_probe_transceiver(dev) != 0; ++ if (np->fixed_phy) ++ printk(KERN_WARNING ++ "eth: No transciever found, falling back " ++ "to fixed phy mode\n"); ++ break; ++ ++ case NO_PHY: ++ /* Don't even bother looking for a PHY, always rely */ ++ /* on fixed PHY */ ++ np->fixed_phy = 1; ++ break; ++ ++ default: /* HAVE_PHY */ ++ /* Look for a PHY and abort if there is none, */ ++ /* otherwise just carry on */ ++ if (crisv32_eth_probe_transceiver(dev)) { ++ printk(KERN_WARNING ++ "eth: No transceiver found, " ++ "removing interface\n"); ++ return -ENODEV; ++ } ++ np->fixed_phy = 0; ++ } ++ ++ if (np->fixed_phy) { ++ reg_eth_rw_rec_ctrl rec_ctrl; ++ ++ /* speed */ ++ np->current_speed = 100; ++ np->current_speed_selection = 100; /* Auto. */ ++ ++ /* duplex */ ++ np->full_duplex = 1; ++ np->current_duplex = full; ++ ++ rec_ctrl = REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.duplex = regk_eth_full; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } else { ++ np->mii_if.supports_gmii = mii_check_gmii_support(&np->mii_if); ++ ++ /* speed */ ++ np->current_speed = 10; ++ np->current_speed_selection = 0; /* Auto. */ ++ np->speed_timer = timer_init; ++ np->speed_timer.expires = jiffies + NET_LINK_UP_CHECK_INTERVAL; ++ np->speed_timer.data = (unsigned long) dev; ++ np->speed_timer.function = crisv32_eth_check_speed; ++ ++ /* duplex */ ++ np->full_duplex = 0; ++ np->current_duplex = autoneg; ++ np->duplex_timer = timer_init; ++ np->duplex_timer.expires = jiffies + NET_DUPLEX_CHECK_INTERVAL; ++ np->duplex_timer.data = (unsigned long) dev; ++ np->duplex_timer.function = crisv32_eth_check_duplex; ++ } ++ ++ return 0; ++} ++ ++static void __init crisv32_eth_setup_controller(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_eth_rw_gen_ctrl gen_ctrl; ++ ++ reg_eth_rw_tr_ctrl tr_ctrl = { ++ /* SW retransmits to avoid transmitter bugs. */ ++ .retry = regk_eth_no, ++ .pad = regk_eth_yes, ++ .crc = regk_eth_yes ++ }; ++ ++ reg_eth_rw_rec_ctrl rec_ctrl = { ++ .ma0 = regk_eth_no, /* enable at open() */ ++ .broadcast = regk_eth_no, ++ .max_size = regk_eth_size1522 ++ }; ++ ++ reg_eth_rw_ga_lo ga_lo = { 0 }; ++ reg_eth_rw_ga_hi ga_hi = { 0 }; ++ ++ /* ++ * Initialize group address registers to make sure that no ++ * unwanted addresses are matched. ++ */ ++ REG_WR(eth, np->eth_inst, rw_ga_lo, ga_lo); ++ REG_WR(eth, np->eth_inst, rw_ga_hi, ga_hi); ++ ++ /* Configure receiver and transmitter */ ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ REG_WR(eth, np->eth_inst, rw_tr_ctrl, tr_ctrl); ++ ++ /* ++ * Read from rw_gen_ctrl so that we don't override any previous ++ * configuration. ++ */ ++ gen_ctrl = REG_RD(eth, np->eth_inst, rw_gen_ctrl); ++ gen_ctrl.phy = regk_eth_mii_clk; ++#ifdef CONFIG_ETRAXFS ++ /* On ETRAX FS, this bit has reversed meaning */ ++ gen_ctrl.flow_ctrl = regk_eth_no; ++#else ++ gen_ctrl.flow_ctrl = regk_eth_yes; ++#endif ++ ++ /* Enable ethernet controller with mii clk. */ ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++ gen_ctrl.en = regk_eth_yes; ++ REG_WR(eth, np->eth_inst, rw_gen_ctrl, gen_ctrl); ++} ++ ++static void crisv32_eth_reset_rx_ring(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int i; ++ ++ /* cleanup the rx-ring */ ++ for (i = 0; i < NBR_RX_DESC; i++) { ++ struct sk_buff *skb; ++ skb = np->dma_rx_descr_list[i].skb; ++ if (!skb ++ || (np->dma_rx_descr_list[i].descr.buf != ++ (void *)virt_to_phys(skb->data))) { ++ if (skb) ++ dev_kfree_skb(skb); ++ skb = dev_alloc_skb(MAX_MEDIA_DATA_SIZE); ++ np->dma_rx_descr_list[i].skb = skb; ++ np->dma_rx_descr_list[i].descr.buf = ++ (char*)virt_to_phys(skb->data); ++ } ++ if (np->dma_rx_descr_list[i].descr.in_eop) ++ np->rx_restarts_dropped++; ++ np->dma_rx_descr_list[i].descr.after = ++ (char*)virt_to_phys(skb->data ++ + MAX_MEDIA_DATA_SIZE); ++ np->dma_rx_descr_list[i].descr.eol = 0; ++ np->dma_rx_descr_list[i].descr.in_eop = 0; ++ /* Workaround cache bug */ ++ flush_dma_descr(&np->dma_rx_descr_list[i].descr, 1); ++ } ++ ++ /* reset rx-ring */ ++ np->active_rx_desc = &np->dma_rx_descr_list[0]; ++ np->prev_rx_desc = &np->dma_rx_descr_list[NBR_RX_DESC - 1]; ++ np->last_rx_desc = np->prev_rx_desc; ++ np->dma_rx_descr_list[NBR_RX_DESC - 1].descr.eol = 1; ++ flush_dma_descr(&np->dma_rx_descr_list[NBR_RX_DESC - 1].descr, 0); ++ /* ready to accept new packets. */ ++ np->new_rx_package = 1; ++ ++ /* Fill context descriptors. */ ++ np->ctxt_in.next = 0; ++ np->ctxt_in.saved_data = ++ (void *)virt_to_phys(&np->active_rx_desc->descr); ++ np->ctxt_in.saved_data_buf = np->active_rx_desc->descr.buf; ++} ++ ++static inline int crisv32_eth_tx_ring_full(struct crisv32_ethernet_local *np) ++{ ++ crisv32_eth_descr *active = np->active_tx_desc; ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ active = phys_to_virt((unsigned long)active->descr.next); ++#endif ++ if (active == np->catch_tx_desc) ++ return 1; ++ return 0; ++} ++ ++static void crisv32_eth_reset_tx_ring(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ /* free un-handled tx packets */ ++ while (np->txpackets || np->catch_tx_desc != np->active_tx_desc) { ++ np->txpackets--; ++ if (np->catch_tx_desc->skb) ++ dev_kfree_skb(np->catch_tx_desc->skb); ++ ++ np->catch_tx_desc->skb = 0; ++ np->catch_tx_desc = ++ phys_to_virt((int)np->catch_tx_desc->descr.next); ++ } ++ ++ WARN_ON(np->txpackets != 0); ++ np->txpackets = 0; ++ ++ /* reset tx-ring */ ++ np->dma_tx_descr_list[0].descr.buf = ++ np->dma_tx_descr_list[0].descr.after = 0; ++ np->dma_tx_descr_list[0].descr.eol = 1; ++ ++ np->active_tx_desc = &np->dma_tx_descr_list[0]; ++ np->prev_tx_desc = &np->dma_tx_descr_list[NBR_TX_DESC - 1]; ++ np->catch_tx_desc = &np->dma_tx_descr_list[0]; ++ ++ np->ctxt_out.next = 0; ++ np->ctxt_out.saved_data = ++ (void *)virt_to_phys(&np->dma_tx_descr_list[0].descr); ++ ++} ++ ++static void crisv32_eth_reset_rings(struct net_device *dev) ++{ ++ crisv32_eth_reset_tx_ring(dev); ++ crisv32_eth_reset_rx_ring(dev); ++} ++ ++/* ++ * Really advance the receive ring. RX interrupts must be off. ++ */ ++static void __crisv32_eth_rx_ring_advance(struct crisv32_ethernet_local *np) ++{ ++ if (np->newbuf) ++ np->active_rx_desc->descr.buf = (void *) np->newbuf; ++ np->active_rx_desc->descr.after = ++ np->active_rx_desc->descr.buf + MAX_MEDIA_DATA_SIZE; ++ np->active_rx_desc->descr.eol = 1; ++ np->active_rx_desc->descr.in_eop = 0; ++ np->active_rx_desc = phys_to_virt((int)np->active_rx_desc->descr.next); ++ barrier(); ++ np->prev_rx_desc->descr.eol = 0; ++ ++ /* Workaround cache bug. */ ++ flush_dma_descr(&np->prev_rx_desc->descr, 0); ++ np->prev_rx_desc = phys_to_virt((int)np->prev_rx_desc->descr.next); ++ flush_dma_descr(&np->prev_rx_desc->descr, 1); ++} ++ ++/* ++ * Advance the receive ring. RX interrupts must be off. ++ */ ++static inline void ++crisv32_eth_rx_ring_advance(struct crisv32_ethernet_local *np) ++{ ++ /* ++ * When the input DMA reaches eol precaution must be taken, otherwise ++ * the DMA could stop. The problem occurs if the eol flag is re-placed ++ * on the descriptor that the DMA stands on before the DMA proceed to ++ * the next descriptor. This case could, for example, happen if there ++ * is a traffic burst and then the network goes silent. To prevent this ++ * we make sure that we do not set the eol flag on the descriptor that ++ * the DMA stands on. ++ */ ++ unsigned long dma_pos; ++ ++ /* Get the current input dma position. */ ++ dma_pos = REG_RD_INT(dma, np->dma_in_inst, rw_saved_data); ++ ++ if (virt_to_phys(&np->active_rx_desc->descr) != dma_pos) { ++ crisv32_eth_descr *cur, *nxt; ++ ++ /* Now really advance the ring one step. */ ++ __crisv32_eth_rx_ring_advance(np); ++ ++ cur = np->active_rx_desc; ++ nxt = (void *)phys_to_virt((unsigned long)cur->descr.next); ++ flush_dma_descr(&cur->descr, 0); ++ flush_dma_descr(&nxt->descr, 0); ++ if (!cur->descr.in_eop && nxt->descr.in_eop) { ++ /* TODO: Investigate this more. The DMA seems to have ++ skipped a descriptor, possibly due to incoherence ++ between the CPU L1 cache and the DMA updates to the ++ descriptor. */ ++ np->newbuf = (unsigned long) np->active_rx_desc->descr.buf; ++ __crisv32_eth_rx_ring_advance(np); ++ } ++ /* flush after peek. */ ++ flush_dma_descr(&cur->descr, 0); ++ flush_dma_descr(&nxt->descr, 0); ++ } else { ++ /* delay the advancing of the ring. */ ++ np->new_rx_package = 0; ++ } ++} ++ ++static void __init crisv32_eth_init_rings(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int i; ++ ++ /* Initialise receive descriptors for interface. */ ++ for (i = 0; i < NBR_RX_DESC; i++) { ++ struct sk_buff *skb = dev_alloc_skb(MAX_MEDIA_DATA_SIZE); ++ ++ np->dma_rx_descr_list[i].skb = skb; ++ np->dma_rx_descr_list[i].descr.buf = ++ (char*)virt_to_phys(skb->data); ++ np->dma_rx_descr_list[i].descr.after = ++ (char*)virt_to_phys(skb->data + MAX_MEDIA_DATA_SIZE); ++ ++ np->dma_rx_descr_list[i].descr.eol = 0; ++ np->dma_rx_descr_list[i].descr.in_eop = 0; ++ np->dma_rx_descr_list[i].descr.next = ++ (void *) virt_to_phys(&np->dma_rx_descr_list[i + 1].descr); ++ } ++ /* bend the list into a ring */ ++ np->dma_rx_descr_list[NBR_RX_DESC - 1].descr.next = ++ (void *) virt_to_phys(&np->dma_rx_descr_list[0].descr); ++ ++ /* Initialize transmit descriptors. */ ++ for (i = 0; i < NBR_TX_DESC; i++) { ++ np->dma_tx_descr_list[i].descr.wait = 1; ++ np->dma_tx_descr_list[i].descr.eol = 0; ++ np->dma_tx_descr_list[i].descr.out_eop = 0; ++ np->dma_tx_descr_list[i].descr.next = ++ (void*)virt_to_phys(&np->dma_tx_descr_list[i+1].descr); ++ } ++ /* bend the list into a ring */ ++ np->dma_tx_descr_list[NBR_TX_DESC - 1].descr.next = ++ (void *) virt_to_phys(&np->dma_tx_descr_list[0].descr); ++ ++ crisv32_eth_reset_rings(dev); ++} ++ ++static void __init crisv32_init_leds(int ledgrp, struct net_device *dev) ++{ ++ struct timer_list timer_init = TIMER_INITIALIZER(NULL, 0, 0); ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ /* Use already allocated led grp if initialized */ ++ if (crisv32_leds[ledgrp] != NULL) { ++ np->leds = crisv32_leds[ledgrp]; ++ return; ++ } ++ ++ crisv32_leds[ledgrp] = ++ kmalloc(sizeof(struct crisv32_eth_leds), GFP_KERNEL); ++ ++ crisv32_leds[ledgrp]->ledgrp = ledgrp; ++ crisv32_leds[ledgrp]->led_active = 0; ++ crisv32_leds[ledgrp]->ifisup[0] = 0; ++ crisv32_leds[ledgrp]->ifisup[1] = 0; ++ /* NOTE: Should this value be set to zero as the jiffies timer ++ can wrap? */ ++ crisv32_leds[ledgrp]->led_next_time = jiffies; ++ ++ crisv32_leds[ledgrp]->clear_led_timer = timer_init; ++ crisv32_leds[ledgrp]->clear_led_timer.function = ++ crisv32_clear_network_leds; ++ crisv32_leds[ledgrp]->clear_led_timer.data = (unsigned long) dev; ++ ++ spin_lock_init(&crisv32_leds[ledgrp]->led_lock); ++ ++ np->leds = crisv32_leds[ledgrp]; ++} ++ ++static int __init crisv32_ethernet_init(void) ++{ ++ struct crisv32_ethernet_local *np; ++ int ret = 0; ++ ++#ifdef CONFIG_ETRAXFS ++ printk("ETRAX FS 10/100MBit ethernet v0.01 (c)" ++ " 2003 Axis Communications AB\n"); ++#else ++ printk("ARTPEC-3 10/100 MBit ethernet (c)" ++ " 2003-2009 Axis Communications AB\n"); ++#endif ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ { ++ reg_clkgen_rw_clk_ctrl clk_ctrl = REG_RD(clkgen, regi_clkgen, ++ rw_clk_ctrl); ++ clk_ctrl.eth = clk_ctrl.dma0_1_eth = regk_clkgen_yes; ++ REG_WR(clkgen, regi_clkgen, rw_clk_ctrl, clk_ctrl); ++ } ++#endif ++{ ++ int iface0 = 0; ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ if (crisv32_pinmux_alloc_fixed(pinmux_eth)) ++ panic("Eth pinmux\n"); ++#endif ++ ++ if (!(crisv32_dev[iface0] = alloc_etherdev(sizeof *np))) ++ return -ENOMEM; ++ ++ ret |= crisv32_ethernet_device_init(crisv32_dev[iface0]); ++ ++ crisv32_init_leds(CRIS_LED_GRP_NONE,crisv32_dev[iface0]); ++ ++ np = (struct crisv32_ethernet_local *) netdev_priv(crisv32_dev[iface0]); ++ np->eth_inst = regi_eth0; ++ np->dma_out_inst = regi_dma0; ++ np->dma_in_inst = regi_dma1; ++ ++ np->mii_if.dev = crisv32_dev[iface0]; ++ np->mii_if.mdio_read = crisv32_eth_get_mdio_reg; ++ np->mii_if.mdio_write = crisv32_eth_set_mdio_reg; ++ np->mii_if.phy_id_mask = 0x1f; ++ np->mii_if.reg_num_mask = 0x1f; ++ ++ np->use_leds = 1; ++ np->autoneg_normal = 1; ++ ++ ++ register_netdev(crisv32_dev[iface0]); ++ ++ /* Set up default MAC address */ ++ memcpy(crisv32_dev[iface0]->dev_addr, default_mac_iface0.sa_data, 6); ++ crisv32_eth_set_mac_address(crisv32_dev[iface0], &default_mac_iface0); ++ if (crisv32_eth_request_irqdma(crisv32_dev[iface0])) ++ printk("%s: eth0 unable to allocate IRQ and DMA resources\n", ++ __func__); ++ np->txpackets = 0; ++ crisv32_eth_init_rings(crisv32_dev[iface0]); ++ crisv32_eth_setup_controller(crisv32_dev[iface0]); ++ ret |= crisv32_eth_init_phy(crisv32_dev[iface0]); ++ if (ret) { ++ unregister_netdev(crisv32_dev[iface0]); ++ return ret; ++ } ++} ++ ++#ifdef CONFIG_ETRAX_ETHERNET_IFACE1 ++{ ++ int iface1 = 0; ++ /* Default MAC address for interface 1. ++ * The real one will be set later. */ ++ static struct sockaddr default_mac_iface1 = ++ {0, {0x00, 0x40, 0x8C, 0xCD, 0x00, 0x01}}; ++ ++ if (crisv32_pinmux_alloc_fixed(pinmux_eth1)) ++ panic("Eth pinmux\n"); ++ ++ /* Increase index to device array if interface 0 is enabled as well.*/ ++#ifdef CONFIG_ETRAX_ETHERNET_IFACE0 ++ iface1++; ++#endif ++ if (!(crisv32_dev[iface1] = alloc_etherdev(sizeof *np))) ++ return -ENOMEM; ++ ++ ret |= crisv32_ethernet_device_init(crisv32_dev[iface1]); ++ ++ crisv32_init_leds(CRIS_LED_GRP_NONE,crisv32_dev[iface1]); ++ ++ np = (struct crisv32_ethernet_local *) netdev_priv(crisv32_dev[iface1]); ++ np->eth_inst = regi_eth1; ++ np->dma_out_inst = regi_dma6; ++ np->dma_in_inst = regi_dma7; ++ ++ np->mii_if.dev = crisv32_dev[iface1]; ++ np->mii_if.mdio_read = crisv32_eth_get_mdio_reg; ++ np->mii_if.mdio_write = crisv32_eth_set_mdio_reg; ++ np->mii_if.phy_id_mask = 0x1f; ++ np->mii_if.reg_num_mask = 0x1f; ++ ++ ++ register_netdev(crisv32_dev[iface1]); ++ ++ /* Set up default MAC address */ ++ memcpy(crisv32_dev[iface1]->dev_addr, default_mac_iface1.sa_data, 6); ++ crisv32_eth_set_mac_address(crisv32_dev[iface1], &default_mac_iface1); ++ ++ if (crisv32_eth_request_irqdma(crisv32_dev[iface1])) ++ printk("%s: eth1 unable to allocate IRQ and DMA resources\n", ++ __func__); ++ np->txpackets = 0; ++ crisv32_eth_init_rings(crisv32_dev[iface1]); ++ crisv32_eth_setup_controller(crisv32_dev[iface1]); ++ ret |= crisv32_eth_init_phy(crisv32_dev[iface1]); ++ if (ret) { ++ unregister_netdev(crisv32_dev[iface1]); ++ return ret; ++ } ++} ++#endif /* CONFIG_ETRAX_ETHERNET_IFACE1 */ ++ ++#ifdef CONFIG_CPU_FREQ ++ cpufreq_register_notifier(&crisv32_ethernet_freq_notifier_block, ++ CPUFREQ_TRANSITION_NOTIFIER); ++#endif ++ ++ return ret; ++} ++ ++static struct net_device_ops crisv32_netdev_ops = { ++ .ndo_open = crisv32_eth_open, ++ .ndo_stop = crisv32_eth_close, ++ .ndo_start_xmit = crisv32_eth_send_packet, ++ .ndo_set_rx_mode = crisv32_eth_set_rx_mode, ++ .ndo_validate_addr = eth_validate_addr, ++ .ndo_set_mac_address = crisv32_eth_set_mac_address, ++ .ndo_do_ioctl =crisv32_eth_ioctl, ++ .ndo_get_stats = crisv32_get_stats, ++ .ndo_tx_timeout = crisv32_eth_do_tx_recovery, ++ .ndo_set_config = crisv32_eth_set_config, ++}; ++ ++static int __init crisv32_ethernet_device_init(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np; ++ struct timer_list timer_init = TIMER_INITIALIZER(NULL, 0, 0); ++ ++ dev->base_addr = 0; /* Just to have something to show. */ ++ ++ /* we do our own locking */ ++ dev->features |= NETIF_F_LLTX; ++ ++ /* We use several IRQs and DMAs so just report 0 here. */ ++ dev->irq = 0; ++ dev->dma = 0; ++ ++ /* ++ * Fill in our handlers so the network layer can talk to us in the ++ * future. ++ */ ++ dev->netdev_ops = &crisv32_netdev_ops; ++ dev->ethtool_ops = &crisv32_ethtool_ops; ++ dev->watchdog_timeo = HZ * 10; ++#ifdef CONFIG_NET_POLL_CONTROLLER ++ dev->poll_controller = crisv32_netpoll; ++#endif ++ np = netdev_priv(dev); ++ np->dev = dev; ++ ++ /* ++ * 8 skbs keeps the system very reponsive even under high load. ++ * At 64 the system locks, pretty much the same way as without NAPI. ++ * ++ * TODO: meassure with 2 interfaces ++ */ ++ netif_napi_add(dev, &np->napi, crisv32_eth_poll, 8); ++ ++ spin_lock_init(&np->lock); ++ spin_lock_init(&np->transceiver_lock); ++ ++ np->receive_timer = timer_init; ++ np->receive_timer.data = (unsigned)dev; ++ np->receive_timer.function = receive_timeout; ++ ++ INIT_WORK(&np->receive_work, receive_timeout_work); ++ ++ np->transmit_timer = timer_init; ++ np->transmit_timer.data = (unsigned)dev; ++ np->transmit_timer.function = transmit_timeout; ++ ++ return 0; ++} ++ ++static int crisv32_eth_open(struct net_device *dev) ++{ ++ struct sockaddr mac_addr; ++ reg_dma_rw_ack_intr ack_intr = { .data = 1, .in_eop = 1 }; ++ reg_eth_rw_clr_err clr_err = {.clr = regk_eth_yes}; ++ /* ++ * dont interrupt us at any stat counter thresholds, only at urun ++ * and exc_col. ++ */ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ /* For Artpec-3 we use overrun to workaround voodoo TR 87 */ ++ int intr_mask_nw = 0x1c00; ++#else ++ int intr_mask_nw = 0x1800; ++#endif ++ int eth_ack_intr = 0xffff; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ spin_lock(&np->lock); ++ crisv32_eth_set_gigabit(np, 0); ++ ++ crisv32_disable_tx_ints(np); ++ crisv32_disable_rx_ints(np); ++ ++ REG_WR(eth, np->eth_inst, rw_clr_err, clr_err); ++ REG_WR_INT(eth, np->eth_inst, rw_ack_intr, eth_ack_intr); ++ REG_WR_INT(eth, np->eth_inst, rw_intr_mask, intr_mask_nw); ++ crisv32_eth_reset_rings(dev); ++ ++ /* Give the hardware an idea of what MAC address we want. */ ++ memcpy(mac_addr.sa_data, dev->dev_addr, dev->addr_len); ++ crisv32_eth_set_mac_address(dev, &mac_addr); ++ ++ /* Enable irq and make sure that the irqs are cleared. */ ++ REG_WR(dma, np->dma_out_inst, rw_ack_intr, ack_intr); ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ ++ crisv32_disconnect_eth_rx_dma(np); ++ ++ /* Prepare input DMA. */ ++ DMA_RESET(np->dma_in_inst); ++ DMA_ENABLE(np->dma_in_inst); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ DMA_WR_CMD(np->dma_in_inst, regk_dma_set_w_size2); ++#endif ++ DMA_START_CONTEXT(np->dma_in_inst, virt_to_phys(&np->ctxt_in)); ++ DMA_CONTINUE(np->dma_in_inst); ++ crisv32_enable_rx_ints(np); ++ crisv32_start_receiver(np); ++ ++ /* Prepare output DMA. */ ++ DMA_RESET(np->dma_out_inst); ++ DMA_ENABLE(np->dma_out_inst); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_set_w_size4); ++#endif ++ crisv32_connect_eth_rx_dma(np); ++ ++ netif_start_queue(dev); ++ crisv32_enable_tx_ints(np); ++ ++ if (!np->fixed_phy) { ++ /* Start duplex/speed timers */ ++ if (!timer_pending(&np->speed_timer)) ++ add_timer(&np->speed_timer); ++ if (!timer_pending(&np->duplex_timer)) ++ add_timer(&np->duplex_timer); ++ } ++ ++ spin_unlock(&np->lock); ++ /* ++ * We are now ready to accept transmit requests from the queueing ++ * layer of the networking. ++ */ ++ np->link = 1; ++ netif_carrier_on(dev); ++ napi_enable(&np->napi); ++ ++ return 0; ++} ++ ++static int crisv32_eth_close(struct net_device *dev) ++{ ++ reg_dma_rw_ack_intr ack_intr = {0}; ++ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ unsigned long flags; ++ ++ del_timer(&np->transmit_timer); ++ spin_lock_irqsave(&np->lock, flags); ++ ++ /* stop the receiver before the DMA channels to avoid overruns. */ ++ crisv32_disable_rx_ints(np); ++ napi_disable(&np->napi); ++ crisv32_stop_receiver(np); ++ ++ netif_stop_queue(dev); ++ ++ /* Reset the TX DMA in case it has hung on something. */ ++ DMA_RESET(np->dma_in_inst); ++ ++ /* Stop DMA */ ++ DMA_STOP(np->dma_in_inst); ++ DMA_STOP(np->dma_out_inst); ++ ++ /* Disable irq and make sure that the irqs are cleared. */ ++ crisv32_disable_tx_ints(np); ++ ack_intr.data = 1; ++ REG_WR(dma, np->dma_out_inst, rw_ack_intr, ack_intr); ++ ++ ack_intr.in_eop = 1; ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ ++ np->sender_started = 0; ++ spin_unlock_irqrestore(&np->lock, flags); ++ ++ /* Update the statistics. */ ++ update_rx_stats(np); ++ update_tx_stats(np); ++ ++ if (!np->fixed_phy) { ++ /* Stop speed/duplex timers */ ++ del_timer(&np->speed_timer); ++ del_timer(&np->duplex_timer); ++ } ++ ++ return 0; ++} ++ ++static int crisv32_eth_set_mac_address(struct net_device *dev, void *vpntr) ++{ ++ int i; ++ static int first = 1; ++ ++ unsigned char *addr = ((struct sockaddr*)vpntr)->sa_data; ++ ++ reg_eth_rw_ma0_lo ma0_lo = ++ { addr[0] | (addr[1] << 8) | (addr[2] << 16) | (addr[3] << 24)}; ++ ++ reg_eth_rw_ma0_hi ma0_hi = { addr[4] | (addr[5] << 8) }; ++ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ /* Remember the address. */ ++ memcpy(dev->dev_addr, addr, dev->addr_len); ++ ++ /* ++ * Write the address to the hardware. ++ * Note the way the address is wrapped: ++ * ma0_l0 = a0_0 | (a0_1 << 8) | (a0_2 << 16) | (a0_3 << 24); ++ * ma0_hi = a0_4 | (a0_5 << 8); ++ */ ++ REG_WR(eth, np->eth_inst, rw_ma0_lo, ma0_lo); ++ REG_WR(eth, np->eth_inst, rw_ma0_hi, ma0_hi); ++ ++ if (first) { ++ printk(KERN_INFO "%s: changed MAC to ", dev->name); ++ ++ for (i = 0; i < 5; i++) ++ printk("%02X:", dev->dev_addr[i]); ++ printk("%02X\n", dev->dev_addr[i]); ++ ++ first = 0; ++ } ++ ++ return 0; ++} ++ ++static irqreturn_t crisv32rx_eth_interrupt(int irq, void *dev_id) ++{ ++ struct net_device *dev = (struct net_device *) dev_id; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_dma_r_masked_intr masked_in; ++ ++ masked_in = REG_RD(dma, np->dma_in_inst, r_masked_intr); ++ ++ if (masked_in.in_eop) { ++ reg_dma_rw_ack_intr ack_intr = {0}; ++ ++ /* ++ * Ack the rx irq even if we are not prepared to start ++ * polling. This is needed to handle incomming packets ++ * during the stop sequence. ++ */ ++ ack_intr.in_eop = 1; ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ ++ mod_timer(&np->receive_timer, jiffies + HZ); ++ np->do_rx_recovery = 0; ++ ++ if (napi_schedule_prep(&np->napi)) { ++ crisv32_disable_rx_ints(np); ++ crisv32_disable_tx_ints(np); ++ /* put us onto the poll list */ ++ __napi_schedule(&np->napi); ++ } ++ } else { ++ /* Unexpected, ACK it and hope for the best. */ ++ reg_dma_rw_ack_intr ack_intr = { ++ .group = 1, ++ .ctxt = 1, ++ .data = 1, ++ .in_eop = 0, ++ .stream_cmd = 1, ++ .dummy1 = ~0 ++ }; ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ } ++ ++ return IRQ_HANDLED; ++} ++ ++static inline void crisv32_eth_roll_tx_timer(struct crisv32_ethernet_local *np) ++{ ++ /* If there are more packets in the ring, roll the tx timer. */ ++ if (np->txpackets) { ++ /* Eth pause frames may halt us for up to 320ms (100mbit). */ ++ unsigned long timeout = jiffies + (HZ / 3) + 1; ++ mod_timer(&np->transmit_timer, timeout); ++ } ++ else ++ del_timer(&np->transmit_timer); ++} ++ ++/* Call with np->lock held. */ ++static void _crisv32_tx_ring_advance(struct crisv32_ethernet_local *np, ++ int cleanup) ++{ ++ reg_dma_rw_stat stat; ++ dma_descr_data *dma_pos; ++ struct net_device *dev = np->dev; ++ int eol; ++ ++ /* Get the current output dma position. */ ++ dma_pos = phys_to_virt(REG_RD_INT(dma, np->dma_out_inst, rw_data)); ++ stat = REG_RD(dma, np->dma_out_inst, rw_stat); ++ eol = stat.list_state == regk_dma_data_at_eol; ++ if (cleanup || eol) ++ dma_pos = &np->active_tx_desc->descr; ++ ++ /* Take care of transmited dma descriptors and report sent packet. */ ++ while (np->txpackets && (&np->catch_tx_desc->descr != dma_pos)) { ++ /* Update sent packet statistics. */ ++ np->stats.tx_bytes += np->catch_tx_desc->skb->len; ++ np->stats.tx_packets++; ++ ++ dev_kfree_skb_any(np->catch_tx_desc->skb); ++ np->catch_tx_desc->skb = 0; ++ np->txpackets--; ++ np->catch_tx_desc->descr.buf = 0; ++ np->catch_tx_desc = ++ phys_to_virt((int)np->catch_tx_desc->descr.next); ++ np->do_tx_recovery = 0; ++ np->retrans = 0; ++ ++ netif_wake_queue(dev); ++ } ++} ++ ++static inline void crisv32_tx_ring_advance(struct crisv32_ethernet_local *np) ++{ ++ unsigned long flags; ++ ++ spin_lock_irqsave(&np->lock, flags); ++ _crisv32_tx_ring_advance(np, 0); ++ crisv32_eth_roll_tx_timer(np); ++ spin_unlock_irqrestore(&np->lock, flags); ++} ++ ++static inline int crisv32_tx_complete(struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_ack_intr ack_intr = { .data = 1 }; ++ reg_dma_r_intr ints; ++ int r = 0; ++ ++ /* We are interested in the unmasked raw interrupt source here. When ++ polling with tx interrupts masked off we still want to do ++ tx completition when the DMA makes progress. */ ++ ints = REG_RD(dma, np->dma_out_inst, r_intr); ++ if (ints.data) ++ { ++ /* ack the interrupt, if it was active */ ++ REG_WR(dma, np->dma_out_inst, rw_ack_intr, ack_intr); ++ crisv32_tx_ring_advance(np); ++ r = 1; ++ } ++ return r; ++} ++ ++static irqreturn_t crisv32tx_eth_interrupt(int irq, void *dev_id) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev_id); ++ ++ crisv32_tx_complete(np); ++ return IRQ_HANDLED; ++} ++ ++ ++/* Update receive errors. */ ++static void ++update_rx_stats(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rs_rec_cnt r; ++ ++ r = REG_RD(eth, np->eth_inst, rs_rec_cnt); ++ ++ np->stats.rx_over_errors += r.congestion; ++ np->stats.rx_crc_errors += r.crc_err; ++ np->stats.rx_frame_errors += r.align_err; ++ np->stats.rx_length_errors += r.oversize; ++ np->stats.rx_errors += r.crc_err + r.align_err + ++ r.oversize + r.congestion; ++} ++ ++/* Update transmit errors. */ ++static void update_tx_stats(struct crisv32_ethernet_local *np) ++{ ++ reg_eth_rs_tr_cnt r; ++ reg_eth_rs_phy_cnt rp; ++ ++ r = REG_RD(eth, np->eth_inst, rs_tr_cnt); ++ rp = REG_RD(eth, np->eth_inst, rs_phy_cnt); ++ ++ /* r.deferred is not good for counting collisions because it also ++ includes frames that have to wait for the interframe gap. That ++ means we get deferred frames even when in full duplex. ++ Here we don't actually count the number of collisions that ++ occured (artpec3 seems to lack such a counter), instead we count ++ the number of frames that collide once or more. */ ++ np->stats.collisions += r.mult_col + r.single_col; ++ np->stats.tx_window_errors += r.late_col; ++ np->stats.tx_carrier_errors += rp.carrier_loss; ++ ++ /* Ordinary collisions are not errors, they are just part of ++ ethernet's bus arbitration and congestion control mechanisms. ++ Late collisions are serious errors though. */ ++ np->stats.tx_errors += r.late_col; ++} ++ ++/* Get current statistics. */ ++static struct net_device_stats *crisv32_get_stats(struct net_device *dev) ++{ ++ unsigned long flags; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ spin_lock_irqsave(&np->lock, flags); ++ ++ update_rx_stats(np); ++ update_tx_stats(np); ++ ++ spin_unlock_irqrestore(&np->lock, flags); ++ ++ return &np->stats; ++} ++ ++/* Check for network errors. This acknowledge the received interrupt. */ ++static irqreturn_t crisv32nw_eth_interrupt(int irq, void *dev_id) ++{ ++ struct net_device *dev = (struct net_device *) dev_id; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_eth_r_masked_intr intr_mask; ++ int ack_intr = 0xffff; ++ reg_eth_rw_clr_err clr_err; ++ ++ intr_mask = REG_RD(eth, np->eth_inst, r_masked_intr); ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ /* Only apply the workaround if it is not already pending. ++ enable_eth_ints will re-enable the orun interrupt regardless ++ of pending_overrun. */ ++ if (intr_mask.orun && !np->pending_overrun) { ++ reg_eth_rw_rec_ctrl rec_ctrl = ++ REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ np->saved_rec_ctrl = rec_ctrl; ++ np->overrun_set = 1; ++ DMA_STOP(np->dma_in_inst); ++ rec_ctrl.ma0 = regk_eth_no; ++ rec_ctrl.broadcast = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ np->saved_ga_lo = REG_RD_INT(eth, np->eth_inst, rw_ga_lo); ++ np->saved_ga_hi = REG_RD_INT(eth, np->eth_inst, rw_ga_hi); ++ REG_WR_INT(eth, np->eth_inst, rw_ga_lo, 0); ++ REG_WR_INT(eth, np->eth_inst, rw_ga_hi, 0); ++ REG_WR_INT(eth, np->eth_inst, rw_intr_mask, ++ REG_RD_INT(eth, np->eth_inst, rw_intr_mask) & 0xfbff); ++ REG_WR_INT(eth, np->eth_inst, rw_ack_intr, 0x400); ++ intr_mask.orun = 0; ++ np->pending_overrun = 1; ++ if (!np->napi_processing) ++ crisv32_eth_restart_rx_dma(np->dev, np); ++ ++ return IRQ_HANDLED; ++ } ++#endif ++ ++ /* ++ * Check for underrun and/or excessive collisions. Note that the ++ * rw_clr_err register clears both underrun and excessive collision ++ * errors, so there's no need to check them separately. ++ */ ++ if (np->sender_started ++ && (intr_mask.urun || intr_mask.exc_col)) { ++ unsigned long flags; ++ ++ /* Underrun are considered to be tx-errors. */ ++ np->stats.tx_errors += intr_mask.urun; ++ np->stats.tx_fifo_errors += intr_mask.urun; ++ ++ /* ++ * Protect against the tx-interrupt messing with ++ * the tx-ring. ++ */ ++ spin_lock_irqsave(&np->lock, flags); ++ ++ /* DMA should have stopped now, eat from the ring before ++ removing anything due to tx errors. */ ++ _crisv32_tx_ring_advance(np, 0); ++ ++ /* ++ * Drop packets after 15 retries. ++ * TODO: Add backoff. ++ */ ++ if (np->retrans > 15 && np->txpackets) { ++ dev_kfree_skb_irq(np->catch_tx_desc->skb); ++ np->catch_tx_desc->skb = 0; ++ np->catch_tx_desc->descr.buf = 0; ++ np->catch_tx_desc = ++ phys_to_virt((int) ++ np->catch_tx_desc->descr.next); ++ flush_dma_descr(&np->catch_tx_desc->descr, 0); ++ ++ np->txpackets--; ++ np->retrans = 0; ++ netif_wake_queue(dev); ++ np->stats.tx_dropped++; ++ } ++ np->ctxt_out.next = 0; ++ if (np->txpackets) { ++ np->retrans++; ++ np->ctxt_out.saved_data = (void *) ++ virt_to_phys(&np->catch_tx_desc->descr); ++ np->ctxt_out.saved_data_buf = ++ np->catch_tx_desc->descr.buf; ++ WARN_ON(!np->ctxt_out.saved_data_buf); ++ flush_dma_descr(&np->catch_tx_desc->descr, 0); ++ cris_flush_cache_range(&np->ctxt_out, ++ sizeof np->ctxt_out); ++ ++ /* restart the DMA */ ++ DMA_START_CONTEXT(np->dma_out_inst, ++ (int) virt_to_phys(&np->ctxt_out)); ++ np->sender_started = 1; ++ } ++ else { ++ /* Load dummy context but do not load the data ++ descriptor nor start the burst. This brings the ++ buggy eth transmitter back in sync with the DMA ++ avoiding malformed frames. */ ++ REG_WR(dma, np->dma_out_inst, rw_group_down, ++ (int) virt_to_phys(&np->ctxt_out)); ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_load_c); ++ np->sender_started = 0; ++ } ++ crisv32_eth_roll_tx_timer(np); ++ spin_unlock_irqrestore(&np->lock, flags); ++ } ++ ++ ack_intr = *(u32 *)&intr_mask; ++ REG_WR_INT(eth, np->eth_inst, rw_ack_intr, ack_intr); ++ clr_err.clr = 1; ++ REG_WR(eth, np->eth_inst, rw_clr_err, clr_err); ++ ++ update_rx_stats(np); ++ update_tx_stats(np); ++ ++ return IRQ_HANDLED; ++} ++ ++/* We have a good packet(s), get it/them out of the buffers. */ ++static int crisv32_eth_receive_packet(struct net_device *dev) ++{ ++ int length; ++ struct sk_buff *skb; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ struct sk_buff *tmp; ++ unsigned long flags; ++ ++ DEBUG(printk("crisv32_receive_packet\n")); ++ ++ /* Roll the rx bug timer. */ ++ mod_timer(&np->receive_timer, jiffies + HZ); ++ ++ /* Activate LED */ ++ spin_lock_irqsave(&np->leds->led_lock, flags); ++ if (!np->leds->led_active && time_after(jiffies, ++ np->leds->led_next_time)) { ++ /* light the network leds depending on the current speed. */ ++ crisv32_set_network_leds(CRIS_LED_ACTIVITY, dev); ++ ++ /* Set the earliest time we may clear the LED */ ++ np->leds->led_next_time = jiffies + NET_FLASH_TIME; ++ np->leds->led_active = 1; ++ np->leds->clear_led_timer.data = (unsigned long) dev; ++ mod_timer(&np->leds->clear_led_timer, jiffies + HZ/10); ++ } ++ spin_unlock_irqrestore(&np->leds->led_lock, flags); ++ ++ /* Discard CRC (4 bytes). */ ++ length = (np->active_rx_desc->descr.after) - ++ (np->active_rx_desc->descr.buf) - 4; ++ ++ tmp = dev_alloc_skb(MAX_MEDIA_DATA_SIZE); ++ if (!tmp) { ++ np->stats.rx_errors++; ++ printk(KERN_NOTICE "%s: memory squeeze," ++ " dropping packet.", ++ dev->name); ++ return 0; ++ } ++ skb = np->active_rx_desc->skb; ++ np->active_rx_desc->skb = tmp; ++ skb_put(skb, length); ++ ++ np->newbuf = virt_to_phys(np->active_rx_desc->skb->data); ++ ++ skb->dev = dev; ++ skb->protocol = eth_type_trans(skb, dev); ++ skb->ip_summed = CHECKSUM_NONE; ++ ++ np->stats.multicast += skb->pkt_type == PACKET_MULTICAST; ++ /* Send the packet to the upper layer. */ ++ netif_receive_skb(skb); ++ np->last_rx_desc = ++ phys_to_virt((int) ++ np->last_rx_desc->descr.next); ++ ++ /* Forward rotate the receive ring. */ ++ crisv32_eth_rx_ring_advance(np); ++ return length; ++} ++ ++/* Must be called with the np-lock held. */ ++static void ++__crisv32_eth_restart_rx_dma(struct net_device* dev, ++ struct crisv32_ethernet_local *np) ++{ ++ reg_dma_rw_ack_intr ack_intr = {0}; ++ reg_dma_rw_stream_cmd dma_sc = {0}; ++ reg_dma_rw_stat stat; ++ int resets = 0; ++ reg_eth_rw_intr_mask eth_intr_mask; ++ ++ np->rx_dma_restarts++; ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ if (np->pending_overrun) { ++ np->pending_overrun = 0; ++ REG_WR_INT(eth, np->eth_inst, rw_ga_lo, np->saved_ga_lo); ++ REG_WR_INT(eth, np->eth_inst, rw_ga_hi, np->saved_ga_hi); ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, np->saved_rec_ctrl); ++ REG_WR_INT(eth, np->eth_inst, rw_intr_mask, ++ REG_RD_INT(eth, regi_eth, rw_intr_mask) | 0x400); ++ DMA_CONTINUE(np->dma_in_inst); ++ } ++#endif ++ /* Bring down the receiver. */ ++ crisv32_disable_rx_ints(np); ++ crisv32_disconnect_eth_rx_dma(np); ++ ++ /* Stop DMA and ack possible ints. */ ++ DMA_STOP(np->dma_in_inst); ++ ack_intr.in_eop = 1; ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ ++ crisv32_stop_receiver(np); ++ ++ /* Disable overrun interrupts while receive is shut off. */ ++ eth_intr_mask = REG_RD(eth, np->eth_inst, rw_intr_mask); ++ eth_intr_mask.orun = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_intr_mask, eth_intr_mask); ++ /* ACK overrun. */ ++ REG_WR_INT(eth, np->eth_inst, rw_ack_intr, 0x400); ++ ++ crisv32_eth_reset_rx_ring(dev); ++ reset: ++ /* TODO: if nr resets grows to high we should reboot. */ ++ if (resets++ > 0) ++ printk("reset DMA %d.\n", resets); ++ ++ DMA_RESET(np->dma_in_inst); ++ /* Wait for the channel to reset. */ ++ do { ++ stat = REG_RD(dma, np->dma_in_inst, rw_stat); ++ } while (stat.mode != regk_dma_rst); ++ ++ /* Now bring the rx path back up. */ ++ DMA_ENABLE(np->dma_in_inst); ++ if (dma_wait_busy(np->dma_in_inst, 100)) ++ goto reset; ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++// DMA_WR_CMD(np->dma_in_inst, regk_dma_set_w_size2); ++ dma_sc.cmd = (regk_dma_set_w_size2); ++ REG_WR(dma, np->dma_in_inst, rw_stream_cmd, dma_sc); ++ if (dma_wait_busy(np->dma_in_inst, 100)) ++ goto reset; ++#endif ++ ++// DMA_START_CONTEXT(np->dma_in_inst, virt_to_phys(&np->ctxt_in)); ++ REG_WR_INT(dma, np->dma_in_inst, rw_group_down, (int)&np->ctxt_in); ++ ++// DMA_WR_CMD(np->dma_in_inst, regk_dma_load_c); ++ dma_sc.cmd = (regk_dma_load_c); ++ REG_WR(dma, np->dma_in_inst, rw_stream_cmd, dma_sc); ++ if (dma_wait_busy(np->dma_in_inst, 100)) ++ goto reset; ++ ++// DMA_WR_CMD(np->dma_in_inst, regk_dma_load_d | regk_dma_burst); ++ dma_sc.cmd = (regk_dma_load_d | regk_dma_burst); ++ REG_WR(dma, np->dma_in_inst, rw_stream_cmd, dma_sc); ++ ++ if (dma_wait_busy(np->dma_in_inst, 100)) ++ goto reset; ++ ++ /* Now things get critical again. Don't give us any interrupts until ++ the following sequence is complete. */ ++ DMA_CONTINUE(np->dma_in_inst); ++ np->overrun_set = 0; ++ crisv32_enable_rx_ints(np); ++ crisv32_start_receiver(np); ++ ++ /* Reenable overrun interrupts when receive is started again. */ ++ eth_intr_mask = REG_RD(eth, np->eth_inst, rw_intr_mask); ++ eth_intr_mask.orun = regk_eth_yes; ++ REG_WR(eth, np->eth_inst, rw_intr_mask, eth_intr_mask); ++ ++ crisv32_connect_eth_rx_dma(np); ++} ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++static void ++crisv32_eth_restart_rx_dma(struct net_device* dev, ++ struct crisv32_ethernet_local *np) ++{ ++ unsigned long flags; ++ ++ spin_lock_irqsave(&np->lock, flags); ++ __crisv32_eth_restart_rx_dma(dev, np); ++ spin_unlock_irqrestore(&np->lock, flags); ++} ++#endif ++ ++/* ++ * Is there work to do in the rx-path? ++ */ ++static inline int crisv32_has_rx_work(struct crisv32_ethernet_local *np, ++ dma_descr_data *active) ++{ ++ int mw; ++ mw = (active->in_eop && np->new_rx_package); ++ return mw; ++} ++ ++static void crisv32_eth_do_rx_recovery(struct net_device* dev, ++ struct crisv32_ethernet_local *np) ++{ ++ unsigned long flags; ++ static int r = 0; ++ ++ r++; ++ ++ /* Bring down the receiver. */ ++ spin_lock_irqsave(&np->lock, flags); ++ if (!np->do_rx_recovery) ++ goto done; ++ ++ napi_disable(&np->napi); ++ ++ np->rx_dma_timeouts++; ++ ++ __crisv32_eth_restart_rx_dma(dev, np); ++ ++ np->do_rx_recovery = 0; ++ ++ napi_enable(&np->napi); ++ done: ++ spin_unlock_irqrestore(&np->lock, flags); ++ ++ WARN_ON(r != 1); ++ r--; ++} ++ ++static void receive_timeout_work(struct work_struct* work) ++{ ++ struct dma_descr_data* descr; ++ struct dma_descr_data* descr2; ++ struct net_device* dev = crisv32_dev[0]; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_eth_r_intr intr_mask; ++ ++ descr = &np->active_rx_desc->descr; ++ descr2 = phys_to_virt(REG_RD_INT(dma, np->dma_in_inst, rw_data)); ++ ++ intr_mask = REG_RD(eth, np->eth_inst, r_intr); ++ ++ if (!np->overrun_set ++ && !intr_mask.orun ++ && !descr->in_eop ++ && !descr2->in_eop) ++ return; ++ ++ crisv32_eth_do_rx_recovery(dev, np); ++} ++ ++static void receive_timeout(unsigned long arg) ++{ ++ struct net_device* dev = (struct net_device*)arg; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ np->do_rx_recovery++; ++ schedule_work(&np->receive_work); ++ mod_timer(&np->receive_timer, jiffies + 1*HZ); ++} ++ ++static void transmit_timeout(unsigned long arg) ++{ ++ struct net_device* dev = (struct net_device*)arg; ++ crisv32_eth_do_tx_recovery(dev); ++} ++ ++/* ++ * NAPI poll ++ * ++ * We are allowed to pull up to budget number of frames from the rx ring. ++ * If we are done, remove us from the poll list and re-enable rx interrupts. ++ * Always return number of pulled frames from the rx ring. ++ */ ++static int crisv32_eth_poll(struct napi_struct *napi, int budget) ++{ ++ struct crisv32_ethernet_local *np; ++ int work_done = 0; ++ int morework; ++ int rx_bytes = 0; ++ reg_dma_rw_ack_intr ack_intr = {0}; ++ ++ np = container_of(napi, struct crisv32_ethernet_local, napi); ++ crisv32_disable_eth_ints(np); ++ np->napi_processing = 1; ++ ack_intr.in_eop = 1; ++ ++ if (np->new_rx_package == 0) { ++ /* ++ * In the previous round we pulled a packet from the ring but ++ * we didn't advance the ring due to hw DMA bug. Try to do it ++ * now. ++ */ ++ np->new_rx_package = 1; ++ crisv32_eth_rx_ring_advance(np); ++ } ++ ++ morework = crisv32_has_rx_work(np, &np->active_rx_desc->descr); ++ ++ /* See if tx needs attention. */ ++ crisv32_tx_complete(np); ++ ++ while (morework) ++ { ++ rx_bytes += crisv32_eth_receive_packet(np->dev); ++ work_done++; ++ ++ /* Ack irq and restart rx dma */ ++ REG_WR(dma, np->dma_in_inst, rw_ack_intr, ack_intr); ++ DMA_CONTINUE_DATA(np->dma_in_inst); ++ ++ if (unlikely(work_done >= budget)) ++ break; ++ ++ /* See if tx needs attention. */ ++ crisv32_tx_complete(np); ++ ++ morework = crisv32_has_rx_work(np, &np->active_rx_desc->descr); ++ } ++ crisv32_enable_eth_ints(np); ++ ++ if (!morework) { ++ np->napi_processing = 0; ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ if (np->pending_overrun) { ++ crisv32_eth_restart_rx_dma(np->dev, np); ++ } ++#endif ++ if (irqs_disabled()) ++ printk("WARNING: %s irqs disabled!\n", __func__); ++ ++ if (work_done < budget) { ++ /* first mark as done, then enable irq's */ ++ napi_complete(napi); ++ crisv32_enable_rx_ints(np); ++ crisv32_enable_tx_ints(np); ++ } ++ } ++ np->napi_processing = 0; ++ ++ np->stats.rx_bytes += rx_bytes; ++ np->stats.rx_packets += work_done; ++ update_rx_stats(np); ++ return work_done; ++} ++ ++/* ++ * This function (i.e. hard_start_xmit) is protected from concurent calls by a ++ * spinlock (xmit_lock) in the net_device structure. ++ */ ++static int ++crisv32_eth_send_packet(struct sk_buff *skb, struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ unsigned char *buf = skb->data; ++ unsigned long flags; ++ ++ /* ++ * Need to disable irq to avoid updating pointer in interrupt while ++ * sending packets. ++ */ ++ spin_lock_irqsave(&np->lock, flags); ++ ++ np->active_tx_desc->skb = skb; ++ crisv32_eth_hw_send_packet(buf, skb->len, np); ++ ++ /* Stop queue if full. */ ++ if (crisv32_eth_tx_ring_full(np)) ++ netif_stop_queue(dev); ++ ++ np->txpackets++; ++ crisv32_eth_roll_tx_timer(np); ++ spin_unlock_irqrestore(&np->lock, flags); ++ ++ spin_lock_irqsave(&np->leds->led_lock, flags); ++ if (!np->leds->led_active && time_after(jiffies, ++ np->leds->led_next_time)) { ++ /* light the network leds depending on the current speed. */ ++ crisv32_set_network_leds(CRIS_LED_ACTIVITY, dev); ++ ++ /* Set the earliest time we may clear the LED */ ++ np->leds->led_next_time = jiffies + NET_FLASH_TIME; ++ np->leds->led_active = 1; ++ np->leds->clear_led_timer.data = (unsigned long) dev; ++ mod_timer(&np->leds->clear_led_timer, jiffies + HZ/10); ++ } ++ spin_unlock_irqrestore(&np->leds->led_lock, flags); ++ ++ return 0; ++} ++ ++ ++static void ++crisv32_eth_hw_send_packet(unsigned char *buf, int length, void *priv) ++{ ++ struct crisv32_ethernet_local *np = ++ (struct crisv32_ethernet_local *) priv; ++ ++ /* Configure the tx dma descriptor. */ ++ np->active_tx_desc->descr.buf = (unsigned char *)virt_to_phys(buf); ++ ++ np->active_tx_desc->descr.after = np->active_tx_desc->descr.buf + ++ length; ++ np->active_tx_desc->descr.intr = 1; ++ np->active_tx_desc->descr.out_eop = 1; ++ ++ /* Move eol. */ ++ np->active_tx_desc->descr.eol = 1; ++ flush_dma_descr(&np->active_tx_desc->descr, 1); ++ ++ if (np->sender_started) ++ WARN_ON(!np->prev_tx_desc->descr.eol); ++ np->prev_tx_desc->descr.eol = 0; ++ flush_dma_descr(&np->prev_tx_desc->descr, 0); ++ ++ /* Update pointers. */ ++ np->prev_tx_desc = np->active_tx_desc; ++ np->active_tx_desc = phys_to_virt((int)np->active_tx_desc->descr.next); ++ ++ /* Start DMA. */ ++ crisv32_start_dma_out(np); ++} ++ ++static void crisv32_start_dma_out(struct crisv32_ethernet_local *np) ++{ ++ if (!np->sender_started) { ++ /* Start DMA for the first time. */ ++ np->ctxt_out.saved_data = ++ (void *)virt_to_phys(&np->prev_tx_desc->descr); ++ np->ctxt_out.saved_data_buf = np->prev_tx_desc->descr.buf; ++ WARN_ON(!np->ctxt_out.saved_data_buf); ++ ++ cris_flush_cache_range(&np->ctxt_out, sizeof np->ctxt_out); ++ REG_WR(dma, np->dma_out_inst, rw_group_down, ++ (int) virt_to_phys(&np->ctxt_out)); ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_load_c); ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_load_d | regk_dma_burst); ++ np->sender_started = 1; ++ } else { ++ DMA_CONTINUE_DATA(np->dma_out_inst); ++ } ++} ++ ++/* ++ * Bring the transmitter back to life. ++ */ ++static void ++crisv32_eth_do_tx_recovery(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_eth_rw_clr_err clr_err; ++ reg_dma_rw_stat stat = {0}; ++ unsigned long flags; ++ /* ACK urun and exc_col. */ ++ int ack_intr = 0x1800; ++ int do_full; ++ ++ /* Give the tx recovery some time without link state polling. */ ++ if (!np->fixed_phy) ++ mod_timer(&np->speed_timer, jiffies + 4 * HZ); ++ ++ np->tx_dma_restarts++; ++ ++ spin_lock_irqsave(&np->lock, flags); ++ ++ do_full = 1; ++ update_tx_stats(np); ++ ++ /* Cancel ongoing frame. */ ++ crisv32_eth_tx_cancel_frame(np); ++ ++ /* In case TR 125 just hit us. */ ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_ack_pkt); ++ dma_wait_busy(np->dma_out_inst, 100); ++ ++ /* At this point, the transmit block should be idle or waiting for us ++ to clear the excessive collision error. Let's reset the DMA. */ ++ DMA_STOP(np->dma_out_inst); ++ ++ crisv32_disconnect_eth_tx_dma(np); ++ ++ /* Eat from the tx ring. */ ++ _crisv32_tx_ring_advance(np, 1); ++ np->do_tx_recovery++; ++ ++ DMA_RESET(np->dma_out_inst); ++ do { ++ stat = REG_RD(dma, np->dma_out_inst, rw_stat); ++ } while (stat.mode != regk_dma_rst); ++ ++ /* Next packet will restart output DMA. */ ++ np->sender_started = 0; ++ ++ crisv32_enable_tx_ints(np); ++ ++ DMA_ENABLE(np->dma_out_inst); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_set_w_size4); ++#endif ++ DMA_CONTINUE(np->dma_out_inst); ++ ++ /* Clear pending errors. */ ++ REG_WR_INT(eth, np->eth_inst, rw_ack_intr, ack_intr); ++ clr_err.clr = 1; ++ REG_WR(eth, np->eth_inst, rw_clr_err, clr_err); ++ ++ /* Do a full reset of the MAC block. */ ++ if (do_full) { ++ np->tx_mac_resets++; ++ crisv32_eth_reset(np); ++ } ++ ++ crisv32_connect_eth_tx_dma(np); ++ ++ if (np->txpackets) { ++ WARN_ON(!np->catch_tx_desc->skb); ++ np->catch_tx_desc->descr.intr = 1; ++ np->catch_tx_desc->descr.out_eop = 1; ++ ++ /* Start DMA for the first time. */ ++ np->ctxt_out.saved_data = ++ (void *)virt_to_phys(&np->catch_tx_desc->descr); ++ np->ctxt_out.saved_data_buf = np->catch_tx_desc->descr.buf; ++ WARN_ON(!np->ctxt_out.saved_data_buf); ++ flush_dma_descr(&np->catch_tx_desc->descr, 0); ++ cris_flush_cache_range(&np->ctxt_out, sizeof np->ctxt_out); ++ ++ REG_WR(dma, np->dma_out_inst, rw_group_down, ++ (int) virt_to_phys(&np->ctxt_out)); ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_load_c); ++ DMA_WR_CMD(np->dma_out_inst, regk_dma_load_d | regk_dma_burst); ++ crisv32_eth_roll_tx_timer(np); ++ np->sender_started = 1; ++ } ++ ++ if (np->txpackets && crisv32_eth_tx_ring_full(np)) ++ netif_stop_queue(dev); ++ else ++ netif_wake_queue(dev); ++ ++ spin_unlock_irqrestore(&np->lock, flags); ++} ++ ++/* ++ * Set or clear the multicast filter for this adaptor. ++ * num_addrs == -1 Promiscuous mode, receive all packets ++ * num_addrs == 0 Normal mode, clear multicast list ++ * num_addrs > 0 Multicast mode, receive normal and MC packets, ++ * and do best-effort filtering. ++ */ ++static void crisv32_eth_set_rx_mode(struct net_device *dev) ++{ ++ int num_addr = netdev_mc_count(dev); ++ unsigned long int lo_bits; ++ unsigned long int hi_bits; ++ reg_eth_rw_rec_ctrl rec_ctrl = {0}; ++ reg_eth_rw_ga_lo ga_lo = {0}; ++ reg_eth_rw_ga_hi ga_hi = {0}; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ if (dev->flags & IFF_PROMISC) { ++ /* Promiscuous mode. */ ++ lo_bits = 0xfffffffful; ++ hi_bits = 0xfffffffful; ++ ++ /* Enable individual receive. */ ++ rec_ctrl = (reg_eth_rw_rec_ctrl) REG_RD(eth, np->eth_inst, ++ rw_rec_ctrl); ++ rec_ctrl.individual = regk_eth_yes; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } else if (dev->flags & IFF_ALLMULTI) { ++ /* Enable all multicasts. */ ++ lo_bits = 0xfffffffful; ++ hi_bits = 0xfffffffful; ++ ++ /* Disable individual receive */ ++ rec_ctrl = ++ (reg_eth_rw_rec_ctrl) REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.individual = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } else if (num_addr == 0) { ++ /* Normal, clear the mc list. */ ++ lo_bits = 0x00000000ul; ++ hi_bits = 0x00000000ul; ++ ++ /* Disable individual receive */ ++ rec_ctrl = ++ (reg_eth_rw_rec_ctrl) REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.individual = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } else { ++ /* MC mode, receive normal and MC packets. */ ++ char hash_ix; ++ struct netdev_hw_addr *ha; ++ char *baddr; ++ lo_bits = 0x00000000ul; ++ hi_bits = 0x00000000ul; ++ ++ netdev_for_each_mc_addr(ha, dev) { ++ /* Calculate the hash index for the GA registers. */ ++ hash_ix = 0; ++ baddr = ha->addr; ++ hash_ix ^= (*baddr) & 0x3f; ++ hash_ix ^= ((*baddr) >> 6) & 0x03; ++ ++baddr; ++ hash_ix ^= ((*baddr) << 2) & 0x03c; ++ hash_ix ^= ((*baddr) >> 4) & 0xf; ++ ++baddr; ++ hash_ix ^= ((*baddr) << 4) & 0x30; ++ hash_ix ^= ((*baddr) >> 2) & 0x3f; ++ ++baddr; ++ hash_ix ^= (*baddr) & 0x3f; ++ hash_ix ^= ((*baddr) >> 6) & 0x03; ++ ++baddr; ++ hash_ix ^= ((*baddr) << 2) & 0x03c; ++ hash_ix ^= ((*baddr) >> 4) & 0xf; ++ ++baddr; ++ hash_ix ^= ((*baddr) << 4) & 0x30; ++ hash_ix ^= ((*baddr) >> 2) & 0x3f; ++ ++ hash_ix &= 0x3f; ++ ++ if (hash_ix > 32) ++ hi_bits |= (1 << (hash_ix - 32)); ++ else ++ lo_bits |= (1 << hash_ix); ++ } ++ ++ /* Disable individual receive. */ ++ rec_ctrl = ++ (reg_eth_rw_rec_ctrl) REG_RD(eth, np->eth_inst, rw_rec_ctrl); ++ rec_ctrl.individual = regk_eth_no; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } ++ ++ ga_lo.table = (unsigned int) lo_bits; ++ ga_hi.table = (unsigned int) hi_bits; ++ ++ REG_WR(eth, np->eth_inst, rw_ga_lo, ga_lo); ++ REG_WR(eth, np->eth_inst, rw_ga_hi, ga_hi); ++} ++ ++static int ++crisv32_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ++{ ++ struct mii_ioctl_data *data = if_mii(ifr); ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int old_autoneg; ++ int rc = 0; ++ ++ spin_lock(&np->lock); /* Preempt protection */ ++ switch (cmd) { ++ case SET_ETH_ENABLE_LEDS: ++ np->use_leds = 1; ++ break; ++ case SET_ETH_DISABLE_LEDS: ++ np->use_leds = 0; ++ break; ++ case SET_ETH_AUTONEG: ++ old_autoneg = np->autoneg_normal; ++ np->autoneg_normal = *(int*)data; ++ if (np->autoneg_normal != old_autoneg) ++ crisv32_eth_negotiate(dev); ++ break; ++ default: ++ rc = generic_mii_ioctl(&np->mii_if, ++ if_mii(ifr), cmd, NULL); ++ break; ++ } ++ spin_unlock(&np->lock); ++ return rc; ++} ++ ++static int crisv32_eth_get_settings(struct net_device *dev, ++ struct ethtool_cmd *cmd) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int err; ++ ++ spin_lock_irq(&np->lock); ++ err = mii_ethtool_gset(&np->mii_if, cmd); ++ spin_unlock_irq(&np->lock); ++ ++ /* The PHY may support 1000baseT, but the EtraxFS does not. */ ++ cmd->supported &= ~(SUPPORTED_1000baseT_Half ++ | SUPPORTED_1000baseT_Full); ++ return err; ++} ++ ++static int crisv32_eth_set_settings(struct net_device *dev, ++ struct ethtool_cmd *ecmd) ++{ ++ if (ecmd->autoneg == AUTONEG_ENABLE) { ++ crisv32_eth_set_duplex(dev, autoneg); ++ crisv32_eth_set_speed(dev, 0); ++ } else { ++ crisv32_eth_set_duplex(dev, ecmd->duplex); ++ crisv32_eth_set_speed(dev, ecmd->speed); ++ } ++ ++ return 0; ++} ++ ++static void crisv32_eth_get_drvinfo(struct net_device *dev, ++ struct ethtool_drvinfo *info) ++{ ++#ifdef CONFIG_ETRAXFS ++ strncpy(info->driver, "ETRAX FS", sizeof(info->driver) - 1); ++#else ++ strncpy(info->driver, "ARTPEC-3", sizeof(info->driver) - 1); ++#endif ++ strncpy(info->version, "$Revision: 1.197 $", sizeof(info->version) - 1); ++ strncpy(info->fw_version, "N/A", sizeof(info->fw_version) - 1); ++ strncpy(info->bus_info, "N/A", sizeof(info->bus_info) - 1); ++} ++ ++static int crisv32_eth_get_ethtool_sset_count(struct net_device *dev, ++ int stringset) ++{ ++ if (stringset != ETH_SS_STATS) ++ return -EINVAL; ++ ++ return ARRAY_SIZE(ethtool_stats_keys); ++} ++ ++static void crisv32_eth_get_ethtool_stats(struct net_device *dev, ++ struct ethtool_stats *stats, ++ u64 *data) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data[0] = np->tx_dma_restarts; ++ data[1] = np->tx_mac_resets; ++ data[2] = np->rx_dma_restarts; ++ data[3] = np->rx_dma_timeouts; ++ data[4] = np->rx_restarts_dropped; ++} ++ ++static void crisv32_eth_get_strings(struct net_device *dev, ++ u32 stringset, u8 *data) ++{ ++ switch (stringset) { ++ case ETH_SS_STATS: ++ memcpy(data, ðtool_stats_keys, ++ sizeof(ethtool_stats_keys)); ++ break; ++ default: ++ WARN_ON(1); ++ break; ++ } ++} ++ ++static int crisv32_eth_nway_reset(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ if (np->current_duplex == autoneg && np->current_speed_selection == 0) ++ crisv32_eth_negotiate(dev); ++ return 0; ++} ++/* The FS/A3 ethernet block has 23 32-bit config registers. */ ++/* plus 2 dma_descr_context */ ++/* plus 2 sets of ring pointers (active, prev, last) */ ++/* plus 2 sets of DMA registers 40*4 bytes = 0xA0 */ ++#define ETRAX_ETH_REGDUMP_LEN (23 * 4 + 2 * sizeof (dma_descr_context) + 2*3*4 + 2*0xA0) ++static int crisv32_eth_get_regs_len(struct net_device *dev) ++{ ++ return ETRAX_ETH_REGDUMP_LEN; ++} ++ ++static void crisv32_eth_get_regs(struct net_device *dev, ++ struct ethtool_regs *regs, void *_p) ++{ ++ u32 *p = _p; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int i; ++ ++ /* Let's call this major version 0, minor version 1 with some ++ * undecided field separation in the version data. Previously ++ * only the eth regs were dumped (version=0: maj 0, min 0).*/ ++ regs->version = 1; ++ memset(p, 0, ETRAX_ETH_REGDUMP_LEN); ++ ++#define GET_REG32_LOOP(base, len) \ ++ do { \ ++ for (i = 0; i < len; i += 4) \ ++ *(p)++ = REG_READ(u32, (base) + i); \ ++ } while (0) ++ ++ GET_REG32_LOOP(np->eth_inst, 0x30); ++ /* Do not dump registers with read side effects. */ ++ GET_REG32_LOOP(np->eth_inst + 0x34, 1); ++ GET_REG32_LOOP(np->eth_inst + 0x3c, 1); ++ GET_REG32_LOOP(np->eth_inst + 0x44, 0x5c - 0x44); ++ ++ ++ memcpy(p, &np->ctxt_out, sizeof (dma_descr_context)); ++ p += sizeof (dma_descr_context)/4; ++ *(p++) = (u32) np->active_tx_desc; ++ *(p++) = (u32) np->prev_tx_desc; ++ *(p++) = (u32) np->catch_tx_desc; ++ ++ GET_REG32_LOOP(np->dma_out_inst, 0xa0); ++ ++ memcpy(p, &np->ctxt_in, sizeof (dma_descr_context)); ++ p += sizeof (dma_descr_context)/4; ++ *(p++) = (u32)np->active_rx_desc; ++ *(p++) = (u32)np->prev_rx_desc; ++ *(p++) = (u32)np->last_rx_desc; ++ ++ GET_REG32_LOOP(np->dma_in_inst, 0xa0); ++#undef GET_REG32_LOOP ++} ++ ++static struct ethtool_ops crisv32_ethtool_ops = { ++ .get_settings = crisv32_eth_get_settings, ++ .set_settings = crisv32_eth_set_settings, ++ .get_drvinfo = crisv32_eth_get_drvinfo, ++ .get_regs_len = crisv32_eth_get_regs_len, ++ .get_regs = crisv32_eth_get_regs, ++ .nway_reset = crisv32_eth_nway_reset, ++ .get_link = ethtool_op_get_link, ++ .get_strings = crisv32_eth_get_strings, ++ .get_ethtool_stats = crisv32_eth_get_ethtool_stats, ++ .get_sset_count = crisv32_eth_get_ethtool_sset_count ++}; ++ ++/* Is this function really needed? Use ethtool instead? */ ++static int crisv32_eth_set_config(struct net_device *dev, struct ifmap *map) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ spin_lock(&np->lock); /* Preempt protection */ ++ ++ switch (map->port) { ++ case IF_PORT_UNKNOWN: ++ /* Use autoneg */ ++ crisv32_eth_set_speed(dev, 0); ++ crisv32_eth_set_duplex(dev, autoneg); ++ break; ++ case IF_PORT_10BASET: ++ crisv32_eth_set_speed(dev, 10); ++ crisv32_eth_set_duplex(dev, autoneg); ++ break; ++ case IF_PORT_100BASET: ++ case IF_PORT_100BASETX: ++ crisv32_eth_set_speed(dev, 100); ++ crisv32_eth_set_duplex(dev, autoneg); ++ break; ++ case IF_PORT_100BASEFX: ++ case IF_PORT_10BASE2: ++ case IF_PORT_AUI: ++ spin_unlock(&np->lock); ++ return -EOPNOTSUPP; ++ break; ++ default: ++ printk(KERN_ERR "%s: Invalid media selected", ++ dev->name); ++ spin_unlock(&np->lock); ++ return -EINVAL; ++ } ++ spin_unlock(&np->lock); ++ return 0; ++} ++ ++static void crisv32_eth_negotiate(struct net_device *dev) ++{ ++ unsigned short data; ++ unsigned short ctrl1000; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_ADVERTISE); ++ ctrl1000 = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MII_CTRL1000); ++ ++ /* Make all capabilities available */ ++ data |= ADVERTISE_10HALF | ADVERTISE_10FULL | ++ ADVERTISE_100HALF | ADVERTISE_100FULL; ++ ctrl1000 |= ADVERTISE_1000HALF | ADVERTISE_1000FULL; ++ ++ /* Remove the speed capabilities that we that do not want */ ++ switch (np->current_speed_selection) { ++ case 10 : ++ data &= ~(ADVERTISE_100HALF | ADVERTISE_100FULL); ++ ctrl1000 &= ~(ADVERTISE_1000HALF | ADVERTISE_1000FULL); ++ break; ++ case 100 : ++ data &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL); ++ ctrl1000 &= ~(ADVERTISE_1000HALF | ADVERTISE_1000FULL); ++ break; ++ case 1000 : ++ data &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL | ++ ADVERTISE_100HALF | ADVERTISE_100FULL); ++ break; ++ } ++ ++ /* Remove the duplex capabilites that we do not want */ ++ if (np->current_duplex == full) { ++ data &= ~(ADVERTISE_10HALF | ADVERTISE_100HALF); ++ ctrl1000 &= ~(ADVERTISE_1000HALF); ++ } ++ else if (np->current_duplex == half) { ++ data &= ~(ADVERTISE_10FULL | ADVERTISE_100FULL); ++ ctrl1000 &= ~(ADVERTISE_1000FULL); ++ } ++ ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, MII_ADVERTISE, data); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, ++ MII_CTRL1000, ctrl1000); ++#endif ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMCR); ++ if (np->autoneg_normal) { ++ /* Renegotiate with link partner */ ++ data |= BMCR_ANENABLE | BMCR_ANRESTART; ++ } else { ++ /* Don't negitiate speed or duplex */ ++ data &= ~(BMCR_ANENABLE | BMCR_ANRESTART); ++ ++ /* Set speed and duplex static */ ++ if (np->current_speed_selection == 10) { ++ data &= ~(BMCR_SPEED100 | BMCR_SPEED1000); ++ } ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ else if (np->current_speed_selection == 1000) { ++ data &= ~BMCR_SPEED100; ++ data |= BMCR_SPEED1000; ++ } ++#endif ++ else { ++ data |= BMCR_SPEED100; ++ data &= ~BMCR_SPEED1000; ++ } ++ ++ if (np->current_duplex != full) { ++ data &= ~BMCR_FULLDPLX; ++ } else { ++ data |= BMCR_FULLDPLX; ++ } ++ } ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, MII_BMCR, data); ++} ++ ++static void crisv32_eth_check_speed(unsigned long idev) ++{ ++#ifndef CONFIG_ETRAX_NO_PHY ++ static int led_initiated = 0; ++ struct net_device *dev = (struct net_device *) idev; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ unsigned long data; ++ int old_speed; ++ unsigned long flags; ++ ++ BUG_ON(!np); ++ BUG_ON(!np->transceiver); ++ ++ spin_lock(&np->transceiver_lock); ++ ++ old_speed = np->current_speed; ++ ++ /* Do a fake read. This is needed for DM9161, otherwise the link will ++ * go up and down all the time. ++ */ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMSR); ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMSR); ++ ++ if (!(data & BMSR_LSTATUS)) ++ np->current_speed = 0; ++ else ++ np->transceiver->check_speed(dev); ++ ++ spin_lock_irqsave(&np->leds->led_lock, flags); ++ if ((old_speed != np->current_speed) || !led_initiated) { ++ led_initiated = 1; ++ np->leds->clear_led_timer.data = (unsigned long) dev; ++ if (np->current_speed) { ++ if (!np->link) ++ netif_carrier_on(dev); ++ crisv32_set_network_leds(CRIS_LED_LINK, dev); ++ np->link = 1; ++ } else { ++ if (np->link) ++ netif_carrier_off(dev); ++ crisv32_set_network_leds(CRIS_LED_NOLINK, dev); ++ np->link = 0; ++ } ++ } ++ spin_unlock_irqrestore(&np->leds->led_lock, flags); ++ ++ /* Reinitialize the timer. */ ++ np->speed_timer.expires = jiffies + NET_LINK_UP_CHECK_INTERVAL; ++ add_timer(&np->speed_timer); ++ ++ spin_unlock(&np->transceiver_lock); ++#endif ++} ++ ++static void crisv32_eth_set_speed(struct net_device *dev, unsigned long speed) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ spin_lock(&np->transceiver_lock); ++ if (np->current_speed_selection != speed) { ++ np->current_speed_selection = speed; ++ crisv32_eth_negotiate(dev); ++ } ++ spin_unlock(&np->transceiver_lock); ++} ++ ++static void crisv32_eth_check_duplex(unsigned long idev) ++{ ++#ifndef CONFIG_ETRAX_NO_PHY ++ struct net_device *dev = (struct net_device *) idev; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ reg_eth_rw_rec_ctrl rec_ctrl; ++ int old_duplex = np->full_duplex; ++ ++ np->transceiver->check_duplex(dev); ++ ++ if (old_duplex != np->full_duplex) { ++ /* Duplex changed. */ ++ rec_ctrl = (reg_eth_rw_rec_ctrl) REG_RD(eth, np->eth_inst, ++ rw_rec_ctrl); ++ rec_ctrl.duplex = np->full_duplex; ++ REG_WR(eth, np->eth_inst, rw_rec_ctrl, rec_ctrl); ++ } ++ ++ /* Reinitialize the timer. */ ++ np->duplex_timer.expires = jiffies + NET_DUPLEX_CHECK_INTERVAL; ++ add_timer(&np->duplex_timer); ++#endif ++} ++ ++static void ++crisv32_eth_set_duplex(struct net_device *dev, enum duplex new_duplex) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ spin_lock(&np->transceiver_lock); ++ if (np->current_duplex != new_duplex) { ++ np->current_duplex = new_duplex; ++ crisv32_eth_negotiate(dev); ++ } ++ spin_unlock(&np->transceiver_lock); ++} ++ ++static int crisv32_eth_probe_transceiver(struct net_device *dev) ++{ ++#ifndef CONFIG_ETRAX_NO_PHY ++ unsigned int phyid_high; ++ unsigned int phyid_low; ++ unsigned int oui; ++ struct transceiver_ops *ops = NULL; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ /* Probe MDIO physical address. */ ++ for (np->mii_if.phy_id = 0; ++ np->mii_if.phy_id <= 31; np->mii_if.phy_id++) { ++ if (crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMSR) ++ != 0xffff) ++ break; ++ } ++ ++ if (np->mii_if.phy_id == 32) ++ return -ENODEV; ++ ++ /* Get manufacturer. */ ++ phyid_high = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MII_PHYSID1); ++ phyid_low = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MII_PHYSID2); ++ ++ oui = (phyid_high << 6) | (phyid_low >> 10); ++ ++ for (ops = &transceivers[0]; ops->oui; ops++) { ++ if (ops->oui == oui) ++ break; ++ } ++ ++ np->transceiver = ops; ++ ++ if (oui == DM9161_OUI) { ++ /* Do not bypass the scrambler/descrambler, this is needed ++ * to make 10Mbit work. ++ */ ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, ++ MII_DM9161_SCR,MII_DM9161_SCR_INIT); ++ /* Clear 10BTCSR to default */ ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, ++ MII_DM9161_10BTCSR, ++ MII_DM9161_10BTCSR_INIT); ++ } ++ return 0; ++#else ++ return -ENODEV; ++#endif ++} ++ ++#ifndef CONFIG_ETRAX_NO_PHY ++static void generic_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_ADVERTISE); ++ if ((data & ADVERTISE_100FULL) || ++ (data & ADVERTISE_100HALF)) ++ np->current_speed = 100; ++ else ++ np->current_speed = 10; ++} ++ ++static void generic_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_ADVERTISE); ++ if ((data & ADVERTISE_10FULL) || ++ (data & ADVERTISE_100FULL)) ++ np->full_duplex = 1; ++ else ++ np->full_duplex = 0; ++} ++ ++static void broadcom_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_AUX_CTRL_STATUS_REG); ++ np->current_speed = (data & MDIO_BC_SPEED ? 100 : 10); ++} ++ ++static void broadcom_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_AUX_CTRL_STATUS_REG); ++ np->full_duplex = (data & MDIO_BC_FULL_DUPLEX_IND) ? 1 : 0; ++} ++ ++static void tdk_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_TDK_DIAGNOSTIC_REG); ++ np->current_speed = (data & MDIO_TDK_DIAGNOSTIC_RATE ? 100 : 10); ++} ++ ++static void tdk_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_TDK_DIAGNOSTIC_REG); ++ np->full_duplex = (data & MDIO_TDK_DIAGNOSTIC_DPLX) ? 1 : 0; ++ ++} ++ ++static void intel_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_INT_STATUS_REG_2); ++ np->current_speed = (data & MDIO_INT_SPEED ? 100 : 10); ++} ++ ++static void intel_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_INT_STATUS_REG_2); ++ np->full_duplex = (data & MDIO_INT_FULL_DUPLEX_IND) ? 1 : 0; ++} ++ ++static void national_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_NAT_LINK_AN_REG); ++ if (data & MDIO_NAT_1000) ++ np->current_speed = 1000; ++ else if (data & MDIO_NAT_100) ++ np->current_speed = 100; ++ else ++ np->current_speed = 10; ++} ++ ++static void national_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_NAT_LINK_AN_REG); ++ if (data & MDIO_NAT_FULL_DUPLEX_IND) ++ np->full_duplex = 1; ++ else ++ np->full_duplex = 0; ++} ++ ++static void vitesse_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_VIT_AUX_STAT); ++ if ((data & 0x18) == MDIO_VIT_1000) ++ np->current_speed = 1000; ++ else if ((data & 0x18) == MDIO_VIT_100) ++ np->current_speed = 100; ++ else ++ np->current_speed = 10; ++} ++ ++static void vitesse_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MDIO_VIT_AUX_STAT); ++ if (data & 0x20) ++ np->full_duplex = 1; ++ else ++ np->full_duplex = 0; ++} ++ ++static void davicom_check_speed(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMCR); ++ np->current_speed = (data & BMCR_SPEED100) ? 100 : 10; ++} ++ ++static void davicom_check_duplex(struct net_device *dev) ++{ ++ unsigned long data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMCR); ++ np->full_duplex = (data & BMCR_FULLDPLX) ? 1 : 0; ++} ++#endif ++ ++#if 0 ++static void crisv32_eth_reset_tranceiver(struct net_device *dev) ++{ ++ int i; ++ unsigned short cmd; ++ unsigned short data; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, MII_BMCR); ++ ++ cmd = (MDIO_START << 14) ++ | (MDIO_WRITE << 12) ++ | (np->mii_if.phy_id << 7) ++ | (MII_BMCR << 2); ++ ++ crisv32_eth_send_mdio_cmd(dev, cmd, 1); ++ ++ data |= 0x8000; ++ ++ /* Magic value is number of bits. */ ++ for (i = 15; i >= 0; i--) ++ crisv32_eth_send_mdio_bit(dev, GET_BIT(i, data)); ++} ++#endif ++ ++static int ++crisv32_eth_get_mdio_reg(struct net_device *dev, int phyid, int reg_num) ++{ ++ int i; ++ unsigned short cmd; /* Data to be sent on MDIO port. */ ++ unsigned short data; /* Data read from MDIO. */ ++ ++#ifdef CONFIG_ETRAX_NO_PHY ++ return 0; ++#endif ++ ++ /* Start of frame, OP Code, Physical Address, Register Address. */ ++ cmd = (MDIO_START << 14) ++ | (MDIO_READ << 12) ++ | (phyid << 7) ++ | (reg_num << 2); ++ ++ crisv32_eth_send_mdio_cmd(dev, cmd, 0); ++ ++ data = 0; ++ ++ /* Receive data. Magic value is number of bits. */ ++ for (i = 15; i >= 0; i--) ++ data |= (crisv32_eth_receive_mdio_bit(dev) << i); ++ ++ return data; ++} ++ ++static void ++crisv32_eth_set_mdio_reg(struct net_device *dev, int phyid, int reg, int value) ++{ ++ int bitCounter; ++ unsigned short cmd; ++ ++#ifdef CONFIG_ETRAX_NO_PHY ++ return; ++#endif ++ cmd = (MDIO_START << 14) ++ | (MDIO_WRITE << 12) ++ | (phyid << 7) ++ | (reg << 2); ++ ++ crisv32_eth_send_mdio_cmd(dev, cmd, 1); ++ ++ /* Data... */ ++ for (bitCounter=15; bitCounter>=0 ; bitCounter--) { ++ crisv32_eth_send_mdio_bit(dev, GET_BIT(bitCounter, value)); ++ } ++} ++ ++static void ++crisv32_eth_send_mdio_cmd(struct net_device *dev, unsigned short cmd, ++ int write_cmd) ++{ ++ int i; ++ unsigned char data = 0x2; ++ ++ /* Preamble. Magic value is number of bits. */ ++ for (i = 31; i >= 0; i--) ++ crisv32_eth_send_mdio_bit(dev, GET_BIT(i, MDIO_PREAMBLE)); ++ ++ for (i = 15; i >= 2; i--) ++ crisv32_eth_send_mdio_bit(dev, GET_BIT(i, cmd)); ++ ++ /* Turnaround. */ ++ for (i = 1; i >= 0; i--) ++ if (write_cmd) ++ crisv32_eth_send_mdio_bit(dev, GET_BIT(i, data)); ++ else ++ crisv32_eth_receive_mdio_bit(dev); ++} ++ ++static void crisv32_eth_send_mdio_bit(struct net_device *dev, unsigned char bit) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ reg_eth_rw_mgm_ctrl mgm_ctrl = { ++ .mdoe = regk_eth_yes, ++ .mdio = bit & 1 ++ }; ++ ++ REG_WR(eth, np->eth_inst, rw_mgm_ctrl, mgm_ctrl); ++ ++ udelay(1); ++ ++ mgm_ctrl.mdc = 1; ++ REG_WR(eth, np->eth_inst, rw_mgm_ctrl, mgm_ctrl); ++ ++ udelay(1); ++} ++ ++static unsigned char crisv32_eth_receive_mdio_bit(struct net_device *dev) ++{ ++ reg_eth_r_stat stat; ++ reg_eth_rw_mgm_ctrl mgm_ctrl = {0}; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ ++ REG_WR(eth, np->eth_inst, rw_mgm_ctrl, mgm_ctrl); ++ stat = REG_RD(eth, np->eth_inst, r_stat); ++ ++ udelay(1); ++ ++ mgm_ctrl.mdc = 1; ++ REG_WR(eth, np->eth_inst, rw_mgm_ctrl, mgm_ctrl); ++ ++ udelay(1); ++ return stat.mdio; ++} ++ ++static void crisv32_clear_network_leds(unsigned long priv) ++{ ++ struct net_device *dev = (struct net_device *)priv; ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ unsigned long flags; ++ ++ spin_lock_irqsave(&np->leds->led_lock, flags); ++ if (np->leds->led_active && time_after(jiffies, ++ np->leds->led_next_time)) { ++ crisv32_set_network_leds(CRIS_LED_NOACTIVITY, dev); ++ ++ /* Set the earliest time we may set the LED */ ++ np->leds->led_next_time = jiffies + NET_FLASH_PAUSE; ++ np->leds->led_active = 0; ++ } ++ spin_unlock_irqrestore(&np->leds->led_lock, flags); ++} ++ ++static void crisv32_set_network_leds(int active, struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ int light_leds = 0; ++ ++ if (np->leds->ledgrp == CRIS_LED_GRP_NONE) ++ return; ++ ++ if (!np->use_leds) ++ return; ++ ++ if (active == CRIS_LED_NOLINK) { ++ if (dev == crisv32_dev[0]) ++ np->leds->ifisup[0] = 0; ++ else ++ np->leds->ifisup[1] = 0; ++ } ++ else if (active == CRIS_LED_LINK) { ++ if (dev == crisv32_dev[0]) ++ np->leds->ifisup[0] = 1; ++ else ++ np->leds->ifisup[1] = 1; ++#if defined(CONFIG_ETRAX_NETWORK_LED_ON_WHEN_LINK) ++ light_leds = 1; ++ } else { ++ light_leds = (active == CRIS_LED_NOACTIVITY); ++#elif defined(CONFIG_ETRAX_NETWORK_LED_ON_WHEN_ACTIVITY) ++ light_leds = 0; ++ } else { ++ light_leds = (active == CRIS_LED_ACTIVITY); ++#else ++#error "Define either CONFIG_ETRAX_NETWORK_LED_ON_WHEN_LINK or CONFIG_ETRAX_NETWORK_LED_ON_WHEN_ACTIVITY" ++#endif ++ } ++} ++ ++#ifdef CONFIG_NET_POLL_CONTROLLER ++static void crisv32_netpoll(struct net_device *netdev) ++{ ++ crisv32rx_eth_interrupt(DMA0_INTR_VECT, netdev); ++} ++#endif ++ ++#ifdef CONFIG_CPU_FREQ ++static int crisv32_ethernet_freq_notifier(struct notifier_block *nb, ++ unsigned long val, void *data) ++{ ++ struct cpufreq_freqs *freqs = data; ++ int i; ++ if (val != CPUFREQ_POSTCHANGE) ++ return 0; ++ ++ for (i = 0; i < 2; i++) { ++ struct net_device *dev = crisv32_dev[i]; ++ unsigned short data; ++ if (dev == NULL) ++ continue; ++ ++ data = crisv32_eth_get_mdio_reg(dev, np->mii_if.phy_id, ++ MII_BMCR); ++ if (freqs->new == 200000) ++ data &= ~BMCR_PDOWN; ++ else ++ data |= BMCR_PDOWN; ++ crisv32_eth_set_mdio_reg(dev, np->mii_if.phy_id, ++ MII_BMCR, data); ++ } ++ return 0; ++} ++#endif ++ ++#if 0 ++/* ++ * Must be called with the np->lock held. ++ */ ++static void crisv32_ethernet_bug(struct net_device *dev) ++{ ++ struct crisv32_ethernet_local *np = netdev_priv(dev); ++ dma_descr_data *dma_pos; ++ dma_descr_data *in_dma_pos; ++ reg_dma_rw_stat stat = {0}; ++ reg_dma_rw_stat in_stat = {0}; ++ int i; ++ ++ /* Get the current output dma position. */ ++ stat = REG_RD(dma, np->dma_out_inst, rw_stat); ++ ++ dma_pos = phys_to_virt(REG_RD_INT(dma, np->dma_out_inst, rw_data)); ++ in_dma_pos = phys_to_virt(REG_RD_INT(dma, np->dma_in_inst, rw_data)); ++ in_stat = REG_RD(dma, np->dma_in_inst, rw_stat); ++ ++ printk("%s:\n" ++ "stat.list_state=%x\n" ++ "stat.mode=%x\n" ++ "stat.stream_cmd_src=%x\n" ++ "dma_pos=%x\n" ++ "tx catch=%x active=%x\n" ++ "packets=%d queue=%d sender_started=%d\n" ++ "intr_vect.r_vect=%x\n" ++ "dma.r_masked_intr=%x dma.rw_ack_intr=%x " ++ "dma.r_intr=%x dma.rw_intr_masked=%x\n" ++ "eth.r_stat=%x\n", ++ __func__, ++ stat.list_state, stat.mode, stat.stream_cmd_src, ++ (unsigned int)dma_pos, ++ (unsigned int)&np->catch_tx_desc->descr, ++ (unsigned int)&np->active_tx_desc->descr, ++ np->txpackets, ++ netif_queue_stopped(dev), np->sender_started, ++ REG_RD_INT(intr_vect, regi_irq, r_vect), ++ REG_RD_INT(dma, np->dma_out_inst, r_masked_intr), ++ REG_RD_INT(dma, np->dma_out_inst, rw_ack_intr), ++ REG_RD_INT(dma, np->dma_out_inst, r_intr), ++ REG_RD_INT(dma, np->dma_out_inst, rw_intr_mask), ++ REG_RD_INT(eth, np->eth_inst, r_stat)); ++ ++ printk("in_stat.list_state=%x\n" ++ "in_stat.mode=%x\n" ++ "in_stat.stream_cmd_src=%x\n" ++ "in_dma_pos=%x\n" ++ "rx last=%x prev=%x active=%x\n", ++ in_stat.list_state, in_stat.mode, in_stat.stream_cmd_src, ++ (unsigned int)in_dma_pos, ++ (unsigned int)&np->last_rx_desc->descr, ++ (unsigned int)&np->prev_rx_desc->descr, ++ (unsigned int)&np->active_rx_desc->descr); ++ ++#if 0 ++ printk("rx-descriptors:\n"); ++ for (i = 0; i < NBR_RX_DESC; i++) { ++ printk("rxdesc[%d]=0x%x\n", i, (unsigned int) ++ virt_to_phys(&np->dma_rx_descr_list[i].descr)); ++ printk("rxdesc[%d].skb=0x%x\n", i, ++ (unsigned int)np->dma_rx_descr_list[i].skb); ++ printk("rxdesc[%d].buf=0x%x\n", i, ++ (unsigned int)np->dma_rx_descr_list[i].descr.buf); ++ printk("rxdesc[%d].after=0x%x\n", i, ++ (unsigned int)np->dma_rx_descr_list[i].descr.after); ++ printk("rxdesc[%d].intr=%x\n", i, ++ np->dma_rx_descr_list[i].descr.intr); ++ printk("rxdesc[%d].eol=%x\n", i, ++ np->dma_rx_descr_list[i].descr.eol); ++ printk("rxdesc[%d].out_eop=%x\n", i, ++ np->dma_rx_descr_list[i].descr.out_eop); ++ printk("rxdesc[%d].in_eop=%x\n", i, ++ np->dma_rx_descr_list[i].descr.in_eop); ++ printk("rxdesc[%d].wait=%x\n", i, ++ np->dma_rx_descr_list[i].descr.wait); ++ } ++#endif ++ ++#if 1 ++ printk("tx-descriptors:\n"); ++ for (i = 0; i < NBR_TX_DESC; i++) { ++ printk("txdesc[%d]=0x%x\n", i, (unsigned int) ++ virt_to_phys(&np->dma_tx_descr_list[i].descr)); ++ printk("txdesc[%d].skb=0x%x\n", i, ++ (unsigned int)np->dma_tx_descr_list[i].skb); ++ printk("txdesc[%d].buf=0x%x\n", i, ++ (unsigned int)np->dma_tx_descr_list[i].descr.buf); ++ printk("txdesc[%d].after=0x%x\n", i, ++ (unsigned int)np->dma_tx_descr_list[i].descr.after); ++ printk("txdesc[%d].intr=%x\n", i, ++ np->dma_tx_descr_list[i].descr.intr); ++ printk("txdesc[%d].eol=%x\n", i, ++ np->dma_tx_descr_list[i].descr.eol); ++ printk("txdesc[%d].out_eop=%x\n", i, ++ np->dma_tx_descr_list[i].descr.out_eop); ++ printk("txdesc[%d].in_eop=%x\n", i, ++ np->dma_tx_descr_list[i].descr.in_eop); ++ printk("txdesc[%d].wait=%x\n", i, ++ np->dma_tx_descr_list[i].descr.wait); ++ } ++#endif ++} ++#endif ++ ++static int __init crisv32_boot_setup(char *str) ++{ ++ struct sockaddr sa = {0}; ++ int i; ++ ++ /* Parse the colon separated Ethernet station address */ ++ for (i = 0; i < ETH_ALEN; i++) { ++ unsigned int tmp; ++ if (sscanf(str + 3*i, "%2x", &tmp) != 1) { ++ printk(KERN_WARNING "Malformed station address"); ++ return 0; ++ } ++ sa.sa_data[i] = (char)tmp; ++ } ++ ++ default_mac_iface0 = sa; ++ return 1; ++} ++ ++__setup("crisv32_eth=", crisv32_boot_setup); ++ ++module_init(crisv32_ethernet_init); +diff -Nur linux-4.7.3.orig/drivers/net/cris/eth_v32.h linux-4.7.3/drivers/net/cris/eth_v32.h +--- linux-4.7.3.orig/drivers/net/cris/eth_v32.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.7.3/drivers/net/cris/eth_v32.h 2016-09-13 01:47:09.527718381 +0200 +@@ -0,0 +1,291 @@ ++/* ++ * Definitions for ETRAX FS ethernet driver. ++ * ++ * Copyright (C) 2003, 2004, 2005 Axis Communications. ++ */ ++ ++#ifndef _ETRAX_ETHERNET_H_ ++#define _ETRAX_ETHERNET_H_ ++ ++#include ++ ++#define MAX_MEDIA_DATA_SIZE 1522 /* Max packet size. */ ++ ++#define NBR_RX_DESC 128 /* Number of RX descriptors. */ ++#define NBR_TX_DESC 16 /* Number of TX descriptors. */ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++#define NBR_INTMEM_RX_DESC 16 /* Number of RX descriptors in int. mem. ++ * when running in gigabit mode. ++ * Should be less then NBR_RX_DESC ++ */ ++#define NBR_INTMEM_TX_BUF 4 /* Number of TX buffers in int. mem ++ * when running in gigabit mode. ++ * Should be less than NBR_TX_DESC ++ */ ++#endif ++ ++/* Large packets are sent directly to upper layers while small packets ++ * are copied (to reduce memory waste). The following constant ++ * decides the breakpoint. ++ */ ++#define RX_COPYBREAK (256) ++ ++#define ETHER_HEAD_LEN (14) ++ ++/* ++ * MDIO constants. ++ */ ++#define MDIO_START 0x1 ++#define MDIO_READ 0x2 ++#define MDIO_WRITE 0x1 ++#define MDIO_PREAMBLE 0xfffffffful ++ ++/* Broadcom specific */ ++#define MDIO_AUX_CTRL_STATUS_REG 0x18 ++#define MDIO_BC_FULL_DUPLEX_IND 0x1 ++#define MDIO_BC_SPEED 0x2 ++ ++/* TDK specific */ ++#define MDIO_TDK_DIAGNOSTIC_REG 18 ++#define MDIO_TDK_DIAGNOSTIC_RATE 0x400 ++#define MDIO_TDK_DIAGNOSTIC_DPLX 0x800 ++ ++/*Intel LXT972A specific*/ ++#define MDIO_INT_STATUS_REG_2 0x0011 ++#define MDIO_INT_FULL_DUPLEX_IND ( 0x0001 << 9 ) ++#define MDIO_INT_SPEED ( 0x0001 << 14 ) ++ ++/*National Semiconductor DP83865 specific*/ ++#define MDIO_NAT_LINK_AN_REG 0x11 ++#define MDIO_NAT_1000 (0x0001 << 4) ++#define MDIO_NAT_100 (0x0001 << 3) ++#define MDIO_NAT_FULL_DUPLEX_IND (0x0001 << 1) ++ ++/* Vitesse VCS8641 specific */ ++#define MDIO_VIT_AUX_STAT 0x1c ++#define MDIO_VIT_1000 (0x2 << 3) ++#define MDIO_VIT_100 (0x1 << 3) ++#define MDIO_VIT_10 0 ++#define MDIO_VIT_FD (0x1 << 5) ++ ++/* Davicom DM9161 specific */ ++#define DM9161_OUI 0x606E ++#define MII_DM9161_SCR 0x10 ++#define MII_DM9161_SCR_INIT 0x0610 ++#define MII_DM9161_SCR_RMII 0x0100 ++#define MII_DM9161_10BTCSR 0x12 ++#define MII_DM9161_10BTCSR_INIT 0x7800 ++ ++/* Network flash constants */ ++#define NET_FLASH_TIME (HZ/50) /* 20 ms */ ++#define NET_FLASH_PAUSE (HZ/100) /* 10 ms */ ++#define NET_LINK_UP_CHECK_INTERVAL (2*HZ) /* 2 seconds. */ ++#define NET_DUPLEX_CHECK_INTERVAL (2*HZ) /* 2 seconds. */ ++ ++/* Duplex settings. */ ++enum duplex { ++ half, ++ full, ++ autoneg ++}; ++ ++/* Some transceivers requires special handling. */ ++struct transceiver_ops { ++ unsigned int oui; ++ void (*check_speed) (struct net_device * dev); ++ void (*check_duplex) (struct net_device * dev); ++}; ++ ++typedef struct crisv32_eth_descr { ++ dma_descr_data descr __attribute__ ((__aligned__(32))); ++ struct sk_buff *skb; ++ unsigned char *linearized_packet; ++} crisv32_eth_descr; ++ ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++struct tx_buffer_list { ++ struct tx_buffer_list *next; ++ unsigned char *buf; ++ char free; ++}; ++#endif ++ ++/* LED stuff */ ++#define CRIS_LED_GRP_0 0 ++#define CRIS_LED_GRP_1 1 ++#define CRIS_LED_GRP_NONE 2 ++ ++#define CRIS_LED_ACTIVITY 0 ++#define CRIS_LED_NOACTIVITY 1 ++#define CRIS_LED_LINK 2 ++#define CRIS_LED_NOLINK 3 ++ ++struct crisv32_eth_leds { ++ unsigned int ledgrp; ++ int led_active; ++ unsigned long led_next_time; ++ struct timer_list clear_led_timer; ++ spinlock_t led_lock; /* Protect LED state */ ++ int ifisup[2]; ++}; ++ ++/* Information that need to be kept for each device. */ ++struct crisv32_ethernet_local { ++ /* FIXME: These align attributes don't really help. If they are really ++ * needed alignment has to be enforced at runtime, these objects ++ * are dynamically allocated. */ ++ dma_descr_context ctxt_in __attribute__ ((__aligned__(32))); ++ dma_descr_context ctxt_out __attribute__ ((__aligned__(32))); ++ ++ crisv32_eth_descr dma_rx_descr_list[NBR_RX_DESC]; ++ crisv32_eth_descr dma_tx_descr_list[NBR_TX_DESC]; ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++ struct tx_buffer_list tx_intmem_buf_list[NBR_INTMEM_TX_BUF]; ++ struct tx_buffer_list *intmem_tx_buf_active; ++ struct tx_buffer_list *intmem_tx_buf_catch; ++ int gigabit_mode; ++#endif ++ /* Transmit data path. */ ++ int dma_out_inst; ++ int sender_started; ++ ++ /* TX-ring state. */ ++ crisv32_eth_descr *active_tx_desc; ++ crisv32_eth_descr *prev_tx_desc; ++ crisv32_eth_descr *catch_tx_desc; ++ int txpackets; ++ int retrans; ++ int do_tx_recovery; ++ struct timer_list transmit_timer; ++ ++ /* Receive data path. */ ++ struct napi_struct napi; ++ int dma_in_inst; ++ ++ /* RX-ring state. */ ++ crisv32_eth_descr *active_rx_desc; ++ crisv32_eth_descr *prev_rx_desc; ++ crisv32_eth_descr *last_rx_desc; ++ ++ unsigned long newbuf; ++ u8 new_rx_package; ++ u8 pending_overrun; ++ u8 overrun_set; ++ u8 link; ++ int napi_processing; ++ struct timer_list receive_timer; ++ struct work_struct receive_work; ++ reg_eth_rw_rec_ctrl saved_rec_ctrl; ++ int saved_ga_lo; ++ int saved_ga_hi; ++ int do_rx_recovery; ++ ++ /* Control paths. */ ++ spinlock_t lock; ++ struct net_device *dev; ++ int eth_inst; ++ ++ /* Toggle network LEDs usage at runtime */ ++ int use_leds; ++ struct crisv32_eth_leds *leds; ++ ++ /* PHY control. */ ++ int fixed_phy; ++ spinlock_t transceiver_lock; /* Protect transceiver state. */ ++ struct transceiver_ops *transceiver; ++ struct mii_if_info mii_if; ++ ++ /* Specifies if we should do autonegotiation or not. ++ * TODO: This ad-hoc hack should be removed. Ethtool already supports ++ * this kind of control. ++ */ ++ int autoneg_normal; ++ ++ struct timer_list duplex_timer; ++ int full_duplex; ++ enum duplex current_duplex; ++ ++ struct timer_list speed_timer; ++ int current_speed; /* Speed read from tranceiver */ ++ int current_speed_selection; /* Speed selected by user */ ++ ++ /* Statistics. */ ++ u64 tx_dma_restarts; ++ u64 tx_mac_resets; ++ u64 rx_dma_restarts; ++ u64 rx_dma_timeouts; ++ u64 rx_restarts_dropped; ++ ++ struct net_device_stats stats; ++}; ++ ++/* Function prototypes. */ ++static int crisv32_ethernet_init(void); ++static int crisv32_ethernet_device_init(struct net_device *dev); ++static int crisv32_eth_open(struct net_device *dev); ++static int crisv32_eth_close(struct net_device *dev); ++static int crisv32_eth_set_mac_address(struct net_device *dev, void *vpntr); ++static irqreturn_t crisv32rx_eth_interrupt(int irq, void *dev_id); ++static irqreturn_t crisv32tx_eth_interrupt(int irq, void *dev_id); ++static irqreturn_t crisv32nw_eth_interrupt(int irq, void *dev_id); ++static int crisv32_eth_send_packet(struct sk_buff *skb, struct net_device *dev); ++static void crisv32_eth_hw_send_packet(unsigned char *buf, int length, ++ void *priv); ++static void crisv32_eth_do_tx_recovery(struct net_device *dev); ++static void crisv32_eth_set_rx_mode(struct net_device *dev); ++static int crisv32_eth_ioctl(struct net_device *dev, struct ifreq *ifr, ++ int cmd); ++static int crisv32_eth_set_config(struct net_device *dev, struct ifmap *map); ++#ifdef CONFIG_CRIS_MACH_ARTPEC3 ++static void crisv32_eth_switch_intmem_usage(struct net_device *dev); ++#endif ++static void crisv32_eth_negotiate(struct net_device *dev); ++static void crisv32_eth_set_speed(struct net_device *dev, unsigned long speed); ++#ifndef CONFIG_ETRAX_NO_PHY ++static void crisv32_eth_check_duplex(unsigned long idev); ++static void crisv32_eth_check_speed(unsigned long idev); ++#endif ++ ++static void crisv32_eth_set_duplex(struct net_device *dev, enum duplex); ++static int crisv32_eth_probe_transceiver(struct net_device *dev); ++ ++static struct ethtool_ops crisv32_ethtool_ops; ++ ++#ifndef CONFIG_ETRAX_NO_PHY ++static void generic_check_speed(struct net_device *dev); ++static void generic_check_duplex(struct net_device *dev); ++static void broadcom_check_speed(struct net_device *dev); ++static void broadcom_check_duplex(struct net_device *dev); ++static void tdk_check_speed(struct net_device *dev); ++static void tdk_check_duplex(struct net_device *dev); ++static void intel_check_speed(struct net_device *dev); ++static void intel_check_duplex(struct net_device *dev); ++static void national_check_speed(struct net_device *dev); ++static void national_check_duplex(struct net_device *dev); ++static void vitesse_check_speed(struct net_device *dev); ++static void vitesse_check_duplex(struct net_device *dev); ++static void davicom_check_speed(struct net_device *dev); ++static void davicom_check_duplex(struct net_device *dev); ++#endif ++ ++#ifdef CONFIG_NET_POLL_CONTROLLER ++static void crisv32_netpoll(struct net_device *dev); ++#endif ++ ++static void crisv32_clear_network_leds(unsigned long dummy); ++static void crisv32_set_network_leds(int active, struct net_device *dev); ++ ++static int crisv32_eth_get_mdio_reg(struct net_device *dev, ++ int phyid, int reg_num); ++static void crisv32_eth_set_mdio_reg(struct net_device *dev, ++ int phyid, int reg_num, int val); ++static void crisv32_eth_send_mdio_cmd(struct net_device *dev, ++ unsigned short cmd, int write_cmd); ++static void crisv32_eth_send_mdio_bit(struct net_device *dev, ++ unsigned char bit); ++static unsigned char crisv32_eth_receive_mdio_bit(struct net_device *dev); ++ ++static struct net_device_stats *crisv32_get_stats(struct net_device *dev); ++static void crisv32_start_dma_out(struct crisv32_ethernet_local *np); ++ ++#endif /* _ETRAX_ETHERNET_H_ */ +diff -Nur linux-4.7.3.orig/drivers/net/cris/Makefile linux-4.7.3/drivers/net/cris/Makefile +--- linux-4.7.3.orig/drivers/net/cris/Makefile 2016-09-07 08:35:12.000000000 +0200 ++++ linux-4.7.3/drivers/net/cris/Makefile 2016-09-13 01:47:09.527718381 +0200 +@@ -1 +1,2 @@ + obj-$(CONFIG_ETRAX_ARCH_V10) += eth_v10.o ++obj-$(CONFIG_ETRAX_ARCH_V32) += eth_v32.o diff --git a/target/linux/patches/4.4.30/initramfs-nosizelimit.patch b/target/linux/patches/4.4.30/initramfs-nosizelimit.patch new file mode 100644 index 000000000..40d2f6bd8 --- /dev/null +++ b/target/linux/patches/4.4.30/initramfs-nosizelimit.patch @@ -0,0 +1,57 @@ +From 9a18df7a71bfa620b1278777d64783a359d7eb4e Mon Sep 17 00:00:00 2001 +From: Thorsten Glaser +Date: Sun, 4 May 2014 01:37:54 +0200 +Subject: [PATCH] mount tmpfs-as-rootfs (initramfs) with -o + nr_blocks=0,nr_inodes=0 + +I would have preferred to write this patch to be able to pass +rootflags=nr_blocks=0,nr_inodes=0 on the kernel command line, +and then hand these rootflags over to the initramfs (tmpfs) +mount in the same way the kernel hands them over to the block +device rootfs mount. But at least the Debian/m68k initrd also +parses $rootflags from the environment and adds it to the call +to the user-space mount for the eventual root device, which +would make the kernel command line rootflags option be used in +both places (tmpfs and e.g. ext4) which is guaranteed to error +out in at least one of them. + +This change is intended to aid people in a setup where the +initrd is the final root filesystem, i.e. not mounted over. +This is especially useful in automated tests running on qemu +for boards with constrained memory (e.g. 64 MiB on sh4). + +Considering that the initramfs is normally emptied out then +overmounted, this change is probably safe for setups where +initramfs just hosts early userspace, too, since the tmpfs +backing it is not accessible any more later on, AFAICT. + +Signed-off-by: Thorsten Glaser +--- + init/do_mounts.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/init/do_mounts.c b/init/do_mounts.c +index 82f2288..55a4cfe 100644 +--- a/init/do_mounts.c ++++ b/init/do_mounts.c +@@ -594,6 +594,7 @@ out: + } + + static bool is_tmpfs; ++static char tmpfs_rootflags[] = "nr_blocks=0,nr_inodes=0"; + static struct dentry *rootfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) + { +@@ -606,6 +607,9 @@ static struct dentry *rootfs_mount(struct file_system_type *fs_type, + if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs) + fill = shmem_fill_super; + ++ if (is_tmpfs) ++ data = tmpfs_rootflags; ++ + return mount_nodev(fs_type, flags, data, fill); + } + +-- +2.0.0.rc0 + diff --git a/target/linux/patches/4.4.30/ld-or1k.patch b/target/linux/patches/4.4.30/ld-or1k.patch new file mode 100644 index 000000000..264f9166f --- /dev/null +++ b/target/linux/patches/4.4.30/ld-or1k.patch @@ -0,0 +1,12 @@ +diff -Nur linux-4.4.5.orig/arch/openrisc/kernel/vmlinux.lds.S linux-4.4.5/arch/openrisc/kernel/vmlinux.lds.S +--- linux-4.4.5.orig/arch/openrisc/kernel/vmlinux.lds.S 2016-03-10 00:35:58.000000000 +0100 ++++ linux-4.4.5/arch/openrisc/kernel/vmlinux.lds.S 2016-03-16 09:21:07.933535532 +0100 +@@ -30,7 +30,7 @@ + #include + #include + +-OUTPUT_FORMAT("elf32-or32", "elf32-or32", "elf32-or32") ++OUTPUT_FORMAT("elf32-or1k", "elf32-or1k", "elf32-or1k") + jiffies = jiffies_64 + 4; + + SECTIONS diff --git a/target/linux/patches/4.4.30/macsonic.patch b/target/linux/patches/4.4.30/macsonic.patch new file mode 100644 index 000000000..75a6fcad2 --- /dev/null +++ b/target/linux/patches/4.4.30/macsonic.patch @@ -0,0 +1,11 @@ +diff -Nur linux-4.4.6.orig/drivers/net/ethernet/natsemi/Kconfig linux-4.4.6/drivers/net/ethernet/natsemi/Kconfig +--- linux-4.4.6.orig/drivers/net/ethernet/natsemi/Kconfig 2016-03-16 16:43:17.000000000 +0100 ++++ linux-4.4.6/drivers/net/ethernet/natsemi/Kconfig 2016-03-18 10:43:34.000000000 +0100 +@@ -18,6 +18,7 @@ + config MACSONIC + tristate "Macintosh SONIC based ethernet (onboard, NuBus, LC, CS)" + depends on MAC ++ select BITREVERSE + ---help--- + Support for NatSemi SONIC based Ethernet devices. This includes + the onboard Ethernet in many Quadras as well as some LC-PDS, diff --git a/target/linux/patches/4.4.30/mips-xz.patch b/target/linux/patches/4.4.30/mips-xz.patch new file mode 100644 index 000000000..5cfac6254 --- /dev/null +++ b/target/linux/patches/4.4.30/mips-xz.patch @@ -0,0 +1,12 @@ +diff -Nur linux-4.4.5.orig/arch/mips/boot/compressed/Makefile linux-4.4.5/arch/mips/boot/compressed/Makefile +--- linux-4.4.5.orig/arch/mips/boot/compressed/Makefile 2016-03-10 00:35:58.000000000 +0100 ++++ linux-4.4.5/arch/mips/boot/compressed/Makefile 2016-03-15 11:35:31.951795457 +0100 +@@ -41,7 +41,7 @@ + endif + + ifdef CONFIG_KERNEL_XZ +-vmlinuzobjs-y += $(obj)/../../lib/ashldi3.o ++vmlinuzobjs-y += $(obj)/../../lib/ashldi3.o $(obj)/../../lib/bswapsi.o + endif + + targets += vmlinux.bin diff --git a/target/linux/patches/4.4.30/patch-realtime b/target/linux/patches/4.4.30/patch-realtime new file mode 100644 index 000000000..9dd3be37b --- /dev/null +++ b/target/linux/patches/4.4.30/patch-realtime @@ -0,0 +1,30987 @@ +diff -Nur linux-4.4.28.orig/arch/arm/include/asm/switch_to.h linux-4.4.28/arch/arm/include/asm/switch_to.h +--- linux-4.4.28.orig/arch/arm/include/asm/switch_to.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/include/asm/switch_to.h 2016-11-01 21:26:56.728210258 +0100 +@@ -3,6 +3,13 @@ + + #include + ++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb +@@ -25,6 +32,7 @@ + #define switch_to(prev,next,last) \ + do { \ + __complete_pending_tlbi(); \ ++ switch_kmaps(prev, next); \ + last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ + } while (0) + +diff -Nur linux-4.4.28.orig/arch/arm/include/asm/thread_info.h linux-4.4.28/arch/arm/include/asm/thread_info.h +--- linux-4.4.28.orig/arch/arm/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/include/asm/thread_info.h 2016-11-01 21:26:56.748211548 +0100 +@@ -49,6 +49,7 @@ + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + __u32 cpu; /* cpu */ +@@ -142,7 +143,8 @@ + #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ + #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ + #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ ++#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ ++#define TIF_NEED_RESCHED_LAZY 7 + + #define TIF_NOHZ 12 /* in adaptive nohz mode */ + #define TIF_USING_IWMMXT 17 +@@ -152,6 +154,7 @@ + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -167,7 +170,8 @@ + * Change these and you break ASM code in entry-common.S + */ + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +- _TIF_NOTIFY_RESUME | _TIF_UPROBE) ++ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ ++ _TIF_NEED_RESCHED_LAZY) + + #endif /* __KERNEL__ */ + #endif /* __ASM_ARM_THREAD_INFO_H */ +diff -Nur linux-4.4.28.orig/arch/arm/Kconfig linux-4.4.28/arch/arm/Kconfig +--- linux-4.4.28.orig/arch/arm/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/Kconfig 2016-11-01 21:26:56.696208202 +0100 +@@ -33,7 +33,7 @@ + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 ++ select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !PREEMPT_RT_BASE + select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 + select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_TRACEHOOK +@@ -68,6 +68,7 @@ + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS +diff -Nur linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c linux-4.4.28/arch/arm/kernel/asm-offsets.c +--- linux-4.4.28.orig/arch/arm/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/asm-offsets.c 2016-11-01 21:26:56.760212322 +0100 +@@ -65,6 +65,7 @@ + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-armv.S linux-4.4.28/arch/arm/kernel/entry-armv.S +--- linux-4.4.28.orig/arch/arm/kernel/entry-armv.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/entry-armv.S 2016-11-01 21:26:56.764212578 +0100 +@@ -215,11 +215,18 @@ + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -234,8 +241,14 @@ + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again +- b 1b ++ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r0, #0 @ if preempt lazy count != 0 ++ beq 1b ++ ret r8 @ go again ++ + #endif + + __und_fault: +diff -Nur linux-4.4.28.orig/arch/arm/kernel/entry-common.S linux-4.4.28/arch/arm/kernel/entry-common.S +--- linux-4.4.28.orig/arch/arm/kernel/entry-common.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/entry-common.S 2016-11-01 21:26:56.764212578 +0100 +@@ -36,7 +36,9 @@ + UNWIND(.cantunwind ) + disable_irq_notrace @ disable interrupts + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne fast_work_pending ++ tst r1, #_TIF_SECCOMP + bne fast_work_pending + + /* perform architecture specific actions before user return */ +@@ -62,8 +64,11 @@ + str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 + disable_irq_notrace @ disable interrupts + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne do_slower_path ++ tst r1, #_TIF_SECCOMP + beq no_work_pending ++do_slower_path: + UNWIND(.fnend ) + ENDPROC(ret_fast_syscall) + +diff -Nur linux-4.4.28.orig/arch/arm/kernel/process.c linux-4.4.28/arch/arm/kernel/process.c +--- linux-4.4.28.orig/arch/arm/kernel/process.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/process.c 2016-11-01 21:26:56.772213095 +0100 +@@ -319,6 +319,30 @@ + } + + #ifdef CONFIG_MMU ++/* ++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not ++ * initialized by pgtable_page_ctor() then a coredump of the vector page will ++ * fail. ++ */ ++static int __init vectors_user_mapping_init_page(void) ++{ ++ struct page *page; ++ unsigned long addr = 0xffff0000; ++ pgd_t *pgd; ++ pud_t *pud; ++ pmd_t *pmd; ++ ++ pgd = pgd_offset_k(addr); ++ pud = pud_offset(pgd, addr); ++ pmd = pmd_offset(pud, addr); ++ page = pmd_page(*(pmd)); ++ ++ pgtable_page_ctor(page); ++ ++ return 0; ++} ++late_initcall(vectors_user_mapping_init_page); ++ + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the +diff -Nur linux-4.4.28.orig/arch/arm/kernel/signal.c linux-4.4.28/arch/arm/kernel/signal.c +--- linux-4.4.28.orig/arch/arm/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/signal.c 2016-11-01 21:26:56.772213095 +0100 +@@ -572,7 +572,8 @@ + */ + trace_hardirqs_off(); + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) +diff -Nur linux-4.4.28.orig/arch/arm/kernel/smp.c linux-4.4.28/arch/arm/kernel/smp.c +--- linux-4.4.28.orig/arch/arm/kernel/smp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/smp.c 2016-11-01 21:26:56.772213095 +0100 +@@ -230,8 +230,6 @@ + flush_cache_louis(); + local_flush_tlb_all(); + +- clear_tasks_mm_cpumask(cpu); +- + return 0; + } + +@@ -247,6 +245,9 @@ + pr_err("CPU%u: cpu didn't die\n", cpu); + return; + } ++ ++ clear_tasks_mm_cpumask(cpu); ++ + pr_notice("CPU%u: shutdown\n", cpu); + + /* +diff -Nur linux-4.4.28.orig/arch/arm/kernel/unwind.c linux-4.4.28/arch/arm/kernel/unwind.c +--- linux-4.4.28.orig/arch/arm/kernel/unwind.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kernel/unwind.c 2016-11-01 21:26:56.776213352 +0100 +@@ -93,7 +93,7 @@ + static const struct unwind_idx *__origin_unwind_idx; + extern const struct unwind_idx __stop_unwind_idx[]; + +-static DEFINE_SPINLOCK(unwind_lock); ++static DEFINE_RAW_SPINLOCK(unwind_lock); + static LIST_HEAD(unwind_tables); + + /* Convert a prel31 symbol to an absolute address */ +@@ -201,7 +201,7 @@ + /* module unwind tables */ + struct unwind_table *table; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_for_each_entry(table, &unwind_tables, list) { + if (addr >= table->begin_addr && + addr < table->end_addr) { +@@ -213,7 +213,7 @@ + break; + } + } +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); +@@ -529,9 +529,9 @@ + tab->begin_addr = text_addr; + tab->end_addr = text_addr + text_size; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_add_tail(&tab->list, &unwind_tables); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + return tab; + } +@@ -543,9 +543,9 @@ + if (!tab) + return; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_del(&tab->list); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + kfree(tab); + } +diff -Nur linux-4.4.28.orig/arch/arm/kvm/arm.c linux-4.4.28/arch/arm/kvm/arm.c +--- linux-4.4.28.orig/arch/arm/kvm/arm.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kvm/arm.c 2016-11-01 21:26:56.776213352 +0100 +@@ -496,18 +496,18 @@ + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { +- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); ++ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); + + vcpu->arch.pause = false; +- wake_up_interruptible(wq); ++ swake_up(wq); + } + } + + static void vcpu_sleep(struct kvm_vcpu *vcpu) + { +- wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); ++ struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); + +- wait_event_interruptible(*wq, ((!vcpu->arch.power_off) && ++ swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + (!vcpu->arch.pause))); + } + +@@ -566,7 +566,7 @@ + * involves poking the GIC, which must be done in a + * non-preemptible context. + */ +- preempt_disable(); ++ migrate_disable(); + kvm_timer_flush_hwstate(vcpu); + kvm_vgic_flush_hwstate(vcpu); + +@@ -585,7 +585,7 @@ + local_irq_enable(); + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); +- preempt_enable(); ++ migrate_enable(); + continue; + } + +@@ -639,7 +639,7 @@ + + kvm_vgic_sync_hwstate(vcpu); + +- preempt_enable(); ++ migrate_enable(); + + ret = handle_exit(vcpu, run, ret); + } +diff -Nur linux-4.4.28.orig/arch/arm/kvm/psci.c linux-4.4.28/arch/arm/kvm/psci.c +--- linux-4.4.28.orig/arch/arm/kvm/psci.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/kvm/psci.c 2016-11-01 21:26:56.780213616 +0100 +@@ -70,7 +70,7 @@ + { + struct kvm *kvm = source_vcpu->kvm; + struct kvm_vcpu *vcpu = NULL; +- wait_queue_head_t *wq; ++ struct swait_queue_head *wq; + unsigned long cpu_id; + unsigned long context_id; + phys_addr_t target_pc; +@@ -119,7 +119,7 @@ + smp_mb(); /* Make sure the above is visible */ + + wq = kvm_arch_vcpu_wq(vcpu); +- wake_up_interruptible(wq); ++ swake_up(wq); + + return PSCI_RET_SUCCESS; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c linux-4.4.28/arch/arm/mach-at91/at91rm9200.c +--- linux-4.4.28.orig/arch/arm/mach-at91/at91rm9200.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/at91rm9200.c 2016-11-01 21:26:56.784213869 +0100 +@@ -12,7 +12,6 @@ + #include + + #include +-#include + + #include "generic.h" + #include "soc.h" +@@ -33,7 +32,6 @@ + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); + +- arm_pm_idle = at91rm9200_idle; + at91rm9200_pm_init(); + } + +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c linux-4.4.28/arch/arm/mach-at91/at91sam9.c +--- linux-4.4.28.orig/arch/arm/mach-at91/at91sam9.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/at91sam9.c 2016-11-01 21:26:56.784213869 +0100 +@@ -62,8 +62,6 @@ + soc_dev = soc_device_to_device(soc); + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); +- +- arm_pm_idle = at91sam9_idle; + } + + static void __init at91sam9_dt_device_init(void) +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/generic.h linux-4.4.28/arch/arm/mach-at91/generic.h +--- linux-4.4.28.orig/arch/arm/mach-at91/generic.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/generic.h 2016-11-01 21:26:56.784213869 +0100 +@@ -11,27 +11,18 @@ + #ifndef _AT91_GENERIC_H + #define _AT91_GENERIC_H + +-#include +-#include +- +- /* Map io */ +-extern void __init at91_map_io(void); +-extern void __init at91_alt_map_io(void); +- +-/* idle */ +-extern void at91rm9200_idle(void); +-extern void at91sam9_idle(void); +- + #ifdef CONFIG_PM + extern void __init at91rm9200_pm_init(void); + extern void __init at91sam9260_pm_init(void); + extern void __init at91sam9g45_pm_init(void); + extern void __init at91sam9x5_pm_init(void); ++extern void __init sama5_pm_init(void); + #else + static inline void __init at91rm9200_pm_init(void) { } + static inline void __init at91sam9260_pm_init(void) { } + static inline void __init at91sam9g45_pm_init(void) { } + static inline void __init at91sam9x5_pm_init(void) { } ++static inline void __init sama5_pm_init(void) { } + #endif + + #endif /* _AT91_GENERIC_H */ +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/Kconfig linux-4.4.28/arch/arm/mach-at91/Kconfig +--- linux-4.4.28.orig/arch/arm/mach-at91/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/Kconfig 2016-11-01 21:26:56.784213869 +0100 +@@ -99,6 +99,7 @@ + config COMMON_CLK_AT91 + bool + select COMMON_CLK ++ select MFD_SYSCON + + config HAVE_AT91_SMD + bool +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/pm.c linux-4.4.28/arch/arm/mach-at91/pm.c +--- linux-4.4.28.orig/arch/arm/mach-at91/pm.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/pm.c 2016-11-01 21:26:56.788214125 +0100 +@@ -31,10 +31,13 @@ + #include + #include + #include ++#include + + #include "generic.h" + #include "pm.h" + ++static void __iomem *pmc; ++ + /* + * FIXME: this is needed to communicate between the pinctrl driver and + * the PM implementation in the machine. Possibly part of the PM +@@ -87,7 +90,7 @@ + unsigned long scsr; + int i; + +- scsr = at91_pmc_read(AT91_PMC_SCSR); ++ scsr = readl(pmc + AT91_PMC_SCSR); + + /* USB must not be using PLLB */ + if ((scsr & at91_pm_data.uhp_udp_mask) != 0) { +@@ -101,8 +104,7 @@ + + if ((scsr & (AT91_PMC_PCK0 << i)) == 0) + continue; +- +- css = at91_pmc_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS; ++ css = readl(pmc + AT91_PMC_PCKR(i)) & AT91_PMC_CSS; + if (css != AT91_PMC_CSS_SLOW) { + pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css); + return 0; +@@ -145,8 +147,8 @@ + flush_cache_all(); + outer_disable(); + +- at91_suspend_sram_fn(at91_pmc_base, at91_ramc_base[0], +- at91_ramc_base[1], pm_data); ++ at91_suspend_sram_fn(pmc, at91_ramc_base[0], ++ at91_ramc_base[1], pm_data); + + outer_resume(); + } +@@ -353,6 +355,21 @@ + at91_pm_set_standby(standby); + } + ++void at91rm9200_idle(void) ++{ ++ /* ++ * Disable the processor clock. The processor will be automatically ++ * re-enabled by an interrupt or by a reset. ++ */ ++ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); ++} ++ ++void at91sam9_idle(void) ++{ ++ writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR); ++ cpu_do_idle(); ++} ++ + static void __init at91_pm_sram_init(void) + { + struct gen_pool *sram_pool; +@@ -399,13 +416,36 @@ + &at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz); + } + +-static void __init at91_pm_init(void) ++static const struct of_device_id atmel_pmc_ids[] __initconst = { ++ { .compatible = "atmel,at91rm9200-pmc" }, ++ { .compatible = "atmel,at91sam9260-pmc" }, ++ { .compatible = "atmel,at91sam9g45-pmc" }, ++ { .compatible = "atmel,at91sam9n12-pmc" }, ++ { .compatible = "atmel,at91sam9x5-pmc" }, ++ { .compatible = "atmel,sama5d3-pmc" }, ++ { .compatible = "atmel,sama5d2-pmc" }, ++ { /* sentinel */ }, ++}; ++ ++static void __init at91_pm_init(void (*pm_idle)(void)) + { +- at91_pm_sram_init(); ++ struct device_node *pmc_np; + + if (at91_cpuidle_device.dev.platform_data) + platform_device_register(&at91_cpuidle_device); + ++ pmc_np = of_find_matching_node(NULL, atmel_pmc_ids); ++ pmc = of_iomap(pmc_np, 0); ++ if (!pmc) { ++ pr_err("AT91: PM not supported, PMC not found\n"); ++ return; ++ } ++ ++ if (pm_idle) ++ arm_pm_idle = pm_idle; ++ ++ at91_pm_sram_init(); ++ + if (at91_suspend_sram_fn) + suspend_set_ops(&at91_pm_ops); + else +@@ -424,7 +464,7 @@ + at91_pm_data.uhp_udp_mask = AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP; + at91_pm_data.memctrl = AT91_MEMCTRL_MC; + +- at91_pm_init(); ++ at91_pm_init(at91rm9200_idle); + } + + void __init at91sam9260_pm_init(void) +@@ -432,7 +472,7 @@ + at91_dt_ramc(); + at91_pm_data.memctrl = AT91_MEMCTRL_SDRAMC; + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); + } + + void __init at91sam9g45_pm_init(void) +@@ -440,7 +480,7 @@ + at91_dt_ramc(); + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP; + at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); + } + + void __init at91sam9x5_pm_init(void) +@@ -448,5 +488,13 @@ + at91_dt_ramc(); + at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; + at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; +- return at91_pm_init(); ++ at91_pm_init(at91sam9_idle); ++} ++ ++void __init sama5_pm_init(void) ++{ ++ at91_dt_ramc(); ++ at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP; ++ at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR; ++ at91_pm_init(NULL); + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-at91/sama5.c linux-4.4.28/arch/arm/mach-at91/sama5.c +--- linux-4.4.28.orig/arch/arm/mach-at91/sama5.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-at91/sama5.c 2016-11-01 21:26:56.788214125 +0100 +@@ -51,7 +51,7 @@ + soc_dev = soc_device_to_device(soc); + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); +- at91sam9x5_pm_init(); ++ sama5_pm_init(); + } + + static const char *const sama5_dt_board_compat[] __initconst = { +diff -Nur linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c linux-4.4.28/arch/arm/mach-exynos/platsmp.c +--- linux-4.4.28.orig/arch/arm/mach-exynos/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-exynos/platsmp.c 2016-11-01 21:26:56.796214642 +0100 +@@ -230,7 +230,7 @@ + return (void __iomem *)(S5P_VA_SCU); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void exynos_secondary_init(unsigned int cpu) + { +@@ -243,8 +243,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) +@@ -308,7 +308,7 @@ + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -335,7 +335,7 @@ + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -381,7 +381,7 @@ + * calibrations, then wait for it to finish + */ + fail: +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? ret : 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c linux-4.4.28/arch/arm/mach-hisi/platmcpm.c +--- linux-4.4.28.orig/arch/arm/mach-hisi/platmcpm.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-hisi/platmcpm.c 2016-11-01 21:26:56.800214899 +0100 +@@ -61,7 +61,7 @@ + + static void __iomem *sysctrl, *fabric; + static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + static u32 fabric_phys_addr; + /* + * [0]: bootwrapper physical address +@@ -113,7 +113,7 @@ + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; +@@ -147,7 +147,7 @@ + + out: + hip04_cpu_table[cluster][cpu]++; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + + return 0; + } +@@ -162,11 +162,11 @@ + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { + /* A power_up request went ahead of us. */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return; + } else if (hip04_cpu_table[cluster][cpu] > 1) { + pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); +@@ -174,7 +174,7 @@ + } + + last_man = hip04_cluster_is_down(cluster); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + if (last_man) { + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( +@@ -203,7 +203,7 @@ + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) + goto err; +@@ -211,10 +211,10 @@ + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; +@@ -231,10 +231,10 @@ + goto err; + if (hip04_cluster_is_down(cluster)) + hip04_set_snoop_filter(cluster, 0); +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 1; + err: +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 0; + } + #endif +diff -Nur linux-4.4.28.orig/arch/arm/mach-imx/Kconfig linux-4.4.28/arch/arm/mach-imx/Kconfig +--- linux-4.4.28.orig/arch/arm/mach-imx/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-imx/Kconfig 2016-11-01 21:26:56.804215163 +0100 +@@ -524,7 +524,7 @@ + bool "i.MX6 Quad/DualLite support" + select ARM_ERRATA_764369 if SMP + select HAVE_ARM_SCU if SMP +- select HAVE_ARM_TWD if SMP ++ select HAVE_ARM_TWD + select PCI_DOMAINS if PCI + select PINCTRL_IMX6Q + select SOC_IMX6 +diff -Nur linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c linux-4.4.28/arch/arm/mach-omap2/omap-smp.c +--- linux-4.4.28.orig/arch/arm/mach-omap2/omap-smp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-omap2/omap-smp.c 2016-11-01 21:26:56.836217219 +0100 +@@ -43,7 +43,7 @@ + /* SCU base address */ + static void __iomem *scu_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __iomem *omap4_get_scu_base(void) + { +@@ -74,8 +74,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -89,7 +89,7 @@ + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Update the AuxCoreBoot0 with boot state for secondary core. +@@ -166,7 +166,7 @@ + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c linux-4.4.28/arch/arm/mach-prima2/platsmp.c +--- linux-4.4.28.orig/arch/arm/mach-prima2/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-prima2/platsmp.c 2016-11-01 21:26:56.864219031 +0100 +@@ -22,7 +22,7 @@ + + static void __iomem *clk_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sirfsoc_secondary_init(unsigned int cpu) + { +@@ -36,8 +36,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static const struct of_device_id clk_ids[] = { +@@ -75,7 +75,7 @@ + /* make sure write buffer is drained */ + mb(); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -107,7 +107,7 @@ + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c linux-4.4.28/arch/arm/mach-qcom/platsmp.c +--- linux-4.4.28.orig/arch/arm/mach-qcom/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-qcom/platsmp.c 2016-11-01 21:26:56.872219540 +0100 +@@ -46,7 +46,7 @@ + + extern void secondary_startup_arm(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + #ifdef CONFIG_HOTPLUG_CPU + static void qcom_cpu_die(unsigned int cpu) +@@ -60,8 +60,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int scss_release_secondary(unsigned int cpu) +@@ -284,7 +284,7 @@ + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Send the secondary CPU a soft interrupt, thereby causing +@@ -297,7 +297,7 @@ + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return ret; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c linux-4.4.28/arch/arm/mach-spear/platsmp.c +--- linux-4.4.28.orig/arch/arm/mach-spear/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-spear/platsmp.c 2016-11-01 21:26:56.896221093 +0100 +@@ -32,7 +32,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void __iomem *scu_base = IOMEM(VA_SCU_BASE); + +@@ -47,8 +47,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -59,7 +59,7 @@ + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -84,7 +84,7 @@ + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c linux-4.4.28/arch/arm/mach-sti/platsmp.c +--- linux-4.4.28.orig/arch/arm/mach-sti/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mach-sti/platsmp.c 2016-11-01 21:26:56.896221093 +0100 +@@ -35,7 +35,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sti_secondary_init(unsigned int cpu) + { +@@ -48,8 +48,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -60,7 +60,7 @@ + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -91,7 +91,7 @@ + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mm/fault.c linux-4.4.28/arch/arm/mm/fault.c +--- linux-4.4.28.orig/arch/arm/mm/fault.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mm/fault.c 2016-11-01 21:26:56.900221345 +0100 +@@ -430,6 +430,9 @@ + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -497,6 +500,9 @@ + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } +diff -Nur linux-4.4.28.orig/arch/arm/mm/highmem.c linux-4.4.28/arch/arm/mm/highmem.c +--- linux-4.4.28.orig/arch/arm/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/mm/highmem.c 2016-11-01 21:26:56.904221609 +0100 +@@ -34,6 +34,11 @@ + return *ptep; + } + ++static unsigned int fixmap_idx(int type) ++{ ++ return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++} ++ + void *kmap(struct page *page) + { + might_sleep(); +@@ -54,12 +59,13 @@ + + void *kmap_atomic(struct page *page) + { ++ pte_t pte = mk_pte(page, kmap_prot); + unsigned int idx; + unsigned long vaddr; + void *kmap; + int type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -79,7 +85,7 @@ + + type = kmap_atomic_idx_push(); + +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + /* +@@ -93,7 +99,10 @@ + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. + */ +- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -106,44 +115,75 @@ + + if (kvaddr >= (void *)FIXADDR_START) { + type = kmap_atomic_idx(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); +- set_fixmap_pte(idx, __pte(0)); + #else + (void) idx; /* to kill a warning */ + #endif ++ set_fixmap_pte(idx, __pte(0)); + kmap_atomic_idx_pop(); + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + + void *kmap_atomic_pfn(unsigned long pfn) + { ++ pte_t pte = pfn_pte(pfn, kmap_prot); + unsigned long vaddr; + int idx, type; + struct page *page = pfn_to_page(pfn); + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + + type = kmap_atomic_idx_push(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); + #endif +- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } ++#if defined CONFIG_PREEMPT_RT_FULL ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ set_fixmap_pte(idx, __pte(0)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_fixmap_pte(idx, next_p->kmap_pte[i]); ++ } ++} ++#endif +diff -Nur linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c linux-4.4.28/arch/arm/plat-versatile/platsmp.c +--- linux-4.4.28.orig/arch/arm/plat-versatile/platsmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm/plat-versatile/platsmp.c 2016-11-01 21:26:56.936223672 +0100 +@@ -30,7 +30,7 @@ + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void versatile_secondary_init(unsigned int cpu) + { +@@ -43,8 +43,8 @@ + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -55,7 +55,7 @@ + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * This is really belt and braces; we hold unintended secondary +@@ -85,7 +85,7 @@ + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +diff -Nur linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h linux-4.4.28/arch/arm64/include/asm/thread_info.h +--- linux-4.4.28.orig/arch/arm64/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm64/include/asm/thread_info.h 2016-11-01 21:26:56.948224439 +0100 +@@ -49,6 +49,7 @@ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + int cpu; /* cpu */ + }; + +@@ -103,6 +104,7 @@ + #define TIF_NEED_RESCHED 1 + #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ + #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ ++#define TIF_NEED_RESCHED_LAZY 4 + #define TIF_NOHZ 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -118,6 +120,7 @@ + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) + #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -126,7 +129,8 @@ + #define _TIF_32BIT (1 << TIF_32BIT) + + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +- _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) ++ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ ++ _TIF_NEED_RESCHED_LAZY) + + #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ +diff -Nur linux-4.4.28.orig/arch/arm64/Kconfig linux-4.4.28/arch/arm64/Kconfig +--- linux-4.4.28.orig/arch/arm64/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm64/Kconfig 2016-11-01 21:26:56.944224187 +0100 +@@ -76,6 +76,7 @@ + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP + select HAVE_RCU_TABLE_FREE ++ select HAVE_PREEMPT_LAZY + select HAVE_SYSCALL_TRACEPOINTS + select IOMMU_DMA if IOMMU_SUPPORT + select IRQ_DOMAIN +@@ -582,7 +583,7 @@ + + config XEN + bool "Xen guest support on ARM64" +- depends on ARM64 && OF ++ depends on ARM64 && OF && !PREEMPT_RT_FULL + select SWIOTLB_XEN + help + Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. +diff -Nur linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c linux-4.4.28/arch/arm64/kernel/asm-offsets.c +--- linux-4.4.28.orig/arch/arm64/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm64/kernel/asm-offsets.c 2016-11-01 21:26:56.976226250 +0100 +@@ -35,6 +35,7 @@ + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +diff -Nur linux-4.4.28.orig/arch/arm64/kernel/entry.S linux-4.4.28/arch/arm64/kernel/entry.S +--- linux-4.4.28.orig/arch/arm64/kernel/entry.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/arm64/kernel/entry.S 2016-11-01 21:26:56.976226250 +0100 +@@ -376,11 +376,16 @@ + #ifdef CONFIG_PREEMPT + get_thread_info tsk + ldr w24, [tsk, #TI_PREEMPT] // get preempt count +- cbnz w24, 1f // preempt count != 0 ++ cbnz w24, 2f // preempt count != 0 + ldr x0, [tsk, #TI_FLAGS] // get flags +- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? +- bl el1_preempt ++ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? ++ ++ ldr w24, [tsk, #TI_PREEMPT_LAZY] // get preempt lazy count ++ cbnz w24, 2f // preempt lazy count != 0 ++ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? + 1: ++ bl el1_preempt ++2: + #endif + #ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_on +@@ -394,6 +399,7 @@ + 1: bl preempt_schedule_irq // irq en/disable is done inside + ldr x0, [tsk, #TI_FLAGS] // get new tasks TI_FLAGS + tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ++ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? + ret x24 + #endif + +@@ -638,6 +644,7 @@ + */ + work_pending: + tbnz x1, #TIF_NEED_RESCHED, work_resched ++ tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched + /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ + ldr x2, [sp, #S_PSTATE] + mov x0, sp // 'regs' +diff -Nur linux-4.4.28.orig/arch/Kconfig linux-4.4.28/arch/Kconfig +--- linux-4.4.28.orig/arch/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/Kconfig 2016-11-01 21:26:56.688207681 +0100 +@@ -9,6 +9,7 @@ + tristate "OProfile system profiling" + depends on PROFILING + depends on HAVE_OPROFILE ++ depends on !PREEMPT_RT_FULL + select RING_BUFFER + select RING_BUFFER_ALLOW_SWAP + help +@@ -52,6 +53,7 @@ + config JUMP_LABEL + bool "Optimize very unlikely/likely branches" + depends on HAVE_ARCH_JUMP_LABEL ++ depends on (!INTERRUPT_OFF_HIST && !PREEMPT_OFF_HIST && !WAKEUP_LATENCY_HIST && !MISSED_TIMER_OFFSETS_HIST) + help + This option enables a transparent branch optimization that + makes certain almost-always-true or almost-always-false branch +diff -Nur linux-4.4.28.orig/arch/mips/Kconfig linux-4.4.28/arch/mips/Kconfig +--- linux-4.4.28.orig/arch/mips/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/mips/Kconfig 2016-11-01 21:26:57.008228310 +0100 +@@ -2410,7 +2410,7 @@ + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool +diff -Nur linux-4.4.28.orig/arch/mips/kvm/mips.c linux-4.4.28/arch/mips/kvm/mips.c +--- linux-4.4.28.orig/arch/mips/kvm/mips.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/mips/kvm/mips.c 2016-11-01 21:26:57.044230629 +0100 +@@ -454,8 +454,8 @@ + + dvcpu->arch.wait = 0; + +- if (waitqueue_active(&dvcpu->wq)) +- wake_up_interruptible(&dvcpu->wq); ++ if (swait_active(&dvcpu->wq)) ++ swake_up(&dvcpu->wq); + + return 0; + } +@@ -1183,8 +1183,8 @@ + kvm_mips_callbacks->queue_timer_int(vcpu); + + vcpu->arch.wait = 0; +- if (waitqueue_active(&vcpu->wq)) +- wake_up_interruptible(&vcpu->wq); ++ if (swait_active(&vcpu->wq)) ++ swake_up(&vcpu->wq); + } + + /* low level hrtimer wake routine */ +diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h linux-4.4.28/arch/powerpc/include/asm/kvm_host.h +--- linux-4.4.28.orig/arch/powerpc/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/include/asm/kvm_host.h 2016-11-01 21:26:57.116235270 +0100 +@@ -286,7 +286,7 @@ + struct list_head runnable_threads; + struct list_head preempt_list; + spinlock_t lock; +- wait_queue_head_t wq; ++ struct swait_queue_head wq; + spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ + u64 stolen_tb; + u64 preempt_tb; +@@ -626,7 +626,7 @@ + u8 prodded; + u32 last_inst; + +- wait_queue_head_t *wqp; ++ struct swait_queue_head *wqp; + struct kvmppc_vcore *vcore; + int ret; + int trap; +diff -Nur linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h linux-4.4.28/arch/powerpc/include/asm/thread_info.h +--- linux-4.4.28.orig/arch/powerpc/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/include/asm/thread_info.h 2016-11-01 21:26:57.124235787 +0100 +@@ -42,6 +42,8 @@ + int cpu; /* cpu we're on */ + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + unsigned long local_flags; /* private flags for thread */ + + /* low level flags - has atomic operations done on it */ +@@ -82,8 +84,7 @@ + #define TIF_SYSCALL_TRACE 0 /* syscall trace active */ + #define TIF_SIGPENDING 1 /* signal pending */ + #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ +-#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling +- TIF_NEED_RESCHED */ ++#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */ + #define TIF_32BIT 4 /* 32 bit binary */ + #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ +@@ -101,6 +102,8 @@ + #if defined(CONFIG_PPC64) + #define TIF_ELF2ABI 18 /* function descriptors must die! */ + #endif ++#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling ++ TIF_NEED_RESCHED */ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1<flags) + set_bits(irqtp->flags, &curtp->flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S linux-4.4.28/arch/powerpc/kernel/misc_32.S +--- linux-4.4.28.orig/arch/powerpc/kernel/misc_32.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/kernel/misc_32.S 2016-11-01 21:26:57.156237855 +0100 +@@ -40,6 +40,7 @@ + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -56,6 +57,7 @@ + stw r10,THREAD+KSP_LIMIT(r2) + mtlr r0 + blr ++#endif + + /* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); +diff -Nur linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S linux-4.4.28/arch/powerpc/kernel/misc_64.S +--- linux-4.4.28.orig/arch/powerpc/kernel/misc_64.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/kernel/misc_64.S 2016-11-01 21:26:57.160238107 +0100 +@@ -30,6 +30,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) +@@ -40,6 +41,7 @@ + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_do_irq) + mflr r0 +diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c linux-4.4.28/arch/powerpc/kvm/book3s_hv.c +--- linux-4.4.28.orig/arch/powerpc/kvm/book3s_hv.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/kvm/book3s_hv.c 2016-11-01 21:26:57.184239655 +0100 +@@ -114,11 +114,11 @@ + static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) + { + int cpu; +- wait_queue_head_t *wqp; ++ struct swait_queue_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swait_active(wqp)) { ++ swake_up(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -707,8 +707,8 @@ + tvcpu->arch.prodded = 1; + smp_mb(); + if (vcpu->arch.ceded) { +- if (waitqueue_active(&vcpu->wq)) { +- wake_up_interruptible(&vcpu->wq); ++ if (swait_active(&vcpu->wq)) { ++ swake_up(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +@@ -1447,7 +1447,7 @@ + INIT_LIST_HEAD(&vcore->runnable_threads); + spin_lock_init(&vcore->lock); + spin_lock_init(&vcore->stoltb_lock); +- init_waitqueue_head(&vcore->wq); ++ init_swait_queue_head(&vcore->wq); + vcore->preempt_tb = TB_NIL; + vcore->lpcr = kvm->arch.lpcr; + vcore->first_vcpuid = core * threads_per_subcore; +@@ -2519,10 +2519,9 @@ + { + struct kvm_vcpu *vcpu; + int do_sleep = 1; ++ DECLARE_SWAITQUEUE(wait); + +- DEFINE_WAIT(wait); +- +- prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); ++ prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + + /* + * Check one last time for pending exceptions and ceded state after +@@ -2536,7 +2535,7 @@ + } + + if (!do_sleep) { +- finish_wait(&vc->wq, &wait); ++ finish_swait(&vc->wq, &wait); + return; + } + +@@ -2544,7 +2543,7 @@ + trace_kvmppc_vcore_blocked(vc, 0); + spin_unlock(&vc->lock); + schedule(); +- finish_wait(&vc->wq, &wait); ++ finish_swait(&vc->wq, &wait); + spin_lock(&vc->lock); + vc->vcore_state = VCORE_INACTIVE; + trace_kvmppc_vcore_blocked(vc, 1); +@@ -2600,7 +2599,7 @@ + kvmppc_start_thread(vcpu, vc); + trace_kvm_guest_enter(vcpu); + } else if (vc->vcore_state == VCORE_SLEEPING) { +- wake_up(&vc->wq); ++ swake_up(&vc->wq); + } + + } +diff -Nur linux-4.4.28.orig/arch/powerpc/kvm/Kconfig linux-4.4.28/arch/powerpc/kvm/Kconfig +--- linux-4.4.28.orig/arch/powerpc/kvm/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/kvm/Kconfig 2016-11-01 21:26:57.168238628 +0100 +@@ -172,6 +172,7 @@ + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 ++ depends on !PREEMPT_RT_FULL + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING +diff -Nur linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c +--- linux-4.4.28.orig/arch/powerpc/platforms/ps3/device-init.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/powerpc/platforms/ps3/device-init.c 2016-11-01 21:26:57.192240175 +0100 +@@ -752,7 +752,7 @@ + } + pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); + +- res = wait_event_interruptible(dev->done.wait, ++ res = swait_event_interruptible(dev->done.wait, + dev->done.done || kthread_should_stop()); + if (kthread_should_stop()) + res = -EINTR; +diff -Nur linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h linux-4.4.28/arch/s390/include/asm/kvm_host.h +--- linux-4.4.28.orig/arch/s390/include/asm/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/s390/include/asm/kvm_host.h 2016-11-01 21:26:57.204240949 +0100 +@@ -427,7 +427,7 @@ + struct kvm_s390_local_interrupt { + spinlock_t lock; + struct kvm_s390_float_interrupt *float_int; +- wait_queue_head_t *wq; ++ struct swait_queue_head *wq; + atomic_t *cpuflags; + DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); + struct kvm_s390_irq_payload irq; +diff -Nur linux-4.4.28.orig/arch/s390/kvm/interrupt.c linux-4.4.28/arch/s390/kvm/interrupt.c +--- linux-4.4.28.orig/arch/s390/kvm/interrupt.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/s390/kvm/interrupt.c 2016-11-01 21:26:57.224242231 +0100 +@@ -868,13 +868,13 @@ + + void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) + { +- if (waitqueue_active(&vcpu->wq)) { ++ if (swait_active(&vcpu->wq)) { + /* + * The vcpu gave up the cpu voluntarily, mark it as a good + * yield-candidate. + */ + vcpu->preempted = true; +- wake_up_interruptible(&vcpu->wq); ++ swake_up(&vcpu->wq); + vcpu->stat.halt_wakeup++; + } + } +diff -Nur linux-4.4.28.orig/arch/sh/kernel/irq.c linux-4.4.28/arch/sh/kernel/irq.c +--- linux-4.4.28.orig/arch/sh/kernel/irq.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/sh/kernel/irq.c 2016-11-01 21:26:57.284246099 +0100 +@@ -147,6 +147,7 @@ + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curctx; +@@ -174,6 +175,7 @@ + "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" + ); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +diff -Nur linux-4.4.28.orig/arch/sparc/Kconfig linux-4.4.28/arch/sparc/Kconfig +--- linux-4.4.28.orig/arch/sparc/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/sparc/Kconfig 2016-11-01 21:26:57.460257444 +0100 +@@ -189,12 +189,10 @@ + source kernel/Kconfig.hz + + config RWSEM_GENERIC_SPINLOCK +- bool +- default y if SPARC32 ++ def_bool PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM +- bool +- default y if SPARC64 ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_HWEIGHT + bool +diff -Nur linux-4.4.28.orig/arch/sparc/kernel/irq_64.c linux-4.4.28/arch/sparc/kernel/irq_64.c +--- linux-4.4.28.orig/arch/sparc/kernel/irq_64.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/sparc/kernel/irq_64.c 2016-11-01 21:26:57.488259255 +0100 +@@ -854,6 +854,7 @@ + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + void *orig_sp, *sp = softirq_stack[smp_processor_id()]; +@@ -868,6 +869,7 @@ + __asm__ __volatile__("mov %0, %%sp" + : : "r" (orig_sp)); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +diff -Nur linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c +--- linux-4.4.28.orig/arch/x86/crypto/aesni-intel_glue.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/crypto/aesni-intel_glue.c 2016-11-01 21:26:57.524261570 +0100 +@@ -383,14 +383,14 @@ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, +- nbytes & AES_BLOCK_MASK); ++ nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -407,14 +407,14 @@ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -431,14 +431,14 @@ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -455,14 +455,14 @@ + err = blkcipher_walk_virt(desc, &walk); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -514,18 +514,20 @@ + err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE); + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { ++ kernel_fpu_begin(); + aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + if (walk.nbytes) { ++ kernel_fpu_begin(); + ctr_crypt_final(ctx, &walk); ++ kernel_fpu_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } +- kernel_fpu_end(); + + return err; + } +diff -Nur linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c +--- linux-4.4.28.orig/arch/x86/crypto/cast5_avx_glue.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/crypto/cast5_avx_glue.c 2016-11-01 21:26:57.528261834 +0100 +@@ -59,7 +59,7 @@ + static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk, + bool enc) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = CAST5_BLOCK_SIZE; + unsigned int nbytes; +@@ -75,7 +75,7 @@ + u8 *wsrc = walk->src.virt.addr; + u8 *wdst = walk->dst.virt.addr; + +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + + /* Process multi-block batch */ + if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { +@@ -103,10 +103,9 @@ + } while (nbytes >= bsize); + + done: ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -227,7 +226,7 @@ + static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -236,12 +235,11 @@ + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes)) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __cbc_decrypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -311,7 +309,7 @@ + static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -320,13 +318,12 @@ + desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; + + while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, nbytes); + nbytes = __ctr_crypt(desc, &walk); ++ cast5_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- cast5_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + ctr_crypt_final(desc, &walk); + err = blkcipher_walk_done(desc, &walk, 0); +diff -Nur linux-4.4.28.orig/arch/x86/crypto/glue_helper.c linux-4.4.28/arch/x86/crypto/glue_helper.c +--- linux-4.4.28.orig/arch/x86/crypto/glue_helper.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/crypto/glue_helper.c 2016-11-01 21:26:57.536262350 +0100 +@@ -39,7 +39,7 @@ + void *ctx = crypto_blkcipher_ctx(desc->tfm); + const unsigned int bsize = 128 / 8; + unsigned int nbytes, i, func_bytes; +- bool fpu_enabled = false; ++ bool fpu_enabled; + int err; + + err = blkcipher_walk_virt(desc, walk); +@@ -49,7 +49,7 @@ + u8 *wdst = walk->dst.virt.addr; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + + for (i = 0; i < gctx->num_funcs; i++) { + func_bytes = bsize * gctx->funcs[i].num_blocks; +@@ -71,10 +71,10 @@ + } + + done: ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + +@@ -194,7 +194,7 @@ + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -203,12 +203,12 @@ + + while ((nbytes = walk.nbytes)) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit); +@@ -277,7 +277,7 @@ + struct scatterlist *src, unsigned int nbytes) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -286,13 +286,12 @@ + + while ((nbytes = walk.nbytes) >= bsize) { + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, nbytes); ++ desc, false, nbytes); + nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk); ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + glue_ctr_crypt_final_128bit( + gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk); +@@ -347,7 +346,7 @@ + void *tweak_ctx, void *crypt_ctx) + { + const unsigned int bsize = 128 / 8; +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct blkcipher_walk walk; + int err; + +@@ -360,21 +359,21 @@ + + /* set minimum length to bsize, for tweak_fn */ + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- desc, fpu_enabled, ++ desc, false, + nbytes < bsize ? bsize : nbytes); +- + /* calculate first value of T */ + tweak_fn(tweak_ctx, walk.iv, walk.iv); ++ glue_fpu_end(fpu_enabled); + + while (nbytes) { ++ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, ++ desc, false, nbytes); + nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk); + ++ glue_fpu_end(fpu_enabled); + err = blkcipher_walk_done(desc, &walk, nbytes); + nbytes = walk.nbytes; + } +- +- glue_fpu_end(fpu_enabled); +- + return err; + } + EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit); +diff -Nur linux-4.4.28.orig/arch/x86/entry/common.c linux-4.4.28/arch/x86/entry/common.c +--- linux-4.4.28.orig/arch/x86/entry/common.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/entry/common.c 2016-11-01 21:26:57.544262865 +0100 +@@ -220,7 +220,7 @@ + + #define EXIT_TO_USERMODE_LOOP_FLAGS \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ +- _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY) ++ _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY) + + static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) + { +@@ -236,9 +236,16 @@ + /* We have work to do. */ + local_irq_enable(); + +- if (cached_flags & _TIF_NEED_RESCHED) ++ if (cached_flags & _TIF_NEED_RESCHED_MASK) + schedule(); + ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (unlikely(current->forced_info.si_signo)) { ++ struct task_struct *t = current; ++ force_sig_info(t->forced_info.si_signo, &t->forced_info, t); ++ t->forced_info.si_signo = 0; ++ } ++#endif + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + +diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_32.S linux-4.4.28/arch/x86/entry/entry_32.S +--- linux-4.4.28.orig/arch/x86/entry/entry_32.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/entry/entry_32.S 2016-11-01 21:26:57.548263117 +0100 +@@ -278,8 +278,24 @@ + ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) + need_resched: ++ # preempt count == 0 + NEED_RS set? + cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all ++#else ++ jz test_int_off ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jne restore_all ++ ++ cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? ++ jnz restore_all ++ ++ testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) ++ jz restore_all ++test_int_off: ++#endif + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq +diff -Nur linux-4.4.28.orig/arch/x86/entry/entry_64.S linux-4.4.28/arch/x86/entry/entry_64.S +--- linux-4.4.28.orig/arch/x86/entry/entry_64.S 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/entry/entry_64.S 2016-11-01 21:26:57.548263117 +0100 +@@ -579,7 +579,23 @@ + bt $9, EFLAGS(%rsp) /* were interrupts off? */ + jnc 1f + 0: cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz 1f ++#else ++ jz do_preempt_schedule_irq ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jnz 1f ++ ++ GET_THREAD_INFO(%rcx) ++ cmpl $0, TI_preempt_lazy_count(%rcx) ++ jnz 1f ++ ++ bt $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx) ++ jnc 1f ++do_preempt_schedule_irq: ++#endif + call preempt_schedule_irq + jmp 0b + 1: +@@ -867,6 +883,7 @@ + jmp 2b + .previous + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(do_softirq_own_stack) + pushq %rbp +@@ -879,6 +896,7 @@ + decl PER_CPU_VAR(irq_count) + ret + END(do_softirq_own_stack) ++#endif + + #ifdef CONFIG_XEN + idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/preempt.h linux-4.4.28/arch/x86/include/asm/preempt.h +--- linux-4.4.28.orig/arch/x86/include/asm/preempt.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/preempt.h 2016-11-01 21:26:57.556263632 +0100 +@@ -79,17 +79,46 @@ + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e"); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u32 tmp; ++ ++ tmp = raw_cpu_read_4(__preempt_count); ++ if (tmp == preempt_offset) ++ return true; ++ ++ /* preempt count == 0 ? */ ++ tmp &= ~PREEMPT_NEED_RESCHED; ++ if (tmp) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); ++#endif + } + + #ifdef CONFIG_PREEMPT +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/signal.h linux-4.4.28/arch/x86/include/asm/signal.h +--- linux-4.4.28.orig/arch/x86/include/asm/signal.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/signal.h 2016-11-01 21:26:57.556263632 +0100 +@@ -23,6 +23,19 @@ + unsigned long sig[_NSIG_WORDS]; + } sigset_t; + ++/* ++ * Because some traps use the IST stack, we must keep preemption ++ * disabled while calling do_trap(), but do_trap() may call ++ * force_sig_info() which will grab the signal spin_locks for the ++ * task, which in PREEMPT_RT_FULL are mutexes. By defining ++ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set ++ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the ++ * trap. ++ */ ++#if defined(CONFIG_PREEMPT_RT_FULL) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #ifndef CONFIG_COMPAT + typedef sigset_t compat_sigset_t; + #endif +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h linux-4.4.28/arch/x86/include/asm/stackprotector.h +--- linux-4.4.28.orig/arch/x86/include/asm/stackprotector.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/stackprotector.h 2016-11-01 21:26:57.560263897 +0100 +@@ -59,7 +59,7 @@ + */ + static __always_inline void boot_init_stack_canary(void) + { +- u64 canary; ++ u64 uninitialized_var(canary); + u64 tsc; + + #ifdef CONFIG_X86_64 +@@ -70,8 +70,15 @@ + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. ++ * ++ * For preempt-rt we need to weaken the randomness a bit, as ++ * we can't call into the random generator from atomic context ++ * due to locking constraints. We just leave canary ++ * uninitialized and use the TSC based randomness on top of it. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + get_random_bytes(&canary, sizeof(canary)); ++#endif + tsc = rdtsc(); + canary += tsc + (tsc << 32UL); + +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/thread_info.h linux-4.4.28/arch/x86/include/asm/thread_info.h +--- linux-4.4.28.orig/arch/x86/include/asm/thread_info.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/thread_info.h 2016-11-01 21:26:57.560263897 +0100 +@@ -58,6 +58,8 @@ + __u32 status; /* thread synchronous flags */ + __u32 cpu; /* current CPU */ + mm_segment_t addr_limit; ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + unsigned int sig_on_uaccess_error:1; + unsigned int uaccess_err:1; /* uaccess failed */ + }; +@@ -95,6 +97,7 @@ + #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SECCOMP 8 /* secure computing */ ++#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ + #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ + #define TIF_UPROBE 12 /* breakpointed or singlestepping */ + #define TIF_NOTSC 16 /* TSC is not accessible in userland */ +@@ -119,6 +122,7 @@ + #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) + #define _TIF_SECCOMP (1 << TIF_SECCOMP) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_NOTSC (1 << TIF_NOTSC) +@@ -152,6 +156,8 @@ + #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h +--- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_bau.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/uv/uv_bau.h 2016-11-01 21:26:57.568264412 +0100 +@@ -615,9 +615,9 @@ + cycles_t send_message; + cycles_t period_end; + cycles_t period_time; +- spinlock_t uvhub_lock; +- spinlock_t queue_lock; +- spinlock_t disable_lock; ++ raw_spinlock_t uvhub_lock; ++ raw_spinlock_t queue_lock; ++ raw_spinlock_t disable_lock; + /* tunables */ + int max_concurr; + int max_concurr_const; +@@ -776,15 +776,15 @@ + * to be lowered below the current 'v'. atomic_add_unless can only stop + * on equal. + */ +-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u) ++static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u) + { +- spin_lock(lock); ++ raw_spin_lock(lock); + if (atomic_read(v) >= u) { +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 0; + } + atomic_inc(v); +- spin_unlock(lock); ++ raw_spin_unlock(lock); + return 1; + } + +diff -Nur linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h +--- linux-4.4.28.orig/arch/x86/include/asm/uv/uv_hub.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/include/asm/uv/uv_hub.h 2016-11-01 21:26:57.568264412 +0100 +@@ -492,7 +492,7 @@ + unsigned short nr_online_cpus; + unsigned short pnode; + short memory_nid; +- spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ ++ raw_spinlock_t nmi_lock; /* obsolete, see uv_hub_nmi */ + unsigned long nmi_count; /* obsolete, see uv_hub_nmi */ + }; + extern struct uv_blade_info *uv_blade_info; +diff -Nur linux-4.4.28.orig/arch/x86/Kconfig linux-4.4.28/arch/x86/Kconfig +--- linux-4.4.28.orig/arch/x86/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/Kconfig 2016-11-01 21:26:57.508260538 +0100 +@@ -17,6 +17,7 @@ + ### Arch settings + config X86 + def_bool y ++ select HAVE_PREEMPT_LAZY + select ACPI_LEGACY_TABLES_LOOKUP if ACPI + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ANON_INODES +@@ -212,8 +213,11 @@ + def_bool y + depends on ISA_DMA_API + ++config RWSEM_GENERIC_SPINLOCK ++ def_bool PREEMPT_RT_FULL ++ + config RWSEM_XCHGADD_ALGORITHM +- def_bool y ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_CALIBRATE_DELAY + def_bool y +@@ -848,7 +852,7 @@ + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL +- select CPUMASK_OFFSTACK ++ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL + ---help--- + Enable maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +diff -Nur linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c linux-4.4.28/arch/x86/kernel/acpi/boot.c +--- linux-4.4.28.orig/arch/x86/kernel/acpi/boot.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/acpi/boot.c 2016-11-01 21:26:57.580265179 +0100 +@@ -87,7 +87,9 @@ + * ->ioapic_mutex + * ->ioapic_lock + */ ++#ifdef CONFIG_X86_IO_APIC + static DEFINE_MUTEX(acpi_ioapic_lock); ++#endif + + /* -------------------------------------------------------------------------- + Boot-time Configuration +diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c linux-4.4.28/arch/x86/kernel/apic/io_apic.c +--- linux-4.4.28.orig/arch/x86/kernel/apic/io_apic.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/apic/io_apic.c 2016-11-01 21:26:57.600266475 +0100 +@@ -1711,7 +1711,8 @@ + static inline bool ioapic_irqd_mask(struct irq_data *data) + { + /* If we are moving the irq we need to mask it */ +- if (unlikely(irqd_is_setaffinity_pending(data))) { ++ if (unlikely(irqd_is_setaffinity_pending(data) && ++ !irqd_irq_inprogress(data))) { + mask_ioapic_irq(data); + return true; + } +diff -Nur linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c +--- linux-4.4.28.orig/arch/x86/kernel/apic/x2apic_uv_x.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/apic/x2apic_uv_x.c 2016-11-01 21:26:57.612267242 +0100 +@@ -947,7 +947,7 @@ + uv_blade_info[blade].pnode = pnode; + uv_blade_info[blade].nr_possible_cpus = 0; + uv_blade_info[blade].nr_online_cpus = 0; +- spin_lock_init(&uv_blade_info[blade].nmi_lock); ++ raw_spin_lock_init(&uv_blade_info[blade].nmi_lock); + min_pnode = min(pnode, min_pnode); + max_pnode = max(pnode, max_pnode); + blade++; +diff -Nur linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c linux-4.4.28/arch/x86/kernel/asm-offsets.c +--- linux-4.4.28.orig/arch/x86/kernel/asm-offsets.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/asm-offsets.c 2016-11-01 21:26:57.612267242 +0100 +@@ -32,6 +32,7 @@ + OFFSET(TI_flags, thread_info, flags); + OFFSET(TI_status, thread_info, status); + OFFSET(TI_addr_limit, thread_info, addr_limit); ++ OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count); + + BLANK(); + OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); +@@ -89,4 +90,5 @@ + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); ++ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); + } +diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c +--- linux-4.4.28.orig/arch/x86/kernel/cpu/mcheck/mce.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/cpu/mcheck/mce.c 2016-11-01 21:26:57.624268022 +0100 +@@ -41,6 +41,8 @@ + #include + #include + #include ++#include ++#include + + #include + #include +@@ -1236,7 +1238,7 @@ + static unsigned long check_interval = INITIAL_CHECK_INTERVAL; + + static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ +-static DEFINE_PER_CPU(struct timer_list, mce_timer); ++static DEFINE_PER_CPU(struct hrtimer, mce_timer); + + static unsigned long mce_adjust_timer_default(unsigned long interval) + { +@@ -1245,32 +1247,18 @@ + + static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; + +-static void __restart_timer(struct timer_list *t, unsigned long interval) ++static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval) + { +- unsigned long when = jiffies + interval; +- unsigned long flags; +- +- local_irq_save(flags); +- +- if (timer_pending(t)) { +- if (time_before(when, t->expires)) +- mod_timer_pinned(t, when); +- } else { +- t->expires = round_jiffies(when); +- add_timer_on(t, smp_processor_id()); +- } +- +- local_irq_restore(flags); ++ if (!interval) ++ return HRTIMER_NORESTART; ++ hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval))); ++ return HRTIMER_RESTART; + } + +-static void mce_timer_fn(unsigned long data) ++static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); +- int cpu = smp_processor_id(); + unsigned long iv; + +- WARN_ON(cpu != data); +- + iv = __this_cpu_read(mce_next_interval); + + if (mce_available(this_cpu_ptr(&cpu_info))) { +@@ -1293,7 +1281,7 @@ + + done: + __this_cpu_write(mce_next_interval, iv); +- __restart_timer(t, iv); ++ return __restart_timer(timer, iv); + } + + /* +@@ -1301,7 +1289,7 @@ + */ + void mce_timer_kick(unsigned long interval) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned long iv = __this_cpu_read(mce_next_interval); + + __restart_timer(t, interval); +@@ -1316,7 +1304,7 @@ + int cpu; + + for_each_online_cpu(cpu) +- del_timer_sync(&per_cpu(mce_timer, cpu)); ++ hrtimer_cancel(&per_cpu(mce_timer, cpu)); + } + + static void mce_do_trigger(struct work_struct *work) +@@ -1326,6 +1314,56 @@ + + static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + ++static void __mce_notify_work(struct swork_event *event) ++{ ++ /* Not more than two messages every minute */ ++ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); ++ ++ /* wake processes polling /dev/mcelog */ ++ wake_up_interruptible(&mce_chrdev_wait); ++ ++ /* ++ * There is no risk of missing notifications because ++ * work_pending is always cleared before the function is ++ * executed. ++ */ ++ if (mce_helper[0] && !work_pending(&mce_trigger_work)) ++ schedule_work(&mce_trigger_work); ++ ++ if (__ratelimit(&ratelimit)) ++ pr_info(HW_ERR "Machine check events logged\n"); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static bool notify_work_ready __read_mostly; ++static struct swork_event notify_work; ++ ++static int mce_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, __mce_notify_work); ++ notify_work_ready = true; ++ return 0; ++} ++ ++static void mce_notify_work(void) ++{ ++ if (notify_work_ready) ++ swork_queue(¬ify_work); ++} ++#else ++static void mce_notify_work(void) ++{ ++ __mce_notify_work(NULL); ++} ++static inline int mce_notify_work_init(void) { return 0; } ++#endif ++ + /* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI +@@ -1333,19 +1371,8 @@ + */ + int mce_notify_irq(void) + { +- /* Not more than two messages every minute */ +- static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); +- + if (test_and_clear_bit(0, &mce_need_notify)) { +- /* wake processes polling /dev/mcelog */ +- wake_up_interruptible(&mce_chrdev_wait); +- +- if (mce_helper[0]) +- schedule_work(&mce_trigger_work); +- +- if (__ratelimit(&ratelimit)) +- pr_info(HW_ERR "Machine check events logged\n"); +- ++ mce_notify_work(); + return 1; + } + return 0; +@@ -1639,7 +1666,7 @@ + } + } + +-static void mce_start_timer(unsigned int cpu, struct timer_list *t) ++static void mce_start_timer(unsigned int cpu, struct hrtimer *t) + { + unsigned long iv = check_interval * HZ; + +@@ -1648,16 +1675,17 @@ + + per_cpu(mce_next_interval, cpu) = iv; + +- t->expires = round_jiffies(jiffies + iv); +- add_timer_on(t, cpu); ++ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL), ++ 0, HRTIMER_MODE_REL_PINNED); + } + + static void __mcheck_cpu_init_timer(void) + { +- struct timer_list *t = this_cpu_ptr(&mce_timer); ++ struct hrtimer *t = this_cpu_ptr(&mce_timer); + unsigned int cpu = smp_processor_id(); + +- setup_timer(t, mce_timer_fn, cpu); ++ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ t->function = mce_timer_fn; + mce_start_timer(cpu, t); + } + +@@ -2376,6 +2404,8 @@ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + ++ hrtimer_cancel(this_cpu_ptr(&mce_timer)); ++ + if (!(action & CPU_TASKS_FROZEN)) + cmci_clear(); + +@@ -2398,6 +2428,7 @@ + if (b->init) + wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + } ++ __mcheck_cpu_init_timer(); + } + + /* Get notified when a cpu comes on/off. Be hotplug friendly. */ +@@ -2405,7 +2436,6 @@ + mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) + { + unsigned int cpu = (unsigned long)hcpu; +- struct timer_list *t = &per_cpu(mce_timer, cpu); + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: +@@ -2425,11 +2455,9 @@ + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, mce_disable_cpu, &action, 1); +- del_timer_sync(t); + break; + case CPU_DOWN_FAILED: + smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); +- mce_start_timer(cpu, t); + break; + } + +@@ -2468,6 +2496,10 @@ + goto err_out; + } + ++ err = mce_notify_work_init(); ++ if (err) ++ goto err_out; ++ + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; +diff -Nur linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c +--- linux-4.4.28.orig/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/cpu/perf_event_intel_rapl.c 2016-11-01 21:26:57.636268789 +0100 +@@ -117,7 +117,7 @@ + }; + + struct rapl_pmu { +- spinlock_t lock; ++ raw_spinlock_t lock; + int n_active; /* number of active events */ + struct list_head active_list; + struct pmu *pmu; /* pointer to rapl_pmu_class */ +@@ -220,13 +220,13 @@ + if (!pmu->n_active) + return HRTIMER_NORESTART; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + list_for_each_entry(event, &pmu->active_list, active_entry) { + rapl_event_update(event); + } + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + + hrtimer_forward_now(hrtimer, pmu->timer_interval); + +@@ -263,9 +263,9 @@ + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + __rapl_pmu_event_start(pmu, event); +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + } + + static void rapl_pmu_event_stop(struct perf_event *event, int mode) +@@ -274,7 +274,7 @@ + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + /* mark event as deactivated and stopped */ + if (!(hwc->state & PERF_HES_STOPPED)) { +@@ -299,7 +299,7 @@ + hwc->state |= PERF_HES_UPTODATE; + } + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + } + + static int rapl_pmu_event_add(struct perf_event *event, int mode) +@@ -308,14 +308,14 @@ + struct hw_perf_event *hwc = &event->hw; + unsigned long flags; + +- spin_lock_irqsave(&pmu->lock, flags); ++ raw_spin_lock_irqsave(&pmu->lock, flags); + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (mode & PERF_EF_START) + __rapl_pmu_event_start(pmu, event); + +- spin_unlock_irqrestore(&pmu->lock, flags); ++ raw_spin_unlock_irqrestore(&pmu->lock, flags); + + return 0; + } +@@ -603,7 +603,7 @@ + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -1; +- spin_lock_init(&pmu->lock); ++ raw_spin_lock_init(&pmu->lock); + + INIT_LIST_HEAD(&pmu->active_list); + +diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c linux-4.4.28/arch/x86/kernel/dumpstack_32.c +--- linux-4.4.28.orig/arch/x86/kernel/dumpstack_32.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/dumpstack_32.c 2016-11-01 21:26:57.648269569 +0100 +@@ -42,7 +42,7 @@ + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) + { +- const unsigned cpu = get_cpu(); ++ const unsigned cpu = get_cpu_light(); + int graph = 0; + u32 *prev_esp; + +@@ -86,7 +86,7 @@ + break; + touch_nmi_watchdog(); + } +- put_cpu(); ++ put_cpu_light(); + } + EXPORT_SYMBOL(dump_trace); + +diff -Nur linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c linux-4.4.28/arch/x86/kernel/dumpstack_64.c +--- linux-4.4.28.orig/arch/x86/kernel/dumpstack_64.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/dumpstack_64.c 2016-11-01 21:26:57.648269569 +0100 +@@ -152,7 +152,7 @@ + unsigned long *stack, unsigned long bp, + const struct stacktrace_ops *ops, void *data) + { +- const unsigned cpu = get_cpu(); ++ const unsigned cpu = get_cpu_light(); + struct thread_info *tinfo; + unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); + unsigned long dummy; +@@ -241,7 +241,7 @@ + * This handles the process stack: + */ + bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); +- put_cpu(); ++ put_cpu_light(); + } + EXPORT_SYMBOL(dump_trace); + +@@ -255,7 +255,7 @@ + int cpu; + int i; + +- preempt_disable(); ++ migrate_disable(); + cpu = smp_processor_id(); + + irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); +@@ -291,7 +291,7 @@ + pr_cont(" %016lx", *stack++); + touch_nmi_watchdog(); + } +- preempt_enable(); ++ migrate_enable(); + + pr_cont("\n"); + show_trace_log_lvl(task, regs, sp, bp, log_lvl); +diff -Nur linux-4.4.28.orig/arch/x86/kernel/irq_32.c linux-4.4.28/arch/x86/kernel/irq_32.c +--- linux-4.4.28.orig/arch/x86/kernel/irq_32.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/irq_32.c 2016-11-01 21:26:57.652269821 +0100 +@@ -128,6 +128,7 @@ + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curstk; +@@ -146,6 +147,7 @@ + + call_on_stack(__do_softirq, isp); + } ++#endif + + bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) + { +diff -Nur linux-4.4.28.orig/arch/x86/kernel/kvm.c linux-4.4.28/arch/x86/kernel/kvm.c +--- linux-4.4.28.orig/arch/x86/kernel/kvm.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/kvm.c 2016-11-01 21:26:57.652269821 +0100 +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -91,14 +92,14 @@ + + struct kvm_task_sleep_node { + struct hlist_node link; +- wait_queue_head_t wq; ++ struct swait_queue_head wq; + u32 token; + int cpu; + bool halted; + }; + + static struct kvm_task_sleep_head { +- spinlock_t lock; ++ raw_spinlock_t lock; + struct hlist_head list; + } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; + +@@ -122,17 +123,17 @@ + u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); + struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; + struct kvm_task_sleep_node n, *e; +- DEFINE_WAIT(wait); ++ DECLARE_SWAITQUEUE(wait); + + rcu_irq_enter(); + +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + e = _find_apf_task(b, token); + if (e) { + /* dummy entry exist -> wake up was delivered ahead of PF */ + hlist_del(&e->link); + kfree(e); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + + rcu_irq_exit(); + return; +@@ -141,13 +142,13 @@ + n.token = token; + n.cpu = smp_processor_id(); + n.halted = is_idle_task(current) || preempt_count() > 1; +- init_waitqueue_head(&n.wq); ++ init_swait_queue_head(&n.wq); + hlist_add_head(&n.link, &b->list); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + + for (;;) { + if (!n.halted) +- prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); ++ prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + if (hlist_unhashed(&n.link)) + break; + +@@ -166,7 +167,7 @@ + } + } + if (!n.halted) +- finish_wait(&n.wq, &wait); ++ finish_swait(&n.wq, &wait); + + rcu_irq_exit(); + return; +@@ -178,8 +179,8 @@ + hlist_del_init(&n->link); + if (n->halted) + smp_send_reschedule(n->cpu); +- else if (waitqueue_active(&n->wq)) +- wake_up(&n->wq); ++ else if (swait_active(&n->wq)) ++ swake_up(&n->wq); + } + + static void apf_task_wake_all(void) +@@ -189,14 +190,14 @@ + for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { + struct hlist_node *p, *next; + struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + hlist_for_each_safe(p, next, &b->list) { + struct kvm_task_sleep_node *n = + hlist_entry(p, typeof(*n), link); + if (n->cpu == smp_processor_id()) + apf_task_wake_one(n); + } +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + } + } + +@@ -212,7 +213,7 @@ + } + + again: +- spin_lock(&b->lock); ++ raw_spin_lock(&b->lock); + n = _find_apf_task(b, token); + if (!n) { + /* +@@ -225,17 +226,17 @@ + * Allocation failed! Busy wait while other cpu + * handles async PF. + */ +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + cpu_relax(); + goto again; + } + n->token = token; + n->cpu = smp_processor_id(); +- init_waitqueue_head(&n->wq); ++ init_swait_queue_head(&n->wq); + hlist_add_head(&n->link, &b->list); + } else + apf_task_wake_one(n); +- spin_unlock(&b->lock); ++ raw_spin_unlock(&b->lock); + return; + } + EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); +@@ -486,7 +487,7 @@ + paravirt_ops_setup(); + register_reboot_notifier(&kvm_pv_reboot_nb); + for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) +- spin_lock_init(&async_pf_sleepers[i].lock); ++ raw_spin_lock_init(&async_pf_sleepers[i].lock); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) + x86_init.irqs.trap_init = kvm_apf_trap_init; + +diff -Nur linux-4.4.28.orig/arch/x86/kernel/nmi.c linux-4.4.28/arch/x86/kernel/nmi.c +--- linux-4.4.28.orig/arch/x86/kernel/nmi.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/nmi.c 2016-11-01 21:26:57.660270336 +0100 +@@ -231,7 +231,7 @@ + #endif + + if (panic_on_unrecovered_nmi) +- panic("NMI: Not continuing"); ++ nmi_panic(regs, "NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); + +@@ -255,8 +255,16 @@ + reason, smp_processor_id()); + show_regs(regs); + +- if (panic_on_io_nmi) +- panic("NMI IOCK error: Not continuing"); ++ if (panic_on_io_nmi) { ++ nmi_panic(regs, "NMI IOCK error: Not continuing"); ++ ++ /* ++ * If we end up here, it means we have received an NMI while ++ * processing panic(). Simply return without delaying and ++ * re-enabling NMIs. ++ */ ++ return; ++ } + + /* Re-enable the IOCK line, wait for a few seconds */ + reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; +@@ -297,7 +305,7 @@ + + pr_emerg("Do you have a strange power saving mode enabled?\n"); + if (unknown_nmi_panic || panic_on_unrecovered_nmi) +- panic("NMI: Not continuing"); ++ nmi_panic(regs, "NMI: Not continuing"); + + pr_emerg("Dazed and confused, but trying to continue\n"); + } +diff -Nur linux-4.4.28.orig/arch/x86/kernel/process_32.c linux-4.4.28/arch/x86/kernel/process_32.c +--- linux-4.4.28.orig/arch/x86/kernel/process_32.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/process_32.c 2016-11-01 21:26:57.664270598 +0100 +@@ -35,6 +35,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -210,6 +211,35 @@ + } + EXPORT_SYMBOL_GPL(start_thread); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ pte_t *ptep = kmap_pte - idx; ++ ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++} ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + + /* + * switch_to(x,y) should switch tasks from x to y. +@@ -286,6 +316,8 @@ + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); + ++ switch_kmaps(prev_p, next_p); ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +diff -Nur linux-4.4.28.orig/arch/x86/kernel/reboot.c linux-4.4.28/arch/x86/kernel/reboot.c +--- linux-4.4.28.orig/arch/x86/kernel/reboot.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kernel/reboot.c 2016-11-01 21:26:57.664270598 +0100 +@@ -726,6 +726,7 @@ + static nmi_shootdown_cb shootdown_callback; + + static atomic_t waiting_for_crash_ipi; ++static int crash_ipi_issued; + + static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) + { +@@ -788,6 +789,9 @@ + + smp_send_nmi_allbutself(); + ++ /* Kick CPUs looping in NMI context. */ ++ WRITE_ONCE(crash_ipi_issued, 1); ++ + msecs = 1000; /* Wait at most a second for the other cpus to stop */ + while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { + mdelay(1); +@@ -796,6 +800,22 @@ + + /* Leave the nmi callback set */ + } ++ ++/* Override the weak function in kernel/panic.c */ ++void nmi_panic_self_stop(struct pt_regs *regs) ++{ ++ while (1) { ++ /* ++ * Wait for the crash dumping IPI to be issued, and then ++ * call its callback directly. ++ */ ++ if (READ_ONCE(crash_ipi_issued)) ++ crash_nmi_callback(0, regs); /* Don't return */ ++ ++ cpu_relax(); ++ } ++} ++ + #else /* !CONFIG_SMP */ + void nmi_shootdown_cpus(nmi_shootdown_cb callback) + { +diff -Nur linux-4.4.28.orig/arch/x86/kvm/lapic.c linux-4.4.28/arch/x86/kvm/lapic.c +--- linux-4.4.28.orig/arch/x86/kvm/lapic.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kvm/lapic.c 2016-11-01 21:26:57.672271115 +0100 +@@ -1195,7 +1195,7 @@ + static void apic_timer_expired(struct kvm_lapic *apic) + { + struct kvm_vcpu *vcpu = apic->vcpu; +- wait_queue_head_t *q = &vcpu->wq; ++ struct swait_queue_head *q = &vcpu->wq; + struct kvm_timer *ktimer = &apic->lapic_timer; + + if (atomic_read(&apic->lapic_timer.pending)) +@@ -1204,8 +1204,8 @@ + atomic_inc(&apic->lapic_timer.pending); + kvm_set_pending_timer(vcpu); + +- if (waitqueue_active(q)) +- wake_up_interruptible(q); ++ if (swait_active(q)) ++ swake_up(q); + + if (apic_lvtt_tscdeadline(apic)) + ktimer->expired_tscdeadline = ktimer->tscdeadline; +@@ -1801,6 +1801,7 @@ + hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + apic->lapic_timer.timer.function = apic_timer_fn; ++ apic->lapic_timer.timer.irqsafe = 1; + + /* + * APIC is created enabled. This will prevent kvm_lapic_set_base from +diff -Nur linux-4.4.28.orig/arch/x86/kvm/x86.c linux-4.4.28/arch/x86/kvm/x86.c +--- linux-4.4.28.orig/arch/x86/kvm/x86.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/kvm/x86.c 2016-11-01 21:26:57.732274981 +0100 +@@ -5792,6 +5792,13 @@ + goto out; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { ++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); ++ return -EOPNOTSUPP; ++ } ++#endif ++ + r = kvm_mmu_module_init(); + if (r) + goto out_free_percpu; +diff -Nur linux-4.4.28.orig/arch/x86/mm/highmem_32.c linux-4.4.28/arch/x86/mm/highmem_32.c +--- linux-4.4.28.orig/arch/x86/mm/highmem_32.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/mm/highmem_32.c 2016-11-01 21:26:57.740275502 +0100 +@@ -32,10 +32,11 @@ + */ + void *kmap_atomic_prot(struct page *page, pgprot_t prot) + { ++ pte_t pte = mk_pte(page, prot); + unsigned long vaddr; + int idx, type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -45,7 +46,10 @@ + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); +- set_pte(kmap_pte-idx, mk_pte(page, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte-idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -88,6 +92,9 @@ + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); +@@ -100,7 +107,7 @@ + #endif + + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +diff -Nur linux-4.4.28.orig/arch/x86/mm/iomap_32.c linux-4.4.28/arch/x86/mm/iomap_32.c +--- linux-4.4.28.orig/arch/x86/mm/iomap_32.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/mm/iomap_32.c 2016-11-01 21:26:57.740275502 +0100 +@@ -56,6 +56,7 @@ + + void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + { ++ pte_t pte = pfn_pte(pfn, prot); + unsigned long vaddr; + int idx, type; + +@@ -65,7 +66,12 @@ + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); ++ WARN_ON(!pte_none(*(kmap_pte - idx))); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte - idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -113,6 +119,9 @@ + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + } +diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c linux-4.4.28/arch/x86/platform/uv/tlb_uv.c +--- linux-4.4.28.orig/arch/x86/platform/uv/tlb_uv.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/platform/uv/tlb_uv.c 2016-11-01 21:26:57.768277302 +0100 +@@ -714,9 +714,9 @@ + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -736,9 +736,9 @@ + + quiesce_local_uvhub(hmaster); + +- spin_lock(&hmaster->queue_lock); ++ raw_spin_lock(&hmaster->queue_lock); + reset_with_ipi(&bau_desc->distribution, bcp); +- spin_unlock(&hmaster->queue_lock); ++ raw_spin_unlock(&hmaster->queue_lock); + + end_uvhub_quiesce(hmaster); + +@@ -759,7 +759,7 @@ + cycles_t tm1; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (!bcp->baudisabled) { + stat->s_bau_disabled++; + tm1 = get_cycles(); +@@ -772,7 +772,7 @@ + } + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + } + + static void count_max_concurr(int stat, struct bau_control *bcp, +@@ -835,7 +835,7 @@ + */ + static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat) + { +- spinlock_t *lock = &hmaster->uvhub_lock; ++ raw_spinlock_t *lock = &hmaster->uvhub_lock; + atomic_t *v; + + v = &hmaster->active_descriptor_count; +@@ -968,7 +968,7 @@ + struct bau_control *hmaster; + + hmaster = bcp->uvhub_master; +- spin_lock(&hmaster->disable_lock); ++ raw_spin_lock(&hmaster->disable_lock); + if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) { + stat->s_bau_reenabled++; + for_each_present_cpu(tcpu) { +@@ -980,10 +980,10 @@ + tbcp->period_giveups = 0; + } + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return 0; + } +- spin_unlock(&hmaster->disable_lock); ++ raw_spin_unlock(&hmaster->disable_lock); + return -1; + } + +@@ -1901,9 +1901,9 @@ + bcp->cong_reps = congested_reps; + bcp->disabled_period = sec_2_cycles(disabled_period); + bcp->giveup_limit = giveup_limit; +- spin_lock_init(&bcp->queue_lock); +- spin_lock_init(&bcp->uvhub_lock); +- spin_lock_init(&bcp->disable_lock); ++ raw_spin_lock_init(&bcp->queue_lock); ++ raw_spin_lock_init(&bcp->uvhub_lock); ++ raw_spin_lock_init(&bcp->disable_lock); + } + } + +diff -Nur linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c linux-4.4.28/arch/x86/platform/uv/uv_time.c +--- linux-4.4.28.orig/arch/x86/platform/uv/uv_time.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/arch/x86/platform/uv/uv_time.c 2016-11-01 21:26:57.768277302 +0100 +@@ -57,7 +57,7 @@ + + /* There is one of these allocated per node */ + struct uv_rtc_timer_head { +- spinlock_t lock; ++ raw_spinlock_t lock; + /* next cpu waiting for timer, local node relative: */ + int next_cpu; + /* number of cpus on this node: */ +@@ -177,7 +177,7 @@ + uv_rtc_deallocate_timers(); + return -ENOMEM; + } +- spin_lock_init(&head->lock); ++ raw_spin_lock_init(&head->lock); + head->ncpus = uv_blade_nr_possible_cpus(bid); + head->next_cpu = -1; + blade_info[bid] = head; +@@ -231,7 +231,7 @@ + unsigned long flags; + int next_cpu; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + next_cpu = head->next_cpu; + *t = expires; +@@ -243,12 +243,12 @@ + if (uv_setup_intr(cpu, expires)) { + *t = ULLONG_MAX; + uv_rtc_find_next_timer(head, pnode); +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return -ETIME; + } + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + return 0; + } + +@@ -267,7 +267,7 @@ + unsigned long flags; + int rc = 0; + +- spin_lock_irqsave(&head->lock, flags); ++ raw_spin_lock_irqsave(&head->lock, flags); + + if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) + rc = 1; +@@ -279,7 +279,7 @@ + uv_rtc_find_next_timer(head, pnode); + } + +- spin_unlock_irqrestore(&head->lock, flags); ++ raw_spin_unlock_irqrestore(&head->lock, flags); + + return rc; + } +@@ -299,13 +299,18 @@ + static cycle_t uv_read_rtc(struct clocksource *cs) + { + unsigned long offset; ++ cycle_t cycles; + ++ preempt_disable(); + if (uv_get_min_hub_revision_id() == 1) + offset = 0; + else + offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE; + +- return (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset); ++ preempt_enable(); ++ ++ return cycles; + } + + /* +diff -Nur linux-4.4.28.orig/block/blk-core.c linux-4.4.28/block/blk-core.c +--- linux-4.4.28.orig/block/blk-core.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-core.c 2016-11-01 21:26:57.788278596 +0100 +@@ -125,6 +125,9 @@ + + INIT_LIST_HEAD(&rq->queuelist); + INIT_LIST_HEAD(&rq->timeout_list); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + rq->cpu = -1; + rq->q = q; + rq->__sector = (sector_t) -1; +@@ -233,7 +236,7 @@ + **/ + void blk_start_queue(struct request_queue *q) + { +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + __blk_run_queue(q); +@@ -659,7 +662,7 @@ + if (!gfpflags_allow_blocking(gfp)) + return -EBUSY; + +- ret = wait_event_interruptible(q->mq_freeze_wq, ++ ret = swait_event_interruptible(q->mq_freeze_wq, + !atomic_read(&q->mq_freeze_depth) || + blk_queue_dying(q)); + if (blk_queue_dying(q)) +@@ -679,7 +682,7 @@ + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ swake_up_all(&q->mq_freeze_wq); + } + + struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) +@@ -741,7 +744,7 @@ + q->bypass_depth = 1; + __set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags); + +- init_waitqueue_head(&q->mq_freeze_wq); ++ init_swait_queue_head(&q->mq_freeze_wq); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +@@ -3200,7 +3203,7 @@ + blk_run_queue_async(q); + else + __blk_run_queue(q); +- spin_unlock(q->queue_lock); ++ spin_unlock_irq(q->queue_lock); + } + + static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) +@@ -3248,7 +3251,6 @@ + void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) + { + struct request_queue *q; +- unsigned long flags; + struct request *rq; + LIST_HEAD(list); + unsigned int depth; +@@ -3268,11 +3270,6 @@ + q = NULL; + depth = 0; + +- /* +- * Save and disable interrupts here, to avoid doing it for every +- * queue lock we have to take. +- */ +- local_irq_save(flags); + while (!list_empty(&list)) { + rq = list_entry_rq(list.next); + list_del_init(&rq->queuelist); +@@ -3285,7 +3282,7 @@ + queue_unplugged(q, depth, from_schedule); + q = rq->q; + depth = 0; +- spin_lock(q->queue_lock); ++ spin_lock_irq(q->queue_lock); + } + + /* +@@ -3312,8 +3309,6 @@ + */ + if (q) + queue_unplugged(q, depth, from_schedule); +- +- local_irq_restore(flags); + } + + void blk_finish_plug(struct blk_plug *plug) +diff -Nur linux-4.4.28.orig/block/blk-ioc.c linux-4.4.28/block/blk-ioc.c +--- linux-4.4.28.orig/block/blk-ioc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-ioc.c 2016-11-01 21:26:57.800279369 +0100 +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include "blk.h" + +@@ -109,7 +110,7 @@ + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -187,7 +188,7 @@ + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } +diff -Nur linux-4.4.28.orig/block/blk-iopoll.c linux-4.4.28/block/blk-iopoll.c +--- linux-4.4.28.orig/block/blk-iopoll.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-iopoll.c 2016-11-01 21:26:57.800279369 +0100 +@@ -35,6 +35,7 @@ + list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(blk_iopoll_sched); + +@@ -132,6 +133,7 @@ + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -201,6 +203,7 @@ + this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +diff -Nur linux-4.4.28.orig/block/blk-mq.c linux-4.4.28/block/blk-mq.c +--- linux-4.4.28.orig/block/blk-mq.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-mq.c 2016-11-01 21:26:57.812280143 +0100 +@@ -92,7 +92,7 @@ + + static void blk_mq_freeze_queue_wait(struct request_queue *q) + { +- wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); ++ swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); + } + + /* +@@ -130,7 +130,7 @@ + WARN_ON_ONCE(freeze_depth < 0); + if (!freeze_depth) { + percpu_ref_reinit(&q->q_usage_counter); +- wake_up_all(&q->mq_freeze_wq); ++ swake_up_all(&q->mq_freeze_wq); + } + } + EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +@@ -149,7 +149,7 @@ + * dying, we need to ensure that processes currently waiting on + * the queue are notified as well. + */ +- wake_up_all(&q->mq_freeze_wq); ++ swake_up_all(&q->mq_freeze_wq); + } + + bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) +@@ -196,6 +196,9 @@ + rq->resid_len = 0; + rq->sense = NULL; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + INIT_LIST_HEAD(&rq->timeout_list); + rq->timeout = 0; + +@@ -325,6 +328,17 @@ + } + EXPORT_SYMBOL(blk_mq_end_request); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++void __blk_mq_complete_request_remote_work(struct work_struct *work) ++{ ++ struct request *rq = container_of(work, struct request, work); ++ ++ rq->q->softirq_done_fn(rq); ++} ++ ++#else ++ + static void __blk_mq_complete_request_remote(void *data) + { + struct request *rq = data; +@@ -332,6 +346,8 @@ + rq->q->softirq_done_fn(rq); + } + ++#endif ++ + static void blk_mq_ipi_complete_request(struct request *rq) + { + struct blk_mq_ctx *ctx = rq->mq_ctx; +@@ -343,19 +359,23 @@ + return; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + shared = cpus_share_cache(cpu, ctx->cpu); + + if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ schedule_work_on(ctx->cpu, &rq->work); ++#else + rq->csd.func = __blk_mq_complete_request_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + smp_call_function_single_async(ctx->cpu, &rq->csd); ++#endif + } else { + rq->q->softirq_done_fn(rq); + } +- put_cpu(); ++ put_cpu_light(); + } + + static void __blk_mq_complete_request(struct request *rq) +@@ -864,14 +884,14 @@ + return; + + if (!async) { +- int cpu = get_cpu(); ++ int cpu = get_cpu_light(); + if (cpumask_test_cpu(cpu, hctx->cpumask)) { + __blk_mq_run_hw_queue(hctx); +- put_cpu(); ++ put_cpu_light(); + return; + } + +- put_cpu(); ++ put_cpu_light(); + } + + kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx), +@@ -1619,7 +1639,7 @@ + { + struct blk_mq_hw_ctx *hctx = data; + +- if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) ++ if (action == CPU_POST_DEAD) + return blk_mq_hctx_cpu_offline(hctx, cpu); + + /* +diff -Nur linux-4.4.28.orig/block/blk-mq-cpu.c linux-4.4.28/block/blk-mq-cpu.c +--- linux-4.4.28.orig/block/blk-mq-cpu.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-mq-cpu.c 2016-11-01 21:26:57.800279369 +0100 +@@ -16,7 +16,7 @@ + #include "blk-mq.h" + + static LIST_HEAD(blk_mq_cpu_notify_list); +-static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock); ++static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock); + + static int blk_mq_main_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +@@ -25,7 +25,10 @@ + struct blk_mq_cpu_notifier *notify; + int ret = NOTIFY_OK; + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ if (action != CPU_POST_DEAD) ++ return NOTIFY_OK; ++ ++ spin_lock(&blk_mq_cpu_notify_lock); + + list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) { + ret = notify->notify(notify->data, action, cpu); +@@ -33,7 +36,7 @@ + break; + } + +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + return ret; + } + +@@ -41,16 +44,16 @@ + { + BUG_ON(!notifier->notify); + +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_add_tail(¬ifier->list, &blk_mq_cpu_notify_list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier) + { +- raw_spin_lock(&blk_mq_cpu_notify_lock); ++ spin_lock(&blk_mq_cpu_notify_lock); + list_del(¬ifier->list); +- raw_spin_unlock(&blk_mq_cpu_notify_lock); ++ spin_unlock(&blk_mq_cpu_notify_lock); + } + + void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, +diff -Nur linux-4.4.28.orig/block/blk-mq.h linux-4.4.28/block/blk-mq.h +--- linux-4.4.28.orig/block/blk-mq.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-mq.h 2016-11-01 21:26:57.812280143 +0100 +@@ -74,7 +74,10 @@ + static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, + unsigned int cpu) + { +- return per_cpu_ptr(q->queue_ctx, cpu); ++ struct blk_mq_ctx *ctx; ++ ++ ctx = per_cpu_ptr(q->queue_ctx, cpu); ++ return ctx; + } + + /* +@@ -85,12 +88,12 @@ + */ + static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) + { +- return __blk_mq_get_ctx(q, get_cpu()); ++ return __blk_mq_get_ctx(q, get_cpu_light()); + } + + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- put_cpu(); ++ put_cpu_light(); + } + + struct blk_mq_alloc_data { +diff -Nur linux-4.4.28.orig/block/blk-softirq.c linux-4.4.28/block/blk-softirq.c +--- linux-4.4.28.orig/block/blk-softirq.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/blk-softirq.c 2016-11-01 21:26:57.812280143 +0100 +@@ -51,6 +51,7 @@ + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -93,6 +94,7 @@ + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + return NOTIFY_OK; +@@ -150,6 +152,7 @@ + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /** +diff -Nur linux-4.4.28.orig/block/bounce.c linux-4.4.28/block/bounce.c +--- linux-4.4.28.orig/block/bounce.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/block/bounce.c 2016-11-01 21:26:57.812280143 +0100 +@@ -55,11 +55,11 @@ + unsigned long flags; + unsigned char *vto; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + vto = kmap_atomic(to->bv_page); + memcpy(vto + to->bv_offset, vfrom, to->bv_len); + kunmap_atomic(vto); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + #else /* CONFIG_HIGHMEM */ +diff -Nur linux-4.4.28.orig/crypto/algapi.c linux-4.4.28/crypto/algapi.c +--- linux-4.4.28.orig/crypto/algapi.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/crypto/algapi.c 2016-11-01 21:26:57.824280917 +0100 +@@ -719,13 +719,13 @@ + + int crypto_register_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_register(&crypto_chain, nb); ++ return srcu_notifier_chain_register(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_register_notifier); + + int crypto_unregister_notifier(struct notifier_block *nb) + { +- return blocking_notifier_chain_unregister(&crypto_chain, nb); ++ return srcu_notifier_chain_unregister(&crypto_chain, nb); + } + EXPORT_SYMBOL_GPL(crypto_unregister_notifier); + +diff -Nur linux-4.4.28.orig/crypto/api.c linux-4.4.28/crypto/api.c +--- linux-4.4.28.orig/crypto/api.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/crypto/api.c 2016-11-01 21:26:57.828281169 +0100 +@@ -31,7 +31,7 @@ + DECLARE_RWSEM(crypto_alg_sem); + EXPORT_SYMBOL_GPL(crypto_alg_sem); + +-BLOCKING_NOTIFIER_HEAD(crypto_chain); ++SRCU_NOTIFIER_HEAD(crypto_chain); + EXPORT_SYMBOL_GPL(crypto_chain); + + static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg); +@@ -236,10 +236,10 @@ + { + int ok; + +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + if (ok == NOTIFY_DONE) { + request_module("cryptomgr"); +- ok = blocking_notifier_call_chain(&crypto_chain, val, v); ++ ok = srcu_notifier_call_chain(&crypto_chain, val, v); + } + + return ok; +diff -Nur linux-4.4.28.orig/crypto/internal.h linux-4.4.28/crypto/internal.h +--- linux-4.4.28.orig/crypto/internal.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/crypto/internal.h 2016-11-01 21:26:57.832281426 +0100 +@@ -47,7 +47,7 @@ + + extern struct list_head crypto_alg_list; + extern struct rw_semaphore crypto_alg_sem; +-extern struct blocking_notifier_head crypto_chain; ++extern struct srcu_notifier_head crypto_chain; + + #ifdef CONFIG_PROC_FS + void __init crypto_init_proc(void); +@@ -143,7 +143,7 @@ + + static inline void crypto_notify(unsigned long val, void *v) + { +- blocking_notifier_call_chain(&crypto_chain, val, v); ++ srcu_notifier_call_chain(&crypto_chain, val, v); + } + + #endif /* _CRYPTO_INTERNAL_H */ +diff -Nur linux-4.4.28.orig/Documentation/hwlat_detector.txt linux-4.4.28/Documentation/hwlat_detector.txt +--- linux-4.4.28.orig/Documentation/hwlat_detector.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/Documentation/hwlat_detector.txt 2016-11-01 21:26:56.600202005 +0100 +@@ -0,0 +1,64 @@ ++Introduction: ++------------- ++ ++The module hwlat_detector is a special purpose kernel module that is used to ++detect large system latencies induced by the behavior of certain underlying ++hardware or firmware, independent of Linux itself. The code was developed ++originally to detect SMIs (System Management Interrupts) on x86 systems, ++however there is nothing x86 specific about this patchset. It was ++originally written for use by the "RT" patch since the Real Time ++kernel is highly latency sensitive. ++ ++SMIs are usually not serviced by the Linux kernel, which typically does not ++even know that they are occuring. SMIs are instead are set up by BIOS code ++and are serviced by BIOS code, usually for "critical" events such as ++management of thermal sensors and fans. Sometimes though, SMIs are used for ++other tasks and those tasks can spend an inordinate amount of time in the ++handler (sometimes measured in milliseconds). Obviously this is a problem if ++you are trying to keep event service latencies down in the microsecond range. ++ ++The hardware latency detector works by hogging all of the cpus for configurable ++amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter ++for some period, then looking for gaps in the TSC data. Any gap indicates a ++time when the polling was interrupted and since the machine is stopped and ++interrupts turned off the only thing that could do that would be an SMI. ++ ++Note that the SMI detector should *NEVER* be used in a production environment. ++It is intended to be run manually to determine if the hardware platform has a ++problem with long system firmware service routines. ++ ++Usage: ++------ ++ ++Loading the module hwlat_detector passing the parameter "enabled=1" (or by ++setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only ++step required to start the hwlat_detector. It is possible to redefine the ++threshold in microseconds (us) above which latency spikes will be taken ++into account (parameter "threshold="). ++ ++Example: ++ ++ # modprobe hwlat_detector enabled=1 threshold=100 ++ ++After the module is loaded, it creates a directory named "hwlat_detector" under ++the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary ++to have debugfs mounted, which might be on /sys/debug on your system. ++ ++The /debug/hwlat_detector interface contains the following files: ++ ++count - number of latency spikes observed since last reset ++enable - a global enable/disable toggle (0/1), resets count ++max - maximum hardware latency actually observed (usecs) ++sample - a pipe from which to read current raw sample data ++ in the format ++ (can be opened O_NONBLOCK for a single sample) ++threshold - minimum latency value to be considered (usecs) ++width - time period to sample with CPUs held (usecs) ++ must be less than the total window size (enforced) ++window - total period of sampling, width being inside (usecs) ++ ++By default we will set width to 500,000 and window to 1,000,000, meaning that ++we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we ++observe any latencies that exceed the threshold (initially 100 usecs), ++then we write to a global sample ring buffer of 8K samples, which is ++consumed by reading from the "sample" (pipe) debugfs file interface. +diff -Nur linux-4.4.28.orig/Documentation/kernel-parameters.txt linux-4.4.28/Documentation/kernel-parameters.txt +--- linux-4.4.28.orig/Documentation/kernel-parameters.txt 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/Documentation/kernel-parameters.txt 2016-11-01 21:26:56.640204584 +0100 +@@ -1636,6 +1636,15 @@ + ip= [IP_PNP] + See Documentation/filesystems/nfs/nfsroot.txt. + ++ irqaffinity= [SMP] Set the default irq affinity mask ++ Format: ++ ,..., ++ or ++ - ++ (must be a positive range in ascending order) ++ or a mixture ++ ,...,- ++ + irqfixup [HW] + When an interrupt is not handled search all handlers + for it. Intended to get systems with badly broken +diff -Nur linux-4.4.28.orig/Documentation/sysrq.txt linux-4.4.28/Documentation/sysrq.txt +--- linux-4.4.28.orig/Documentation/sysrq.txt 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/Documentation/sysrq.txt 2016-11-01 21:26:56.652205360 +0100 +@@ -59,10 +59,17 @@ + On other - If you know of the key combos for other architectures, please + let me know so I can add them to this section. + +-On all - write a character to /proc/sysrq-trigger. e.g.: +- ++On all - write a character to /proc/sysrq-trigger, e.g.: + echo t > /proc/sysrq-trigger + ++On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g. ++ echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq ++ Send an ICMP echo request with this pattern plus the particular ++ SysRq command key. Example: ++ # ping -c1 -s57 -p0102030468 ++ will trigger the SysRq-H (help) command. ++ ++ + * What are the 'command' keys? + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 'b' - Will immediately reboot the system without syncing or unmounting +diff -Nur linux-4.4.28.orig/Documentation/trace/histograms.txt linux-4.4.28/Documentation/trace/histograms.txt +--- linux-4.4.28.orig/Documentation/trace/histograms.txt 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/Documentation/trace/histograms.txt 2016-11-01 21:26:56.672206655 +0100 +@@ -0,0 +1,186 @@ ++ Using the Linux Kernel Latency Histograms ++ ++ ++This document gives a short explanation how to enable, configure and use ++latency histograms. Latency histograms are primarily relevant in the ++context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT) ++and are used in the quality management of the Linux real-time ++capabilities. ++ ++ ++* Purpose of latency histograms ++ ++A latency histogram continuously accumulates the frequencies of latency ++data. There are two types of histograms ++- potential sources of latencies ++- effective latencies ++ ++ ++* Potential sources of latencies ++ ++Potential sources of latencies are code segments where interrupts, ++preemption or both are disabled (aka critical sections). To create ++histograms of potential sources of latency, the kernel stores the time ++stamp at the start of a critical section, determines the time elapsed ++when the end of the section is reached, and increments the frequency ++counter of that latency value - irrespective of whether any concurrently ++running process is affected by latency or not. ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_INTERRUPT_OFF_LATENCY ++ CONFIG_PREEMPT_OFF_LATENCY ++ ++ ++* Effective latencies ++ ++Effective latencies are actually occuring during wakeup of a process. To ++determine effective latencies, the kernel stores the time stamp when a ++process is scheduled to be woken up, and determines the duration of the ++wakeup time shortly before control is passed over to this process. Note ++that the apparent latency in user space may be somewhat longer, since the ++process may be interrupted after control is passed over to it but before ++the execution in user space takes place. Simply measuring the interval ++between enqueuing and wakeup may also not appropriate in cases when a ++process is scheduled as a result of a timer expiration. The timer may have ++missed its deadline, e.g. due to disabled interrupts, but this latency ++would not be registered. Therefore, the offsets of missed timers are ++recorded in a separate histogram. If both wakeup latency and missed timer ++offsets are configured and enabled, a third histogram may be enabled that ++records the overall latency as a sum of the timer latency, if any, and the ++wakeup latency. This histogram is called "timerandwakeup". ++- Configuration items (in the Kernel hacking/Tracers submenu) ++ CONFIG_WAKEUP_LATENCY ++ CONFIG_MISSED_TIMER_OFSETS ++ ++ ++* Usage ++ ++The interface to the administration of the latency histograms is located ++in the debugfs file system. To mount it, either enter ++ ++mount -t sysfs nodev /sys ++mount -t debugfs nodev /sys/kernel/debug ++ ++from shell command line level, or add ++ ++nodev /sys sysfs defaults 0 0 ++nodev /sys/kernel/debug debugfs defaults 0 0 ++ ++to the file /etc/fstab. All latency histogram related files are then ++available in the directory /sys/kernel/debug/tracing/latency_hist. A ++particular histogram type is enabled by writing non-zero to the related ++variable in the /sys/kernel/debug/tracing/latency_hist/enable directory. ++Select "preemptirqsoff" for the histograms of potential sources of ++latencies and "wakeup" for histograms of effective latencies etc. The ++histogram data - one per CPU - are available in the files ++ ++/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx ++/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx ++/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx ++/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx ++ ++The histograms are reset by writing non-zero to the file "reset" in a ++particular latency directory. To reset all latency data, use ++ ++#!/bin/sh ++ ++TRACINGDIR=/sys/kernel/debug/tracing ++HISTDIR=$TRACINGDIR/latency_hist ++ ++if test -d $HISTDIR ++then ++ cd $HISTDIR ++ for i in `find . | grep /reset$` ++ do ++ echo 1 >$i ++ done ++fi ++ ++ ++* Data format ++ ++Latency data are stored with a resolution of one microsecond. The ++maximum latency is 10,240 microseconds. The data are only valid, if the ++overflow register is empty. Every output line contains the latency in ++microseconds in the first row and the number of samples in the second ++row. To display only lines with a positive latency count, use, for ++example, ++ ++grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0 ++ ++#Minimum latency: 0 microseconds. ++#Average latency: 0 microseconds. ++#Maximum latency: 25 microseconds. ++#Total samples: 3104770694 ++#There are 0 samples greater or equal than 10240 microseconds ++#usecs samples ++ 0 2984486876 ++ 1 49843506 ++ 2 58219047 ++ 3 5348126 ++ 4 2187960 ++ 5 3388262 ++ 6 959289 ++ 7 208294 ++ 8 40420 ++ 9 4485 ++ 10 14918 ++ 11 18340 ++ 12 25052 ++ 13 19455 ++ 14 5602 ++ 15 969 ++ 16 47 ++ 17 18 ++ 18 14 ++ 19 1 ++ 20 3 ++ 21 2 ++ 22 5 ++ 23 2 ++ 25 1 ++ ++ ++* Wakeup latency of a selected process ++ ++To only collect wakeup latency data of a particular process, write the ++PID of the requested process to ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/pid ++ ++PIDs are not considered, if this variable is set to 0. ++ ++ ++* Details of the process with the highest wakeup latency so far ++ ++Selected data of the process that suffered from the highest wakeup ++latency that occurred in a particular CPU are available in the file ++ ++/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx. ++ ++In addition, other relevant system data at the time when the ++latency occurred are given. ++ ++The format of the data is (all in one line): ++ () \ ++<- ++ ++The value of is only relevant in the combined timer ++and wakeup latency recording. In the wakeup recording, it is ++always 0, in the missed_timer_offsets recording, it is the same ++as . ++ ++When retrospectively searching for the origin of a latency and ++tracing was not enabled, it may be helpful to know the name and ++some basic data of the task that (finally) was switching to the ++late real-tlme task. In addition to the victim's data, also the ++data of the possible culprit are therefore displayed after the ++"<-" symbol. ++ ++Finally, the timestamp of the time when the latency occurred ++in . after the most recent system boot ++is provided. ++ ++These data are also reset when the wakeup histogram is reset. +diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h linux-4.4.28/drivers/acpi/acpica/acglobal.h +--- linux-4.4.28.orig/drivers/acpi/acpica/acglobal.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/acpi/acpica/acglobal.h 2016-11-01 21:26:57.844282199 +0100 +@@ -116,7 +116,7 @@ + * interrupt level + */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */ +-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ ++ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */ + ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock); + + /* Mutex for _OSI support */ +diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c linux-4.4.28/drivers/acpi/acpica/hwregs.c +--- linux-4.4.28.orig/drivers/acpi/acpica/hwregs.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/acpi/acpica/hwregs.c 2016-11-01 21:26:57.852282717 +0100 +@@ -269,14 +269,14 @@ + ACPI_BITMASK_ALL_FIXED_STATUS, + ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address))); + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* Clear the fixed events in PM1 A/B */ + + status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS, + ACPI_BITMASK_ALL_FIXED_STATUS); + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + + if (ACPI_FAILURE(status)) { + goto exit; +diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c linux-4.4.28/drivers/acpi/acpica/hwxface.c +--- linux-4.4.28.orig/drivers/acpi/acpica/hwxface.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/acpi/acpica/hwxface.c 2016-11-01 21:26:57.852282717 +0100 +@@ -374,7 +374,7 @@ + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + +- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock); ++ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags); + + /* + * At this point, we know that the parent register is one of the +@@ -435,7 +435,7 @@ + + unlock_and_exit: + +- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags); ++ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags); + return_ACPI_STATUS(status); + } + +diff -Nur linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c linux-4.4.28/drivers/acpi/acpica/utmutex.c +--- linux-4.4.28.orig/drivers/acpi/acpica/utmutex.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/acpi/acpica/utmutex.c 2016-11-01 21:26:57.864283490 +0100 +@@ -88,7 +88,7 @@ + return_ACPI_STATUS (status); + } + +- status = acpi_os_create_lock (&acpi_gbl_hardware_lock); ++ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock); + if (ACPI_FAILURE (status)) { + return_ACPI_STATUS (status); + } +@@ -156,7 +156,7 @@ + /* Delete the spinlocks */ + + acpi_os_delete_lock(acpi_gbl_gpe_lock); +- acpi_os_delete_lock(acpi_gbl_hardware_lock); ++ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock); + acpi_os_delete_lock(acpi_gbl_reference_count_lock); + + /* Delete the reader/writer lock */ +diff -Nur linux-4.4.28.orig/drivers/ata/libata-sff.c linux-4.4.28/drivers/ata/libata-sff.c +--- linux-4.4.28.orig/drivers/ata/libata-sff.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ata/libata-sff.c 2016-11-01 21:26:57.884284784 +0100 +@@ -678,9 +678,9 @@ + unsigned long flags; + unsigned int consumed; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + consumed = ata_sff_data_xfer32(dev, buf, buflen, rw); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + return consumed; + } +@@ -719,7 +719,7 @@ + unsigned long flags; + + /* FIXME: use a bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -727,7 +727,7 @@ + do_write); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size, +@@ -864,7 +864,7 @@ + unsigned long flags; + + /* FIXME: use bounce buffer */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + buf = kmap_atomic(page); + + /* do the actual data transfer */ +@@ -872,7 +872,7 @@ + count, rw); + + kunmap_atomic(buf); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } else { + buf = page_address(page); + consumed = ap->ops->sff_data_xfer(dev, buf + offset, +diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.c linux-4.4.28/drivers/block/zram/zram_drv.c +--- linux-4.4.28.orig/drivers/block/zram/zram_drv.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/block/zram/zram_drv.c 2016-11-01 21:26:57.892285294 +0100 +@@ -520,6 +520,8 @@ + goto out_error; + } + ++ zram_meta_init_table_locks(meta, disksize); ++ + return meta; + + out_error: +@@ -568,12 +570,12 @@ + unsigned long handle; + size_t size; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + handle = meta->table[index].handle; + size = zram_get_obj_size(meta, index); + + if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) { +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + clear_page(mem); + return 0; + } +@@ -584,7 +586,7 @@ + else + ret = zcomp_decompress(zram->comp, cmem, size, mem); + zs_unmap_object(meta->mem_pool, handle); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + /* Should NEVER happen. Return bio error if it does. */ + if (unlikely(ret)) { +@@ -604,14 +606,14 @@ + struct zram_meta *meta = zram->meta; + page = bvec->bv_page; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + if (unlikely(!meta->table[index].handle) || + zram_test_flag(meta, index, ZRAM_ZERO)) { +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + handle_zero_page(bvec); + return 0; + } +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + if (is_partial_io(bvec)) + /* Use a temporary buffer to decompress the page */ +@@ -689,10 +691,10 @@ + if (user_mem) + kunmap_atomic(user_mem); + /* Free memory associated with this sector now. */ +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); + zram_set_flag(meta, index, ZRAM_ZERO); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + atomic64_inc(&zram->stats.zero_pages); + ret = 0; +@@ -752,12 +754,12 @@ + * Free memory associated with this sector + * before overwriting unused sectors. + */ +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); + + meta->table[index].handle = handle; + zram_set_obj_size(meta, index, clen); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + + /* Update stats */ + atomic64_add(clen, &zram->stats.compr_data_size); +@@ -800,9 +802,9 @@ + } + + while (n >= PAGE_SIZE) { +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + atomic64_inc(&zram->stats.notify_free); + index++; + n -= PAGE_SIZE; +@@ -928,9 +930,9 @@ + zram = bdev->bd_disk->private_data; + meta = zram->meta; + +- bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_lock_table(&meta->table[index]); + zram_free_page(zram, index); +- bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); ++ zram_unlock_table(&meta->table[index]); + atomic64_inc(&zram->stats.notify_free); + } + +diff -Nur linux-4.4.28.orig/drivers/block/zram/zram_drv.h linux-4.4.28/drivers/block/zram/zram_drv.h +--- linux-4.4.28.orig/drivers/block/zram/zram_drv.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/block/zram/zram_drv.h 2016-11-01 21:26:57.892285294 +0100 +@@ -72,6 +72,9 @@ + struct zram_table_entry { + unsigned long handle; + unsigned long value; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t lock; ++#endif + }; + + struct zram_stats { +@@ -119,4 +122,42 @@ + */ + bool claim; /* Protected by bdev->bd_mutex */ + }; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++static inline void zram_lock_table(struct zram_table_entry *table) ++{ ++ bit_spin_lock(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_unlock_table(struct zram_table_entry *table) ++{ ++ bit_spin_unlock(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) { } ++#else /* CONFIG_PREEMPT_RT_BASE */ ++static inline void zram_lock_table(struct zram_table_entry *table) ++{ ++ spin_lock(&table->lock); ++ __set_bit(ZRAM_ACCESS, &table->value); ++} ++ ++static inline void zram_unlock_table(struct zram_table_entry *table) ++{ ++ __clear_bit(ZRAM_ACCESS, &table->value); ++ spin_unlock(&table->lock); ++} ++ ++static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) ++{ ++ size_t num_pages = disksize >> PAGE_SHIFT; ++ size_t index; ++ ++ for (index = 0; index < num_pages; index++) { ++ spinlock_t *lock = &meta->table[index].lock; ++ spin_lock_init(lock); ++ } ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + #endif +diff -Nur linux-4.4.28.orig/drivers/char/random.c linux-4.4.28/drivers/char/random.c +--- linux-4.4.28.orig/drivers/char/random.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/char/random.c 2016-11-01 21:26:57.900285811 +0100 +@@ -799,8 +799,6 @@ + } sample; + long delta, delta2, delta3; + +- preempt_disable(); +- + sample.jiffies = jiffies; + sample.cycles = random_get_entropy(); + sample.num = num; +@@ -841,7 +839,6 @@ + */ + credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); + } +- preempt_enable(); + } + + void add_input_randomness(unsigned int type, unsigned int code, +@@ -894,28 +891,27 @@ + return *(ptr + f->reg_idx++); + } + +-void add_interrupt_randomness(int irq, int irq_flags) ++void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) + { + struct entropy_store *r; + struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); +- struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + cycles_t cycles = random_get_entropy(); + __u32 c_high, j_high; +- __u64 ip; + unsigned long seed; + int credit = 0; + + if (cycles == 0) +- cycles = get_reg(fast_pool, regs); ++ cycles = get_reg(fast_pool, NULL); + c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; + j_high = (sizeof(now) > 4) ? now >> 32 : 0; + fast_pool->pool[0] ^= cycles ^ j_high ^ irq; + fast_pool->pool[1] ^= now ^ c_high; +- ip = regs ? instruction_pointer(regs) : _RET_IP_; ++ if (!ip) ++ ip = _RET_IP_; + fast_pool->pool[2] ^= ip; + fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : +- get_reg(fast_pool, regs); ++ get_reg(fast_pool, NULL); + + fast_mix(fast_pool); + add_interrupt_bench(cycles); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-generated.c linux-4.4.28/drivers/clk/at91/clk-generated.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-generated.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-generated.c 2016-11-01 21:26:57.916286841 +0100 +@@ -15,8 +15,8 @@ + #include + #include + #include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -28,8 +28,9 @@ + + struct clk_generated { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + struct clk_range range; ++ spinlock_t *lock; + u32 id; + u32 gckdiv; + u8 parent_id; +@@ -41,49 +42,52 @@ + static int clk_generated_enable(struct clk_hw *hw) + { + struct clk_generated *gck = to_clk_generated(hw); +- struct at91_pmc *pmc = gck->pmc; +- u32 tmp; ++ unsigned long flags; + + pr_debug("GCLK: %s, gckdiv = %d, parent id = %d\n", + __func__, gck->gckdiv, gck->parent_id); + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR) & +- ~(AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK); +- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_GCKCSS(gck->parent_id) +- | AT91_PMC_PCR_CMD +- | AT91_PMC_PCR_GCKDIV(gck->gckdiv) +- | AT91_PMC_PCR_GCKEN); +- pmc_unlock(pmc); ++ spin_lock_irqsave(gck->lock, flags); ++ regmap_write(gck->regmap, AT91_PMC_PCR, ++ (gck->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_update_bits(gck->regmap, AT91_PMC_PCR, ++ AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK | ++ AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN, ++ AT91_PMC_PCR_GCKCSS(gck->parent_id) | ++ AT91_PMC_PCR_CMD | ++ AT91_PMC_PCR_GCKDIV(gck->gckdiv) | ++ AT91_PMC_PCR_GCKEN); ++ spin_unlock_irqrestore(gck->lock, flags); + return 0; + } + + static void clk_generated_disable(struct clk_hw *hw) + { + struct clk_generated *gck = to_clk_generated(hw); +- struct at91_pmc *pmc = gck->pmc; +- u32 tmp; ++ unsigned long flags; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_GCKEN; +- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD); +- pmc_unlock(pmc); ++ spin_lock_irqsave(gck->lock, flags); ++ regmap_write(gck->regmap, AT91_PMC_PCR, ++ (gck->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_update_bits(gck->regmap, AT91_PMC_PCR, ++ AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN, ++ AT91_PMC_PCR_CMD); ++ spin_unlock_irqrestore(gck->lock, flags); + } + + static int clk_generated_is_enabled(struct clk_hw *hw) + { + struct clk_generated *gck = to_clk_generated(hw); +- struct at91_pmc *pmc = gck->pmc; +- int ret; ++ unsigned long flags; ++ unsigned int status; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); +- ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_GCKEN); +- pmc_unlock(pmc); ++ spin_lock_irqsave(gck->lock, flags); ++ regmap_write(gck->regmap, AT91_PMC_PCR, ++ (gck->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_read(gck->regmap, AT91_PMC_PCR, &status); ++ spin_unlock_irqrestore(gck->lock, flags); + +- return ret; ++ return status & AT91_PMC_PCR_GCKEN ? 1 : 0; + } + + static unsigned long +@@ -214,13 +218,14 @@ + */ + static void clk_generated_startup(struct clk_generated *gck) + { +- struct at91_pmc *pmc = gck->pmc; + u32 tmp; ++ unsigned long flags; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR); +- pmc_unlock(pmc); ++ spin_lock_irqsave(gck->lock, flags); ++ regmap_write(gck->regmap, AT91_PMC_PCR, ++ (gck->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_read(gck->regmap, AT91_PMC_PCR, &tmp); ++ spin_unlock_irqrestore(gck->lock, flags); + + gck->parent_id = (tmp & AT91_PMC_PCR_GCKCSS_MASK) + >> AT91_PMC_PCR_GCKCSS_OFFSET; +@@ -229,8 +234,8 @@ + } + + static struct clk * __init +-at91_clk_register_generated(struct at91_pmc *pmc, const char *name, +- const char **parent_names, u8 num_parents, ++at91_clk_register_generated(struct regmap *regmap, spinlock_t *lock, const char ++ *name, const char **parent_names, u8 num_parents, + u8 id, const struct clk_range *range) + { + struct clk_generated *gck; +@@ -249,7 +254,8 @@ + + gck->id = id; + gck->hw.init = &init; +- gck->pmc = pmc; ++ gck->regmap = regmap; ++ gck->lock = lock; + gck->range = *range; + + clk = clk_register(NULL, &gck->hw); +@@ -261,8 +267,7 @@ + return clk; + } + +-void __init of_sama5d2_clk_generated_setup(struct device_node *np, +- struct at91_pmc *pmc) ++void __init of_sama5d2_clk_generated_setup(struct device_node *np) + { + int num; + u32 id; +@@ -272,6 +277,7 @@ + const char *parent_names[GENERATED_SOURCE_MAX]; + struct device_node *gcknp; + struct clk_range range = CLK_RANGE(0, 0); ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > GENERATED_SOURCE_MAX) +@@ -283,6 +289,10 @@ + if (!num || num > PERIPHERAL_MAX) + return; + ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ + for_each_child_of_node(np, gcknp) { + if (of_property_read_u32(gcknp, "reg", &id)) + continue; +@@ -296,11 +306,14 @@ + of_at91_get_clk_range(gcknp, "atmel,clk-output-range", + &range); + +- clk = at91_clk_register_generated(pmc, name, parent_names, +- num_parents, id, &range); ++ clk = at91_clk_register_generated(regmap, &pmc_pcr_lock, name, ++ parent_names, num_parents, ++ id, &range); + if (IS_ERR(clk)) + continue; + + of_clk_add_provider(gcknp, of_clk_src_simple_get, clk); + } + } ++CLK_OF_DECLARE(of_sama5d2_clk_generated_setup, "atmel,sama5d2-clk-generated", ++ of_sama5d2_clk_generated_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c linux-4.4.28/drivers/clk/at91/clk-h32mx.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-h32mx.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-h32mx.c 2016-11-01 21:26:57.916286841 +0100 +@@ -15,15 +15,9 @@ + #include + #include + #include +-#include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -31,7 +25,7 @@ + + struct clk_sama5d4_h32mx { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + #define to_clk_sama5d4_h32mx(hw) container_of(hw, struct clk_sama5d4_h32mx, hw) +@@ -40,8 +34,10 @@ + unsigned long parent_rate) + { + struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw); ++ unsigned int mckr; + +- if (pmc_read(h32mxclk->pmc, AT91_PMC_MCKR) & AT91_PMC_H32MXDIV) ++ regmap_read(h32mxclk->regmap, AT91_PMC_MCKR, &mckr); ++ if (mckr & AT91_PMC_H32MXDIV) + return parent_rate / 2; + + if (parent_rate > H32MX_MAX_FREQ) +@@ -70,18 +66,16 @@ + unsigned long parent_rate) + { + struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw); +- struct at91_pmc *pmc = h32mxclk->pmc; +- u32 tmp; ++ u32 mckr = 0; + + if (parent_rate != rate && (parent_rate / 2) != rate) + return -EINVAL; + +- pmc_lock(pmc); +- tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_H32MXDIV; + if ((parent_rate / 2) == rate) +- tmp |= AT91_PMC_H32MXDIV; +- pmc_write(pmc, AT91_PMC_MCKR, tmp); +- pmc_unlock(pmc); ++ mckr = AT91_PMC_H32MXDIV; ++ ++ regmap_update_bits(h32mxclk->regmap, AT91_PMC_MCKR, ++ AT91_PMC_H32MXDIV, mckr); + + return 0; + } +@@ -92,14 +86,18 @@ + .set_rate = clk_sama5d4_h32mx_set_rate, + }; + +-void __init of_sama5d4_clk_h32mx_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_sama5d4_clk_h32mx_setup(struct device_node *np) + { + struct clk_sama5d4_h32mx *h32mxclk; + struct clk_init_data init; + const char *parent_name; ++ struct regmap *regmap; + struct clk *clk; + ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ + h32mxclk = kzalloc(sizeof(*h32mxclk), GFP_KERNEL); + if (!h32mxclk) + return; +@@ -113,7 +111,7 @@ + init.flags = CLK_SET_RATE_GATE; + + h32mxclk->hw.init = &init; +- h32mxclk->pmc = pmc; ++ h32mxclk->regmap = regmap; + + clk = clk_register(NULL, &h32mxclk->hw); + if (IS_ERR(clk)) { +@@ -123,3 +121,5 @@ + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(of_sama5d4_clk_h32mx_setup, "atmel,sama5d4-clk-h32mx", ++ of_sama5d4_clk_h32mx_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-main.c linux-4.4.28/drivers/clk/at91/clk-main.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-main.c 2016-11-01 21:26:57.920287105 +0100 +@@ -13,13 +13,8 @@ + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -34,18 +29,14 @@ + + struct clk_main_osc { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + }; + + #define to_clk_main_osc(hw) container_of(hw, struct clk_main_osc, hw) + + struct clk_main_rc_osc { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + unsigned long frequency; + unsigned long accuracy; + }; +@@ -54,51 +45,47 @@ + + struct clk_rm9200_main { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + #define to_clk_rm9200_main(hw) container_of(hw, struct clk_rm9200_main, hw) + + struct clk_sam9x5_main { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + u8 parent; + }; + + #define to_clk_sam9x5_main(hw) container_of(hw, struct clk_sam9x5_main, hw) + +-static irqreturn_t clk_main_osc_irq_handler(int irq, void *dev_id) ++static inline bool clk_main_osc_ready(struct regmap *regmap) + { +- struct clk_main_osc *osc = dev_id; ++ unsigned int status; + +- wake_up(&osc->wait); +- disable_irq_nosync(osc->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & AT91_PMC_MOSCS; + } + + static int clk_main_osc_prepare(struct clk_hw *hw) + { + struct clk_main_osc *osc = to_clk_main_osc(hw); +- struct at91_pmc *pmc = osc->pmc; ++ struct regmap *regmap = osc->regmap; + u32 tmp; + +- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; ++ regmap_read(regmap, AT91_CKGR_MOR, &tmp); ++ tmp &= ~MOR_KEY_MASK; ++ + if (tmp & AT91_PMC_OSCBYPASS) + return 0; + + if (!(tmp & AT91_PMC_MOSCEN)) { + tmp |= AT91_PMC_MOSCEN | AT91_PMC_KEY; +- pmc_write(pmc, AT91_CKGR_MOR, tmp); ++ regmap_write(regmap, AT91_CKGR_MOR, tmp); + } + +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS)) { +- enable_irq(osc->irq); +- wait_event(osc->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS); +- } ++ while (!clk_main_osc_ready(regmap)) ++ cpu_relax(); + + return 0; + } +@@ -106,9 +93,10 @@ + static void clk_main_osc_unprepare(struct clk_hw *hw) + { + struct clk_main_osc *osc = to_clk_main_osc(hw); +- struct at91_pmc *pmc = osc->pmc; +- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); ++ struct regmap *regmap = osc->regmap; ++ u32 tmp; + ++ regmap_read(regmap, AT91_CKGR_MOR, &tmp); + if (tmp & AT91_PMC_OSCBYPASS) + return; + +@@ -116,20 +104,22 @@ + return; + + tmp &= ~(AT91_PMC_KEY | AT91_PMC_MOSCEN); +- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); ++ regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); + } + + static int clk_main_osc_is_prepared(struct clk_hw *hw) + { + struct clk_main_osc *osc = to_clk_main_osc(hw); +- struct at91_pmc *pmc = osc->pmc; +- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); ++ struct regmap *regmap = osc->regmap; ++ u32 tmp, status; + ++ regmap_read(regmap, AT91_CKGR_MOR, &tmp); + if (tmp & AT91_PMC_OSCBYPASS) + return 1; + +- return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS) && +- (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN)); ++ regmap_read(regmap, AT91_PMC_SR, &status); ++ ++ return (status & AT91_PMC_MOSCS) && (tmp & AT91_PMC_MOSCEN); + } + + static const struct clk_ops main_osc_ops = { +@@ -139,18 +129,16 @@ + }; + + static struct clk * __init +-at91_clk_register_main_osc(struct at91_pmc *pmc, +- unsigned int irq, ++at91_clk_register_main_osc(struct regmap *regmap, + const char *name, + const char *parent_name, + bool bypass) + { +- int ret; + struct clk_main_osc *osc; + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !irq || !name || !parent_name) ++ if (!name || !parent_name) + return ERR_PTR(-EINVAL); + + osc = kzalloc(sizeof(*osc), GFP_KERNEL); +@@ -164,85 +152,70 @@ + init.flags = CLK_IGNORE_UNUSED; + + osc->hw.init = &init; +- osc->pmc = pmc; +- osc->irq = irq; +- +- init_waitqueue_head(&osc->wait); +- irq_set_status_flags(osc->irq, IRQ_NOAUTOEN); +- ret = request_irq(osc->irq, clk_main_osc_irq_handler, +- IRQF_TRIGGER_HIGH, name, osc); +- if (ret) { +- kfree(osc); +- return ERR_PTR(ret); +- } ++ osc->regmap = regmap; + + if (bypass) +- pmc_write(pmc, AT91_CKGR_MOR, +- (pmc_read(pmc, AT91_CKGR_MOR) & +- ~(MOR_KEY_MASK | AT91_PMC_MOSCEN)) | +- AT91_PMC_OSCBYPASS | AT91_PMC_KEY); ++ regmap_update_bits(regmap, ++ AT91_CKGR_MOR, MOR_KEY_MASK | ++ AT91_PMC_MOSCEN, ++ AT91_PMC_OSCBYPASS | AT91_PMC_KEY); + + clk = clk_register(NULL, &osc->hw); +- if (IS_ERR(clk)) { +- free_irq(irq, osc); ++ if (IS_ERR(clk)) + kfree(osc); +- } + + return clk; + } + +-void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np) + { + struct clk *clk; +- unsigned int irq; + const char *name = np->name; + const char *parent_name; ++ struct regmap *regmap; + bool bypass; + + of_property_read_string(np, "clock-output-names", &name); + bypass = of_property_read_bool(np, "atmel,osc-bypass"); + parent_name = of_clk_get_parent_name(np, 0); + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) + return; + +- clk = at91_clk_register_main_osc(pmc, irq, name, parent_name, bypass); ++ clk = at91_clk_register_main_osc(regmap, name, parent_name, bypass); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91rm9200_clk_main_osc, "atmel,at91rm9200-clk-main-osc", ++ of_at91rm9200_clk_main_osc_setup); + +-static irqreturn_t clk_main_rc_osc_irq_handler(int irq, void *dev_id) ++static bool clk_main_rc_osc_ready(struct regmap *regmap) + { +- struct clk_main_rc_osc *osc = dev_id; ++ unsigned int status; + +- wake_up(&osc->wait); +- disable_irq_nosync(osc->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & AT91_PMC_MOSCRCS; + } + + static int clk_main_rc_osc_prepare(struct clk_hw *hw) + { + struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); +- struct at91_pmc *pmc = osc->pmc; +- u32 tmp; ++ struct regmap *regmap = osc->regmap; ++ unsigned int mor; + +- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; ++ regmap_read(regmap, AT91_CKGR_MOR, &mor); + +- if (!(tmp & AT91_PMC_MOSCRCEN)) { +- tmp |= AT91_PMC_MOSCRCEN | AT91_PMC_KEY; +- pmc_write(pmc, AT91_CKGR_MOR, tmp); +- } ++ if (!(mor & AT91_PMC_MOSCRCEN)) ++ regmap_update_bits(regmap, AT91_CKGR_MOR, ++ MOR_KEY_MASK | AT91_PMC_MOSCRCEN, ++ AT91_PMC_MOSCRCEN | AT91_PMC_KEY); + +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS)) { +- enable_irq(osc->irq); +- wait_event(osc->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS); +- } ++ while (!clk_main_rc_osc_ready(regmap)) ++ cpu_relax(); + + return 0; + } +@@ -250,23 +223,28 @@ + static void clk_main_rc_osc_unprepare(struct clk_hw *hw) + { + struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); +- struct at91_pmc *pmc = osc->pmc; +- u32 tmp = pmc_read(pmc, AT91_CKGR_MOR); ++ struct regmap *regmap = osc->regmap; ++ unsigned int mor; + +- if (!(tmp & AT91_PMC_MOSCRCEN)) ++ regmap_read(regmap, AT91_CKGR_MOR, &mor); ++ ++ if (!(mor & AT91_PMC_MOSCRCEN)) + return; + +- tmp &= ~(MOR_KEY_MASK | AT91_PMC_MOSCRCEN); +- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY); ++ regmap_update_bits(regmap, AT91_CKGR_MOR, ++ MOR_KEY_MASK | AT91_PMC_MOSCRCEN, AT91_PMC_KEY); + } + + static int clk_main_rc_osc_is_prepared(struct clk_hw *hw) + { + struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw); +- struct at91_pmc *pmc = osc->pmc; ++ struct regmap *regmap = osc->regmap; ++ unsigned int mor, status; ++ ++ regmap_read(regmap, AT91_CKGR_MOR, &mor); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS) && +- (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCRCEN)); ++ return (mor & AT91_PMC_MOSCRCEN) && (status & AT91_PMC_MOSCRCS); + } + + static unsigned long clk_main_rc_osc_recalc_rate(struct clk_hw *hw, +@@ -294,17 +272,15 @@ + }; + + static struct clk * __init +-at91_clk_register_main_rc_osc(struct at91_pmc *pmc, +- unsigned int irq, ++at91_clk_register_main_rc_osc(struct regmap *regmap, + const char *name, + u32 frequency, u32 accuracy) + { +- int ret; + struct clk_main_rc_osc *osc; + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !irq || !name || !frequency) ++ if (!name || !frequency) + return ERR_PTR(-EINVAL); + + osc = kzalloc(sizeof(*osc), GFP_KERNEL); +@@ -318,63 +294,53 @@ + init.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED; + + osc->hw.init = &init; +- osc->pmc = pmc; +- osc->irq = irq; ++ osc->regmap = regmap; + osc->frequency = frequency; + osc->accuracy = accuracy; + +- init_waitqueue_head(&osc->wait); +- irq_set_status_flags(osc->irq, IRQ_NOAUTOEN); +- ret = request_irq(osc->irq, clk_main_rc_osc_irq_handler, +- IRQF_TRIGGER_HIGH, name, osc); +- if (ret) +- return ERR_PTR(ret); +- + clk = clk_register(NULL, &osc->hw); +- if (IS_ERR(clk)) { +- free_irq(irq, osc); ++ if (IS_ERR(clk)) + kfree(osc); +- } + + return clk; + } + +-void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np) + { + struct clk *clk; +- unsigned int irq; + u32 frequency = 0; + u32 accuracy = 0; + const char *name = np->name; ++ struct regmap *regmap; + + of_property_read_string(np, "clock-output-names", &name); + of_property_read_u32(np, "clock-frequency", &frequency); + of_property_read_u32(np, "clock-accuracy", &accuracy); + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) + return; + +- clk = at91_clk_register_main_rc_osc(pmc, irq, name, frequency, +- accuracy); ++ clk = at91_clk_register_main_rc_osc(regmap, name, frequency, accuracy); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9x5_clk_main_rc_osc, "atmel,at91sam9x5-clk-main-rc-osc", ++ of_at91sam9x5_clk_main_rc_osc_setup); + + +-static int clk_main_probe_frequency(struct at91_pmc *pmc) ++static int clk_main_probe_frequency(struct regmap *regmap) + { + unsigned long prep_time, timeout; +- u32 tmp; ++ unsigned int mcfr; + + timeout = jiffies + usecs_to_jiffies(MAINFRDY_TIMEOUT); + do { + prep_time = jiffies; +- tmp = pmc_read(pmc, AT91_CKGR_MCFR); +- if (tmp & AT91_PMC_MAINRDY) ++ regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); ++ if (mcfr & AT91_PMC_MAINRDY) + return 0; + usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT); + } while (time_before(prep_time, timeout)); +@@ -382,34 +348,37 @@ + return -ETIMEDOUT; + } + +-static unsigned long clk_main_recalc_rate(struct at91_pmc *pmc, ++static unsigned long clk_main_recalc_rate(struct regmap *regmap, + unsigned long parent_rate) + { +- u32 tmp; ++ unsigned int mcfr; + + if (parent_rate) + return parent_rate; + + pr_warn("Main crystal frequency not set, using approximate value\n"); +- tmp = pmc_read(pmc, AT91_CKGR_MCFR); +- if (!(tmp & AT91_PMC_MAINRDY)) ++ regmap_read(regmap, AT91_CKGR_MCFR, &mcfr); ++ if (!(mcfr & AT91_PMC_MAINRDY)) + return 0; + +- return ((tmp & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV; ++ return ((mcfr & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV; + } + + static int clk_rm9200_main_prepare(struct clk_hw *hw) + { + struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); + +- return clk_main_probe_frequency(clkmain->pmc); ++ return clk_main_probe_frequency(clkmain->regmap); + } + + static int clk_rm9200_main_is_prepared(struct clk_hw *hw) + { + struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); ++ unsigned int status; ++ ++ regmap_read(clkmain->regmap, AT91_CKGR_MCFR, &status); + +- return !!(pmc_read(clkmain->pmc, AT91_CKGR_MCFR) & AT91_PMC_MAINRDY); ++ return status & AT91_PMC_MAINRDY ? 1 : 0; + } + + static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw, +@@ -417,7 +386,7 @@ + { + struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw); + +- return clk_main_recalc_rate(clkmain->pmc, parent_rate); ++ return clk_main_recalc_rate(clkmain->regmap, parent_rate); + } + + static const struct clk_ops rm9200_main_ops = { +@@ -427,7 +396,7 @@ + }; + + static struct clk * __init +-at91_clk_register_rm9200_main(struct at91_pmc *pmc, ++at91_clk_register_rm9200_main(struct regmap *regmap, + const char *name, + const char *parent_name) + { +@@ -435,7 +404,7 @@ + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !name) ++ if (!name) + return ERR_PTR(-EINVAL); + + if (!parent_name) +@@ -452,7 +421,7 @@ + init.flags = 0; + + clkmain->hw.init = &init; +- clkmain->pmc = pmc; ++ clkmain->regmap = regmap; + + clk = clk_register(NULL, &clkmain->hw); + if (IS_ERR(clk)) +@@ -461,52 +430,54 @@ + return clk; + } + +-void __init of_at91rm9200_clk_main_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_main_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_name; + const char *name = np->name; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91_clk_register_rm9200_main(pmc, name, parent_name); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ ++ clk = at91_clk_register_rm9200_main(regmap, name, parent_name); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91rm9200_clk_main, "atmel,at91rm9200-clk-main", ++ of_at91rm9200_clk_main_setup); + +-static irqreturn_t clk_sam9x5_main_irq_handler(int irq, void *dev_id) ++static inline bool clk_sam9x5_main_ready(struct regmap *regmap) + { +- struct clk_sam9x5_main *clkmain = dev_id; ++ unsigned int status; + +- wake_up(&clkmain->wait); +- disable_irq_nosync(clkmain->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & AT91_PMC_MOSCSELS ? 1 : 0; + } + + static int clk_sam9x5_main_prepare(struct clk_hw *hw) + { + struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); +- struct at91_pmc *pmc = clkmain->pmc; ++ struct regmap *regmap = clkmain->regmap; + +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) { +- enable_irq(clkmain->irq); +- wait_event(clkmain->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); +- } ++ while (!clk_sam9x5_main_ready(regmap)) ++ cpu_relax(); + +- return clk_main_probe_frequency(pmc); ++ return clk_main_probe_frequency(regmap); + } + + static int clk_sam9x5_main_is_prepared(struct clk_hw *hw) + { + struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); + +- return !!(pmc_read(clkmain->pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); ++ return clk_sam9x5_main_ready(clkmain->regmap); + } + + static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw, +@@ -514,30 +485,28 @@ + { + struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); + +- return clk_main_recalc_rate(clkmain->pmc, parent_rate); ++ return clk_main_recalc_rate(clkmain->regmap, parent_rate); + } + + static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index) + { + struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); +- struct at91_pmc *pmc = clkmain->pmc; +- u32 tmp; ++ struct regmap *regmap = clkmain->regmap; ++ unsigned int tmp; + + if (index > 1) + return -EINVAL; + +- tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK; ++ regmap_read(regmap, AT91_CKGR_MOR, &tmp); ++ tmp &= ~MOR_KEY_MASK; + + if (index && !(tmp & AT91_PMC_MOSCSEL)) +- pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL); ++ regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL); + else if (!index && (tmp & AT91_PMC_MOSCSEL)) +- pmc_write(pmc, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL); ++ regmap_write(regmap, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL); + +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) { +- enable_irq(clkmain->irq); +- wait_event(clkmain->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS); +- } ++ while (!clk_sam9x5_main_ready(regmap)) ++ cpu_relax(); + + return 0; + } +@@ -545,8 +514,11 @@ + static u8 clk_sam9x5_main_get_parent(struct clk_hw *hw) + { + struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw); ++ unsigned int status; ++ ++ regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status); + +- return !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN); ++ return status & AT91_PMC_MOSCEN ? 1 : 0; + } + + static const struct clk_ops sam9x5_main_ops = { +@@ -558,18 +530,17 @@ + }; + + static struct clk * __init +-at91_clk_register_sam9x5_main(struct at91_pmc *pmc, +- unsigned int irq, ++at91_clk_register_sam9x5_main(struct regmap *regmap, + const char *name, + const char **parent_names, + int num_parents) + { +- int ret; + struct clk_sam9x5_main *clkmain; + struct clk *clk = NULL; + struct clk_init_data init; ++ unsigned int status; + +- if (!pmc || !irq || !name) ++ if (!name) + return ERR_PTR(-EINVAL); + + if (!parent_names || !num_parents) +@@ -586,51 +557,42 @@ + init.flags = CLK_SET_PARENT_GATE; + + clkmain->hw.init = &init; +- clkmain->pmc = pmc; +- clkmain->irq = irq; +- clkmain->parent = !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & +- AT91_PMC_MOSCEN); +- init_waitqueue_head(&clkmain->wait); +- irq_set_status_flags(clkmain->irq, IRQ_NOAUTOEN); +- ret = request_irq(clkmain->irq, clk_sam9x5_main_irq_handler, +- IRQF_TRIGGER_HIGH, name, clkmain); +- if (ret) +- return ERR_PTR(ret); ++ clkmain->regmap = regmap; ++ regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status); ++ clkmain->parent = status & AT91_PMC_MOSCEN ? 1 : 0; + + clk = clk_register(NULL, &clkmain->hw); +- if (IS_ERR(clk)) { +- free_irq(clkmain->irq, clkmain); ++ if (IS_ERR(clk)) + kfree(clkmain); +- } + + return clk; + } + +-void __init of_at91sam9x5_clk_main_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_main_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_names[2]; + int num_parents; +- unsigned int irq; + const char *name = np->name; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > 2) + return; + + of_clk_parent_fill(np, parent_names, num_parents); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; + + of_property_read_string(np, "clock-output-names", &name); + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) +- return; +- +- clk = at91_clk_register_sam9x5_main(pmc, irq, name, parent_names, ++ clk = at91_clk_register_sam9x5_main(regmap, name, parent_names, + num_parents); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9x5_clk_main, "atmel,at91sam9x5-clk-main", ++ of_at91sam9x5_clk_main_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-master.c linux-4.4.28/drivers/clk/at91/clk-master.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-master.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-master.c 2016-11-01 21:26:57.920287105 +0100 +@@ -12,13 +12,8 @@ + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -44,32 +39,26 @@ + + struct clk_master { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + const struct clk_master_layout *layout; + const struct clk_master_characteristics *characteristics; + }; + +-static irqreturn_t clk_master_irq_handler(int irq, void *dev_id) ++static inline bool clk_master_ready(struct regmap *regmap) + { +- struct clk_master *master = (struct clk_master *)dev_id; ++ unsigned int status; + +- wake_up(&master->wait); +- disable_irq_nosync(master->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & AT91_PMC_MCKRDY ? 1 : 0; + } ++ + static int clk_master_prepare(struct clk_hw *hw) + { + struct clk_master *master = to_clk_master(hw); +- struct at91_pmc *pmc = master->pmc; + +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY)) { +- enable_irq(master->irq); +- wait_event(master->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY); +- } ++ while (!clk_master_ready(master->regmap)) ++ cpu_relax(); + + return 0; + } +@@ -78,7 +67,7 @@ + { + struct clk_master *master = to_clk_master(hw); + +- return !!(pmc_read(master->pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY); ++ return clk_master_ready(master->regmap); + } + + static unsigned long clk_master_recalc_rate(struct clk_hw *hw, +@@ -88,18 +77,16 @@ + u8 div; + unsigned long rate = parent_rate; + struct clk_master *master = to_clk_master(hw); +- struct at91_pmc *pmc = master->pmc; + const struct clk_master_layout *layout = master->layout; + const struct clk_master_characteristics *characteristics = + master->characteristics; +- u32 tmp; ++ unsigned int mckr; + +- pmc_lock(pmc); +- tmp = pmc_read(pmc, AT91_PMC_MCKR) & layout->mask; +- pmc_unlock(pmc); ++ regmap_read(master->regmap, AT91_PMC_MCKR, &mckr); ++ mckr &= layout->mask; + +- pres = (tmp >> layout->pres_shift) & MASTER_PRES_MASK; +- div = (tmp >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK; ++ pres = (mckr >> layout->pres_shift) & MASTER_PRES_MASK; ++ div = (mckr >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK; + + if (characteristics->have_div3_pres && pres == MASTER_PRES_MAX) + rate /= 3; +@@ -119,9 +106,11 @@ + static u8 clk_master_get_parent(struct clk_hw *hw) + { + struct clk_master *master = to_clk_master(hw); +- struct at91_pmc *pmc = master->pmc; ++ unsigned int mckr; + +- return pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_CSS; ++ regmap_read(master->regmap, AT91_PMC_MCKR, &mckr); ++ ++ return mckr & AT91_PMC_CSS; + } + + static const struct clk_ops master_ops = { +@@ -132,18 +121,17 @@ + }; + + static struct clk * __init +-at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq, ++at91_clk_register_master(struct regmap *regmap, + const char *name, int num_parents, + const char **parent_names, + const struct clk_master_layout *layout, + const struct clk_master_characteristics *characteristics) + { +- int ret; + struct clk_master *master; + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !irq || !name || !num_parents || !parent_names) ++ if (!name || !num_parents || !parent_names) + return ERR_PTR(-EINVAL); + + master = kzalloc(sizeof(*master), GFP_KERNEL); +@@ -159,20 +147,10 @@ + master->hw.init = &init; + master->layout = layout; + master->characteristics = characteristics; +- master->pmc = pmc; +- master->irq = irq; +- init_waitqueue_head(&master->wait); +- irq_set_status_flags(master->irq, IRQ_NOAUTOEN); +- ret = request_irq(master->irq, clk_master_irq_handler, +- IRQF_TRIGGER_HIGH, "clk-master", master); +- if (ret) { +- kfree(master); +- return ERR_PTR(ret); +- } ++ master->regmap = regmap; + + clk = clk_register(NULL, &master->hw); + if (IS_ERR(clk)) { +- free_irq(master->irq, master); + kfree(master); + } + +@@ -217,15 +195,15 @@ + } + + static void __init +-of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc, ++of_at91_clk_master_setup(struct device_node *np, + const struct clk_master_layout *layout) + { + struct clk *clk; + int num_parents; +- unsigned int irq; + const char *parent_names[MASTER_SOURCE_MAX]; + const char *name = np->name; + struct clk_master_characteristics *characteristics; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX) +@@ -239,11 +217,11 @@ + if (!characteristics) + return; + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) +- goto out_free_characteristics; ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; + +- clk = at91_clk_register_master(pmc, irq, name, num_parents, ++ clk = at91_clk_register_master(regmap, name, num_parents, + parent_names, layout, + characteristics); + if (IS_ERR(clk)) +@@ -256,14 +234,16 @@ + kfree(characteristics); + } + +-void __init of_at91rm9200_clk_master_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_master_setup(struct device_node *np) + { +- of_at91_clk_master_setup(np, pmc, &at91rm9200_master_layout); ++ of_at91_clk_master_setup(np, &at91rm9200_master_layout); + } ++CLK_OF_DECLARE(at91rm9200_clk_master, "atmel,at91rm9200-clk-master", ++ of_at91rm9200_clk_master_setup); + +-void __init of_at91sam9x5_clk_master_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_master_setup(struct device_node *np) + { +- of_at91_clk_master_setup(np, pmc, &at91sam9x5_master_layout); ++ of_at91_clk_master_setup(np, &at91sam9x5_master_layout); + } ++CLK_OF_DECLARE(at91sam9x5_clk_master, "atmel,at91sam9x5-clk-master", ++ of_at91sam9x5_clk_master_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c linux-4.4.28/drivers/clk/at91/clk-peripheral.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-peripheral.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-peripheral.c 2016-11-01 21:26:57.920287105 +0100 +@@ -12,11 +12,13 @@ + #include + #include + #include +-#include +-#include ++#include ++#include + + #include "pmc.h" + ++DEFINE_SPINLOCK(pmc_pcr_lock); ++ + #define PERIPHERAL_MAX 64 + + #define PERIPHERAL_AT91RM9200 0 +@@ -33,7 +35,7 @@ + + struct clk_peripheral { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + u32 id; + }; + +@@ -41,8 +43,9 @@ + + struct clk_sam9x5_peripheral { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + struct clk_range range; ++ spinlock_t *lock; + u32 id; + u32 div; + bool auto_div; +@@ -54,7 +57,6 @@ + static int clk_peripheral_enable(struct clk_hw *hw) + { + struct clk_peripheral *periph = to_clk_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; + int offset = AT91_PMC_PCER; + u32 id = periph->id; + +@@ -62,14 +64,14 @@ + return 0; + if (id > PERIPHERAL_ID_MAX) + offset = AT91_PMC_PCER1; +- pmc_write(pmc, offset, PERIPHERAL_MASK(id)); ++ regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id)); ++ + return 0; + } + + static void clk_peripheral_disable(struct clk_hw *hw) + { + struct clk_peripheral *periph = to_clk_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; + int offset = AT91_PMC_PCDR; + u32 id = periph->id; + +@@ -77,21 +79,23 @@ + return; + if (id > PERIPHERAL_ID_MAX) + offset = AT91_PMC_PCDR1; +- pmc_write(pmc, offset, PERIPHERAL_MASK(id)); ++ regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id)); + } + + static int clk_peripheral_is_enabled(struct clk_hw *hw) + { + struct clk_peripheral *periph = to_clk_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; + int offset = AT91_PMC_PCSR; ++ unsigned int status; + u32 id = periph->id; + + if (id < PERIPHERAL_ID_MIN) + return 1; + if (id > PERIPHERAL_ID_MAX) + offset = AT91_PMC_PCSR1; +- return !!(pmc_read(pmc, offset) & PERIPHERAL_MASK(id)); ++ regmap_read(periph->regmap, offset, &status); ++ ++ return status & PERIPHERAL_MASK(id) ? 1 : 0; + } + + static const struct clk_ops peripheral_ops = { +@@ -101,14 +105,14 @@ + }; + + static struct clk * __init +-at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name, ++at91_clk_register_peripheral(struct regmap *regmap, const char *name, + const char *parent_name, u32 id) + { + struct clk_peripheral *periph; + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !name || !parent_name || id > PERIPHERAL_ID_MAX) ++ if (!name || !parent_name || id > PERIPHERAL_ID_MAX) + return ERR_PTR(-EINVAL); + + periph = kzalloc(sizeof(*periph), GFP_KERNEL); +@@ -123,7 +127,7 @@ + + periph->id = id; + periph->hw.init = &init; +- periph->pmc = pmc; ++ periph->regmap = regmap; + + clk = clk_register(NULL, &periph->hw); + if (IS_ERR(clk)) +@@ -160,53 +164,58 @@ + static int clk_sam9x5_peripheral_enable(struct clk_hw *hw) + { + struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; +- u32 tmp; ++ unsigned long flags; + + if (periph->id < PERIPHERAL_ID_MIN) + return 0; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_DIV_MASK; +- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_DIV(periph->div) +- | AT91_PMC_PCR_CMD +- | AT91_PMC_PCR_EN); +- pmc_unlock(pmc); ++ spin_lock_irqsave(periph->lock, flags); ++ regmap_write(periph->regmap, AT91_PMC_PCR, ++ (periph->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_update_bits(periph->regmap, AT91_PMC_PCR, ++ AT91_PMC_PCR_DIV_MASK | AT91_PMC_PCR_CMD | ++ AT91_PMC_PCR_EN, ++ AT91_PMC_PCR_DIV(periph->div) | ++ AT91_PMC_PCR_CMD | ++ AT91_PMC_PCR_EN); ++ spin_unlock_irqrestore(periph->lock, flags); ++ + return 0; + } + + static void clk_sam9x5_peripheral_disable(struct clk_hw *hw) + { + struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; +- u32 tmp; ++ unsigned long flags; + + if (periph->id < PERIPHERAL_ID_MIN) + return; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_EN; +- pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD); +- pmc_unlock(pmc); ++ spin_lock_irqsave(periph->lock, flags); ++ regmap_write(periph->regmap, AT91_PMC_PCR, ++ (periph->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_update_bits(periph->regmap, AT91_PMC_PCR, ++ AT91_PMC_PCR_EN | AT91_PMC_PCR_CMD, ++ AT91_PMC_PCR_CMD); ++ spin_unlock_irqrestore(periph->lock, flags); + } + + static int clk_sam9x5_peripheral_is_enabled(struct clk_hw *hw) + { + struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; +- int ret; ++ unsigned long flags; ++ unsigned int status; + + if (periph->id < PERIPHERAL_ID_MIN) + return 1; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); +- ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_EN); +- pmc_unlock(pmc); ++ spin_lock_irqsave(periph->lock, flags); ++ regmap_write(periph->regmap, AT91_PMC_PCR, ++ (periph->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_read(periph->regmap, AT91_PMC_PCR, &status); ++ spin_unlock_irqrestore(periph->lock, flags); + +- return ret; ++ return status & AT91_PMC_PCR_EN ? 1 : 0; + } + + static unsigned long +@@ -214,19 +223,20 @@ + unsigned long parent_rate) + { + struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); +- struct at91_pmc *pmc = periph->pmc; +- u32 tmp; ++ unsigned long flags; ++ unsigned int status; + + if (periph->id < PERIPHERAL_ID_MIN) + return parent_rate; + +- pmc_lock(pmc); +- pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK)); +- tmp = pmc_read(pmc, AT91_PMC_PCR); +- pmc_unlock(pmc); ++ spin_lock_irqsave(periph->lock, flags); ++ regmap_write(periph->regmap, AT91_PMC_PCR, ++ (periph->id & AT91_PMC_PCR_PID_MASK)); ++ regmap_read(periph->regmap, AT91_PMC_PCR, &status); ++ spin_unlock_irqrestore(periph->lock, flags); + +- if (tmp & AT91_PMC_PCR_EN) { +- periph->div = PERIPHERAL_RSHIFT(tmp); ++ if (status & AT91_PMC_PCR_EN) { ++ periph->div = PERIPHERAL_RSHIFT(status); + periph->auto_div = false; + } else { + clk_sam9x5_peripheral_autodiv(periph); +@@ -318,15 +328,15 @@ + }; + + static struct clk * __init +-at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name, +- const char *parent_name, u32 id, +- const struct clk_range *range) ++at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock, ++ const char *name, const char *parent_name, ++ u32 id, const struct clk_range *range) + { + struct clk_sam9x5_peripheral *periph; + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !name || !parent_name) ++ if (!name || !parent_name) + return ERR_PTR(-EINVAL); + + periph = kzalloc(sizeof(*periph), GFP_KERNEL); +@@ -342,7 +352,8 @@ + periph->id = id; + periph->hw.init = &init; + periph->div = 0; +- periph->pmc = pmc; ++ periph->regmap = regmap; ++ periph->lock = lock; + periph->auto_div = true; + periph->range = *range; + +@@ -356,7 +367,7 @@ + } + + static void __init +-of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type) ++of_at91_clk_periph_setup(struct device_node *np, u8 type) + { + int num; + u32 id; +@@ -364,6 +375,7 @@ + const char *parent_name; + const char *name; + struct device_node *periphclknp; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + if (!parent_name) +@@ -373,6 +385,10 @@ + if (!num || num > PERIPHERAL_MAX) + return; + ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ + for_each_child_of_node(np, periphclknp) { + if (of_property_read_u32(periphclknp, "reg", &id)) + continue; +@@ -384,7 +400,7 @@ + name = periphclknp->name; + + if (type == PERIPHERAL_AT91RM9200) { +- clk = at91_clk_register_peripheral(pmc, name, ++ clk = at91_clk_register_peripheral(regmap, name, + parent_name, id); + } else { + struct clk_range range = CLK_RANGE(0, 0); +@@ -393,7 +409,9 @@ + "atmel,clk-output-range", + &range); + +- clk = at91_clk_register_sam9x5_peripheral(pmc, name, ++ clk = at91_clk_register_sam9x5_peripheral(regmap, ++ &pmc_pcr_lock, ++ name, + parent_name, + id, &range); + } +@@ -405,14 +423,16 @@ + } + } + +-void __init of_at91rm9200_clk_periph_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_periph_setup(struct device_node *np) + { +- of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91RM9200); ++ of_at91_clk_periph_setup(np, PERIPHERAL_AT91RM9200); + } ++CLK_OF_DECLARE(at91rm9200_clk_periph, "atmel,at91rm9200-clk-peripheral", ++ of_at91rm9200_clk_periph_setup); + +-void __init of_at91sam9x5_clk_periph_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_periph_setup(struct device_node *np) + { +- of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91SAM9X5); ++ of_at91_clk_periph_setup(np, PERIPHERAL_AT91SAM9X5); + } ++CLK_OF_DECLARE(at91sam9x5_clk_periph, "atmel,at91sam9x5-clk-peripheral", ++ of_at91sam9x5_clk_periph_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-pll.c linux-4.4.28/drivers/clk/at91/clk-pll.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-pll.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-pll.c 2016-11-01 21:26:57.924287358 +0100 +@@ -12,14 +12,8 @@ + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -58,9 +52,7 @@ + + struct clk_pll { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + u8 id; + u8 div; + u8 range; +@@ -69,20 +61,19 @@ + const struct clk_pll_characteristics *characteristics; + }; + +-static irqreturn_t clk_pll_irq_handler(int irq, void *dev_id) ++static inline bool clk_pll_ready(struct regmap *regmap, int id) + { +- struct clk_pll *pll = (struct clk_pll *)dev_id; ++ unsigned int status; + +- wake_up(&pll->wait); +- disable_irq_nosync(pll->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & PLL_STATUS_MASK(id) ? 1 : 0; + } + + static int clk_pll_prepare(struct clk_hw *hw) + { + struct clk_pll *pll = to_clk_pll(hw); +- struct at91_pmc *pmc = pll->pmc; ++ struct regmap *regmap = pll->regmap; + const struct clk_pll_layout *layout = pll->layout; + const struct clk_pll_characteristics *characteristics = + pll->characteristics; +@@ -90,39 +81,34 @@ + u32 mask = PLL_STATUS_MASK(id); + int offset = PLL_REG(id); + u8 out = 0; +- u32 pllr, icpr; ++ unsigned int pllr; ++ unsigned int status; + u8 div; + u16 mul; + +- pllr = pmc_read(pmc, offset); ++ regmap_read(regmap, offset, &pllr); + div = PLL_DIV(pllr); + mul = PLL_MUL(pllr, layout); + +- if ((pmc_read(pmc, AT91_PMC_SR) & mask) && ++ regmap_read(regmap, AT91_PMC_SR, &status); ++ if ((status & mask) && + (div == pll->div && mul == pll->mul)) + return 0; + + if (characteristics->out) + out = characteristics->out[pll->range]; +- if (characteristics->icpll) { +- icpr = pmc_read(pmc, AT91_PMC_PLLICPR) & ~PLL_ICPR_MASK(id); +- icpr |= (characteristics->icpll[pll->range] << +- PLL_ICPR_SHIFT(id)); +- pmc_write(pmc, AT91_PMC_PLLICPR, icpr); +- } + +- pllr &= ~layout->pllr_mask; +- pllr |= layout->pllr_mask & +- (pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) | +- (out << PLL_OUT_SHIFT) | +- ((pll->mul & layout->mul_mask) << layout->mul_shift)); +- pmc_write(pmc, offset, pllr); +- +- while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) { +- enable_irq(pll->irq); +- wait_event(pll->wait, +- pmc_read(pmc, AT91_PMC_SR) & mask); +- } ++ if (characteristics->icpll) ++ regmap_update_bits(regmap, AT91_PMC_PLLICPR, PLL_ICPR_MASK(id), ++ characteristics->icpll[pll->range] << PLL_ICPR_SHIFT(id)); ++ ++ regmap_update_bits(regmap, offset, layout->pllr_mask, ++ pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) | ++ (out << PLL_OUT_SHIFT) | ++ ((pll->mul & layout->mul_mask) << layout->mul_shift)); ++ ++ while (!clk_pll_ready(regmap, pll->id)) ++ cpu_relax(); + + return 0; + } +@@ -130,32 +116,35 @@ + static int clk_pll_is_prepared(struct clk_hw *hw) + { + struct clk_pll *pll = to_clk_pll(hw); +- struct at91_pmc *pmc = pll->pmc; + +- return !!(pmc_read(pmc, AT91_PMC_SR) & +- PLL_STATUS_MASK(pll->id)); ++ return clk_pll_ready(pll->regmap, pll->id); + } + + static void clk_pll_unprepare(struct clk_hw *hw) + { + struct clk_pll *pll = to_clk_pll(hw); +- struct at91_pmc *pmc = pll->pmc; +- const struct clk_pll_layout *layout = pll->layout; +- int offset = PLL_REG(pll->id); +- u32 tmp = pmc_read(pmc, offset) & ~(layout->pllr_mask); ++ unsigned int mask = pll->layout->pllr_mask; + +- pmc_write(pmc, offset, tmp); ++ regmap_update_bits(pll->regmap, PLL_REG(pll->id), mask, ~mask); + } + + static unsigned long clk_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) + { + struct clk_pll *pll = to_clk_pll(hw); ++ unsigned int pllr; ++ u16 mul; ++ u8 div; ++ ++ regmap_read(pll->regmap, PLL_REG(pll->id), &pllr); ++ ++ div = PLL_DIV(pllr); ++ mul = PLL_MUL(pllr, pll->layout); + +- if (!pll->div || !pll->mul) ++ if (!div || !mul) + return 0; + +- return (parent_rate / pll->div) * (pll->mul + 1); ++ return (parent_rate / div) * (mul + 1); + } + + static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate, +@@ -308,7 +297,7 @@ + }; + + static struct clk * __init +-at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name, ++at91_clk_register_pll(struct regmap *regmap, const char *name, + const char *parent_name, u8 id, + const struct clk_pll_layout *layout, + const struct clk_pll_characteristics *characteristics) +@@ -316,9 +305,8 @@ + struct clk_pll *pll; + struct clk *clk = NULL; + struct clk_init_data init; +- int ret; + int offset = PLL_REG(id); +- u32 tmp; ++ unsigned int pllr; + + if (id > PLL_MAX_ID) + return ERR_PTR(-EINVAL); +@@ -337,23 +325,13 @@ + pll->hw.init = &init; + pll->layout = layout; + pll->characteristics = characteristics; +- pll->pmc = pmc; +- pll->irq = irq; +- tmp = pmc_read(pmc, offset) & layout->pllr_mask; +- pll->div = PLL_DIV(tmp); +- pll->mul = PLL_MUL(tmp, layout); +- init_waitqueue_head(&pll->wait); +- irq_set_status_flags(pll->irq, IRQ_NOAUTOEN); +- ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH, +- id ? "clk-pllb" : "clk-plla", pll); +- if (ret) { +- kfree(pll); +- return ERR_PTR(ret); +- } ++ pll->regmap = regmap; ++ regmap_read(regmap, offset, &pllr); ++ pll->div = PLL_DIV(pllr); ++ pll->mul = PLL_MUL(pllr, layout); + + clk = clk_register(NULL, &pll->hw); + if (IS_ERR(clk)) { +- free_irq(pll->irq, pll); + kfree(pll); + } + +@@ -483,12 +461,12 @@ + } + + static void __init +-of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc, ++of_at91_clk_pll_setup(struct device_node *np, + const struct clk_pll_layout *layout) + { + u32 id; +- unsigned int irq; + struct clk *clk; ++ struct regmap *regmap; + const char *parent_name; + const char *name = np->name; + struct clk_pll_characteristics *characteristics; +@@ -500,15 +478,15 @@ + + of_property_read_string(np, "clock-output-names", &name); + +- characteristics = of_at91_clk_pll_get_characteristics(np); +- if (!characteristics) ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) + return; + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) ++ characteristics = of_at91_clk_pll_get_characteristics(np); ++ if (!characteristics) + return; + +- clk = at91_clk_register_pll(pmc, irq, name, parent_name, id, layout, ++ clk = at91_clk_register_pll(regmap, name, parent_name, id, layout, + characteristics); + if (IS_ERR(clk)) + goto out_free_characteristics; +@@ -520,26 +498,30 @@ + kfree(characteristics); + } + +-void __init of_at91rm9200_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_pll_setup(struct device_node *np) + { +- of_at91_clk_pll_setup(np, pmc, &at91rm9200_pll_layout); ++ of_at91_clk_pll_setup(np, &at91rm9200_pll_layout); + } ++CLK_OF_DECLARE(at91rm9200_clk_pll, "atmel,at91rm9200-clk-pll", ++ of_at91rm9200_clk_pll_setup); + +-void __init of_at91sam9g45_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9g45_clk_pll_setup(struct device_node *np) + { +- of_at91_clk_pll_setup(np, pmc, &at91sam9g45_pll_layout); ++ of_at91_clk_pll_setup(np, &at91sam9g45_pll_layout); + } ++CLK_OF_DECLARE(at91sam9g45_clk_pll, "atmel,at91sam9g45-clk-pll", ++ of_at91sam9g45_clk_pll_setup); + +-void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np) + { +- of_at91_clk_pll_setup(np, pmc, &at91sam9g20_pllb_layout); ++ of_at91_clk_pll_setup(np, &at91sam9g20_pllb_layout); + } ++CLK_OF_DECLARE(at91sam9g20_clk_pllb, "atmel,at91sam9g20-clk-pllb", ++ of_at91sam9g20_clk_pllb_setup); + +-void __init of_sama5d3_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_sama5d3_clk_pll_setup(struct device_node *np) + { +- of_at91_clk_pll_setup(np, pmc, &sama5d3_pll_layout); ++ of_at91_clk_pll_setup(np, &sama5d3_pll_layout); + } ++CLK_OF_DECLARE(sama5d3_clk_pll, "atmel,sama5d3-clk-pll", ++ of_sama5d3_clk_pll_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c linux-4.4.28/drivers/clk/at91/clk-plldiv.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-plldiv.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-plldiv.c 2016-11-01 21:26:57.924287358 +0100 +@@ -12,8 +12,8 @@ + #include + #include + #include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -21,16 +21,18 @@ + + struct clk_plldiv { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + static unsigned long clk_plldiv_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) + { + struct clk_plldiv *plldiv = to_clk_plldiv(hw); +- struct at91_pmc *pmc = plldiv->pmc; ++ unsigned int mckr; + +- if (pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_PLLADIV2) ++ regmap_read(plldiv->regmap, AT91_PMC_MCKR, &mckr); ++ ++ if (mckr & AT91_PMC_PLLADIV2) + return parent_rate / 2; + + return parent_rate; +@@ -57,18 +59,12 @@ + unsigned long parent_rate) + { + struct clk_plldiv *plldiv = to_clk_plldiv(hw); +- struct at91_pmc *pmc = plldiv->pmc; +- u32 tmp; + +- if (parent_rate != rate && (parent_rate / 2) != rate) ++ if ((parent_rate != rate) && (parent_rate / 2 != rate)) + return -EINVAL; + +- pmc_lock(pmc); +- tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_PLLADIV2; +- if ((parent_rate / 2) == rate) +- tmp |= AT91_PMC_PLLADIV2; +- pmc_write(pmc, AT91_PMC_MCKR, tmp); +- pmc_unlock(pmc); ++ regmap_update_bits(plldiv->regmap, AT91_PMC_MCKR, AT91_PMC_PLLADIV2, ++ parent_rate != rate ? AT91_PMC_PLLADIV2 : 0); + + return 0; + } +@@ -80,7 +76,7 @@ + }; + + static struct clk * __init +-at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name, ++at91_clk_register_plldiv(struct regmap *regmap, const char *name, + const char *parent_name) + { + struct clk_plldiv *plldiv; +@@ -98,7 +94,7 @@ + init.flags = CLK_SET_RATE_GATE; + + plldiv->hw.init = &init; +- plldiv->pmc = pmc; ++ plldiv->regmap = regmap; + + clk = clk_register(NULL, &plldiv->hw); + +@@ -109,27 +105,27 @@ + } + + static void __init +-of_at91_clk_plldiv_setup(struct device_node *np, struct at91_pmc *pmc) ++of_at91sam9x5_clk_plldiv_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_name; + const char *name = np->name; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91_clk_register_plldiv(pmc, name, parent_name); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; + ++ clk = at91_clk_register_plldiv(regmap, name, parent_name); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + return; + } +- +-void __init of_at91sam9x5_clk_plldiv_setup(struct device_node *np, +- struct at91_pmc *pmc) +-{ +- of_at91_clk_plldiv_setup(np, pmc); +-} ++CLK_OF_DECLARE(at91sam9x5_clk_plldiv, "atmel,at91sam9x5-clk-plldiv", ++ of_at91sam9x5_clk_plldiv_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c linux-4.4.28/drivers/clk/at91/clk-programmable.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-programmable.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-programmable.c 2016-11-01 21:26:57.936288132 +0100 +@@ -12,10 +12,8 @@ + #include + #include + #include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -24,6 +22,7 @@ + + #define PROG_STATUS_MASK(id) (1 << ((id) + 8)) + #define PROG_PRES_MASK 0x7 ++#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & PROG_PRES_MASK) + #define PROG_MAX_RM9200_CSS 3 + + struct clk_programmable_layout { +@@ -34,7 +33,7 @@ + + struct clk_programmable { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + u8 id; + const struct clk_programmable_layout *layout; + }; +@@ -44,14 +43,12 @@ + static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) + { +- u32 pres; + struct clk_programmable *prog = to_clk_programmable(hw); +- struct at91_pmc *pmc = prog->pmc; +- const struct clk_programmable_layout *layout = prog->layout; ++ unsigned int pckr; ++ ++ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); + +- pres = (pmc_read(pmc, AT91_PMC_PCKR(prog->id)) >> layout->pres_shift) & +- PROG_PRES_MASK; +- return parent_rate >> pres; ++ return parent_rate >> PROG_PRES(prog->layout, pckr); + } + + static int clk_programmable_determine_rate(struct clk_hw *hw, +@@ -101,36 +98,36 @@ + { + struct clk_programmable *prog = to_clk_programmable(hw); + const struct clk_programmable_layout *layout = prog->layout; +- struct at91_pmc *pmc = prog->pmc; +- u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & ~layout->css_mask; ++ unsigned int mask = layout->css_mask; ++ unsigned int pckr = 0; + + if (layout->have_slck_mck) +- tmp &= AT91_PMC_CSSMCK_MCK; ++ mask |= AT91_PMC_CSSMCK_MCK; + + if (index > layout->css_mask) { +- if (index > PROG_MAX_RM9200_CSS && layout->have_slck_mck) { +- tmp |= AT91_PMC_CSSMCK_MCK; +- return 0; +- } else { ++ if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck) + return -EINVAL; +- } ++ ++ pckr |= AT91_PMC_CSSMCK_MCK; + } + +- pmc_write(pmc, AT91_PMC_PCKR(prog->id), tmp | index); ++ regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), mask, pckr); ++ + return 0; + } + + static u8 clk_programmable_get_parent(struct clk_hw *hw) + { +- u32 tmp; +- u8 ret; + struct clk_programmable *prog = to_clk_programmable(hw); +- struct at91_pmc *pmc = prog->pmc; + const struct clk_programmable_layout *layout = prog->layout; ++ unsigned int pckr; ++ u8 ret; ++ ++ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); ++ ++ ret = pckr & layout->css_mask; + +- tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)); +- ret = tmp & layout->css_mask; +- if (layout->have_slck_mck && (tmp & AT91_PMC_CSSMCK_MCK) && !ret) ++ if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret) + ret = PROG_MAX_RM9200_CSS + 1; + + return ret; +@@ -140,26 +137,27 @@ + unsigned long parent_rate) + { + struct clk_programmable *prog = to_clk_programmable(hw); +- struct at91_pmc *pmc = prog->pmc; + const struct clk_programmable_layout *layout = prog->layout; + unsigned long div = parent_rate / rate; ++ unsigned int pckr; + int shift = 0; +- u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & +- ~(PROG_PRES_MASK << layout->pres_shift); ++ ++ regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); + + if (!div) + return -EINVAL; + + shift = fls(div) - 1; + +- if (div != (1<= PROG_PRES_MASK) + return -EINVAL; + +- pmc_write(pmc, AT91_PMC_PCKR(prog->id), +- tmp | (shift << layout->pres_shift)); ++ regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), ++ PROG_PRES_MASK << layout->pres_shift, ++ shift << layout->pres_shift); + + return 0; + } +@@ -173,7 +171,7 @@ + }; + + static struct clk * __init +-at91_clk_register_programmable(struct at91_pmc *pmc, ++at91_clk_register_programmable(struct regmap *regmap, + const char *name, const char **parent_names, + u8 num_parents, u8 id, + const struct clk_programmable_layout *layout) +@@ -198,7 +196,7 @@ + prog->id = id; + prog->layout = layout; + prog->hw.init = &init; +- prog->pmc = pmc; ++ prog->regmap = regmap; + + clk = clk_register(NULL, &prog->hw); + if (IS_ERR(clk)) +@@ -226,7 +224,7 @@ + }; + + static void __init +-of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc, ++of_at91_clk_prog_setup(struct device_node *np, + const struct clk_programmable_layout *layout) + { + int num; +@@ -236,6 +234,7 @@ + const char *parent_names[PROG_SOURCE_MAX]; + const char *name; + struct device_node *progclknp; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX) +@@ -247,6 +246,10 @@ + if (!num || num > (PROG_ID_MAX + 1)) + return; + ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ + for_each_child_of_node(np, progclknp) { + if (of_property_read_u32(progclknp, "reg", &id)) + continue; +@@ -254,7 +257,7 @@ + if (of_property_read_string(np, "clock-output-names", &name)) + name = progclknp->name; + +- clk = at91_clk_register_programmable(pmc, name, ++ clk = at91_clk_register_programmable(regmap, name, + parent_names, num_parents, + id, layout); + if (IS_ERR(clk)) +@@ -265,20 +268,23 @@ + } + + +-void __init of_at91rm9200_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_prog_setup(struct device_node *np) + { +- of_at91_clk_prog_setup(np, pmc, &at91rm9200_programmable_layout); ++ of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout); + } ++CLK_OF_DECLARE(at91rm9200_clk_prog, "atmel,at91rm9200-clk-programmable", ++ of_at91rm9200_clk_prog_setup); + +-void __init of_at91sam9g45_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9g45_clk_prog_setup(struct device_node *np) + { +- of_at91_clk_prog_setup(np, pmc, &at91sam9g45_programmable_layout); ++ of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout); + } ++CLK_OF_DECLARE(at91sam9g45_clk_prog, "atmel,at91sam9g45-clk-programmable", ++ of_at91sam9g45_clk_prog_setup); + +-void __init of_at91sam9x5_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_prog_setup(struct device_node *np) + { +- of_at91_clk_prog_setup(np, pmc, &at91sam9x5_programmable_layout); ++ of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout); + } ++CLK_OF_DECLARE(at91sam9x5_clk_prog, "atmel,at91sam9x5-clk-programmable", ++ of_at91sam9x5_clk_prog_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-slow.c linux-4.4.28/drivers/clk/at91/clk-slow.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-slow.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-slow.c 2016-11-01 21:26:57.940288388 +0100 +@@ -13,17 +13,11 @@ + #include + #include + #include +-#include + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + #include "sckc.h" +@@ -59,7 +53,7 @@ + + struct clk_sam9260_slow { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + #define to_clk_sam9260_slow(hw) container_of(hw, struct clk_sam9260_slow, hw) +@@ -393,8 +387,11 @@ + static u8 clk_sam9260_slow_get_parent(struct clk_hw *hw) + { + struct clk_sam9260_slow *slowck = to_clk_sam9260_slow(hw); ++ unsigned int status; + +- return !!(pmc_read(slowck->pmc, AT91_PMC_SR) & AT91_PMC_OSCSEL); ++ regmap_read(slowck->regmap, AT91_PMC_SR, &status); ++ ++ return status & AT91_PMC_OSCSEL ? 1 : 0; + } + + static const struct clk_ops sam9260_slow_ops = { +@@ -402,7 +399,7 @@ + }; + + static struct clk * __init +-at91_clk_register_sam9260_slow(struct at91_pmc *pmc, ++at91_clk_register_sam9260_slow(struct regmap *regmap, + const char *name, + const char **parent_names, + int num_parents) +@@ -411,7 +408,7 @@ + struct clk *clk = NULL; + struct clk_init_data init; + +- if (!pmc || !name) ++ if (!name) + return ERR_PTR(-EINVAL); + + if (!parent_names || !num_parents) +@@ -428,7 +425,7 @@ + init.flags = 0; + + slowck->hw.init = &init; +- slowck->pmc = pmc; ++ slowck->regmap = regmap; + + clk = clk_register(NULL, &slowck->hw); + if (IS_ERR(clk)) +@@ -439,29 +436,34 @@ + return clk; + } + +-void __init of_at91sam9260_clk_slow_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9260_clk_slow_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_names[2]; + int num_parents; + const char *name = np->name; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents != 2) + return; + + of_clk_parent_fill(np, parent_names, num_parents); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91_clk_register_sam9260_slow(pmc, name, parent_names, ++ clk = at91_clk_register_sam9260_slow(regmap, name, parent_names, + num_parents); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9260_clk_slow, "atmel,at91sam9260-clk-slow", ++ of_at91sam9260_clk_slow_setup); + + /* + * FIXME: All slow clk users are not properly claiming it (get + prepare + +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-smd.c linux-4.4.28/drivers/clk/at91/clk-smd.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-smd.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-smd.c 2016-11-01 21:26:57.940288388 +0100 +@@ -12,8 +12,8 @@ + #include + #include + #include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -24,7 +24,7 @@ + + struct at91sam9x5_clk_smd { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + #define to_at91sam9x5_clk_smd(hw) \ +@@ -33,13 +33,13 @@ + static unsigned long at91sam9x5_clk_smd_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) + { +- u32 tmp; +- u8 smddiv; + struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); +- struct at91_pmc *pmc = smd->pmc; ++ unsigned int smdr; ++ u8 smddiv; ++ ++ regmap_read(smd->regmap, AT91_PMC_SMD, &smdr); ++ smddiv = (smdr & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT; + +- tmp = pmc_read(pmc, AT91_PMC_SMD); +- smddiv = (tmp & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT; + return parent_rate / (smddiv + 1); + } + +@@ -67,40 +67,38 @@ + + static int at91sam9x5_clk_smd_set_parent(struct clk_hw *hw, u8 index) + { +- u32 tmp; + struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); +- struct at91_pmc *pmc = smd->pmc; + + if (index > 1) + return -EINVAL; +- tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMDS; +- if (index) +- tmp |= AT91_PMC_SMDS; +- pmc_write(pmc, AT91_PMC_SMD, tmp); ++ ++ regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMDS, ++ index ? AT91_PMC_SMDS : 0); ++ + return 0; + } + + static u8 at91sam9x5_clk_smd_get_parent(struct clk_hw *hw) + { + struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); +- struct at91_pmc *pmc = smd->pmc; ++ unsigned int smdr; + +- return pmc_read(pmc, AT91_PMC_SMD) & AT91_PMC_SMDS; ++ regmap_read(smd->regmap, AT91_PMC_SMD, &smdr); ++ ++ return smdr & AT91_PMC_SMDS; + } + + static int at91sam9x5_clk_smd_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) + { +- u32 tmp; + struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw); +- struct at91_pmc *pmc = smd->pmc; + unsigned long div = parent_rate / rate; + + if (parent_rate % rate || div < 1 || div > (SMD_MAX_DIV + 1)) + return -EINVAL; +- tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMD_DIV; +- tmp |= (div - 1) << SMD_DIV_SHIFT; +- pmc_write(pmc, AT91_PMC_SMD, tmp); ++ ++ regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMD_DIV, ++ (div - 1) << SMD_DIV_SHIFT); + + return 0; + } +@@ -114,7 +112,7 @@ + }; + + static struct clk * __init +-at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name, ++at91sam9x5_clk_register_smd(struct regmap *regmap, const char *name, + const char **parent_names, u8 num_parents) + { + struct at91sam9x5_clk_smd *smd; +@@ -132,7 +130,7 @@ + init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE; + + smd->hw.init = &init; +- smd->pmc = pmc; ++ smd->regmap = regmap; + + clk = clk_register(NULL, &smd->hw); + if (IS_ERR(clk)) +@@ -141,13 +139,13 @@ + return clk; + } + +-void __init of_at91sam9x5_clk_smd_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_smd_setup(struct device_node *np) + { + struct clk *clk; + int num_parents; + const char *parent_names[SMD_SOURCE_MAX]; + const char *name = np->name; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX) +@@ -157,10 +155,16 @@ + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91sam9x5_clk_register_smd(pmc, name, parent_names, ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ ++ clk = at91sam9x5_clk_register_smd(regmap, name, parent_names, + num_parents); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9x5_clk_smd, "atmel,at91sam9x5-clk-smd", ++ of_at91sam9x5_clk_smd_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-system.c linux-4.4.28/drivers/clk/at91/clk-system.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-system.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-system.c 2016-11-01 21:26:57.940288388 +0100 +@@ -12,13 +12,8 @@ + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -29,9 +24,7 @@ + #define to_clk_system(hw) container_of(hw, struct clk_system, hw) + struct clk_system { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + u8 id; + }; + +@@ -39,58 +32,54 @@ + { + return (id >= 8) && (id <= 15); + } +-static irqreturn_t clk_system_irq_handler(int irq, void *dev_id) ++ ++static inline bool clk_system_ready(struct regmap *regmap, int id) + { +- struct clk_system *sys = (struct clk_system *)dev_id; ++ unsigned int status; + +- wake_up(&sys->wait); +- disable_irq_nosync(sys->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & (1 << id) ? 1 : 0; + } + + static int clk_system_prepare(struct clk_hw *hw) + { + struct clk_system *sys = to_clk_system(hw); +- struct at91_pmc *pmc = sys->pmc; +- u32 mask = 1 << sys->id; + +- pmc_write(pmc, AT91_PMC_SCER, mask); ++ regmap_write(sys->regmap, AT91_PMC_SCER, 1 << sys->id); + + if (!is_pck(sys->id)) + return 0; + +- while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) { +- if (sys->irq) { +- enable_irq(sys->irq); +- wait_event(sys->wait, +- pmc_read(pmc, AT91_PMC_SR) & mask); +- } else +- cpu_relax(); +- } ++ while (!clk_system_ready(sys->regmap, sys->id)) ++ cpu_relax(); ++ + return 0; + } + + static void clk_system_unprepare(struct clk_hw *hw) + { + struct clk_system *sys = to_clk_system(hw); +- struct at91_pmc *pmc = sys->pmc; + +- pmc_write(pmc, AT91_PMC_SCDR, 1 << sys->id); ++ regmap_write(sys->regmap, AT91_PMC_SCDR, 1 << sys->id); + } + + static int clk_system_is_prepared(struct clk_hw *hw) + { + struct clk_system *sys = to_clk_system(hw); +- struct at91_pmc *pmc = sys->pmc; ++ unsigned int status; ++ ++ regmap_read(sys->regmap, AT91_PMC_SCSR, &status); + +- if (!(pmc_read(pmc, AT91_PMC_SCSR) & (1 << sys->id))) ++ if (!(status & (1 << sys->id))) + return 0; + + if (!is_pck(sys->id)) + return 1; + +- return !!(pmc_read(pmc, AT91_PMC_SR) & (1 << sys->id)); ++ regmap_read(sys->regmap, AT91_PMC_SR, &status); ++ ++ return status & (1 << sys->id) ? 1 : 0; + } + + static const struct clk_ops system_ops = { +@@ -100,13 +89,12 @@ + }; + + static struct clk * __init +-at91_clk_register_system(struct at91_pmc *pmc, const char *name, +- const char *parent_name, u8 id, int irq) ++at91_clk_register_system(struct regmap *regmap, const char *name, ++ const char *parent_name, u8 id) + { + struct clk_system *sys; + struct clk *clk = NULL; + struct clk_init_data init; +- int ret; + + if (!parent_name || id > SYSTEM_MAX_ID) + return ERR_PTR(-EINVAL); +@@ -123,44 +111,33 @@ + + sys->id = id; + sys->hw.init = &init; +- sys->pmc = pmc; +- sys->irq = irq; +- if (irq) { +- init_waitqueue_head(&sys->wait); +- irq_set_status_flags(sys->irq, IRQ_NOAUTOEN); +- ret = request_irq(sys->irq, clk_system_irq_handler, +- IRQF_TRIGGER_HIGH, name, sys); +- if (ret) { +- kfree(sys); +- return ERR_PTR(ret); +- } +- } ++ sys->regmap = regmap; + + clk = clk_register(NULL, &sys->hw); +- if (IS_ERR(clk)) { +- if (irq) +- free_irq(sys->irq, sys); ++ if (IS_ERR(clk)) + kfree(sys); +- } + + return clk; + } + +-static void __init +-of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_sys_setup(struct device_node *np) + { + int num; +- int irq = 0; + u32 id; + struct clk *clk; + const char *name; + struct device_node *sysclknp; + const char *parent_name; ++ struct regmap *regmap; + + num = of_get_child_count(np); + if (num > (SYSTEM_MAX_ID + 1)) + return; + ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ + for_each_child_of_node(np, sysclknp) { + if (of_property_read_u32(sysclknp, "reg", &id)) + continue; +@@ -168,21 +145,14 @@ + if (of_property_read_string(np, "clock-output-names", &name)) + name = sysclknp->name; + +- if (is_pck(id)) +- irq = irq_of_parse_and_map(sysclknp, 0); +- + parent_name = of_clk_get_parent_name(sysclknp, 0); + +- clk = at91_clk_register_system(pmc, name, parent_name, id, irq); ++ clk = at91_clk_register_system(regmap, name, parent_name, id); + if (IS_ERR(clk)) + continue; + + of_clk_add_provider(sysclknp, of_clk_src_simple_get, clk); + } + } +- +-void __init of_at91rm9200_clk_sys_setup(struct device_node *np, +- struct at91_pmc *pmc) +-{ +- of_at91_clk_sys_setup(np, pmc); +-} ++CLK_OF_DECLARE(at91rm9200_clk_sys, "atmel,at91rm9200-clk-system", ++ of_at91rm9200_clk_sys_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-usb.c linux-4.4.28/drivers/clk/at91/clk-usb.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-usb.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-usb.c 2016-11-01 21:26:57.940288388 +0100 +@@ -12,8 +12,8 @@ + #include + #include + #include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -27,7 +27,7 @@ + + struct at91sam9x5_clk_usb { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + }; + + #define to_at91sam9x5_clk_usb(hw) \ +@@ -35,7 +35,7 @@ + + struct at91rm9200_clk_usb { + struct clk_hw hw; +- struct at91_pmc *pmc; ++ struct regmap *regmap; + u32 divisors[4]; + }; + +@@ -45,13 +45,12 @@ + static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) + { +- u32 tmp; +- u8 usbdiv; + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; ++ unsigned int usbr; ++ u8 usbdiv; + +- tmp = pmc_read(pmc, AT91_PMC_USB); +- usbdiv = (tmp & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT; ++ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); ++ usbdiv = (usbr & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT; + + return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1)); + } +@@ -109,33 +108,31 @@ + + static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index) + { +- u32 tmp; + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; + + if (index > 1) + return -EINVAL; +- tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS; +- if (index) +- tmp |= AT91_PMC_USBS; +- pmc_write(pmc, AT91_PMC_USB, tmp); ++ ++ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, ++ index ? AT91_PMC_USBS : 0); ++ + return 0; + } + + static u8 at91sam9x5_clk_usb_get_parent(struct clk_hw *hw) + { + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; ++ unsigned int usbr; + +- return pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS; ++ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); ++ ++ return usbr & AT91_PMC_USBS; + } + + static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) + { +- u32 tmp; + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; + unsigned long div; + + if (!rate) +@@ -145,9 +142,8 @@ + if (div > SAM9X5_USB_MAX_DIV + 1 || !div) + return -EINVAL; + +- tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_OHCIUSBDIV; +- tmp |= (div - 1) << SAM9X5_USB_DIV_SHIFT; +- pmc_write(pmc, AT91_PMC_USB, tmp); ++ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_OHCIUSBDIV, ++ (div - 1) << SAM9X5_USB_DIV_SHIFT); + + return 0; + } +@@ -163,28 +159,28 @@ + static int at91sam9n12_clk_usb_enable(struct clk_hw *hw) + { + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; + +- pmc_write(pmc, AT91_PMC_USB, +- pmc_read(pmc, AT91_PMC_USB) | AT91_PMC_USBS); ++ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, ++ AT91_PMC_USBS); ++ + return 0; + } + + static void at91sam9n12_clk_usb_disable(struct clk_hw *hw) + { + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; + +- pmc_write(pmc, AT91_PMC_USB, +- pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS); ++ regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, 0); + } + + static int at91sam9n12_clk_usb_is_enabled(struct clk_hw *hw) + { + struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; ++ unsigned int usbr; + +- return !!(pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS); ++ regmap_read(usb->regmap, AT91_PMC_USB, &usbr); ++ ++ return usbr & AT91_PMC_USBS; + } + + static const struct clk_ops at91sam9n12_usb_ops = { +@@ -197,7 +193,7 @@ + }; + + static struct clk * __init +-at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name, ++at91sam9x5_clk_register_usb(struct regmap *regmap, const char *name, + const char **parent_names, u8 num_parents) + { + struct at91sam9x5_clk_usb *usb; +@@ -216,7 +212,7 @@ + CLK_SET_RATE_PARENT; + + usb->hw.init = &init; +- usb->pmc = pmc; ++ usb->regmap = regmap; + + clk = clk_register(NULL, &usb->hw); + if (IS_ERR(clk)) +@@ -226,7 +222,7 @@ + } + + static struct clk * __init +-at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name, ++at91sam9n12_clk_register_usb(struct regmap *regmap, const char *name, + const char *parent_name) + { + struct at91sam9x5_clk_usb *usb; +@@ -244,7 +240,7 @@ + init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT; + + usb->hw.init = &init; +- usb->pmc = pmc; ++ usb->regmap = regmap; + + clk = clk_register(NULL, &usb->hw); + if (IS_ERR(clk)) +@@ -257,12 +253,12 @@ + unsigned long parent_rate) + { + struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; +- u32 tmp; ++ unsigned int pllbr; + u8 usbdiv; + +- tmp = pmc_read(pmc, AT91_CKGR_PLLBR); +- usbdiv = (tmp & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT; ++ regmap_read(usb->regmap, AT91_CKGR_PLLBR, &pllbr); ++ ++ usbdiv = (pllbr & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT; + if (usb->divisors[usbdiv]) + return parent_rate / usb->divisors[usbdiv]; + +@@ -310,10 +306,8 @@ + static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) + { +- u32 tmp; + int i; + struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw); +- struct at91_pmc *pmc = usb->pmc; + unsigned long div; + + if (!rate) +@@ -323,10 +317,10 @@ + + for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) { + if (usb->divisors[i] == div) { +- tmp = pmc_read(pmc, AT91_CKGR_PLLBR) & +- ~AT91_PMC_USBDIV; +- tmp |= i << RM9200_USB_DIV_SHIFT; +- pmc_write(pmc, AT91_CKGR_PLLBR, tmp); ++ regmap_update_bits(usb->regmap, AT91_CKGR_PLLBR, ++ AT91_PMC_USBDIV, ++ i << RM9200_USB_DIV_SHIFT); ++ + return 0; + } + } +@@ -341,7 +335,7 @@ + }; + + static struct clk * __init +-at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name, ++at91rm9200_clk_register_usb(struct regmap *regmap, const char *name, + const char *parent_name, const u32 *divisors) + { + struct at91rm9200_clk_usb *usb; +@@ -359,7 +353,7 @@ + init.flags = CLK_SET_RATE_PARENT; + + usb->hw.init = &init; +- usb->pmc = pmc; ++ usb->regmap = regmap; + memcpy(usb->divisors, divisors, sizeof(usb->divisors)); + + clk = clk_register(NULL, &usb->hw); +@@ -369,13 +363,13 @@ + return clk; + } + +-void __init of_at91sam9x5_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_usb_setup(struct device_node *np) + { + struct clk *clk; + int num_parents; + const char *parent_names[USB_SOURCE_MAX]; + const char *name = np->name; ++ struct regmap *regmap; + + num_parents = of_clk_get_parent_count(np); + if (num_parents <= 0 || num_parents > USB_SOURCE_MAX) +@@ -385,19 +379,26 @@ + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91sam9x5_clk_register_usb(pmc, name, parent_names, num_parents); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ ++ clk = at91sam9x5_clk_register_usb(regmap, name, parent_names, ++ num_parents); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9x5_clk_usb, "atmel,at91sam9x5-clk-usb", ++ of_at91sam9x5_clk_usb_setup); + +-void __init of_at91sam9n12_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91sam9n12_clk_usb_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_name; + const char *name = np->name; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + if (!parent_name) +@@ -405,20 +406,26 @@ + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91sam9n12_clk_register_usb(pmc, name, parent_name); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ ++ clk = at91sam9n12_clk_register_usb(regmap, name, parent_name); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91sam9n12_clk_usb, "atmel,at91sam9n12-clk-usb", ++ of_at91sam9n12_clk_usb_setup); + +-void __init of_at91rm9200_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc) ++static void __init of_at91rm9200_clk_usb_setup(struct device_node *np) + { + struct clk *clk; + const char *parent_name; + const char *name = np->name; + u32 divisors[4] = {0, 0, 0, 0}; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + if (!parent_name) +@@ -430,9 +437,15 @@ + + of_property_read_string(np, "clock-output-names", &name); + +- clk = at91rm9200_clk_register_usb(pmc, name, parent_name, divisors); ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) ++ return; ++ ++ clk = at91rm9200_clk_register_usb(regmap, name, parent_name, divisors); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + } ++CLK_OF_DECLARE(at91rm9200_clk_usb, "atmel,at91rm9200-clk-usb", ++ of_at91rm9200_clk_usb_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c linux-4.4.28/drivers/clk/at91/clk-utmi.c +--- linux-4.4.28.orig/drivers/clk/at91/clk-utmi.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/clk-utmi.c 2016-11-01 21:26:57.940288388 +0100 +@@ -11,14 +11,9 @@ + #include + #include + #include +-#include +-#include + #include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include "pmc.h" + +@@ -26,37 +21,30 @@ + + struct clk_utmi { + struct clk_hw hw; +- struct at91_pmc *pmc; +- unsigned int irq; +- wait_queue_head_t wait; ++ struct regmap *regmap; + }; + + #define to_clk_utmi(hw) container_of(hw, struct clk_utmi, hw) + +-static irqreturn_t clk_utmi_irq_handler(int irq, void *dev_id) ++static inline bool clk_utmi_ready(struct regmap *regmap) + { +- struct clk_utmi *utmi = (struct clk_utmi *)dev_id; ++ unsigned int status; + +- wake_up(&utmi->wait); +- disable_irq_nosync(utmi->irq); ++ regmap_read(regmap, AT91_PMC_SR, &status); + +- return IRQ_HANDLED; ++ return status & AT91_PMC_LOCKU; + } + + static int clk_utmi_prepare(struct clk_hw *hw) + { + struct clk_utmi *utmi = to_clk_utmi(hw); +- struct at91_pmc *pmc = utmi->pmc; +- u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) | AT91_PMC_UPLLEN | +- AT91_PMC_UPLLCOUNT | AT91_PMC_BIASEN; +- +- pmc_write(pmc, AT91_CKGR_UCKR, tmp); +- +- while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU)) { +- enable_irq(utmi->irq); +- wait_event(utmi->wait, +- pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU); +- } ++ unsigned int uckr = AT91_PMC_UPLLEN | AT91_PMC_UPLLCOUNT | ++ AT91_PMC_BIASEN; ++ ++ regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, uckr, uckr); ++ ++ while (!clk_utmi_ready(utmi->regmap)) ++ cpu_relax(); + + return 0; + } +@@ -64,18 +52,15 @@ + static int clk_utmi_is_prepared(struct clk_hw *hw) + { + struct clk_utmi *utmi = to_clk_utmi(hw); +- struct at91_pmc *pmc = utmi->pmc; + +- return !!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU); ++ return clk_utmi_ready(utmi->regmap); + } + + static void clk_utmi_unprepare(struct clk_hw *hw) + { + struct clk_utmi *utmi = to_clk_utmi(hw); +- struct at91_pmc *pmc = utmi->pmc; +- u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) & ~AT91_PMC_UPLLEN; + +- pmc_write(pmc, AT91_CKGR_UCKR, tmp); ++ regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, AT91_PMC_UPLLEN, 0); + } + + static unsigned long clk_utmi_recalc_rate(struct clk_hw *hw, +@@ -93,10 +78,9 @@ + }; + + static struct clk * __init +-at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq, ++at91_clk_register_utmi(struct regmap *regmap, + const char *name, const char *parent_name) + { +- int ret; + struct clk_utmi *utmi; + struct clk *clk = NULL; + struct clk_init_data init; +@@ -112,52 +96,36 @@ + init.flags = CLK_SET_RATE_GATE; + + utmi->hw.init = &init; +- utmi->pmc = pmc; +- utmi->irq = irq; +- init_waitqueue_head(&utmi->wait); +- irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN); +- ret = request_irq(utmi->irq, clk_utmi_irq_handler, +- IRQF_TRIGGER_HIGH, "clk-utmi", utmi); +- if (ret) { +- kfree(utmi); +- return ERR_PTR(ret); +- } ++ utmi->regmap = regmap; + + clk = clk_register(NULL, &utmi->hw); +- if (IS_ERR(clk)) { +- free_irq(utmi->irq, utmi); ++ if (IS_ERR(clk)) + kfree(utmi); +- } + + return clk; + } + +-static void __init +-of_at91_clk_utmi_setup(struct device_node *np, struct at91_pmc *pmc) ++static void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np) + { +- unsigned int irq; + struct clk *clk; + const char *parent_name; + const char *name = np->name; ++ struct regmap *regmap; + + parent_name = of_clk_get_parent_name(np, 0); + + of_property_read_string(np, "clock-output-names", &name); + +- irq = irq_of_parse_and_map(np, 0); +- if (!irq) ++ regmap = syscon_node_to_regmap(of_get_parent(np)); ++ if (IS_ERR(regmap)) + return; + +- clk = at91_clk_register_utmi(pmc, irq, name, parent_name); ++ clk = at91_clk_register_utmi(regmap, name, parent_name); + if (IS_ERR(clk)) + return; + + of_clk_add_provider(np, of_clk_src_simple_get, clk); + return; + } +- +-void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np, +- struct at91_pmc *pmc) +-{ +- of_at91_clk_utmi_setup(np, pmc); +-} ++CLK_OF_DECLARE(at91sam9x5_clk_utmi, "atmel,at91sam9x5-clk-utmi", ++ of_at91sam9x5_clk_utmi_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.c linux-4.4.28/drivers/clk/at91/pmc.c +--- linux-4.4.28.orig/drivers/clk/at91/pmc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/pmc.c 2016-11-01 21:26:57.940288388 +0100 +@@ -12,36 +12,13 @@ + #include + #include + #include +-#include +-#include +-#include +-#include +-#include +-#include +-#include ++#include ++#include + + #include + + #include "pmc.h" + +-void __iomem *at91_pmc_base; +-EXPORT_SYMBOL_GPL(at91_pmc_base); +- +-void at91rm9200_idle(void) +-{ +- /* +- * Disable the processor clock. The processor will be automatically +- * re-enabled by an interrupt or by a reset. +- */ +- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); +-} +- +-void at91sam9_idle(void) +-{ +- at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK); +- cpu_do_idle(); +-} +- + int of_at91_get_clk_range(struct device_node *np, const char *propname, + struct clk_range *range) + { +@@ -64,402 +41,3 @@ + return 0; + } + EXPORT_SYMBOL_GPL(of_at91_get_clk_range); +- +-static void pmc_irq_mask(struct irq_data *d) +-{ +- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); +- +- pmc_write(pmc, AT91_PMC_IDR, 1 << d->hwirq); +-} +- +-static void pmc_irq_unmask(struct irq_data *d) +-{ +- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); +- +- pmc_write(pmc, AT91_PMC_IER, 1 << d->hwirq); +-} +- +-static int pmc_irq_set_type(struct irq_data *d, unsigned type) +-{ +- if (type != IRQ_TYPE_LEVEL_HIGH) { +- pr_warn("PMC: type not supported (support only IRQ_TYPE_LEVEL_HIGH type)\n"); +- return -EINVAL; +- } +- +- return 0; +-} +- +-static void pmc_irq_suspend(struct irq_data *d) +-{ +- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); +- +- pmc->imr = pmc_read(pmc, AT91_PMC_IMR); +- pmc_write(pmc, AT91_PMC_IDR, pmc->imr); +-} +- +-static void pmc_irq_resume(struct irq_data *d) +-{ +- struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); +- +- pmc_write(pmc, AT91_PMC_IER, pmc->imr); +-} +- +-static struct irq_chip pmc_irq = { +- .name = "PMC", +- .irq_disable = pmc_irq_mask, +- .irq_mask = pmc_irq_mask, +- .irq_unmask = pmc_irq_unmask, +- .irq_set_type = pmc_irq_set_type, +- .irq_suspend = pmc_irq_suspend, +- .irq_resume = pmc_irq_resume, +-}; +- +-static struct lock_class_key pmc_lock_class; +- +-static int pmc_irq_map(struct irq_domain *h, unsigned int virq, +- irq_hw_number_t hw) +-{ +- struct at91_pmc *pmc = h->host_data; +- +- irq_set_lockdep_class(virq, &pmc_lock_class); +- +- irq_set_chip_and_handler(virq, &pmc_irq, +- handle_level_irq); +- irq_set_chip_data(virq, pmc); +- +- return 0; +-} +- +-static int pmc_irq_domain_xlate(struct irq_domain *d, +- struct device_node *ctrlr, +- const u32 *intspec, unsigned int intsize, +- irq_hw_number_t *out_hwirq, +- unsigned int *out_type) +-{ +- struct at91_pmc *pmc = d->host_data; +- const struct at91_pmc_caps *caps = pmc->caps; +- +- if (WARN_ON(intsize < 1)) +- return -EINVAL; +- +- *out_hwirq = intspec[0]; +- +- if (!(caps->available_irqs & (1 << *out_hwirq))) +- return -EINVAL; +- +- *out_type = IRQ_TYPE_LEVEL_HIGH; +- +- return 0; +-} +- +-static const struct irq_domain_ops pmc_irq_ops = { +- .map = pmc_irq_map, +- .xlate = pmc_irq_domain_xlate, +-}; +- +-static irqreturn_t pmc_irq_handler(int irq, void *data) +-{ +- struct at91_pmc *pmc = (struct at91_pmc *)data; +- unsigned long sr; +- int n; +- +- sr = pmc_read(pmc, AT91_PMC_SR) & pmc_read(pmc, AT91_PMC_IMR); +- if (!sr) +- return IRQ_NONE; +- +- for_each_set_bit(n, &sr, BITS_PER_LONG) +- generic_handle_irq(irq_find_mapping(pmc->irqdomain, n)); +- +- return IRQ_HANDLED; +-} +- +-static const struct at91_pmc_caps at91rm9200_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | +- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | +- AT91_PMC_PCK3RDY, +-}; +- +-static const struct at91_pmc_caps at91sam9260_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | +- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY, +-}; +- +-static const struct at91_pmc_caps at91sam9g45_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | +- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY, +-}; +- +-static const struct at91_pmc_caps at91sam9n12_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB | +- AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS | +- AT91_PMC_MOSCRCS | AT91_PMC_CFDEV, +-}; +- +-static const struct at91_pmc_caps at91sam9x5_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | +- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS | +- AT91_PMC_MOSCRCS | AT91_PMC_CFDEV, +-}; +- +-static const struct at91_pmc_caps sama5d2_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | +- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | +- AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS | +- AT91_PMC_CFDEV | AT91_PMC_GCKRDY, +-}; +- +-static const struct at91_pmc_caps sama5d3_caps = { +- .available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY | +- AT91_PMC_LOCKU | AT91_PMC_PCK0RDY | +- AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY | +- AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS | +- AT91_PMC_CFDEV, +-}; +- +-static struct at91_pmc *__init at91_pmc_init(struct device_node *np, +- void __iomem *regbase, int virq, +- const struct at91_pmc_caps *caps) +-{ +- struct at91_pmc *pmc; +- +- if (!regbase || !virq || !caps) +- return NULL; +- +- at91_pmc_base = regbase; +- +- pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); +- if (!pmc) +- return NULL; +- +- spin_lock_init(&pmc->lock); +- pmc->regbase = regbase; +- pmc->virq = virq; +- pmc->caps = caps; +- +- pmc->irqdomain = irq_domain_add_linear(np, 32, &pmc_irq_ops, pmc); +- +- if (!pmc->irqdomain) +- goto out_free_pmc; +- +- pmc_write(pmc, AT91_PMC_IDR, 0xffffffff); +- if (request_irq(pmc->virq, pmc_irq_handler, +- IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc)) +- goto out_remove_irqdomain; +- +- return pmc; +- +-out_remove_irqdomain: +- irq_domain_remove(pmc->irqdomain); +-out_free_pmc: +- kfree(pmc); +- +- return NULL; +-} +- +-static const struct of_device_id pmc_clk_ids[] __initconst = { +- /* Slow oscillator */ +- { +- .compatible = "atmel,at91sam9260-clk-slow", +- .data = of_at91sam9260_clk_slow_setup, +- }, +- /* Main clock */ +- { +- .compatible = "atmel,at91rm9200-clk-main-osc", +- .data = of_at91rm9200_clk_main_osc_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-main-rc-osc", +- .data = of_at91sam9x5_clk_main_rc_osc_setup, +- }, +- { +- .compatible = "atmel,at91rm9200-clk-main", +- .data = of_at91rm9200_clk_main_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-main", +- .data = of_at91sam9x5_clk_main_setup, +- }, +- /* PLL clocks */ +- { +- .compatible = "atmel,at91rm9200-clk-pll", +- .data = of_at91rm9200_clk_pll_setup, +- }, +- { +- .compatible = "atmel,at91sam9g45-clk-pll", +- .data = of_at91sam9g45_clk_pll_setup, +- }, +- { +- .compatible = "atmel,at91sam9g20-clk-pllb", +- .data = of_at91sam9g20_clk_pllb_setup, +- }, +- { +- .compatible = "atmel,sama5d3-clk-pll", +- .data = of_sama5d3_clk_pll_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-plldiv", +- .data = of_at91sam9x5_clk_plldiv_setup, +- }, +- /* Master clock */ +- { +- .compatible = "atmel,at91rm9200-clk-master", +- .data = of_at91rm9200_clk_master_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-master", +- .data = of_at91sam9x5_clk_master_setup, +- }, +- /* System clocks */ +- { +- .compatible = "atmel,at91rm9200-clk-system", +- .data = of_at91rm9200_clk_sys_setup, +- }, +- /* Peripheral clocks */ +- { +- .compatible = "atmel,at91rm9200-clk-peripheral", +- .data = of_at91rm9200_clk_periph_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-peripheral", +- .data = of_at91sam9x5_clk_periph_setup, +- }, +- /* Programmable clocks */ +- { +- .compatible = "atmel,at91rm9200-clk-programmable", +- .data = of_at91rm9200_clk_prog_setup, +- }, +- { +- .compatible = "atmel,at91sam9g45-clk-programmable", +- .data = of_at91sam9g45_clk_prog_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-programmable", +- .data = of_at91sam9x5_clk_prog_setup, +- }, +- /* UTMI clock */ +-#if defined(CONFIG_HAVE_AT91_UTMI) +- { +- .compatible = "atmel,at91sam9x5-clk-utmi", +- .data = of_at91sam9x5_clk_utmi_setup, +- }, +-#endif +- /* USB clock */ +-#if defined(CONFIG_HAVE_AT91_USB_CLK) +- { +- .compatible = "atmel,at91rm9200-clk-usb", +- .data = of_at91rm9200_clk_usb_setup, +- }, +- { +- .compatible = "atmel,at91sam9x5-clk-usb", +- .data = of_at91sam9x5_clk_usb_setup, +- }, +- { +- .compatible = "atmel,at91sam9n12-clk-usb", +- .data = of_at91sam9n12_clk_usb_setup, +- }, +-#endif +- /* SMD clock */ +-#if defined(CONFIG_HAVE_AT91_SMD) +- { +- .compatible = "atmel,at91sam9x5-clk-smd", +- .data = of_at91sam9x5_clk_smd_setup, +- }, +-#endif +-#if defined(CONFIG_HAVE_AT91_H32MX) +- { +- .compatible = "atmel,sama5d4-clk-h32mx", +- .data = of_sama5d4_clk_h32mx_setup, +- }, +-#endif +-#if defined(CONFIG_HAVE_AT91_GENERATED_CLK) +- { +- .compatible = "atmel,sama5d2-clk-generated", +- .data = of_sama5d2_clk_generated_setup, +- }, +-#endif +- { /*sentinel*/ } +-}; +- +-static void __init of_at91_pmc_setup(struct device_node *np, +- const struct at91_pmc_caps *caps) +-{ +- struct at91_pmc *pmc; +- struct device_node *childnp; +- void (*clk_setup)(struct device_node *, struct at91_pmc *); +- const struct of_device_id *clk_id; +- void __iomem *regbase = of_iomap(np, 0); +- int virq; +- +- if (!regbase) +- return; +- +- virq = irq_of_parse_and_map(np, 0); +- if (!virq) +- return; +- +- pmc = at91_pmc_init(np, regbase, virq, caps); +- if (!pmc) +- return; +- for_each_child_of_node(np, childnp) { +- clk_id = of_match_node(pmc_clk_ids, childnp); +- if (!clk_id) +- continue; +- clk_setup = clk_id->data; +- clk_setup(childnp, pmc); +- } +-} +- +-static void __init of_at91rm9200_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &at91rm9200_caps); +-} +-CLK_OF_DECLARE(at91rm9200_clk_pmc, "atmel,at91rm9200-pmc", +- of_at91rm9200_pmc_setup); +- +-static void __init of_at91sam9260_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &at91sam9260_caps); +-} +-CLK_OF_DECLARE(at91sam9260_clk_pmc, "atmel,at91sam9260-pmc", +- of_at91sam9260_pmc_setup); +- +-static void __init of_at91sam9g45_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &at91sam9g45_caps); +-} +-CLK_OF_DECLARE(at91sam9g45_clk_pmc, "atmel,at91sam9g45-pmc", +- of_at91sam9g45_pmc_setup); +- +-static void __init of_at91sam9n12_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &at91sam9n12_caps); +-} +-CLK_OF_DECLARE(at91sam9n12_clk_pmc, "atmel,at91sam9n12-pmc", +- of_at91sam9n12_pmc_setup); +- +-static void __init of_at91sam9x5_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &at91sam9x5_caps); +-} +-CLK_OF_DECLARE(at91sam9x5_clk_pmc, "atmel,at91sam9x5-pmc", +- of_at91sam9x5_pmc_setup); +- +-static void __init of_sama5d2_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &sama5d2_caps); +-} +-CLK_OF_DECLARE(sama5d2_clk_pmc, "atmel,sama5d2-pmc", +- of_sama5d2_pmc_setup); +- +-static void __init of_sama5d3_pmc_setup(struct device_node *np) +-{ +- of_at91_pmc_setup(np, &sama5d3_caps); +-} +-CLK_OF_DECLARE(sama5d3_clk_pmc, "atmel,sama5d3-pmc", +- of_sama5d3_pmc_setup); +diff -Nur linux-4.4.28.orig/drivers/clk/at91/pmc.h linux-4.4.28/drivers/clk/at91/pmc.h +--- linux-4.4.28.orig/drivers/clk/at91/pmc.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clk/at91/pmc.h 2016-11-01 21:26:57.944288652 +0100 +@@ -14,8 +14,11 @@ + + #include + #include ++#include + #include + ++extern spinlock_t pmc_pcr_lock; ++ + struct clk_range { + unsigned long min; + unsigned long max; +@@ -23,102 +26,7 @@ + + #define CLK_RANGE(MIN, MAX) {.min = MIN, .max = MAX,} + +-struct at91_pmc_caps { +- u32 available_irqs; +-}; +- +-struct at91_pmc { +- void __iomem *regbase; +- int virq; +- spinlock_t lock; +- const struct at91_pmc_caps *caps; +- struct irq_domain *irqdomain; +- u32 imr; +-}; +- +-static inline void pmc_lock(struct at91_pmc *pmc) +-{ +- spin_lock(&pmc->lock); +-} +- +-static inline void pmc_unlock(struct at91_pmc *pmc) +-{ +- spin_unlock(&pmc->lock); +-} +- +-static inline u32 pmc_read(struct at91_pmc *pmc, int offset) +-{ +- return readl(pmc->regbase + offset); +-} +- +-static inline void pmc_write(struct at91_pmc *pmc, int offset, u32 value) +-{ +- writel(value, pmc->regbase + offset); +-} +- + int of_at91_get_clk_range(struct device_node *np, const char *propname, + struct clk_range *range); + +-void of_at91sam9260_clk_slow_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_main_osc_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91rm9200_clk_main_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_main_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9g45_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9g20_clk_pllb_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_sama5d3_clk_pll_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_plldiv_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_master_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_master_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_sys_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_periph_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_periph_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9g45_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_prog_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91sam9x5_clk_utmi_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91rm9200_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9x5_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc); +-void of_at91sam9n12_clk_usb_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_at91sam9x5_clk_smd_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_sama5d4_clk_h32mx_setup(struct device_node *np, +- struct at91_pmc *pmc); +- +-void of_sama5d2_clk_generated_setup(struct device_node *np, +- struct at91_pmc *pmc); +- + #endif /* __PMC_H_ */ +diff -Nur linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c linux-4.4.28/drivers/clocksource/tcb_clksrc.c +--- linux-4.4.28.orig/drivers/clocksource/tcb_clksrc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clocksource/tcb_clksrc.c 2016-11-01 21:26:57.948288905 +0100 +@@ -23,8 +23,7 @@ + * this 32 bit free-running counter. the second channel is not used. + * + * - The third channel may be used to provide a 16-bit clockevent +- * source, used in either periodic or oneshot mode. This runs +- * at 32 KiHZ, and can handle delays of up to two seconds. ++ * source, used in either periodic or oneshot mode. + * + * A boot clocksource and clockevent source are also currently needed, + * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so +@@ -74,6 +73,8 @@ + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ bool clk_enabled; ++ u32 freq; + void __iomem *regs; + }; + +@@ -82,15 +83,26 @@ + return container_of(clkevt, struct tc_clkevt_device, clkevt); + } + +-/* For now, we always use the 32K clock ... this optimizes for NO_HZ, +- * because using one of the divided clocks would usually mean the +- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). +- * +- * A divided clock could be good for high resolution timers, since +- * 30.5 usec resolution can seem "low". +- */ + static u32 timer_clock; + ++static void tc_clk_disable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ clk_disable(tcd->clk); ++ tcd->clk_enabled = false; ++} ++ ++static void tc_clk_enable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ if (tcd->clk_enabled) ++ return; ++ clk_enable(tcd->clk); ++ tcd->clk_enabled = true; ++} ++ + static int tc_shutdown(struct clock_event_device *d) + { + struct tc_clkevt_device *tcd = to_tc_clkevt(d); +@@ -98,8 +110,14 @@ + + __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); + __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); ++ return 0; ++} ++ ++static int tc_shutdown_clk_off(struct clock_event_device *d) ++{ ++ tc_shutdown(d); + if (!clockevent_state_detached(d)) +- clk_disable(tcd->clk); ++ tc_clk_disable(d); + + return 0; + } +@@ -112,9 +130,9 @@ + if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) + tc_shutdown(d); + +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and stop */ ++ /* count up to RC, then irq and stop */ + __raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | + ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); + __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -134,12 +152,12 @@ + /* By not making the gentime core emulate periodic mode on top + * of oneshot, we get lower overhead and improved accuracy. + */ +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and restart */ ++ /* count up to RC, then irq and restart */ + __raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +- __raw_writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); ++ __raw_writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); + + /* Enable clock and interrupts on RC compare */ + __raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -166,9 +184,13 @@ + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + /* Should be lower than at91rm9200's system timer */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + .rating = 125, ++#else ++ .rating = 200, ++#endif + .set_next_event = tc_next_event, +- .set_state_shutdown = tc_shutdown, ++ .set_state_shutdown = tc_shutdown_clk_off, + .set_state_periodic = tc_set_periodic, + .set_state_oneshot = tc_set_oneshot, + }, +@@ -188,8 +210,9 @@ + return IRQ_NONE; + } + +-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + int ret; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; +@@ -210,7 +233,11 @@ + clkevt.regs = tc->regs; + clkevt.clk = t2_clk; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk) / divisor; + + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -221,7 +248,7 @@ + return ret; + } + +- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); ++ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); + + return ret; + } +@@ -358,7 +385,11 @@ + goto err_disable_t1; + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + ret = setup_clkevents(tc, clk32k_divisor_idx); ++#else ++ ret = setup_clkevents(tc, best_divisor_idx); ++#endif + if (ret) + goto err_unregister_clksrc; + +diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c linux-4.4.28/drivers/clocksource/timer-atmel-pit.c +--- linux-4.4.28.orig/drivers/clocksource/timer-atmel-pit.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clocksource/timer-atmel-pit.c 2016-11-01 21:26:57.952289162 +0100 +@@ -46,6 +46,7 @@ + u32 cycle; + u32 cnt; + unsigned int irq; ++ bool irq_requested; + struct clk *mck; + }; + +@@ -96,15 +97,29 @@ + + /* disable irq, leaving the clocksource active */ + pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN); ++ if (data->irq_requested) { ++ free_irq(data->irq, data); ++ data->irq_requested = false; ++ } + return 0; + } + ++static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id); + /* + * Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16) + */ + static int pit_clkevt_set_periodic(struct clock_event_device *dev) + { + struct pit_data *data = clkevt_to_pit_data(dev); ++ int ret; ++ ++ ret = request_irq(data->irq, at91sam926x_pit_interrupt, ++ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, ++ "at91_tick", data); ++ if (ret) ++ panic(pr_fmt("Unable to setup IRQ\n")); ++ ++ data->irq_requested = true; + + /* update clocksource counter */ + data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR)); +@@ -181,7 +196,6 @@ + { + unsigned long pit_rate; + unsigned bits; +- int ret; + + /* + * Use our actual MCK to figure out how many MCK/16 ticks per +@@ -206,13 +220,6 @@ + data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS; + clocksource_register_hz(&data->clksrc, pit_rate); + +- /* Set up irq handler */ +- ret = request_irq(data->irq, at91sam926x_pit_interrupt, +- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, +- "at91_tick", data); +- if (ret) +- panic(pr_fmt("Unable to setup IRQ\n")); +- + /* Set up and register clockevents */ + data->clkevt.name = "pit"; + data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC; +diff -Nur linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c linux-4.4.28/drivers/clocksource/timer-atmel-st.c +--- linux-4.4.28.orig/drivers/clocksource/timer-atmel-st.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/clocksource/timer-atmel-st.c 2016-11-01 21:26:57.952289162 +0100 +@@ -115,18 +115,29 @@ + last_crtr = read_CRTR(); + } + ++static int atmel_st_irq; ++ + static int clkevt32k_shutdown(struct clock_event_device *evt) + { + clkdev32k_disable_and_flush_irq(); + irqmask = 0; + regmap_write(regmap_st, AT91_ST_IER, irqmask); ++ free_irq(atmel_st_irq, regmap_st); + return 0; + } + + static int clkevt32k_set_oneshot(struct clock_event_device *dev) + { ++ int ret; ++ + clkdev32k_disable_and_flush_irq(); + ++ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt, ++ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, ++ "at91_tick", regmap_st); ++ if (ret) ++ panic(pr_fmt("Unable to setup IRQ\n")); ++ + /* + * ALM for oneshot irqs, set by next_event() + * before 32 seconds have passed. +@@ -139,8 +150,16 @@ + + static int clkevt32k_set_periodic(struct clock_event_device *dev) + { ++ int ret; ++ + clkdev32k_disable_and_flush_irq(); + ++ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt, ++ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, ++ "at91_tick", regmap_st); ++ if (ret) ++ panic(pr_fmt("Unable to setup IRQ\n")); ++ + /* PIT for periodic irqs; fixed rate of 1/HZ */ + irqmask = AT91_ST_PITS; + regmap_write(regmap_st, AT91_ST_PIMR, timer_latch); +@@ -198,7 +217,7 @@ + { + struct clk *sclk; + unsigned int sclk_rate, val; +- int irq, ret; ++ int ret; + + regmap_st = syscon_node_to_regmap(node); + if (IS_ERR(regmap_st)) +@@ -210,17 +229,10 @@ + regmap_read(regmap_st, AT91_ST_SR, &val); + + /* Get the interrupts property */ +- irq = irq_of_parse_and_map(node, 0); +- if (!irq) ++ atmel_st_irq = irq_of_parse_and_map(node, 0); ++ if (!atmel_st_irq) + panic(pr_fmt("Unable to get IRQ from DT\n")); + +- /* Make IRQs happen for the system timer */ +- ret = request_irq(irq, at91rm9200_timer_interrupt, +- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL, +- "at91_tick", regmap_st); +- if (ret) +- panic(pr_fmt("Unable to setup IRQ\n")); +- + sclk = of_clk_get(node, 0); + if (IS_ERR(sclk)) + panic(pr_fmt("Unable to get slow clock\n")); +diff -Nur linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 linux-4.4.28/drivers/cpufreq/Kconfig.x86 +--- linux-4.4.28.orig/drivers/cpufreq/Kconfig.x86 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/cpufreq/Kconfig.x86 2016-11-01 21:26:57.956289426 +0100 +@@ -123,7 +123,7 @@ + + config X86_POWERNOW_K8 + tristate "AMD Opteron/Athlon64 PowerNow!" +- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ ++ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE + help + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. +diff -Nur linux-4.4.28.orig/drivers/cpuidle/coupled.c linux-4.4.28/drivers/cpuidle/coupled.c +--- linux-4.4.28.orig/drivers/cpuidle/coupled.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/cpuidle/coupled.c 2016-11-01 21:26:57.960289679 +0100 +@@ -119,7 +119,6 @@ + + #define CPUIDLE_COUPLED_NOT_IDLE (-1) + +-static DEFINE_MUTEX(cpuidle_coupled_lock); + static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); + + /* +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c +--- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_execbuffer.c 2016-11-01 21:26:57.980290973 +0100 +@@ -1264,7 +1264,9 @@ + if (ret) + return ret; + ++#ifndef CONFIG_PREEMPT_RT_BASE + trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags); ++#endif + + i915_gem_execbuffer_move_to_active(vmas, params->request); + i915_gem_execbuffer_retire_commands(params); +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c +--- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/i915/i915_gem_shrinker.c 2016-11-01 21:26:57.984291226 +0100 +@@ -39,7 +39,7 @@ + if (!mutex_is_locked(mutex)) + return false; + +-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) ++#if (defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)) && !defined(CONFIG_PREEMPT_RT_BASE) + return mutex->owner == task; + #else + /* Since UP may be pre-empted, we cannot assume that we own the lock */ +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c +--- linux-4.4.28.orig/drivers/gpu/drm/i915/i915_irq.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/i915/i915_irq.c 2016-11-01 21:26:58.000292256 +0100 +@@ -812,6 +812,7 @@ + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -863,6 +864,7 @@ + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c linux-4.4.28/drivers/gpu/drm/i915/intel_display.c +--- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_display.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/i915/intel_display.c 2016-11-01 21:26:58.040294841 +0100 +@@ -11400,7 +11400,7 @@ + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_unpin_work *work; + +- WARN_ON(!in_interrupt()); ++ WARN_ON_NONRT(!in_interrupt()); + + if (crtc == NULL) + return; +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c +--- linux-4.4.28.orig/drivers/gpu/drm/i915/intel_sprite.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/i915/intel_sprite.c 2016-11-01 21:26:58.056295867 +0100 +@@ -38,6 +38,7 @@ + #include "intel_drv.h" + #include + #include "i915_drv.h" ++#include + + static bool + format_is_yuv(uint32_t format) +@@ -64,6 +65,8 @@ + 1000 * adjusted_mode->crtc_htotal); + } + ++static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); ++ + /** + * intel_pipe_update_start() - start update of a set of display registers + * @crtc: the crtc of which the registers are going to be updated +@@ -96,7 +99,7 @@ + min = vblank_start - usecs_to_scanlines(adjusted_mode, 100); + max = vblank_start - 1; + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + + if (min <= 0 || max <= 0) + return; +@@ -126,11 +129,11 @@ + break; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + timeout = schedule_timeout(timeout); + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + } + + finish_wait(wq, &wait); +@@ -164,7 +167,7 @@ + + trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end); + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + if (crtc->debug.start_vbl_count && + crtc->debug.start_vbl_count != end_vbl_count) { +diff -Nur linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c +--- linux-4.4.28.orig/drivers/gpu/drm/radeon/radeon_display.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/gpu/drm/radeon/radeon_display.c 2016-11-01 21:26:58.068296641 +0100 +@@ -1862,6 +1862,7 @@ + struct radeon_device *rdev = dev->dev_private; + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1954,6 +1955,7 @@ + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + /* Decode into vertical and horizontal scanout position. */ + *vpos = position & 0x1fff; +diff -Nur linux-4.4.28.orig/drivers/hv/vmbus_drv.c linux-4.4.28/drivers/hv/vmbus_drv.c +--- linux-4.4.28.orig/drivers/hv/vmbus_drv.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/hv/vmbus_drv.c 2016-11-01 21:26:58.080297414 +0100 +@@ -820,7 +820,7 @@ + tasklet_schedule(&msg_dpc); + } + +- add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0); ++ add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0); + } + + +diff -Nur linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c linux-4.4.28/drivers/i2c/busses/i2c-omap.c +--- linux-4.4.28.orig/drivers/i2c/busses/i2c-omap.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/i2c/busses/i2c-omap.c 2016-11-01 21:26:58.088297935 +0100 +@@ -995,15 +995,12 @@ + u16 mask; + u16 stat; + +- spin_lock(&omap->lock); +- mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); + stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG); ++ mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); + + if (stat & mask) + ret = IRQ_WAKE_THREAD; + +- spin_unlock(&omap->lock); +- + return ret; + } + +diff -Nur linux-4.4.28.orig/drivers/ide/alim15x3.c linux-4.4.28/drivers/ide/alim15x3.c +--- linux-4.4.28.orig/drivers/ide/alim15x3.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/alim15x3.c 2016-11-01 21:26:58.096298444 +0100 +@@ -234,7 +234,7 @@ + + isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + if (m5229_revision < 0xC2) { + /* +@@ -325,7 +325,7 @@ + } + pci_dev_put(north); + pci_dev_put(isa_dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return 0; + } + +diff -Nur linux-4.4.28.orig/drivers/ide/hpt366.c linux-4.4.28/drivers/ide/hpt366.c +--- linux-4.4.28.orig/drivers/ide/hpt366.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/hpt366.c 2016-11-01 21:26:58.100298709 +0100 +@@ -1241,7 +1241,7 @@ + + dma_old = inb(base + 2); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + dma_new = dma_old; + pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma); +@@ -1252,7 +1252,7 @@ + if (dma_new != dma_old) + outb(dma_new, base + 2); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n", + hwif->name, base, base + 7); +diff -Nur linux-4.4.28.orig/drivers/ide/ide-io.c linux-4.4.28/drivers/ide/ide-io.c +--- linux-4.4.28.orig/drivers/ide/ide-io.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/ide-io.c 2016-11-01 21:26:58.108299218 +0100 +@@ -659,7 +659,7 @@ + /* disable_irq_nosync ?? */ + disable_irq(hwif->irq); + /* local CPU only, as if we were handling an interrupt */ +- local_irq_disable(); ++ local_irq_disable_nort(); + if (hwif->polling) { + startstop = handler(drive); + } else if (drive_is_ready(drive)) { +diff -Nur linux-4.4.28.orig/drivers/ide/ide-iops.c linux-4.4.28/drivers/ide/ide-iops.c +--- linux-4.4.28.orig/drivers/ide/ide-iops.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/ide-iops.c 2016-11-01 21:26:58.108299218 +0100 +@@ -129,12 +129,12 @@ + if ((stat & ATA_BUSY) == 0) + break; + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + *rstat = stat; + return -EBUSY; + } + } +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + /* + * Allow status to settle, then read it again. +diff -Nur linux-4.4.28.orig/drivers/ide/ide-io-std.c linux-4.4.28/drivers/ide/ide-io-std.c +--- linux-4.4.28.orig/drivers/ide/ide-io-std.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/ide-io-std.c 2016-11-01 21:26:58.104298962 +0100 +@@ -175,7 +175,7 @@ + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -186,7 +186,7 @@ + insl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +@@ -219,7 +219,7 @@ + unsigned long uninitialized_var(flags); + + if ((io_32bit & 2) && !mmio) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + ata_vlb_sync(io_ports->nsect_addr); + } + +@@ -230,7 +230,7 @@ + outsl(data_addr, buf, words); + + if ((io_32bit & 2) && !mmio) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + if (((len + 1) & 3) < 2) + return; +diff -Nur linux-4.4.28.orig/drivers/ide/ide-probe.c linux-4.4.28/drivers/ide/ide-probe.c +--- linux-4.4.28.orig/drivers/ide/ide-probe.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/ide-probe.c 2016-11-01 21:26:58.116299735 +0100 +@@ -196,10 +196,10 @@ + int bswap = 1; + + /* local CPU only; some systems need this */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + /* read 512 bytes of id info */ + hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + drive->dev_flags |= IDE_DFLAG_ID_READ; + #ifdef DEBUG +diff -Nur linux-4.4.28.orig/drivers/ide/ide-taskfile.c linux-4.4.28/drivers/ide/ide-taskfile.c +--- linux-4.4.28.orig/drivers/ide/ide-taskfile.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/ide/ide-taskfile.c 2016-11-01 21:26:58.116299735 +0100 +@@ -250,7 +250,7 @@ + + page_is_high = PageHighMem(page); + if (page_is_high) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + buf = kmap_atomic(page) + offset; + +@@ -271,7 +271,7 @@ + kunmap_atomic(buf); + + if (page_is_high) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + len -= nr_bytes; + } +@@ -414,7 +414,7 @@ + } + + if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0) +- local_irq_disable(); ++ local_irq_disable_nort(); + + ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE); + +diff -Nur linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +--- linux-4.4.28.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/infiniband/ulp/ipoib/ipoib_multicast.c 2016-11-01 21:26:58.124300256 +0100 +@@ -857,7 +857,7 @@ + + ipoib_dbg_mcast(priv, "restarting multicast task\n"); + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + netif_addr_lock(dev); + spin_lock(&priv->lock); + +@@ -939,7 +939,7 @@ + + spin_unlock(&priv->lock); + netif_addr_unlock(dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + /* + * make sure the in-flight joins have finished before we attempt +diff -Nur linux-4.4.28.orig/drivers/input/gameport/gameport.c linux-4.4.28/drivers/input/gameport/gameport.c +--- linux-4.4.28.orig/drivers/input/gameport/gameport.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/input/gameport/gameport.c 2016-11-01 21:26:58.132300765 +0100 +@@ -91,13 +91,13 @@ + tx = ~0; + + for (i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + t1 = ktime_get_ns(); + for (t = 0; t < 50; t++) + gameport_read(gameport); + t2 = ktime_get_ns(); + t3 = ktime_get_ns(); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + t = (t2 - t1) - (t3 - t2); + if (t < tx) +@@ -124,12 +124,12 @@ + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + GET_TIME(t1); + for (t = 0; t < 50; t++) gameport_read(gameport); + GET_TIME(t2); + GET_TIME(t3); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t; + } +@@ -148,11 +148,11 @@ + tx = 1 << 30; + + for(i = 0; i < 50; i++) { +- local_irq_save(flags); ++ local_irq_save_nort(flags); + t1 = rdtsc(); + for (t = 0; t < 50; t++) gameport_read(gameport); + t2 = rdtsc(); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + udelay(i * 10); + if (t2 - t1 < tx) tx = t2 - t1; + } +diff -Nur linux-4.4.28.orig/drivers/iommu/amd_iommu.c linux-4.4.28/drivers/iommu/amd_iommu.c +--- linux-4.4.28.orig/drivers/iommu/amd_iommu.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/iommu/amd_iommu.c 2016-11-01 21:26:58.156302312 +0100 +@@ -2019,10 +2019,10 @@ + int ret; + + /* +- * Must be called with IRQs disabled. Warn here to detect early +- * when its not. ++ * Must be called with IRQs disabled on a non RT kernel. Warn here to ++ * detect early when its not. + */ +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + + /* lock domain */ + spin_lock(&domain->lock); +@@ -2185,10 +2185,10 @@ + struct protection_domain *domain; + + /* +- * Must be called with IRQs disabled. Warn here to detect early +- * when its not. ++ * Must be called with IRQs disabled on a non RT kernel. Warn here to ++ * detect early when its not. + */ +- WARN_ON(!irqs_disabled()); ++ WARN_ON_NONRT(!irqs_disabled()); + + if (WARN_ON(!dev_data->domain)) + return; +diff -Nur linux-4.4.28.orig/drivers/leds/trigger/Kconfig linux-4.4.28/drivers/leds/trigger/Kconfig +--- linux-4.4.28.orig/drivers/leds/trigger/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/leds/trigger/Kconfig 2016-11-01 21:26:58.168303087 +0100 +@@ -61,7 +61,7 @@ + + config LEDS_TRIGGER_CPU + bool "LED CPU Trigger" +- depends on LEDS_TRIGGERS ++ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE + help + This allows LEDs to be controlled by active CPUs. This shows + the active CPUs across an array of LEDs so you can see which +diff -Nur linux-4.4.28.orig/drivers/md/bcache/Kconfig linux-4.4.28/drivers/md/bcache/Kconfig +--- linux-4.4.28.orig/drivers/md/bcache/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/md/bcache/Kconfig 2016-11-01 21:26:58.172303343 +0100 +@@ -1,6 +1,7 @@ + + config BCACHE + tristate "Block device as cache" ++ depends on !PREEMPT_RT_FULL + ---help--- + Allows a block device to be used as cache for other devices; uses + a btree for indexing and the layout is optimized for SSDs. +diff -Nur linux-4.4.28.orig/drivers/md/dm.c linux-4.4.28/drivers/md/dm.c +--- linux-4.4.28.orig/drivers/md/dm.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/md/dm.c 2016-11-01 21:26:58.196304892 +0100 +@@ -2127,7 +2127,7 @@ + /* Establish tio->ti before queuing work (map_tio_request) */ + tio->ti = ti; + queue_kthread_work(&md->kworker, &tio->work); +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + } + + goto out; +diff -Nur linux-4.4.28.orig/drivers/md/raid5.c linux-4.4.28/drivers/md/raid5.c +--- linux-4.4.28.orig/drivers/md/raid5.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/md/raid5.c 2016-11-01 21:26:58.224306697 +0100 +@@ -1920,8 +1920,9 @@ + struct raid5_percpu *percpu; + unsigned long cpu; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + percpu = per_cpu_ptr(conf->percpu, cpu); ++ spin_lock(&percpu->lock); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; +@@ -1977,7 +1978,8 @@ + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +- put_cpu(); ++ spin_unlock(&percpu->lock); ++ put_cpu_light(); + } + + static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp) +@@ -6414,6 +6416,7 @@ + __func__, cpu); + break; + } ++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); + } + put_online_cpus(); + +diff -Nur linux-4.4.28.orig/drivers/md/raid5.h linux-4.4.28/drivers/md/raid5.h +--- linux-4.4.28.orig/drivers/md/raid5.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/md/raid5.h 2016-11-01 21:26:58.236307469 +0100 +@@ -504,6 +504,7 @@ + int recovery_disabled; + /* per cpu variables */ + struct raid5_percpu { ++ spinlock_t lock; /* Protection for -RT */ + struct page *spare_page; /* Used when checking P/Q in raid6 */ + struct flex_array *scribble; /* space for constructing buffer + * lists and performing address +diff -Nur linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c +--- linux-4.4.28.orig/drivers/media/platform/vsp1/vsp1_video.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/media/platform/vsp1/vsp1_video.c 2016-11-01 21:26:58.244307986 +0100 +@@ -520,7 +520,7 @@ + bool stopped; + + spin_lock_irqsave(&pipe->irqlock, flags); +- stopped = pipe->state == VSP1_PIPELINE_STOPPED, ++ stopped = pipe->state == VSP1_PIPELINE_STOPPED; + spin_unlock_irqrestore(&pipe->irqlock, flags); + + return stopped; +diff -Nur linux-4.4.28.orig/drivers/misc/hwlat_detector.c linux-4.4.28/drivers/misc/hwlat_detector.c +--- linux-4.4.28.orig/drivers/misc/hwlat_detector.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/drivers/misc/hwlat_detector.c 2016-11-01 21:26:58.256308759 +0100 +@@ -0,0 +1,1240 @@ ++/* ++ * hwlat_detector.c - A simple Hardware Latency detector. ++ * ++ * Use this module to detect large system latencies induced by the behavior of ++ * certain underlying system hardware or firmware, independent of Linux itself. ++ * The code was developed originally to detect the presence of SMIs on Intel ++ * and AMD systems, although there is no dependency upon x86 herein. ++ * ++ * The classical example usage of this module is in detecting the presence of ++ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a ++ * somewhat special form of hardware interrupt spawned from earlier CPU debug ++ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge ++ * LPC (or other device) to generate a special interrupt under certain ++ * circumstances, for example, upon expiration of a special SMI timer device, ++ * due to certain external thermal readings, on certain I/O address accesses, ++ * and other situations. An SMI hits a special CPU pin, triggers a special ++ * SMI mode (complete with special memory map), and the OS is unaware. ++ * ++ * Although certain hardware-inducing latencies are necessary (for example, ++ * a modern system often requires an SMI handler for correct thermal control ++ * and remote management) they can wreak havoc upon any OS-level performance ++ * guarantees toward low-latency, especially when the OS is not even made ++ * aware of the presence of these interrupts. For this reason, we need a ++ * somewhat brute force mechanism to detect these interrupts. In this case, ++ * we do it by hogging all of the CPU(s) for configurable timer intervals, ++ * sampling the built-in CPU timer, looking for discontiguous readings. ++ * ++ * WARNING: This implementation necessarily introduces latencies. Therefore, ++ * you should NEVER use this module in a production environment ++ * requiring any kind of low-latency performance guarantee(s). ++ * ++ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. ++ * ++ * Includes useful feedback from Clark Williams ++ * ++ * This file is licensed under the terms of the GNU General Public ++ * License version 2. This program is licensed "as is" without any ++ * warranty of any kind, whether express or implied. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#define BUF_SIZE_DEFAULT 262144UL /* 8K*(sizeof(entry)) */ ++#define BUF_FLAGS (RB_FL_OVERWRITE) /* no block on full */ ++#define U64STR_SIZE 22 /* 20 digits max */ ++ ++#define VERSION "1.0.0" ++#define BANNER "hwlat_detector: " ++#define DRVNAME "hwlat_detector" ++#define DEFAULT_SAMPLE_WINDOW 1000000 /* 1s */ ++#define DEFAULT_SAMPLE_WIDTH 500000 /* 0.5s */ ++#define DEFAULT_LAT_THRESHOLD 10 /* 10us */ ++ ++/* Module metadata */ ++ ++MODULE_LICENSE("GPL"); ++MODULE_AUTHOR("Jon Masters "); ++MODULE_DESCRIPTION("A simple hardware latency detector"); ++MODULE_VERSION(VERSION); ++ ++/* Module parameters */ ++ ++static int debug; ++static int enabled; ++static int threshold; ++ ++module_param(debug, int, 0); /* enable debug */ ++module_param(enabled, int, 0); /* enable detector */ ++module_param(threshold, int, 0); /* latency threshold */ ++ ++/* Buffering and sampling */ ++ ++static struct ring_buffer *ring_buffer; /* sample buffer */ ++static DEFINE_MUTEX(ring_buffer_mutex); /* lock changes */ ++static unsigned long buf_size = BUF_SIZE_DEFAULT; ++static struct task_struct *kthread; /* sampling thread */ ++ ++/* DebugFS filesystem entries */ ++ ++static struct dentry *debug_dir; /* debugfs directory */ ++static struct dentry *debug_max; /* maximum TSC delta */ ++static struct dentry *debug_count; /* total detect count */ ++static struct dentry *debug_sample_width; /* sample width us */ ++static struct dentry *debug_sample_window; /* sample window us */ ++static struct dentry *debug_sample; /* raw samples us */ ++static struct dentry *debug_threshold; /* threshold us */ ++static struct dentry *debug_enable; /* enable/disable */ ++ ++/* Individual samples and global state */ ++ ++struct sample; /* latency sample */ ++struct data; /* Global state */ ++ ++/* Sampling functions */ ++static int __buffer_add_sample(struct sample *sample); ++static struct sample *buffer_get_sample(struct sample *sample); ++ ++/* Threading and state */ ++static int kthread_fn(void *unused); ++static int start_kthread(void); ++static int stop_kthread(void); ++static void __reset_stats(void); ++static int init_stats(void); ++ ++/* Debugfs interface */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry); ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry); ++static int debug_sample_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static int debug_sample_release(struct inode *inode, struct file *filp); ++static int debug_enable_fopen(struct inode *inode, struct file *filp); ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos); ++static ssize_t debug_enable_fwrite(struct file *file, ++ const char __user *user_buffer, ++ size_t user_size, loff_t *offset); ++ ++/* Initialization functions */ ++static int init_debugfs(void); ++static void free_debugfs(void); ++static int detector_init(void); ++static void detector_exit(void); ++ ++/* Individual latency samples are stored here when detected and packed into ++ * the ring_buffer circular buffer, where they are overwritten when ++ * more than buf_size/sizeof(sample) samples are received. */ ++struct sample { ++ u64 seqnum; /* unique sequence */ ++ u64 duration; /* ktime delta */ ++ u64 outer_duration; /* ktime delta (outer loop) */ ++ struct timespec timestamp; /* wall time */ ++ unsigned long lost; ++}; ++ ++/* keep the global state somewhere. */ ++static struct data { ++ ++ struct mutex lock; /* protect changes */ ++ ++ u64 count; /* total since reset */ ++ u64 max_sample; /* max hardware latency */ ++ u64 threshold; /* sample threshold level */ ++ ++ u64 sample_window; /* total sampling window (on+off) */ ++ u64 sample_width; /* active sampling portion of window */ ++ ++ atomic_t sample_open; /* whether the sample file is open */ ++ ++ wait_queue_head_t wq; /* waitqeue for new sample values */ ++ ++} data; ++ ++/** ++ * __buffer_add_sample - add a new latency sample recording to the ring buffer ++ * @sample: The new latency sample value ++ * ++ * This receives a new latency sample and records it in a global ring buffer. ++ * No additional locking is used in this case. ++ */ ++static int __buffer_add_sample(struct sample *sample) ++{ ++ return ring_buffer_write(ring_buffer, ++ sizeof(struct sample), sample); ++} ++ ++/** ++ * buffer_get_sample - remove a hardware latency sample from the ring buffer ++ * @sample: Pre-allocated storage for the sample ++ * ++ * This retrieves a hardware latency sample from the global circular buffer ++ */ ++static struct sample *buffer_get_sample(struct sample *sample) ++{ ++ struct ring_buffer_event *e = NULL; ++ struct sample *s = NULL; ++ unsigned int cpu = 0; ++ ++ if (!sample) ++ return NULL; ++ ++ mutex_lock(&ring_buffer_mutex); ++ for_each_online_cpu(cpu) { ++ e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost); ++ if (e) ++ break; ++ } ++ ++ if (e) { ++ s = ring_buffer_event_data(e); ++ memcpy(sample, s, sizeof(struct sample)); ++ } else ++ sample = NULL; ++ mutex_unlock(&ring_buffer_mutex); ++ ++ return sample; ++} ++ ++#ifndef CONFIG_TRACING ++#define time_type ktime_t ++#define time_get() ktime_get() ++#define time_to_us(x) ktime_to_us(x) ++#define time_sub(a, b) ktime_sub(a, b) ++#define init_time(a, b) (a).tv64 = b ++#define time_u64(a) ((a).tv64) ++#else ++#define time_type u64 ++#define time_get() trace_clock_local() ++#define time_to_us(x) div_u64(x, 1000) ++#define time_sub(a, b) ((a) - (b)) ++#define init_time(a, b) (a = b) ++#define time_u64(a) a ++#endif ++/** ++ * get_sample - sample the CPU TSC and look for likely hardware latencies ++ * ++ * Used to repeatedly capture the CPU TSC (or similar), looking for potential ++ * hardware-induced latency. Called with interrupts disabled and with ++ * data.lock held. ++ */ ++static int get_sample(void) ++{ ++ time_type start, t1, t2, last_t2; ++ s64 diff, total = 0; ++ u64 sample = 0; ++ u64 outer_sample = 0; ++ int ret = -1; ++ ++ init_time(last_t2, 0); ++ start = time_get(); /* start timestamp */ ++ ++ do { ++ ++ t1 = time_get(); /* we'll look for a discontinuity */ ++ t2 = time_get(); ++ ++ if (time_u64(last_t2)) { ++ /* Check the delta from outer loop (t2 to next t1) */ ++ diff = time_to_us(time_sub(t1, last_t2)); ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ pr_err(BANNER "time running backwards\n"); ++ goto out; ++ } ++ if (diff > outer_sample) ++ outer_sample = diff; ++ } ++ last_t2 = t2; ++ ++ total = time_to_us(time_sub(t2, start)); /* sample width */ ++ ++ /* This checks the inner loop (t1 to t2) */ ++ diff = time_to_us(time_sub(t2, t1)); /* current diff */ ++ ++ /* This shouldn't happen */ ++ if (diff < 0) { ++ pr_err(BANNER "time running backwards\n"); ++ goto out; ++ } ++ ++ if (diff > sample) ++ sample = diff; /* only want highest value */ ++ ++ } while (total <= data.sample_width); ++ ++ ret = 0; ++ ++ /* If we exceed the threshold value, we have found a hardware latency */ ++ if (sample > data.threshold || outer_sample > data.threshold) { ++ struct sample s; ++ ++ ret = 1; ++ ++ data.count++; ++ s.seqnum = data.count; ++ s.duration = sample; ++ s.outer_duration = outer_sample; ++ s.timestamp = CURRENT_TIME; ++ __buffer_add_sample(&s); ++ ++ /* Keep a running maximum ever recorded hardware latency */ ++ if (sample > data.max_sample) ++ data.max_sample = sample; ++ } ++ ++out: ++ return ret; ++} ++ ++/* ++ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread ++ * @unused: A required part of the kthread API. ++ * ++ * Used to periodically sample the CPU TSC via a call to get_sample. We ++ * disable interrupts, which does (intentionally) introduce latency since we ++ * need to ensure nothing else might be running (and thus pre-empting). ++ * Obviously this should never be used in production environments. ++ * ++ * Currently this runs on which ever CPU it was scheduled on, but most ++ * real-worald hardware latency situations occur across several CPUs, ++ * but we might later generalize this if we find there are any actualy ++ * systems with alternate SMI delivery or other hardware latencies. ++ */ ++static int kthread_fn(void *unused) ++{ ++ int ret; ++ u64 interval; ++ ++ while (!kthread_should_stop()) { ++ ++ mutex_lock(&data.lock); ++ ++ local_irq_disable(); ++ ret = get_sample(); ++ local_irq_enable(); ++ ++ if (ret > 0) ++ wake_up(&data.wq); /* wake up reader(s) */ ++ ++ interval = data.sample_window - data.sample_width; ++ do_div(interval, USEC_PER_MSEC); /* modifies interval value */ ++ ++ mutex_unlock(&data.lock); ++ ++ if (msleep_interruptible(interval)) ++ break; ++ } ++ ++ return 0; ++} ++ ++/** ++ * start_kthread - Kick off the hardware latency sampling/detector kthread ++ * ++ * This starts a kernel thread that will sit and sample the CPU timestamp ++ * counter (TSC or similar) and look for potential hardware latencies. ++ */ ++static int start_kthread(void) ++{ ++ kthread = kthread_run(kthread_fn, NULL, ++ DRVNAME); ++ if (IS_ERR(kthread)) { ++ pr_err(BANNER "could not start sampling thread\n"); ++ enabled = 0; ++ return -ENOMEM; ++ } ++ ++ return 0; ++} ++ ++/** ++ * stop_kthread - Inform the hardware latency samping/detector kthread to stop ++ * ++ * This kicks the running hardware latency sampling/detector kernel thread and ++ * tells it to stop sampling now. Use this on unload and at system shutdown. ++ */ ++static int stop_kthread(void) ++{ ++ int ret; ++ ++ ret = kthread_stop(kthread); ++ ++ return ret; ++} ++ ++/** ++ * __reset_stats - Reset statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We call this ++ * function in order to reset those when "enable" is toggled on or off, and ++ * also at initialization. Should be called with data.lock held. ++ */ ++static void __reset_stats(void) ++{ ++ data.count = 0; ++ data.max_sample = 0; ++ ring_buffer_reset(ring_buffer); /* flush out old sample entries */ ++} ++ ++/** ++ * init_stats - Setup global state statistics for the hardware latency detector ++ * ++ * We use data to store various statistics and global state. We also use ++ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware ++ * induced system latencies. This function initializes these structures and ++ * allocates the global ring buffer also. ++ */ ++static int init_stats(void) ++{ ++ int ret = -ENOMEM; ++ ++ mutex_init(&data.lock); ++ init_waitqueue_head(&data.wq); ++ atomic_set(&data.sample_open, 0); ++ ++ ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS); ++ ++ if (WARN(!ring_buffer, KERN_ERR BANNER ++ "failed to allocate ring buffer!\n")) ++ goto out; ++ ++ __reset_stats(); ++ data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */ ++ data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */ ++ data.sample_width = DEFAULT_SAMPLE_WIDTH; /* width us */ ++ ++ ret = 0; ++ ++out: ++ return ret; ++ ++} ++ ++/* ++ * simple_data_read - Wrapper read function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * @entry: The entry to read from ++ * ++ * This function provides a generic read implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_read directly, but we need to make sure that the data.lock ++ * is held during the actual read. ++ */ ++static ssize_t simple_data_read(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos, const u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ u64 val = 0; ++ int len = 0; ++ ++ memset(buf, 0, sizeof(buf)); ++ ++ if (!entry) ++ return -EFAULT; ++ ++ mutex_lock(&data.lock); ++ val = *entry; ++ mutex_unlock(&data.lock); ++ ++ len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val); ++ ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); ++ ++} ++ ++/* ++ * simple_data_write - Wrapper write function for global state debugfs entries ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to write value from ++ * @cnt: The maximum number of bytes to write ++ * @ppos: The current "file" position ++ * @entry: The entry to write to ++ * ++ * This function provides a generic write implementation for the global state ++ * "data" structure debugfs filesystem entries. It would be nice to use ++ * simple_attr_write directly, but we need to make sure that the data.lock ++ * is held during the actual write. ++ */ ++static ssize_t simple_data_write(struct file *filp, const char __user *ubuf, ++ size_t cnt, loff_t *ppos, u64 *entry) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ *entry = val; ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/** ++ * debug_count_fopen - Open function for "count" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "count" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_count_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_count_fread - Read function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to read the ++ * number of latency readings exceeding the configured threshold since ++ * the detector was last reset (e.g. by writing a zero into "count"). ++ */ ++static ssize_t debug_count_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_count_fwrite - Write function for "count" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "count" debugfs ++ * interface to the hardware latency detector. Can be used to write a ++ * desired value, especially to zero the total count. ++ */ ++static ssize_t debug_count_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.count); ++} ++ ++/** ++ * debug_enable_fopen - Dummy open function for "enable" debugfs interface ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "enable" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_enable_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_enable_fread - Read function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * whether the detector is currently enabled ("0\n" or "1\n" returned). ++ */ ++static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[4]; ++ ++ if ((cnt < sizeof(buf)) || (*ppos)) ++ return 0; ++ ++ buf[0] = enabled ? '1' : '0'; ++ buf[1] = '\n'; ++ buf[2] = '\0'; ++ if (copy_to_user(ubuf, buf, strlen(buf))) ++ return -EFAULT; ++ return *ppos = strlen(buf); ++} ++ ++/** ++ * debug_enable_fwrite - Write function for "enable" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "enable" debugfs ++ * interface to the hardware latency detector. Can be used to enable or ++ * disable the detector, which will have the side-effect of possibly ++ * also resetting the global stats and kicking off the measuring ++ * kthread (on an enable) or the converse (upon a disable). ++ */ ++static ssize_t debug_enable_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[4]; ++ int csize = min(cnt, sizeof(buf)); ++ long val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[sizeof(buf)-1] = '\0'; /* just in case */ ++ err = kstrtoul(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ if (val) { ++ if (enabled) ++ goto unlock; ++ enabled = 1; ++ __reset_stats(); ++ if (start_kthread()) ++ return -EFAULT; ++ } else { ++ if (!enabled) ++ goto unlock; ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) { ++ pr_err(BANNER "cannot stop kthread\n"); ++ return -EFAULT; ++ } ++ wake_up(&data.wq); /* reader(s) should return */ ++ } ++unlock: ++ return csize; ++} ++ ++/** ++ * debug_max_fopen - Open function for "max" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "max" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_max_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_max_fread - Read function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to determine ++ * the maximum latency value observed since it was last reset. ++ */ ++static ssize_t debug_max_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++/** ++ * debug_max_fwrite - Write function for "max" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "max" debugfs ++ * interface to the hardware latency detector. Can be used to reset the ++ * maximum or set it to some other desired value - if, then, subsequent ++ * measurements exceed this value, the maximum will be updated. ++ */ ++static ssize_t debug_max_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample); ++} ++ ++ ++/** ++ * debug_sample_fopen - An open function for "sample" debugfs interface ++ * @inode: The in-kernel inode representation of this debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function handles opening the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. Can be opened blocking or non-blocking, ++ * affecting whether it behaves as a buffer read pipe, or does not. ++ * Implements simple locking to prevent multiple simultaneous use. ++ */ ++static int debug_sample_fopen(struct inode *inode, struct file *filp) ++{ ++ if (!atomic_add_unless(&data.sample_open, 1, 1)) ++ return -EBUSY; ++ else ++ return 0; ++} ++ ++/** ++ * debug_sample_fread - A read function for "sample" debugfs interface ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that will contain the samples read ++ * @cnt: The maximum bytes to read from the debugfs "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function handles reading from the "sample" file within the hardware ++ * latency detector debugfs directory interface. This file is used to read ++ * raw samples from the global ring_buffer and allows the user to see a ++ * running latency history. By default this will block pending a new ++ * value written into the sample buffer, unless there are already a ++ * number of value(s) waiting in the buffer, or the sample file was ++ * previously opened in a non-blocking mode of operation. ++ */ ++static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ int len = 0; ++ char buf[64]; ++ struct sample *sample = NULL; ++ ++ if (!enabled) ++ return 0; ++ ++ sample = kzalloc(sizeof(struct sample), GFP_KERNEL); ++ if (!sample) ++ return -ENOMEM; ++ ++ while (!buffer_get_sample(sample)) { ++ ++ DEFINE_WAIT(wait); ++ ++ if (filp->f_flags & O_NONBLOCK) { ++ len = -EAGAIN; ++ goto out; ++ } ++ ++ prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE); ++ schedule(); ++ finish_wait(&data.wq, &wait); ++ ++ if (signal_pending(current)) { ++ len = -EINTR; ++ goto out; ++ } ++ ++ if (!enabled) { /* enable was toggled */ ++ len = 0; ++ goto out; ++ } ++ } ++ ++ len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n", ++ sample->timestamp.tv_sec, ++ sample->timestamp.tv_nsec, ++ sample->duration, ++ sample->outer_duration); ++ ++ ++ /* handling partial reads is more trouble than it's worth */ ++ if (len > cnt) ++ goto out; ++ ++ if (copy_to_user(ubuf, buf, len)) ++ len = -EFAULT; ++ ++out: ++ kfree(sample); ++ return len; ++} ++ ++/** ++ * debug_sample_release - Release function for "sample" debugfs interface ++ * @inode: The in-kernel inode represenation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function completes the close of the debugfs interface "sample" file. ++ * Frees the sample_open "lock" so that other users may open the interface. ++ */ ++static int debug_sample_release(struct inode *inode, struct file *filp) ++{ ++ atomic_dec(&data.sample_open); ++ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fopen - Open function for "threshold" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_threshold_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_threshold_fread - Read function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * the current threshold level at which a latency will be recorded in the ++ * global ring buffer, typically on the order of 10us. ++ */ ++static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold); ++} ++ ++/** ++ * debug_threshold_fwrite - Write function for "threshold" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "threshold" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * the threshold level at which any subsequently detected latencies will ++ * be recorded into the global ring buffer. ++ */ ++static ssize_t debug_threshold_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ int ret; ++ ++ ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return ret; ++} ++ ++/** ++ * debug_width_fopen - Open function for "width" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "width" debugfs ++ * interface to the hardware latency detector. ++ */ ++static int debug_width_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_width_fread - Read function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to determine ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latecy periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. ++ */ ++static ssize_t debug_width_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width); ++} ++ ++/** ++ * debug_width_fwrite - Write function for "width" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "width" debugfs ++ * interface to the hardware latency detector. It can be used to configure ++ * for how many us of the total window us we will actively sample for any ++ * hardware-induced latency periods. Obviously, it is not possible to ++ * sample constantly and have the system respond to a sample reader, or, ++ * worse, without having the system appear to have gone out to lunch. It ++ * is enforced that width is less that the total window size. ++ */ ++static ssize_t debug_width_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (val < data.sample_window) ++ data.sample_width = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ if (enabled) ++ wake_up_process(kthread); ++ ++ return csize; ++} ++ ++/** ++ * debug_window_fopen - Open function for "window" debugfs entry ++ * @inode: The in-kernel inode representation of the debugfs "file" ++ * @filp: The active open file structure for the debugfs "file" ++ * ++ * This function provides an open implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. ++ */ ++static int debug_window_fopen(struct inode *inode, struct file *filp) ++{ ++ return 0; ++} ++ ++/** ++ * debug_window_fread - Read function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The userspace provided buffer to read value into ++ * @cnt: The maximum number of bytes to read ++ * @ppos: The current "file" position ++ * ++ * This function provides a read implementation for the "window" debugfs ++ * interface to the hardware latency detector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to read the total window size. ++ */ ++static ssize_t debug_window_fread(struct file *filp, char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window); ++} ++ ++/** ++ * debug_window_fwrite - Write function for "window" debugfs entry ++ * @filp: The active open file structure for the debugfs "file" ++ * @ubuf: The user buffer that contains the value to write ++ * @cnt: The maximum number of bytes to write to "file" ++ * @ppos: The current position in the debugfs "file" ++ * ++ * This function provides a write implementation for the "window" debufds ++ * interface to the hardware latency detetector. The window is the total time ++ * in us that will be considered one sample period. Conceptually, windows ++ * occur back-to-back and contain a sample width period during which ++ * actual sampling occurs. Can be used to write a new total window size. It ++ * is enfoced that any value written must be greater than the sample width ++ * size, or an error results. ++ */ ++static ssize_t debug_window_fwrite(struct file *filp, ++ const char __user *ubuf, ++ size_t cnt, ++ loff_t *ppos) ++{ ++ char buf[U64STR_SIZE]; ++ int csize = min(cnt, sizeof(buf)); ++ u64 val = 0; ++ int err = 0; ++ ++ memset(buf, '\0', sizeof(buf)); ++ if (copy_from_user(buf, ubuf, csize)) ++ return -EFAULT; ++ ++ buf[U64STR_SIZE-1] = '\0'; /* just in case */ ++ err = kstrtoull(buf, 10, &val); ++ if (err) ++ return -EINVAL; ++ ++ mutex_lock(&data.lock); ++ if (data.sample_width < val) ++ data.sample_window = val; ++ else { ++ mutex_unlock(&data.lock); ++ return -EINVAL; ++ } ++ mutex_unlock(&data.lock); ++ ++ return csize; ++} ++ ++/* ++ * Function pointers for the "count" debugfs file operations ++ */ ++static const struct file_operations count_fops = { ++ .open = debug_count_fopen, ++ .read = debug_count_fread, ++ .write = debug_count_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "enable" debugfs file operations ++ */ ++static const struct file_operations enable_fops = { ++ .open = debug_enable_fopen, ++ .read = debug_enable_fread, ++ .write = debug_enable_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "max" debugfs file operations ++ */ ++static const struct file_operations max_fops = { ++ .open = debug_max_fopen, ++ .read = debug_max_fread, ++ .write = debug_max_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "sample" debugfs file operations ++ */ ++static const struct file_operations sample_fops = { ++ .open = debug_sample_fopen, ++ .read = debug_sample_fread, ++ .release = debug_sample_release, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "threshold" debugfs file operations ++ */ ++static const struct file_operations threshold_fops = { ++ .open = debug_threshold_fopen, ++ .read = debug_threshold_fread, ++ .write = debug_threshold_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "width" debugfs file operations ++ */ ++static const struct file_operations width_fops = { ++ .open = debug_width_fopen, ++ .read = debug_width_fread, ++ .write = debug_width_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/* ++ * Function pointers for the "window" debugfs file operations ++ */ ++static const struct file_operations window_fops = { ++ .open = debug_window_fopen, ++ .read = debug_window_fread, ++ .write = debug_window_fwrite, ++ .owner = THIS_MODULE, ++}; ++ ++/** ++ * init_debugfs - A function to initialize the debugfs interface files ++ * ++ * This function creates entries in debugfs for "hwlat_detector", including ++ * files to read values from the detector, current samples, and the ++ * maximum sample that has been captured since the hardware latency ++ * dectector was started. ++ */ ++static int init_debugfs(void) ++{ ++ int ret = -ENOMEM; ++ ++ debug_dir = debugfs_create_dir(DRVNAME, NULL); ++ if (!debug_dir) ++ goto err_debug_dir; ++ ++ debug_sample = debugfs_create_file("sample", 0444, ++ debug_dir, NULL, ++ &sample_fops); ++ if (!debug_sample) ++ goto err_sample; ++ ++ debug_count = debugfs_create_file("count", 0444, ++ debug_dir, NULL, ++ &count_fops); ++ if (!debug_count) ++ goto err_count; ++ ++ debug_max = debugfs_create_file("max", 0444, ++ debug_dir, NULL, ++ &max_fops); ++ if (!debug_max) ++ goto err_max; ++ ++ debug_sample_window = debugfs_create_file("window", 0644, ++ debug_dir, NULL, ++ &window_fops); ++ if (!debug_sample_window) ++ goto err_window; ++ ++ debug_sample_width = debugfs_create_file("width", 0644, ++ debug_dir, NULL, ++ &width_fops); ++ if (!debug_sample_width) ++ goto err_width; ++ ++ debug_threshold = debugfs_create_file("threshold", 0644, ++ debug_dir, NULL, ++ &threshold_fops); ++ if (!debug_threshold) ++ goto err_threshold; ++ ++ debug_enable = debugfs_create_file("enable", 0644, ++ debug_dir, &enabled, ++ &enable_fops); ++ if (!debug_enable) ++ goto err_enable; ++ ++ else { ++ ret = 0; ++ goto out; ++ } ++ ++err_enable: ++ debugfs_remove(debug_threshold); ++err_threshold: ++ debugfs_remove(debug_sample_width); ++err_width: ++ debugfs_remove(debug_sample_window); ++err_window: ++ debugfs_remove(debug_max); ++err_max: ++ debugfs_remove(debug_count); ++err_count: ++ debugfs_remove(debug_sample); ++err_sample: ++ debugfs_remove(debug_dir); ++err_debug_dir: ++out: ++ return ret; ++} ++ ++/** ++ * free_debugfs - A function to cleanup the debugfs file interface ++ */ ++static void free_debugfs(void) ++{ ++ /* could also use a debugfs_remove_recursive */ ++ debugfs_remove(debug_enable); ++ debugfs_remove(debug_threshold); ++ debugfs_remove(debug_sample_width); ++ debugfs_remove(debug_sample_window); ++ debugfs_remove(debug_max); ++ debugfs_remove(debug_count); ++ debugfs_remove(debug_sample); ++ debugfs_remove(debug_dir); ++} ++ ++/** ++ * detector_init - Standard module initialization code ++ */ ++static int detector_init(void) ++{ ++ int ret = -ENOMEM; ++ ++ pr_info(BANNER "version %s\n", VERSION); ++ ++ ret = init_stats(); ++ if (ret) ++ goto out; ++ ++ ret = init_debugfs(); ++ if (ret) ++ goto err_stats; ++ ++ if (enabled) ++ ret = start_kthread(); ++ ++ goto out; ++ ++err_stats: ++ ring_buffer_free(ring_buffer); ++out: ++ return ret; ++ ++} ++ ++/** ++ * detector_exit - Standard module cleanup code ++ */ ++static void detector_exit(void) ++{ ++ int err; ++ ++ if (enabled) { ++ enabled = 0; ++ err = stop_kthread(); ++ if (err) ++ pr_err(BANNER "cannot stop kthread\n"); ++ } ++ ++ free_debugfs(); ++ ring_buffer_free(ring_buffer); /* free up the ring buffer */ ++ ++} ++ ++module_init(detector_init); ++module_exit(detector_exit); +diff -Nur linux-4.4.28.orig/drivers/misc/Kconfig linux-4.4.28/drivers/misc/Kconfig +--- linux-4.4.28.orig/drivers/misc/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/misc/Kconfig 2016-11-01 21:26:58.256308759 +0100 +@@ -54,6 +54,7 @@ + config ATMEL_TCLIB + bool "Atmel AT32/AT91 Timer/Counter Library" + depends on (AVR32 || ARCH_AT91) ++ default y if PREEMPT_RT_FULL + help + Select this if you want a library to allocate the Timer/Counter + blocks found on many Atmel processors. This facilitates using +@@ -69,8 +70,7 @@ + are combined to make a single 32-bit timer. + + When GENERIC_CLOCKEVENTS is defined, the third timer channel +- may be used as a clock event device supporting oneshot mode +- (delays of up to two seconds) based on the 32 KiHz clock. ++ may be used as a clock event device supporting oneshot mode. + + config ATMEL_TCB_CLKSRC_BLOCK + int +@@ -84,6 +84,15 @@ + TC can be used for other purposes, such as PWM generation and + interval timing. + ++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ++ bool "TC Block use 32 KiHz clock" ++ depends on ATMEL_TCB_CLKSRC ++ default y if !PREEMPT_RT_FULL ++ help ++ Select this to use 32 KiHz base clock rate as TC block clock ++ source for clock events. ++ ++ + config DUMMY_IRQ + tristate "Dummy IRQ handler" + default n +@@ -113,6 +122,35 @@ + for information on the specific driver level and support statement + for your IBM server. + ++config HWLAT_DETECTOR ++ tristate "Testing module to detect hardware-induced latencies" ++ depends on DEBUG_FS ++ depends on RING_BUFFER ++ default m ++ ---help--- ++ A simple hardware latency detector. Use this module to detect ++ large latencies introduced by the behavior of the underlying ++ system firmware external to Linux. We do this using periodic ++ use of stop_machine to grab all available CPUs and measure ++ for unexplainable gaps in the CPU timestamp counter(s). By ++ default, the module is not enabled until the "enable" file ++ within the "hwlat_detector" debugfs directory is toggled. ++ ++ This module is often used to detect SMI (System Management ++ Interrupts) on x86 systems, though is not x86 specific. To ++ this end, we default to using a sample window of 1 second, ++ during which we will sample for 0.5 seconds. If an SMI or ++ similar event occurs during that time, it is recorded ++ into an 8K samples global ring buffer until retreived. ++ ++ WARNING: This software should never be enabled (it can be built ++ but should not be turned on after it is loaded) in a production ++ environment where high latencies are a concern since the ++ sampling mechanism actually introduces latencies for ++ regular tasks while the CPU(s) are being held. ++ ++ If unsure, say N ++ + config PHANTOM + tristate "Sensable PHANToM (PCI)" + depends on PCI +diff -Nur linux-4.4.28.orig/drivers/misc/Makefile linux-4.4.28/drivers/misc/Makefile +--- linux-4.4.28.orig/drivers/misc/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/misc/Makefile 2016-11-01 21:26:58.256308759 +0100 +@@ -39,6 +39,7 @@ + obj-$(CONFIG_HMC6352) += hmc6352.o + obj-y += eeprom/ + obj-y += cb710/ ++obj-$(CONFIG_HWLAT_DETECTOR) += hwlat_detector.o + obj-$(CONFIG_SPEAR13XX_PCIE_GADGET) += spear13xx_pcie_gadget.o + obj-$(CONFIG_VMWARE_BALLOON) += vmw_balloon.o + obj-$(CONFIG_ARM_CHARLCD) += arm-charlcd.o +diff -Nur linux-4.4.28.orig/drivers/mmc/host/mmci.c linux-4.4.28/drivers/mmc/host/mmci.c +--- linux-4.4.28.orig/drivers/mmc/host/mmci.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/mmc/host/mmci.c 2016-11-01 21:26:58.268309533 +0100 +@@ -1155,15 +1155,12 @@ + struct sg_mapping_iter *sg_miter = &host->sg_miter; + struct variant_data *variant = host->variant; + void __iomem *base = host->base; +- unsigned long flags; + u32 status; + + status = readl(base + MMCISTATUS); + + dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status); + +- local_irq_save(flags); +- + do { + unsigned int remain, len; + char *buffer; +@@ -1203,8 +1200,6 @@ + + sg_miter_stop(sg_miter); + +- local_irq_restore(flags); +- + /* + * If we have less than the fifo 'half-full' threshold to transfer, + * trigger a PIO interrupt as soon as any data is available. +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c linux-4.4.28/drivers/net/ethernet/3com/3c59x.c +--- linux-4.4.28.orig/drivers/net/ethernet/3com/3c59x.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/3com/3c59x.c 2016-11-01 21:26:58.300311601 +0100 +@@ -842,9 +842,9 @@ + { + struct vortex_private *vp = netdev_priv(dev); + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + #endif + +@@ -1916,12 +1916,12 @@ + * Block interrupts because vortex_interrupt does a bare spin_lock() + */ + unsigned long flags; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (vp->full_bus_master_tx) + boomerang_interrupt(dev->irq, dev); + else + vortex_interrupt(dev->irq, dev); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + } + +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +--- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/atheros/atl1c/atl1c_main.c 2016-11-01 21:26:58.324313148 +0100 +@@ -2221,11 +2221,7 @@ + } + + tpd_req = atl1c_cal_tpd_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) { +- if (netif_msg_pktdata(adapter)) +- dev_info(&adapter->pdev->dev, "tx locked\n"); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1c_tpd_avail(adapter, type) < tpd_req) { + /* no enough descriptor, just stop queue */ +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +--- linux-4.4.28.orig/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/atheros/atl1e/atl1e_main.c 2016-11-01 21:26:58.336313921 +0100 +@@ -1880,8 +1880,7 @@ + return NETDEV_TX_OK; + } + tpd_req = atl1e_cal_tdp_req(skb); +- if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) +- return NETDEV_TX_LOCKED; ++ spin_lock_irqsave(&adapter->tx_lock, flags); + + if (atl1e_tpd_avail(adapter) < tpd_req) { + /* no enough descriptor, just stop queue */ +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c +--- linux-4.4.28.orig/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/chelsio/cxgb/sge.c 2016-11-01 21:26:58.348314695 +0100 +@@ -1664,8 +1664,7 @@ + struct cmdQ *q = &sge->cmdQ[qid]; + unsigned int credits, pidx, genbit, count, use_sched_skb = 0; + +- if (!spin_trylock(&q->lock)) +- return NETDEV_TX_LOCKED; ++ spin_lock(&q->lock); + + reclaim_completed_tx(sge, q); + +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c linux-4.4.28/drivers/net/ethernet/neterion/s2io.c +--- linux-4.4.28.orig/drivers/net/ethernet/neterion/s2io.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/neterion/s2io.c 2016-11-01 21:26:58.372316242 +0100 +@@ -4084,12 +4084,7 @@ + [skb->priority & (MAX_TX_FIFOS - 1)]; + fifo = &mac_control->fifos[queue]; + +- if (do_spin_lock) +- spin_lock_irqsave(&fifo->tx_lock, flags); +- else { +- if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags))) +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&fifo->tx_lock, flags); + + if (sp->config.multiq) { + if (__netif_subqueue_stopped(dev, fifo->fifo_no)) { +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +--- linux-4.4.28.orig/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c 2016-11-01 21:26:58.396317789 +0100 +@@ -2137,10 +2137,8 @@ + struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring; + unsigned long flags; + +- if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) { +- /* Collision - tell upper layer to requeue */ +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&tx_ring->tx_lock, flags); ++ + if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) { + netif_stop_queue(netdev); + spin_unlock_irqrestore(&tx_ring->tx_lock, flags); +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c linux-4.4.28/drivers/net/ethernet/realtek/8139too.c +--- linux-4.4.28.orig/drivers/net/ethernet/realtek/8139too.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/realtek/8139too.c 2016-11-01 21:26:58.416319072 +0100 +@@ -2229,7 +2229,7 @@ + struct rtl8139_private *tp = netdev_priv(dev); + const int irq = tp->pci_dev->irq; + +- disable_irq(irq); ++ disable_irq_nosync(irq); + rtl8139_interrupt(irq, dev); + enable_irq(irq); + } +diff -Nur linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c +--- linux-4.4.28.orig/drivers/net/ethernet/tehuti/tehuti.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/ethernet/tehuti/tehuti.c 2016-11-01 21:26:58.436320363 +0100 +@@ -1629,13 +1629,8 @@ + unsigned long flags; + + ENTER; +- local_irq_save(flags); +- if (!spin_trylock(&priv->tx_lock)) { +- local_irq_restore(flags); +- DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n", +- BDX_DRV_NAME, ndev->name); +- return NETDEV_TX_LOCKED; +- } ++ ++ spin_lock_irqsave(&priv->tx_lock, flags); + + /* build tx descriptor */ + BDX_ASSERT(f->m.wptr >= f->m.memsz); /* started with valid wptr */ +diff -Nur linux-4.4.28.orig/drivers/net/rionet.c linux-4.4.28/drivers/net/rionet.c +--- linux-4.4.28.orig/drivers/net/rionet.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/rionet.c 2016-11-01 21:26:58.448321136 +0100 +@@ -174,11 +174,7 @@ + unsigned long flags; + int add_num = 1; + +- local_irq_save(flags); +- if (!spin_trylock(&rnet->tx_lock)) { +- local_irq_restore(flags); +- return NETDEV_TX_LOCKED; +- } ++ spin_lock_irqsave(&rnet->tx_lock, flags); + + if (is_multicast_ether_addr(eth->h_dest)) + add_num = nets[rnet->mport->id].nact; +diff -Nur linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c +--- linux-4.4.28.orig/drivers/net/wireless/orinoco/orinoco_usb.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/net/wireless/orinoco/orinoco_usb.c 2016-11-01 21:26:58.460321910 +0100 +@@ -697,7 +697,7 @@ + while (!ctx->done.done && msecs--) + udelay(1000); + } else { +- wait_event_interruptible(ctx->done.wait, ++ swait_event_interruptible(ctx->done.wait, + ctx->done.done); + } + break; +diff -Nur linux-4.4.28.orig/drivers/pci/access.c linux-4.4.28/drivers/pci/access.c +--- linux-4.4.28.orig/drivers/pci/access.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/pci/access.c 2016-11-01 21:26:58.472322683 +0100 +@@ -561,7 +561,7 @@ + WARN_ON(!dev->block_cfg_access); + + dev->block_cfg_access = 0; +- wake_up_all(&pci_cfg_wait); ++ wake_up_all_locked(&pci_cfg_wait); + raw_spin_unlock_irqrestore(&pci_lock, flags); + } + EXPORT_SYMBOL_GPL(pci_cfg_access_unlock); +diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c linux-4.4.28/drivers/scsi/fcoe/fcoe.c +--- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/scsi/fcoe/fcoe.c 2016-11-01 21:26:58.496324231 +0100 +@@ -1286,7 +1286,7 @@ + struct sk_buff *skb; + #ifdef CONFIG_SMP + struct fcoe_percpu_s *p0; +- unsigned targ_cpu = get_cpu(); ++ unsigned targ_cpu = get_cpu_light(); + #endif /* CONFIG_SMP */ + + FCOE_DBG("Destroying receive thread for CPU %d\n", cpu); +@@ -1342,7 +1342,7 @@ + kfree_skb(skb); + spin_unlock_bh(&p->fcoe_rx_list.lock); + } +- put_cpu(); ++ put_cpu_light(); + #else + /* + * This a non-SMP scenario where the singular Rx thread is +@@ -1566,11 +1566,11 @@ + static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) + { + struct fcoe_percpu_s *fps; +- int rc; ++ int rc, cpu = get_cpu_light(); + +- fps = &get_cpu_var(fcoe_percpu); ++ fps = &per_cpu(fcoe_percpu, cpu); + rc = fcoe_get_paged_crc_eof(skb, tlen, fps); +- put_cpu_var(fcoe_percpu); ++ put_cpu_light(); + + return rc; + } +@@ -1766,11 +1766,11 @@ + return 0; + } + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + stats->InvalidCRCCount++; + if (stats->InvalidCRCCount < 5) + printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); +- put_cpu(); ++ put_cpu_light(); + return -EINVAL; + } + +@@ -1814,7 +1814,7 @@ + */ + hp = (struct fcoe_hdr *) skb_network_header(skb); + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { + if (stats->ErrorFrames < 5) + printk(KERN_WARNING "fcoe: FCoE version " +@@ -1846,13 +1846,13 @@ + goto drop; + + if (!fcoe_filter_frames(lport, fp)) { +- put_cpu(); ++ put_cpu_light(); + fc_exch_recv(lport, fp); + return; + } + drop: + stats->ErrorFrames++; +- put_cpu(); ++ put_cpu_light(); + kfree_skb(skb); + } + +diff -Nur linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c +--- linux-4.4.28.orig/drivers/scsi/fcoe/fcoe_ctlr.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/scsi/fcoe/fcoe_ctlr.c 2016-11-01 21:26:58.516325525 +0100 +@@ -831,7 +831,7 @@ + + INIT_LIST_HEAD(&del_list); + +- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -867,7 +867,7 @@ + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + + list_for_each_entry_safe(fcf, next, &del_list, list) { + /* Removes fcf from current list */ +diff -Nur linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c linux-4.4.28/drivers/scsi/libfc/fc_exch.c +--- linux-4.4.28.orig/drivers/scsi/libfc/fc_exch.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/scsi/libfc/fc_exch.c 2016-11-01 21:26:58.536326808 +0100 +@@ -814,10 +814,10 @@ + } + memset(ep, 0, sizeof(*ep)); + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = per_cpu_ptr(mp->pool, cpu); + spin_lock_bh(&pool->lock); +- put_cpu(); ++ put_cpu_light(); + + /* peek cache of free slot */ + if (pool->left != FC_XID_UNKNOWN) { +diff -Nur linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c linux-4.4.28/drivers/scsi/libsas/sas_ata.c +--- linux-4.4.28.orig/drivers/scsi/libsas/sas_ata.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/scsi/libsas/sas_ata.c 2016-11-01 21:26:58.548327581 +0100 +@@ -190,7 +190,7 @@ + /* TODO: audit callers to ensure they are ready for qc_issue to + * unconditionally re-enable interrupts + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + spin_unlock(ap->lock); + + /* If the device fell off, no sense in issuing commands */ +@@ -255,7 +255,7 @@ + + out: + spin_lock(ap->lock); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return ret; + } + +diff -Nur linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h +--- linux-4.4.28.orig/drivers/scsi/qla2xxx/qla_inline.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/scsi/qla2xxx/qla_inline.h 2016-11-01 21:26:58.560328355 +0100 +@@ -59,12 +59,12 @@ + { + unsigned long flags; + struct qla_hw_data *ha = rsp->hw; +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (IS_P3P_TYPE(ha)) + qla82xx_poll(0, rsp); + else + ha->isp_ops->intr_handler(0, rsp); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + static inline uint8_t * +diff -Nur linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c +--- linux-4.4.28.orig/drivers/thermal/x86_pkg_temp_thermal.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/thermal/x86_pkg_temp_thermal.c 2016-11-01 21:26:58.572329128 +0100 +@@ -29,6 +29,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -352,7 +353,7 @@ + } + } + +-static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++static void platform_thermal_notify_work(struct swork_event *event) + { + unsigned long flags; + int cpu = smp_processor_id(); +@@ -369,7 +370,7 @@ + pkg_work_scheduled[phy_id]) { + disable_pkg_thres_interrupt(); + spin_unlock_irqrestore(&pkg_work_lock, flags); +- return -EINVAL; ++ return; + } + pkg_work_scheduled[phy_id] = 1; + spin_unlock_irqrestore(&pkg_work_lock, flags); +@@ -378,9 +379,48 @@ + schedule_delayed_work_on(cpu, + &per_cpu(pkg_temp_thermal_threshold_work, cpu), + msecs_to_jiffies(notify_delay_ms)); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct swork_event notify_work; ++ ++static int thermal_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, platform_thermal_notify_work); + return 0; + } + ++static void thermal_notify_work_cleanup(void) ++{ ++ swork_put(); ++} ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ swork_queue(¬ify_work); ++ return 0; ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static int thermal_notify_work_init(void) { return 0; } ++ ++static void thermal_notify_work_cleanup(void) { } ++ ++static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val) ++{ ++ platform_thermal_notify_work(NULL); ++ ++ return 0; ++} ++#endif /* CONFIG_PREEMPT_RT_FULL */ ++ + static int find_siblings_cpu(int cpu) + { + int i; +@@ -584,6 +624,9 @@ + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + ++ if (!thermal_notify_work_init()) ++ return -ENODEV; ++ + spin_lock_init(&pkg_work_lock); + platform_thermal_package_notify = + pkg_temp_thermal_platform_thermal_notify; +@@ -608,7 +651,7 @@ + kfree(pkg_work_scheduled); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; +- ++ thermal_notify_work_cleanup(); + return -ENODEV; + } + +@@ -633,6 +676,7 @@ + mutex_unlock(&phy_dev_list_mutex); + platform_thermal_package_notify = NULL; + platform_thermal_package_rate_control = NULL; ++ thermal_notify_work_cleanup(); + for_each_online_cpu(i) + cancel_delayed_work_sync( + &per_cpu(pkg_temp_thermal_threshold_work, i)); +diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c linux-4.4.28/drivers/tty/serial/8250/8250_core.c +--- linux-4.4.28.orig/drivers/tty/serial/8250/8250_core.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/tty/serial/8250/8250_core.c 2016-11-01 21:26:58.576329393 +0100 +@@ -58,7 +58,16 @@ + + static unsigned int skip_txen_test; /* force skip of txen test at init time */ + +-#define PASS_LIMIT 512 ++/* ++ * On -rt we can have a more delays, and legitimately ++ * so - so don't drop work spuriously and spam the ++ * syslog: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define PASS_LIMIT 1000000 ++#else ++# define PASS_LIMIT 512 ++#endif + + #include + /* +diff -Nur linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c linux-4.4.28/drivers/tty/serial/8250/8250_port.c +--- linux-4.4.28.orig/drivers/tty/serial/8250/8250_port.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/tty/serial/8250/8250_port.c 2016-11-01 21:26:58.596330676 +0100 +@@ -35,6 +35,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -2843,9 +2844,9 @@ + + serial8250_rpm_get(up); + +- if (port->sysrq) ++ if (port->sysrq || oops_in_progress) + locked = 0; +- else if (oops_in_progress) ++ else if (in_kdb_printk()) + locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); +diff -Nur linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c linux-4.4.28/drivers/tty/serial/amba-pl011.c +--- linux-4.4.28.orig/drivers/tty/serial/amba-pl011.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/tty/serial/amba-pl011.c 2016-11-01 21:26:58.608331449 +0100 +@@ -2067,13 +2067,19 @@ + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -2098,8 +2104,7 @@ + writew(old_cr, uap->port.membase + UART011_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } +diff -Nur linux-4.4.28.orig/drivers/tty/serial/omap-serial.c linux-4.4.28/drivers/tty/serial/omap-serial.c +--- linux-4.4.28.orig/drivers/tty/serial/omap-serial.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/tty/serial/omap-serial.c 2016-11-01 21:26:58.620332223 +0100 +@@ -1257,13 +1257,10 @@ + + pm_runtime_get_sync(up->dev); + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1292,8 +1289,7 @@ + pm_runtime_mark_last_busy(up->dev); + pm_runtime_put_autosuspend(up->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init +diff -Nur linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c linux-4.4.28/drivers/tty/serial/sc16is7xx.c +--- linux-4.4.28.orig/drivers/tty/serial/sc16is7xx.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/tty/serial/sc16is7xx.c 2016-11-01 21:26:58.628332740 +0100 +@@ -1230,7 +1230,7 @@ + + /* Setup interrupt */ + ret = devm_request_irq(dev, irq, sc16is7xx_irq, +- IRQF_ONESHOT | flags, dev_name(dev), s); ++ flags, dev_name(dev), s); + if (!ret) + return 0; + +diff -Nur linux-4.4.28.orig/drivers/usb/core/hcd.c linux-4.4.28/drivers/usb/core/hcd.c +--- linux-4.4.28.orig/drivers/usb/core/hcd.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/usb/core/hcd.c 2016-11-01 21:26:58.648334034 +0100 +@@ -1735,9 +1735,9 @@ + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ +- local_irq_save(flags); ++ local_irq_save_nort(flags); + urb->complete(urb); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + + usb_anchor_resume_wakeups(anchor); + atomic_dec(&urb->use_count); +diff -Nur linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c linux-4.4.28/drivers/usb/gadget/function/f_fs.c +--- linux-4.4.28.orig/drivers/usb/gadget/function/f_fs.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/usb/gadget/function/f_fs.c 2016-11-01 21:26:58.680336091 +0100 +@@ -1404,7 +1404,7 @@ + pr_info("%s(): freeing\n", __func__); + ffs_data_clear(ffs); + BUG_ON(waitqueue_active(&ffs->ev.waitq) || +- waitqueue_active(&ffs->ep0req_completion.wait)); ++ swait_active(&ffs->ep0req_completion.wait)); + kfree(ffs->dev_name); + kfree(ffs); + } +diff -Nur linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c linux-4.4.28/drivers/usb/gadget/legacy/inode.c +--- linux-4.4.28.orig/drivers/usb/gadget/legacy/inode.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/usb/gadget/legacy/inode.c 2016-11-01 21:26:58.692336864 +0100 +@@ -345,7 +345,7 @@ + spin_unlock_irq (&epdata->dev->lock); + + if (likely (value == 0)) { +- value = wait_event_interruptible (done.wait, done.done); ++ value = swait_event_interruptible (done.wait, done.done); + if (value != 0) { + spin_lock_irq (&epdata->dev->lock); + if (likely (epdata->ep != NULL)) { +@@ -354,7 +354,7 @@ + usb_ep_dequeue (epdata->ep, epdata->req); + spin_unlock_irq (&epdata->dev->lock); + +- wait_event (done.wait, done.done); ++ swait_event (done.wait, done.done); + if (epdata->status == -ECONNRESET) + epdata->status = -EINTR; + } else { +diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c +--- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.c 2016-11-01 21:26:58.704337638 +0100 +@@ -17,7 +17,9 @@ + #include + #include + #include ++#include + #include ++#include + #include + #include + #include +@@ -1888,20 +1890,15 @@ + #ifdef CONFIG_OF + static void at91sam9rl_toggle_bias(struct usba_udc *udc, int is_on) + { +- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); +- +- if (is_on) +- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); +- else +- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, ++ is_on ? AT91_PMC_BIASEN : 0); + } + + static void at91sam9g45_pulse_bias(struct usba_udc *udc) + { +- unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR); +- +- at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN)); +- at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, 0); ++ regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, ++ AT91_PMC_BIASEN); + } + + static const struct usba_udc_errata at91sam9rl_errata = { +@@ -1938,6 +1935,9 @@ + return ERR_PTR(-EINVAL); + + udc->errata = match->data; ++ udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc"); ++ if (udc->errata && IS_ERR(udc->pmc)) ++ return ERR_CAST(udc->pmc); + + udc->num_ep = 0; + +diff -Nur linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h +--- linux-4.4.28.orig/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/drivers/usb/gadget/udc/atmel_usba_udc.h 2016-11-01 21:26:58.704337638 +0100 +@@ -354,6 +354,8 @@ + struct dentry *debugfs_root; + struct dentry *debugfs_regs; + #endif ++ ++ struct regmap *pmc; + }; + + static inline struct usba_ep *to_usba_ep(struct usb_ep *ep) +diff -Nur linux-4.4.28.orig/fs/aio.c linux-4.4.28/fs/aio.c +--- linux-4.4.28.orig/fs/aio.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/aio.c 2016-11-01 21:26:58.716338411 +0100 +@@ -40,6 +40,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -115,7 +116,7 @@ + struct page **ring_pages; + long nr_pages; + +- struct work_struct free_work; ++ struct swork_event free_work; + + /* + * signals when all in-flight requests are done +@@ -258,6 +259,7 @@ + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; ++ BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -573,9 +575,9 @@ + return cancel(&kiocb->common); + } + +-static void free_ioctx(struct work_struct *work) ++static void free_ioctx(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(work, struct kioctx, free_work); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + + pr_debug("freeing %p\n", ctx); + +@@ -594,8 +596,8 @@ + if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) + complete(&ctx->rq_wait->comp); + +- INIT_WORK(&ctx->free_work, free_ioctx); +- schedule_work(&ctx->free_work); ++ INIT_SWORK(&ctx->free_work, free_ioctx); ++ swork_queue(&ctx->free_work); + } + + /* +@@ -603,9 +605,9 @@ + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_work); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -624,6 +626,14 @@ + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ INIT_SWORK(&ctx->free_work, free_ioctx_users_work); ++ swork_queue(&ctx->free_work); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; +diff -Nur linux-4.4.28.orig/fs/autofs4/autofs_i.h linux-4.4.28/fs/autofs4/autofs_i.h +--- linux-4.4.28.orig/fs/autofs4/autofs_i.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/autofs4/autofs_i.h 2016-11-01 21:26:58.716338411 +0100 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + #include + #include + +diff -Nur linux-4.4.28.orig/fs/autofs4/expire.c linux-4.4.28/fs/autofs4/expire.c +--- linux-4.4.28.orig/fs/autofs4/expire.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/autofs4/expire.c 2016-11-01 21:26:58.716338411 +0100 +@@ -150,7 +150,7 @@ + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + spin_unlock(&p->d_lock); +diff -Nur linux-4.4.28.orig/fs/buffer.c linux-4.4.28/fs/buffer.c +--- linux-4.4.28.orig/fs/buffer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/buffer.c 2016-11-01 21:26:58.716338411 +0100 +@@ -305,8 +305,7 @@ + * decide that the page is now completely done. + */ + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -319,8 +318,7 @@ + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + + /* + * If none of the buffers had errors and they are all +@@ -332,9 +330,7 @@ + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -362,8 +358,7 @@ + } + + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + + clear_buffer_async_write(bh); + unlock_buffer(bh); +@@ -375,15 +370,12 @@ + } + tmp = tmp->b_this_page; + } +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + end_page_writeback(page); + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + EXPORT_SYMBOL(end_buffer_async_write); + +@@ -3325,6 +3317,7 @@ + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + if (ret) { + INIT_LIST_HEAD(&ret->b_assoc_buffers); ++ buffer_head_init_locks(ret); + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); + recalc_bh_state(); +diff -Nur linux-4.4.28.orig/fs/dcache.c linux-4.4.28/fs/dcache.c +--- linux-4.4.28.orig/fs/dcache.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/dcache.c 2016-11-01 21:26:58.720338675 +0100 +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -747,6 +748,8 @@ + */ + void dput(struct dentry *dentry) + { ++ struct dentry *parent; ++ + if (unlikely(!dentry)) + return; + +@@ -783,9 +786,18 @@ + return; + + kill_it: +- dentry = dentry_kill(dentry); +- if (dentry) { +- cond_resched(); ++ parent = dentry_kill(dentry); ++ if (parent) { ++ int r; ++ ++ if (parent == dentry) { ++ /* the task with the highest priority won't schedule */ ++ r = cond_resched(); ++ if (!r) ++ cpu_chill(); ++ } else { ++ dentry = parent; ++ } + goto repeat; + } + } +@@ -2394,7 +2406,7 @@ + if (dentry->d_lockref.count == 1) { + if (!spin_trylock(&inode->i_lock)) { + spin_unlock(&dentry->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto again; + } + dentry->d_flags &= ~DCACHE_CANT_MOUNT; +diff -Nur linux-4.4.28.orig/fs/eventpoll.c linux-4.4.28/fs/eventpoll.c +--- linux-4.4.28.orig/fs/eventpoll.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/eventpoll.c 2016-11-01 21:26:58.720338675 +0100 +@@ -505,12 +505,12 @@ + */ + static void ep_poll_safewake(wait_queue_head_t *wq) + { +- int this_cpu = get_cpu(); ++ int this_cpu = get_cpu_light(); + + ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + +- put_cpu(); ++ put_cpu_light(); + } + + static void ep_remove_wait_queue(struct eppoll_entry *pwq) +diff -Nur linux-4.4.28.orig/fs/exec.c linux-4.4.28/fs/exec.c +--- linux-4.4.28.orig/fs/exec.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/exec.c 2016-11-01 21:26:58.720338675 +0100 +@@ -865,12 +865,14 @@ + } + } + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + if (old_mm) { + up_read(&old_mm->mmap_sem); +diff -Nur linux-4.4.28.orig/fs/f2fs/f2fs.h linux-4.4.28/fs/f2fs/f2fs.h +--- linux-4.4.28.orig/fs/f2fs/f2fs.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/f2fs/f2fs.h 2016-11-01 21:26:58.720338675 +0100 +@@ -24,7 +24,6 @@ + + #ifdef CONFIG_F2FS_CHECK_FS + #define f2fs_bug_on(sbi, condition) BUG_ON(condition) +-#define f2fs_down_write(x, y) down_write_nest_lock(x, y) + #else + #define f2fs_bug_on(sbi, condition) \ + do { \ +@@ -33,7 +32,6 @@ + set_sbi_flag(sbi, SBI_NEED_FSCK); \ + } \ + } while (0) +-#define f2fs_down_write(x, y) down_write(x) + #endif + + /* +@@ -959,7 +957,7 @@ + + static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) + { +- f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex); ++ down_write(&sbi->cp_rwsem); + } + + static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) +diff -Nur linux-4.4.28.orig/fs/jbd2/checkpoint.c linux-4.4.28/fs/jbd2/checkpoint.c +--- linux-4.4.28.orig/fs/jbd2/checkpoint.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/jbd2/checkpoint.c 2016-11-01 21:26:58.720338675 +0100 +@@ -116,6 +116,8 @@ + nblocks = jbd2_space_needed(journal); + while (jbd2_log_space_left(journal) < nblocks) { + write_unlock(&journal->j_state_lock); ++ if (current->plug) ++ io_schedule(); + mutex_lock(&journal->j_checkpoint_mutex); + + /* +diff -Nur linux-4.4.28.orig/fs/namespace.c linux-4.4.28/fs/namespace.c +--- linux-4.4.28.orig/fs/namespace.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/namespace.c 2016-11-01 21:26:58.724338928 +0100 +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include /* init_rootfs */ +@@ -353,8 +354,11 @@ + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) +- cpu_relax(); ++ while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { ++ preempt_enable(); ++ cpu_chill(); ++ preempt_disable(); ++ } + /* + * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will + * be set to match its requirements. So we must not load that until +diff -Nur linux-4.4.28.orig/fs/ntfs/aops.c linux-4.4.28/fs/ntfs/aops.c +--- linux-4.4.28.orig/fs/ntfs/aops.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/ntfs/aops.c 2016-11-01 21:26:58.724338928 +0100 +@@ -107,8 +107,7 @@ + "0x%llx.", (unsigned long long)bh->b_blocknr); + } + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -123,8 +122,7 @@ + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + /* + * If none of the buffers had errors then we can set the page uptodate, + * but we first have to perform the post read mst fixups, if the +@@ -145,13 +143,13 @@ + recs = PAGE_CACHE_SIZE / rec_size; + /* Should have been verified before we got here... */ + BUG_ON(!recs); +- local_irq_save(flags); ++ local_irq_save_nort(flags); + kaddr = kmap_atomic(page); + for (i = 0; i < recs; i++) + post_read_mst_fixup((NTFS_RECORD*)(kaddr + + i * rec_size), rec_size); + kunmap_atomic(kaddr); +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + flush_dcache_page(page); + if (likely(page_uptodate && !PageError(page))) + SetPageUptodate(page); +@@ -159,9 +157,7 @@ + unlock_page(page); + return; + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /** +diff -Nur linux-4.4.28.orig/fs/timerfd.c linux-4.4.28/fs/timerfd.c +--- linux-4.4.28.orig/fs/timerfd.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/fs/timerfd.c 2016-11-01 21:26:58.724338928 +0100 +@@ -450,7 +450,10 @@ + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ if (isalarm(ctx)) ++ hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ else ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* +diff -Nur linux-4.4.28.orig/include/acpi/platform/aclinux.h linux-4.4.28/include/acpi/platform/aclinux.h +--- linux-4.4.28.orig/include/acpi/platform/aclinux.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/acpi/platform/aclinux.h 2016-11-01 21:26:58.724338928 +0100 +@@ -127,6 +127,7 @@ + + #define acpi_cache_t struct kmem_cache + #define acpi_spinlock spinlock_t * ++#define acpi_raw_spinlock raw_spinlock_t * + #define acpi_cpu_flags unsigned long + + /* Use native linux version of acpi_os_allocate_zeroed */ +@@ -145,6 +146,20 @@ + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id + #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock + ++#define acpi_os_create_raw_lock(__handle) \ ++({ \ ++ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ ++ \ ++ if (lock) { \ ++ *(__handle) = lock; \ ++ raw_spin_lock_init(*(__handle)); \ ++ } \ ++ lock ? AE_OK : AE_NO_MEMORY; \ ++ }) ++ ++#define acpi_os_delete_raw_lock(__handle) kfree(__handle) ++ ++ + /* + * OSL interfaces used by debugger/disassembler + */ +diff -Nur linux-4.4.28.orig/include/asm-generic/bug.h linux-4.4.28/include/asm-generic/bug.h +--- linux-4.4.28.orig/include/asm-generic/bug.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/asm-generic/bug.h 2016-11-01 21:26:58.724338928 +0100 +@@ -206,6 +206,20 @@ + # define WARN_ON_SMP(x) ({0;}) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define BUG_ON_RT(c) BUG_ON(c) ++# define BUG_ON_NONRT(c) do { } while (0) ++# define WARN_ON_RT(condition) WARN_ON(condition) ++# define WARN_ON_NONRT(condition) do { } while (0) ++# define WARN_ON_ONCE_NONRT(condition) do { } while (0) ++#else ++# define BUG_ON_RT(c) do { } while (0) ++# define BUG_ON_NONRT(c) BUG_ON(c) ++# define WARN_ON_RT(condition) do { } while (0) ++# define WARN_ON_NONRT(condition) WARN_ON(condition) ++# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition) ++#endif ++ + #endif /* __ASSEMBLY__ */ + + #endif +diff -Nur linux-4.4.28.orig/include/asm-generic/preempt.h linux-4.4.28/include/asm-generic/preempt.h +--- linux-4.4.28.orig/include/asm-generic/preempt.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/asm-generic/preempt.h 2016-11-01 21:26:58.724338928 +0100 +@@ -7,10 +7,10 @@ + + static __always_inline int preempt_count(void) + { +- return current_thread_info()->preempt_count; ++ return READ_ONCE(current_thread_info()->preempt_count); + } + +-static __always_inline int *preempt_count_ptr(void) ++static __always_inline volatile int *preempt_count_ptr(void) + { + return ¤t_thread_info()->preempt_count; + } +diff -Nur linux-4.4.28.orig/include/linux/blkdev.h linux-4.4.28/include/linux/blkdev.h +--- linux-4.4.28.orig/include/linux/blkdev.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/blkdev.h 2016-11-01 21:26:58.724338928 +0100 +@@ -89,6 +89,7 @@ + struct list_head queuelist; + union { + struct call_single_data csd; ++ struct work_struct work; + unsigned long fifo_time; + }; + +@@ -455,7 +456,7 @@ + struct throtl_data *td; + #endif + struct rcu_head rcu_head; +- wait_queue_head_t mq_freeze_wq; ++ struct swait_queue_head mq_freeze_wq; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + +diff -Nur linux-4.4.28.orig/include/linux/blk-mq.h linux-4.4.28/include/linux/blk-mq.h +--- linux-4.4.28.orig/include/linux/blk-mq.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/blk-mq.h 2016-11-01 21:26:58.724338928 +0100 +@@ -212,6 +212,7 @@ + + struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index); + struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int); ++void __blk_mq_complete_request_remote_work(struct work_struct *work); + + int blk_mq_request_started(struct request *rq); + void blk_mq_start_request(struct request *rq); +diff -Nur linux-4.4.28.orig/include/linux/bottom_half.h linux-4.4.28/include/linux/bottom_half.h +--- linux-4.4.28.orig/include/linux/bottom_half.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/bottom_half.h 2016-11-01 21:26:58.724338928 +0100 +@@ -3,6 +3,39 @@ + + #include + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++extern void __local_bh_disable(void); ++extern void _local_bh_enable(void); ++extern void __local_bh_enable(void); ++ ++static inline void local_bh_disable(void) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void local_bh_enable(void) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void local_bh_enable_ip(unsigned long ip) ++{ ++ __local_bh_enable(); ++} ++ ++#else ++ + #ifdef CONFIG_TRACE_IRQFLAGS + extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); + #else +@@ -30,5 +63,6 @@ + { + __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); + } ++#endif + + #endif /* _LINUX_BH_H */ +diff -Nur linux-4.4.28.orig/include/linux/buffer_head.h linux-4.4.28/include/linux/buffer_head.h +--- linux-4.4.28.orig/include/linux/buffer_head.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/buffer_head.h 2016-11-01 21:26:58.724338928 +0100 +@@ -75,8 +75,50 @@ + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ + atomic_t b_count; /* users using this buffer_head */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t b_uptodate_lock; ++#if IS_ENABLED(CONFIG_JBD2) ++ spinlock_t b_state_lock; ++ spinlock_t b_journal_head_lock; ++#endif ++#endif + }; + ++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) ++{ ++ unsigned long flags; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ local_irq_save(flags); ++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); ++#else ++ spin_lock_irqsave(&bh->b_uptodate_lock, flags); ++#endif ++ return flags; ++} ++ ++static inline void ++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) ++{ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); ++ local_irq_restore(flags); ++#else ++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); ++#endif ++} ++ ++static inline void buffer_head_init_locks(struct buffer_head *bh) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spin_lock_init(&bh->b_uptodate_lock); ++#if IS_ENABLED(CONFIG_JBD2) ++ spin_lock_init(&bh->b_state_lock); ++ spin_lock_init(&bh->b_journal_head_lock); ++#endif ++#endif ++} ++ + /* + * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() + * and buffer_foo() functions. +diff -Nur linux-4.4.28.orig/include/linux/cgroup-defs.h linux-4.4.28/include/linux/cgroup-defs.h +--- linux-4.4.28.orig/include/linux/cgroup-defs.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/cgroup-defs.h 2016-11-01 21:26:58.728339185 +0100 +@@ -16,6 +16,7 @@ + #include + #include + #include ++#include + + #ifdef CONFIG_CGROUPS + +@@ -142,6 +143,7 @@ + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; ++ struct swork_event destroy_swork; + }; + + /* +diff -Nur linux-4.4.28.orig/include/linux/clk/at91_pmc.h linux-4.4.28/include/linux/clk/at91_pmc.h +--- linux-4.4.28.orig/include/linux/clk/at91_pmc.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/clk/at91_pmc.h 2016-11-01 21:26:58.728339185 +0100 +@@ -16,18 +16,6 @@ + #ifndef AT91_PMC_H + #define AT91_PMC_H + +-#ifndef __ASSEMBLY__ +-extern void __iomem *at91_pmc_base; +- +-#define at91_pmc_read(field) \ +- readl_relaxed(at91_pmc_base + field) +- +-#define at91_pmc_write(field, value) \ +- writel_relaxed(value, at91_pmc_base + field) +-#else +-.extern at91_pmc_base +-#endif +- + #define AT91_PMC_SCER 0x00 /* System Clock Enable Register */ + #define AT91_PMC_SCDR 0x04 /* System Clock Disable Register */ + +diff -Nur linux-4.4.28.orig/include/linux/completion.h linux-4.4.28/include/linux/completion.h +--- linux-4.4.28.orig/include/linux/completion.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/completion.h 2016-11-01 21:26:58.728339185 +0100 +@@ -7,8 +7,7 @@ + * Atomic wait-for-completion handler data structures. + * See kernel/sched/completion.c for details. + */ +- +-#include ++#include + + /* + * struct completion - structure used to maintain state for a "completion" +@@ -24,11 +23,11 @@ + */ + struct completion { + unsigned int done; +- wait_queue_head_t wait; ++ struct swait_queue_head wait; + }; + + #define COMPLETION_INITIALIZER(work) \ +- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } ++ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } + + #define COMPLETION_INITIALIZER_ONSTACK(work) \ + ({ init_completion(&work); work; }) +@@ -73,7 +72,7 @@ + static inline void init_completion(struct completion *x) + { + x->done = 0; +- init_waitqueue_head(&x->wait); ++ init_swait_queue_head(&x->wait); + } + + /** +diff -Nur linux-4.4.28.orig/include/linux/cpu.h linux-4.4.28/include/linux/cpu.h +--- linux-4.4.28.orig/include/linux/cpu.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/cpu.h 2016-11-01 21:26:58.728339185 +0100 +@@ -231,6 +231,8 @@ + extern void put_online_cpus(void); + extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + #define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri) + #define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri) + #define register_hotcpu_notifier(nb) register_cpu_notifier(nb) +@@ -248,6 +250,8 @@ + #define put_online_cpus() do { } while (0) + #define cpu_hotplug_disable() do { } while (0) + #define cpu_hotplug_enable() do { } while (0) ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } + #define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + #define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0) + /* These aren't inline functions due to a GCC bug. */ +diff -Nur linux-4.4.28.orig/include/linux/delay.h linux-4.4.28/include/linux/delay.h +--- linux-4.4.28.orig/include/linux/delay.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/delay.h 2016-11-01 21:26:58.728339185 +0100 +@@ -52,4 +52,10 @@ + msleep(seconds * 1000); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void cpu_chill(void); ++#else ++# define cpu_chill() cpu_relax() ++#endif ++ + #endif /* defined(_LINUX_DELAY_H) */ +diff -Nur linux-4.4.28.orig/include/linux/ftrace.h linux-4.4.28/include/linux/ftrace.h +--- linux-4.4.28.orig/include/linux/ftrace.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/ftrace.h 2016-11-01 21:26:58.728339185 +0100 +@@ -694,6 +694,18 @@ + #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) + #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) + ++static inline unsigned long get_lock_parent_ip(void) ++{ ++ unsigned long addr = CALLER_ADDR0; ++ ++ if (!in_lock_functions(addr)) ++ return addr; ++ addr = CALLER_ADDR1; ++ if (!in_lock_functions(addr)) ++ return addr; ++ return CALLER_ADDR2; ++} ++ + #ifdef CONFIG_IRQSOFF_TRACER + extern void time_hardirqs_on(unsigned long a0, unsigned long a1); + extern void time_hardirqs_off(unsigned long a0, unsigned long a1); +diff -Nur linux-4.4.28.orig/include/linux/highmem.h linux-4.4.28/include/linux/highmem.h +--- linux-4.4.28.orig/include/linux/highmem.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/highmem.h 2016-11-01 21:26:58.728339185 +0100 +@@ -7,6 +7,7 @@ + #include + #include + #include ++#include + + #include + +@@ -65,7 +66,7 @@ + + static inline void *kmap_atomic(struct page *page) + { +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + return page_address(page); + } +@@ -74,7 +75,7 @@ + static inline void __kunmap_atomic(void *addr) + { + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + + #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) +@@ -86,32 +87,51 @@ + + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + ++#ifndef CONFIG_PREEMPT_RT_FULL + DECLARE_PER_CPU(int, __kmap_atomic_idx); ++#endif + + static inline int kmap_atomic_idx_push(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + +-#ifdef CONFIG_DEBUG_HIGHMEM ++# ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx >= KM_TYPE_NR); +-#endif ++# endif + return idx; ++#else ++ current->kmap_idx++; ++ BUG_ON(current->kmap_idx > KM_TYPE_NR); ++ return current->kmap_idx - 1; ++#endif + } + + static inline int kmap_atomic_idx(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + return __this_cpu_read(__kmap_atomic_idx) - 1; ++#else ++ return current->kmap_idx - 1; ++#endif + } + + static inline void kmap_atomic_idx_pop(void) + { +-#ifdef CONFIG_DEBUG_HIGHMEM ++#ifndef CONFIG_PREEMPT_RT_FULL ++# ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + + BUG_ON(idx < 0); +-#else ++# else + __this_cpu_dec(__kmap_atomic_idx); ++# endif ++#else ++ current->kmap_idx--; ++# ifdef CONFIG_DEBUG_HIGHMEM ++ BUG_ON(current->kmap_idx < 0); ++# endif + #endif + } + +diff -Nur linux-4.4.28.orig/include/linux/hrtimer.h linux-4.4.28/include/linux/hrtimer.h +--- linux-4.4.28.orig/include/linux/hrtimer.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/hrtimer.h 2016-11-01 21:26:58.728339185 +0100 +@@ -87,6 +87,9 @@ + * @function: timer expiry callback function + * @base: pointer to the timer base (per cpu and per clock) + * @state: state information (See bit values above) ++ * @cb_entry: list entry to defer timers from hardirq context ++ * @irqsafe: timer can run in hardirq context ++ * @praecox: timer expiry time if expired at the time of programming + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which + * started the timer +@@ -103,6 +106,11 @@ + enum hrtimer_restart (*function)(struct hrtimer *); + struct hrtimer_clock_base *base; + u8 state; ++ struct list_head cb_entry; ++ int irqsafe; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ ktime_t praecox; ++#endif + u8 is_rel; + #ifdef CONFIG_TIMER_STATS + int start_pid; +@@ -123,11 +131,7 @@ + struct task_struct *task; + }; + +-#ifdef CONFIG_64BIT + # define HRTIMER_CLOCK_BASE_ALIGN 64 +-#else +-# define HRTIMER_CLOCK_BASE_ALIGN 32 +-#endif + + /** + * struct hrtimer_clock_base - the timer base for a specific clock +@@ -136,6 +140,7 @@ + * timer to a base on another cpu. + * @clockid: clock id for per_cpu support + * @active: red black tree root node for the active timers ++ * @expired: list head for deferred timers. + * @get_time: function to retrieve the current time of the clock + * @offset: offset of this clock to the monotonic base + */ +@@ -144,6 +149,7 @@ + int index; + clockid_t clockid; + struct timerqueue_head active; ++ struct list_head expired; + ktime_t (*get_time)(void); + ktime_t offset; + } __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN))); +@@ -187,6 +193,7 @@ + raw_spinlock_t lock; + seqcount_t seq; + struct hrtimer *running; ++ struct hrtimer *running_soft; + unsigned int cpu; + unsigned int active_bases; + unsigned int clock_was_set_seq; +@@ -203,6 +210,9 @@ + unsigned int nr_hangs; + unsigned int max_hang_time; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ wait_queue_head_t wait; ++#endif + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + } ____cacheline_aligned; + +@@ -412,6 +422,13 @@ + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* Softirq preemption could deadlock timer removal */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); ++#else ++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) ++#endif ++ + /* Query timers: */ + extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +@@ -436,7 +453,7 @@ + * Helper function to check, whether the timer is running the callback + * function + */ +-static inline int hrtimer_callback_running(struct hrtimer *timer) ++static inline int hrtimer_callback_running(const struct hrtimer *timer) + { + return timer->base->cpu_base->running == timer; + } +diff -Nur linux-4.4.28.orig/include/linux/idr.h linux-4.4.28/include/linux/idr.h +--- linux-4.4.28.orig/include/linux/idr.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/idr.h 2016-11-01 21:26:58.728339185 +0100 +@@ -95,10 +95,14 @@ + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++void idr_preload_end(void); ++#else + static inline void idr_preload_end(void) + { + preempt_enable(); + } ++#endif + + /** + * idr_find - return pointer for given id +diff -Nur linux-4.4.28.orig/include/linux/init_task.h linux-4.4.28/include/linux/init_task.h +--- linux-4.4.28.orig/include/linux/init_task.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/init_task.h 2016-11-01 21:26:58.728339185 +0100 +@@ -148,9 +148,15 @@ + # define INIT_PERF_EVENTS(tsk) + #endif + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define INIT_TIMER_LIST .posix_timer_list = NULL, ++#else ++# define INIT_TIMER_LIST ++#endif ++ + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + # define INIT_VTIME(tsk) \ +- .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ ++ .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ + .vtime_snap = 0, \ + .vtime_snap_whence = VTIME_SYS, + #else +@@ -239,6 +245,7 @@ + .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ + .timer_slack_ns = 50000, /* 50 usec default slack */ \ ++ INIT_TIMER_LIST \ + .pids = { \ + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ +diff -Nur linux-4.4.28.orig/include/linux/interrupt.h linux-4.4.28/include/linux/interrupt.h +--- linux-4.4.28.orig/include/linux/interrupt.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/interrupt.h 2016-11-01 21:26:58.728339185 +0100 +@@ -61,6 +61,7 @@ + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_SHARED 0x00000080 + #define IRQF_PROBE_SHARED 0x00000100 +@@ -74,6 +75,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_COND_SUSPEND 0x00040000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +@@ -186,7 +188,7 @@ + #ifdef CONFIG_LOCKDEP + # define local_irq_enable_in_hardirq() do { } while (0) + #else +-# define local_irq_enable_in_hardirq() local_irq_enable() ++# define local_irq_enable_in_hardirq() local_irq_enable_nort() + #endif + + extern void disable_irq_nosync(unsigned int irq); +@@ -206,6 +208,7 @@ + * @irq: Interrupt to which notification applies + * @kref: Reference count, for internal use + * @work: Work item, for internal use ++ * @list: List item for deferred callbacks + * @notify: Function to be called on change. This will be + * called in process context. + * @release: Function to be called on release. This will be +@@ -217,6 +220,7 @@ + unsigned int irq; + struct kref kref; + struct work_struct work; ++ struct list_head list; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); + }; +@@ -379,9 +383,13 @@ + bool state); + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + extern bool force_irqthreads; ++# else ++# define force_irqthreads (true) ++# endif + #else +-#define force_irqthreads (0) ++#define force_irqthreads (false) + #endif + + #ifndef __ARCH_SET_SOFTIRQ_PENDING +@@ -438,9 +446,10 @@ + void (*action)(struct softirq_action *); + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); +- ++static inline void thread_do_softirq(void) { do_softirq(); } + #ifdef __ARCH_HAS_DO_SOFTIRQ + void do_softirq_own_stack(void); + #else +@@ -449,13 +458,25 @@ + __do_softirq(); + } + #endif ++#else ++extern void thread_do_softirq(void); ++#endif + + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); + extern void __raise_softirq_irqoff(unsigned int nr); ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void __raise_softirq_irqoff_ksoft(unsigned int nr); ++#else ++static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++} ++#endif + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); ++extern void softirq_check_pending_idle(void); + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +@@ -477,8 +498,9 @@ + to be executed on some cpu at least once after this. + * If the tasklet is already scheduled, but its execution is still not + started, it will be executed only once. +- * If this tasklet is already running on another CPU (or schedule is called +- from tasklet itself), it is rescheduled for later. ++ * If this tasklet is already running on another CPU, it is rescheduled ++ for later. ++ * Schedule must not be called from the tasklet itself (a lockup occurs) + * Tasklet is strictly serialized wrt itself, but not + wrt another tasklets. If client needs some intertask synchronization, + he makes it with spinlocks. +@@ -503,27 +525,36 @@ + enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ +- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_PENDING /* Tasklet is pending */ + }; + +-#ifdef CONFIG_SMP ++#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) ++#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) ++#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++ ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) + { + return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); + } + ++static inline int tasklet_tryunlock(struct tasklet_struct *t) ++{ ++ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; ++} ++ + static inline void tasklet_unlock(struct tasklet_struct *t) + { + smp_mb__before_atomic(); + clear_bit(TASKLET_STATE_RUN, &(t)->state); + } + +-static inline void tasklet_unlock_wait(struct tasklet_struct *t) +-{ +- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +-} ++extern void tasklet_unlock_wait(struct tasklet_struct *t); ++ + #else + #define tasklet_trylock(t) 1 ++#define tasklet_tryunlock(t) 1 + #define tasklet_unlock_wait(t) do { } while (0) + #define tasklet_unlock(t) do { } while (0) + #endif +@@ -572,12 +603,7 @@ + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic(); +- atomic_dec(&t->count); +-} +- ++extern void tasklet_enable(struct tasklet_struct *t); + extern void tasklet_kill(struct tasklet_struct *t); + extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); + extern void tasklet_init(struct tasklet_struct *t, +@@ -608,6 +634,12 @@ + tasklet_kill(&ttimer->tasklet); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void softirq_early_init(void); ++#else ++static inline void softirq_early_init(void) { } ++#endif ++ + /* + * Autoprobing for irqs: + * +diff -Nur linux-4.4.28.orig/include/linux/irqdesc.h linux-4.4.28/include/linux/irqdesc.h +--- linux-4.4.28.orig/include/linux/irqdesc.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/irqdesc.h 2016-11-01 21:26:58.732339449 +0100 +@@ -61,6 +61,7 @@ + unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; ++ u64 random_ip; + raw_spinlock_t lock; + struct cpumask *percpu_enabled; + #ifdef CONFIG_SMP +diff -Nur linux-4.4.28.orig/include/linux/irqflags.h linux-4.4.28/include/linux/irqflags.h +--- linux-4.4.28.orig/include/linux/irqflags.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/irqflags.h 2016-11-01 21:26:58.732339449 +0100 +@@ -25,8 +25,6 @@ + # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) + # define trace_hardirq_enter() do { current->hardirq_context++; } while (0) + # define trace_hardirq_exit() do { current->hardirq_context--; } while (0) +-# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) +-# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) + # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, + #else + # define trace_hardirqs_on() do { } while (0) +@@ -39,9 +37,15 @@ + # define trace_softirqs_enabled(p) 0 + # define trace_hardirq_enter() do { } while (0) + # define trace_hardirq_exit() do { } while (0) ++# define INIT_TRACE_IRQFLAGS ++#endif ++ ++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) ++# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) ++# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) ++#else + # define lockdep_softirq_enter() do { } while (0) + # define lockdep_softirq_exit() do { } while (0) +-# define INIT_TRACE_IRQFLAGS + #endif + + #if defined(CONFIG_IRQSOFF_TRACER) || \ +@@ -148,4 +152,23 @@ + + #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags) + ++/* ++ * local_irq* variants depending on RT/!RT ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define local_irq_disable_nort() do { } while (0) ++# define local_irq_enable_nort() do { } while (0) ++# define local_irq_save_nort(flags) local_save_flags(flags) ++# define local_irq_restore_nort(flags) (void)(flags) ++# define local_irq_disable_rt() local_irq_disable() ++# define local_irq_enable_rt() local_irq_enable() ++#else ++# define local_irq_disable_nort() local_irq_disable() ++# define local_irq_enable_nort() local_irq_enable() ++# define local_irq_save_nort(flags) local_irq_save(flags) ++# define local_irq_restore_nort(flags) local_irq_restore(flags) ++# define local_irq_disable_rt() do { } while (0) ++# define local_irq_enable_rt() do { } while (0) ++#endif ++ + #endif +diff -Nur linux-4.4.28.orig/include/linux/irq.h linux-4.4.28/include/linux/irq.h +--- linux-4.4.28.orig/include/linux/irq.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/irq.h 2016-11-01 21:26:58.728339185 +0100 +@@ -72,6 +72,7 @@ + * IRQ_IS_POLLED - Always polled by another interrupt. Exclude + * it from the spurious interrupt detection + * mechanism and from core side polling. ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + * IRQ_DISABLE_UNLAZY - Disable lazy irq disable + */ + enum { +@@ -99,13 +100,14 @@ + IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_IS_POLLED = (1 << 18), + IRQ_DISABLE_UNLAZY = (1 << 19), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 20), + }; + + #define IRQF_MODIFY_MASK \ + (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ +- IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) ++ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +diff -Nur linux-4.4.28.orig/include/linux/irq_work.h linux-4.4.28/include/linux/irq_work.h +--- linux-4.4.28.orig/include/linux/irq_work.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/irq_work.h 2016-11-01 21:26:58.728339185 +0100 +@@ -16,6 +16,7 @@ + #define IRQ_WORK_BUSY 2UL + #define IRQ_WORK_FLAGS 3UL + #define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */ ++#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */ + + struct irq_work { + unsigned long flags; +@@ -51,4 +52,10 @@ + static inline void irq_work_run(void) { } + #endif + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void); ++#else ++static inline void irq_work_tick_soft(void) { } ++#endif ++ + #endif /* _LINUX_IRQ_WORK_H */ +diff -Nur linux-4.4.28.orig/include/linux/jbd2.h linux-4.4.28/include/linux/jbd2.h +--- linux-4.4.28.orig/include/linux/jbd2.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/jbd2.h 2016-11-01 21:26:58.732339449 +0100 +@@ -352,32 +352,56 @@ + + static inline void jbd_lock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); ++#else ++ spin_lock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_trylock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); ++#else ++ return spin_trylock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_is_locked_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); ++#else ++ return spin_is_locked(&bh->b_state_lock); ++#endif + } + + static inline void jbd_unlock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); ++#else ++ spin_unlock(&bh->b_state_lock); ++#endif + } + + static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); ++#else ++ spin_lock(&bh->b_journal_head_lock); ++#endif + } + + static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); ++#else ++ spin_unlock(&bh->b_journal_head_lock); ++#endif + } + + #define J_ASSERT(assert) BUG_ON(!(assert)) +diff -Nur linux-4.4.28.orig/include/linux/kdb.h linux-4.4.28/include/linux/kdb.h +--- linux-4.4.28.orig/include/linux/kdb.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/kdb.h 2016-11-01 21:26:58.732339449 +0100 +@@ -167,6 +167,7 @@ + extern __printf(1, 2) int kdb_printf(const char *, ...); + typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); + ++#define in_kdb_printk() (kdb_trap_printk) + extern void kdb_init(int level); + + /* Access to kdb specific polling devices */ +@@ -201,6 +202,7 @@ + extern int kdb_unregister(char *); + #else /* ! CONFIG_KGDB_KDB */ + static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } ++#define in_kdb_printk() (0) + static inline void kdb_init(int level) {} + static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen) { return 0; } +diff -Nur linux-4.4.28.orig/include/linux/kernel.h linux-4.4.28/include/linux/kernel.h +--- linux-4.4.28.orig/include/linux/kernel.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/kernel.h 2016-11-01 21:26:58.732339449 +0100 +@@ -188,6 +188,9 @@ + */ + # define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) ++ ++# define might_sleep_no_state_check() \ ++ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + # define sched_annotate_sleep() (current->task_state_change = 0) + #else + static inline void ___might_sleep(const char *file, int line, +@@ -195,6 +198,7 @@ + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } + # define might_sleep() do { might_resched(); } while (0) ++# define might_sleep_no_state_check() do { might_resched(); } while (0) + # define sched_annotate_sleep() do { } while (0) + #endif + +@@ -255,6 +259,7 @@ + __printf(1, 2) + void panic(const char *fmt, ...) + __noreturn __cold; ++void nmi_panic(struct pt_regs *regs, const char *msg); + extern void oops_enter(void); + extern void oops_exit(void); + void print_oops_end_marker(void); +@@ -448,6 +453,14 @@ + extern bool crash_kexec_post_notifiers; + + /* ++ * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It ++ * holds a CPU number which is executing panic() currently. A value of ++ * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). ++ */ ++extern atomic_t panic_cpu; ++#define PANIC_CPU_INVALID -1 ++ ++/* + * Only to be used by arch init code. If the user over-wrote the default + * CONFIG_PANIC_TIMEOUT, honor it. + */ +@@ -475,6 +488,7 @@ + SYSTEM_HALT, + SYSTEM_POWER_OFF, + SYSTEM_RESTART, ++ SYSTEM_SUSPEND, + } system_state; + + #define TAINT_PROPRIETARY_MODULE 0 +diff -Nur linux-4.4.28.orig/include/linux/kvm_host.h linux-4.4.28/include/linux/kvm_host.h +--- linux-4.4.28.orig/include/linux/kvm_host.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/kvm_host.h 2016-11-01 21:26:58.732339449 +0100 +@@ -25,6 +25,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -243,7 +244,7 @@ + int fpu_active; + int guest_fpu_loaded, guest_xcr0_loaded; + unsigned char fpu_counter; +- wait_queue_head_t wq; ++ struct swait_queue_head wq; + struct pid *pid; + int sigset_active; + sigset_t sigset; +@@ -794,7 +795,7 @@ + } + #endif + +-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) ++static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) + { + #ifdef __KVM_HAVE_ARCH_WQP + return vcpu->arch.wqp; +diff -Nur linux-4.4.28.orig/include/linux/lglock.h linux-4.4.28/include/linux/lglock.h +--- linux-4.4.28.orig/include/linux/lglock.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/lglock.h 2016-11-01 21:26:58.732339449 +0100 +@@ -34,13 +34,30 @@ + #endif + + struct lglock { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct rt_mutex __percpu *lock; ++#else + arch_spinlock_t __percpu *lock; ++#endif + #ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lock_key; + struct lockdep_map lock_dep_map; + #endif + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define DEFINE_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ struct lglock name = { .lock = &name ## _lock } ++ ++# define DEFINE_STATIC_LGLOCK(name) \ ++ static DEFINE_PER_CPU(struct rt_mutex, name ## _lock) \ ++ = __RT_MUTEX_INITIALIZER( name ## _lock); \ ++ static struct lglock name = { .lock = &name ## _lock } ++ ++#else ++ + #define DEFINE_LGLOCK(name) \ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ +@@ -50,6 +67,7 @@ + static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock) \ + = __ARCH_SPIN_LOCK_UNLOCKED; \ + static struct lglock name = { .lock = &name ## _lock } ++#endif + + void lg_lock_init(struct lglock *lg, char *name); + +@@ -64,6 +82,12 @@ + void lg_global_lock(struct lglock *lg); + void lg_global_unlock(struct lglock *lg); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define lg_global_trylock_relax(name) lg_global_lock(name) ++#else ++void lg_global_trylock_relax(struct lglock *lg); ++#endif ++ + #else + /* When !CONFIG_SMP, map lglock to spinlock */ + #define lglock spinlock +diff -Nur linux-4.4.28.orig/include/linux/list_bl.h linux-4.4.28/include/linux/list_bl.h +--- linux-4.4.28.orig/include/linux/list_bl.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/list_bl.h 2016-11-01 21:26:58.732339449 +0100 +@@ -2,6 +2,7 @@ + #define _LINUX_LIST_BL_H + + #include ++#include + #include + + /* +@@ -32,13 +33,24 @@ + + struct hlist_bl_head { + struct hlist_bl_node *first; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spinlock_t lock; ++#endif + }; + + struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; +-#define INIT_HLIST_BL_HEAD(ptr) \ +- ((ptr)->first = NULL) ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++#define INIT_HLIST_BL_HEAD(h) \ ++do { \ ++ (h)->first = NULL; \ ++ raw_spin_lock_init(&(h)->lock); \ ++} while (0) ++#else ++#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL ++#endif + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -118,12 +130,26 @@ + + static inline void hlist_bl_lock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(0, (unsigned long *)b); ++#else ++ raw_spin_lock(&b->lock); ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __set_bit(0, (unsigned long *)b); ++#endif ++#endif + } + + static inline void hlist_bl_unlock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + __bit_spin_unlock(0, (unsigned long *)b); ++#else ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __clear_bit(0, (unsigned long *)b); ++#endif ++ raw_spin_unlock(&b->lock); ++#endif + } + + static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) +diff -Nur linux-4.4.28.orig/include/linux/locallock.h linux-4.4.28/include/linux/locallock.h +--- linux-4.4.28.orig/include/linux/locallock.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/locallock.h 2016-11-01 21:26:58.732339449 +0100 +@@ -0,0 +1,276 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include ++#include ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define LL_WARN(cond) WARN_ON(cond) ++#else ++# define LL_WARN(cond) do { } while (0) ++#endif ++ ++/* ++ * per cpu lock based substitute for local_irq_*() ++ */ ++struct local_irq_lock { ++ spinlock_t lock; ++ struct task_struct *owner; ++ int nestcnt; ++ unsigned long flags; ++}; ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ ++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ ++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } ++ ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ ++ DECLARE_PER_CPU(struct local_irq_lock, lvar) ++ ++#define local_irq_lock_init(lvar) \ ++ do { \ ++ int __cpu; \ ++ for_each_possible_cpu(__cpu) \ ++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ ++ } while (0) ++ ++/* ++ * spin_lock|trylock|unlock_local flavour that does not migrate disable ++ * used for __local_lock|trylock|unlock where get_local_var/put_local_var ++ * already takes care of the migrate_disable/enable ++ * for CONFIG_PREEMPT_BASE map to the normal spin_* calls. ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define spin_lock_local(lock) rt_spin_lock__no_mg(lock) ++# define spin_trylock_local(lock) rt_spin_trylock__no_mg(lock) ++# define spin_unlock_local(lock) rt_spin_unlock__no_mg(lock) ++#else ++# define spin_lock_local(lock) spin_lock(lock) ++# define spin_trylock_local(lock) spin_trylock(lock) ++# define spin_unlock_local(lock) spin_unlock(lock) ++#endif ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock_local(&lv->lock); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ } ++ lv->nestcnt++; ++} ++ ++#define local_lock(lvar) \ ++ do { __local_lock(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_on(lvar, cpu) \ ++ do { __local_lock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock_local(&lv->lock)) { ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++ return 1; ++ } ++ return 0; ++} ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ int __locked; \ ++ __locked = __local_trylock(&get_local_var(lvar)); \ ++ if (!__locked) \ ++ put_local_var(lvar); \ ++ __locked; \ ++ }) ++ ++static inline void __local_unlock(struct local_irq_lock *lv) ++{ ++ LL_WARN(lv->nestcnt == 0); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return; ++ ++ lv->owner = NULL; ++ spin_unlock_local(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_on(lvar, cpu) \ ++ do { __local_unlock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_lock_irq(struct local_irq_lock *lv) ++{ ++ spin_lock_irqsave(&lv->lock, lv->flags); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++} ++ ++#define local_lock_irq(lvar) \ ++ do { __local_lock_irq(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_irq_on(lvar, cpu) \ ++ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_unlock_irq(struct local_irq_lock *lv) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ lv->owner = NULL; ++ lv->nestcnt = 0; ++ spin_unlock_irq(&lv->lock); ++} ++ ++#define local_unlock_irq(lvar) \ ++ do { \ ++ __local_unlock_irq(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irq_on(lvar, cpu) \ ++ do { \ ++ __local_unlock_irq(&per_cpu(lvar, cpu)); \ ++ } while (0) ++ ++static inline int __local_lock_irqsave(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ __local_lock_irq(lv); ++ return 0; ++ } else { ++ lv->nestcnt++; ++ return 1; ++ } ++} ++ ++#define local_lock_irqsave(lvar, _flags) \ ++ do { \ ++ if (__local_lock_irqsave(&get_local_var(lvar))) \ ++ put_local_var(lvar); \ ++ _flags = __this_cpu_read(lvar.flags); \ ++ } while (0) ++ ++#define local_lock_irqsave_on(lvar, _flags, cpu) \ ++ do { \ ++ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ ++ _flags = per_cpu(lvar, cpu).flags; \ ++ } while (0) ++ ++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, ++ unsigned long flags) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return 0; ++ ++ lv->owner = NULL; ++ spin_unlock_irqrestore(&lv->lock, lv->flags); ++ return 1; ++} ++ ++#define local_unlock_irqrestore(lvar, flags) \ ++ do { \ ++ if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irqrestore_on(lvar, flags, cpu) \ ++ do { \ ++ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ ++ } while (0) ++ ++#define local_spin_trylock_irq(lvar, lock) \ ++ ({ \ ++ int __locked; \ ++ local_lock_irq(lvar); \ ++ __locked = spin_trylock(lock); \ ++ if (!__locked) \ ++ local_unlock_irq(lvar); \ ++ __locked; \ ++ }) ++ ++#define local_spin_lock_irq(lvar, lock) \ ++ do { \ ++ local_lock_irq(lvar); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irq(lvar, lock) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irq(lvar); \ ++ } while (0) ++ ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ do { \ ++ local_lock_irqsave(lvar, flags); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irqrestore(lvar, flags); \ ++ } while (0) ++ ++#define get_locked_var(lvar, var) \ ++ (*({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(&var); \ ++ })) ++ ++#define put_locked_var(lvar, var) local_unlock(lvar); ++ ++#define local_lock_cpu(lvar) \ ++ ({ \ ++ local_lock(lvar); \ ++ smp_processor_id(); \ ++ }) ++ ++#define local_unlock_cpu(lvar) local_unlock(lvar) ++ ++#else /* PREEMPT_RT_BASE */ ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar ++ ++static inline void local_irq_lock_init(int lvar) { } ++ ++#define local_lock(lvar) preempt_disable() ++#define local_unlock(lvar) preempt_enable() ++#define local_lock_irq(lvar) local_irq_disable() ++#define local_unlock_irq(lvar) local_irq_enable() ++#define local_lock_irqsave(lvar, flags) local_irq_save(flags) ++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) ++ ++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) ++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) ++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ spin_lock_irqsave(lock, flags) ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ spin_unlock_irqrestore(lock, flags) ++ ++#define get_locked_var(lvar, var) get_cpu_var(var) ++#define put_locked_var(lvar, var) put_cpu_var(var) ++ ++#define local_lock_cpu(lvar) get_cpu() ++#define local_unlock_cpu(lvar) put_cpu() ++ ++#endif ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/mm_types.h linux-4.4.28/include/linux/mm_types.h +--- linux-4.4.28.orig/include/linux/mm_types.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/mm_types.h 2016-11-01 21:26:58.732339449 +0100 +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -504,6 +505,9 @@ + bool tlb_flush_pending; + #endif + struct uprobes_state uprobes_state; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + #ifdef CONFIG_X86_INTEL_MPX + /* address of the bounds directory */ + void __user *bd_addr; +diff -Nur linux-4.4.28.orig/include/linux/mutex.h linux-4.4.28/include/linux/mutex.h +--- linux-4.4.28.orig/include/linux/mutex.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/mutex.h 2016-11-01 21:26:58.732339449 +0100 +@@ -19,6 +19,17 @@ + #include + #include + ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ ++ , .dep_map = { .name = #lockname } ++#else ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) ++#endif ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++ + /* + * Simple, straightforward mutexes with strict semantics: + * +@@ -99,13 +110,6 @@ + static inline void mutex_destroy(struct mutex *lock) {} + #endif + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ +- , .dep_map = { .name = #lockname } +-#else +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +-#endif +- + #define __MUTEX_INITIALIZER(lockname) \ + { .count = ATOMIC_INIT(1) \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ +@@ -173,6 +177,8 @@ + extern int mutex_trylock(struct mutex *lock); + extern void mutex_unlock(struct mutex *lock); + ++#endif /* !PREEMPT_RT_FULL */ ++ + extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); + + #endif /* __LINUX_MUTEX_H */ +diff -Nur linux-4.4.28.orig/include/linux/mutex_rt.h linux-4.4.28/include/linux/mutex_rt.h +--- linux-4.4.28.orig/include/linux/mutex_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/mutex_rt.h 2016-11-01 21:26:58.732339449 +0100 +@@ -0,0 +1,84 @@ ++#ifndef __LINUX_MUTEX_RT_H ++#define __LINUX_MUTEX_RT_H ++ ++#ifndef __LINUX_MUTEX_H ++#error "Please include mutex.h" ++#endif ++ ++#include ++ ++/* FIXME: Just for __lockfunc */ ++#include ++ ++struct mutex { ++ struct rt_mutex lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __MUTEX_INITIALIZER(mutexname) \ ++ { \ ++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ ++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ ++ } ++ ++#define DEFINE_MUTEX(mutexname) \ ++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) ++ ++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); ++extern void __lockfunc _mutex_lock(struct mutex *lock); ++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); ++extern int __lockfunc _mutex_lock_killable(struct mutex *lock); ++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); ++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); ++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_trylock(struct mutex *lock); ++extern void __lockfunc _mutex_unlock(struct mutex *lock); ++ ++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) ++#define mutex_lock(l) _mutex_lock(l) ++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) ++#define mutex_lock_killable(l) _mutex_lock_killable(l) ++#define mutex_trylock(l) _mutex_trylock(l) ++#define mutex_unlock(l) _mutex_unlock(l) ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible_nested(l, s) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable_nested(l, s) ++ ++# define mutex_lock_nest_lock(lock, nest_lock) \ ++do { \ ++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ ++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ ++} while (0) ++ ++#else ++# define mutex_lock_nested(l, s) _mutex_lock(l) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible(l) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable(l) ++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) ++#endif ++ ++# define mutex_init(mutex) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), #mutex, &__key); \ ++} while (0) ++ ++# define __mutex_init(mutex, name, key) \ ++do { \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), name, key); \ ++} while (0) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/netdevice.h linux-4.4.28/include/linux/netdevice.h +--- linux-4.4.28.orig/include/linux/netdevice.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/netdevice.h 2016-11-01 21:26:58.736339702 +0100 +@@ -2248,11 +2248,20 @@ + void synchronize_net(void); + int init_dummy_netdev(struct net_device *dev); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int dev_recursion_level(void) ++{ ++ return current->xmit_recursion; ++} ++ ++#else ++ + DECLARE_PER_CPU(int, xmit_recursion); + static inline int dev_recursion_level(void) + { + return this_cpu_read(xmit_recursion); + } ++#endif + + struct net_device *dev_get_by_index(struct net *net, int ifindex); + struct net_device *__dev_get_by_index(struct net *net, int ifindex); +@@ -2563,6 +2572,7 @@ + unsigned int dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + + }; + +diff -Nur linux-4.4.28.orig/include/linux/netfilter/x_tables.h linux-4.4.28/include/linux/netfilter/x_tables.h +--- linux-4.4.28.orig/include/linux/netfilter/x_tables.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/netfilter/x_tables.h 2016-11-01 21:26:58.736339702 +0100 +@@ -4,6 +4,7 @@ + + #include + #include ++#include + #include + + /** +@@ -289,6 +290,8 @@ + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /* xt_tee_enabled - true if x_tables needs to handle reentrancy + * + * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. +@@ -309,6 +312,9 @@ + { + unsigned int addend; + ++ /* RT protection */ ++ local_lock(xt_write_lock); ++ + /* + * Low order bit of sequence is set if we already + * called xt_write_recseq_begin(). +@@ -339,6 +345,7 @@ + /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ + smp_wmb(); + __this_cpu_add(xt_recseq.sequence, addend); ++ local_unlock(xt_write_lock); + } + + /* +diff -Nur linux-4.4.28.orig/include/linux/notifier.h linux-4.4.28/include/linux/notifier.h +--- linux-4.4.28.orig/include/linux/notifier.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/notifier.h 2016-11-01 21:26:58.736339702 +0100 +@@ -6,7 +6,7 @@ + * + * Alan Cox + */ +- ++ + #ifndef _LINUX_NOTIFIER_H + #define _LINUX_NOTIFIER_H + #include +@@ -42,9 +42,7 @@ + * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. + * As compensation, srcu_notifier_chain_unregister() is rather expensive. + * SRCU notifier chains should be used when the chain will be called very +- * often but notifier_blocks will seldom be removed. Also, SRCU notifier +- * chains are slightly more difficult to use because they require special +- * runtime initialization. ++ * often but notifier_blocks will seldom be removed. + */ + + typedef int (*notifier_fn_t)(struct notifier_block *nb, +@@ -88,7 +86,7 @@ + (name)->head = NULL; \ + } while (0) + +-/* srcu_notifier_heads must be initialized and cleaned up dynamically */ ++/* srcu_notifier_heads must be cleaned up dynamically */ + extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); + #define srcu_cleanup_notifier_head(name) \ + cleanup_srcu_struct(&(name)->srcu); +@@ -101,7 +99,13 @@ + .head = NULL } + #define RAW_NOTIFIER_INIT(name) { \ + .head = NULL } +-/* srcu_notifier_heads cannot be initialized statically */ ++ ++#define SRCU_NOTIFIER_INIT(name, pcpu) \ ++ { \ ++ .mutex = __MUTEX_INITIALIZER(name.mutex), \ ++ .head = NULL, \ ++ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ ++ } + + #define ATOMIC_NOTIFIER_HEAD(name) \ + struct atomic_notifier_head name = \ +@@ -113,6 +117,18 @@ + struct raw_notifier_head name = \ + RAW_NOTIFIER_INIT(name) + ++#define _SRCU_NOTIFIER_HEAD(name, mod) \ ++ static DEFINE_PER_CPU(struct srcu_struct_array, \ ++ name##_head_srcu_array); \ ++ mod struct srcu_notifier_head name = \ ++ SRCU_NOTIFIER_INIT(name, name##_head_srcu_array) ++ ++#define SRCU_NOTIFIER_HEAD(name) \ ++ _SRCU_NOTIFIER_HEAD(name, ) ++ ++#define SRCU_NOTIFIER_HEAD_STATIC(name) \ ++ _SRCU_NOTIFIER_HEAD(name, static) ++ + #ifdef __KERNEL__ + + extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, +@@ -182,12 +198,12 @@ + + /* + * Declared notifiers so far. I can imagine quite a few more chains +- * over time (eg laptop power reset chains, reboot chain (to clean ++ * over time (eg laptop power reset chains, reboot chain (to clean + * device units up), device [un]mount chain, module load/unload chain, +- * low memory chain, screenblank chain (for plug in modular screenblankers) ++ * low memory chain, screenblank chain (for plug in modular screenblankers) + * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... + */ +- ++ + /* CPU notfiers are defined in include/linux/cpu.h. */ + + /* netdevice notifiers are defined in include/linux/netdevice.h */ +diff -Nur linux-4.4.28.orig/include/linux/percpu.h linux-4.4.28/include/linux/percpu.h +--- linux-4.4.28.orig/include/linux/percpu.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/percpu.h 2016-11-01 21:26:58.736339702 +0100 +@@ -24,6 +24,35 @@ + PERCPU_MODULE_RESERVE) + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++#define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(&var); })) ++ ++#define put_local_var(var) do { \ ++ (void)&(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++# define get_local_ptr(var) ({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(var); }) ++ ++# define put_local_ptr(var) do { \ ++ (void)(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++#else ++ ++#define get_local_var(var) get_cpu_var(var) ++#define put_local_var(var) put_cpu_var(var) ++#define get_local_ptr(var) get_cpu_ptr(var) ++#define put_local_ptr(var) put_cpu_ptr(var) ++ ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + +diff -Nur linux-4.4.28.orig/include/linux/pid.h linux-4.4.28/include/linux/pid.h +--- linux-4.4.28.orig/include/linux/pid.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/pid.h 2016-11-01 21:26:58.736339702 +0100 +@@ -2,6 +2,7 @@ + #define _LINUX_PID_H + + #include ++#include + + enum pid_type + { +diff -Nur linux-4.4.28.orig/include/linux/preempt.h linux-4.4.28/include/linux/preempt.h +--- linux-4.4.28.orig/include/linux/preempt.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/preempt.h 2016-11-01 21:26:58.736339702 +0100 +@@ -50,7 +50,11 @@ + #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) + #define NMI_OFFSET (1UL << NMI_SHIFT) + +-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#else ++# define SOFTIRQ_DISABLE_OFFSET (0) ++#endif + + /* We use the MSB mostly because its available */ + #define PREEMPT_NEED_RESCHED 0x80000000 +@@ -59,9 +63,15 @@ + #include + + #define hardirq_count() (preempt_count() & HARDIRQ_MASK) +-#define softirq_count() (preempt_count() & SOFTIRQ_MASK) + #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define softirq_count() (preempt_count() & SOFTIRQ_MASK) ++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) ++#else ++# define softirq_count() (0UL) ++extern int in_serving_softirq(void); ++#endif + + /* + * Are we doing bottom half or hardware interrupt processing? +@@ -72,7 +82,6 @@ + #define in_irq() (hardirq_count()) + #define in_softirq() (softirq_count()) + #define in_interrupt() (irq_count()) +-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + + /* + * Are we in NMI context? +@@ -91,7 +100,11 @@ + /* + * The preempt_count offset after spin_lock() + */ ++#if !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET ++#else ++#define PREEMPT_LOCK_OFFSET 0 ++#endif + + /* + * The preempt_count offset needed for things like: +@@ -140,6 +153,20 @@ + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -148,13 +175,25 @@ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ + preempt_count_dec(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() preempt_check_resched() ++#else ++# define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() barrier(); ++#endif + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + +@@ -179,6 +218,13 @@ + __preempt_schedule(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ preempt_check_resched(); \ ++} while (0) ++ + #else /* !CONFIG_PREEMPT */ + #define preempt_enable() \ + do { \ +@@ -224,6 +270,7 @@ + #define preempt_disable_notrace() barrier() + #define preempt_enable_no_resched_notrace() barrier() + #define preempt_enable_notrace() barrier() ++#define preempt_check_resched_rt() barrier() + #define preemptible() 0 + + #endif /* CONFIG_PREEMPT_COUNT */ +@@ -244,10 +291,31 @@ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() barrier() ++# define preempt_enable_nort() barrier() ++# ifdef CONFIG_SMP ++ extern void migrate_disable(void); ++ extern void migrate_enable(void); ++# else /* CONFIG_SMP */ ++# define migrate_disable() barrier() ++# define migrate_enable() barrier() ++# endif /* CONFIG_SMP */ ++#else ++# define preempt_disable_rt() barrier() ++# define preempt_enable_rt() barrier() ++# define preempt_disable_nort() preempt_disable() ++# define preempt_enable_nort() preempt_enable() ++# define migrate_disable() preempt_disable() ++# define migrate_enable() preempt_enable() ++#endif ++ + #ifdef CONFIG_PREEMPT_NOTIFIERS + + struct preempt_notifier; +diff -Nur linux-4.4.28.orig/include/linux/printk.h linux-4.4.28/include/linux/printk.h +--- linux-4.4.28.orig/include/linux/printk.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/printk.h 2016-11-01 21:26:58.736339702 +0100 +@@ -117,9 +117,11 @@ + #ifdef CONFIG_EARLY_PRINTK + extern asmlinkage __printf(1, 2) + void early_printk(const char *fmt, ...); ++extern void printk_kill(void); + #else + static inline __printf(1, 2) __cold + void early_printk(const char *s, ...) { } ++static inline void printk_kill(void) { } + #endif + + typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); +diff -Nur linux-4.4.28.orig/include/linux/radix-tree.h linux-4.4.28/include/linux/radix-tree.h +--- linux-4.4.28.orig/include/linux/radix-tree.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/radix-tree.h 2016-11-01 21:26:58.736339702 +0100 +@@ -277,8 +277,13 @@ + unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, + void ***results, unsigned long *indices, + unsigned long first_index, unsigned int max_items); ++#ifndef CONFIG_PREEMPT_RT_FULL + int radix_tree_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload(gfp_t gfp_mask); ++#else ++static inline int radix_tree_preload(gfp_t gm) { return 0; } ++static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; } ++#endif + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *root, + unsigned long index, unsigned int tag); +@@ -303,7 +308,7 @@ + + static inline void radix_tree_preload_end(void) + { +- preempt_enable(); ++ preempt_enable_nort(); + } + + /** +diff -Nur linux-4.4.28.orig/include/linux/random.h linux-4.4.28/include/linux/random.h +--- linux-4.4.28.orig/include/linux/random.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/random.h 2016-11-01 21:26:58.736339702 +0100 +@@ -20,7 +20,7 @@ + extern void add_device_randomness(const void *, unsigned int); + extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value); +-extern void add_interrupt_randomness(int irq, int irq_flags); ++extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip); + + extern void get_random_bytes(void *buf, int nbytes); + extern int add_random_ready_callback(struct random_ready_callback *rdy); +diff -Nur linux-4.4.28.orig/include/linux/rbtree.h linux-4.4.28/include/linux/rbtree.h +--- linux-4.4.28.orig/include/linux/rbtree.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rbtree.h 2016-11-01 21:26:58.736339702 +0100 +@@ -31,7 +31,6 @@ + + #include + #include +-#include + + struct rb_node { + unsigned long __rb_parent_color; +@@ -86,14 +85,8 @@ + *rb_link = node; + } + +-static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, +- struct rb_node **rb_link) +-{ +- node->__rb_parent_color = (unsigned long)parent; +- node->rb_left = node->rb_right = NULL; +- +- rcu_assign_pointer(*rb_link, node); +-} ++void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, ++ struct rb_node **rb_link); + + #define rb_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ +diff -Nur linux-4.4.28.orig/include/linux/rcupdate.h linux-4.4.28/include/linux/rcupdate.h +--- linux-4.4.28.orig/include/linux/rcupdate.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rcupdate.h 2016-11-01 21:26:58.740339958 +0100 +@@ -169,6 +169,9 @@ + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define call_rcu_bh call_rcu ++#else + /** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. +@@ -192,6 +195,7 @@ + */ + void call_rcu_bh(struct rcu_head *head, + rcu_callback_t func); ++#endif + + /** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. +@@ -292,6 +296,11 @@ + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ + #define rcu_preempt_depth() (current->rcu_read_lock_nesting) ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++#else ++static inline int sched_rcu_preempt_depth(void) { return 0; } ++#endif + + #else /* #ifdef CONFIG_PREEMPT_RCU */ + +@@ -317,6 +326,8 @@ + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +@@ -489,7 +500,14 @@ + int debug_lockdep_rcu_enabled(void); + + int rcu_read_lock_held(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + int rcu_read_lock_bh_held(void); ++#endif + + /** + * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? +@@ -937,10 +955,14 @@ + static inline void rcu_read_lock_bh(void) + { + local_bh_disable(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_lock(); ++#else + __acquire(RCU_BH); + rcu_lock_acquire(&rcu_bh_lock_map); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -950,10 +972,14 @@ + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +diff -Nur linux-4.4.28.orig/include/linux/rcutree.h linux-4.4.28/include/linux/rcutree.h +--- linux-4.4.28.orig/include/linux/rcutree.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rcutree.h 2016-11-01 21:26:58.740339958 +0100 +@@ -44,7 +44,11 @@ + rcu_note_context_switch(); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define synchronize_rcu_bh synchronize_rcu ++#else + void synchronize_rcu_bh(void); ++#endif + void synchronize_sched_expedited(void); + void synchronize_rcu_expedited(void); + +@@ -72,7 +76,11 @@ + } + + void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + void rcu_barrier_bh(void); ++#endif + void rcu_barrier_sched(void); + unsigned long get_state_synchronize_rcu(void); + void cond_synchronize_rcu(unsigned long oldstate); +@@ -85,12 +93,10 @@ + unsigned long rcu_batches_started_bh(void); + unsigned long rcu_batches_started_sched(void); + unsigned long rcu_batches_completed(void); +-unsigned long rcu_batches_completed_bh(void); + unsigned long rcu_batches_completed_sched(void); + void show_rcu_gp_kthreads(void); + + void rcu_force_quiescent_state(void); +-void rcu_bh_force_quiescent_state(void); + void rcu_sched_force_quiescent_state(void); + + void rcu_idle_enter(void); +@@ -105,6 +111,14 @@ + + bool rcu_is_watching(void); + ++#ifndef CONFIG_PREEMPT_RT_FULL ++void rcu_bh_force_quiescent_state(void); ++unsigned long rcu_batches_completed_bh(void); ++#else ++# define rcu_bh_force_quiescent_state rcu_force_quiescent_state ++# define rcu_batches_completed_bh rcu_batches_completed ++#endif ++ + void rcu_all_qs(void); + + #endif /* __LINUX_RCUTREE_H */ +diff -Nur linux-4.4.28.orig/include/linux/rtmutex.h linux-4.4.28/include/linux/rtmutex.h +--- linux-4.4.28.orig/include/linux/rtmutex.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rtmutex.h 2016-11-01 21:26:58.740339958 +0100 +@@ -13,11 +13,15 @@ + #define __LINUX_RT_MUTEX_H + + #include ++#include + #include +-#include + + extern int max_lock_depth; /* for sysctl */ + ++#ifdef CONFIG_DEBUG_MUTEXES ++#include ++#endif ++ + /** + * The rt_mutex structure + * +@@ -31,8 +35,8 @@ + struct rb_root waiters; + struct rb_node *waiters_leftmost; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; ++#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *name, *file; + int line; + void *magic; +@@ -55,22 +59,33 @@ + # define rt_mutex_debug_check_no_locks_held(task) do { } while (0) + #endif + ++# define rt_mutex_init(mutex) \ ++ do { \ ++ raw_spin_lock_init(&(mutex)->wait_lock); \ ++ __rt_mutex_init(mutex, #mutex); \ ++ } while (0) ++ + #ifdef CONFIG_DEBUG_RT_MUTEXES + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ + , .name = #mutexname, .file = __FILE__, .line = __LINE__ +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, __func__) + extern void rt_mutex_debug_task_free(struct task_struct *tsk); + #else + # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) +-# define rt_mutex_init(mutex) __rt_mutex_init(mutex, NULL) + # define rt_mutex_debug_task_free(t) do { } while (0) + #endif + +-#define __RT_MUTEX_INITIALIZER(mutexname) \ +- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ ++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ + , .waiters = RB_ROOT \ + , .owner = NULL \ +- __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} ++ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) ++ ++#define __RT_MUTEX_INITIALIZER(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } ++ ++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ , .save_state = 1 } + + #define DEFINE_RT_MUTEX(mutexname) \ + struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) +@@ -91,6 +106,7 @@ + + extern void rt_mutex_lock(struct rt_mutex *lock); + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); ++extern int rt_mutex_lock_killable(struct rt_mutex *lock); + extern int rt_mutex_timed_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout); + +diff -Nur linux-4.4.28.orig/include/linux/rwlock_rt.h linux-4.4.28/include/linux/rwlock_rt.h +--- linux-4.4.28.orig/include/linux/rwlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/rwlock_rt.h 2016-11-01 21:26:58.740339958 +0100 +@@ -0,0 +1,99 @@ ++#ifndef __LINUX_RWLOCK_RT_H ++#define __LINUX_RWLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#define rwlock_init(rwl) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(rwl)->lock); \ ++ __rt_rwlock_init(rwl, #rwl, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_write_lock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags); ++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); ++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock); ++extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock); ++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); ++ ++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) ++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) ++ ++#define write_trylock_irqsave(lock, flags) \ ++ __cond_lock(lock, rt_write_trylock_irqsave(lock, &flags)) ++ ++#define read_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = rt_read_lock_irqsave(lock); \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = rt_write_lock_irqsave(lock); \ ++ } while (0) ++ ++#define read_lock(lock) rt_read_lock(lock) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) rt_write_lock(lock) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) rt_read_unlock(lock) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) rt_write_unlock(lock) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define write_unlock_irq(lock) write_unlock(lock) ++ ++#define read_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_read_unlock(lock); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ } while (0) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/rwlock_types.h linux-4.4.28/include/linux/rwlock_types.h +--- linux-4.4.28.orig/include/linux/rwlock_types.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rwlock_types.h 2016-11-01 21:26:58.740339958 +0100 +@@ -1,6 +1,10 @@ + #ifndef __LINUX_RWLOCK_TYPES_H + #define __LINUX_RWLOCK_TYPES_H + ++#if !defined(__LINUX_SPINLOCK_TYPES_H) ++# error "Do not include directly, include spinlock_types.h" ++#endif ++ + /* + * include/linux/rwlock_types.h - generic rwlock type definitions + * and initializers +@@ -43,6 +47,7 @@ + RW_DEP_MAP_INIT(lockname) } + #endif + +-#define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) + + #endif /* __LINUX_RWLOCK_TYPES_H */ +diff -Nur linux-4.4.28.orig/include/linux/rwlock_types_rt.h linux-4.4.28/include/linux/rwlock_types_rt.h +--- linux-4.4.28.orig/include/linux/rwlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/rwlock_types_rt.h 2016-11-01 21:26:58.740339958 +0100 +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_RWLOCK_TYPES_RT_H ++#define __LINUX_RWLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * rwlocks - rtmutex which allows single reader recursion ++ */ ++typedef struct { ++ struct rt_mutex lock; ++ int read_depth; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} rwlock_t; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define RW_DEP_MAP_INIT(lockname) ++#endif ++ ++#define __RW_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/rwsem.h linux-4.4.28/include/linux/rwsem.h +--- linux-4.4.28.orig/include/linux/rwsem.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/rwsem.h 2016-11-01 21:26:58.740339958 +0100 +@@ -18,6 +18,10 @@ + #include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -177,4 +181,6 @@ + # define up_read_non_owner(sem) up_read(sem) + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* _LINUX_RWSEM_H */ +diff -Nur linux-4.4.28.orig/include/linux/rwsem_rt.h linux-4.4.28/include/linux/rwsem_rt.h +--- linux-4.4.28.orig/include/linux/rwsem_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/rwsem_rt.h 2016-11-01 21:26:58.740339958 +0100 +@@ -0,0 +1,152 @@ ++#ifndef _LINUX_RWSEM_RT_H ++#define _LINUX_RWSEM_RT_H ++ ++#ifndef _LINUX_RWSEM_H ++#error "Include rwsem.h" ++#endif ++ ++/* ++ * RW-semaphores are a spinlock plus a reader-depth count. ++ * ++ * Note that the semantics are different from the usual ++ * Linux rw-sems, in PREEMPT_RT mode we do not allow ++ * multiple readers to hold the lock at once, we only allow ++ * a read-lock owner to read-lock recursively. This is ++ * better for latency, makes the implementation inherently ++ * fair and makes it simpler as well. ++ */ ++ ++#include ++ ++struct rw_semaphore { ++ struct rt_mutex lock; ++ int read_depth; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __RWSEM_INITIALIZER(name) \ ++ { .lock = __RT_MUTEX_INITIALIZER(name.lock), \ ++ RW_DEP_MAP_INIT(name) } ++ ++#define DECLARE_RWSEM(lockname) \ ++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) ++ ++extern void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key); ++ ++#define __rt_init_rwsem(sem, name, key) \ ++ do { \ ++ rt_mutex_init(&(sem)->lock); \ ++ __rt_rwsem_init((sem), (name), (key));\ ++ } while (0) ++ ++#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key) ++ ++# define rt_init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rt_init_rwsem((sem), #sem, &__key); \ ++} while (0) ++ ++extern void rt_down_write(struct rw_semaphore *rwsem); ++extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass); ++extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest); ++extern void rt__down_read(struct rw_semaphore *rwsem); ++extern void rt_down_read(struct rw_semaphore *rwsem); ++extern int rt_down_write_trylock(struct rw_semaphore *rwsem); ++extern int rt__down_read_trylock(struct rw_semaphore *rwsem); ++extern int rt_down_read_trylock(struct rw_semaphore *rwsem); ++extern void __rt_up_read(struct rw_semaphore *rwsem); ++extern void rt_up_read(struct rw_semaphore *rwsem); ++extern void rt_up_write(struct rw_semaphore *rwsem); ++extern void rt_downgrade_write(struct rw_semaphore *rwsem); ++ ++#define init_rwsem(sem) rt_init_rwsem(sem) ++#define rwsem_is_locked(s) rt_mutex_is_locked(&(s)->lock) ++ ++static inline int rwsem_is_contended(struct rw_semaphore *sem) ++{ ++ /* rt_mutex_has_waiters() */ ++ return !RB_EMPTY_ROOT(&sem->lock.waiters); ++} ++ ++static inline void __down_read(struct rw_semaphore *sem) ++{ ++ rt__down_read(sem); ++} ++ ++static inline void down_read(struct rw_semaphore *sem) ++{ ++ rt_down_read(sem); ++} ++ ++static inline int __down_read_trylock(struct rw_semaphore *sem) ++{ ++ return rt__down_read_trylock(sem); ++} ++ ++static inline int down_read_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_read_trylock(sem); ++} ++ ++static inline void down_write(struct rw_semaphore *sem) ++{ ++ rt_down_write(sem); ++} ++ ++static inline int down_write_trylock(struct rw_semaphore *sem) ++{ ++ return rt_down_write_trylock(sem); ++} ++ ++static inline void __up_read(struct rw_semaphore *sem) ++{ ++ __rt_up_read(sem); ++} ++ ++static inline void up_read(struct rw_semaphore *sem) ++{ ++ rt_up_read(sem); ++} ++ ++static inline void up_write(struct rw_semaphore *sem) ++{ ++ rt_up_write(sem); ++} ++ ++static inline void downgrade_write(struct rw_semaphore *sem) ++{ ++ rt_downgrade_write(sem); ++} ++ ++static inline void down_read_nested(struct rw_semaphore *sem, int subclass) ++{ ++ return rt_down_read_nested(sem, subclass); ++} ++ ++static inline void down_write_nested(struct rw_semaphore *sem, int subclass) ++{ ++ rt_down_write_nested(sem, subclass); ++} ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, &nest_lock->dep_map); ++} ++ ++#else ++ ++static inline void down_write_nest_lock(struct rw_semaphore *sem, ++ struct rw_semaphore *nest_lock) ++{ ++ rt_down_write_nested_lock(sem, NULL); ++} ++#endif ++#endif +diff -Nur linux-4.4.28.orig/include/linux/sched.h linux-4.4.28/include/linux/sched.h +--- linux-4.4.28.orig/include/linux/sched.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/sched.h 2016-11-01 21:26:58.740339958 +0100 +@@ -26,6 +26,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -182,8 +183,6 @@ + static inline void update_cpu_load_nohz(void) { } + #endif + +-extern unsigned long get_parent_ip(unsigned long addr); +- + extern void dump_cpu_task(int cpu); + + struct seq_file; +@@ -242,10 +241,7 @@ + TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ + __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD) + +-#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) + #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +-#define task_is_stopped_or_traced(task) \ +- ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) + #define task_contributes_to_load(task) \ + ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0 && \ +@@ -311,6 +307,11 @@ + + #endif + ++#define __set_current_state_no_track(state_value) \ ++ do { current->state = (state_value); } while (0) ++#define set_current_state_no_track(state_value) \ ++ set_mb(current->state, (state_value)) ++ + /* Task command name length */ + #define TASK_COMM_LEN 16 + +@@ -970,8 +971,18 @@ + struct wake_q_head name = { WAKE_Q_TAIL, &name.first } + + extern void wake_q_add(struct wake_q_head *head, +- struct task_struct *task); +-extern void wake_up_q(struct wake_q_head *head); ++ struct task_struct *task); ++extern void __wake_up_q(struct wake_q_head *head, bool sleeper); ++ ++static inline void wake_up_q(struct wake_q_head *head) ++{ ++ __wake_up_q(head, false); ++} ++ ++static inline void wake_up_q_sleeper(struct wake_q_head *head) ++{ ++ __wake_up_q(head, true); ++} + + /* + * sched-domains (multiprocessor balancing) declarations: +@@ -1379,6 +1390,7 @@ + + struct task_struct { + volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ ++ volatile long saved_state; /* saved state for "spinlock sleepers" */ + void *stack; + atomic_t usage; + unsigned int flags; /* per process flags, defined below */ +@@ -1415,6 +1427,12 @@ + #endif + + unsigned int policy; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int migrate_disable; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif + int nr_cpus_allowed; + cpumask_t cpus_allowed; + +@@ -1522,11 +1540,14 @@ + cputime_t gtime; + struct prev_cputime prev_cputime; + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_t vtime_seqlock; ++ seqcount_t vtime_seqcount; + unsigned long long vtime_snap; + enum { +- VTIME_SLEEPING = 0, ++ /* Task is sleeping or running in a CPU with VTIME inactive */ ++ VTIME_INACTIVE = 0, ++ /* Task runs in userspace in a CPU with VTIME active */ + VTIME_USER, ++ /* Task runs in kernelspace in a CPU with VTIME active */ + VTIME_SYS, + } vtime_snap_whence; + #endif +@@ -1538,6 +1559,9 @@ + + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *posix_timer_list; ++#endif + + /* process credentials */ + const struct cred __rcu *real_cred; /* objective and real subjective task +@@ -1568,10 +1592,15 @@ + /* signal handlers */ + struct signal_struct *signal; + struct sighand_struct *sighand; ++ struct sigqueue *sigqueue_cache; + + sigset_t blocked, real_blocked; + sigset_t saved_sigmask; /* restored if set_restore_sigmask() was used */ + struct sigpending pending; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* TODO: move me into ->restart_block ? */ ++ struct siginfo forced_info; ++#endif + + unsigned long sas_ss_sp; + size_t sas_ss_size; +@@ -1795,6 +1824,12 @@ + unsigned long trace; + /* bitmask and counter of trace recursion */ + unsigned long trace_recursion; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ u64 preempt_timestamp_hist; ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ long timer_offset; ++#endif ++#endif + #endif /* CONFIG_TRACING */ + #ifdef CONFIG_MEMCG + struct mem_cgroup *memcg_in_oom; +@@ -1811,9 +1846,23 @@ + unsigned int sequential_io; + unsigned int sequential_io_avg; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++ int softirq_nestcnt; ++ unsigned int softirqs_raised; ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 ++ int kmap_idx; ++ pte_t kmap_pte[KM_TYPE_NR]; ++# endif ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int xmit_recursion; ++#endif + int pagefault_disabled; + /* CPU-specific state of this task */ + struct thread_struct thread; +@@ -1831,9 +1880,6 @@ + # define arch_task_struct_size (sizeof(struct task_struct)) + #endif + +-/* Future-safe accessor for struct task_struct's cpus_allowed. */ +-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) +- + #define TNF_MIGRATED 0x01 + #define TNF_NO_GROUP 0x02 + #define TNF_SHARED 0x04 +@@ -2023,6 +2069,15 @@ + extern void free_task(struct task_struct *tsk); + #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __put_task_struct_cb(struct rcu_head *rhp); ++ ++static inline void put_task_struct(struct task_struct *t) ++{ ++ if (atomic_dec_and_test(&t->usage)) ++ call_rcu(&t->put_rcu, __put_task_struct_cb); ++} ++#else + extern void __put_task_struct(struct task_struct *t); + + static inline void put_task_struct(struct task_struct *t) +@@ -2030,6 +2085,7 @@ + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } ++#endif + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN + extern void task_cputime(struct task_struct *t, +@@ -2068,6 +2124,7 @@ + /* + * Per process flags + */ ++#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ + #define PF_EXITING 0x00000004 /* getting shut down */ + #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ + #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +@@ -2232,6 +2289,10 @@ + + extern int set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask); ++int migrate_me(void); ++void tell_sched_cpu_down_begin(int cpu); ++void tell_sched_cpu_down_done(int cpu); ++ + #else + static inline void do_set_cpus_allowed(struct task_struct *p, + const struct cpumask *new_mask) +@@ -2244,6 +2305,9 @@ + return -EINVAL; + return 0; + } ++static inline int migrate_me(void) { return 0; } ++static inline void tell_sched_cpu_down_begin(int cpu) { } ++static inline void tell_sched_cpu_down_done(int cpu) { } + #endif + + #ifdef CONFIG_NO_HZ_COMMON +@@ -2453,6 +2517,7 @@ + + extern int wake_up_state(struct task_struct *tsk, unsigned int state); + extern int wake_up_process(struct task_struct *tsk); ++extern int wake_up_lock_sleeper(struct task_struct * tsk); + extern void wake_up_new_task(struct task_struct *tsk); + #ifdef CONFIG_SMP + extern void kick_process(struct task_struct *tsk); +@@ -2576,12 +2641,24 @@ + + /* mmdrop drops the mm and the page tables */ + extern void __mmdrop(struct mm_struct *); ++ + static inline void mmdrop(struct mm_struct * mm) + { + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __mmdrop_delayed(struct rcu_head *rhp); ++static inline void mmdrop_delayed(struct mm_struct *mm) ++{ ++ if (atomic_dec_and_test(&mm->mm_count)) ++ call_rcu(&mm->delayed_drop, __mmdrop_delayed); ++} ++#else ++# define mmdrop_delayed(mm) mmdrop(mm) ++#endif ++ + /* mmput gets rid of the mappings and all user-space */ + extern void mmput(struct mm_struct *); + /* Grab a reference to a task's mm, if it is not already going away */ +@@ -2891,6 +2968,43 @@ + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ + static inline int restart_syscall(void) + { + set_tsk_thread_flag(current, TIF_SIGPENDING); +@@ -2922,6 +3036,51 @@ + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); + } + ++static inline bool __task_is_stopped_or_traced(struct task_struct *task) ++{ ++ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#endif ++ return false; ++} ++ ++static inline bool task_is_stopped_or_traced(struct task_struct *task) ++{ ++ bool traced_stopped; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ traced_stopped = __task_is_stopped_or_traced(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++#else ++ traced_stopped = __task_is_stopped_or_traced(task); ++#endif ++ return traced_stopped; ++} ++ ++static inline bool task_is_traced(struct task_struct *task) ++{ ++ bool traced = false; ++ ++ if (task->state & __TASK_TRACED) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* in case the task is sleeping on tasklist_lock */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ traced = true; ++ else if (task->saved_state & __TASK_TRACED) ++ traced = true; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ return traced; ++} ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +@@ -2943,12 +3102,16 @@ + __cond_resched_lock(lock); \ + }) + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern int __cond_resched_softirq(void); + + #define cond_resched_softirq() ({ \ + ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + __cond_resched_softirq(); \ + }) ++#else ++# define cond_resched_softirq() cond_resched() ++#endif + + static inline void cond_resched_rcu(void) + { +@@ -3110,6 +3273,31 @@ + + #endif /* CONFIG_SMP */ + ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ return p->migrate_disable; ++#else ++ return 0; ++#endif ++} ++ ++/* Future-safe accessor for struct task_struct's cpus_allowed. */ ++static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p) ++{ ++ if (__migrate_disabled(p)) ++ return cpumask_of(task_cpu(p)); ++ ++ return &p->cpus_allowed; ++} ++ ++static inline int tsk_nr_cpus_allowed(struct task_struct *p) ++{ ++ if (__migrate_disabled(p)) ++ return 1; ++ return p->nr_cpus_allowed; ++} ++ + extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); + extern long sched_getaffinity(pid_t pid, struct cpumask *mask); + +diff -Nur linux-4.4.28.orig/include/linux/seqlock.h linux-4.4.28/include/linux/seqlock.h +--- linux-4.4.28.orig/include/linux/seqlock.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/seqlock.h 2016-11-01 21:26:58.744340223 +0100 +@@ -220,20 +220,30 @@ + return __read_seqcount_retry(s, start); + } + +- +- +-static inline void raw_write_seqcount_begin(seqcount_t *s) ++static inline void __raw_write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void raw_write_seqcount_end(seqcount_t *s) ++static inline void raw_write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __raw_write_seqcount_begin(s); ++} ++ ++static inline void __raw_write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void raw_write_seqcount_end(seqcount_t *s) ++{ ++ __raw_write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /** + * raw_write_seqcount_barrier - do a seq write barrier + * @s: pointer to seqcount_t +@@ -425,10 +435,32 @@ + /* + * Read side functions for starting and finalizing a read side section. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + static inline unsigned read_seqbegin(const seqlock_t *sl) + { + return read_seqcount_begin(&sl->seqcount); + } ++#else ++/* ++ * Starvation safe read side for RT ++ */ ++static inline unsigned read_seqbegin(seqlock_t *sl) ++{ ++ unsigned ret; ++ ++repeat: ++ ret = ACCESS_ONCE(sl->seqcount.sequence); ++ if (unlikely(ret & 1)) { ++ /* ++ * Take the lock and let the writer proceed (i.e. evtl ++ * boost it), otherwise we could loop here forever. ++ */ ++ spin_unlock_wait(&sl->lock); ++ goto repeat; ++ } ++ return ret; ++} ++#endif + + static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + { +@@ -443,36 +475,36 @@ + static inline void write_seqlock(seqlock_t *sl) + { + spin_lock(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock(&sl->lock); + } + + static inline void write_seqlock_bh(seqlock_t *sl) + { + spin_lock_bh(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_bh(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_bh(&sl->lock); + } + + static inline void write_seqlock_irq(seqlock_t *sl) + { + spin_lock_irq(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_irq(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); + } + +@@ -481,7 +513,7 @@ + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + return flags; + } + +@@ -491,7 +523,7 @@ + static inline void + write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); + } + +diff -Nur linux-4.4.28.orig/include/linux/signal.h linux-4.4.28/include/linux/signal.h +--- linux-4.4.28.orig/include/linux/signal.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/signal.h 2016-11-01 21:26:58.744340223 +0100 +@@ -233,6 +233,7 @@ + } + + extern void flush_sigqueue(struct sigpending *queue); ++extern void flush_task_sigqueue(struct task_struct *tsk); + + /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ + static inline int valid_signal(unsigned long sig) +diff -Nur linux-4.4.28.orig/include/linux/skbuff.h linux-4.4.28/include/linux/skbuff.h +--- linux-4.4.28.orig/include/linux/skbuff.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/skbuff.h 2016-11-01 21:26:58.744340223 +0100 +@@ -203,6 +203,7 @@ + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -1465,6 +1466,12 @@ + __skb_queue_head_init(list); + } + ++static inline void skb_queue_head_init_raw(struct sk_buff_head *list) ++{ ++ raw_spin_lock_init(&list->raw_lock); ++ __skb_queue_head_init(list); ++} ++ + static inline void skb_queue_head_init_class(struct sk_buff_head *list, + struct lock_class_key *class) + { +diff -Nur linux-4.4.28.orig/include/linux/smp.h linux-4.4.28/include/linux/smp.h +--- linux-4.4.28.orig/include/linux/smp.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/smp.h 2016-11-01 21:26:58.744340223 +0100 +@@ -185,6 +185,9 @@ + #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) + #define put_cpu() preempt_enable() + ++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) ++#define put_cpu_light() migrate_enable() ++ + /* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: +diff -Nur linux-4.4.28.orig/include/linux/spinlock_api_smp.h linux-4.4.28/include/linux/spinlock_api_smp.h +--- linux-4.4.28.orig/include/linux/spinlock_api_smp.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/spinlock_api_smp.h 2016-11-01 21:26:58.744340223 +0100 +@@ -189,6 +189,8 @@ + return 0; + } + +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +diff -Nur linux-4.4.28.orig/include/linux/spinlock.h linux-4.4.28/include/linux/spinlock.h +--- linux-4.4.28.orig/include/linux/spinlock.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/spinlock.h 2016-11-01 21:26:58.744340223 +0100 +@@ -271,7 +271,11 @@ + #define raw_spin_can_lock(lock) (!raw_spin_is_locked(lock)) + + /* Include rwlock functions */ +-#include ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++# include ++#endif + + /* + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: +@@ -282,6 +286,10 @@ + # include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else /* PREEMPT_RT_FULL */ ++ + /* + * Map the spin_lock functions to the raw variants for PREEMPT_RT=n + */ +@@ -347,6 +355,12 @@ + raw_spin_unlock(&lock->rlock); + } + ++static __always_inline int spin_unlock_no_deboost(spinlock_t *lock) ++{ ++ raw_spin_unlock(&lock->rlock); ++ return 0; ++} ++ + static __always_inline void spin_unlock_bh(spinlock_t *lock) + { + raw_spin_unlock_bh(&lock->rlock); +@@ -416,4 +430,6 @@ + #define atomic_dec_and_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* __LINUX_SPINLOCK_H */ +diff -Nur linux-4.4.28.orig/include/linux/spinlock_rt.h linux-4.4.28/include/linux/spinlock_rt.h +--- linux-4.4.28.orig/include/linux/spinlock_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/spinlock_rt.h 2016-11-01 21:26:58.744340223 +0100 +@@ -0,0 +1,165 @@ ++#ifndef __LINUX_SPINLOCK_RT_H ++#define __LINUX_SPINLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#include ++ ++extern void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key); ++ ++#define spin_lock_init(slock) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(slock)->lock); \ ++ __rt_spin_lock_init(slock, #slock, &__key); \ ++} while (0) ++ ++void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock); ++void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock); ++int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock); ++ ++extern void __lockfunc rt_spin_lock(spinlock_t *lock); ++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); ++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); ++extern void __lockfunc rt_spin_unlock(spinlock_t *lock); ++extern int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); ++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock(spinlock_t *lock); ++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); ++ ++/* ++ * lockdep-less calls, for derived types like rwlock: ++ * (for trylock they can use rt_mutex_trylock() directly. ++ */ ++extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++extern int __lockfunc __rt_spin_trylock(struct rt_mutex *lock); ++ ++#define spin_lock(lock) rt_spin_lock(lock) ++ ++#define spin_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_irq(lock) spin_lock(lock) ++ ++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) ++ ++#define spin_trylock(lock) \ ++({ \ ++ int __locked; \ ++ __locked = spin_do_trylock(lock); \ ++ __locked; \ ++}) ++ ++#ifdef CONFIG_LOCKDEP ++# define spin_lock_nested(lock, subclass) \ ++ do { \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++#define spin_lock_bh_nested(lock, subclass) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++#else ++# define spin_lock_nested(lock, subclass) spin_lock(lock) ++# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++#endif ++ ++#define spin_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++ ++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) ++{ ++ unsigned long flags = 0; ++#ifdef CONFIG_TRACE_IRQFLAGS ++ flags = rt_spin_lock_trace_flags(lock); ++#else ++ spin_lock(lock); /* lock_local */ ++#endif ++ return flags; ++} ++ ++/* FIXME: we need rt_spin_lock_nest_lock */ ++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) ++ ++#define spin_unlock(lock) rt_spin_unlock(lock) ++#define spin_unlock_no_deboost(lock) rt_spin_unlock_no_deboost(lock) ++ ++#define spin_unlock_bh(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define spin_unlock_irq(lock) spin_unlock(lock) ++ ++#define spin_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ spin_unlock(lock); \ ++ } while (0) ++ ++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) ++#define spin_trylock_irq(lock) spin_trylock(lock) ++ ++#define spin_trylock_irqsave(lock, flags) \ ++ rt_spin_trylock_irqsave(lock, &(flags)) ++ ++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) ++ ++#ifdef CONFIG_GENERIC_LOCKBREAK ++# define spin_is_contended(lock) ((lock)->break_lock) ++#else ++# define spin_is_contended(lock) (((void)(lock), 0)) ++#endif ++ ++static inline int spin_can_lock(spinlock_t *lock) ++{ ++ return !rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline int spin_is_locked(spinlock_t *lock) ++{ ++ return rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline void assert_spin_locked(spinlock_t *lock) ++{ ++ BUG_ON(!spin_is_locked(lock)); ++} ++ ++#define atomic_dec_and_lock(atomic, lock) \ ++ atomic_dec_and_spin_lock(atomic, lock) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/spinlock_types.h linux-4.4.28/include/linux/spinlock_types.h +--- linux-4.4.28.orig/include/linux/spinlock_types.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/spinlock_types.h 2016-11-01 21:26:58.744340223 +0100 +@@ -9,80 +9,15 @@ + * Released under the General Public License (GPL). + */ + +-#if defined(CONFIG_SMP) +-# include +-#else +-# include +-#endif +- +-#include +- +-typedef struct raw_spinlock { +- arch_spinlock_t raw_lock; +-#ifdef CONFIG_GENERIC_LOCKBREAK +- unsigned int break_lock; +-#endif +-#ifdef CONFIG_DEBUG_SPINLOCK +- unsigned int magic, owner_cpu; +- void *owner; +-#endif +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +- struct lockdep_map dep_map; +-#endif +-} raw_spinlock_t; +- +-#define SPINLOCK_MAGIC 0xdead4ead +- +-#define SPINLOCK_OWNER_INIT ((void *)-1L) +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +-#else +-# define SPIN_DEP_MAP_INIT(lockname) +-#endif ++#include + +-#ifdef CONFIG_DEBUG_SPINLOCK +-# define SPIN_DEBUG_INIT(lockname) \ +- .magic = SPINLOCK_MAGIC, \ +- .owner_cpu = -1, \ +- .owner = SPINLOCK_OWNER_INIT, ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++# include + #else +-# define SPIN_DEBUG_INIT(lockname) ++# include ++# include ++# include + #endif + +-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +- { \ +- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +- SPIN_DEBUG_INIT(lockname) \ +- SPIN_DEP_MAP_INIT(lockname) } +- +-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ +- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +- +-typedef struct spinlock { +- union { +- struct raw_spinlock rlock; +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) +- struct { +- u8 __padding[LOCK_PADSIZE]; +- struct lockdep_map dep_map; +- }; +-#endif +- }; +-} spinlock_t; +- +-#define __SPIN_LOCK_INITIALIZER(lockname) \ +- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } +- +-#define __SPIN_LOCK_UNLOCKED(lockname) \ +- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) +- +-#include +- + #endif /* __LINUX_SPINLOCK_TYPES_H */ +diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_nort.h linux-4.4.28/include/linux/spinlock_types_nort.h +--- linux-4.4.28.orig/include/linux/spinlock_types_nort.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/spinlock_types_nort.h 2016-11-01 21:26:58.744340223 +0100 +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H ++#define __LINUX_SPINLOCK_TYPES_NORT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * The non RT version maps spinlocks to raw_spinlocks ++ */ ++typedef struct spinlock { ++ union { ++ struct raw_spinlock rlock; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) ++ struct { ++ u8 __padding[LOCK_PADSIZE]; ++ struct lockdep_map dep_map; ++ }; ++#endif ++ }; ++} spinlock_t; ++ ++#define __SPIN_LOCK_INITIALIZER(lockname) \ ++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } ++ ++#define __SPIN_LOCK_UNLOCKED(lockname) \ ++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_raw.h linux-4.4.28/include/linux/spinlock_types_raw.h +--- linux-4.4.28.orig/include/linux/spinlock_types_raw.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/spinlock_types_raw.h 2016-11-01 21:26:58.744340223 +0100 +@@ -0,0 +1,56 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H ++#define __LINUX_SPINLOCK_TYPES_RAW_H ++ ++#if defined(CONFIG_SMP) ++# include ++#else ++# include ++#endif ++ ++#include ++ ++typedef struct raw_spinlock { ++ arch_spinlock_t raw_lock; ++#ifdef CONFIG_GENERIC_LOCKBREAK ++ unsigned int break_lock; ++#endif ++#ifdef CONFIG_DEBUG_SPINLOCK ++ unsigned int magic, owner_cpu; ++ void *owner; ++#endif ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} raw_spinlock_t; ++ ++#define SPINLOCK_MAGIC 0xdead4ead ++ ++#define SPINLOCK_OWNER_INIT ((void *)-1L) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define SPIN_DEP_MAP_INIT(lockname) ++#endif ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define SPIN_DEBUG_INIT(lockname) \ ++ .magic = SPINLOCK_MAGIC, \ ++ .owner_cpu = -1, \ ++ .owner = SPINLOCK_OWNER_INIT, ++#else ++# define SPIN_DEBUG_INIT(lockname) ++#endif ++ ++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ ++ { \ ++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ ++ SPIN_DEBUG_INIT(lockname) \ ++ SPIN_DEP_MAP_INIT(lockname) } ++ ++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ ++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/spinlock_types_rt.h linux-4.4.28/include/linux/spinlock_types_rt.h +--- linux-4.4.28.orig/include/linux/spinlock_types_rt.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/spinlock_types_rt.h 2016-11-01 21:26:58.744340223 +0100 +@@ -0,0 +1,51 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RT_H ++#define __LINUX_SPINLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#include ++ ++/* ++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: ++ */ ++typedef struct spinlock { ++ struct rt_mutex lock; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} spinlock_t; ++ ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ .file = __FILE__, \ ++ .line = __LINE__ , \ ++ } ++#else ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ } ++#endif ++ ++/* ++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) ++*/ ++ ++#define __SPIN_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ ++ SPIN_DEP_MAP_INIT(name) } ++ ++#define __DEFINE_SPINLOCK(name) \ ++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) ++ ++#define DEFINE_SPINLOCK(name) \ ++ spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name) ++ ++#endif +diff -Nur linux-4.4.28.orig/include/linux/srcu.h linux-4.4.28/include/linux/srcu.h +--- linux-4.4.28.orig/include/linux/srcu.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/srcu.h 2016-11-01 21:26:58.744340223 +0100 +@@ -84,10 +84,10 @@ + + void process_srcu(struct work_struct *work); + +-#define __SRCU_STRUCT_INIT(name) \ ++#define __SRCU_STRUCT_INIT(name, pcpu_name) \ + { \ + .completed = -300, \ +- .per_cpu_ref = &name##_srcu_array, \ ++ .per_cpu_ref = &pcpu_name, \ + .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \ + .running = false, \ + .batch_queue = RCU_BATCH_INIT(name.batch_queue), \ +@@ -104,7 +104,7 @@ + */ + #define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ +- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) ++ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array) + #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) + #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) + +diff -Nur linux-4.4.28.orig/include/linux/suspend.h linux-4.4.28/include/linux/suspend.h +--- linux-4.4.28.orig/include/linux/suspend.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/suspend.h 2016-11-01 21:26:58.748340476 +0100 +@@ -194,6 +194,12 @@ + void (*end)(void); + }; + ++#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) ++extern bool pm_in_action; ++#else ++# define pm_in_action false ++#endif ++ + #ifdef CONFIG_SUSPEND + /** + * suspend_set_ops - set platform dependent suspend operations +diff -Nur linux-4.4.28.orig/include/linux/swait.h linux-4.4.28/include/linux/swait.h +--- linux-4.4.28.orig/include/linux/swait.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/swait.h 2016-11-01 21:26:58.748340476 +0100 +@@ -0,0 +1,173 @@ ++#ifndef _LINUX_SWAIT_H ++#define _LINUX_SWAIT_H ++ ++#include ++#include ++#include ++#include ++ ++/* ++ * Simple wait queues ++ * ++ * While these are very similar to the other/complex wait queues (wait.h) the ++ * most important difference is that the simple waitqueue allows for ++ * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold ++ * times. ++ * ++ * In order to make this so, we had to drop a fair number of features of the ++ * other waitqueue code; notably: ++ * ++ * - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue; ++ * all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right ++ * sleeper state. ++ * ++ * - the exclusive mode; because this requires preserving the list order ++ * and this is hard. ++ * ++ * - custom wake functions; because you cannot give any guarantees about ++ * random code. ++ * ++ * As a side effect of this; the data structures are slimmer. ++ * ++ * One would recommend using this wait queue where possible. ++ */ ++ ++struct task_struct; ++ ++struct swait_queue_head { ++ raw_spinlock_t lock; ++ struct list_head task_list; ++}; ++ ++struct swait_queue { ++ struct task_struct *task; ++ struct list_head task_list; ++}; ++ ++#define __SWAITQUEUE_INITIALIZER(name) { \ ++ .task = current, \ ++ .task_list = LIST_HEAD_INIT((name).task_list), \ ++} ++ ++#define DECLARE_SWAITQUEUE(name) \ ++ struct swait_queue name = __SWAITQUEUE_INITIALIZER(name) ++ ++#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) { \ ++ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ ++ .task_list = LIST_HEAD_INIT((name).task_list), \ ++} ++ ++#define DECLARE_SWAIT_QUEUE_HEAD(name) \ ++ struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name) ++ ++extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name, ++ struct lock_class_key *key); ++ ++#define init_swait_queue_head(q) \ ++ do { \ ++ static struct lock_class_key __key; \ ++ __init_swait_queue_head((q), #q, &__key); \ ++ } while (0) ++ ++#ifdef CONFIG_LOCKDEP ++# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ ++ ({ init_swait_queue_head(&name); name; }) ++# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ ++ struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name) ++#else ++# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name) \ ++ DECLARE_SWAIT_QUEUE_HEAD(name) ++#endif ++ ++static inline int swait_active(struct swait_queue_head *q) ++{ ++ return !list_empty(&q->task_list); ++} ++ ++extern void swake_up(struct swait_queue_head *q); ++extern void swake_up_all(struct swait_queue_head *q); ++extern void swake_up_locked(struct swait_queue_head *q); ++extern void swake_up_all_locked(struct swait_queue_head *q); ++ ++extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); ++extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); ++extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state); ++ ++extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait); ++extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait); ++ ++/* as per ___wait_event() but for swait, therefore "exclusive == 0" */ ++#define ___swait_event(wq, condition, state, ret, cmd) \ ++({ \ ++ struct swait_queue __wait; \ ++ long __ret = ret; \ ++ \ ++ INIT_LIST_HEAD(&__wait.task_list); \ ++ for (;;) { \ ++ long __int = prepare_to_swait_event(&wq, &__wait, state);\ ++ \ ++ if (condition) \ ++ break; \ ++ \ ++ if (___wait_is_interruptible(state) && __int) { \ ++ __ret = __int; \ ++ break; \ ++ } \ ++ \ ++ cmd; \ ++ } \ ++ finish_swait(&wq, &__wait); \ ++ __ret; \ ++}) ++ ++#define __swait_event(wq, condition) \ ++ (void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, \ ++ schedule()) ++ ++#define swait_event(wq, condition) \ ++do { \ ++ if (condition) \ ++ break; \ ++ __swait_event(wq, condition); \ ++} while (0) ++ ++#define __swait_event_timeout(wq, condition, timeout) \ ++ ___swait_event(wq, ___wait_cond_timeout(condition), \ ++ TASK_UNINTERRUPTIBLE, timeout, \ ++ __ret = schedule_timeout(__ret)) ++ ++#define swait_event_timeout(wq, condition, timeout) \ ++({ \ ++ long __ret = timeout; \ ++ if (!___wait_cond_timeout(condition)) \ ++ __ret = __swait_event_timeout(wq, condition, timeout); \ ++ __ret; \ ++}) ++ ++#define __swait_event_interruptible(wq, condition) \ ++ ___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0, \ ++ schedule()) ++ ++#define swait_event_interruptible(wq, condition) \ ++({ \ ++ int __ret = 0; \ ++ if (!(condition)) \ ++ __ret = __swait_event_interruptible(wq, condition); \ ++ __ret; \ ++}) ++ ++#define __swait_event_interruptible_timeout(wq, condition, timeout) \ ++ ___swait_event(wq, ___wait_cond_timeout(condition), \ ++ TASK_INTERRUPTIBLE, timeout, \ ++ __ret = schedule_timeout(__ret)) ++ ++#define swait_event_interruptible_timeout(wq, condition, timeout) \ ++({ \ ++ long __ret = timeout; \ ++ if (!___wait_cond_timeout(condition)) \ ++ __ret = __swait_event_interruptible_timeout(wq, \ ++ condition, timeout); \ ++ __ret; \ ++}) ++ ++#endif /* _LINUX_SWAIT_H */ +diff -Nur linux-4.4.28.orig/include/linux/swap.h linux-4.4.28/include/linux/swap.h +--- linux-4.4.28.orig/include/linux/swap.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/swap.h 2016-11-01 21:26:58.748340476 +0100 +@@ -11,6 +11,7 @@ + #include + #include + #include ++#include + #include + + struct notifier_block; +@@ -252,7 +253,8 @@ + void *workingset_eviction(struct address_space *mapping, struct page *page); + bool workingset_refault(void *shadow); + void workingset_activation(struct page *page); +-extern struct list_lru workingset_shadow_nodes; ++extern struct list_lru __workingset_shadow_nodes; ++DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static inline unsigned int workingset_node_pages(struct radix_tree_node *node) + { +@@ -298,6 +300,7 @@ + + + /* linux/mm/swap.c */ ++DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); + extern void lru_cache_add(struct page *); + extern void lru_cache_add_anon(struct page *page); + extern void lru_cache_add_file(struct page *page); +diff -Nur linux-4.4.28.orig/include/linux/swork.h linux-4.4.28/include/linux/swork.h +--- linux-4.4.28.orig/include/linux/swork.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/linux/swork.h 2016-11-01 21:26:58.748340476 +0100 +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_SWORK_H ++#define _LINUX_SWORK_H ++ ++#include ++ ++struct swork_event { ++ struct list_head item; ++ unsigned long flags; ++ void (*func)(struct swork_event *); ++}; ++ ++static inline void INIT_SWORK(struct swork_event *event, ++ void (*func)(struct swork_event *)) ++{ ++ event->flags = 0; ++ event->func = func; ++} ++ ++bool swork_queue(struct swork_event *sev); ++ ++int swork_get(void); ++void swork_put(void); ++ ++#endif /* _LINUX_SWORK_H */ +diff -Nur linux-4.4.28.orig/include/linux/thread_info.h linux-4.4.28/include/linux/thread_info.h +--- linux-4.4.28.orig/include/linux/thread_info.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/thread_info.h 2016-11-01 21:26:58.748340476 +0100 +@@ -102,7 +102,17 @@ + #define test_thread_flag(flag) \ + test_ti_thread_flag(current_thread_info(), flag) + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK + /* +diff -Nur linux-4.4.28.orig/include/linux/timer.h linux-4.4.28/include/linux/timer.h +--- linux-4.4.28.orig/include/linux/timer.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/timer.h 2016-11-01 21:26:58.748340476 +0100 +@@ -225,7 +225,7 @@ + + extern int try_to_del_timer_sync(struct timer_list *timer); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + extern int del_timer_sync(struct timer_list *timer); + #else + # define del_timer_sync(t) del_timer(t) +diff -Nur linux-4.4.28.orig/include/linux/trace_events.h linux-4.4.28/include/linux/trace_events.h +--- linux-4.4.28.orig/include/linux/trace_events.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/trace_events.h 2016-11-01 21:26:58.748340476 +0100 +@@ -66,6 +66,9 @@ + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned short migrate_disable; ++ unsigned short padding; ++ unsigned char preempt_lazy_count; + }; + + #define TRACE_EVENT_TYPE_MAX \ +diff -Nur linux-4.4.28.orig/include/linux/uaccess.h linux-4.4.28/include/linux/uaccess.h +--- linux-4.4.28.orig/include/linux/uaccess.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/uaccess.h 2016-11-01 21:26:58.748340476 +0100 +@@ -24,6 +24,7 @@ + */ + static inline void pagefault_disable(void) + { ++ migrate_disable(); + pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault +@@ -40,6 +41,7 @@ + */ + barrier(); + pagefault_disabled_dec(); ++ migrate_enable(); + } + + /* +diff -Nur linux-4.4.28.orig/include/linux/uprobes.h linux-4.4.28/include/linux/uprobes.h +--- linux-4.4.28.orig/include/linux/uprobes.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/uprobes.h 2016-11-01 21:26:58.748340476 +0100 +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + + struct vm_area_struct; + struct mm_struct; +diff -Nur linux-4.4.28.orig/include/linux/vmstat.h linux-4.4.28/include/linux/vmstat.h +--- linux-4.4.28.orig/include/linux/vmstat.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/vmstat.h 2016-11-01 21:26:58.748340476 +0100 +@@ -33,7 +33,9 @@ + */ + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + raw_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -43,7 +45,9 @@ + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + raw_cpu_add(vm_event_states.event[item], delta); ++ preempt_enable_rt(); + } + + static inline void count_vm_events(enum vm_event_item item, long delta) +diff -Nur linux-4.4.28.orig/include/linux/wait.h linux-4.4.28/include/linux/wait.h +--- linux-4.4.28.orig/include/linux/wait.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/linux/wait.h 2016-11-01 21:26:58.748340476 +0100 +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + + typedef struct __wait_queue wait_queue_t; + typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key); +diff -Nur linux-4.4.28.orig/include/net/dst.h linux-4.4.28/include/net/dst.h +--- linux-4.4.28.orig/include/net/dst.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/net/dst.h 2016-11-01 21:26:58.748340476 +0100 +@@ -437,7 +437,7 @@ + static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, + struct sk_buff *skb) + { +- const struct hh_cache *hh; ++ struct hh_cache *hh; + + if (dst->pending_confirm) { + unsigned long now = jiffies; +diff -Nur linux-4.4.28.orig/include/net/neighbour.h linux-4.4.28/include/net/neighbour.h +--- linux-4.4.28.orig/include/net/neighbour.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/net/neighbour.h 2016-11-01 21:26:58.748340476 +0100 +@@ -446,7 +446,7 @@ + } + #endif + +-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) ++static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) + { + unsigned int seq; + int hh_len; +@@ -501,7 +501,7 @@ + + #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) + +-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, ++static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, + const struct net_device *dev) + { + unsigned int seq; +diff -Nur linux-4.4.28.orig/include/net/netns/ipv4.h linux-4.4.28/include/net/netns/ipv4.h +--- linux-4.4.28.orig/include/net/netns/ipv4.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/net/netns/ipv4.h 2016-11-01 21:26:58.748340476 +0100 +@@ -70,6 +70,7 @@ + + int sysctl_icmp_echo_ignore_all; + int sysctl_icmp_echo_ignore_broadcasts; ++ int sysctl_icmp_echo_sysrq; + int sysctl_icmp_ignore_bogus_error_responses; + int sysctl_icmp_ratelimit; + int sysctl_icmp_ratemask; +diff -Nur linux-4.4.28.orig/include/trace/events/hist.h linux-4.4.28/include/trace/events/hist.h +--- linux-4.4.28.orig/include/trace/events/hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/trace/events/hist.h 2016-11-01 21:26:58.748340476 +0100 +@@ -0,0 +1,73 @@ ++#undef TRACE_SYSTEM ++#define TRACE_SYSTEM hist ++ ++#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ) ++#define _TRACE_HIST_H ++ ++#include "latency_hist.h" ++#include ++ ++#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST) ++#define trace_preemptirqsoff_hist(a, b) ++#define trace_preemptirqsoff_hist_rcuidle(a, b) ++#else ++TRACE_EVENT(preemptirqsoff_hist, ++ ++ TP_PROTO(int reason, int starthist), ++ ++ TP_ARGS(reason, starthist), ++ ++ TP_STRUCT__entry( ++ __field(int, reason) ++ __field(int, starthist) ++ ), ++ ++ TP_fast_assign( ++ __entry->reason = reason; ++ __entry->starthist = starthist; ++ ), ++ ++ TP_printk("reason=%s starthist=%s", getaction(__entry->reason), ++ __entry->starthist ? "start" : "stop") ++); ++#endif ++ ++#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST ++#define trace_hrtimer_interrupt(a, b, c, d) ++#else ++TRACE_EVENT(hrtimer_interrupt, ++ ++ TP_PROTO(int cpu, long long offset, struct task_struct *curr, ++ struct task_struct *task), ++ ++ TP_ARGS(cpu, offset, curr, task), ++ ++ TP_STRUCT__entry( ++ __field(int, cpu) ++ __field(long long, offset) ++ __array(char, ccomm, TASK_COMM_LEN) ++ __field(int, cprio) ++ __array(char, tcomm, TASK_COMM_LEN) ++ __field(int, tprio) ++ ), ++ ++ TP_fast_assign( ++ __entry->cpu = cpu; ++ __entry->offset = offset; ++ memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN); ++ __entry->cprio = curr->prio; ++ memcpy(__entry->tcomm, task != NULL ? task->comm : "", ++ task != NULL ? TASK_COMM_LEN : 7); ++ __entry->tprio = task != NULL ? task->prio : -1; ++ ), ++ ++ TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]", ++ __entry->cpu, __entry->offset, __entry->ccomm, ++ __entry->cprio, __entry->tcomm, __entry->tprio) ++); ++#endif ++ ++#endif /* _TRACE_HIST_H */ ++ ++/* This part must be outside protection */ ++#include +diff -Nur linux-4.4.28.orig/include/trace/events/latency_hist.h linux-4.4.28/include/trace/events/latency_hist.h +--- linux-4.4.28.orig/include/trace/events/latency_hist.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/include/trace/events/latency_hist.h 2016-11-01 21:26:58.752340732 +0100 +@@ -0,0 +1,29 @@ ++#ifndef _LATENCY_HIST_H ++#define _LATENCY_HIST_H ++ ++enum hist_action { ++ IRQS_ON, ++ PREEMPT_ON, ++ TRACE_STOP, ++ IRQS_OFF, ++ PREEMPT_OFF, ++ TRACE_START, ++}; ++ ++static char *actions[] = { ++ "IRQS_ON", ++ "PREEMPT_ON", ++ "TRACE_STOP", ++ "IRQS_OFF", ++ "PREEMPT_OFF", ++ "TRACE_START", ++}; ++ ++static inline char *getaction(int action) ++{ ++ if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0])) ++ return actions[action]; ++ return "unknown"; ++} ++ ++#endif /* _LATENCY_HIST_H */ +diff -Nur linux-4.4.28.orig/include/trace/events/writeback.h linux-4.4.28/include/trace/events/writeback.h +--- linux-4.4.28.orig/include/trace/events/writeback.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/include/trace/events/writeback.h 2016-11-01 21:26:58.752340732 +0100 +@@ -134,58 +134,28 @@ + #ifdef CREATE_TRACE_POINTS + #ifdef CONFIG_CGROUP_WRITEBACK + +-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) ++static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) + { +- return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1; ++ return wb->memcg_css->cgroup->kn->ino; + } + +-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) +-{ +- struct cgroup *cgrp = wb->memcg_css->cgroup; +- char *path; +- +- path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1); +- WARN_ON_ONCE(path != buf); +-} +- +-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) +-{ +- if (wbc->wb) +- return __trace_wb_cgroup_size(wbc->wb); +- else +- return 2; +-} +- +-static inline void __trace_wbc_assign_cgroup(char *buf, +- struct writeback_control *wbc) ++static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) + { + if (wbc->wb) +- __trace_wb_assign_cgroup(buf, wbc->wb); ++ return __trace_wb_assign_cgroup(wbc->wb); + else +- strcpy(buf, "/"); ++ return -1U; + } +- + #else /* CONFIG_CGROUP_WRITEBACK */ + +-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb) +-{ +- return 2; +-} +- +-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb) +-{ +- strcpy(buf, "/"); +-} +- +-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc) ++static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb) + { +- return 2; ++ return -1U; + } + +-static inline void __trace_wbc_assign_cgroup(char *buf, +- struct writeback_control *wbc) ++static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc) + { +- strcpy(buf, "/"); ++ return -1U; + } + + #endif /* CONFIG_CGROUP_WRITEBACK */ +@@ -201,7 +171,7 @@ + __array(char, name, 32) + __field(unsigned long, ino) + __field(int, sync_mode) +- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -209,14 +179,14 @@ + dev_name(inode_to_bdi(inode)->dev), 32); + __entry->ino = inode->i_ino; + __entry->sync_mode = wbc->sync_mode; +- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ++ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); + ), + +- TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s", ++ TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u", + __entry->name, + __entry->ino, + __entry->sync_mode, +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +@@ -246,7 +216,7 @@ + __field(int, range_cyclic) + __field(int, for_background) + __field(int, reason) +- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ++ __field(unsigned int, cgroup_ino) + ), + TP_fast_assign( + strncpy(__entry->name, +@@ -258,10 +228,10 @@ + __entry->range_cyclic = work->range_cyclic; + __entry->for_background = work->for_background; + __entry->reason = work->reason; +- __trace_wb_assign_cgroup(__get_str(cgroup), wb); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); + ), + TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " +- "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s", ++ "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u", + __entry->name, + MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), + __entry->nr_pages, +@@ -270,7 +240,7 @@ + __entry->range_cyclic, + __entry->for_background, + __print_symbolic(__entry->reason, WB_WORK_REASON), +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + #define DEFINE_WRITEBACK_WORK_EVENT(name) \ +@@ -300,15 +270,15 @@ + TP_ARGS(wb), + TP_STRUCT__entry( + __array(char, name, 32) +- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ++ __field(unsigned int, cgroup_ino) + ), + TP_fast_assign( + strncpy(__entry->name, dev_name(wb->bdi->dev), 32); +- __trace_wb_assign_cgroup(__get_str(cgroup), wb); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); + ), +- TP_printk("bdi %s: cgroup=%s", ++ TP_printk("bdi %s: cgroup_ino=%u", + __entry->name, +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + #define DEFINE_WRITEBACK_EVENT(name) \ +@@ -347,7 +317,7 @@ + __field(int, range_cyclic) + __field(long, range_start) + __field(long, range_end) +- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -361,12 +331,12 @@ + __entry->range_cyclic = wbc->range_cyclic; + __entry->range_start = (long)wbc->range_start; + __entry->range_end = (long)wbc->range_end; +- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ++ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); + ), + + TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " + "bgrd=%d reclm=%d cyclic=%d " +- "start=0x%lx end=0x%lx cgroup=%s", ++ "start=0x%lx end=0x%lx cgroup_ino=%u", + __entry->name, + __entry->nr_to_write, + __entry->pages_skipped, +@@ -377,7 +347,7 @@ + __entry->range_cyclic, + __entry->range_start, + __entry->range_end, +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ) + +@@ -398,7 +368,7 @@ + __field(long, age) + __field(int, moved) + __field(int, reason) +- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ++ __field(unsigned int, cgroup_ino) + ), + TP_fast_assign( + unsigned long *older_than_this = work->older_than_this; +@@ -408,15 +378,15 @@ + (jiffies - *older_than_this) * 1000 / HZ : -1; + __entry->moved = moved; + __entry->reason = work->reason; +- __trace_wb_assign_cgroup(__get_str(cgroup), wb); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); + ), +- TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s", ++ TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u", + __entry->name, + __entry->older, /* older_than_this in jiffies */ + __entry->age, /* older_than_this in relative milliseconds */ + __entry->moved, + __print_symbolic(__entry->reason, WB_WORK_REASON), +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +@@ -484,7 +454,7 @@ + __field(unsigned long, dirty_ratelimit) + __field(unsigned long, task_ratelimit) + __field(unsigned long, balanced_dirty_ratelimit) +- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -496,13 +466,13 @@ + __entry->task_ratelimit = KBps(task_ratelimit); + __entry->balanced_dirty_ratelimit = + KBps(wb->balanced_dirty_ratelimit); +- __trace_wb_assign_cgroup(__get_str(cgroup), wb); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); + ), + + TP_printk("bdi %s: " + "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " + "dirty_ratelimit=%lu task_ratelimit=%lu " +- "balanced_dirty_ratelimit=%lu cgroup=%s", ++ "balanced_dirty_ratelimit=%lu cgroup_ino=%u", + __entry->bdi, + __entry->write_bw, /* write bandwidth */ + __entry->avg_write_bw, /* avg write bandwidth */ +@@ -510,7 +480,7 @@ + __entry->dirty_ratelimit, /* base ratelimit */ + __entry->task_ratelimit, /* ratelimit with position control */ + __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +@@ -548,7 +518,7 @@ + __field( long, pause) + __field(unsigned long, period) + __field( long, think) +- __dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb)) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -571,7 +541,7 @@ + __entry->period = period * 1000 / HZ; + __entry->pause = pause * 1000 / HZ; + __entry->paused = (jiffies - start_time) * 1000 / HZ; +- __trace_wb_assign_cgroup(__get_str(cgroup), wb); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); + ), + + +@@ -580,7 +550,7 @@ + "bdi_setpoint=%lu bdi_dirty=%lu " + "dirty_ratelimit=%lu task_ratelimit=%lu " + "dirtied=%u dirtied_pause=%u " +- "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s", ++ "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u", + __entry->bdi, + __entry->limit, + __entry->setpoint, +@@ -595,7 +565,7 @@ + __entry->pause, /* ms */ + __entry->period, /* ms */ + __entry->think, /* ms */ +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +@@ -609,8 +579,7 @@ + __field(unsigned long, ino) + __field(unsigned long, state) + __field(unsigned long, dirtied_when) +- __dynamic_array(char, cgroup, +- __trace_wb_cgroup_size(inode_to_wb(inode))) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -619,16 +588,16 @@ + __entry->ino = inode->i_ino; + __entry->state = inode->i_state; + __entry->dirtied_when = inode->dirtied_when; +- __trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode)); ++ __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); + ), + +- TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s", ++ TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u", + __entry->name, + __entry->ino, + show_inode_state(__entry->state), + __entry->dirtied_when, + (jiffies - __entry->dirtied_when) / HZ, +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +@@ -684,7 +653,7 @@ + __field(unsigned long, writeback_index) + __field(long, nr_to_write) + __field(unsigned long, wrote) +- __dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc)) ++ __field(unsigned int, cgroup_ino) + ), + + TP_fast_assign( +@@ -696,11 +665,11 @@ + __entry->writeback_index = inode->i_mapping->writeback_index; + __entry->nr_to_write = nr_to_write; + __entry->wrote = nr_to_write - wbc->nr_to_write; +- __trace_wbc_assign_cgroup(__get_str(cgroup), wbc); ++ __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); + ), + + TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " +- "index=%lu to_write=%ld wrote=%lu cgroup=%s", ++ "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u", + __entry->name, + __entry->ino, + show_inode_state(__entry->state), +@@ -709,7 +678,7 @@ + __entry->writeback_index, + __entry->nr_to_write, + __entry->wrote, +- __get_str(cgroup) ++ __entry->cgroup_ino + ) + ); + +diff -Nur linux-4.4.28.orig/init/Kconfig linux-4.4.28/init/Kconfig +--- linux-4.4.28.orig/init/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/init/Kconfig 2016-11-01 21:26:58.752340732 +0100 +@@ -498,7 +498,7 @@ + + config RCU_EXPERT + bool "Make expert-level adjustments to RCU configuration" +- default n ++ default y if PREEMPT_RT_FULL + help + This option needs to be enabled if you wish to make + expert-level adjustments to RCU configuration. By default, +@@ -614,7 +614,7 @@ + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ_COMMON && SMP && RCU_EXPERT ++ depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL + default n + help + This option permits CPUs to enter dynticks-idle state even if +@@ -641,7 +641,7 @@ + config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT +- default n ++ default y if PREEMPT_RT_FULL + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. +@@ -1106,6 +1106,7 @@ + config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth +@@ -1719,6 +1720,7 @@ + + config SLAB + bool "SLAB" ++ depends on !PREEMPT_RT_FULL + help + The regular slab allocator that is established and known to work + well in all environments. It organizes cache hot objects in +@@ -1737,6 +1739,7 @@ + config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but +@@ -1746,7 +1749,7 @@ + + config SLUB_CPU_PARTIAL + default y +- depends on SLUB && SMP ++ depends on SLUB && SMP && !PREEMPT_RT_FULL + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accellerate objects allocation and freeing +diff -Nur linux-4.4.28.orig/init/main.c linux-4.4.28/init/main.c +--- linux-4.4.28.orig/init/main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/init/main.c 2016-11-01 21:26:58.752340732 +0100 +@@ -530,6 +530,7 @@ + setup_command_line(command_line); + setup_nr_cpu_ids(); + setup_per_cpu_areas(); ++ softirq_early_init(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + + build_all_zonelists(NULL, NULL); +diff -Nur linux-4.4.28.orig/init/Makefile linux-4.4.28/init/Makefile +--- linux-4.4.28.orig/init/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/init/Makefile 2016-11-01 21:26:58.752340732 +0100 +@@ -33,4 +33,4 @@ + include/generated/compile.h: FORCE + @$($(quiet)chk_compile.h) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ +- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" ++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" +diff -Nur linux-4.4.28.orig/ipc/msg.c linux-4.4.28/ipc/msg.c +--- linux-4.4.28.orig/ipc/msg.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/ipc/msg.c 2016-11-01 21:26:58.752340732 +0100 +@@ -183,20 +183,14 @@ + } + } + +-static void expunge_all(struct msg_queue *msq, int res) ++static void expunge_all(struct msg_queue *msq, int res, ++ struct wake_q_head *wake_q) + { + struct msg_receiver *msr, *t; + + list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { +- msr->r_msg = NULL; /* initialize expunge ordering */ +- wake_up_process(msr->r_tsk); +- /* +- * Ensure that the wakeup is visible before setting r_msg as +- * the receiving end depends on it: either spinning on a nil, +- * or dealing with -EAGAIN cases. See lockless receive part 1 +- * and 2 in do_msgrcv(). +- */ +- smp_wmb(); /* barrier (B) */ ++ ++ wake_q_add(wake_q, msr->r_tsk); + msr->r_msg = ERR_PTR(res); + } + } +@@ -213,11 +207,13 @@ + { + struct msg_msg *msg, *t; + struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); ++ WAKE_Q(wake_q); + +- expunge_all(msq, -EIDRM); ++ expunge_all(msq, -EIDRM, &wake_q); + ss_wakeup(&msq->q_senders, 1); + msg_rmid(ns, msq); + ipc_unlock_object(&msq->q_perm); ++ wake_up_q(&wake_q); + rcu_read_unlock(); + + list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { +@@ -342,6 +338,7 @@ + struct kern_ipc_perm *ipcp; + struct msqid64_ds uninitialized_var(msqid64); + struct msg_queue *msq; ++ WAKE_Q(wake_q); + int err; + + if (cmd == IPC_SET) { +@@ -389,7 +386,7 @@ + /* sleeping receivers might be excluded by + * stricter permissions. + */ +- expunge_all(msq, -EAGAIN); ++ expunge_all(msq, -EAGAIN, &wake_q); + /* sleeping senders might be able to send + * due to a larger queue size. + */ +@@ -402,6 +399,7 @@ + + out_unlock0: + ipc_unlock_object(&msq->q_perm); ++ wake_up_q(&wake_q); + out_unlock1: + rcu_read_unlock(); + out_up: +@@ -566,7 +564,8 @@ + return 0; + } + +-static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) ++static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, ++ struct wake_q_head *wake_q) + { + struct msg_receiver *msr, *t; + +@@ -577,27 +576,13 @@ + + list_del(&msr->r_list); + if (msr->r_maxsize < msg->m_ts) { +- /* initialize pipelined send ordering */ +- msr->r_msg = NULL; +- wake_up_process(msr->r_tsk); +- /* barrier (B) see barrier comment below */ +- smp_wmb(); ++ wake_q_add(wake_q, msr->r_tsk); + msr->r_msg = ERR_PTR(-E2BIG); + } else { +- msr->r_msg = NULL; + msq->q_lrpid = task_pid_vnr(msr->r_tsk); + msq->q_rtime = get_seconds(); +- wake_up_process(msr->r_tsk); +- /* +- * Ensure that the wakeup is visible before +- * setting r_msg, as the receiving can otherwise +- * exit - once r_msg is set, the receiver can +- * continue. See lockless receive part 1 and 2 +- * in do_msgrcv(). Barrier (B). +- */ +- smp_wmb(); ++ wake_q_add(wake_q, msr->r_tsk); + msr->r_msg = msg; +- + return 1; + } + } +@@ -613,6 +598,7 @@ + struct msg_msg *msg; + int err; + struct ipc_namespace *ns; ++ WAKE_Q(wake_q); + + ns = current->nsproxy->ipc_ns; + +@@ -698,7 +684,7 @@ + msq->q_lspid = task_tgid_vnr(current); + msq->q_stime = get_seconds(); + +- if (!pipelined_send(msq, msg)) { ++ if (!pipelined_send(msq, msg, &wake_q)) { + /* no one is waiting for this message, enqueue it */ + list_add_tail(&msg->m_list, &msq->q_messages); + msq->q_cbytes += msgsz; +@@ -712,6 +698,7 @@ + + out_unlock0: + ipc_unlock_object(&msq->q_perm); ++ wake_up_q(&wake_q); + out_unlock1: + rcu_read_unlock(); + if (msg != NULL) +@@ -932,57 +919,25 @@ + rcu_read_lock(); + + /* Lockless receive, part 2: +- * Wait until pipelined_send or expunge_all are outside of +- * wake_up_process(). There is a race with exit(), see +- * ipc/mqueue.c for the details. The correct serialization +- * ensures that a receiver cannot continue without the wakeup +- * being visibible _before_ setting r_msg: ++ * The work in pipelined_send() and expunge_all(): ++ * - Set pointer to message ++ * - Queue the receiver task for later wakeup ++ * - Wake up the process after the lock is dropped. + * +- * CPU 0 CPU 1 +- * +- * smp_rmb(); (A) <-- pair -. +- * r_msg> | msr->r_msg = NULL; +- * | wake_up_process(); +- * `------> smp_wmb(); (B) +- * msr->r_msg = msg; +- * +- * Where (A) orders the message value read and where (B) orders +- * the write to the r_msg -- done in both pipelined_send and +- * expunge_all. ++ * Should the process wake up before this wakeup (due to a ++ * signal) it will either see the message and continue … + */ +- for (;;) { +- /* +- * Pairs with writer barrier in pipelined_send +- * or expunge_all. +- */ +- smp_rmb(); /* barrier (A) */ +- msg = (struct msg_msg *)msr_d.r_msg; +- if (msg) +- break; + +- /* +- * The cpu_relax() call is a compiler barrier +- * which forces everything in this loop to be +- * re-loaded. +- */ +- cpu_relax(); +- } +- +- /* Lockless receive, part 3: +- * If there is a message or an error then accept it without +- * locking. +- */ ++ msg = (struct msg_msg *)msr_d.r_msg; + if (msg != ERR_PTR(-EAGAIN)) + goto out_unlock1; + +- /* Lockless receive, part 3: +- * Acquire the queue spinlock. +- */ ++ /* ++ * … or see -EAGAIN, acquire the lock to check the message ++ * again. ++ */ + ipc_lock_object(&msq->q_perm); + +- /* Lockless receive, part 4: +- * Repeat test after acquiring the spinlock. +- */ + msg = (struct msg_msg *)msr_d.r_msg; + if (msg != ERR_PTR(-EAGAIN)) + goto out_unlock0; +diff -Nur linux-4.4.28.orig/ipc/sem.c linux-4.4.28/ipc/sem.c +--- linux-4.4.28.orig/ipc/sem.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/ipc/sem.c 2016-11-01 21:26:58.756340996 +0100 +@@ -708,6 +708,13 @@ + static void wake_up_sem_queue_prepare(struct list_head *pt, + struct sem_queue *q, int error) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *p = q->sleeper; ++ get_task_struct(p); ++ q->status = error; ++ wake_up_process(p); ++ put_task_struct(p); ++#else + if (list_empty(pt)) { + /* + * Hold preempt off so that we don't get preempted and have the +@@ -719,6 +726,7 @@ + q->pid = error; + + list_add_tail(&q->list, pt); ++#endif + } + + /** +@@ -732,6 +740,7 @@ + */ + static void wake_up_sem_queue_do(struct list_head *pt) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + struct sem_queue *q, *t; + int did_something; + +@@ -744,6 +753,7 @@ + } + if (did_something) + preempt_enable(); ++#endif + } + + static void unlink_queue(struct sem_array *sma, struct sem_queue *q) +diff -Nur linux-4.4.28.orig/kernel/cgroup.c linux-4.4.28/kernel/cgroup.c +--- linux-4.4.28.orig/kernel/cgroup.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/cgroup.c 2016-11-01 21:26:58.756340996 +0100 +@@ -4737,10 +4737,10 @@ + queue_work(cgroup_destroy_wq, &css->destroy_work); + } + +-static void css_release_work_fn(struct work_struct *work) ++static void css_release_work_fn(struct swork_event *sev) + { + struct cgroup_subsys_state *css = +- container_of(work, struct cgroup_subsys_state, destroy_work); ++ container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + +@@ -4779,8 +4779,8 @@ + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + +- INIT_WORK(&css->destroy_work, css_release_work_fn); +- queue_work(cgroup_destroy_wq, &css->destroy_work); ++ INIT_SWORK(&css->destroy_swork, css_release_work_fn); ++ swork_queue(&css->destroy_swork); + } + + static void init_and_link_css(struct cgroup_subsys_state *css, +@@ -5397,6 +5397,7 @@ + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); ++ BUG_ON(swork_get()); + + /* + * Used to destroy pidlists and separate to serve as flush domain. +diff -Nur linux-4.4.28.orig/kernel/cpu.c linux-4.4.28/kernel/cpu.c +--- linux-4.4.28.orig/kernel/cpu.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/cpu.c 2016-11-01 21:26:58.756340996 +0100 +@@ -75,8 +75,8 @@ + #endif + } cpu_hotplug = { + .active_writer = NULL, +- .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), + .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock), ++ .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq), + #ifdef CONFIG_DEBUG_LOCK_ALLOC + .dep_map = {.name = "cpu_hotplug.lock" }, + #endif +@@ -89,6 +89,289 @@ + #define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map) + #define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map) + ++/** ++ * hotplug_pcp - per cpu hotplug descriptor ++ * @unplug: set when pin_current_cpu() needs to sync tasks ++ * @sync_tsk: the task that waits for tasks to finish pinned sections ++ * @refcount: counter of tasks in pinned sections ++ * @grab_lock: set when the tasks entering pinned sections should wait ++ * @synced: notifier for @sync_tsk to tell cpu_down it's finished ++ * @mutex: the mutex to make tasks wait (used when @grab_lock is true) ++ * @mutex_init: zero if the mutex hasn't been initialized yet. ++ * ++ * Although @unplug and @sync_tsk may point to the same task, the @unplug ++ * is used as a flag and still exists after @sync_tsk has exited and ++ * @sync_tsk set to NULL. ++ */ ++struct hotplug_pcp { ++ struct task_struct *unplug; ++ struct task_struct *sync_tsk; ++ int refcount; ++ int grab_lock; ++ struct completion synced; ++ struct completion unplug_wait; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * Note, on PREEMPT_RT, the hotplug lock must save the state of ++ * the task, otherwise the mutex will cause the task to fail ++ * to sleep when required. (Because it's called from migrate_disable()) ++ * ++ * The spinlock_t on PREEMPT_RT is a mutex that saves the task's ++ * state. ++ */ ++ spinlock_t lock; ++#else ++ struct mutex mutex; ++#endif ++ int mutex_init; ++}; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define hotplug_lock(hp) rt_spin_lock__no_mg(&(hp)->lock) ++# define hotplug_unlock(hp) rt_spin_unlock__no_mg(&(hp)->lock) ++#else ++# define hotplug_lock(hp) mutex_lock(&(hp)->mutex) ++# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex) ++#endif ++ ++static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp); ++ ++/** ++ * pin_current_cpu - Prevent the current cpu from being unplugged ++ * ++ * Lightweight version of get_online_cpus() to prevent cpu from being ++ * unplugged when code runs in a migration disabled region. ++ * ++ * Must be called with preemption disabled (preempt_count = 1)! ++ */ ++void pin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp; ++ int force = 0; ++ ++retry: ++ hp = this_cpu_ptr(&hotplug_pcp); ++ ++ if (!hp->unplug || hp->refcount || force || preempt_count() > 1 || ++ hp->unplug == current) { ++ hp->refcount++; ++ return; ++ } ++ if (hp->grab_lock) { ++ preempt_enable(); ++ hotplug_lock(hp); ++ hotplug_unlock(hp); ++ } else { ++ preempt_enable(); ++ /* ++ * Try to push this task off of this CPU. ++ */ ++ if (!migrate_me()) { ++ preempt_disable(); ++ hp = this_cpu_ptr(&hotplug_pcp); ++ if (!hp->grab_lock) { ++ /* ++ * Just let it continue it's already pinned ++ * or about to sleep. ++ */ ++ force = 1; ++ goto retry; ++ } ++ preempt_enable(); ++ } ++ } ++ preempt_disable(); ++ goto retry; ++} ++ ++/** ++ * unpin_current_cpu - Allow unplug of current cpu ++ * ++ * Must be called with preemption or interrupts disabled! ++ */ ++void unpin_current_cpu(void) ++{ ++ struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp); ++ ++ WARN_ON(hp->refcount <= 0); ++ ++ /* This is safe. sync_unplug_thread is pinned to this cpu */ ++ if (!--hp->refcount && hp->unplug && hp->unplug != current) ++ wake_up_process(hp->unplug); ++} ++ ++static void wait_for_pinned_cpus(struct hotplug_pcp *hp) ++{ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (hp->refcount) { ++ schedule_preempt_disabled(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++} ++ ++static int sync_unplug_thread(void *data) ++{ ++ struct hotplug_pcp *hp = data; ++ ++ wait_for_completion(&hp->unplug_wait); ++ preempt_disable(); ++ hp->unplug = current; ++ wait_for_pinned_cpus(hp); ++ ++ /* ++ * This thread will synchronize the cpu_down() with threads ++ * that have pinned the CPU. When the pinned CPU count reaches ++ * zero, we inform the cpu_down code to continue to the next step. ++ */ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ preempt_enable(); ++ complete(&hp->synced); ++ ++ /* ++ * If all succeeds, the next step will need tasks to wait till ++ * the CPU is offline before continuing. To do this, the grab_lock ++ * is set and tasks going into pin_current_cpu() will block on the ++ * mutex. But we still need to wait for those that are already in ++ * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop() ++ * will kick this thread out. ++ */ ++ while (!hp->grab_lock && !kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ ++ /* Make sure grab_lock is seen before we see a stale completion */ ++ smp_mb(); ++ ++ /* ++ * Now just before cpu_down() enters stop machine, we need to make ++ * sure all tasks that are in pinned CPU sections are out, and new ++ * tasks will now grab the lock, keeping them from entering pinned ++ * CPU sections. ++ */ ++ if (!kthread_should_stop()) { ++ preempt_disable(); ++ wait_for_pinned_cpus(hp); ++ preempt_enable(); ++ complete(&hp->synced); ++ } ++ ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ } ++ set_current_state(TASK_RUNNING); ++ ++ /* ++ * Force this thread off this CPU as it's going down and ++ * we don't want any more work on this CPU. ++ */ ++ current->flags &= ~PF_NO_SETAFFINITY; ++ set_cpus_allowed_ptr(current, cpu_present_mask); ++ migrate_me(); ++ return 0; ++} ++ ++static void __cpu_unplug_sync(struct hotplug_pcp *hp) ++{ ++ wake_up_process(hp->sync_tsk); ++ wait_for_completion(&hp->synced); ++} ++ ++static void __cpu_unplug_wait(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ complete(&hp->unplug_wait); ++ wait_for_completion(&hp->synced); ++} ++ ++/* ++ * Start the sync_unplug_thread on the target cpu and wait for it to ++ * complete. ++ */ ++static int cpu_unplug_begin(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ int err; ++ ++ /* Protected by cpu_hotplug.lock */ ++ if (!hp->mutex_init) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ spin_lock_init(&hp->lock); ++#else ++ mutex_init(&hp->mutex); ++#endif ++ hp->mutex_init = 1; ++ } ++ ++ /* Inform the scheduler to migrate tasks off this CPU */ ++ tell_sched_cpu_down_begin(cpu); ++ ++ init_completion(&hp->synced); ++ init_completion(&hp->unplug_wait); ++ ++ hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu); ++ if (IS_ERR(hp->sync_tsk)) { ++ err = PTR_ERR(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++ return err; ++ } ++ kthread_bind(hp->sync_tsk, cpu); ++ ++ /* ++ * Wait for tasks to get out of the pinned sections, ++ * it's still OK if new tasks enter. Some CPU notifiers will ++ * wait for tasks that are going to enter these sections and ++ * we must not have them block. ++ */ ++ wake_up_process(hp->sync_tsk); ++ return 0; ++} ++ ++static void cpu_unplug_sync(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ init_completion(&hp->synced); ++ /* The completion needs to be initialzied before setting grab_lock */ ++ smp_wmb(); ++ ++ /* Grab the mutex before setting grab_lock */ ++ hotplug_lock(hp); ++ hp->grab_lock = 1; ++ ++ /* ++ * The CPU notifiers have been completed. ++ * Wait for tasks to get out of pinned CPU sections and have new ++ * tasks block until the CPU is completely down. ++ */ ++ __cpu_unplug_sync(hp); ++ ++ /* All done with the sync thread */ ++ kthread_stop(hp->sync_tsk); ++ hp->sync_tsk = NULL; ++} ++ ++static void cpu_unplug_done(unsigned int cpu) ++{ ++ struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu); ++ ++ hp->unplug = NULL; ++ /* Let all tasks know cpu unplug is finished before cleaning up */ ++ smp_wmb(); ++ ++ if (hp->sync_tsk) ++ kthread_stop(hp->sync_tsk); ++ ++ if (hp->grab_lock) { ++ hotplug_unlock(hp); ++ /* protected by cpu_hotplug.lock */ ++ hp->grab_lock = 0; ++ } ++ tell_sched_cpu_down_done(cpu); ++} + + void get_online_cpus(void) + { +@@ -338,13 +621,15 @@ + /* Requires cpu_add_remove_lock to be held */ + static int _cpu_down(unsigned int cpu, int tasks_frozen) + { +- int err, nr_calls = 0; ++ int mycpu, err, nr_calls = 0; + void *hcpu = (void *)(long)cpu; + unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; + struct take_cpu_down_param tcd_param = { + .mod = mod, + .hcpu = hcpu, + }; ++ cpumask_var_t cpumask; ++ cpumask_var_t cpumask_org; + + if (num_online_cpus() == 1) + return -EBUSY; +@@ -352,7 +637,34 @@ + if (!cpu_online(cpu)) + return -EINVAL; + ++ /* Move the downtaker off the unplug cpu */ ++ if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) ++ return -ENOMEM; ++ if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL)) { ++ free_cpumask_var(cpumask); ++ return -ENOMEM; ++ } ++ ++ cpumask_copy(cpumask_org, tsk_cpus_allowed(current)); ++ cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu)); ++ set_cpus_allowed_ptr(current, cpumask); ++ free_cpumask_var(cpumask); ++ migrate_disable(); ++ mycpu = smp_processor_id(); ++ if (mycpu == cpu) { ++ printk(KERN_ERR "Yuck! Still on unplug CPU\n!"); ++ migrate_enable(); ++ err = -EBUSY; ++ goto restore_cpus; ++ } ++ migrate_enable(); ++ + cpu_hotplug_begin(); ++ err = cpu_unplug_begin(cpu); ++ if (err) { ++ printk("cpu_unplug_begin(%d) failed\n", cpu); ++ goto out_cancel; ++ } + + err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); + if (err) { +@@ -378,8 +690,12 @@ + else + synchronize_rcu(); + ++ __cpu_unplug_wait(cpu); + smpboot_park_threads(cpu); + ++ /* Notifiers are done. Don't let any more tasks pin this CPU. */ ++ cpu_unplug_sync(cpu); ++ + /* + * Prevent irq alloc/free while the dying cpu reorganizes the + * interrupt affinities. +@@ -424,9 +740,14 @@ + check_for_tasks(cpu); + + out_release: ++ cpu_unplug_done(cpu); ++out_cancel: + cpu_hotplug_done(); + if (!err) + cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu); ++restore_cpus: ++ set_cpus_allowed_ptr(current, cpumask_org); ++ free_cpumask_var(cpumask_org); + return err; + } + +diff -Nur linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c linux-4.4.28/kernel/debug/kdb/kdb_io.c +--- linux-4.4.28.orig/kernel/debug/kdb/kdb_io.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/debug/kdb/kdb_io.c 2016-11-01 21:26:58.756340996 +0100 +@@ -554,7 +554,6 @@ + int linecount; + int colcount; + int logging, saved_loglevel = 0; +- int saved_trap_printk; + int got_printf_lock = 0; + int retlen = 0; + int fnd, len; +@@ -565,8 +564,6 @@ + unsigned long uninitialized_var(flags); + + preempt_disable(); +- saved_trap_printk = kdb_trap_printk; +- kdb_trap_printk = 0; + + /* Serialize kdb_printf if multiple cpus try to write at once. + * But if any cpu goes recursive in kdb, just print the output, +@@ -855,7 +852,6 @@ + } else { + __release(kdb_printf_lock); + } +- kdb_trap_printk = saved_trap_printk; + preempt_enable(); + return retlen; + } +@@ -865,9 +861,11 @@ + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } +diff -Nur linux-4.4.28.orig/kernel/events/core.c linux-4.4.28/kernel/events/core.c +--- linux-4.4.28.orig/kernel/events/core.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/events/core.c 2016-11-01 21:26:58.760341249 +0100 +@@ -802,6 +802,7 @@ + raw_spin_lock_init(&cpuctx->hrtimer_lock); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + timer->function = perf_mux_hrtimer_handler; ++ timer->irqsafe = 1; + } + + static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) +@@ -7240,6 +7241,7 @@ + + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hwc->hrtimer.function = perf_swevent_hrtimer; ++ hwc->hrtimer.irqsafe = 1; + + /* + * Since hrtimers have a fixed rate, we can do a static freq->period +diff -Nur linux-4.4.28.orig/kernel/exit.c linux-4.4.28/kernel/exit.c +--- linux-4.4.28.orig/kernel/exit.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/exit.c 2016-11-01 21:26:58.760341249 +0100 +@@ -144,7 +144,7 @@ + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ +- flush_sigqueue(&tsk->pending); ++ flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + +diff -Nur linux-4.4.28.orig/kernel/fork.c linux-4.4.28/kernel/fork.c +--- linux-4.4.28.orig/kernel/fork.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/fork.c 2016-11-01 21:26:58.764341506 +0100 +@@ -108,7 +108,7 @@ + + DEFINE_PER_CPU(unsigned long, process_counts) = 0; + +-__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ ++DEFINE_RWLOCK(tasklist_lock); /* outer */ + + #ifdef CONFIG_PROVE_RCU + int lockdep_tasklist_lock_is_held(void) +@@ -244,7 +244,9 @@ + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++static ++#endif + void __put_task_struct(struct task_struct *tsk) + { + WARN_ON(!tsk->exit_state); +@@ -261,7 +263,18 @@ + if (!profile_handoff_task(tsk)) + free_task(tsk); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + EXPORT_SYMBOL_GPL(__put_task_struct); ++#else ++void __put_task_struct_cb(struct rcu_head *rhp) ++{ ++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); ++ ++ __put_task_struct(tsk); ++ ++} ++EXPORT_SYMBOL_GPL(__put_task_struct_cb); ++#endif + + void __init __weak arch_task_cache_init(void) { } + +@@ -689,6 +702,19 @@ + } + EXPORT_SYMBOL_GPL(__mmdrop); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++/* ++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't ++ * want another facility to make this work. ++ */ ++void __mmdrop_delayed(struct rcu_head *rhp) ++{ ++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); ++ ++ __mmdrop(mm); ++} ++#endif ++ + /* + * Decrement the use count and release all resources for an mm. + */ +@@ -1239,6 +1265,9 @@ + */ + static void posix_cpu_timers_init(struct task_struct *tsk) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ tsk->posix_timer_list = NULL; ++#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; +@@ -1364,15 +1393,16 @@ + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); ++ p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + p->utimescaled = p->stimescaled = 0; + prev_cputime_init(&p->prev_cputime); + + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +- seqlock_init(&p->vtime_seqlock); ++ seqcount_init(&p->vtime_seqcount); + p->vtime_snap = 0; +- p->vtime_snap_whence = VTIME_SLEEPING; ++ p->vtime_snap_whence = VTIME_INACTIVE; + #endif + + #if defined(SPLIT_RSS_COUNTING) +diff -Nur linux-4.4.28.orig/kernel/futex.c linux-4.4.28/kernel/futex.c +--- linux-4.4.28.orig/kernel/futex.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/futex.c 2016-11-01 21:26:58.764341506 +0100 +@@ -815,7 +815,9 @@ + * task still owns the PI-state: + */ + if (head->next != next) { ++ raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); + continue; + } + +@@ -1210,6 +1212,7 @@ + struct futex_pi_state *pi_state = this->pi_state; + u32 uninitialized_var(curval), newval; + WAKE_Q(wake_q); ++ WAKE_Q(wake_sleeper_q); + bool deboost; + int ret = 0; + +@@ -1223,7 +1226,7 @@ + if (pi_state->owner != current) + return -EINVAL; + +- raw_spin_lock(&pi_state->pi_mutex.wait_lock); ++ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); + + /* +@@ -1259,24 +1262,25 @@ + ret = -EINVAL; + } + if (ret) { +- raw_spin_unlock(&pi_state->pi_mutex.wait_lock); ++ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + return ret; + } + +- raw_spin_lock_irq(&pi_state->owner->pi_lock); ++ raw_spin_lock(&pi_state->owner->pi_lock); + WARN_ON(list_empty(&pi_state->list)); + list_del_init(&pi_state->list); +- raw_spin_unlock_irq(&pi_state->owner->pi_lock); ++ raw_spin_unlock(&pi_state->owner->pi_lock); + +- raw_spin_lock_irq(&new_owner->pi_lock); ++ raw_spin_lock(&new_owner->pi_lock); + WARN_ON(!list_empty(&pi_state->list)); + list_add(&pi_state->list, &new_owner->pi_state_list); + pi_state->owner = new_owner; +- raw_spin_unlock_irq(&new_owner->pi_lock); ++ raw_spin_unlock(&new_owner->pi_lock); + +- raw_spin_unlock(&pi_state->pi_mutex.wait_lock); ++ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + +- deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); ++ deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, ++ &wake_sleeper_q); + + /* + * First unlock HB so the waiter does not spin on it once he got woken +@@ -1284,8 +1288,9 @@ + * deboost first (and lose our higher priority), then the task might get + * scheduled away before the wake up can take place. + */ +- spin_unlock(&hb->lock); ++ deboost |= spin_unlock_no_deboost(&hb->lock); + wake_up_q(&wake_q); ++ wake_up_q_sleeper(&wake_sleeper_q); + if (deboost) + rt_mutex_adjust_prio(current); + +@@ -1822,6 +1827,16 @@ + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ free_pi_state(pi_state); ++ continue; + } else if (ret) { + /* -EDEADLK */ + this->pi_state = NULL; +@@ -2139,11 +2154,11 @@ + * we returned due to timeout or signal without taking the + * rt_mutex. Too late. + */ +- raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); ++ raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); + owner = rt_mutex_owner(&q->pi_state->pi_mutex); + if (!owner) + owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); +- raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); ++ raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); + ret = fixup_pi_state_owner(uaddr, q, owner); + goto out; + } +@@ -2691,7 +2706,7 @@ + struct hrtimer_sleeper timeout, *to = NULL; + struct rt_mutex_waiter rt_waiter; + struct rt_mutex *pi_mutex = NULL; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -2716,10 +2731,7 @@ + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- debug_rt_mutex_init_waiter(&rt_waiter); +- RB_CLEAR_NODE(&rt_waiter.pi_tree_entry); +- RB_CLEAR_NODE(&rt_waiter.tree_entry); +- rt_waiter.task = NULL; ++ rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) +@@ -2750,20 +2762,55 @@ + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -2772,14 +2819,15 @@ + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + free_pi_state(q.pi_state); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + } + } else { + /* +@@ -2792,7 +2840,8 @@ + ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter); + debug_rt_mutex_free_waiter(&rt_waiter); + +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + /* + * Fixup the pi_state owner and possibly acquire the lock if we + * haven't already. +diff -Nur linux-4.4.28.orig/kernel/irq/handle.c linux-4.4.28/kernel/irq/handle.c +--- linux-4.4.28.orig/kernel/irq/handle.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq/handle.c 2016-11-01 21:26:58.764341506 +0100 +@@ -134,6 +134,8 @@ + + irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) + { ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + irqreturn_t retval = IRQ_NONE; + unsigned int flags = 0, irq = desc->irq_data.irq; + struct irqaction *action = desc->action; +@@ -176,7 +178,11 @@ + action = action->next; + } + +- add_interrupt_randomness(irq, flags); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ desc->random_ip = ip; ++#else ++ add_interrupt_randomness(irq, flags, ip); ++#endif + + if (!noirqdebug) + note_interrupt(desc, retval); +diff -Nur linux-4.4.28.orig/kernel/irq/irqdesc.c linux-4.4.28/kernel/irq/irqdesc.c +--- linux-4.4.28.orig/kernel/irq/irqdesc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq/irqdesc.c 2016-11-01 21:26:58.764341506 +0100 +@@ -24,10 +24,27 @@ + static struct lock_class_key irq_desc_lock_class; + + #if defined(CONFIG_SMP) ++static int __init irq_affinity_setup(char *str) ++{ ++ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); ++ cpulist_parse(str, irq_default_affinity); ++ /* ++ * Set at least the boot cpu. We don't want to end up with ++ * bugreports caused by random comandline masks ++ */ ++ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); ++ return 1; ++} ++__setup("irqaffinity=", irq_affinity_setup); ++ + static void __init init_irq_default_affinity(void) + { +- alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); +- cpumask_setall(irq_default_affinity); ++#ifdef CONFIG_CPUMASK_OFFSTACK ++ if (!irq_default_affinity) ++ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); ++#endif ++ if (cpumask_empty(irq_default_affinity)) ++ cpumask_setall(irq_default_affinity); + } + #else + static void __init init_irq_default_affinity(void) +diff -Nur linux-4.4.28.orig/kernel/irq/manage.c linux-4.4.28/kernel/irq/manage.c +--- linux-4.4.28.orig/kernel/irq/manage.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq/manage.c 2016-11-01 21:26:58.764341506 +0100 +@@ -22,6 +22,7 @@ + #include "internals.h" + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + __read_mostly bool force_irqthreads; + + static int __init setup_forced_irqthreads(char *arg) +@@ -30,6 +31,7 @@ + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + static void __synchronize_hardirq(struct irq_desc *desc) +@@ -181,6 +183,62 @@ + irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void _irq_affinity_notify(struct irq_affinity_notify *notify); ++static struct task_struct *set_affinity_helper; ++static LIST_HEAD(affinity_list); ++static DEFINE_RAW_SPINLOCK(affinity_list_lock); ++ ++static int set_affinity_thread(void *unused) ++{ ++ while (1) { ++ struct irq_affinity_notify *notify; ++ int empty; ++ ++ set_current_state(TASK_INTERRUPTIBLE); ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ empty = list_empty(&affinity_list); ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (empty) ++ schedule(); ++ if (kthread_should_stop()) ++ break; ++ set_current_state(TASK_RUNNING); ++try_next: ++ notify = NULL; ++ ++ raw_spin_lock_irq(&affinity_list_lock); ++ if (!list_empty(&affinity_list)) { ++ notify = list_first_entry(&affinity_list, ++ struct irq_affinity_notify, list); ++ list_del_init(¬ify->list); ++ } ++ raw_spin_unlock_irq(&affinity_list_lock); ++ ++ if (!notify) ++ continue; ++ _irq_affinity_notify(notify); ++ goto try_next; ++ } ++ return 0; ++} ++ ++static void init_helper_thread(void) ++{ ++ if (set_affinity_helper) ++ return; ++ set_affinity_helper = kthread_run(set_affinity_thread, NULL, ++ "affinity-cb"); ++ WARN_ON(IS_ERR(set_affinity_helper)); ++} ++#else ++ ++static inline void init_helper_thread(void) { } ++ ++#endif ++ + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) + { +@@ -220,7 +278,17 @@ + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_lock(&affinity_list_lock); ++ if (list_empty(&desc->affinity_notify->list)) ++ list_add_tail(&affinity_list, ++ &desc->affinity_notify->list); ++ raw_spin_unlock(&affinity_list_lock); ++ wake_up_process(set_affinity_helper); ++#else + schedule_work(&desc->affinity_notify->work); ++#endif + } + irqd_set(data, IRQD_AFFINITY_SET); + +@@ -258,10 +326,8 @@ + } + EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +-static void irq_affinity_notify(struct work_struct *work) ++static void _irq_affinity_notify(struct irq_affinity_notify *notify) + { +- struct irq_affinity_notify *notify = +- container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; +@@ -283,6 +349,13 @@ + kref_put(¬ify->kref, notify->release); + } + ++static void irq_affinity_notify(struct work_struct *work) ++{ ++ struct irq_affinity_notify *notify = ++ container_of(work, struct irq_affinity_notify, work); ++ _irq_affinity_notify(notify); ++} ++ + /** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification +@@ -312,6 +385,8 @@ + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); ++ INIT_LIST_HEAD(¬ify->list); ++ init_helper_thread(); + } + + raw_spin_lock_irqsave(&desc->lock, flags); +@@ -865,7 +940,15 @@ + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); +- local_bh_enable(); ++ /* ++ * Interrupts which have real time requirements can be set up ++ * to avoid softirq processing in the thread handler. This is ++ * safe as these interrupts do not raise soft interrupts. ++ */ ++ if (irq_settings_no_softirq_call(desc)) ++ _local_bh_enable(); ++ else ++ local_bh_enable(); + return ret; + } + +@@ -962,6 +1045,12 @@ + if (action_ret == IRQ_WAKE_THREAD) + irq_wake_secondary(desc, action); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ migrate_disable(); ++ add_interrupt_randomness(action->irq, 0, ++ desc->random_ip ^ (unsigned long) action); ++ migrate_enable(); ++#endif + wake_threads_waitq(desc); + } + +@@ -1315,6 +1404,9 @@ + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + ++ if (new->flags & IRQF_NO_SOFTIRQ_CALL) ++ irq_settings_set_no_softirq_call(desc); ++ + /* Set default affinity mask once everything is setup */ + setup_affinity(desc, mask); + +@@ -1968,7 +2060,7 @@ + * This call sets the internal irqchip state of an interrupt, + * depending on the value of @which. + * +- * This function should be called with preemption disabled if the ++ * This function should be called with migration disabled if the + * interrupt controller has per-cpu registers. + */ + int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, +diff -Nur linux-4.4.28.orig/kernel/irq/settings.h linux-4.4.28/kernel/irq/settings.h +--- linux-4.4.28.orig/kernel/irq/settings.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq/settings.h 2016-11-01 21:26:58.764341506 +0100 +@@ -16,6 +16,7 @@ + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -30,6 +31,7 @@ + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON + #define IRQ_IS_POLLED GOT_YOU_MORON + #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -40,6 +42,16 @@ + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); + } + ++static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) ++{ ++ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; ++} ++ ++static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) ++{ ++ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; ++} ++ + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) + { + return desc->status_use_accessors & _IRQ_PER_CPU; +diff -Nur linux-4.4.28.orig/kernel/irq/spurious.c linux-4.4.28/kernel/irq/spurious.c +--- linux-4.4.28.orig/kernel/irq/spurious.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq/spurious.c 2016-11-01 21:26:58.764341506 +0100 +@@ -444,6 +444,10 @@ + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -456,6 +460,10 @@ + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); +diff -Nur linux-4.4.28.orig/kernel/irq_work.c linux-4.4.28/kernel/irq_work.c +--- linux-4.4.28.orig/kernel/irq_work.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/irq_work.c 2016-11-01 21:26:58.768341770 +0100 +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + + +@@ -65,6 +66,8 @@ + */ + bool irq_work_queue_on(struct irq_work *work, int cpu) + { ++ struct llist_head *list; ++ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + +@@ -75,7 +78,12 @@ + if (!irq_work_claim(work)) + return false; + +- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ list = &per_cpu(lazy_list, cpu); ++ else ++ list = &per_cpu(raised_list, cpu); ++ ++ if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + + return true; +@@ -86,6 +94,9 @@ + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { ++ struct llist_head *list; ++ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++ + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; +@@ -93,13 +104,15 @@ + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + +- /* If the work is "lazy", handle it from next tick if any */ +- if (work->flags & IRQ_WORK_LAZY) { +- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && +- tick_nohz_tick_stopped()) +- arch_irq_work_raise(); +- } else { +- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) ++ lazy_work = work->flags & IRQ_WORK_LAZY; ++ ++ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ list = this_cpu_ptr(&lazy_list); ++ else ++ list = this_cpu_ptr(&raised_list); ++ ++ if (llist_add(&work->llnode, list)) { ++ if (!lazy_work || tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } + +@@ -116,9 +129,8 @@ + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + +- if (llist_empty(raised) || arch_irq_work_has_interrupt()) +- if (llist_empty(lazy)) +- return false; ++ if (llist_empty(raised) && llist_empty(lazy)) ++ return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); +@@ -132,7 +144,7 @@ + struct irq_work *work; + struct llist_node *llnode; + +- BUG_ON(!irqs_disabled()); ++ BUG_ON_NONRT(!irqs_disabled()); + + if (llist_empty(list)) + return; +@@ -169,7 +181,16 @@ + void irq_work_run(void) + { + irq_work_run_list(this_cpu_ptr(&raised_list)); +- irq_work_run_list(this_cpu_ptr(&lazy_list)); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { ++ /* ++ * NOTE: we raise softirq via IPI for safety, ++ * and execute in irq_work_tick() to move the ++ * overhead from hard to soft irq context. ++ */ ++ if (!llist_empty(this_cpu_ptr(&lazy_list))) ++ raise_softirq(TIMER_SOFTIRQ); ++ } else ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); + } + EXPORT_SYMBOL_GPL(irq_work_run); + +@@ -179,8 +200,17 @@ + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); ++ ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); ++} ++ ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void) ++{ + irq_work_run_list(this_cpu_ptr(&lazy_list)); + } ++#endif + + /* + * Synchronize against the irq_work @entry, ensures the entry is not +diff -Nur linux-4.4.28.orig/kernel/Kconfig.locks linux-4.4.28/kernel/Kconfig.locks +--- linux-4.4.28.orig/kernel/Kconfig.locks 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/Kconfig.locks 2016-11-01 21:26:58.756340996 +0100 +@@ -225,11 +225,11 @@ + + config MUTEX_SPIN_ON_OWNER + def_bool y +- depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config RWSEM_SPIN_ON_OWNER + def_bool y +- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config LOCK_SPIN_ON_OWNER + def_bool y +diff -Nur linux-4.4.28.orig/kernel/Kconfig.preempt linux-4.4.28/kernel/Kconfig.preempt +--- linux-4.4.28.orig/kernel/Kconfig.preempt 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/Kconfig.preempt 2016-11-01 21:26:58.756340996 +0100 +@@ -1,3 +1,16 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT ++ ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL + + choice + prompt "Preemption Model" +@@ -33,9 +46,9 @@ + + Select this if you are building a kernel for a desktop system. + +-config PREEMPT ++config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" +- select PREEMPT_COUNT ++ select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making +@@ -52,6 +65,22 @@ + embedded system with latency requirements in the milliseconds + range. + ++config PREEMPT_RTB ++ bool "Preemptible Kernel (Basic RT)" ++ select PREEMPT_RT_BASE ++ help ++ This option is basically the same as (Low-Latency Desktop) but ++ enables changes which are preliminary for the full preemptible ++ RT kernel. ++ ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ select PREEMPT_RCU ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +diff -Nur linux-4.4.28.orig/kernel/ksysfs.c linux-4.4.28/kernel/ksysfs.c +--- linux-4.4.28.orig/kernel/ksysfs.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/ksysfs.c 2016-11-01 21:26:58.768341770 +0100 +@@ -136,6 +136,15 @@ + + #endif /* CONFIG_KEXEC_CORE */ + ++#if defined(CONFIG_PREEMPT_RT_FULL) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -203,6 +212,9 @@ + &vmcoreinfo_attr.attr, + #endif + &rcu_expedited_attr.attr, ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, ++#endif + NULL + }; + +diff -Nur linux-4.4.28.orig/kernel/locking/lglock.c linux-4.4.28/kernel/locking/lglock.c +--- linux-4.4.28.orig/kernel/locking/lglock.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/lglock.c 2016-11-01 21:26:58.768341770 +0100 +@@ -4,6 +4,15 @@ + #include + #include + ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define lg_lock_ptr arch_spinlock_t ++# define lg_do_lock(l) arch_spin_lock(l) ++# define lg_do_unlock(l) arch_spin_unlock(l) ++#else ++# define lg_lock_ptr struct rt_mutex ++# define lg_do_lock(l) __rt_spin_lock__no_mg(l) ++# define lg_do_unlock(l) __rt_spin_unlock(l) ++#endif + /* + * Note there is no uninit, so lglocks cannot be defined in + * modules (but it's fine to use them from there) +@@ -12,51 +21,60 @@ + + void lg_lock_init(struct lglock *lg, char *name) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int i; ++ ++ for_each_possible_cpu(i) { ++ struct rt_mutex *lock = per_cpu_ptr(lg->lock, i); ++ ++ rt_mutex_init(lock); ++ } ++#endif + LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); + } + EXPORT_SYMBOL(lg_lock_init); + + void lg_local_lock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ migrate_disable(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock); + + void lg_local_unlock(struct lglock *lg) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = this_cpu_ptr(lg->lock); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ migrate_enable(); + } + EXPORT_SYMBOL(lg_local_unlock); + + void lg_local_lock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + EXPORT_SYMBOL(lg_local_lock_cpu); + + void lg_local_unlock_cpu(struct lglock *lg, int cpu) + { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + lock = per_cpu_ptr(lg->lock, cpu); +- arch_spin_unlock(lock); +- preempt_enable(); ++ lg_do_unlock(lock); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_local_unlock_cpu); + +@@ -68,30 +86,30 @@ + if (cpu2 < cpu1) + swap(cpu1, cpu2); + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); +- arch_spin_lock(per_cpu_ptr(lg->lock, cpu1)); +- arch_spin_lock(per_cpu_ptr(lg->lock, cpu2)); ++ lg_do_lock(per_cpu_ptr(lg->lock, cpu1)); ++ lg_do_lock(per_cpu_ptr(lg->lock, cpu2)); + } + + void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2) + { + lock_release(&lg->lock_dep_map, 1, _RET_IP_); +- arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1)); +- arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2)); +- preempt_enable(); ++ lg_do_unlock(per_cpu_ptr(lg->lock, cpu1)); ++ lg_do_unlock(per_cpu_ptr(lg->lock, cpu2)); ++ preempt_enable_nort(); + } + + void lg_global_lock(struct lglock *lg) + { + int i; + +- preempt_disable(); ++ preempt_disable_nort(); + lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_lock(lock); ++ lg_do_lock(lock); + } + } + EXPORT_SYMBOL(lg_global_lock); +@@ -102,10 +120,35 @@ + + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + for_each_possible_cpu(i) { +- arch_spinlock_t *lock; ++ lg_lock_ptr *lock; + lock = per_cpu_ptr(lg->lock, i); +- arch_spin_unlock(lock); ++ lg_do_unlock(lock); + } +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(lg_global_unlock); ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * HACK: If you use this, you get to keep the pieces. ++ * Used in queue_stop_cpus_work() when stop machinery ++ * is called from inactive CPU, so we can't schedule. ++ */ ++# define lg_do_trylock_relax(l) \ ++ do { \ ++ while (!__rt_spin_trylock(l)) \ ++ cpu_relax(); \ ++ } while (0) ++ ++void lg_global_trylock_relax(struct lglock *lg) ++{ ++ int i; ++ ++ lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); ++ for_each_possible_cpu(i) { ++ lg_lock_ptr *lock; ++ lock = per_cpu_ptr(lg->lock, i); ++ lg_do_trylock_relax(lock); ++ } ++} ++#endif +diff -Nur linux-4.4.28.orig/kernel/locking/lockdep.c linux-4.4.28/kernel/locking/lockdep.c +--- linux-4.4.28.orig/kernel/locking/lockdep.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/lockdep.c 2016-11-01 21:26:58.768341770 +0100 +@@ -3525,6 +3525,7 @@ + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3539,6 +3540,7 @@ + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); +diff -Nur linux-4.4.28.orig/kernel/locking/locktorture.c linux-4.4.28/kernel/locking/locktorture.c +--- linux-4.4.28.orig/kernel/locking/locktorture.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/locktorture.c 2016-11-01 21:26:58.768341770 +0100 +@@ -26,7 +26,6 @@ + #include + #include + #include +-#include + #include + #include + #include +diff -Nur linux-4.4.28.orig/kernel/locking/Makefile linux-4.4.28/kernel/locking/Makefile +--- linux-4.4.28.orig/kernel/locking/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/Makefile 2016-11-01 21:26:58.768341770 +0100 +@@ -1,5 +1,5 @@ + +-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o ++obj-y += semaphore.o percpu-rwsem.o + + ifdef CONFIG_FUNCTION_TRACER + CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +@@ -8,7 +8,11 @@ + CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) + endif + ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) ++obj-y += mutex.o + obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o ++obj-y += rwsem.o ++endif + obj-$(CONFIG_LOCKDEP) += lockdep.o + ifeq ($(CONFIG_PROC_FS),y) + obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +@@ -22,7 +26,10 @@ + obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o ++endif ++obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o + obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o + obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o +diff -Nur linux-4.4.28.orig/kernel/locking/rt.c linux-4.4.28/kernel/locking/rt.c +--- linux-4.4.28.orig/kernel/locking/rt.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/kernel/locking/rt.c 2016-11-01 21:26:58.768341770 +0100 +@@ -0,0 +1,474 @@ ++/* ++ * kernel/rt.c ++ * ++ * Real-Time Preemption Support ++ * ++ * started by Ingo Molnar: ++ * ++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * ++ * historic credit for proving that Linux spinlocks can be implemented via ++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow ++ * and others) who prototyped it on 2.4 and did lots of comparative ++ * research and analysis; TimeSys, for proving that you can implement a ++ * fully preemptible kernel via the use of IRQ threading and mutexes; ++ * Bill Huey for persuasively arguing on lkml that the mutex model is the ++ * right one; and to MontaVista, who ported pmutexes to 2.6. ++ * ++ * This code is a from-scratch implementation and is not based on pmutexes, ++ * but the idea of converting spinlocks to mutexes is used here too. ++ * ++ * lock debugging, locking tree, deadlock detection: ++ * ++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey ++ * Released under the General Public License (GPL). ++ * ++ * Includes portions of the generic R/W semaphore implementation from: ++ * ++ * Copyright (c) 2001 David Howells (dhowells@redhat.com). ++ * - Derived partially from idea by Andrea Arcangeli ++ * - Derived also from comments by Linus ++ * ++ * Pending ownership of locks and ownership stealing: ++ * ++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt ++ * ++ * (also by Steven Rostedt) ++ * - Converted single pi_lock to individual task locks. ++ * ++ * By Esben Nielsen: ++ * Doing priority inheritance with help of the scheduler. ++ * ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * - major rework based on Esben Nielsens initial patch ++ * - replaced thread_info references by task_struct refs ++ * - removed task->pending_owner dependency ++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks ++ * in the scheduler return path as discussed with Steven Rostedt ++ * ++ * Copyright (C) 2006, Kihon Technologies Inc. ++ * Steven Rostedt ++ * - debugged and patched Thomas Gleixner's rework. ++ * - added back the cmpxchg to the rework. ++ * - turned atomic require back on for SMP. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "rtmutex_common.h" ++ ++/* ++ * struct mutex functions ++ */ ++void __mutex_do_init(struct mutex *mutex, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); ++ lockdep_init_map(&mutex->dep_map, name, key, 0); ++#endif ++ mutex->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__mutex_do_init); ++ ++void __lockfunc _mutex_lock(struct mutex *lock) ++{ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock); ++ ++int __lockfunc _mutex_lock_interruptible(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible); ++ ++int __lockfunc _mutex_lock_killable(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) ++{ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nested); ++ ++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) ++{ ++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_lock_nest_lock); ++ ++int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ ret = rt_mutex_lock_interruptible(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible_nested); ++ ++int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ ret = rt_mutex_lock_killable(&lock->lock); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable_nested); ++#endif ++ ++int __lockfunc _mutex_trylock(struct mutex *lock) ++{ ++ int ret = rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_trylock); ++ ++void __lockfunc _mutex_unlock(struct mutex *lock) ++{ ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_unlock); ++ ++/* ++ * rwlock_t functions ++ */ ++int __lockfunc rt_write_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = rt_mutex_trylock(&rwlock->lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock); ++ ++int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = rt_write_trylock(rwlock); ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock_irqsave); ++ ++int __lockfunc rt_read_trylock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the lock, ++ * but not when read_depth == 0 which means that the lock is ++ * write locked. ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ migrate_disable(); ++ ret = rt_mutex_trylock(lock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ ++ } else if (!rwlock->read_depth) { ++ ret = 0; ++ } ++ ++ if (ret) ++ rwlock->read_depth++; ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ __rt_spin_lock(&rwlock->lock); ++} ++EXPORT_SYMBOL(rt_write_lock); ++ ++void __lockfunc rt_read_lock(rwlock_t *rwlock) ++{ ++ struct rt_mutex *lock = &rwlock->lock; ++ ++ ++ /* ++ * recursive read locks succeed when current owns the lock ++ */ ++ if (rt_mutex_owner(lock) != current) { ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ __rt_spin_lock(lock); ++ } ++ rwlock->read_depth++; ++} ++ ++EXPORT_SYMBOL(rt_read_lock); ++ ++void __lockfunc rt_write_unlock(rwlock_t *rwlock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_write_unlock); ++ ++void __lockfunc rt_read_unlock(rwlock_t *rwlock) ++{ ++ /* Release the lock only when read_depth is down to 0 */ ++ if (--rwlock->read_depth == 0) { ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ __rt_spin_unlock(&rwlock->lock); ++ migrate_enable(); ++ } ++} ++EXPORT_SYMBOL(rt_read_unlock); ++ ++unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_write_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_write_lock_irqsave); ++ ++unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock) ++{ ++ rt_read_lock(rwlock); ++ ++ return 0; ++} ++EXPORT_SYMBOL(rt_read_lock_irqsave); ++ ++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock)); ++ lockdep_init_map(&rwlock->dep_map, name, key, 0); ++#endif ++ rwlock->lock.save_state = 1; ++ rwlock->read_depth = 0; ++} ++EXPORT_SYMBOL(__rt_rwlock_init); ++ ++/* ++ * rw_semaphores ++ */ ++ ++void rt_up_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ rt_mutex_unlock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_up_write); ++ ++void __rt_up_read(struct rw_semaphore *rwsem) ++{ ++ if (--rwsem->read_depth == 0) ++ rt_mutex_unlock(&rwsem->lock); ++} ++ ++void rt_up_read(struct rw_semaphore *rwsem) ++{ ++ rwsem_release(&rwsem->dep_map, 1, _RET_IP_); ++ __rt_up_read(rwsem); ++} ++EXPORT_SYMBOL(rt_up_read); ++ ++/* ++ * downgrade a write lock into a read lock ++ * - just wake up any readers at the front of the queue ++ */ ++void rt_downgrade_write(struct rw_semaphore *rwsem) ++{ ++ BUG_ON(rt_mutex_owner(&rwsem->lock) != current); ++ rwsem->read_depth = 1; ++} ++EXPORT_SYMBOL(rt_downgrade_write); ++ ++int rt_down_write_trylock(struct rw_semaphore *rwsem) ++{ ++ int ret = rt_mutex_trylock(&rwsem->lock); ++ ++ if (ret) ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_write_trylock); ++ ++void rt_down_write(struct rw_semaphore *rwsem) ++{ ++ rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write); ++ ++void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested); ++ ++void rt_down_write_nested_lock(struct rw_semaphore *rwsem, ++ struct lockdep_map *nest) ++{ ++ rwsem_acquire_nest(&rwsem->dep_map, 0, 0, nest, _RET_IP_); ++ rt_mutex_lock(&rwsem->lock); ++} ++EXPORT_SYMBOL(rt_down_write_nested_lock); ++ ++int rt__down_read_trylock(struct rw_semaphore *rwsem) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ int ret = 1; ++ ++ /* ++ * recursive read locks succeed when current owns the rwsem, ++ * but not when read_depth == 0 which means that the rwsem is ++ * write locked. ++ */ ++ if (rt_mutex_owner(lock) != current) ++ ret = rt_mutex_trylock(&rwsem->lock); ++ else if (!rwsem->read_depth) ++ ret = 0; ++ ++ if (ret) ++ rwsem->read_depth++; ++ return ret; ++ ++} ++ ++int rt_down_read_trylock(struct rw_semaphore *rwsem) ++{ ++ int ret; ++ ++ ret = rt__down_read_trylock(rwsem); ++ if (ret) ++ rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(rt_down_read_trylock); ++ ++void rt__down_read(struct rw_semaphore *rwsem) ++{ ++ struct rt_mutex *lock = &rwsem->lock; ++ ++ if (rt_mutex_owner(lock) != current) ++ rt_mutex_lock(&rwsem->lock); ++ rwsem->read_depth++; ++} ++EXPORT_SYMBOL(rt__down_read); ++ ++static void __rt_down_read(struct rw_semaphore *rwsem, int subclass) ++{ ++ rwsem_acquire_read(&rwsem->dep_map, subclass, 0, _RET_IP_); ++ rt__down_read(rwsem); ++} ++ ++void rt_down_read(struct rw_semaphore *rwsem) ++{ ++ __rt_down_read(rwsem, 0); ++} ++EXPORT_SYMBOL(rt_down_read); ++ ++void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass) ++{ ++ __rt_down_read(rwsem, subclass); ++} ++EXPORT_SYMBOL(rt_down_read_nested); ++ ++void __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem)); ++ lockdep_init_map(&rwsem->dep_map, name, key, 0); ++#endif ++ rwsem->read_depth = 0; ++ rwsem->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__rt_rwsem_init); ++ ++/** ++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 ++ * @cnt: the atomic which we are to dec ++ * @lock: the mutex to return holding if we dec to 0 ++ * ++ * return true and hold lock if we dec to 0, return false otherwise ++ */ ++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) ++{ ++ /* dec if we can't possibly hit 0 */ ++ if (atomic_add_unless(cnt, -1, 1)) ++ return 0; ++ /* we might hit 0, so take the lock */ ++ mutex_lock(lock); ++ if (!atomic_dec_and_test(cnt)) { ++ /* when we actually did the dec, we didn't hit 0 */ ++ mutex_unlock(lock); ++ return 0; ++ } ++ /* we hit 0, and we hold the lock */ ++ return 1; ++} ++EXPORT_SYMBOL(atomic_dec_and_mutex_lock); +diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex.c linux-4.4.28/kernel/locking/rtmutex.c +--- linux-4.4.28.orig/kernel/locking/rtmutex.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/rtmutex.c 2016-11-01 21:26:58.772342023 +0100 +@@ -7,6 +7,11 @@ + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen ++ * Adaptive Spinlocks: ++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, ++ * and Peter Morreale, ++ * Adaptive Spinlocks simplification: ++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt + * + * See Documentation/locking/rt-mutex-design.txt for details. + */ +@@ -16,6 +21,7 @@ + #include + #include + #include ++#include + + #include "rtmutex_common.h" + +@@ -69,6 +75,12 @@ + clear_rt_mutex_waiters(lock); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if there's no debugging state to be + * set up. +@@ -99,13 +111,14 @@ + * 2) Drop lock->wait_lock + * 3) Try to unlock the lock with cmpxchg + */ +-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) ++static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, ++ unsigned long flags) + __releases(lock->wait_lock) + { + struct task_struct *owner = rt_mutex_owner(lock); + + clear_rt_mutex_waiters(lock); +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + /* + * If a new waiter comes in between the unlock and the cmpxchg + * we have two situations: +@@ -147,11 +160,12 @@ + /* + * Simple slow path only version: lock->owner is protected by lock->wait_lock. + */ +-static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) ++static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, ++ unsigned long flags) + __releases(lock->wait_lock) + { + lock->owner = NULL; +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + return true; + } + #endif +@@ -348,6 +362,14 @@ + return debug_rt_mutex_detect_deadlock(waiter, chwalk); + } + ++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) ++{ ++ if (waiter->savestate) ++ wake_up_lock_sleeper(waiter->task); ++ else ++ wake_up_process(waiter->task); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -355,7 +377,8 @@ + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -433,7 +456,6 @@ + int ret = 0, depth = 0; + struct rt_mutex *lock; + bool detect_deadlock; +- unsigned long flags; + bool requeue = true; + + detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); +@@ -476,7 +498,7 @@ + /* + * [1] Task cannot go away as we did a get_task() before ! + */ +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ raw_spin_lock_irq(&task->pi_lock); + + /* + * [2] Get the waiter on which @task is blocked on. +@@ -492,7 +514,7 @@ + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -560,7 +582,7 @@ + * operations. + */ + if (!raw_spin_trylock(&lock->wait_lock)) { +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock_irq(&task->pi_lock); + cpu_relax(); + goto retry; + } +@@ -591,7 +613,7 @@ + /* + * No requeue[7] here. Just release @task [8] + */ +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock(&task->pi_lock); + put_task_struct(task); + + /* +@@ -599,14 +621,14 @@ + * If there is no owner of the lock, end of chain. + */ + if (!rt_mutex_owner(lock)) { +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + return 0; + } + + /* [10] Grab the next task, i.e. owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ raw_spin_lock(&task->pi_lock); + + /* + * No requeue [11] here. We just do deadlock detection. +@@ -621,8 +643,8 @@ + top_waiter = rt_mutex_top_waiter(lock); + + /* [13] Drop locks */ +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock(&task->pi_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + /* If owner is not blocked, end of chain. */ + if (!next_lock) +@@ -643,7 +665,7 @@ + rt_mutex_enqueue(lock, waiter); + + /* [8] Release the task */ +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock(&task->pi_lock); + put_task_struct(task); + + /* +@@ -654,21 +676,24 @@ + * follow here. This is the end of the chain we are walking. + */ + if (!rt_mutex_owner(lock)) { ++ struct rt_mutex_waiter *lock_top_waiter; ++ + /* + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ +- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) +- wake_up_process(rt_mutex_top_waiter(lock)->task); +- raw_spin_unlock(&lock->wait_lock); ++ lock_top_waiter = rt_mutex_top_waiter(lock); ++ if (prerequeue_top_waiter != lock_top_waiter) ++ rt_mutex_wake_waiter(lock_top_waiter); ++ raw_spin_unlock_irq(&lock->wait_lock); + return 0; + } + + /* [10] Grab the next task, i.e. the owner of @lock */ + task = rt_mutex_owner(lock); + get_task_struct(task); +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ raw_spin_lock(&task->pi_lock); + + /* [11] requeue the pi waiters if necessary */ + if (waiter == rt_mutex_top_waiter(lock)) { +@@ -722,8 +747,8 @@ + top_waiter = rt_mutex_top_waiter(lock); + + /* [13] Drop the locks */ +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock(&task->pi_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + /* + * Make the actual exit decisions [12], based on the stored +@@ -746,28 +771,46 @@ + goto again; + + out_unlock_pi: +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock_irq(&task->pi_lock); + out_put_task: + put_task_struct(task); + + return ret; + } + ++ ++#define STEAL_NORMAL 0 ++#define STEAL_LATERAL 1 ++ ++/* ++ * Note that RT tasks are excluded from lateral-steals to prevent the ++ * introduction of an unbounded latency ++ */ ++static inline int lock_is_stealable(struct task_struct *task, ++ struct task_struct *pendowner, int mode) ++{ ++ if (mode == STEAL_NORMAL || rt_task(task)) { ++ if (task->prio >= pendowner->prio) ++ return 0; ++ } else if (task->prio > pendowner->prio) ++ return 0; ++ return 1; ++} ++ + /* + * Try to take an rt-mutex + * +- * Must be called with lock->wait_lock held. ++ * Must be called with lock->wait_lock held and interrupts disabled + * + * @lock: The lock to be acquired. + * @task: The task which wants to acquire the lock + * @waiter: The waiter that is queued to the lock's wait tree if the + * callsite called task_blocked_on_lock(), otherwise NULL + */ +-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +- struct rt_mutex_waiter *waiter) ++static int __try_to_take_rt_mutex(struct rt_mutex *lock, ++ struct task_struct *task, ++ struct rt_mutex_waiter *waiter, int mode) + { +- unsigned long flags; +- + /* + * Before testing whether we can acquire @lock, we set the + * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all +@@ -803,8 +846,10 @@ + * If waiter is not the highest priority waiter of + * @lock, give up. + */ +- if (waiter != rt_mutex_top_waiter(lock)) ++ if (waiter != rt_mutex_top_waiter(lock)) { ++ /* XXX lock_is_stealable() ? */ + return 0; ++ } + + /* + * We can acquire the lock. Remove the waiter from the +@@ -822,14 +867,10 @@ + * not need to be dequeued. + */ + if (rt_mutex_has_waiters(lock)) { +- /* +- * If @task->prio is greater than or equal to +- * the top waiter priority (kernel view), +- * @task lost. +- */ +- if (task->prio >= rt_mutex_top_waiter(lock)->prio) +- return 0; ++ struct task_struct *pown = rt_mutex_top_waiter(lock)->task; + ++ if (task != pown && !lock_is_stealable(task, pown, mode)) ++ return 0; + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock +@@ -852,7 +893,7 @@ + * case, but conditionals are more expensive than a redundant + * store. + */ +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ raw_spin_lock(&task->pi_lock); + task->pi_blocked_on = NULL; + /* + * Finish the lock acquisition. @task is the new owner. If +@@ -861,7 +902,7 @@ + */ + if (rt_mutex_has_waiters(lock)) + rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock(&task->pi_lock); + + takeit: + /* We got the lock. */ +@@ -878,12 +919,444 @@ + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * preemptible spin_lock functions: ++ */ ++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock, ++ bool mg_off), ++ bool do_mig_dis) ++{ ++ might_sleep_no_state_check(); ++ ++ if (do_mig_dis) ++ migrate_disable(); ++ ++ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) ++ rt_mutex_deadlock_account_lock(lock, current); ++ else ++ slowfn(lock, do_mig_dis); ++} ++ ++static inline int rt_spin_lock_fastunlock(struct rt_mutex *lock, ++ int (*slowfn)(struct rt_mutex *lock)) ++{ ++ if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { ++ rt_mutex_deadlock_account_unlock(current); ++ return 0; ++ } ++ return slowfn(lock); ++} ++#ifdef CONFIG_SMP ++/* ++ * Note that owner is a speculative pointer and dereferencing relies ++ * on rcu_read_lock() and the check against the lock owner. ++ */ ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *owner) ++{ ++ int res = 0; ++ ++ rcu_read_lock(); ++ for (;;) { ++ if (owner != rt_mutex_owner(lock)) ++ break; ++ /* ++ * Ensure that owner->on_cpu is dereferenced _after_ ++ * checking the above to be valid. ++ */ ++ barrier(); ++ if (!owner->on_cpu) { ++ res = 1; ++ break; ++ } ++ cpu_relax(); ++ } ++ rcu_read_unlock(); ++ return res; ++} ++#else ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *orig_owner) ++{ ++ return 1; ++} ++#endif ++ ++static int task_blocks_on_rt_mutex(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ struct task_struct *task, ++ enum rtmutex_chainwalk chwalk); ++/* ++ * Slow path lock function spin_lock style: this variant is very ++ * careful not to miss any non-lock wakeups. ++ * ++ * We store the current state under p->pi_lock in p->saved_state and ++ * the try_to_wake_up() code handles this accordingly. ++ */ ++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock, ++ bool mg_off) ++{ ++ struct task_struct *lock_owner, *self = current; ++ struct rt_mutex_waiter waiter, *top_waiter; ++ unsigned long flags; ++ int ret; ++ ++ rt_mutex_init_waiter(&waiter, true); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) { ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ return; ++ } ++ ++ BUG_ON(rt_mutex_owner(lock) == self); ++ ++ /* ++ * We save whatever state the task is in and we'll restore it ++ * after acquiring the lock taking real wakeups into account ++ * as well. We are serialized via pi_lock against wakeups. See ++ * try_to_wake_up(). ++ */ ++ raw_spin_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ ++ ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK); ++ BUG_ON(ret); ++ ++ for (;;) { ++ /* Try to acquire the lock again. */ ++ if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL)) ++ break; ++ ++ top_waiter = rt_mutex_top_waiter(lock); ++ lock_owner = rt_mutex_owner(lock); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_print_deadlock(&waiter); ++ ++ if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) { ++ if (mg_off) ++ migrate_enable(); ++ schedule(); ++ if (mg_off) ++ migrate_disable(); ++ } ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ } ++ ++ /* ++ * Restore the task state to current->saved_state. We set it ++ * to the original state above and the try_to_wake_up() code ++ * has possibly updated it when a real (non-rtmutex) wakeup ++ * happened while we were blocked. Clear saved_state so ++ * try_to_wakeup() does not get confused. ++ */ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock(&self->pi_lock); ++ ++ /* ++ * try_to_take_rt_mutex() sets the waiter bit ++ * unconditionally. We might have to fix that up: ++ */ ++ fixup_rt_mutex_waiters(lock); ++ ++ BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock)); ++ BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry)); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q, ++ struct rt_mutex *lock); ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++static int noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ unsigned long flags; ++ WAKE_Q(wake_q); ++ WAKE_Q(wake_sleeper_q); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_unlock(lock); ++ ++ rt_mutex_deadlock_account_unlock(current); ++ ++ if (!rt_mutex_has_waiters(lock)) { ++ lock->owner = NULL; ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ return 0; ++ } ++ ++ mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ wake_up_q(&wake_q); ++ wake_up_q_sleeper(&wake_sleeper_q); ++ ++ /* Undo pi boosting.when necessary */ ++ rt_mutex_adjust_prio(current); ++ return 0; ++} ++ ++static int noinline __sched rt_spin_lock_slowunlock_no_deboost(struct rt_mutex *lock) ++{ ++ unsigned long flags; ++ WAKE_Q(wake_q); ++ WAKE_Q(wake_sleeper_q); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_unlock(lock); ++ ++ rt_mutex_deadlock_account_unlock(current); ++ ++ if (!rt_mutex_has_waiters(lock)) { ++ lock->owner = NULL; ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ return 0; ++ } ++ ++ mark_wakeup_next_waiter(&wake_q, &wake_sleeper_q, lock); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ wake_up_q(&wake_q); ++ wake_up_q_sleeper(&wake_sleeper_q); ++ return 1; ++} ++ ++void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, false); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock__no_mg); ++ ++void __lockfunc rt_spin_lock(spinlock_t *lock) ++{ ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++} ++EXPORT_SYMBOL(rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, true); ++} ++EXPORT_SYMBOL(__rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, false); ++} ++EXPORT_SYMBOL(__rt_spin_lock__no_mg); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) ++{ ++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true); ++} ++EXPORT_SYMBOL(rt_spin_lock_nested); ++#endif ++ ++void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(rt_spin_unlock__no_mg); ++ ++void __lockfunc rt_spin_unlock(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_spin_unlock); ++ ++int __lockfunc rt_spin_unlock_no_deboost(spinlock_t *lock) ++{ ++ int ret; ++ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ ret = rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_no_deboost); ++ migrate_enable(); ++ return ret; ++} ++ ++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(__rt_spin_unlock); ++ ++/* ++ * Wait for the lock to get unlocked: instead of polling for an unlock ++ * (like raw spinlocks do), we lock and unlock, to force the kernel to ++ * schedule if there's contention: ++ */ ++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ spin_unlock(lock); ++} ++EXPORT_SYMBOL(rt_spin_unlock_wait); ++ ++int __lockfunc __rt_spin_trylock(struct rt_mutex *lock) ++{ ++ return rt_mutex_trylock(lock); ++} ++ ++int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock) ++{ ++ int ret; ++ ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock__no_mg); ++ ++int __lockfunc rt_spin_trylock(spinlock_t *lock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock); ++ ++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) ++{ ++ int ret; ++ ++ local_bh_disable(); ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } else ++ local_bh_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_bh); ++ ++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_irqsave); ++ ++int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock) ++{ ++ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ ++ if (atomic_add_unless(atomic, -1, 1)) ++ return 0; ++ rt_spin_lock(lock); ++ if (atomic_dec_and_test(atomic)) ++ return 1; ++ rt_spin_unlock(lock); ++ return 0; ++} ++EXPORT_SYMBOL(atomic_dec_and_spin_lock); ++ ++ void ++__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++} ++EXPORT_SYMBOL(__rt_spin_lock_init); ++ ++#endif /* PREEMPT_RT_FULL */ ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx); ++ ++ if (!hold_ctx) ++ return 0; ++ ++ if (unlikely(ctx == hold_ctx)) ++ return -EALREADY; ++ ++ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && ++ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); ++ ctx->contending_lock = ww; ++#endif ++ return -EDEADLK; ++ } ++ ++ return 0; ++} ++#else ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ BUG(); ++ return 0; ++} ++ ++#endif ++ ++static inline int ++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter) ++{ ++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); ++} ++ + /* + * Task blocks on lock. + * + * Prepare waiter and propagate pi chain + * +- * This must be called with lock->wait_lock held. ++ * This must be called with lock->wait_lock held and interrupts disabled + */ + static int task_blocks_on_rt_mutex(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, +@@ -894,7 +1367,6 @@ + struct rt_mutex_waiter *top_waiter = waiter; + struct rt_mutex *next_lock; + int chain_walk = 0, res; +- unsigned long flags; + + /* + * Early deadlock detection. We really don't want the task to +@@ -908,7 +1380,24 @@ + if (owner == task) + return -EDEADLK; + +- raw_spin_lock_irqsave(&task->pi_lock, flags); ++ raw_spin_lock(&task->pi_lock); ++ ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + __rt_mutex_adjust_prio(task); + waiter->task = task; + waiter->lock = lock; +@@ -921,18 +1410,18 @@ + + task->pi_blocked_on = waiter; + +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++ raw_spin_unlock(&task->pi_lock); + + if (!owner) + return 0; + +- raw_spin_lock_irqsave(&owner->pi_lock, flags); ++ raw_spin_lock(&owner->pi_lock); + if (waiter == rt_mutex_top_waiter(lock)) { + rt_mutex_dequeue_pi(owner, top_waiter); + rt_mutex_enqueue_pi(owner, waiter); + + __rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -941,7 +1430,7 @@ + /* Store the lock on which owner is blocked or NULL */ + next_lock = task_blocked_on_lock(owner); + +- raw_spin_unlock_irqrestore(&owner->pi_lock, flags); ++ raw_spin_unlock(&owner->pi_lock); + /* + * Even if full deadlock detection is on, if the owner is not + * blocked itself, we can avoid finding this out in the chain +@@ -957,12 +1446,12 @@ + */ + get_task_struct(owner); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, + next_lock, waiter, task); + +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irq(&lock->wait_lock); + + return res; + } +@@ -971,15 +1460,15 @@ + * Remove the top waiter from the current tasks pi waiter tree and + * queue it up. + * +- * Called with lock->wait_lock held. ++ * Called with lock->wait_lock held and interrupts disabled. + */ + static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q, + struct rt_mutex *lock) + { + struct rt_mutex_waiter *waiter; +- unsigned long flags; + +- raw_spin_lock_irqsave(¤t->pi_lock, flags); ++ raw_spin_lock(¤t->pi_lock); + + waiter = rt_mutex_top_waiter(lock); + +@@ -1001,15 +1490,18 @@ + */ + lock->owner = (void *) RT_MUTEX_HAS_WAITERS; + +- raw_spin_unlock_irqrestore(¤t->pi_lock, flags); ++ raw_spin_unlock(¤t->pi_lock); + +- wake_q_add(wake_q, waiter->task); ++ if (waiter->savestate) ++ wake_q_add(wake_sleeper_q, waiter->task); ++ else ++ wake_q_add(wake_q, waiter->task); + } + + /* + * Remove a waiter from a lock and give up + * +- * Must be called with lock->wait_lock held and ++ * Must be called with lock->wait_lock held and interrupts disabled. I must + * have just failed to try_to_take_rt_mutex(). + */ + static void remove_waiter(struct rt_mutex *lock, +@@ -1017,13 +1509,12 @@ + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; +- unsigned long flags; ++ struct rt_mutex *next_lock = NULL; + +- raw_spin_lock_irqsave(¤t->pi_lock, flags); ++ raw_spin_lock(¤t->pi_lock); + rt_mutex_dequeue(lock, waiter); + current->pi_blocked_on = NULL; +- raw_spin_unlock_irqrestore(¤t->pi_lock, flags); ++ raw_spin_unlock(¤t->pi_lock); + + /* + * Only update priority if the waiter was the highest priority +@@ -1032,7 +1523,7 @@ + if (!owner || !is_top_waiter) + return; + +- raw_spin_lock_irqsave(&owner->pi_lock, flags); ++ raw_spin_lock(&owner->pi_lock); + + rt_mutex_dequeue_pi(owner, waiter); + +@@ -1042,9 +1533,10 @@ + __rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + +- raw_spin_unlock_irqrestore(&owner->pi_lock, flags); ++ raw_spin_unlock(&owner->pi_lock); + + /* + * Don't walk the chain, if the owner task is not blocked +@@ -1056,12 +1548,12 @@ + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(owner); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, + next_lock, NULL, current); + +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irq(&lock->wait_lock); + } + + /* +@@ -1078,17 +1570,17 @@ + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || (waiter->prio == task->prio && ++ if (!rt_mutex_real_waiter(waiter) || (waiter->prio == task->prio && + !dl_prio(task->prio))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } + next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); + ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); + } +@@ -1097,16 +1589,17 @@ + * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop + * @lock: the rt_mutex to take + * @state: the state the task should block in (TASK_INTERRUPTIBLE +- * or TASK_UNINTERRUPTIBLE) ++ * or TASK_UNINTERRUPTIBLE) + * @timeout: the pre-initialized and started timer, or NULL for none + * @waiter: the pre-initialized rt_mutex_waiter + * +- * lock->wait_lock must be held by the caller. ++ * Must be called with lock->wait_lock held and interrupts disabled + */ + static int __sched + __rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- struct rt_mutex_waiter *waiter) ++ struct rt_mutex_waiter *waiter, ++ struct ww_acquire_ctx *ww_ctx) + { + int ret = 0; + +@@ -1129,13 +1622,19 @@ + break; + } + +- raw_spin_unlock(&lock->wait_lock); ++ if (ww_ctx && ww_ctx->acquired > 0) { ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ if (ret) ++ break; ++ } ++ ++ raw_spin_unlock_irq(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); + + schedule(); + +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irq(&lock->wait_lock); + set_current_state(state); + } + +@@ -1163,26 +1662,112 @@ + } + } + ++static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++#ifdef CONFIG_DEBUG_MUTEXES ++ /* ++ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, ++ * but released with a normal mutex_unlock in this call. ++ * ++ * This should never happen, always use ww_mutex_unlock. ++ */ ++ DEBUG_LOCKS_WARN_ON(ww->ctx); ++ ++ /* ++ * Not quite done after calling ww_acquire_done() ? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); ++ ++ if (ww_ctx->contending_lock) { ++ /* ++ * After -EDEADLK you tried to ++ * acquire a different ww_mutex? Bad! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); ++ ++ /* ++ * You called ww_mutex_lock after receiving -EDEADLK, ++ * but 'forgot' to unlock everything else first? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); ++ ww_ctx->contending_lock = NULL; ++ } ++ ++ /* ++ * Naughty, using a different class will lead to undefined behavior! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); ++#endif ++ ww_ctx->acquired++; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct rt_mutex_waiter *waiter, *n; ++ ++ /* ++ * This branch gets optimized out for the common case, ++ * and is only important for ww_mutex_lock. ++ */ ++ ww_mutex_lock_acquired(ww, ww_ctx); ++ ww->ctx = ww_ctx; ++ ++ /* ++ * Give any possible sleeping processes the chance to wake up, ++ * so they can recheck if they have to back off. ++ */ ++ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters, ++ tree_entry) { ++ /* XXX debug rt mutex waiter wakeup */ ++ ++ BUG_ON(waiter->lock != lock); ++ rt_mutex_wake_waiter(waiter); ++ } ++} ++ ++#else ++ ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++#endif ++ + /* + * Slow path lock function: + */ + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx) + { + struct rt_mutex_waiter waiter; ++ unsigned long flags; + int ret = 0; + +- debug_rt_mutex_init_waiter(&waiter); +- RB_CLEAR_NODE(&waiter.pi_tree_entry); +- RB_CLEAR_NODE(&waiter.tree_entry); ++ rt_mutex_init_waiter(&waiter, false); + +- raw_spin_lock(&lock->wait_lock); ++ /* ++ * Technically we could use raw_spin_[un]lock_irq() here, but this can ++ * be called in early boot if the cmpxchg() fast path is disabled ++ * (debug, no architecture support). In this case we will acquire the ++ * rtmutex with lock->wait_lock held. But we cannot unconditionally ++ * enable interrupts in that early boot case. So we need to use the ++ * irqsave/restore variants. ++ */ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); + + /* Try to acquire the lock again: */ + if (try_to_take_rt_mutex(lock, current, NULL)) { +- raw_spin_unlock(&lock->wait_lock); ++ if (ww_ctx) ++ ww_mutex_account_lock(lock, ww_ctx); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + return 0; + } + +@@ -1196,13 +1781,23 @@ + + if (likely(!ret)) + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, ++ ww_ctx); ++ else if (ww_ctx) { ++ /* ww_mutex received EDEADLK, let it become EALREADY */ ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ BUG_ON(!ret); ++ } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + if (rt_mutex_has_waiters(lock)) + remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ /* ww_mutex want to report EDEADLK/EALREADY, let them */ ++ if (!ww_ctx) ++ rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ } else if (ww_ctx) { ++ ww_mutex_account_lock(lock, ww_ctx); + } + + /* +@@ -1211,7 +1806,7 @@ + */ + fixup_rt_mutex_waiters(lock); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + /* Remove pending timer: */ + if (unlikely(timeout)) +@@ -1227,6 +1822,7 @@ + */ + static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) + { ++ unsigned long flags; + int ret; + + /* +@@ -1238,10 +1834,10 @@ + return 0; + + /* +- * The mutex has currently no owner. Lock the wait lock and +- * try to acquire the lock. ++ * The mutex has currently no owner. Lock the wait lock and try to ++ * acquire the lock. We use irqsave here to support early boot calls. + */ +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); + + ret = try_to_take_rt_mutex(lock, current, NULL); + +@@ -1251,7 +1847,7 @@ + */ + fixup_rt_mutex_waiters(lock); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + return ret; + } +@@ -1261,9 +1857,13 @@ + * Return whether the current task needs to undo a potential priority boosting. + */ + static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, +- struct wake_q_head *wake_q) ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q) + { +- raw_spin_lock(&lock->wait_lock); ++ unsigned long flags; ++ ++ /* irqsave required to support early boot calls */ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); + + debug_rt_mutex_unlock(lock); + +@@ -1302,10 +1902,10 @@ + */ + while (!rt_mutex_has_waiters(lock)) { + /* Drops lock->wait_lock ! */ +- if (unlock_rt_mutex_safe(lock) == true) ++ if (unlock_rt_mutex_safe(lock, flags) == true) + return false; + /* Relock the rtmutex and try again */ +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); + } + + /* +@@ -1314,9 +1914,9 @@ + * + * Queue the next waiter for wakeup once we release the wait_lock. + */ +- mark_wakeup_next_waiter(wake_q, lock); ++ mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + /* check PI boosting */ + return true; +@@ -1330,31 +1930,36 @@ + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ++ ww_ctx); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { + rt_mutex_deadlock_account_lock(lock, current); + return 0; + } else +- return slowfn(lock, state, timeout, chwalk); ++ return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + + static inline int +@@ -1371,17 +1976,20 @@ + static inline void + rt_mutex_fastunlock(struct rt_mutex *lock, + bool (*slowfn)(struct rt_mutex *lock, +- struct wake_q_head *wqh)) ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper)) + { + WAKE_Q(wake_q); ++ WAKE_Q(wake_sleeper_q); + + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); + + } else { +- bool deboost = slowfn(lock, &wake_q); ++ bool deboost = slowfn(lock, &wake_q, &wake_sleeper_q); + + wake_up_q(&wake_q); ++ wake_up_q_sleeper(&wake_sleeper_q); + + /* Undo pi boosting if necessary: */ + if (deboost) +@@ -1398,7 +2006,7 @@ + { + might_sleep(); + +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); ++ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock); + +@@ -1415,7 +2023,7 @@ + { + might_sleep(); + +- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); ++ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, NULL, rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +@@ -1428,11 +2036,30 @@ + might_sleep(); + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, +- RT_MUTEX_FULL_CHAINWALK, ++ RT_MUTEX_FULL_CHAINWALK, NULL, + rt_mutex_slowlock); + } + + /** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * @detect_deadlock: deadlock detection on/off ++ * ++ * Returns: ++ * 0 on success ++ * -EINTR when interrupted by a signal ++ * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ */ ++int __sched rt_mutex_lock_killable(struct rt_mutex *lock) ++{ ++ might_sleep(); ++ ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, NULL, rt_mutex_slowlock); ++} ++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); ++ ++/** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided + * by the caller +@@ -1452,6 +2079,7 @@ + + return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, ++ NULL, + rt_mutex_slowlock); + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); +@@ -1469,7 +2097,11 @@ + */ + int __sched rt_mutex_trylock(struct rt_mutex *lock) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (WARN_ON_ONCE(in_irq() || in_nmi())) ++#else + if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq())) ++#endif + return 0; + + return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); +@@ -1495,13 +2127,14 @@ + * required or not. + */ + bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wqh) ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper) + { + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { + rt_mutex_deadlock_account_unlock(current); + return false; + } +- return rt_mutex_slowunlock(lock, wqh); ++ return rt_mutex_slowunlock(lock, wqh, wq_sleeper); + } + + /** +@@ -1534,13 +2167,12 @@ + void __rt_mutex_init(struct rt_mutex *lock, const char *name) + { + lock->owner = NULL; +- raw_spin_lock_init(&lock->wait_lock); + lock->waiters = RB_ROOT; + lock->waiters_leftmost = NULL; + + debug_rt_mutex_init(lock, name); + } +-EXPORT_SYMBOL_GPL(__rt_mutex_init); ++EXPORT_SYMBOL(__rt_mutex_init); + + /** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a +@@ -1555,7 +2187,7 @@ + void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner) + { +- __rt_mutex_init(lock, NULL); ++ rt_mutex_init(lock); + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + rt_mutex_deadlock_account_lock(lock, proxy_owner); +@@ -1596,13 +2228,42 @@ + { + int ret; + +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irq(&lock->wait_lock); + + if (try_to_take_rt_mutex(lock, task, NULL)) { +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock(&task->pi_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +@@ -1617,10 +2278,10 @@ + ret = 0; + } + +- if (unlikely(ret)) ++ if (ret && rt_mutex_has_waiters(lock)) + remove_waiter(lock, waiter); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); + +@@ -1668,12 +2329,12 @@ + { + int ret; + +- raw_spin_lock(&lock->wait_lock); ++ raw_spin_lock_irq(&lock->wait_lock); + + set_current_state(TASK_INTERRUPTIBLE); + + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); ++ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + + if (unlikely(ret)) + remove_waiter(lock, waiter); +@@ -1684,7 +2345,93 @@ + */ + fixup_rt_mutex_waiters(lock); + +- raw_spin_unlock(&lock->wait_lock); ++ raw_spin_unlock_irq(&lock->wait_lock); + + return ret; + } ++ ++static inline int ++ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ++ unsigned tmp; ++ ++ if (ctx->deadlock_inject_countdown-- == 0) { ++ tmp = ctx->deadlock_inject_interval; ++ if (tmp > UINT_MAX/4) ++ tmp = UINT_MAX; ++ else ++ tmp = tmp*2 + tmp + tmp/2; ++ ++ ctx->deadlock_inject_interval = tmp; ++ ctx->deadlock_inject_countdown = tmp; ++ ctx->contending_lock = lock; ++ ++ ww_mutex_unlock(lock); ++ ++ return -EDEADLK; ++ } ++#endif ++ ++ return 0; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++int __sched ++__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); ++ ++int __sched ++__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ww_ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ww_ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(__ww_mutex_lock); ++ ++void __sched ww_mutex_unlock(struct ww_mutex *lock) ++{ ++ int nest = !!lock->ctx; ++ ++ /* ++ * The unlocking fastpath is the 0->1 transition from 'locked' ++ * into 'unlocked' state: ++ */ ++ if (nest) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); ++#endif ++ if (lock->ctx->acquired > 0) ++ lock->ctx->acquired--; ++ lock->ctx = NULL; ++ } ++ ++ mutex_release(&lock->base.dep_map, nest, _RET_IP_); ++ rt_mutex_unlock(&lock->base.lock); ++} ++EXPORT_SYMBOL(ww_mutex_unlock); ++#endif +diff -Nur linux-4.4.28.orig/kernel/locking/rtmutex_common.h linux-4.4.28/kernel/locking/rtmutex_common.h +--- linux-4.4.28.orig/kernel/locking/rtmutex_common.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/rtmutex_common.h 2016-11-01 21:26:58.772342023 +0100 +@@ -27,6 +27,7 @@ + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -97,6 +98,9 @@ + /* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); +@@ -110,7 +114,8 @@ + struct rt_mutex_waiter *waiter); + extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to); + extern bool rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wqh); ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper); + extern void rt_mutex_adjust_prio(struct task_struct *task); + + #ifdef CONFIG_DEBUG_RT_MUTEXES +@@ -119,4 +124,14 @@ + # include "rtmutex.h" + #endif + ++static inline void ++rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) ++{ ++ debug_rt_mutex_init_waiter(waiter); ++ waiter->task = NULL; ++ waiter->savestate = savestate; ++ RB_CLEAR_NODE(&waiter->pi_tree_entry); ++ RB_CLEAR_NODE(&waiter->tree_entry); ++} ++ + #endif +diff -Nur linux-4.4.28.orig/kernel/locking/spinlock.c linux-4.4.28/kernel/locking/spinlock.c +--- linux-4.4.28.orig/kernel/locking/spinlock.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/spinlock.c 2016-11-01 21:26:58.772342023 +0100 +@@ -124,8 +124,11 @@ + * __[spin|read|write]_lock_bh() + */ + BUILD_LOCK_OPS(spin, raw_spinlock); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + BUILD_LOCK_OPS(read, rwlock); + BUILD_LOCK_OPS(write, rwlock); ++#endif + + #endif + +@@ -209,6 +212,8 @@ + EXPORT_SYMBOL(_raw_spin_unlock_bh); + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #ifndef CONFIG_INLINE_READ_TRYLOCK + int __lockfunc _raw_read_trylock(rwlock_t *lock) + { +@@ -353,6 +358,8 @@ + EXPORT_SYMBOL(_raw_write_unlock_bh); + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #ifdef CONFIG_DEBUG_LOCK_ALLOC + + void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +diff -Nur linux-4.4.28.orig/kernel/locking/spinlock_debug.c linux-4.4.28/kernel/locking/spinlock_debug.c +--- linux-4.4.28.orig/kernel/locking/spinlock_debug.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/locking/spinlock_debug.c 2016-11-01 21:26:58.772342023 +0100 +@@ -31,6 +31,7 @@ + + EXPORT_SYMBOL(__raw_spin_lock_init); + ++#ifndef CONFIG_PREEMPT_RT_FULL + void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) + { +@@ -48,6 +49,7 @@ + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -159,6 +161,7 @@ + arch_spin_unlock(&lock->raw_lock); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static void rwlock_bug(rwlock_t *lock, const char *msg) + { + if (!debug_locks_off()) +@@ -300,3 +303,5 @@ + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif +diff -Nur linux-4.4.28.orig/kernel/panic.c linux-4.4.28/kernel/panic.c +--- linux-4.4.28.orig/kernel/panic.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/panic.c 2016-11-01 21:26:58.772342023 +0100 +@@ -61,6 +61,37 @@ + cpu_relax(); + } + ++/* ++ * Stop ourselves in NMI context if another CPU has already panicked. Arch code ++ * may override this to prepare for crash dumping, e.g. save regs info. ++ */ ++void __weak nmi_panic_self_stop(struct pt_regs *regs) ++{ ++ panic_smp_self_stop(); ++} ++ ++atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); ++ ++/* ++ * A variant of panic() called from NMI context. We return if we've already ++ * panicked on this CPU. If another CPU already panicked, loop in ++ * nmi_panic_self_stop() which can provide architecture dependent code such ++ * as saving register state for crash dump. ++ */ ++void nmi_panic(struct pt_regs *regs, const char *msg) ++{ ++ int old_cpu, cpu; ++ ++ cpu = raw_smp_processor_id(); ++ old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); ++ ++ if (old_cpu == PANIC_CPU_INVALID) ++ panic("%s", msg); ++ else if (old_cpu != cpu) ++ nmi_panic_self_stop(regs); ++} ++EXPORT_SYMBOL(nmi_panic); ++ + /** + * panic - halt the system + * @fmt: The text string to print +@@ -71,17 +102,17 @@ + */ + void panic(const char *fmt, ...) + { +- static DEFINE_SPINLOCK(panic_lock); + static char buf[1024]; + va_list args; + long i, i_next = 0; + int state = 0; ++ int old_cpu, this_cpu; + + /* + * Disable local interrupts. This will prevent panic_smp_self_stop + * from deadlocking the first cpu that invokes the panic, since + * there is nothing to prevent an interrupt handler (that runs +- * after the panic_lock is acquired) from invoking panic again. ++ * after setting panic_cpu) from invoking panic() again. + */ + local_irq_disable(); + +@@ -94,8 +125,16 @@ + * multiple parallel invocations of panic, all other CPUs either + * stop themself or will wait until they are stopped by the 1st CPU + * with smp_send_stop(). ++ * ++ * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which ++ * comes here, so go ahead. ++ * `old_cpu == this_cpu' means we came from nmi_panic() which sets ++ * panic_cpu to this CPU. In this case, this is also the 1st CPU. + */ +- if (!spin_trylock(&panic_lock)) ++ this_cpu = raw_smp_processor_id(); ++ old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); ++ ++ if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu) + panic_smp_self_stop(); + + console_verbose(); +@@ -400,9 +439,11 @@ + + static int init_oops_id(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else ++#endif + oops_id++; + + return 0; +diff -Nur linux-4.4.28.orig/kernel/power/hibernate.c linux-4.4.28/kernel/power/hibernate.c +--- linux-4.4.28.orig/kernel/power/hibernate.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/power/hibernate.c 2016-11-01 21:26:58.772342023 +0100 +@@ -285,6 +285,8 @@ + + local_irq_disable(); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (error) { + printk(KERN_ERR "PM: Some system devices failed to power down, " +@@ -314,6 +316,7 @@ + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -438,6 +441,7 @@ + goto Enable_cpus; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + + error = syscore_suspend(); + if (error) +@@ -471,6 +475,7 @@ + syscore_resume(); + + Enable_irqs: ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -556,6 +561,7 @@ + goto Enable_cpus; + + local_irq_disable(); ++ system_state = SYSTEM_SUSPEND; + syscore_suspend(); + if (pm_wakeup_pending()) { + error = -EAGAIN; +@@ -568,6 +574,7 @@ + + Power_up: + syscore_resume(); ++ system_state = SYSTEM_RUNNING; + local_irq_enable(); + + Enable_cpus: +@@ -642,6 +649,10 @@ + cpu_relax(); + } + ++#ifndef CONFIG_SUSPEND ++bool pm_in_action; ++#endif ++ + /** + * hibernate - Carry out system hibernation, including saving the image. + */ +@@ -654,6 +665,8 @@ + return -EPERM; + } + ++ pm_in_action = true; ++ + lock_system_sleep(); + /* The snapshot device should not be opened while we're running */ + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { +@@ -719,6 +732,7 @@ + atomic_inc(&snapshot_device_available); + Unlock: + unlock_system_sleep(); ++ pm_in_action = false; + return error; + } + +diff -Nur linux-4.4.28.orig/kernel/power/suspend.c linux-4.4.28/kernel/power/suspend.c +--- linux-4.4.28.orig/kernel/power/suspend.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/power/suspend.c 2016-11-01 21:26:58.772342023 +0100 +@@ -359,6 +359,8 @@ + arch_suspend_disable_irqs(); + BUG_ON(!irqs_disabled()); + ++ system_state = SYSTEM_SUSPEND; ++ + error = syscore_suspend(); + if (!error) { + *wakeup = pm_wakeup_pending(); +@@ -375,6 +377,8 @@ + syscore_resume(); + } + ++ system_state = SYSTEM_RUNNING; ++ + arch_suspend_enable_irqs(); + BUG_ON(irqs_disabled()); + +@@ -518,6 +522,8 @@ + return error; + } + ++bool pm_in_action; ++ + /** + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. +@@ -532,6 +538,8 @@ + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + ++ pm_in_action = true; ++ + error = enter_state(state); + if (error) { + suspend_stats.fail++; +@@ -539,6 +547,7 @@ + } else { + suspend_stats.success++; + } ++ pm_in_action = false; + return error; + } + EXPORT_SYMBOL(pm_suspend); +diff -Nur linux-4.4.28.orig/kernel/printk/printk.c linux-4.4.28/kernel/printk/printk.c +--- linux-4.4.28.orig/kernel/printk/printk.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/printk/printk.c 2016-11-01 21:26:58.776342279 +0100 +@@ -241,6 +241,65 @@ + */ + static DEFINE_RAW_SPINLOCK(logbuf_lock); + ++#ifdef CONFIG_EARLY_PRINTK ++struct console *early_console; ++ ++static void early_vprintk(const char *fmt, va_list ap) ++{ ++ if (early_console) { ++ char buf[512]; ++ int n = vscnprintf(buf, sizeof(buf), fmt, ap); ++ ++ early_console->write(early_console, buf, n); ++ } ++} ++ ++asmlinkage void early_printk(const char *fmt, ...) ++{ ++ va_list ap; ++ ++ va_start(ap, fmt); ++ early_vprintk(fmt, ap); ++ va_end(ap); ++} ++ ++/* ++ * This is independent of any log levels - a global ++ * kill switch that turns off all of printk. ++ * ++ * Used by the NMI watchdog if early-printk is enabled. ++ */ ++static bool __read_mostly printk_killswitch; ++ ++static int __init force_early_printk_setup(char *str) ++{ ++ printk_killswitch = true; ++ return 0; ++} ++early_param("force_early_printk", force_early_printk_setup); ++ ++void printk_kill(void) ++{ ++ printk_killswitch = true; ++} ++ ++#ifdef CONFIG_PRINTK ++static int forced_early_printk(const char *fmt, va_list ap) ++{ ++ if (!printk_killswitch) ++ return 0; ++ early_vprintk(fmt, ap); ++ return 1; ++} ++#endif ++ ++#else ++static inline int forced_early_printk(const char *fmt, va_list ap) ++{ ++ return 0; ++} ++#endif ++ + #ifdef CONFIG_PRINTK + DECLARE_WAIT_QUEUE_HEAD(log_wait); + /* the next printk record to read by syslog(READ) or /proc/kmsg */ +@@ -1203,6 +1262,7 @@ + { + char *text; + int len = 0; ++ int attempts = 0; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) +@@ -1214,7 +1274,14 @@ + u64 seq; + u32 idx; + enum log_flags prev; +- ++ int num_msg; ++try_again: ++ attempts++; ++ if (attempts > 10) { ++ len = -EBUSY; ++ goto out; ++ } ++ num_msg = 0; + if (clear_seq < log_first_seq) { + /* messages are gone, move to first available one */ + clear_seq = log_first_seq; +@@ -1235,6 +1302,14 @@ + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* move first record forward until length fits into the buffer */ +@@ -1248,6 +1323,14 @@ + prev = msg->flags; + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ raw_spin_unlock_irq(&logbuf_lock); ++ raw_spin_lock_irq(&logbuf_lock); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* last message fitting into this dump */ +@@ -1288,6 +1371,7 @@ + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } ++out: + raw_spin_unlock_irq(&logbuf_lock); + + kfree(text); +@@ -1443,6 +1527,12 @@ + if (!console_drivers) + return; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -1458,6 +1548,7 @@ + else + con->write(con, text, len); + } ++ migrate_enable(); + } + + /* +@@ -1518,6 +1609,15 @@ + static int console_trylock_for_printk(void) + { + unsigned int cpu = smp_processor_id(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int lock = !early_boot_irqs_disabled && (preempt_count() == 0) && ++ !irqs_disabled(); ++#else ++ int lock = 1; ++#endif ++ ++ if (!lock) ++ return 0; + + if (!console_trylock()) + return 0; +@@ -1672,6 +1772,13 @@ + /* cpu currently holding logbuf_lock in this function */ + static unsigned int logbuf_cpu = UINT_MAX; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; +@@ -1813,8 +1920,7 @@ + * console_sem which would prevent anyone from printing to + * console + */ +- preempt_disable(); +- ++ migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up +@@ -1822,7 +1928,7 @@ + */ + if (console_trylock_for_printk()) + console_unlock(); +- preempt_enable(); ++ migrate_enable(); + lockdep_on(); + } + +@@ -1961,26 +2067,6 @@ + + #endif /* CONFIG_PRINTK */ + +-#ifdef CONFIG_EARLY_PRINTK +-struct console *early_console; +- +-asmlinkage __visible void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- char buf[512]; +- int n; +- +- if (!early_console) +- return; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- va_end(ap); +- +- early_console->write(early_console, buf, n); +-} +-#endif +- + static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) + { +@@ -2202,11 +2288,16 @@ + goto out; + + len = cont_print_text(text, size); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(cont.level, NULL, 0, text, len); ++#else + raw_spin_unlock(&logbuf_lock); + stop_critical_timings(); + call_console_drivers(cont.level, NULL, 0, text, len); + start_critical_timings(); + local_irq_restore(flags); ++#endif + return; + out: + raw_spin_unlock_irqrestore(&logbuf_lock, flags); +@@ -2316,13 +2407,17 @@ + console_idx = log_next(console_idx); + console_seq++; + console_prev = msg->flags; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ raw_spin_unlock_irqrestore(&logbuf_lock, flags); ++ call_console_drivers(level, ext_text, ext_len, text, len); ++#else + raw_spin_unlock(&logbuf_lock); + + stop_critical_timings(); /* don't trace print latency */ + call_console_drivers(level, ext_text, ext_len, text, len); + start_critical_timings(); + local_irq_restore(flags); +- ++#endif + if (do_cond_resched) + cond_resched(); + } +@@ -2374,6 +2469,11 @@ + { + struct console *c; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. +diff -Nur linux-4.4.28.orig/kernel/ptrace.c linux-4.4.28/kernel/ptrace.c +--- linux-4.4.28.orig/kernel/ptrace.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/ptrace.c 2016-11-01 21:26:58.776342279 +0100 +@@ -129,7 +129,14 @@ + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { +- task->state = __TASK_TRACED; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (task->state & __TASK_TRACED) ++ task->state = __TASK_TRACED; ++ else ++ task->saved_state = __TASK_TRACED; ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); +diff -Nur linux-4.4.28.orig/kernel/rcu/rcutorture.c linux-4.4.28/kernel/rcu/rcutorture.c +--- linux-4.4.28.orig/kernel/rcu/rcutorture.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/rcu/rcutorture.c 2016-11-01 21:26:58.776342279 +0100 +@@ -390,6 +390,7 @@ + .name = "rcu" + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Definitions for rcu_bh torture testing. + */ +@@ -429,6 +430,12 @@ + .name = "rcu_bh" + }; + ++#else ++static struct rcu_torture_ops rcu_bh_ops = { ++ .ttype = INVALID_RCU_FLAVOR, ++}; ++#endif ++ + /* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! +diff -Nur linux-4.4.28.orig/kernel/rcu/tree.c linux-4.4.28/kernel/rcu/tree.c +--- linux-4.4.28.orig/kernel/rcu/tree.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/rcu/tree.c 2016-11-01 21:26:58.780342543 +0100 +@@ -56,6 +56,11 @@ + #include + #include + #include ++#include ++#include ++#include ++#include ++#include "../time/tick-internal.h" + + #include "tree.h" + #include "rcu.h" +@@ -266,6 +271,19 @@ + } + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(void); ++ ++void rcu_bh_qs(void) ++{ ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); ++ rcu_preempt_qs(); ++ local_irq_restore(flags); ++} ++#else + void rcu_bh_qs(void) + { + if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { +@@ -275,6 +293,7 @@ + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); + } + } ++#endif + + static DEFINE_PER_CPU(int, rcu_sched_qs_mask); + +@@ -435,11 +454,13 @@ + /* + * Return the number of RCU BH batches started thus far for debug & stats. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + unsigned long rcu_batches_started_bh(void) + { + return rcu_bh_state.gpnum; + } + EXPORT_SYMBOL_GPL(rcu_batches_started_bh); ++#endif + + /* + * Return the number of RCU batches completed thus far for debug & stats. +@@ -459,6 +480,7 @@ + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU BH batches completed thus far for debug & stats. + */ +@@ -486,6 +508,13 @@ + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + ++#else ++void rcu_force_quiescent_state(void) ++{ ++} ++EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); ++#endif ++ + /* + * Force a quiescent state for RCU-sched. + */ +@@ -536,9 +565,11 @@ + case RCU_FLAVOR: + rsp = rcu_state_p; + break; ++#ifndef CONFIG_PREEMPT_RT_FULL + case RCU_BH_FLAVOR: + rsp = &rcu_bh_state; + break; ++#endif + case RCU_SCHED_FLAVOR: + rsp = &rcu_sched_state; + break; +@@ -1590,7 +1621,6 @@ + int needmore; + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + +- rcu_nocb_gp_cleanup(rsp, rnp); + rnp->need_future_gp[c & 0x1] = 0; + needmore = rnp->need_future_gp[(c + 1) & 0x1]; + trace_rcu_future_gp(rnp, rdp, c, +@@ -1611,7 +1641,7 @@ + !READ_ONCE(rsp->gp_flags) || + !rsp->gp_kthread) + return; +- wake_up(&rsp->gp_wq); ++ swake_up(&rsp->gp_wq); + } + + /* +@@ -1991,6 +2021,7 @@ + int nocb = 0; + struct rcu_data *rdp; + struct rcu_node *rnp = rcu_get_root(rsp); ++ struct swait_queue_head *sq; + + WRITE_ONCE(rsp->gp_activity, jiffies); + raw_spin_lock_irq(&rnp->lock); +@@ -2029,7 +2060,9 @@ + needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; + /* smp_mb() provided by prior unlock-lock pair. */ + nocb += rcu_future_gp_cleanup(rsp, rnp); ++ sq = rcu_nocb_gp_get(rnp); + raw_spin_unlock_irq(&rnp->lock); ++ rcu_nocb_gp_cleanup(sq); + cond_resched_rcu_qs(); + WRITE_ONCE(rsp->gp_activity, jiffies); + rcu_gp_slow(rsp, gp_cleanup_delay); +@@ -2076,7 +2109,7 @@ + READ_ONCE(rsp->gpnum), + TPS("reqwait")); + rsp->gp_state = RCU_GP_WAIT_GPS; +- wait_event_interruptible(rsp->gp_wq, ++ swait_event_interruptible(rsp->gp_wq, + READ_ONCE(rsp->gp_flags) & + RCU_GP_FLAG_INIT); + rsp->gp_state = RCU_GP_DONE_GPS; +@@ -2106,7 +2139,7 @@ + READ_ONCE(rsp->gpnum), + TPS("fqswait")); + rsp->gp_state = RCU_GP_WAIT_FQS; +- ret = wait_event_interruptible_timeout(rsp->gp_wq, ++ ret = swait_event_interruptible_timeout(rsp->gp_wq, + rcu_gp_fqs_check_wake(rsp, &gf), j); + rsp->gp_state = RCU_GP_DOING_FQS; + /* Locking provides needed memory barriers. */ +@@ -2230,7 +2263,7 @@ + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); + raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); +- rcu_gp_kthread_wake(rsp); ++ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ + } + + /* +@@ -2891,7 +2924,7 @@ + } + WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); +- rcu_gp_kthread_wake(rsp); ++ swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ + } + + /* +@@ -2934,18 +2967,17 @@ + /* + * Do RCU core processing for the current CPU. + */ +-static void rcu_process_callbacks(struct softirq_action *unused) ++static void rcu_process_callbacks(void) + { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; +- trace_rcu_utilization(TPS("Start RCU core")); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +- trace_rcu_utilization(TPS("End RCU core")); + } + ++static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + /* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, +@@ -2957,18 +2989,105 @@ + { + if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) + return; +- if (likely(!rsp->boost)) { +- rcu_do_batch(rsp, rdp); ++ rcu_do_batch(rsp, rdp); ++} ++ ++static void rcu_wake_cond(struct task_struct *t, int status) ++{ ++ /* ++ * If the thread is yielding, only wake it when this ++ * is invoked from idle ++ */ ++ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) ++ wake_up_process(t); ++} ++ ++/* ++ * Wake up this CPU's rcuc kthread to do RCU core processing. ++ */ ++static void invoke_rcu_core(void) ++{ ++ unsigned long flags; ++ struct task_struct *t; ++ ++ if (!cpu_online(smp_processor_id())) + return; ++ local_irq_save(flags); ++ __this_cpu_write(rcu_cpu_has_work, 1); ++ t = __this_cpu_read(rcu_cpu_kthread_task); ++ if (t != NULL && current != t) ++ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); ++ local_irq_restore(flags); ++} ++ ++static void rcu_cpu_kthread_park(unsigned int cpu) ++{ ++ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; ++} ++ ++static int rcu_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(rcu_cpu_has_work); ++} ++ ++/* ++ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the ++ * RCU softirq used in flavors and configurations of RCU that do not ++ * support RCU priority boosting. ++ */ ++static void rcu_cpu_kthread(unsigned int cpu) ++{ ++ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); ++ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); ++ int spincnt; ++ ++ for (spincnt = 0; spincnt < 10; spincnt++) { ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); ++ local_bh_disable(); ++ *statusp = RCU_KTHREAD_RUNNING; ++ this_cpu_inc(rcu_cpu_kthread_loops); ++ local_irq_disable(); ++ work = *workp; ++ *workp = 0; ++ local_irq_enable(); ++ if (work) ++ rcu_process_callbacks(); ++ local_bh_enable(); ++ if (*workp == 0) { ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); ++ *statusp = RCU_KTHREAD_WAITING; ++ return; ++ } + } +- invoke_rcu_callbacks_kthread(); ++ *statusp = RCU_KTHREAD_YIELDING; ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); ++ schedule_timeout_interruptible(2); ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); ++ *statusp = RCU_KTHREAD_WAITING; + } + +-static void invoke_rcu_core(void) ++static struct smp_hotplug_thread rcu_cpu_thread_spec = { ++ .store = &rcu_cpu_kthread_task, ++ .thread_should_run = rcu_cpu_kthread_should_run, ++ .thread_fn = rcu_cpu_kthread, ++ .thread_comm = "rcuc/%u", ++ .setup = rcu_cpu_kthread_setup, ++ .park = rcu_cpu_kthread_park, ++}; ++ ++/* ++ * Spawn per-CPU RCU core processing kthreads. ++ */ ++static int __init rcu_spawn_core_kthreads(void) + { +- if (cpu_online(smp_processor_id())) +- raise_softirq(RCU_SOFTIRQ); ++ int cpu; ++ ++ for_each_possible_cpu(cpu) ++ per_cpu(rcu_cpu_has_work, cpu) = 0; ++ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); ++ return 0; + } ++early_initcall(rcu_spawn_core_kthreads); + + /* + * Handle any core-RCU processing required by a call_rcu() invocation. +@@ -3114,6 +3233,7 @@ + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Queue an RCU callback for invocation after a quicker grace period. + */ +@@ -3122,6 +3242,7 @@ + __call_rcu(head, func, &rcu_bh_state, -1, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /* + * Queue an RCU callback for lazy invocation after a grace period. +@@ -3213,6 +3334,7 @@ + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -3239,6 +3361,7 @@ + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + /** + * get_state_synchronize_rcu - Snapshot current RCU state +@@ -3524,7 +3647,7 @@ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (wake) { + smp_mb(); /* EGP done before wake_up(). */ +- wake_up(&rsp->expedited_wq); ++ swake_up(&rsp->expedited_wq); + } + break; + } +@@ -3781,7 +3904,7 @@ + jiffies_start = jiffies; + + for (;;) { +- ret = wait_event_interruptible_timeout( ++ ret = swait_event_timeout( + rsp->expedited_wq, + sync_rcu_preempt_exp_done(rnp_root), + jiffies_stall); +@@ -3789,7 +3912,7 @@ + return; + if (ret < 0) { + /* Hit a signal, disable CPU stall warnings. */ +- wait_event(rsp->expedited_wq, ++ swait_event(rsp->expedited_wq, + sync_rcu_preempt_exp_done(rnp_root)); + return; + } +@@ -4101,6 +4224,7 @@ + mutex_unlock(&rsp->barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -4109,6 +4233,7 @@ + _rcu_barrier(&rcu_bh_state); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +@@ -4455,8 +4580,8 @@ + } + } + +- init_waitqueue_head(&rsp->gp_wq); +- init_waitqueue_head(&rsp->expedited_wq); ++ init_swait_queue_head(&rsp->gp_wq); ++ init_swait_queue_head(&rsp->expedited_wq); + rnp = rsp->level[rcu_num_lvls - 1]; + for_each_possible_cpu(i) { + while (i > rnp->grphi) +@@ -4576,12 +4701,13 @@ + + rcu_bootup_announce(); + rcu_init_geometry(); ++#ifndef CONFIG_PREEMPT_RT_FULL + rcu_init_one(&rcu_bh_state, &rcu_bh_data); ++#endif + rcu_init_one(&rcu_sched_state, &rcu_sched_data); + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); + __rcu_init_preempt(); +- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because +diff -Nur linux-4.4.28.orig/kernel/rcu/tree.h linux-4.4.28/kernel/rcu/tree.h +--- linux-4.4.28.orig/kernel/rcu/tree.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/rcu/tree.h 2016-11-01 21:26:58.780342543 +0100 +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + #include + + /* +@@ -241,7 +242,7 @@ + /* Refused to boost: not sure why, though. */ + /* This can happen due to race conditions. */ + #ifdef CONFIG_RCU_NOCB_CPU +- wait_queue_head_t nocb_gp_wq[2]; ++ struct swait_queue_head nocb_gp_wq[2]; + /* Place for rcu_nocb_kthread() to wait GP. */ + #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ + int need_future_gp[2]; +@@ -393,7 +394,7 @@ + atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ + struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ + struct rcu_head **nocb_follower_tail; +- wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ ++ struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ + struct task_struct *nocb_kthread; + int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ + +@@ -472,7 +473,7 @@ + unsigned long gpnum; /* Current gp number. */ + unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ +- wait_queue_head_t gp_wq; /* Where GP task waits. */ ++ struct swait_queue_head gp_wq; /* Where GP task waits. */ + short gp_flags; /* Commands for GP task. */ + short gp_state; /* GP kthread sleep state. */ + +@@ -504,7 +505,7 @@ + atomic_long_t expedited_workdone3; /* # done by others #3. */ + atomic_long_t expedited_normal; /* # fallbacks to normal. */ + atomic_t expedited_need_qs; /* # CPUs left to check in. */ +- wait_queue_head_t expedited_wq; /* Wait for check-ins. */ ++ struct swait_queue_head expedited_wq; /* Wait for check-ins. */ + int ncpus_snap; /* # CPUs seen last time. */ + + unsigned long jiffies_force_qs; /* Time at which to invoke */ +@@ -556,18 +557,18 @@ + */ + extern struct rcu_state rcu_sched_state; + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern struct rcu_state rcu_bh_state; ++#endif + + #ifdef CONFIG_PREEMPT_RCU + extern struct rcu_state rcu_preempt_state; + #endif /* #ifdef CONFIG_PREEMPT_RCU */ + +-#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DECLARE_PER_CPU(char, rcu_cpu_has_work); +-#endif /* #ifdef CONFIG_RCU_BOOST */ + + #ifndef RCU_TREE_NONCORE + +@@ -587,10 +588,9 @@ + static void __init __rcu_init_preempt(void); + static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +-static void invoke_rcu_callbacks_kthread(void); + static bool rcu_is_callbacks_kthread(void); ++static void rcu_cpu_kthread_setup(unsigned int cpu); + #ifdef CONFIG_RCU_BOOST +-static void rcu_preempt_do_callbacks(void); + static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); + #endif /* #ifdef CONFIG_RCU_BOOST */ +@@ -607,7 +607,8 @@ + static void increment_cpu_stall_ticks(void); + static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); + static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); +-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); ++static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); ++static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); + static void rcu_init_one_nocb(struct rcu_node *rnp); + static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, + bool lazy, unsigned long flags); +diff -Nur linux-4.4.28.orig/kernel/rcu/tree_plugin.h linux-4.4.28/kernel/rcu/tree_plugin.h +--- linux-4.4.28.orig/kernel/rcu/tree_plugin.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/rcu/tree_plugin.h 2016-11-01 21:26:58.780342543 +0100 +@@ -24,25 +24,10 @@ + * Paul E. McKenney + */ + +-#include +-#include +-#include +-#include +-#include "../time/tick-internal.h" +- + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" + +-/* +- * Control variables for per-CPU and per-rcu_node kthreads. These +- * handle all flavors of RCU. +- */ +-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); +-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +-DEFINE_PER_CPU(char, rcu_cpu_has_work); +- + #else /* #ifdef CONFIG_RCU_BOOST */ + + /* +@@ -55,6 +40,14 @@ + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + ++/* ++ * Control variables for per-CPU and per-rcu_node kthreads. These ++ * handle all flavors of RCU. ++ */ ++DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); ++DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); ++DEFINE_PER_CPU(char, rcu_cpu_has_work); ++ + #ifdef CONFIG_RCU_NOCB_CPU + static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ + static bool have_rcu_nocb_mask; /* Was rcu_nocb_mask allocated? */ +@@ -432,7 +425,7 @@ + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", +@@ -645,15 +638,6 @@ + t->rcu_read_unlock_special.b.need_qs = true; + } + +-#ifdef CONFIG_RCU_BOOST +- +-static void rcu_preempt_do_callbacks(void) +-{ +- rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p)); +-} +- +-#endif /* #ifdef CONFIG_RCU_BOOST */ +- + /* + * Queue a preemptible-RCU callback for invocation after a grace period. + */ +@@ -930,6 +914,19 @@ + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++/* ++ * If boosting, set rcuc kthreads to realtime priority. ++ */ ++static void rcu_cpu_kthread_setup(unsigned int cpu) ++{ ++#ifdef CONFIG_RCU_BOOST ++ struct sched_param sp; ++ ++ sp.sched_priority = kthread_prio; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++#endif /* #ifdef CONFIG_RCU_BOOST */ ++} ++ + #ifdef CONFIG_RCU_BOOST + + #include "../locking/rtmutex_common.h" +@@ -961,16 +958,6 @@ + + #endif /* #else #ifdef CONFIG_RCU_TRACE */ + +-static void rcu_wake_cond(struct task_struct *t, int status) +-{ +- /* +- * If the thread is yielding, only wake it when this +- * is invoked from idle +- */ +- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) +- wake_up_process(t); +-} +- + /* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the +@@ -1115,23 +1102,6 @@ + } + + /* +- * Wake up the per-CPU kthread to invoke RCU callbacks. +- */ +-static void invoke_rcu_callbacks_kthread(void) +-{ +- unsigned long flags; +- +- local_irq_save(flags); +- __this_cpu_write(rcu_cpu_has_work, 1); +- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && +- current != __this_cpu_read(rcu_cpu_kthread_task)) { +- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), +- __this_cpu_read(rcu_cpu_kthread_status)); +- } +- local_irq_restore(flags); +-} +- +-/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +@@ -1186,67 +1156,6 @@ + return 0; + } + +-static void rcu_kthread_do_work(void) +-{ +- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); +- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); +- rcu_preempt_do_callbacks(); +-} +- +-static void rcu_cpu_kthread_setup(unsigned int cpu) +-{ +- struct sched_param sp; +- +- sp.sched_priority = kthread_prio; +- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +-} +- +-static void rcu_cpu_kthread_park(unsigned int cpu) +-{ +- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +-} +- +-static int rcu_cpu_kthread_should_run(unsigned int cpu) +-{ +- return __this_cpu_read(rcu_cpu_has_work); +-} +- +-/* +- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the +- * RCU softirq used in flavors and configurations of RCU that do not +- * support RCU priority boosting. +- */ +-static void rcu_cpu_kthread(unsigned int cpu) +-{ +- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); +- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); +- int spincnt; +- +- for (spincnt = 0; spincnt < 10; spincnt++) { +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); +- local_bh_disable(); +- *statusp = RCU_KTHREAD_RUNNING; +- this_cpu_inc(rcu_cpu_kthread_loops); +- local_irq_disable(); +- work = *workp; +- *workp = 0; +- local_irq_enable(); +- if (work) +- rcu_kthread_do_work(); +- local_bh_enable(); +- if (*workp == 0) { +- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); +- *statusp = RCU_KTHREAD_WAITING; +- return; +- } +- } +- *statusp = RCU_KTHREAD_YIELDING; +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); +- schedule_timeout_interruptible(2); +- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); +- *statusp = RCU_KTHREAD_WAITING; +-} +- + /* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still +@@ -1276,26 +1185,12 @@ + free_cpumask_var(cm); + } + +-static struct smp_hotplug_thread rcu_cpu_thread_spec = { +- .store = &rcu_cpu_kthread_task, +- .thread_should_run = rcu_cpu_kthread_should_run, +- .thread_fn = rcu_cpu_kthread, +- .thread_comm = "rcuc/%u", +- .setup = rcu_cpu_kthread_setup, +- .park = rcu_cpu_kthread_park, +-}; +- + /* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ + static void __init rcu_spawn_boost_kthreads(void) + { + struct rcu_node *rnp; +- int cpu; +- +- for_each_possible_cpu(cpu) +- per_cpu(rcu_cpu_has_work, cpu) = 0; +- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + } +@@ -1318,11 +1213,6 @@ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + +-static void invoke_rcu_callbacks_kthread(void) +-{ +- WARN_ON_ONCE(1); +-} +- + static bool rcu_is_callbacks_kthread(void) + { + return false; +@@ -1346,7 +1236,7 @@ + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + +-#if !defined(CONFIG_RCU_FAST_NO_HZ) ++#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + + /* + * Check to see if any future RCU-related work will need to be done +@@ -1363,7 +1253,9 @@ + return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) + ? 0 : rcu_cpu_has_callbacks(NULL); + } ++#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + ++#if !defined(CONFIG_RCU_FAST_NO_HZ) + /* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. +@@ -1459,6 +1351,8 @@ + return cbs_ready; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the +@@ -1504,6 +1398,7 @@ + *nextevt = basemono + dj * TICK_NSEC; + return 0; + } ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + + /* + * Prepare a CPU for idle from an RCU perspective. The first major task +@@ -1822,9 +1717,9 @@ + * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended + * grace period. + */ +-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) ++static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) + { +- wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); ++ swake_up_all(sq); + } + + /* +@@ -1840,10 +1735,15 @@ + rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; + } + ++static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) ++{ ++ return &rnp->nocb_gp_wq[rnp->completed & 0x1]; ++} ++ + static void rcu_init_one_nocb(struct rcu_node *rnp) + { +- init_waitqueue_head(&rnp->nocb_gp_wq[0]); +- init_waitqueue_head(&rnp->nocb_gp_wq[1]); ++ init_swait_queue_head(&rnp->nocb_gp_wq[0]); ++ init_swait_queue_head(&rnp->nocb_gp_wq[1]); + } + + #ifndef CONFIG_RCU_NOCB_CPU_ALL +@@ -1868,7 +1768,7 @@ + if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { + /* Prior smp_mb__after_atomic() orders against prior enqueue. */ + WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); +- wake_up(&rdp_leader->nocb_wq); ++ swake_up(&rdp_leader->nocb_wq); + } + } + +@@ -2081,7 +1981,7 @@ + */ + trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); + for (;;) { +- wait_event_interruptible( ++ swait_event_interruptible( + rnp->nocb_gp_wq[c & 0x1], + (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); + if (likely(d)) +@@ -2109,7 +2009,7 @@ + /* Wait for callbacks to appear. */ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); +- wait_event_interruptible(my_rdp->nocb_wq, ++ swait_event_interruptible(my_rdp->nocb_wq, + !READ_ONCE(my_rdp->nocb_leader_sleep)); + /* Memory barrier handled by smp_mb() calls below and repoll. */ + } else if (firsttime) { +@@ -2184,7 +2084,7 @@ + * List was empty, wake up the follower. + * Memory barriers supplied by atomic_long_add(). + */ +- wake_up(&rdp->nocb_wq); ++ swake_up(&rdp->nocb_wq); + } + } + +@@ -2205,7 +2105,7 @@ + if (!rcu_nocb_poll) { + trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + "FollowerSleep"); +- wait_event_interruptible(rdp->nocb_wq, ++ swait_event_interruptible(rdp->nocb_wq, + READ_ONCE(rdp->nocb_follower_head)); + } else if (firsttime) { + /* Don't drown trace log with "Poll"! */ +@@ -2364,7 +2264,7 @@ + static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) + { + rdp->nocb_tail = &rdp->nocb_head; +- init_waitqueue_head(&rdp->nocb_wq); ++ init_swait_queue_head(&rdp->nocb_wq); + rdp->nocb_follower_tail = &rdp->nocb_follower_head; + } + +@@ -2514,7 +2414,7 @@ + return false; + } + +-static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) ++static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) + { + } + +@@ -2522,6 +2422,11 @@ + { + } + ++static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) ++{ ++ return NULL; ++} ++ + static void rcu_init_one_nocb(struct rcu_node *rnp) + { + } +diff -Nur linux-4.4.28.orig/kernel/rcu/update.c linux-4.4.28/kernel/rcu/update.c +--- linux-4.4.28.orig/kernel/rcu/update.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/rcu/update.c 2016-11-01 21:26:58.780342543 +0100 +@@ -276,6 +276,7 @@ + } + EXPORT_SYMBOL_GPL(rcu_read_lock_held); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -302,6 +303,7 @@ + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +diff -Nur linux-4.4.28.orig/kernel/relay.c linux-4.4.28/kernel/relay.c +--- linux-4.4.28.orig/kernel/relay.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/relay.c 2016-11-01 21:26:58.780342543 +0100 +@@ -336,6 +336,10 @@ + { + struct rchan_buf *buf = (struct rchan_buf *)data; + wake_up_interruptible(&buf->read_wait); ++ /* ++ * Stupid polling for now: ++ */ ++ mod_timer(&buf->timer, jiffies + 1); + } + + /** +@@ -353,6 +357,7 @@ + init_waitqueue_head(&buf->read_wait); + kref_init(&buf->kref); + setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); ++ mod_timer(&buf->timer, jiffies + 1); + } else + del_timer_sync(&buf->timer); + +@@ -736,15 +741,6 @@ + else + buf->early_bytes += buf->chan->subbuf_size - + buf->padding[old_subbuf]; +- smp_mb(); +- if (waitqueue_active(&buf->read_wait)) +- /* +- * Calling wake_up_interruptible() from here +- * will deadlock if we happen to be logging +- * from the scheduler (trying to re-grab +- * rq->lock), so defer it. +- */ +- mod_timer(&buf->timer, jiffies + 1); + } + + old = buf->data; +diff -Nur linux-4.4.28.orig/kernel/sched/completion.c linux-4.4.28/kernel/sched/completion.c +--- linux-4.4.28.orig/kernel/sched/completion.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/completion.c 2016-11-01 21:26:58.780342543 +0100 +@@ -30,10 +30,10 @@ + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done++; +- __wake_up_locked(&x->wait, TASK_NORMAL, 1); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete); + +@@ -50,10 +50,10 @@ + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; +- __wake_up_locked(&x->wait, TASK_NORMAL, 0); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_all_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete_all); + +@@ -62,20 +62,20 @@ + long (*action)(long), long timeout, int state) + { + if (!x->done) { +- DECLARE_WAITQUEUE(wait, current); ++ DECLARE_SWAITQUEUE(wait); + +- __add_wait_queue_tail_exclusive(&x->wait, &wait); ++ __prepare_to_swait(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); +- __remove_wait_queue(&x->wait, &wait); ++ __finish_swait(&x->wait, &wait); + if (!x->done) + return timeout; + } +@@ -89,9 +89,9 @@ + { + might_sleep(); + +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + return timeout; + } + +@@ -277,12 +277,12 @@ + if (!READ_ONCE(x->done)) + return 0; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = 0; + else + x->done--; +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; + } + EXPORT_SYMBOL(try_wait_for_completion); +@@ -311,7 +311,7 @@ + * after it's acquired the lock. + */ + smp_rmb(); +- spin_unlock_wait(&x->wait.lock); ++ raw_spin_unlock_wait(&x->wait.lock); + return true; + } + EXPORT_SYMBOL(completion_done); +diff -Nur linux-4.4.28.orig/kernel/sched/core.c linux-4.4.28/kernel/sched/core.c +--- linux-4.4.28.orig/kernel/sched/core.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/core.c 2016-11-01 21:26:58.784342796 +0100 +@@ -260,7 +260,11 @@ + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + const_debug unsigned int sysctl_sched_nr_migrate = 32; ++#else ++const_debug unsigned int sysctl_sched_nr_migrate = 8; ++#endif + + /* + * period over which we average the RT time consumption, measured +@@ -438,6 +442,7 @@ + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; ++ rq->hrtick_timer.irqsafe = 1; + } + #else /* CONFIG_SCHED_HRTICK */ + static inline void hrtick_clear(struct rq *rq) +@@ -542,7 +547,7 @@ + head->lastp = &node->next; + } + +-void wake_up_q(struct wake_q_head *head) ++void __wake_up_q(struct wake_q_head *head, bool sleeper) + { + struct wake_q_node *node = head->first; + +@@ -559,7 +564,10 @@ + * wake_up_process() implies a wmb() to pair with the queueing + * in wake_q_add() so as not to miss wakeups. + */ +- wake_up_process(task); ++ if (sleeper) ++ wake_up_lock_sleeper(task); ++ else ++ wake_up_process(task); + put_task_struct(task); + } + } +@@ -595,6 +603,38 @@ + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ lockdep_assert_held(&rq->lock); ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -618,11 +658,14 @@ + */ + int get_nohz_timer_target(void) + { +- int i, cpu = smp_processor_id(); ++ int i, cpu; + struct sched_domain *sd; + ++ preempt_disable_rt(); ++ cpu = smp_processor_id(); ++ + if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) +- return cpu; ++ goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -641,6 +684,8 @@ + cpu = housekeeping_any_cpu(); + unlock: + rcu_read_unlock(); ++preempt_en_rt: ++ preempt_enable_rt(); + return cpu; + } + /* +@@ -1174,6 +1219,11 @@ + + lockdep_assert_held(&p->pi_lock); + ++ if (__migrate_disabled(p)) { ++ cpumask_copy(&p->cpus_allowed, new_mask); ++ return; ++ } ++ + queued = task_on_rq_queued(p); + running = task_current(rq, p); + +@@ -1196,6 +1246,84 @@ + enqueue_task(rq, p, ENQUEUE_RESTORE); + } + ++static DEFINE_PER_CPU(struct cpumask, sched_cpumasks); ++static DEFINE_MUTEX(sched_down_mutex); ++static cpumask_t sched_down_cpumask; ++ ++void tell_sched_cpu_down_begin(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_set_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++void tell_sched_cpu_down_done(int cpu) ++{ ++ mutex_lock(&sched_down_mutex); ++ cpumask_clear_cpu(cpu, &sched_down_cpumask); ++ mutex_unlock(&sched_down_mutex); ++} ++ ++/** ++ * migrate_me - try to move the current task off this cpu ++ * ++ * Used by the pin_current_cpu() code to try to get tasks ++ * to move off the current CPU as it is going down. ++ * It will only move the task if the task isn't pinned to ++ * the CPU (with migrate_disable, affinity or NO_SETAFFINITY) ++ * and the task has to be in a RUNNING state. Otherwise the ++ * movement of the task will wake it up (change its state ++ * to running) when the task did not expect it. ++ * ++ * Returns 1 if it succeeded in moving the current task ++ * 0 otherwise. ++ */ ++int migrate_me(void) ++{ ++ struct task_struct *p = current; ++ struct migration_arg arg; ++ struct cpumask *cpumask; ++ struct cpumask *mask; ++ unsigned long flags; ++ unsigned int dest_cpu; ++ struct rq *rq; ++ ++ /* ++ * We can not migrate tasks bounded to a CPU or tasks not ++ * running. The movement of the task will wake it up. ++ */ ++ if (p->flags & PF_NO_SETAFFINITY || p->state) ++ return 0; ++ ++ mutex_lock(&sched_down_mutex); ++ rq = task_rq_lock(p, &flags); ++ ++ cpumask = this_cpu_ptr(&sched_cpumasks); ++ mask = &p->cpus_allowed; ++ ++ cpumask_andnot(cpumask, mask, &sched_down_cpumask); ++ ++ if (!cpumask_weight(cpumask)) { ++ /* It's only on this CPU? */ ++ task_rq_unlock(rq, p, &flags); ++ mutex_unlock(&sched_down_mutex); ++ return 0; ++ } ++ ++ dest_cpu = cpumask_any_and(cpu_active_mask, cpumask); ++ ++ arg.task = p; ++ arg.dest_cpu = dest_cpu; ++ ++ task_rq_unlock(rq, p, &flags); ++ ++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); ++ tlb_migrate_finish(p->mm); ++ mutex_unlock(&sched_down_mutex); ++ ++ return 1; ++} ++ + /* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on +@@ -1235,7 +1363,7 @@ + do_set_cpus_allowed(p, new_mask); + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); +@@ -1411,6 +1539,18 @@ + return ret; + } + ++static bool check_task_state(struct task_struct *p, long match_state) ++{ ++ bool match = false; ++ ++ raw_spin_lock_irq(&p->pi_lock); ++ if (p->state == match_state || p->saved_state == match_state) ++ match = true; ++ raw_spin_unlock_irq(&p->pi_lock); ++ ++ return match; ++} ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -1455,7 +1595,7 @@ + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } +@@ -1470,7 +1610,8 @@ + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; +- if (!match_state || p->state == match_state) ++ if (!match_state || p->state == match_state || ++ p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &flags); + +@@ -1627,7 +1768,7 @@ + { + lockdep_assert_held(&p->pi_lock); + +- if (p->nr_cpus_allowed > 1) ++ if (tsk_nr_cpus_allowed(p) > 1) + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + + /* +@@ -1707,10 +1848,6 @@ + { + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +- +- /* if a worker is waking up, notify workqueue */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -1937,8 +2074,27 @@ + */ + smp_mb__before_spinlock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); +- if (!(p->state & state)) ++ if (!(p->state & state)) { ++ /* ++ * The task might be running due to a spinlock sleeper ++ * wakeup. Check the saved state and set it to running ++ * if the wakeup condition is true. ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) { ++ if (p->saved_state & state) { ++ p->saved_state = TASK_RUNNING; ++ success = 1; ++ } ++ } + goto out; ++ } ++ ++ /* ++ * If this is a regular wakeup, then we can unconditionally ++ * clear the saved state of a "lock sleeper". ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) ++ p->saved_state = TASK_RUNNING; + + trace_sched_waking(p); + +@@ -2030,52 +2186,6 @@ + } + + /** +- * try_to_wake_up_local - try to wake up a local task with rq lock held +- * @p: the thread to be awakened +- * +- * Put @p on the run-queue if it's not already there. The caller must +- * ensure that this_rq() is locked, @p is bound to this_rq() and not +- * the current task. +- */ +-static void try_to_wake_up_local(struct task_struct *p) +-{ +- struct rq *rq = task_rq(p); +- +- if (WARN_ON_ONCE(rq != this_rq()) || +- WARN_ON_ONCE(p == current)) +- return; +- +- lockdep_assert_held(&rq->lock); +- +- if (!raw_spin_trylock(&p->pi_lock)) { +- /* +- * This is OK, because current is on_cpu, which avoids it being +- * picked for load-balance and preemption/IRQs are still +- * disabled avoiding further scheduler activity on it and we've +- * not yet picked a replacement task. +- */ +- lockdep_unpin_lock(&rq->lock); +- raw_spin_unlock(&rq->lock); +- raw_spin_lock(&p->pi_lock); +- raw_spin_lock(&rq->lock); +- lockdep_pin_lock(&rq->lock); +- } +- +- if (!(p->state & TASK_NORMAL)) +- goto out; +- +- trace_sched_waking(p); +- +- if (!task_on_rq_queued(p)) +- ttwu_activate(rq, p, ENQUEUE_WAKEUP); +- +- ttwu_do_wakeup(rq, p, 0); +- ttwu_stat(p, smp_processor_id(), 0); +-out: +- raw_spin_unlock(&p->pi_lock); +-} +- +-/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * +@@ -2093,6 +2203,18 @@ + } + EXPORT_SYMBOL(wake_up_process); + ++/** ++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" ++ * @p: The process to be woken up. ++ * ++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate ++ * the nature of the wakeup. ++ */ ++int wake_up_lock_sleeper(struct task_struct *p) ++{ ++ return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER); ++} ++ + int wake_up_state(struct task_struct *p, unsigned int state) + { + return try_to_wake_up(p, state, 0); +@@ -2279,6 +2401,9 @@ + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -2603,8 +2728,12 @@ + finish_arch_post_lock_switch(); + + fire_sched_in_preempt_notifiers(current); ++ /* ++ * We use mmdrop_delayed() here so we don't have to do the ++ * full __mmdrop() when we are the last user. ++ */ + if (mm) +- mmdrop(mm); ++ mmdrop_delayed(mm); + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); +@@ -2935,16 +3064,6 @@ + } + #endif + +-notrace unsigned long get_parent_ip(unsigned long addr) +-{ +- if (in_lock_functions(addr)) { +- addr = CALLER_ADDR2; +- if (in_lock_functions(addr)) +- addr = CALLER_ADDR3; +- } +- return addr; +-} +- + #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +@@ -2966,7 +3085,7 @@ + PREEMPT_MASK - 10); + #endif + if (preempt_count() == val) { +- unsigned long ip = get_parent_ip(CALLER_ADDR1); ++ unsigned long ip = get_lock_parent_ip(); + #ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; + #endif +@@ -2993,7 +3112,7 @@ + #endif + + if (preempt_count() == val) +- trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); + __preempt_count_sub(val); + } + EXPORT_SYMBOL(preempt_count_sub); +@@ -3048,6 +3167,77 @@ + schedstat_inc(this_rq(), sched_count); + } + ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP) ++ ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ return; ++ } ++ ++ preempt_disable(); ++ preempt_lazy_disable(); ++ pin_current_cpu(); ++ p->migrate_disable = 1; ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ ++ if (p->migrate_disable > 1) { ++ p->migrate_disable--; ++ return; ++ } ++ ++ preempt_disable(); ++ /* ++ * Clearing migrate_disable causes tsk_cpus_allowed to ++ * show the tasks original cpu affinity. ++ */ ++ p->migrate_disable = 0; ++ ++ unpin_current_cpu(); ++ preempt_enable(); ++ preempt_lazy_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#endif ++ + /* + * Pick up the highest-prio task: + */ +@@ -3172,19 +3362,6 @@ + } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; +- +- /* +- * If a worker went to sleep, notify and ask workqueue +- * whether it wants to wake up a task to maintain +- * concurrency. +- */ +- if (prev->flags & PF_WQ_WORKER) { +- struct task_struct *to_wakeup; +- +- to_wakeup = wq_worker_sleeping(prev, cpu); +- if (to_wakeup) +- try_to_wake_up_local(to_wakeup); +- } + } + switch_count = &prev->nvcsw; + } +@@ -3194,6 +3371,7 @@ + + next = pick_next_task(rq, prev); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + rq->clock_skip_update = 0; + +@@ -3215,9 +3393,20 @@ + + static inline void sched_submit_work(struct task_struct *tsk) + { +- if (!tsk->state || tsk_is_pi_blocked(tsk)) ++ if (!tsk->state) + return; + /* ++ * If a worker went to sleep, notify and ask workqueue whether ++ * it wants to wake up a task to maintain concurrency. ++ */ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_sleeping(tsk); ++ ++ ++ if (tsk_is_pi_blocked(tsk)) ++ return; ++ ++ /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ +@@ -3225,6 +3414,12 @@ + blk_schedule_flush_plug(tsk); + } + ++static void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage __visible void __sched schedule(void) + { + struct task_struct *tsk = current; +@@ -3235,6 +3430,7 @@ + __schedule(false); + sched_preempt_enable_no_resched(); + } while (need_resched()); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +@@ -3283,6 +3479,30 @@ + } while (need_resched()); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++/* ++ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is ++ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as ++ * preempt_lazy_count counter >0. ++ */ ++static __always_inline int preemptible_lazy(void) ++{ ++ if (test_thread_flag(TIF_NEED_RESCHED)) ++ return 1; ++ if (current_thread_info()->preempt_lazy_count) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline int preemptible_lazy(void) ++{ ++ return 1; ++} ++ ++#endif ++ + #ifdef CONFIG_PREEMPT + /* + * this is the entry point to schedule() from in-kernel preemption +@@ -3297,6 +3517,8 @@ + */ + if (likely(!preemptible())) + return; ++ if (!preemptible_lazy()) ++ return; + + preempt_schedule_common(); + } +@@ -3323,6 +3545,8 @@ + + if (likely(!preemptible())) + return; ++ if (!preemptible_lazy()) ++ return; + + do { + preempt_disable_notrace(); +@@ -3332,7 +3556,16 @@ + * an infinite recursion. + */ + prev_ctx = exception_enter(); ++ /* ++ * The add/subtract must not be traced by the function ++ * tracer. But we still want to account for the ++ * preempt off latency tracer. Since the _notrace versions ++ * of add/subtract skip the accounting for latency tracer ++ * we must force it manually. ++ */ ++ start_critical_timings(); + __schedule(true); ++ stop_critical_timings(); + exception_exit(prev_ctx); + + preempt_enable_no_resched_notrace(); +@@ -4676,6 +4909,7 @@ + } + EXPORT_SYMBOL(__cond_resched_lock); + ++#ifndef CONFIG_PREEMPT_RT_FULL + int __sched __cond_resched_softirq(void) + { + BUG_ON(!in_softirq()); +@@ -4689,6 +4923,7 @@ + return 0; + } + EXPORT_SYMBOL(__cond_resched_softirq); ++#endif + + /** + * yield - yield the current processor to other threads. +@@ -5055,7 +5290,9 @@ + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +@@ -5196,6 +5433,8 @@ + #endif /* CONFIG_NUMA_BALANCING */ + + #ifdef CONFIG_HOTPLUG_CPU ++static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); ++ + /* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. +@@ -5210,7 +5449,11 @@ + switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } +- mmdrop(mm); ++ /* ++ * Defer the cleanup to an alive cpu. On RT we can neither ++ * call mmdrop() nor mmdrop_delayed() from here. ++ */ ++ per_cpu(idle_last_mm, smp_processor_id()) = mm; + } + + /* +@@ -5583,6 +5826,10 @@ + + case CPU_DEAD: + calc_load_migrate(rq); ++ if (per_cpu(idle_last_mm, cpu)) { ++ mmdrop(per_cpu(idle_last_mm, cpu)); ++ per_cpu(idle_last_mm, cpu) = NULL; ++ } + break; + #endif + } +@@ -7566,7 +7813,7 @@ + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + static inline int preempt_count_equals(int preempt_offset) + { +- int nested = preempt_count() + rcu_preempt_depth(); ++ int nested = preempt_count() + sched_rcu_preempt_depth(); + + return (nested == preempt_offset); + } +diff -Nur linux-4.4.28.orig/kernel/sched/cpudeadline.c linux-4.4.28/kernel/sched/cpudeadline.c +--- linux-4.4.28.orig/kernel/sched/cpudeadline.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/cpudeadline.c 2016-11-01 21:26:58.784342796 +0100 +@@ -103,10 +103,10 @@ + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && +- cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { ++ cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) { + best_cpu = cpumask_any(later_mask); + goto out; +- } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && ++ } else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + best_cpu = cpudl_maximum(cp); + if (later_mask) +diff -Nur linux-4.4.28.orig/kernel/sched/cpupri.c linux-4.4.28/kernel/sched/cpupri.c +--- linux-4.4.28.orig/kernel/sched/cpupri.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/cpupri.c 2016-11-01 21:26:58.784342796 +0100 +@@ -103,11 +103,11 @@ + if (skip) + continue; + +- if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) ++ if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids) + continue; + + if (lowest_mask) { +- cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); ++ cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask); + + /* + * We have to ensure that we have at least one bit +diff -Nur linux-4.4.28.orig/kernel/sched/cputime.c linux-4.4.28/kernel/sched/cputime.c +--- linux-4.4.28.orig/kernel/sched/cputime.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/cputime.c 2016-11-01 21:26:58.788343053 +0100 +@@ -685,7 +685,7 @@ + { + unsigned long long delta = vtime_delta(tsk); + +- WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); ++ WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); + tsk->vtime_snap += delta; + + /* CHECKME: always safe to convert nsecs to cputime? */ +@@ -701,37 +701,37 @@ + + void vtime_account_system(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + __vtime_account_system(tsk); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + + void vtime_gen_account_irq_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + __vtime_account_system(tsk); + if (context_tracking_in_user()) + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + + void vtime_account_user(struct task_struct *tsk) + { + cputime_t delta_cpu; + +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + delta_cpu = get_vtime_delta(tsk); + tsk->vtime_snap_whence = VTIME_SYS; + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + + void vtime_user_enter(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + __vtime_account_system(tsk); + tsk->vtime_snap_whence = VTIME_USER; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + + void vtime_guest_enter(struct task_struct *tsk) +@@ -743,19 +743,19 @@ + * synchronization against the reader (task_gtime()) + * that can thus safely catch up with a tickless delta. + */ +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + __vtime_account_system(tsk); + current->flags |= PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + EXPORT_SYMBOL_GPL(vtime_guest_enter); + + void vtime_guest_exit(struct task_struct *tsk) + { +- write_seqlock(&tsk->vtime_seqlock); ++ write_seqcount_begin(&tsk->vtime_seqcount); + __vtime_account_system(tsk); + current->flags &= ~PF_VCPU; +- write_sequnlock(&tsk->vtime_seqlock); ++ write_seqcount_end(&tsk->vtime_seqcount); + } + EXPORT_SYMBOL_GPL(vtime_guest_exit); + +@@ -768,24 +768,26 @@ + + void arch_vtime_task_switch(struct task_struct *prev) + { +- write_seqlock(&prev->vtime_seqlock); +- prev->vtime_snap_whence = VTIME_SLEEPING; +- write_sequnlock(&prev->vtime_seqlock); ++ write_seqcount_begin(&prev->vtime_seqcount); ++ prev->vtime_snap_whence = VTIME_INACTIVE; ++ write_seqcount_end(&prev->vtime_seqcount); + +- write_seqlock(¤t->vtime_seqlock); ++ write_seqcount_begin(¤t->vtime_seqcount); + current->vtime_snap_whence = VTIME_SYS; + current->vtime_snap = sched_clock_cpu(smp_processor_id()); +- write_sequnlock(¤t->vtime_seqlock); ++ write_seqcount_end(¤t->vtime_seqcount); + } + + void vtime_init_idle(struct task_struct *t, int cpu) + { + unsigned long flags; + +- write_seqlock_irqsave(&t->vtime_seqlock, flags); ++ local_irq_save(flags); ++ write_seqcount_begin(&t->vtime_seqcount); + t->vtime_snap_whence = VTIME_SYS; + t->vtime_snap = sched_clock_cpu(cpu); +- write_sequnlock_irqrestore(&t->vtime_seqlock, flags); ++ write_seqcount_end(&t->vtime_seqcount); ++ local_irq_restore(flags); + } + + cputime_t task_gtime(struct task_struct *t) +@@ -797,13 +799,13 @@ + return t->gtime; + + do { +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seqcount); + + gtime = t->gtime; + if (t->flags & PF_VCPU) + gtime += vtime_delta(t); + +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seqcount, seq)); + + return gtime; + } +@@ -826,7 +828,7 @@ + *udelta = 0; + *sdelta = 0; + +- seq = read_seqbegin(&t->vtime_seqlock); ++ seq = read_seqcount_begin(&t->vtime_seqcount); + + if (u_dst) + *u_dst = *u_src; +@@ -834,7 +836,7 @@ + *s_dst = *s_src; + + /* Task is sleeping, nothing to add */ +- if (t->vtime_snap_whence == VTIME_SLEEPING || ++ if (t->vtime_snap_whence == VTIME_INACTIVE || + is_idle_task(t)) + continue; + +@@ -850,7 +852,7 @@ + if (t->vtime_snap_whence == VTIME_SYS) + *sdelta = delta; + } +- } while (read_seqretry(&t->vtime_seqlock, seq)); ++ } while (read_seqcount_retry(&t->vtime_seqcount, seq)); + } + + +diff -Nur linux-4.4.28.orig/kernel/sched/deadline.c linux-4.4.28/kernel/sched/deadline.c +--- linux-4.4.28.orig/kernel/sched/deadline.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/deadline.c 2016-11-01 21:26:58.788343053 +0100 +@@ -134,7 +134,7 @@ + { + struct task_struct *p = dl_task_of(dl_se); + +- if (p->nr_cpus_allowed > 1) ++ if (tsk_nr_cpus_allowed(p) > 1) + dl_rq->dl_nr_migratory++; + + update_dl_migration(dl_rq); +@@ -144,7 +144,7 @@ + { + struct task_struct *p = dl_task_of(dl_se); + +- if (p->nr_cpus_allowed > 1) ++ if (tsk_nr_cpus_allowed(p) > 1) + dl_rq->dl_nr_migratory--; + + update_dl_migration(dl_rq); +@@ -697,6 +697,7 @@ + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; ++ timer->irqsafe = 1; + } + + static +@@ -989,7 +990,7 @@ + + enqueue_dl_entity(&p->dl, pi_se, flags); + +- if (!task_current(rq, p) && p->nr_cpus_allowed > 1) ++ if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) + enqueue_pushable_dl_task(rq, p); + } + +@@ -1067,9 +1068,9 @@ + * try to make it stay here, it might be important. + */ + if (unlikely(dl_task(curr)) && +- (curr->nr_cpus_allowed < 2 || ++ (tsk_nr_cpus_allowed(curr) < 2 || + !dl_entity_preempt(&p->dl, &curr->dl)) && +- (p->nr_cpus_allowed > 1)) { ++ (tsk_nr_cpus_allowed(p) > 1)) { + int target = find_later_rq(p); + + if (target != -1 && +@@ -1090,7 +1091,7 @@ + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ +- if (rq->curr->nr_cpus_allowed == 1 || ++ if (tsk_nr_cpus_allowed(rq->curr) == 1 || + cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) + return; + +@@ -1098,7 +1099,7 @@ + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ +- if (p->nr_cpus_allowed != 1 && ++ if (tsk_nr_cpus_allowed(p) != 1 && + cpudl_find(&rq->rd->cpudl, p, NULL) != -1) + return; + +@@ -1212,7 +1213,7 @@ + { + update_curr_dl(rq); + +- if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) ++ if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1) + enqueue_pushable_dl_task(rq, p); + } + +@@ -1335,7 +1336,7 @@ + if (unlikely(!later_mask)) + return -1; + +- if (task->nr_cpus_allowed == 1) ++ if (tsk_nr_cpus_allowed(task) == 1) + return -1; + + /* +@@ -1441,7 +1442,7 @@ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(later_rq->cpu, +- &task->cpus_allowed) || ++ tsk_cpus_allowed(task)) || + task_running(rq, task) || + !task_on_rq_queued(task))) { + double_unlock_balance(rq, later_rq); +@@ -1480,7 +1481,7 @@ + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); +- BUG_ON(p->nr_cpus_allowed <= 1); ++ BUG_ON(tsk_nr_cpus_allowed(p) <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!dl_task(p)); +@@ -1519,7 +1520,7 @@ + */ + if (dl_task(rq->curr) && + dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && +- rq->curr->nr_cpus_allowed > 1) { ++ tsk_nr_cpus_allowed(rq->curr) > 1) { + resched_curr(rq); + return 0; + } +@@ -1666,9 +1667,9 @@ + { + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && +- p->nr_cpus_allowed > 1 && ++ tsk_nr_cpus_allowed(p) > 1 && + dl_task(rq->curr) && +- (rq->curr->nr_cpus_allowed < 2 || ++ (tsk_nr_cpus_allowed(rq->curr) < 2 || + !dl_entity_preempt(&p->dl, &rq->curr->dl))) { + push_dl_tasks(rq); + } +@@ -1769,7 +1770,7 @@ + { + if (task_on_rq_queued(p) && rq->curr != p) { + #ifdef CONFIG_SMP +- if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) ++ if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) + queue_push_tasks(rq); + #else + if (dl_task(rq->curr)) +diff -Nur linux-4.4.28.orig/kernel/sched/debug.c linux-4.4.28/kernel/sched/debug.c +--- linux-4.4.28.orig/kernel/sched/debug.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/debug.c 2016-11-01 21:26:58.788343053 +0100 +@@ -251,6 +251,9 @@ + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); ++#ifdef CONFIG_SMP ++ P(rt_nr_migratory); ++#endif + + #undef PN + #undef P +@@ -635,6 +638,10 @@ + #endif + P(policy); + P(prio); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ P(migrate_disable); ++#endif ++ P(nr_cpus_allowed); + #undef PN + #undef __PN + #undef P +diff -Nur linux-4.4.28.orig/kernel/sched/fair.c linux-4.4.28/kernel/sched/fair.c +--- linux-4.4.28.orig/kernel/sched/fair.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/fair.c 2016-11-01 21:26:58.792343317 +0100 +@@ -3166,7 +3166,7 @@ + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -3190,7 +3190,7 @@ + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -3330,7 +3330,7 @@ + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -3512,7 +3512,7 @@ + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -4124,7 +4124,7 @@ + + if (delta < 0) { + if (rq->curr == p) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -5213,7 +5213,7 @@ + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -7964,7 +7964,7 @@ + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -7989,7 +7989,7 @@ + */ + if (rq->curr == p) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +diff -Nur linux-4.4.28.orig/kernel/sched/features.h linux-4.4.28/kernel/sched/features.h +--- linux-4.4.28.orig/kernel/sched/features.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/features.h 2016-11-01 21:26:58.792343317 +0100 +@@ -45,11 +45,19 @@ + */ + SCHED_FEAT(NONTASK_CAPACITY, true) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif ++#else ++ + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#endif + + #ifdef HAVE_RT_PUSH_IPI + /* +diff -Nur linux-4.4.28.orig/kernel/sched/Makefile linux-4.4.28/kernel/sched/Makefile +--- linux-4.4.28.orig/kernel/sched/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/Makefile 2016-11-01 21:26:58.780342543 +0100 +@@ -13,7 +13,7 @@ + + obj-y += core.o loadavg.o clock.o cputime.o + obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +-obj-y += wait.o completion.o idle.o ++obj-y += wait.o swait.o swork.o completion.o idle.o + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o + obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o + obj-$(CONFIG_SCHEDSTATS) += stats.o +diff -Nur linux-4.4.28.orig/kernel/sched/rt.c linux-4.4.28/kernel/sched/rt.c +--- linux-4.4.28.orig/kernel/sched/rt.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/rt.c 2016-11-01 21:26:58.792343317 +0100 +@@ -47,6 +47,7 @@ + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ rt_b->rt_period_timer.irqsafe = 1; + rt_b->rt_period_timer.function = sched_rt_period_timer; + } + +@@ -93,6 +94,7 @@ + rt_rq->push_cpu = nr_cpu_ids; + raw_spin_lock_init(&rt_rq->push_lock); + init_irq_work(&rt_rq->push_work, push_irq_work_func); ++ rt_rq->push_work.flags |= IRQ_WORK_HARD_IRQ; + #endif + #endif /* CONFIG_SMP */ + /* We start is dequeued state, because no RT tasks are queued */ +@@ -326,7 +328,7 @@ + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total++; +- if (p->nr_cpus_allowed > 1) ++ if (tsk_nr_cpus_allowed(p) > 1) + rt_rq->rt_nr_migratory++; + + update_rt_migration(rt_rq); +@@ -343,7 +345,7 @@ + rt_rq = &rq_of_rt_rq(rt_rq)->rt; + + rt_rq->rt_nr_total--; +- if (p->nr_cpus_allowed > 1) ++ if (tsk_nr_cpus_allowed(p) > 1) + rt_rq->rt_nr_migratory--; + + update_rt_migration(rt_rq); +@@ -1262,7 +1264,7 @@ + + enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + +- if (!task_current(rq, p) && p->nr_cpus_allowed > 1) ++ if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) + enqueue_pushable_task(rq, p); + } + +@@ -1351,7 +1353,7 @@ + * will have to sort it out. + */ + if (curr && unlikely(rt_task(curr)) && +- (curr->nr_cpus_allowed < 2 || ++ (tsk_nr_cpus_allowed(curr) < 2 || + curr->prio <= p->prio)) { + int target = find_lowest_rq(p); + +@@ -1375,7 +1377,7 @@ + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ +- if (rq->curr->nr_cpus_allowed == 1 || ++ if (tsk_nr_cpus_allowed(rq->curr) == 1 || + !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) + return; + +@@ -1383,7 +1385,7 @@ + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ +- if (p->nr_cpus_allowed != 1 ++ if (tsk_nr_cpus_allowed(p) != 1 + && cpupri_find(&rq->rd->cpupri, p, NULL)) + return; + +@@ -1517,7 +1519,7 @@ + * The previous task needs to be made eligible for pushing + * if it is still active + */ +- if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) ++ if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1) + enqueue_pushable_task(rq, p); + } + +@@ -1567,7 +1569,7 @@ + if (unlikely(!lowest_mask)) + return -1; + +- if (task->nr_cpus_allowed == 1) ++ if (tsk_nr_cpus_allowed(task) == 1) + return -1; /* No other targets possible */ + + if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) +@@ -1699,7 +1701,7 @@ + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); +- BUG_ON(p->nr_cpus_allowed <= 1); ++ BUG_ON(tsk_nr_cpus_allowed(p) <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!rt_task(p)); +@@ -2059,9 +2061,9 @@ + { + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && +- p->nr_cpus_allowed > 1 && ++ tsk_nr_cpus_allowed(p) > 1 && + (dl_task(rq->curr) || rt_task(rq->curr)) && +- (rq->curr->nr_cpus_allowed < 2 || ++ (tsk_nr_cpus_allowed(rq->curr) < 2 || + rq->curr->prio <= p->prio)) + push_rt_tasks(rq); + } +@@ -2134,7 +2136,7 @@ + */ + if (task_on_rq_queued(p) && rq->curr != p) { + #ifdef CONFIG_SMP +- if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) ++ if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) + queue_push_tasks(rq); + #else + if (p->prio < rq->curr->prio) +diff -Nur linux-4.4.28.orig/kernel/sched/sched.h linux-4.4.28/kernel/sched/sched.h +--- linux-4.4.28.orig/kernel/sched/sched.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/sched/sched.h 2016-11-01 21:26:58.792343317 +0100 +@@ -1100,6 +1100,7 @@ + #define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ + #define WF_FORK 0x02 /* child wakeup after fork */ + #define WF_MIGRATED 0x4 /* internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + /* + * To aid in avoiding the subversion of "niceness" due to uneven distribution +@@ -1299,6 +1300,15 @@ + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +diff -Nur linux-4.4.28.orig/kernel/sched/swait.c linux-4.4.28/kernel/sched/swait.c +--- linux-4.4.28.orig/kernel/sched/swait.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/kernel/sched/swait.c 2016-11-01 21:26:58.792343317 +0100 +@@ -0,0 +1,143 @@ ++#include ++#include ++#include ++ ++void __init_swait_queue_head(struct swait_queue_head *q, const char *name, ++ struct lock_class_key *key) ++{ ++ raw_spin_lock_init(&q->lock); ++ lockdep_set_class_and_name(&q->lock, key, name); ++ INIT_LIST_HEAD(&q->task_list); ++} ++EXPORT_SYMBOL(__init_swait_queue_head); ++ ++/* ++ * The thing about the wake_up_state() return value; I think we can ignore it. ++ * ++ * If for some reason it would return 0, that means the previously waiting ++ * task is already running, so it will observe condition true (or has already). ++ */ ++void swake_up_locked(struct swait_queue_head *q) ++{ ++ struct swait_queue *curr; ++ ++ if (list_empty(&q->task_list)) ++ return; ++ ++ curr = list_first_entry(&q->task_list, typeof(*curr), task_list); ++ wake_up_process(curr->task); ++ list_del_init(&curr->task_list); ++} ++EXPORT_SYMBOL(swake_up_locked); ++ ++void swake_up_all_locked(struct swait_queue_head *q) ++{ ++ struct swait_queue *curr; ++ int wakes = 0; ++ ++ while (!list_empty(&q->task_list)) { ++ ++ curr = list_first_entry(&q->task_list, typeof(*curr), ++ task_list); ++ wake_up_process(curr->task); ++ list_del_init(&curr->task_list); ++ wakes++; ++ } ++ if (pm_in_action) ++ return; ++ WARN(wakes > 2, "complate_all() with %d waiters\n", wakes); ++} ++EXPORT_SYMBOL(swake_up_all_locked); ++ ++void swake_up(struct swait_queue_head *q) ++{ ++ unsigned long flags; ++ ++ if (!swait_active(q)) ++ return; ++ ++ raw_spin_lock_irqsave(&q->lock, flags); ++ swake_up_locked(q); ++ raw_spin_unlock_irqrestore(&q->lock, flags); ++} ++EXPORT_SYMBOL(swake_up); ++ ++/* ++ * Does not allow usage from IRQ disabled, since we must be able to ++ * release IRQs to guarantee bounded hold time. ++ */ ++void swake_up_all(struct swait_queue_head *q) ++{ ++ struct swait_queue *curr; ++ LIST_HEAD(tmp); ++ ++ if (!swait_active(q)) ++ return; ++ ++ raw_spin_lock_irq(&q->lock); ++ list_splice_init(&q->task_list, &tmp); ++ while (!list_empty(&tmp)) { ++ curr = list_first_entry(&tmp, typeof(*curr), task_list); ++ ++ wake_up_state(curr->task, TASK_NORMAL); ++ list_del_init(&curr->task_list); ++ ++ if (list_empty(&tmp)) ++ break; ++ ++ raw_spin_unlock_irq(&q->lock); ++ raw_spin_lock_irq(&q->lock); ++ } ++ raw_spin_unlock_irq(&q->lock); ++} ++EXPORT_SYMBOL(swake_up_all); ++ ++void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) ++{ ++ wait->task = current; ++ if (list_empty(&wait->task_list)) ++ list_add(&wait->task_list, &q->task_list); ++} ++ ++void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) ++{ ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&q->lock, flags); ++ __prepare_to_swait(q, wait); ++ set_current_state(state); ++ raw_spin_unlock_irqrestore(&q->lock, flags); ++} ++EXPORT_SYMBOL(prepare_to_swait); ++ ++long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) ++{ ++ if (signal_pending_state(state, current)) ++ return -ERESTARTSYS; ++ ++ prepare_to_swait(q, wait, state); ++ ++ return 0; ++} ++EXPORT_SYMBOL(prepare_to_swait_event); ++ ++void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait) ++{ ++ __set_current_state(TASK_RUNNING); ++ if (!list_empty(&wait->task_list)) ++ list_del_init(&wait->task_list); ++} ++ ++void finish_swait(struct swait_queue_head *q, struct swait_queue *wait) ++{ ++ unsigned long flags; ++ ++ __set_current_state(TASK_RUNNING); ++ ++ if (!list_empty_careful(&wait->task_list)) { ++ raw_spin_lock_irqsave(&q->lock, flags); ++ list_del_init(&wait->task_list); ++ raw_spin_unlock_irqrestore(&q->lock, flags); ++ } ++} ++EXPORT_SYMBOL(finish_swait); +diff -Nur linux-4.4.28.orig/kernel/sched/swork.c linux-4.4.28/kernel/sched/swork.c +--- linux-4.4.28.orig/kernel/sched/swork.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/kernel/sched/swork.c 2016-11-01 21:26:58.792343317 +0100 +@@ -0,0 +1,173 @@ ++/* ++ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de ++ * ++ * Provides a framework for enqueuing callbacks from irq context ++ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#define SWORK_EVENT_PENDING (1 << 0) ++ ++static DEFINE_MUTEX(worker_mutex); ++static struct sworker *glob_worker; ++ ++struct sworker { ++ struct list_head events; ++ struct swait_queue_head wq; ++ ++ raw_spinlock_t lock; ++ ++ struct task_struct *task; ++ int refs; ++}; ++ ++static bool swork_readable(struct sworker *worker) ++{ ++ bool r; ++ ++ if (kthread_should_stop()) ++ return true; ++ ++ raw_spin_lock_irq(&worker->lock); ++ r = !list_empty(&worker->events); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ return r; ++} ++ ++static int swork_kthread(void *arg) ++{ ++ struct sworker *worker = arg; ++ ++ for (;;) { ++ swait_event_interruptible(worker->wq, ++ swork_readable(worker)); ++ if (kthread_should_stop()) ++ break; ++ ++ raw_spin_lock_irq(&worker->lock); ++ while (!list_empty(&worker->events)) { ++ struct swork_event *sev; ++ ++ sev = list_first_entry(&worker->events, ++ struct swork_event, item); ++ list_del(&sev->item); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, ++ &sev->flags)); ++ sev->func(sev); ++ raw_spin_lock_irq(&worker->lock); ++ } ++ raw_spin_unlock_irq(&worker->lock); ++ } ++ return 0; ++} ++ ++static struct sworker *swork_create(void) ++{ ++ struct sworker *worker; ++ ++ worker = kzalloc(sizeof(*worker), GFP_KERNEL); ++ if (!worker) ++ return ERR_PTR(-ENOMEM); ++ ++ INIT_LIST_HEAD(&worker->events); ++ raw_spin_lock_init(&worker->lock); ++ init_swait_queue_head(&worker->wq); ++ ++ worker->task = kthread_run(swork_kthread, worker, "kswork"); ++ if (IS_ERR(worker->task)) { ++ kfree(worker); ++ return ERR_PTR(-ENOMEM); ++ } ++ ++ return worker; ++} ++ ++static void swork_destroy(struct sworker *worker) ++{ ++ kthread_stop(worker->task); ++ ++ WARN_ON(!list_empty(&worker->events)); ++ kfree(worker); ++} ++ ++/** ++ * swork_queue - queue swork ++ * ++ * Returns %false if @work was already on a queue, %true otherwise. ++ * ++ * The work is queued and processed on a random CPU ++ */ ++bool swork_queue(struct swork_event *sev) ++{ ++ unsigned long flags; ++ ++ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) ++ return false; ++ ++ raw_spin_lock_irqsave(&glob_worker->lock, flags); ++ list_add_tail(&sev->item, &glob_worker->events); ++ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); ++ ++ swake_up(&glob_worker->wq); ++ return true; ++} ++EXPORT_SYMBOL_GPL(swork_queue); ++ ++/** ++ * swork_get - get an instance of the sworker ++ * ++ * Returns an negative error code if the initialization if the worker did not ++ * work, %0 otherwise. ++ * ++ */ ++int swork_get(void) ++{ ++ struct sworker *worker; ++ ++ mutex_lock(&worker_mutex); ++ if (!glob_worker) { ++ worker = swork_create(); ++ if (IS_ERR(worker)) { ++ mutex_unlock(&worker_mutex); ++ return -ENOMEM; ++ } ++ ++ glob_worker = worker; ++ } ++ ++ glob_worker->refs++; ++ mutex_unlock(&worker_mutex); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(swork_get); ++ ++/** ++ * swork_put - puts an instance of the sworker ++ * ++ * Will destroy the sworker thread. This function must not be called until all ++ * queued events have been completed. ++ */ ++void swork_put(void) ++{ ++ mutex_lock(&worker_mutex); ++ ++ glob_worker->refs--; ++ if (glob_worker->refs > 0) ++ goto out; ++ ++ swork_destroy(glob_worker); ++ glob_worker = NULL; ++out: ++ mutex_unlock(&worker_mutex); ++} ++EXPORT_SYMBOL_GPL(swork_put); +diff -Nur linux-4.4.28.orig/kernel/signal.c linux-4.4.28/kernel/signal.c +--- linux-4.4.28.orig/kernel/signal.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/signal.c 2016-11-01 21:26:58.796343570 +0100 +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -352,13 +353,30 @@ + return false; + } + ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ struct sigqueue *q = t->sigqueue_cache; ++ ++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) ++ return NULL; ++ return q; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) ++ return 0; ++ return 1; ++} ++ + /* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ + static struct sigqueue * +-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) ++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit, int fromslab) + { + struct sigqueue *q = NULL; + struct user_struct *user; +@@ -375,7 +393,10 @@ + if (override_rlimit || + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { +- q = kmem_cache_alloc(sigqueue_cachep, flags); ++ if (!fromslab) ++ q = get_task_cache(t); ++ if (!q) ++ q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } +@@ -392,6 +413,13 @@ + return q; + } + ++static struct sigqueue * ++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit) ++{ ++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); ++} ++ + static void __sigqueue_free(struct sigqueue *q) + { + if (q->flags & SIGQUEUE_PREALLOC) +@@ -401,6 +429,21 @@ + kmem_cache_free(sigqueue_cachep, q); + } + ++static void sigqueue_free_current(struct sigqueue *q) ++{ ++ struct user_struct *up; ++ ++ if (q->flags & SIGQUEUE_PREALLOC) ++ return; ++ ++ up = q->user; ++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { ++ atomic_dec(&up->sigpending); ++ free_uid(up); ++ } else ++ __sigqueue_free(q); ++} ++ + void flush_sigqueue(struct sigpending *queue) + { + struct sigqueue *q; +@@ -414,6 +457,21 @@ + } + + /* ++ * Called from __exit_signal. Flush tsk->pending and ++ * tsk->sigqueue_cache ++ */ ++void flush_task_sigqueue(struct task_struct *tsk) ++{ ++ struct sigqueue *q; ++ ++ flush_sigqueue(&tsk->pending); ++ ++ q = get_task_cache(tsk); ++ if (q) ++ kmem_cache_free(sigqueue_cachep, q); ++} ++ ++/* + * Flush all pending signals for this kthread. + */ + void flush_signals(struct task_struct *t) +@@ -525,7 +583,7 @@ + still_pending: + list_del_init(&first->list); + copy_siginfo(info, &first->info); +- __sigqueue_free(first); ++ sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be +@@ -560,6 +618,8 @@ + { + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -1156,8 +1216,8 @@ + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +-int +-force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++static int ++do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + { + unsigned long int flags; + int ret, blocked, ignored; +@@ -1182,6 +1242,39 @@ + return ret; + } + ++int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++{ ++/* ++ * On some archs, PREEMPT_RT has to delay sending a signal from a trap ++ * since it can not enable preemption, and the signal code's spin_locks ++ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will ++ * send the signal on exit of the trap. ++ */ ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (in_atomic()) { ++ if (WARN_ON_ONCE(t != current)) ++ return 0; ++ if (WARN_ON_ONCE(t->forced_info.si_signo)) ++ return 0; ++ ++ if (is_si_special(info)) { ++ WARN_ON_ONCE(info != SEND_SIG_PRIV); ++ t->forced_info.si_signo = sig; ++ t->forced_info.si_errno = 0; ++ t->forced_info.si_code = SI_KERNEL; ++ t->forced_info.si_pid = 0; ++ t->forced_info.si_uid = 0; ++ } else { ++ t->forced_info = *info; ++ } ++ ++ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); ++ return 0; ++ } ++#endif ++ return do_force_sig_info(sig, info, t); ++} ++ + /* + * Nuke all other threads in the group. + */ +@@ -1216,12 +1309,12 @@ + * Disable interrupts early to avoid deadlocks. + * See rcu_read_unlock() comment header for details. + */ +- local_irq_save(*flags); ++ local_irq_save_nort(*flags); + rcu_read_lock(); + sighand = rcu_dereference(tsk->sighand); + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + break; + } + /* +@@ -1242,7 +1335,7 @@ + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_irq_restore_nort(*flags); + } + + return sighand; +@@ -1485,7 +1578,8 @@ + */ + struct sigqueue *sigqueue_alloc(void) + { +- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); ++ /* Preallocated sigqueue objects always from the slabcache ! */ ++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; +@@ -1846,15 +1940,7 @@ + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + +- /* +- * Don't want to allow preemption here, because +- * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). +- */ +- preempt_disable(); + read_unlock(&tasklist_lock); +- preempt_enable_no_resched(); + freezable_schedule(); + } else { + /* +diff -Nur linux-4.4.28.orig/kernel/softirq.c linux-4.4.28/kernel/softirq.c +--- linux-4.4.28.orig/kernel/softirq.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/softirq.c 2016-11-01 21:26:58.796343570 +0100 +@@ -21,10 +21,12 @@ + #include + #include + #include ++#include + #include + #include + #include + #include ++#include + #include + + #define CREATE_TRACE_POINTS +@@ -56,12 +58,108 @@ + static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; + + DEFINE_PER_CPU(struct task_struct *, ksoftirqd); ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) ++DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); ++#endif + + const char * const softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ_COMMON ++# ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct softirq_runner { ++ struct task_struct *runner[NR_SOFTIRQS]; ++}; ++ ++static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); ++ ++static inline void softirq_set_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = current; ++} ++ ++static inline void softirq_clr_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = NULL; ++} ++ ++/* ++ * On preempt-rt a softirq running context might be blocked on a ++ * lock. There might be no other runnable task on this CPU because the ++ * lock owner runs on some other CPU. So we have to go into idle with ++ * the pending bit set. Therefor we need to check this otherwise we ++ * warn about false positives which confuses users and defeats the ++ * whole purpose of this test. ++ * ++ * This code is called with interrupts disabled. ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ u32 warnpending; ++ int i; ++ ++ if (rate_limit >= 10) ++ return; ++ ++ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ for (i = 0; i < NR_SOFTIRQS; i++) { ++ struct task_struct *tsk = sr->runner[i]; ++ ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ if (tsk) { ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ warnpending &= ~(tsk->softirqs_raised); ++ warnpending &= ~(1 << i); ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ warnpending); ++ rate_limit++; ++ } ++} ++# else ++/* ++ * On !PREEMPT_RT we just printk rate limited: ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ ++ if (rate_limit < 10 && ++ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++ ++#else /* !CONFIG_NO_HZ_COMMON */ ++static inline void softirq_set_runner(unsigned int sirq) { } ++static inline void softirq_clr_runner(unsigned int sirq) { } ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -77,6 +175,79 @@ + wake_up_process(tsk); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void wakeup_timer_softirqd(void) ++{ ++ /* Interrupts are disabled: no need to stop preemption */ ++ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); ++ ++ if (tsk && tsk->state != TASK_RUNNING) ++ wake_up_process(tsk); ++} ++#endif ++ ++static void handle_softirq(unsigned int vec_nr) ++{ ++ struct softirq_action *h = softirq_vec + vec_nr; ++ int prev_count; ++ ++ prev_count = preempt_count(); ++ ++ kstat_incr_softirqs_this_cpu(vec_nr); ++ ++ trace_softirq_entry(vec_nr); ++ h->action(h); ++ trace_softirq_exit(vec_nr); ++ if (unlikely(prev_count != preempt_count())) { ++ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", ++ vec_nr, softirq_to_name[vec_nr], h->action, ++ prev_count, preempt_count()); ++ preempt_count_set(prev_count); ++ } ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return local_softirq_pending(); ++} ++ ++static void handle_pending_softirqs(u32 pending) ++{ ++ struct softirq_action *h = softirq_vec; ++ int softirq_bit; ++ ++ local_irq_enable(); ++ ++ h = softirq_vec; ++ ++ while ((softirq_bit = ffs(pending))) { ++ unsigned int vec_nr; ++ ++ h += softirq_bit - 1; ++ vec_nr = h - softirq_vec; ++ handle_softirq(vec_nr); ++ ++ h++; ++ pending >>= softirq_bit; ++ } ++ ++ rcu_bh_qs(); ++ local_irq_disable(); ++} ++ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ if (ksoftirqd_softirq_pending()) { ++ __do_softirq(); ++ local_irq_enable(); ++ cond_resched_rcu_qs(); ++ return; ++ } ++ local_irq_enable(); ++} ++ + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -116,9 +287,9 @@ + + if (preempt_count() == cnt) { + #ifdef CONFIG_DEBUG_PREEMPT +- current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); ++ current->preempt_disable_ip = get_lock_parent_ip(); + #endif +- trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); ++ trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); + } + } + EXPORT_SYMBOL(__local_bh_disable_ip); +@@ -232,10 +403,8 @@ + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; +- struct softirq_action *h; + bool in_hardirq; + __u32 pending; +- int softirq_bit; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the +@@ -254,36 +423,7 @@ + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- while ((softirq_bit = ffs(pending))) { +- unsigned int vec_nr; +- int prev_count; +- +- h += softirq_bit - 1; +- +- vec_nr = h - softirq_vec; +- prev_count = preempt_count(); +- +- kstat_incr_softirqs_this_cpu(vec_nr); +- +- trace_softirq_entry(vec_nr); +- h->action(h); +- trace_softirq_exit(vec_nr); +- if (unlikely(prev_count != preempt_count())) { +- pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", +- vec_nr, softirq_to_name[vec_nr], h->action, +- prev_count, preempt_count()); +- preempt_count_set(prev_count); +- } +- h++; +- pending >>= softirq_bit; +- } +- +- rcu_bh_qs(); +- local_irq_disable(); ++ handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { +@@ -320,6 +460,310 @@ + } + + /* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an interrupt or softirq, we're done ++ * (this also catches softirq-disabled code). We will ++ * actually run the softirq once we return from ++ * the irq or softirq. ++ * ++ * Otherwise we wake up ksoftirqd to make sure we ++ * schedule the softirq soon. ++ */ ++ if (!in_interrupt()) ++ wakeup_softirqd(); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++} ++ ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static void ksoftirqd_set_sched_params(unsigned int cpu) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock per softirq ++ */ ++static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); ++ ++void __init softirq_early_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < NR_SOFTIRQS; i++) ++ local_irq_lock_init(local_softirq_locks[i]); ++} ++ ++static void lock_softirq(int which) ++{ ++ local_lock(local_softirq_locks[which]); ++} ++ ++static void unlock_softirq(int which) ++{ ++ local_unlock(local_softirq_locks[which]); ++} ++ ++static void do_single_softirq(int which) ++{ ++ unsigned long old_flags = current->flags; ++ ++ current->flags &= ~PF_MEMALLOC; ++ vtime_account_irq_enter(current); ++ current->flags |= PF_IN_SOFTIRQ; ++ lockdep_softirq_enter(); ++ local_irq_enable(); ++ handle_softirq(which); ++ local_irq_disable(); ++ lockdep_softirq_exit(); ++ current->flags &= ~PF_IN_SOFTIRQ; ++ vtime_account_irq_enter(current); ++ tsk_restore_flags(current, old_flags, PF_MEMALLOC); ++} ++ ++/* ++ * Called with interrupts disabled. Process softirqs which were raised ++ * in current context (or on behalf of ksoftirqd). ++ */ ++static void do_current_softirqs(void) ++{ ++ while (current->softirqs_raised) { ++ int i = __ffs(current->softirqs_raised); ++ unsigned int pending, mask = (1U << i); ++ ++ current->softirqs_raised &= ~mask; ++ local_irq_enable(); ++ ++ /* ++ * If the lock is contended, we boost the owner to ++ * process the softirq or leave the critical section ++ * now. ++ */ ++ lock_softirq(i); ++ local_irq_disable(); ++ softirq_set_runner(i); ++ /* ++ * Check with the local_softirq_pending() bits, ++ * whether we need to process this still or if someone ++ * else took care of it. ++ */ ++ pending = local_softirq_pending(); ++ if (pending & mask) { ++ set_softirq_pending(pending & ~mask); ++ do_single_softirq(i); ++ } ++ softirq_clr_runner(i); ++ WARN_ON(current->softirq_nestcnt != 1); ++ local_irq_enable(); ++ unlock_softirq(i); ++ local_irq_disable(); ++ } ++} ++ ++void __local_bh_disable(void) ++{ ++ if (++current->softirq_nestcnt == 1) ++ migrate_disable(); ++} ++EXPORT_SYMBOL(__local_bh_disable); ++ ++void __local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ local_irq_disable(); ++ if (current->softirq_nestcnt == 1 && current->softirqs_raised) ++ do_current_softirqs(); ++ local_irq_enable(); ++ ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(__local_bh_enable); ++ ++void _local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ ++int in_serving_softirq(void) ++{ ++ return current->flags & PF_IN_SOFTIRQ; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* Called with preemption disabled */ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ current->softirq_nestcnt++; ++ ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ local_irq_enable(); ++ cond_resched_rcu_qs(); ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled, but migration ++ * disabled. So the cpu can't go away under us. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq() && current->softirqs_raised) { ++ current->softirq_nestcnt++; ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ } ++} ++ ++static void do_raise_softirq_irqoff(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ ++ /* ++ * If we are not in a hard interrupt and inside a bh disabled ++ * region, we simply raise the flag on current. local_bh_enable() ++ * will make sure that the softirq is executed. Otherwise we ++ * delegate it to ksoftirqd. ++ */ ++ if (!in_irq() && current->softirq_nestcnt) ++ current->softirqs_raised |= mask; ++ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) ++ return; ++ ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++} ++ ++static void wakeup_proper_softirq(unsigned int nr) ++{ ++ if ((1UL << nr) & TIMER_SOFTIRQS) ++ wakeup_timer_softirqd(); ++ else ++ wakeup_softirqd(); ++} ++ ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ if (!in_irq() && !current->softirq_nestcnt) ++ wakeup_proper_softirq(nr); ++} ++ ++/* ++ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd ++ */ ++void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || ++ !__this_cpu_read(ktimer_softirqd))) ++ return; ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++ wakeup_proper_softirq(nr); ++} ++ ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an hard interrupt we let irq return code deal ++ * with the wakeup of ksoftirqd. ++ */ ++ if (in_irq()) ++ return; ++ /* ++ * If we are in thread context but outside of a bh disabled ++ * region, we need to wake ksoftirqd as well. ++ * ++ * CHECKME: Some of the places which do that could be wrapped ++ * into local_bh_disable/enable pairs. Though it's unclear ++ * whether this is worth the effort. To find those places just ++ * raise a WARN() if the condition is met. ++ */ ++ if (!current->softirq_nestcnt) ++ wakeup_proper_softirq(nr); ++} ++ ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return current->softirqs_raised; ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ /* Take over all but timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++ ++ /* Take over timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, ++ bool online) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++static int ktimer_softirqd_should_run(unsigned int cpu) ++{ ++ return current->softirqs_raised; ++} ++ ++#endif /* PREEMPT_RT_FULL */ ++/* + * Enter an interrupt context. + */ + void irq_enter(void) +@@ -330,9 +774,9 @@ + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ +- local_bh_disable(); ++ local_bh_disable_nort(); + tick_irq_enter(); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -340,6 +784,7 @@ + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!force_irqthreads) { + #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK + /* +@@ -359,6 +804,18 @@ + } else { + wakeup_softirqd(); + } ++#else /* PREEMPT_RT_FULL */ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ if (__this_cpu_read(ksoftirqd) && ++ __this_cpu_read(ksoftirqd)->softirqs_raised) ++ wakeup_softirqd(); ++ if (__this_cpu_read(ktimer_softirqd) && ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised) ++ wakeup_timer_softirqd(); ++ local_irq_restore(flags); ++#endif + } + + static inline void tick_irq_exit(void) +@@ -395,26 +852,6 @@ + trace_hardirq_exit(); /* must be last! */ + } + +-/* +- * This function must run with irqs disabled! +- */ +-inline void raise_softirq_irqoff(unsigned int nr) +-{ +- __raise_softirq_irqoff(nr); +- +- /* +- * If we're in an interrupt or softirq, we're done +- * (this also catches softirq-disabled code). We will +- * actually run the softirq once we return from +- * the irq or softirq. +- * +- * Otherwise we wake up ksoftirqd to make sure we +- * schedule the softirq soon. +- */ +- if (!in_interrupt()) +- wakeup_softirqd(); +-} +- + void raise_softirq(unsigned int nr) + { + unsigned long flags; +@@ -424,12 +861,6 @@ + local_irq_restore(flags); + } + +-void __raise_softirq_irqoff(unsigned int nr) +-{ +- trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); +-} +- + void open_softirq(int nr, void (*action)(struct softirq_action *)) + { + softirq_vec[nr].action = action; +@@ -446,15 +877,45 @@ + static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); + static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); + ++static void inline ++__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr) ++{ ++ if (tasklet_trylock(t)) { ++again: ++ /* We may have been preempted before tasklet_trylock ++ * and __tasklet_action may have already run. ++ * So double check the sched bit while the takslet ++ * is locked before adding it to the list. ++ */ ++ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ t->next = NULL; ++ *head->tail = t; ++ head->tail = &(t->next); ++ raise_softirq_irqoff(nr); ++ tasklet_unlock(t); ++ } else { ++ /* This is subtle. If we hit the corner case above ++ * It is possible that we get preempted right here, ++ * and another task has successfully called ++ * tasklet_schedule(), then this function, and ++ * failed on the trylock. Thus we must be sure ++ * before releasing the tasklet lock, that the ++ * SCHED_BIT is clear. Otherwise the tasklet ++ * may get its SCHED_BIT set, but not added to the ++ * list ++ */ ++ if (!tasklet_tryunlock(t)) ++ goto again; ++ } ++ } ++} ++ + void __tasklet_schedule(struct tasklet_struct *t) + { + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- raise_softirq_irqoff(TASKLET_SOFTIRQ); ++ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_schedule); +@@ -464,10 +925,7 @@ + unsigned long flags; + + local_irq_save(flags); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_common_schedule(t, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); + local_irq_restore(flags); + } + EXPORT_SYMBOL(__tasklet_hi_schedule); +@@ -476,82 +934,122 @@ + { + BUG_ON(!irqs_disabled()); + +- t->next = __this_cpu_read(tasklet_hi_vec.head); +- __this_cpu_write(tasklet_hi_vec.head, t); +- __raise_softirq_irqoff(HI_SOFTIRQ); ++ __tasklet_hi_schedule(t); + } + EXPORT_SYMBOL(__tasklet_hi_schedule_first); + +-static void tasklet_action(struct softirq_action *a) ++void tasklet_enable(struct tasklet_struct *t) + { +- struct tasklet_struct *list; ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_schedule(t); ++} ++EXPORT_SYMBOL(tasklet_enable); + +- local_irq_disable(); +- list = __this_cpu_read(tasklet_vec.head); +- __this_cpu_write(tasklet_vec.head, NULL); +- __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); +- local_irq_enable(); ++static void __tasklet_action(struct softirq_action *a, ++ struct tasklet_struct *list) ++{ ++ int loops = 1000000; + + while (list) { + struct tasklet_struct *t = list; + + list = list->next; + +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); ++ /* ++ * Should always succeed - after a tasklist got on the ++ * list (after getting the SCHED bit set from 0 to 1), ++ * nothing but the tasklet softirq it got queued to can ++ * lock it: ++ */ ++ if (!tasklet_trylock(t)) { ++ WARN_ON(1); ++ continue; + } + +- local_irq_disable(); + t->next = NULL; +- *__this_cpu_read(tasklet_vec.tail) = t; +- __this_cpu_write(tasklet_vec.tail, &(t->next)); +- __raise_softirq_irqoff(TASKLET_SOFTIRQ); +- local_irq_enable(); ++ ++ /* ++ * If we cannot handle the tasklet because it's disabled, ++ * mark it as pending. tasklet_enable() will later ++ * re-schedule the tasklet. ++ */ ++ if (unlikely(atomic_read(&t->count))) { ++out_disabled: ++ /* implicit unlock: */ ++ wmb(); ++ t->state = TASKLET_STATEF_PENDING; ++ continue; ++ } ++ ++ /* ++ * After this point on the tasklet might be rescheduled ++ * on another CPU, but it can only be added to another ++ * CPU's tasklet list if we unlock the tasklet (which we ++ * dont do yet). ++ */ ++ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ WARN_ON(1); ++ ++again: ++ t->func(t->data); ++ ++ /* ++ * Try to unlock the tasklet. We must use cmpxchg, because ++ * another CPU might have scheduled or disabled the tasklet. ++ * We only allow the STATE_RUN -> 0 transition here. ++ */ ++ while (!tasklet_tryunlock(t)) { ++ /* ++ * If it got disabled meanwhile, bail out: ++ */ ++ if (atomic_read(&t->count)) ++ goto out_disabled; ++ /* ++ * If it got scheduled meanwhile, re-execute ++ * the tasklet function: ++ */ ++ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ goto again; ++ if (!--loops) { ++ printk("hm, tasklet state: %08lx\n", t->state); ++ WARN_ON(1); ++ tasklet_unlock(t); ++ break; ++ } ++ } + } + } + ++static void tasklet_action(struct softirq_action *a) ++{ ++ struct tasklet_struct *list; ++ ++ local_irq_disable(); ++ ++ list = __this_cpu_read(tasklet_vec.head); ++ __this_cpu_write(tasklet_vec.head, NULL); ++ __this_cpu_write(tasklet_vec.tail, this_cpu_ptr(&tasklet_vec.head)); ++ ++ local_irq_enable(); ++ ++ __tasklet_action(a, list); ++} ++ + static void tasklet_hi_action(struct softirq_action *a) + { + struct tasklet_struct *list; + + local_irq_disable(); ++ + list = __this_cpu_read(tasklet_hi_vec.head); + __this_cpu_write(tasklet_hi_vec.head, NULL); + __this_cpu_write(tasklet_hi_vec.tail, this_cpu_ptr(&tasklet_hi_vec.head)); +- local_irq_enable(); + +- while (list) { +- struct tasklet_struct *t = list; +- +- list = list->next; +- +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); +- tasklet_unlock(t); +- continue; +- } +- tasklet_unlock(t); +- } ++ local_irq_enable(); + +- local_irq_disable(); +- t->next = NULL; +- *__this_cpu_read(tasklet_hi_vec.tail) = t; +- __this_cpu_write(tasklet_hi_vec.tail, &(t->next)); +- __raise_softirq_irqoff(HI_SOFTIRQ); +- local_irq_enable(); +- } ++ __tasklet_action(a, list); + } + + void tasklet_init(struct tasklet_struct *t, +@@ -572,7 +1070,7 @@ + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { +- yield(); ++ msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); +@@ -646,25 +1144,26 @@ + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + +-static int ksoftirqd_should_run(unsigned int cpu) +-{ +- return local_softirq_pending(); +-} +- +-static void run_ksoftirqd(unsigned int cpu) ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) + { +- local_irq_disable(); +- if (local_softirq_pending()) { ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { + /* +- * We can safely run softirq on inline stack, as we are not deep +- * in the task stack here. ++ * Hack for now to avoid this busy-loop: + */ +- __do_softirq(); +- local_irq_enable(); +- cond_resched_rcu_qs(); +- return; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif + } +- local_irq_enable(); ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ ++static int ksoftirqd_should_run(unsigned int cpu) ++{ ++ return ksoftirqd_softirq_pending(); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -746,16 +1245,31 @@ + + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, ++ .setup = ksoftirqd_set_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct smp_hotplug_thread softirq_timer_threads = { ++ .store = &ktimer_softirqd, ++ .setup = ktimer_softirqd_set_sched_params, ++ .cleanup = ktimer_softirqd_clr_sched_params, ++ .thread_should_run = ktimer_softirqd_should_run, ++ .thread_fn = run_ksoftirqd, ++ .thread_comm = "ktimersoftd/%u", ++}; ++#endif ++ + static __init int spawn_ksoftirqd(void) + { + register_cpu_notifier(&cpu_nfb); + + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); ++#endif + + return 0; + } +diff -Nur linux-4.4.28.orig/kernel/stop_machine.c linux-4.4.28/kernel/stop_machine.c +--- linux-4.4.28.orig/kernel/stop_machine.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/stop_machine.c 2016-11-01 21:26:58.796343570 +0100 +@@ -37,7 +37,7 @@ + struct cpu_stopper { + struct task_struct *thread; + +- spinlock_t lock; ++ raw_spinlock_t lock; + bool enabled; /* is this stopper enabled? */ + struct list_head works; /* list of pending works */ + +@@ -86,12 +86,12 @@ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + unsigned long flags; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + if (stopper->enabled) + __cpu_stop_queue_work(stopper, work); + else + cpu_stop_signal_done(work->done, false); +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + } + + /** +@@ -224,8 +224,8 @@ + int err; + + lg_double_lock(&stop_cpus_lock, cpu1, cpu2); +- spin_lock_irq(&stopper1->lock); +- spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); ++ raw_spin_lock_irq(&stopper1->lock); ++ raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); + + err = -ENOENT; + if (!stopper1->enabled || !stopper2->enabled) +@@ -235,8 +235,8 @@ + __cpu_stop_queue_work(stopper1, work1); + __cpu_stop_queue_work(stopper2, work2); + unlock: +- spin_unlock(&stopper2->lock); +- spin_unlock_irq(&stopper1->lock); ++ raw_spin_unlock(&stopper2->lock); ++ raw_spin_unlock_irq(&stopper1->lock); + lg_double_unlock(&stop_cpus_lock, cpu1, cpu2); + + return err; +@@ -258,7 +258,7 @@ + struct cpu_stop_work work1, work2; + struct multi_stop_data msdata; + +- preempt_disable(); ++ preempt_disable_nort(); + msdata = (struct multi_stop_data){ + .fn = fn, + .data = arg, +@@ -278,11 +278,11 @@ + if (cpu1 > cpu2) + swap(cpu1, cpu2); + if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) { +- preempt_enable(); ++ preempt_enable_nort(); + return -ENOENT; + } + +- preempt_enable(); ++ preempt_enable_nort(); + + wait_for_completion(&done.completion); + +@@ -315,17 +315,20 @@ + + static void queue_stop_cpus_work(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg, +- struct cpu_stop_done *done) ++ struct cpu_stop_done *done, bool inactive) + { + struct cpu_stop_work *work; + unsigned int cpu; + + /* +- * Disable preemption while queueing to avoid getting +- * preempted by a stopper which might wait for other stoppers +- * to enter @fn which can lead to deadlock. ++ * Make sure that all work is queued on all cpus before ++ * any of the cpus can execute it. + */ +- lg_global_lock(&stop_cpus_lock); ++ if (!inactive) ++ lg_global_lock(&stop_cpus_lock); ++ else ++ lg_global_trylock_relax(&stop_cpus_lock); ++ + for_each_cpu(cpu, cpumask) { + work = &per_cpu(cpu_stopper.stop_work, cpu); + work->fn = fn; +@@ -342,7 +345,7 @@ + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); +- queue_stop_cpus_work(cpumask, fn, arg, &done); ++ queue_stop_cpus_work(cpumask, fn, arg, &done, false); + wait_for_completion(&done.completion); + return done.executed ? done.ret : -ENOENT; + } +@@ -422,9 +425,9 @@ + unsigned long flags; + int run; + +- spin_lock_irqsave(&stopper->lock, flags); ++ raw_spin_lock_irqsave(&stopper->lock, flags); + run = !list_empty(&stopper->works); +- spin_unlock_irqrestore(&stopper->lock, flags); ++ raw_spin_unlock_irqrestore(&stopper->lock, flags); + return run; + } + +@@ -436,13 +439,13 @@ + + repeat: + work = NULL; +- spin_lock_irq(&stopper->lock); ++ raw_spin_lock_irq(&stopper->lock); + if (!list_empty(&stopper->works)) { + work = list_first_entry(&stopper->works, + struct cpu_stop_work, list); + list_del_init(&work->list); + } +- spin_unlock_irq(&stopper->lock); ++ raw_spin_unlock_irq(&stopper->lock); + + if (work) { + cpu_stop_fn_t fn = work->fn; +@@ -450,6 +453,16 @@ + struct cpu_stop_done *done = work->done; + char ksym_buf[KSYM_NAME_LEN] __maybe_unused; + ++ /* ++ * Wait until the stopper finished scheduling on all ++ * cpus ++ */ ++ lg_global_lock(&stop_cpus_lock); ++ /* ++ * Let other cpu threads continue as well ++ */ ++ lg_global_unlock(&stop_cpus_lock); ++ + /* cpu stop callbacks are not allowed to sleep */ + preempt_disable(); + +@@ -520,10 +533,12 @@ + for_each_possible_cpu(cpu) { + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + +- spin_lock_init(&stopper->lock); ++ raw_spin_lock_init(&stopper->lock); + INIT_LIST_HEAD(&stopper->works); + } + ++ lg_lock_init(&stop_cpus_lock, "stop_cpus_lock"); ++ + BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); + stop_machine_unpark(raw_smp_processor_id()); + stop_machine_initialized = true; +@@ -620,7 +635,7 @@ + set_state(&msdata, MULTI_STOP_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, +- &done); ++ &done, true); + ret = multi_cpu_stop(&msdata); + + /* Busy wait for completion. */ +diff -Nur linux-4.4.28.orig/kernel/time/hrtimer.c linux-4.4.28/kernel/time/hrtimer.c +--- linux-4.4.28.orig/kernel/time/hrtimer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/hrtimer.c 2016-11-01 21:26:58.796343570 +0100 +@@ -48,11 +48,13 @@ + #include + #include + #include ++#include + #include + + #include + + #include ++#include + + #include "tick-internal.h" + +@@ -717,6 +719,44 @@ + + static DECLARE_WORK(hrtimer_work, clock_was_set_work); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *clock_set_delay_thread; ++static bool do_clock_set_delay; ++ ++static int run_clock_set_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_clock_set_delay) { ++ do_clock_set_delay = false; ++ schedule_work(&hrtimer_work); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void clock_was_set_delayed(void) ++{ ++ do_clock_set_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(clock_set_delay_thread); ++} ++ ++static __init int create_clock_set_delay_thread(void) ++{ ++ clock_set_delay_thread = kthread_run(run_clock_set_delay, NULL, "kclksetdelayd"); ++ BUG_ON(!clock_set_delay_thread); ++ return 0; ++} ++early_initcall(create_clock_set_delay_thread); ++#else /* PREEMPT_RT_FULL */ + /* + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. +@@ -725,6 +765,7 @@ + { + schedule_work(&hrtimer_work); + } ++#endif + + #else + +@@ -734,11 +775,8 @@ + static inline void hrtimer_switch_to_hres(void) { } + static inline void + hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } +-static inline int hrtimer_reprogram(struct hrtimer *timer, +- struct hrtimer_clock_base *base) +-{ +- return 0; +-} ++static inline void hrtimer_reprogram(struct hrtimer *timer, ++ struct hrtimer_clock_base *base) { } + static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } + static inline void retrigger_next_event(void *arg) { } + +@@ -870,6 +908,32 @@ + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define wake_up_timer_waiters(b) wake_up(&(b)->wait) ++ ++/** ++ * hrtimer_wait_for_timer - Wait for a running timer ++ * ++ * @timer: timer to wait for ++ * ++ * The function waits in case the timers callback function is ++ * currently executed on the waitqueue of the timer base. The ++ * waitqueue is woken up after the timer callback function has ++ * finished execution. ++ */ ++void hrtimer_wait_for_timer(const struct hrtimer *timer) ++{ ++ struct hrtimer_clock_base *base = timer->base; ++ ++ if (base && base->cpu_base && !timer->irqsafe) ++ wait_event(base->cpu_base->wait, ++ !(hrtimer_callback_running(timer))); ++} ++ ++#else ++# define wake_up_timer_waiters(b) do { } while (0) ++#endif ++ + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -911,6 +975,11 @@ + if (!(state & HRTIMER_STATE_ENQUEUED)) + return; + ++ if (unlikely(!list_empty(&timer->cb_entry))) { ++ list_del_init(&timer->cb_entry); ++ return; ++ } ++ + if (!timerqueue_del(&base->active, &timer->node)) + cpu_base->active_bases &= ~(1 << base->index); + +@@ -1006,7 +1075,16 @@ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + + timer_stats_hrtimer_set_start_info(timer); ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ { ++ ktime_t now = new_base->get_time(); + ++ if (ktime_to_ns(tim) < ktime_to_ns(now)) ++ timer->praecox = now; ++ else ++ timer->praecox = ktime_set(0, 0); ++ } ++#endif + leftmost = enqueue_hrtimer(timer, new_base); + if (!leftmost) + goto unlock; +@@ -1078,7 +1156,7 @@ + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1142,6 +1220,7 @@ + + base = hrtimer_clockid_to_base(clock_id); + timer->base = &cpu_base->clock_base[base]; ++ INIT_LIST_HEAD(&timer->cb_entry); + timerqueue_init(&timer->node); + + #ifdef CONFIG_TIMER_STATS +@@ -1182,6 +1261,7 @@ + seq = raw_read_seqcount_begin(&cpu_base->seq); + + if (timer->state != HRTIMER_STATE_INACTIVE || ++ cpu_base->running_soft == timer || + cpu_base->running == timer) + return true; + +@@ -1280,10 +1360,112 @@ + cpu_base->running = NULL; + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer, ++ struct hrtimer_clock_base *base) ++{ ++ int leftmost; ++ ++ if (restart != HRTIMER_NORESTART && ++ !(timer->state & HRTIMER_STATE_ENQUEUED)) { ++ ++ leftmost = enqueue_hrtimer(timer, base); ++ if (!leftmost) ++ return; ++#ifdef CONFIG_HIGH_RES_TIMERS ++ if (!hrtimer_is_hres_active(timer)) { ++ /* ++ * Kick to reschedule the next tick to handle the new timer ++ * on dynticks target. ++ */ ++ if (base->cpu_base->nohz_active) ++ wake_up_nohz_cpu(base->cpu_base->cpu); ++ } else { ++ ++ hrtimer_reprogram(timer, base); ++ } ++#endif ++ } ++} ++ ++/* ++ * The changes in mainline which removed the callback modes from ++ * hrtimer are not yet working with -rt. The non wakeup_process() ++ * based callbacks which involve sleeping locks need to be treated ++ * seperately. ++ */ ++static void hrtimer_rt_run_pending(void) ++{ ++ enum hrtimer_restart (*fn)(struct hrtimer *); ++ struct hrtimer_cpu_base *cpu_base; ++ struct hrtimer_clock_base *base; ++ struct hrtimer *timer; ++ int index, restart; ++ ++ local_irq_disable(); ++ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id()); ++ ++ raw_spin_lock(&cpu_base->lock); ++ ++ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { ++ base = &cpu_base->clock_base[index]; ++ ++ while (!list_empty(&base->expired)) { ++ timer = list_first_entry(&base->expired, ++ struct hrtimer, cb_entry); ++ ++ /* ++ * Same as the above __run_hrtimer function ++ * just we run with interrupts enabled. ++ */ ++ debug_deactivate(timer); ++ cpu_base->running_soft = timer; ++ raw_write_seqcount_barrier(&cpu_base->seq); ++ ++ __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); ++ timer_stats_account_hrtimer(timer); ++ fn = timer->function; ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ restart = fn(timer); ++ raw_spin_lock_irq(&cpu_base->lock); ++ ++ hrtimer_rt_reprogram(restart, timer, base); ++ raw_write_seqcount_barrier(&cpu_base->seq); ++ ++ WARN_ON_ONCE(cpu_base->running_soft != timer); ++ cpu_base->running_soft = NULL; ++ } ++ } ++ ++ raw_spin_unlock_irq(&cpu_base->lock); ++ ++ wake_up_timer_waiters(cpu_base); ++} ++ ++static int hrtimer_rt_defer(struct hrtimer *timer) ++{ ++ if (timer->irqsafe) ++ return 0; ++ ++ __remove_hrtimer(timer, timer->base, timer->state, 0); ++ list_add_tail(&timer->cb_entry, &timer->base->expired); ++ return 1; ++} ++ ++#else ++ ++static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; } ++ ++#endif ++ ++static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer); ++ + static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now) + { + struct hrtimer_clock_base *base = cpu_base->clock_base; + unsigned int active = cpu_base->active_bases; ++ int raise = 0; + + for (; active; base++, active >>= 1) { + struct timerqueue_node *node; +@@ -1299,6 +1481,15 @@ + + timer = container_of(node, struct hrtimer, node); + ++ trace_hrtimer_interrupt(raw_smp_processor_id(), ++ ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? ++ timer->praecox : hrtimer_get_expires(timer), ++ basenow)), ++ current, ++ timer->function == hrtimer_wakeup ? ++ container_of(timer, struct hrtimer_sleeper, ++ timer)->task : NULL); ++ + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the +@@ -1314,9 +1505,14 @@ + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) + break; + +- __run_hrtimer(cpu_base, base, timer, &basenow); ++ if (!hrtimer_rt_defer(timer)) ++ __run_hrtimer(cpu_base, base, timer, &basenow); ++ else ++ raise = 1; + } + } ++ if (raise) ++ raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + + #ifdef CONFIG_HIGH_RES_TIMERS +@@ -1479,16 +1675,18 @@ + void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) + { + sl->timer.function = hrtimer_wakeup; ++ sl->timer.irqsafe = 1; + sl->task = task; + } + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + +-static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) ++static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode, ++ unsigned long state) + { + hrtimer_init_sleeper(t, current); + + do { +- set_current_state(TASK_INTERRUPTIBLE); ++ set_current_state(state); + hrtimer_start_expires(&t->timer, mode); + + if (likely(t->task)) +@@ -1530,7 +1728,8 @@ + HRTIMER_MODE_ABS); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); + +- if (do_nanosleep(&t, HRTIMER_MODE_ABS)) ++ /* cpu_chill() does not care about restart state. */ ++ if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE)) + goto out; + + rmtp = restart->nanosleep.rmtp; +@@ -1547,8 +1746,10 @@ + return ret; + } + +-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, +- const enum hrtimer_mode mode, const clockid_t clockid) ++static long ++__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid, ++ unsigned long state) + { + struct restart_block *restart; + struct hrtimer_sleeper t; +@@ -1561,7 +1762,7 @@ + + hrtimer_init_on_stack(&t.timer, clockid, mode); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); +- if (do_nanosleep(&t, mode)) ++ if (do_nanosleep(&t, mode, state)) + goto out; + + /* Absolute timers do not update the rmtp value and restart: */ +@@ -1588,6 +1789,12 @@ + return ret; + } + ++long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, ++ const enum hrtimer_mode mode, const clockid_t clockid) ++{ ++ return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE); ++} ++ + SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp, + struct timespec __user *, rmtp) + { +@@ -1602,6 +1809,26 @@ + return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Sleep for 1 ms in hope whoever holds what we want will let it go. ++ */ ++void cpu_chill(void) ++{ ++ struct timespec tu = { ++ .tv_nsec = NSEC_PER_MSEC, ++ }; ++ unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ ++ current->flags |= PF_NOFREEZE; ++ __hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC, ++ TASK_UNINTERRUPTIBLE); ++ if (!freeze_flag) ++ current->flags &= ~PF_NOFREEZE; ++} ++EXPORT_SYMBOL(cpu_chill); ++#endif ++ + /* + * Functions related to boot-time initialization: + */ +@@ -1613,10 +1840,14 @@ + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { + cpu_base->clock_base[i].cpu_base = cpu_base; + timerqueue_init_head(&cpu_base->clock_base[i].active); ++ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired); + } + + cpu_base->cpu = cpu; + hrtimer_init_hres(cpu_base); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -1714,11 +1945,21 @@ + .notifier_call = hrtimer_cpu_notify, + }; + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void run_hrtimer_softirq(struct softirq_action *h) ++{ ++ hrtimer_rt_run_pending(); ++} ++#endif ++ + void __init hrtimers_init(void) + { + hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); + register_cpu_notifier(&hrtimers_nb); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); ++#endif + } + + /** +diff -Nur linux-4.4.28.orig/kernel/time/itimer.c linux-4.4.28/kernel/time/itimer.c +--- linux-4.4.28.orig/kernel/time/itimer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/itimer.c 2016-11-01 21:26:58.796343570 +0100 +@@ -213,6 +213,7 @@ + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); ++ hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +diff -Nur linux-4.4.28.orig/kernel/time/jiffies.c linux-4.4.28/kernel/time/jiffies.c +--- linux-4.4.28.orig/kernel/time/jiffies.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/jiffies.c 2016-11-01 21:26:58.796343570 +0100 +@@ -74,7 +74,8 @@ + .max_cycles = 10, + }; + +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); ++__cacheline_aligned_in_smp seqcount_t jiffies_seq; + + #if (BITS_PER_LONG < 64) + u64 get_jiffies_64(void) +@@ -83,9 +84,9 @@ + u64 ret; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +diff -Nur linux-4.4.28.orig/kernel/time/ntp.c linux-4.4.28/kernel/time/ntp.c +--- linux-4.4.28.orig/kernel/time/ntp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/ntp.c 2016-11-01 21:26:58.796343570 +0100 +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -562,10 +563,52 @@ + &sync_cmos_work, timespec64_to_jiffies(&next)); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT can not call schedule_delayed_work from real interrupt context. ++ * Need to make a thread to do the real work. ++ */ ++static struct task_struct *cmos_delay_thread; ++static bool do_cmos_delay; ++ ++static int run_cmos_delay(void *ignore) ++{ ++ while (!kthread_should_stop()) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ if (do_cmos_delay) { ++ do_cmos_delay = false; ++ queue_delayed_work(system_power_efficient_wq, ++ &sync_cmos_work, 0); ++ } ++ schedule(); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++void ntp_notify_cmos_timer(void) ++{ ++ do_cmos_delay = true; ++ /* Make visible before waking up process */ ++ smp_wmb(); ++ wake_up_process(cmos_delay_thread); ++} ++ ++static __init int create_cmos_delay_thread(void) ++{ ++ cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd"); ++ BUG_ON(!cmos_delay_thread); ++ return 0; ++} ++early_initcall(create_cmos_delay_thread); ++ ++#else ++ + void ntp_notify_cmos_timer(void) + { + queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); + } ++#endif /* CONFIG_PREEMPT_RT_FULL */ + + #else + void ntp_notify_cmos_timer(void) { } +diff -Nur linux-4.4.28.orig/kernel/time/posix-cpu-timers.c linux-4.4.28/kernel/time/posix-cpu-timers.c +--- linux-4.4.28.orig/kernel/time/posix-cpu-timers.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/posix-cpu-timers.c 2016-11-01 21:26:58.800343826 +0100 +@@ -3,6 +3,7 @@ + */ + + #include ++#include + #include + #include + #include +@@ -650,7 +651,7 @@ + /* + * Disarm any old timer after extracting its expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + ret = 0; + old_incr = timer->it.cpu.incr; +@@ -1092,7 +1093,7 @@ + /* + * Now re-arm for the new expiry time. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + arm_timer(timer); + unlock_task_sighand(p, &flags); + +@@ -1183,13 +1184,13 @@ + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +-void run_posix_cpu_timers(struct task_struct *tsk) ++static void __run_posix_cpu_timers(struct task_struct *tsk) + { + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + /* + * The fast path checks that there are no expired thread or thread +@@ -1243,6 +1244,190 @@ + } + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#include ++#include ++DEFINE_PER_CPU(struct task_struct *, posix_timer_task); ++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); ++ ++static int posix_cpu_timers_thread(void *data) ++{ ++ int cpu = (long)data; ++ ++ BUG_ON(per_cpu(posix_timer_task,cpu) != current); ++ ++ while (!kthread_should_stop()) { ++ struct task_struct *tsk = NULL; ++ struct task_struct *next = NULL; ++ ++ if (cpu_is_offline(cpu)) ++ goto wait_to_die; ++ ++ /* grab task list */ ++ raw_local_irq_disable(); ++ tsk = per_cpu(posix_timer_tasklist, cpu); ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ raw_local_irq_enable(); ++ ++ /* its possible the list is empty, just return */ ++ if (!tsk) { ++ set_current_state(TASK_INTERRUPTIBLE); ++ schedule(); ++ __set_current_state(TASK_RUNNING); ++ continue; ++ } ++ ++ /* Process task list */ ++ while (1) { ++ /* save next */ ++ next = tsk->posix_timer_list; ++ ++ /* run the task timers, clear its ptr and ++ * unreference it ++ */ ++ __run_posix_cpu_timers(tsk); ++ tsk->posix_timer_list = NULL; ++ put_task_struct(tsk); ++ ++ /* check if this is the last on the list */ ++ if (next == tsk) ++ break; ++ tsk = next; ++ } ++ } ++ return 0; ++ ++wait_to_die: ++ /* Wait for kthread_stop */ ++ set_current_state(TASK_INTERRUPTIBLE); ++ while (!kthread_should_stop()) { ++ schedule(); ++ set_current_state(TASK_INTERRUPTIBLE); ++ } ++ __set_current_state(TASK_RUNNING); ++ return 0; ++} ++ ++static inline int __fastpath_timer_check(struct task_struct *tsk) ++{ ++ /* tsk == current, ensure it is safe to use ->signal/sighand */ ++ if (unlikely(tsk->exit_state)) ++ return 0; ++ ++ if (!task_cputime_zero(&tsk->cputime_expires)) ++ return 1; ++ ++ if (!task_cputime_zero(&tsk->signal->cputime_expires)) ++ return 1; ++ ++ return 0; ++} ++ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ unsigned long cpu = smp_processor_id(); ++ struct task_struct *tasklist; ++ ++ BUG_ON(!irqs_disabled()); ++ if(!per_cpu(posix_timer_task, cpu)) ++ return; ++ /* get per-cpu references */ ++ tasklist = per_cpu(posix_timer_tasklist, cpu); ++ ++ /* check to see if we're already queued */ ++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { ++ get_task_struct(tsk); ++ if (tasklist) { ++ tsk->posix_timer_list = tasklist; ++ } else { ++ /* ++ * The list is terminated by a self-pointing ++ * task_struct ++ */ ++ tsk->posix_timer_list = tsk; ++ } ++ per_cpu(posix_timer_tasklist, cpu) = tsk; ++ ++ wake_up_process(per_cpu(posix_timer_task, cpu)); ++ } ++} ++ ++/* ++ * posix_cpu_thread_call - callback that gets triggered when a CPU is added. ++ * Here we can start up the necessary migration thread for the new CPU. ++ */ ++static int posix_cpu_thread_call(struct notifier_block *nfb, ++ unsigned long action, void *hcpu) ++{ ++ int cpu = (long)hcpu; ++ struct task_struct *p; ++ struct sched_param param; ++ ++ switch (action) { ++ case CPU_UP_PREPARE: ++ p = kthread_create(posix_cpu_timers_thread, hcpu, ++ "posixcputmr/%d",cpu); ++ if (IS_ERR(p)) ++ return NOTIFY_BAD; ++ p->flags |= PF_NOFREEZE; ++ kthread_bind(p, cpu); ++ /* Must be high prio to avoid getting starved */ ++ param.sched_priority = MAX_RT_PRIO-1; ++ sched_setscheduler(p, SCHED_FIFO, ¶m); ++ per_cpu(posix_timer_task,cpu) = p; ++ break; ++ case CPU_ONLINE: ++ /* Strictly unneccessary, as first user will wake it. */ ++ wake_up_process(per_cpu(posix_timer_task,cpu)); ++ break; ++#ifdef CONFIG_HOTPLUG_CPU ++ case CPU_UP_CANCELED: ++ /* Unbind it from offline cpu so it can run. Fall thru. */ ++ kthread_bind(per_cpu(posix_timer_task, cpu), ++ cpumask_any(cpu_online_mask)); ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++ case CPU_DEAD: ++ kthread_stop(per_cpu(posix_timer_task,cpu)); ++ per_cpu(posix_timer_task,cpu) = NULL; ++ break; ++#endif ++ } ++ return NOTIFY_OK; ++} ++ ++/* Register at highest priority so that task migration (migrate_all_tasks) ++ * happens before everything else. ++ */ ++static struct notifier_block posix_cpu_thread_notifier = { ++ .notifier_call = posix_cpu_thread_call, ++ .priority = 10 ++}; ++ ++static int __init posix_cpu_thread_init(void) ++{ ++ void *hcpu = (void *)(long)smp_processor_id(); ++ /* Start one for boot CPU. */ ++ unsigned long cpu; ++ ++ /* init the per-cpu posix_timer_tasklets */ ++ for_each_possible_cpu(cpu) ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu); ++ posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu); ++ register_cpu_notifier(&posix_cpu_thread_notifier); ++ return 0; ++} ++early_initcall(posix_cpu_thread_init); ++#else /* CONFIG_PREEMPT_RT_BASE */ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ __run_posix_cpu_timers(tsk); ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + /* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. +diff -Nur linux-4.4.28.orig/kernel/time/posix-timers.c linux-4.4.28/kernel/time/posix-timers.c +--- linux-4.4.28.orig/kernel/time/posix-timers.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/posix-timers.c 2016-11-01 21:26:58.800343826 +0100 +@@ -506,6 +506,7 @@ + static struct pid *good_sigevent(sigevent_t * event) + { + struct task_struct *rtn = current->group_leader; ++ int sig = event->sigev_signo; + + if ((event->sigev_notify & SIGEV_THREAD_ID ) && + (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) || +@@ -514,7 +515,8 @@ + return NULL; + + if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) && +- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) ++ (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) || ++ sig_kernel_coredump(sig))) + return NULL; + + return task_pid(rtn); +@@ -826,6 +828,20 @@ + return overrun; + } + ++/* ++ * Protected by RCU! ++ */ ++static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (kc->timer_set == common_timer_set) ++ hrtimer_wait_for_timer(&timr->it.real.timer); ++ else ++ /* FIXME: Whacky hack for posix-cpu-timers */ ++ schedule_timeout(1); ++#endif ++} ++ + /* Set a POSIX.1b interval timer. */ + /* timr->it_lock is taken. */ + static int +@@ -903,6 +919,7 @@ + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = clockid_to_kclock(timr->it_clock); + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -911,9 +928,12 @@ + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ timer_wait_for_callback(kc, timr); + rtn = NULL; // We already got the old time... ++ rcu_read_unlock(); + goto retry; + } ++ rcu_read_unlock(); + + if (old_setting && !error && + copy_to_user(old_setting, &old_spec, sizeof (old_spec))) +@@ -951,10 +971,15 @@ + if (!timer) + return -EINVAL; + ++ rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } ++ rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -980,8 +1005,18 @@ + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + ++ /* On RT we can race with a deletion */ ++ if (!timer->it_signal) { ++ unlock_timer(timer, flags); ++ return; ++ } ++ + if (timer_delete_hook(timer) == TIMER_RETRY) { ++ rcu_read_lock(); + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); +diff -Nur linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c +--- linux-4.4.28.orig/kernel/time/tick-broadcast-hrtimer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/tick-broadcast-hrtimer.c 2016-11-01 21:26:58.800343826 +0100 +@@ -106,5 +106,6 @@ + { + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + bctimer.function = bc_handler; ++ bctimer.irqsafe = true; + clockevents_register_device(&ce_broadcast_hrtimer); + } +diff -Nur linux-4.4.28.orig/kernel/time/tick-common.c linux-4.4.28/kernel/time/tick-common.c +--- linux-4.4.28.orig/kernel/time/tick-common.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/tick-common.c 2016-11-01 21:26:58.800343826 +0100 +@@ -79,13 +79,15 @@ + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -157,9 +159,9 @@ + ktime_t next; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); + +diff -Nur linux-4.4.28.orig/kernel/time/tick-sched.c linux-4.4.28/kernel/time/tick-sched.c +--- linux-4.4.28.orig/kernel/time/tick-sched.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/tick-sched.c 2016-11-01 21:26:58.800343826 +0100 +@@ -62,7 +62,8 @@ + return; + + /* Reevalute with jiffies_lock held */ +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 >= tick_period.tv64) { +@@ -85,10 +86,12 @@ + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return; + } +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -99,12 +102,14 @@ + { + ktime_t period; + +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update.tv64 == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return period; + } + +@@ -176,6 +181,11 @@ + return false; + } + ++ if (!arch_irq_work_has_interrupt()) { ++ trace_tick_stop(0, "missing irq work interrupt\n"); ++ return false; ++ } ++ + /* sched_clock_tick() needs us? */ + #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + /* +@@ -204,6 +214,7 @@ + + static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_work_func, ++ .flags = IRQ_WORK_HARD_IRQ, + }; + + /* +@@ -578,10 +589,10 @@ + + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + basemono = last_jiffies_update.tv64; + basejiff = jiffies; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + ts->last_jiffies = basejiff; + + if (rcu_needs_cpu(basemono, &next_rcu) || +@@ -753,14 +764,7 @@ + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10 && +- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { +- pr_warn("NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return false; + } + +@@ -1100,6 +1104,7 @@ + * Emulate tick processing via per-CPU hrtimers: + */ + hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ ts->sched_timer.irqsafe = 1; + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per cpu) */ +diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.c linux-4.4.28/kernel/time/timekeeping.c +--- linux-4.4.28.orig/kernel/time/timekeeping.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/timekeeping.c 2016-11-01 21:26:58.800343826 +0100 +@@ -2070,8 +2070,10 @@ + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + do_timer(ticks); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } +diff -Nur linux-4.4.28.orig/kernel/time/timekeeping.h linux-4.4.28/kernel/time/timekeeping.h +--- linux-4.4.28.orig/kernel/time/timekeeping.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/timekeeping.h 2016-11-01 21:26:58.800343826 +0100 +@@ -19,7 +19,8 @@ + extern void do_timer(unsigned long ticks); + extern void update_wall_time(void); + +-extern seqlock_t jiffies_lock; ++extern raw_spinlock_t jiffies_lock; ++extern seqcount_t jiffies_seq; + + #define CS_NAME_LEN 32 + +diff -Nur linux-4.4.28.orig/kernel/time/timer.c linux-4.4.28/kernel/time/timer.c +--- linux-4.4.28.orig/kernel/time/timer.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/time/timer.c 2016-11-01 21:26:58.804344090 +0100 +@@ -80,6 +80,9 @@ + struct tvec_base { + spinlock_t lock; + struct timer_list *running_timer; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ wait_queue_head_t wait_for_running_timer; ++#endif + unsigned long timer_jiffies; + unsigned long next_timer; + unsigned long active_timers; +@@ -777,6 +780,39 @@ + cpu_relax(); + } + } ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* ++ * We cannot do the below because we might be preempted and ++ * then the preempter would see NULL and loop forever. ++ */ ++ if (spin_trylock(&new->lock)) { ++ WRITE_ONCE(timer->flags, ++ (timer->flags & ~TIMER_BASEMASK) | new->cpu); ++ spin_unlock(&old->lock); ++ return new; ++ } ++ return old; ++} ++ ++#else ++static inline struct tvec_base *switch_timer_base(struct timer_list *timer, ++ struct tvec_base *old, ++ struct tvec_base *new) ++{ ++ /* See the comment in lock_timer_base() */ ++ timer->flags |= TIMER_MIGRATING; ++ ++ spin_unlock(&old->lock); ++ spin_lock(&new->lock); ++ WRITE_ONCE(timer->flags, ++ (timer->flags & ~TIMER_BASEMASK) | new->cpu); ++ return new; ++} ++#endif + + static inline int + __mod_timer(struct timer_list *timer, unsigned long expires, +@@ -807,16 +843,8 @@ + * handler yet has not finished. This also guarantees that + * the timer is serialized wrt itself. + */ +- if (likely(base->running_timer != timer)) { +- /* See the comment in lock_timer_base() */ +- timer->flags |= TIMER_MIGRATING; +- +- spin_unlock(&base->lock); +- base = new_base; +- spin_lock(&base->lock); +- WRITE_ONCE(timer->flags, +- (timer->flags & ~TIMER_BASEMASK) | base->cpu); +- } ++ if (likely(base->running_timer != timer)) ++ base = switch_timer_base(timer, base, new_base); + } + + timer->expires = expires; +@@ -1006,6 +1034,33 @@ + } + EXPORT_SYMBOL_GPL(add_timer_on); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Wait for a running timer ++ */ ++static void wait_for_running_timer(struct timer_list *timer) ++{ ++ struct tvec_base *base; ++ u32 tf = timer->flags; ++ ++ if (tf & TIMER_MIGRATING) ++ return; ++ ++ base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK); ++ wait_event(base->wait_for_running_timer, ++ base->running_timer != timer); ++} ++ ++# define wakeup_timer_waiters(b) wake_up_all(&(b)->wait_for_running_timer) ++#else ++static inline void wait_for_running_timer(struct timer_list *timer) ++{ ++ cpu_relax(); ++} ++ ++# define wakeup_timer_waiters(b) do { } while (0) ++#endif ++ + /** + * del_timer - deactive a timer. + * @timer: the timer to be deactivated +@@ -1063,7 +1118,7 @@ + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + /** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated +@@ -1123,7 +1178,7 @@ + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; +- cpu_relax(); ++ wait_for_running_timer(timer); + } + } + EXPORT_SYMBOL(del_timer_sync); +@@ -1248,16 +1303,18 @@ + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); ++ base->running_timer = NULL; + spin_lock_irq(&base->lock); + } + } + } +- base->running_timer = NULL; + spin_unlock_irq(&base->lock); ++ wakeup_timer_waiters(base); + } + + #ifdef CONFIG_NO_HZ_COMMON +@@ -1390,6 +1447,14 @@ + if (cpu_is_offline(smp_processor_id())) + return expires; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * On PREEMPT_RT we cannot sleep here. As a result we can't take ++ * the base lock to check when the next timer is pending and so ++ * we assume the next jiffy. ++ */ ++ return basem + TICK_NSEC; ++#endif + spin_lock(&base->lock); + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) +@@ -1416,13 +1481,13 @@ + + /* Note: this timer irq context must be accounted for as well. */ + account_process_tick(p, user_tick); ++ scheduler_tick(); + run_local_timers(); + rcu_check_callbacks(user_tick); +-#ifdef CONFIG_IRQ_WORK ++#if defined(CONFIG_IRQ_WORK) + if (in_irq()) + irq_work_tick(); + #endif +- scheduler_tick(); + run_posix_cpu_timers(p); + } + +@@ -1433,6 +1498,8 @@ + { + struct tvec_base *base = this_cpu_ptr(&tvec_bases); + ++ irq_work_tick_soft(); ++ + if (time_after_eq(jiffies, base->timer_jiffies)) + __run_timers(base); + } +@@ -1589,7 +1656,7 @@ + + BUG_ON(cpu_online(cpu)); + old_base = per_cpu_ptr(&tvec_bases, cpu); +- new_base = get_cpu_ptr(&tvec_bases); ++ new_base = get_local_ptr(&tvec_bases); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. +@@ -1613,7 +1680,7 @@ + + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); +- put_cpu_ptr(&tvec_bases); ++ put_local_ptr(&tvec_bases); + } + + static int timer_cpu_notify(struct notifier_block *self, +@@ -1645,6 +1712,9 @@ + + base->cpu = cpu; + spin_lock_init(&base->lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_waitqueue_head(&base->wait_for_running_timer); ++#endif + + base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; +diff -Nur linux-4.4.28.orig/kernel/trace/Kconfig linux-4.4.28/kernel/trace/Kconfig +--- linux-4.4.28.orig/kernel/trace/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/Kconfig 2016-11-01 21:26:58.804344090 +0100 +@@ -187,6 +187,24 @@ + enabled. This option and the preempt-off timing option can be + used together or separately.) + ++config INTERRUPT_OFF_HIST ++ bool "Interrupts-off Latency Histogram" ++ depends on IRQSOFF_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with interrupts disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If PREEMPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/irqsoff ++ + config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n +@@ -211,6 +229,24 @@ + enabled. This option and the irqs-off timing option can be + used together or separately.) + ++config PREEMPT_OFF_HIST ++ bool "Preemption-off Latency Histogram" ++ depends on PREEMPT_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the duration of time periods with preemption disabled. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff ++ ++ If INTERRUPT_OFF_HIST is also selected, additional histograms (one ++ per cpu) are generated that accumulate the duration of time periods ++ when both interrupts and preemption are disabled. The histogram data ++ will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/preemptoff ++ + config SCHED_TRACER + bool "Scheduling Latency Tracer" + select GENERIC_TRACER +@@ -221,6 +257,74 @@ + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + ++config WAKEUP_LATENCY_HIST ++ bool "Scheduling Latency Histogram" ++ depends on SCHED_TRACER ++ help ++ This option generates continuously updated histograms (one per cpu) ++ of the scheduling latency of the highest priority task. ++ The histograms are disabled by default. To enable them, write a ++ non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/wakeup ++ ++ Two different algorithms are used, one to determine the latency of ++ processes that exclusively use the highest priority of the system and ++ another one to determine the latency of processes that share the ++ highest system priority with other processes. The former is used to ++ improve hardware and system software, the latter to optimize the ++ priority design of a given system. The histogram data will be ++ located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup ++ ++ and ++ ++ /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ ++config MISSED_TIMER_OFFSETS_HIST ++ depends on HIGH_RES_TIMERS ++ select GENERIC_TRACER ++ bool "Missed Timer Offsets Histogram" ++ help ++ Generate a histogram of missed timer offsets in microseconds. The ++ histograms are disabled by default. To enable them, write a non-zero ++ number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets ++ ++ The histogram data will be located in the debug file system at ++ ++ /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets ++ ++ If both Scheduling Latency Histogram and Missed Timer Offsets ++ Histogram are selected, additional histogram data will be collected ++ that contain, in addition to the wakeup latency, the timer latency, in ++ case the wakeup was triggered by an expired timer. These histograms ++ are available in the ++ ++ /sys/kernel/debug/tracing/latency_hist/timerandwakeup ++ ++ directory. They reflect the apparent interrupt and scheduling latency ++ and are best suitable to determine the worst-case latency of a given ++ system. To enable these histograms, write a non-zero number to ++ ++ /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup ++ + config ENABLE_DEFAULT_TRACERS + bool "Trace process context switches and events" + depends on !GENERIC_TRACER +diff -Nur linux-4.4.28.orig/kernel/trace/latency_hist.c linux-4.4.28/kernel/trace/latency_hist.c +--- linux-4.4.28.orig/kernel/trace/latency_hist.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.4.28/kernel/trace/latency_hist.c 2016-11-01 21:26:58.804344090 +0100 +@@ -0,0 +1,1178 @@ ++/* ++ * kernel/trace/latency_hist.c ++ * ++ * Add support for histograms of preemption-off latency and ++ * interrupt-off latency and wakeup latency, it depends on ++ * Real-Time Preemption Support. ++ * ++ * Copyright (C) 2005 MontaVista Software, Inc. ++ * Yi Yang ++ * ++ * Converted to work with the new latency tracer. ++ * Copyright (C) 2008 Red Hat, Inc. ++ * Steven Rostedt ++ * ++ */ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "trace.h" ++#include ++ ++#define NSECS_PER_USECS 1000L ++ ++#define CREATE_TRACE_POINTS ++#include ++ ++enum { ++ IRQSOFF_LATENCY = 0, ++ PREEMPTOFF_LATENCY, ++ PREEMPTIRQSOFF_LATENCY, ++ WAKEUP_LATENCY, ++ WAKEUP_LATENCY_SHAREDPRIO, ++ MISSED_TIMER_OFFSETS, ++ TIMERANDWAKEUP_LATENCY, ++ MAX_LATENCY_TYPE, ++}; ++ ++#define MAX_ENTRY_NUM 10240 ++ ++struct hist_data { ++ atomic_t hist_mode; /* 0 log, 1 don't log */ ++ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ ++ long min_lat; ++ long max_lat; ++ unsigned long long below_hist_bound_samples; ++ unsigned long long above_hist_bound_samples; ++ long long accumulate_lat; ++ unsigned long long total_samples; ++ unsigned long long hist_array[MAX_ENTRY_NUM]; ++}; ++ ++struct enable_data { ++ int latency_type; ++ int enabled; ++}; ++ ++static char *latency_hist_dir_root = "latency_hist"; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, irqsoff_hist); ++static char *irqsoff_hist_dir = "irqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start); ++static DEFINE_PER_CPU(int, hist_irqsoff_counting); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++static DEFINE_PER_CPU(struct hist_data, preemptoff_hist); ++static char *preemptoff_hist_dir = "preemptoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start); ++static DEFINE_PER_CPU(int, hist_preemptoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist); ++static char *preemptirqsoff_hist_dir = "preemptirqsoff"; ++static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start); ++static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting); ++#endif ++ ++#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start); ++static struct enable_data preemptirqsoff_enabled_data = { ++ .latency_type = PREEMPTIRQSOFF_LATENCY, ++ .enabled = 0, ++}; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++struct maxlatproc_data { ++ char comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ char current_comm[FIELD_SIZEOF(struct task_struct, comm)]; ++ int pid; ++ int current_pid; ++ int prio; ++ int current_prio; ++ long latency; ++ long timeroffset; ++ cycle_t timestamp; ++}; ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist); ++static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio); ++static char *wakeup_latency_hist_dir = "wakeup"; ++static char *wakeup_latency_hist_dir_sharedprio = "sharedprio"; ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p); ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ bool preempt, struct task_struct *prev, struct task_struct *next); ++static notrace void probe_sched_migrate_task(void *, ++ struct task_struct *task, int cpu); ++static struct enable_data wakeup_latency_enabled_data = { ++ .latency_type = WAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc); ++static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio); ++static DEFINE_PER_CPU(struct task_struct *, wakeup_task); ++static DEFINE_PER_CPU(int, wakeup_sharedprio); ++static unsigned long wakeup_pid; ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets); ++static char *missed_timer_offsets_dir = "missed_timer_offsets"; ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long offset, struct task_struct *curr, struct task_struct *task); ++static struct enable_data missed_timer_offsets_enabled_data = { ++ .latency_type = MISSED_TIMER_OFFSETS, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc); ++static unsigned long missed_timer_offsets_pid; ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist); ++static char *timerandwakeup_latency_hist_dir = "timerandwakeup"; ++static struct enable_data timerandwakeup_enabled_data = { ++ .latency_type = TIMERANDWAKEUP_LATENCY, ++ .enabled = 0, ++}; ++static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); ++#endif ++ ++void notrace latency_hist(int latency_type, int cpu, long latency, ++ long timeroffset, cycle_t stop, ++ struct task_struct *p) ++{ ++ struct hist_data *my_hist; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ if (!cpu_possible(cpu) || latency_type < 0 || ++ latency_type >= MAX_LATENCY_TYPE) ++ return; ++ ++ switch (latency_type) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ my_hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ my_hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ my_hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ my_hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ my_hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ my_hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ ++ default: ++ return; ++ } ++ ++ latency += my_hist->offset; ++ ++ if (atomic_read(&my_hist->hist_mode) == 0) ++ return; ++ ++ if (latency < 0 || latency >= MAX_ENTRY_NUM) { ++ if (latency < 0) ++ my_hist->below_hist_bound_samples++; ++ else ++ my_hist->above_hist_bound_samples++; ++ } else ++ my_hist->hist_array[latency]++; ++ ++ if (unlikely(latency > my_hist->max_lat || ++ my_hist->min_lat == LONG_MAX)) { ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) { ++ strncpy(mp->comm, p->comm, sizeof(mp->comm)); ++ strncpy(mp->current_comm, current->comm, ++ sizeof(mp->current_comm)); ++ mp->pid = task_pid_nr(p); ++ mp->current_pid = task_pid_nr(current); ++ mp->prio = p->prio; ++ mp->current_prio = current->prio; ++ mp->latency = latency; ++ mp->timeroffset = timeroffset; ++ mp->timestamp = stop; ++ } ++#endif ++ my_hist->max_lat = latency; ++ } ++ if (unlikely(latency < my_hist->min_lat)) ++ my_hist->min_lat = latency; ++ my_hist->total_samples++; ++ my_hist->accumulate_lat += latency; ++} ++ ++static void *l_start(struct seq_file *m, loff_t *pos) ++{ ++ loff_t *index_ptr = NULL; ++ loff_t index = *pos; ++ struct hist_data *my_hist = m->private; ++ ++ if (index == 0) { ++ char minstr[32], avgstr[32], maxstr[32]; ++ ++ atomic_dec(&my_hist->hist_mode); ++ ++ if (likely(my_hist->total_samples)) { ++ long avg = (long) div64_s64(my_hist->accumulate_lat, ++ my_hist->total_samples); ++ snprintf(minstr, sizeof(minstr), "%ld", ++ my_hist->min_lat - my_hist->offset); ++ snprintf(avgstr, sizeof(avgstr), "%ld", ++ avg - my_hist->offset); ++ snprintf(maxstr, sizeof(maxstr), "%ld", ++ my_hist->max_lat - my_hist->offset); ++ } else { ++ strcpy(minstr, ""); ++ strcpy(avgstr, minstr); ++ strcpy(maxstr, minstr); ++ } ++ ++ seq_printf(m, "#Minimum latency: %s microseconds\n" ++ "#Average latency: %s microseconds\n" ++ "#Maximum latency: %s microseconds\n" ++ "#Total samples: %llu\n" ++ "#There are %llu samples lower than %ld" ++ " microseconds.\n" ++ "#There are %llu samples greater or equal" ++ " than %ld microseconds.\n" ++ "#usecs\t%16s\n", ++ minstr, avgstr, maxstr, ++ my_hist->total_samples, ++ my_hist->below_hist_bound_samples, ++ -my_hist->offset, ++ my_hist->above_hist_bound_samples, ++ MAX_ENTRY_NUM - my_hist->offset, ++ "samples"); ++ } ++ if (index < MAX_ENTRY_NUM) { ++ index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL); ++ if (index_ptr) ++ *index_ptr = index; ++ } ++ ++ return index_ptr; ++} ++ ++static void *l_next(struct seq_file *m, void *p, loff_t *pos) ++{ ++ loff_t *index_ptr = p; ++ struct hist_data *my_hist = m->private; ++ ++ if (++*pos >= MAX_ENTRY_NUM) { ++ atomic_inc(&my_hist->hist_mode); ++ return NULL; ++ } ++ *index_ptr = *pos; ++ return index_ptr; ++} ++ ++static void l_stop(struct seq_file *m, void *p) ++{ ++ kfree(p); ++} ++ ++static int l_show(struct seq_file *m, void *p) ++{ ++ int index = *(loff_t *) p; ++ struct hist_data *my_hist = m->private; ++ ++ seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset, ++ my_hist->hist_array[index]); ++ return 0; ++} ++ ++static const struct seq_operations latency_hist_seq_op = { ++ .start = l_start, ++ .next = l_next, ++ .stop = l_stop, ++ .show = l_show ++}; ++ ++static int latency_hist_open(struct inode *inode, struct file *file) ++{ ++ int ret; ++ ++ ret = seq_open(file, &latency_hist_seq_op); ++ if (!ret) { ++ struct seq_file *seq = file->private_data; ++ seq->private = inode->i_private; ++ } ++ return ret; ++} ++ ++static const struct file_operations latency_hist_fops = { ++ .open = latency_hist_open, ++ .read = seq_read, ++ .llseek = seq_lseek, ++ .release = seq_release, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static void clear_maxlatprocdata(struct maxlatproc_data *mp) ++{ ++ mp->comm[0] = mp->current_comm[0] = '\0'; ++ mp->prio = mp->current_prio = mp->pid = mp->current_pid = ++ mp->latency = mp->timeroffset = -1; ++ mp->timestamp = 0; ++} ++#endif ++ ++static void hist_reset(struct hist_data *hist) ++{ ++ atomic_dec(&hist->hist_mode); ++ ++ memset(hist->hist_array, 0, sizeof(hist->hist_array)); ++ hist->below_hist_bound_samples = 0ULL; ++ hist->above_hist_bound_samples = 0ULL; ++ hist->min_lat = LONG_MAX; ++ hist->max_lat = LONG_MIN; ++ hist->total_samples = 0ULL; ++ hist->accumulate_lat = 0LL; ++ ++ atomic_inc(&hist->hist_mode); ++} ++ ++static ssize_t ++latency_hist_reset(struct file *file, const char __user *a, ++ size_t size, loff_t *off) ++{ ++ int cpu; ++ struct hist_data *hist = NULL; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ struct maxlatproc_data *mp = NULL; ++#endif ++ off_t latency_type = (off_t) file->private_data; ++ ++ for_each_online_cpu(cpu) { ++ ++ switch (latency_type) { ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ case PREEMPTOFF_LATENCY: ++ hist = &per_cpu(preemptoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ case IRQSOFF_LATENCY: ++ hist = &per_cpu(irqsoff_hist, cpu); ++ break; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ hist = &per_cpu(preemptirqsoff_hist, cpu); ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ hist = &per_cpu(wakeup_latency_hist, cpu); ++ mp = &per_cpu(wakeup_maxlatproc, cpu); ++ break; ++ case WAKEUP_LATENCY_SHAREDPRIO: ++ hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu); ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu); ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ hist = &per_cpu(missed_timer_offsets, cpu); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu); ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ hist = &per_cpu(timerandwakeup_latency_hist, cpu); ++ mp = &per_cpu(timerandwakeup_maxlatproc, cpu); ++ break; ++#endif ++ } ++ ++ hist_reset(hist); ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ if (latency_type == WAKEUP_LATENCY || ++ latency_type == WAKEUP_LATENCY_SHAREDPRIO || ++ latency_type == MISSED_TIMER_OFFSETS || ++ latency_type == TIMERANDWAKEUP_LATENCY) ++ clear_maxlatprocdata(mp); ++#endif ++ } ++ ++ return size; ++} ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ int r; ++ unsigned long *this_pid = file->private_data; ++ ++ r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t do_pid(struct file *file, const char __user *ubuf, ++ size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ unsigned long pid; ++ unsigned long *this_pid = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = '\0'; ++ ++ if (kstrtoul(buf, 10, &pid)) ++ return -EINVAL; ++ ++ *this_pid = pid; ++ ++ return cnt; ++} ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static ssize_t ++show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ int r; ++ struct maxlatproc_data *mp = file->private_data; ++ int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8); ++ unsigned long long t; ++ unsigned long usecs, secs; ++ char *buf; ++ ++ if (mp->pid == -1 || mp->current_pid == -1) { ++ buf = "(none)\n"; ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, ++ strlen(buf)); ++ } ++ ++ buf = kmalloc(strmaxlen, GFP_KERNEL); ++ if (buf == NULL) ++ return -ENOMEM; ++ ++ t = ns2usecs(mp->timestamp); ++ usecs = do_div(t, USEC_PER_SEC); ++ secs = (unsigned long) t; ++ r = snprintf(buf, strmaxlen, ++ "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid, ++ MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm, ++ mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm, ++ secs, usecs); ++ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++ kfree(buf); ++ return r; ++} ++#endif ++ ++static ssize_t ++show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ struct enable_data *ed = file->private_data; ++ int r; ++ ++ r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled); ++ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); ++} ++ ++static ssize_t ++do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) ++{ ++ char buf[64]; ++ long enable; ++ struct enable_data *ed = file->private_data; ++ ++ if (cnt >= sizeof(buf)) ++ return -EINVAL; ++ ++ if (copy_from_user(&buf, ubuf, cnt)) ++ return -EFAULT; ++ ++ buf[cnt] = 0; ++ ++ if (kstrtoul(buf, 10, &enable)) ++ return -EINVAL; ++ ++ if ((enable && ed->enabled) || (!enable && !ed->enabled)) ++ return cnt; ++ ++ if (enable) { ++ int ret; ++ ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ ret = register_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_preemptirqsoff_hist " ++ "to trace_preemptirqsoff_hist\n"); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ ret = register_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup\n"); ++ return ret; ++ } ++ ret = register_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_start " ++ "to trace_sched_wakeup_new\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_wakeup_latency_hist_stop " ++ "to trace_sched_switch\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ return ret; ++ } ++ ret = register_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_sched_migrate_task " ++ "to trace_sched_migrate_task\n"); ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ return ret; ++ } ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ ret = register_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++ if (ret) { ++ pr_info("wakeup trace: Couldn't assign " ++ "probe_hrtimer_interrupt " ++ "to trace_hrtimer_interrupt\n"); ++ return ret; ++ } ++ break; ++#endif ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ case TIMERANDWAKEUP_LATENCY: ++ if (!wakeup_latency_enabled_data.enabled || ++ !missed_timer_offsets_enabled_data.enabled) ++ return -EINVAL; ++ break; ++#endif ++ default: ++ break; ++ } ++ } else { ++ switch (ed->latency_type) { ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ case PREEMPTIRQSOFF_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_preemptirqsoff_hist( ++ probe_preemptirqsoff_hist, NULL); ++ for_each_online_cpu(cpu) { ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ per_cpu(hist_irqsoff_counting, ++ cpu) = 0; ++#endif ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ per_cpu(hist_preemptoff_counting, ++ cpu) = 0; ++#endif ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ per_cpu(hist_preemptirqsoff_counting, ++ cpu) = 0; ++#endif ++ } ++ } ++ break; ++#endif ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ case WAKEUP_LATENCY: ++ { ++ int cpu; ++ ++ unregister_trace_sched_wakeup( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_wakeup_new( ++ probe_wakeup_latency_hist_start, NULL); ++ unregister_trace_sched_switch( ++ probe_wakeup_latency_hist_stop, NULL); ++ unregister_trace_sched_migrate_task( ++ probe_sched_migrate_task, NULL); ++ ++ for_each_online_cpu(cpu) { ++ per_cpu(wakeup_task, cpu) = NULL; ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } ++ } ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ case MISSED_TIMER_OFFSETS: ++ unregister_trace_hrtimer_interrupt( ++ probe_hrtimer_interrupt, NULL); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ timerandwakeup_enabled_data.enabled = 0; ++#endif ++ break; ++#endif ++ default: ++ break; ++ } ++ } ++ ed->enabled = enable; ++ return cnt; ++} ++ ++static const struct file_operations latency_hist_reset_fops = { ++ .open = tracing_open_generic, ++ .write = latency_hist_reset, ++}; ++ ++static const struct file_operations enable_fops = { ++ .open = tracing_open_generic, ++ .read = show_enable, ++ .write = do_enable, ++}; ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++static const struct file_operations pid_fops = { ++ .open = tracing_open_generic, ++ .read = show_pid, ++ .write = do_pid, ++}; ++ ++static const struct file_operations maxlatproc_fops = { ++ .open = tracing_open_generic, ++ .read = show_maxlatproc, ++}; ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++static notrace void probe_preemptirqsoff_hist(void *v, int reason, ++ int starthist) ++{ ++ int cpu = raw_smp_processor_id(); ++ int time_set = 0; ++ ++ if (starthist) { ++ cycle_t uninitialized_var(start); ++ ++ if (!preempt_count() && !irqs_disabled()) ++ return; ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_OFF || reason == TRACE_START) && ++ !per_cpu(hist_irqsoff_counting, cpu)) { ++ per_cpu(hist_irqsoff_counting, cpu) = 1; ++ start = ftrace_now(cpu); ++ time_set++; ++ per_cpu(hist_irqsoff_start, cpu) = start; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_OFF || reason == TRACE_START) && ++ !per_cpu(hist_preemptoff_counting, cpu)) { ++ per_cpu(hist_preemptoff_counting, cpu) = 1; ++ if (!(time_set++)) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptoff_start, cpu) = start; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if (per_cpu(hist_irqsoff_counting, cpu) && ++ per_cpu(hist_preemptoff_counting, cpu) && ++ !per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 1; ++ if (!time_set) ++ start = ftrace_now(cpu); ++ per_cpu(hist_preemptirqsoff_start, cpu) = start; ++ } ++#endif ++ } else { ++ cycle_t uninitialized_var(stop); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ if ((reason == IRQS_ON || reason == TRACE_STOP) && ++ per_cpu(hist_irqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_irqsoff_start, cpu); ++ ++ stop = ftrace_now(cpu); ++ time_set++; ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, ++ stop, NULL); ++ } ++ per_cpu(hist_irqsoff_counting, cpu) = 0; ++ } ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ if ((reason == PREEMPT_ON || reason == TRACE_STOP) && ++ per_cpu(hist_preemptoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptoff_start, cpu); ++ ++ if (!(time_set++)) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTOFF_LATENCY, cpu, latency, ++ 0, stop, NULL); ++ } ++ per_cpu(hist_preemptoff_counting, cpu) = 0; ++ } ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ if ((!per_cpu(hist_irqsoff_counting, cpu) || ++ !per_cpu(hist_preemptoff_counting, cpu)) && ++ per_cpu(hist_preemptirqsoff_counting, cpu)) { ++ cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu); ++ ++ if (!time_set) ++ stop = ftrace_now(cpu); ++ if (start) { ++ long latency = ((long) (stop - start)) / ++ NSECS_PER_USECS; ++ ++ latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, ++ latency, 0, stop, NULL); ++ } ++ per_cpu(hist_preemptirqsoff_counting, cpu) = 0; ++ } ++#endif ++ } ++} ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++static DEFINE_RAW_SPINLOCK(wakeup_lock); ++static notrace void probe_sched_migrate_task(void *v, struct task_struct *task, ++ int cpu) ++{ ++ int old_cpu = task_cpu(task); ++ ++ if (cpu != old_cpu) { ++ unsigned long flags; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, old_cpu); ++ if (task == cpu_wakeup_task) { ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, old_cpu) = NULL; ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task; ++ get_task_struct(cpu_wakeup_task); ++ } ++ ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++ } ++} ++ ++static notrace void probe_wakeup_latency_hist_start(void *v, ++ struct task_struct *p) ++{ ++ unsigned long flags; ++ struct task_struct *curr = current; ++ int cpu = task_cpu(p); ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (wakeup_pid) { ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ if (likely(wakeup_pid != task_pid_nr(p))) ++ goto out; ++ } else { ++ if (likely(!rt_task(p)) || ++ (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) || ++ p->prio > curr->prio) ++ goto out; ++ if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) || ++ p->prio == curr->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ } ++ ++ if (cpu_wakeup_task) ++ put_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p; ++ get_task_struct(cpu_wakeup_task); ++ cpu_wakeup_task->preempt_timestamp_hist = ++ ftrace_now(raw_smp_processor_id()); ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++ ++static notrace void probe_wakeup_latency_hist_stop(void *v, ++ bool preempt, struct task_struct *prev, struct task_struct *next) ++{ ++ unsigned long flags; ++ int cpu = task_cpu(next); ++ long latency; ++ cycle_t stop; ++ struct task_struct *cpu_wakeup_task; ++ ++ raw_spin_lock_irqsave(&wakeup_lock, flags); ++ ++ cpu_wakeup_task = per_cpu(wakeup_task, cpu); ++ ++ if (cpu_wakeup_task == NULL) ++ goto out; ++ ++ /* Already running? */ ++ if (unlikely(current == cpu_wakeup_task)) ++ goto out_reset; ++ ++ if (next != cpu_wakeup_task) { ++ if (next->prio < cpu_wakeup_task->prio) ++ goto out_reset; ++ ++ if (next->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ goto out; ++ } ++ ++ if (current->prio == cpu_wakeup_task->prio) ++ per_cpu(wakeup_sharedprio, cpu) = 1; ++ ++ /* ++ * The task we are waiting for is about to be switched to. ++ * Calculate latency and store it in histogram. ++ */ ++ stop = ftrace_now(raw_smp_processor_id()); ++ ++ latency = ((long) (stop - next->preempt_timestamp_hist)) / ++ NSECS_PER_USECS; ++ ++ if (per_cpu(wakeup_sharedprio, cpu)) { ++ latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, ++ next); ++ per_cpu(wakeup_sharedprio, cpu) = 0; ++ } else { ++ latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next); ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ if (timerandwakeup_enabled_data.enabled) { ++ latency_hist(TIMERANDWAKEUP_LATENCY, cpu, ++ next->timer_offset + latency, next->timer_offset, ++ stop, next); ++ } ++#endif ++ } ++ ++out_reset: ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ next->timer_offset = 0; ++#endif ++ put_task_struct(cpu_wakeup_task); ++ per_cpu(wakeup_task, cpu) = NULL; ++out: ++ raw_spin_unlock_irqrestore(&wakeup_lock, flags); ++} ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++static notrace void probe_hrtimer_interrupt(void *v, int cpu, ++ long long latency_ns, struct task_struct *curr, ++ struct task_struct *task) ++{ ++ if (latency_ns <= 0 && task != NULL && rt_task(task) && ++ (task->prio < curr->prio || ++ (task->prio == curr->prio && ++ !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { ++ long latency; ++ cycle_t now; ++ ++ if (missed_timer_offsets_pid) { ++ if (likely(missed_timer_offsets_pid != ++ task_pid_nr(task))) ++ return; ++ } ++ ++ now = ftrace_now(cpu); ++ latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); ++ latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, ++ task); ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ task->timer_offset = latency; ++#endif ++ } ++} ++#endif ++ ++static __init int latency_hist_init(void) ++{ ++ struct dentry *latency_hist_root = NULL; ++ struct dentry *dentry; ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ struct dentry *dentry_sharedprio; ++#endif ++ struct dentry *entry; ++ struct dentry *enable_root; ++ int i = 0; ++ struct hist_data *my_hist; ++ char name[64]; ++ char *cpufmt = "CPU%d"; ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ char *cpufmt_maxlatproc = "max_latency-CPU%d"; ++ struct maxlatproc_data *mp = NULL; ++#endif ++ ++ dentry = tracing_init_dentry(); ++ latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry); ++ enable_root = debugfs_create_dir("enable", latency_hist_root); ++ ++#ifdef CONFIG_INTERRUPT_OFF_HIST ++ dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(irqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(irqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#ifdef CONFIG_PREEMPT_OFF_HIST ++ dentry = debugfs_create_dir(preemptoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST) ++ dentry = debugfs_create_dir(preemptirqsoff_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); ++ my_hist = &per_cpu(preemptirqsoff_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); ++#endif ++ ++#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST) ++ entry = debugfs_create_file("preemptirqsoff", 0644, ++ enable_root, (void *)&preemptirqsoff_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_WAKEUP_LATENCY_HIST ++ dentry = debugfs_create_dir(wakeup_latency_hist_dir, ++ latency_hist_root); ++ dentry_sharedprio = debugfs_create_dir( ++ wakeup_latency_hist_dir_sharedprio, dentry); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(wakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, ++ &per_cpu(wakeup_latency_hist_sharedprio, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ ++ mp = &per_cpu(wakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ ++ mp = &per_cpu(wakeup_maxlatproc_sharedprio, i); ++ entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&wakeup_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)WAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("reset", 0644, dentry_sharedprio, ++ (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops); ++ entry = debugfs_create_file("wakeup", 0644, ++ enable_root, (void *)&wakeup_latency_enabled_data, ++ &enable_fops); ++#endif ++ ++#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST ++ dentry = debugfs_create_dir(missed_timer_offsets_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(missed_timer_offsets, i), &latency_hist_fops); ++ my_hist = &per_cpu(missed_timer_offsets, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(missed_timer_offsets_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("pid", 0644, dentry, ++ (void *)&missed_timer_offsets_pid, &pid_fops); ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops); ++ entry = debugfs_create_file("missed_timer_offsets", 0644, ++ enable_root, (void *)&missed_timer_offsets_enabled_data, ++ &enable_fops); ++#endif ++ ++#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \ ++ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) ++ dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir, ++ latency_hist_root); ++ for_each_possible_cpu(i) { ++ sprintf(name, cpufmt, i); ++ entry = debugfs_create_file(name, 0444, dentry, ++ &per_cpu(timerandwakeup_latency_hist, i), ++ &latency_hist_fops); ++ my_hist = &per_cpu(timerandwakeup_latency_hist, i); ++ atomic_set(&my_hist->hist_mode, 1); ++ my_hist->min_lat = LONG_MAX; ++ ++ sprintf(name, cpufmt_maxlatproc, i); ++ mp = &per_cpu(timerandwakeup_maxlatproc, i); ++ entry = debugfs_create_file(name, 0444, dentry, mp, ++ &maxlatproc_fops); ++ clear_maxlatprocdata(mp); ++ } ++ entry = debugfs_create_file("reset", 0644, dentry, ++ (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops); ++ entry = debugfs_create_file("timerandwakeup", 0644, ++ enable_root, (void *)&timerandwakeup_enabled_data, ++ &enable_fops); ++#endif ++ return 0; ++} ++ ++device_initcall(latency_hist_init); +diff -Nur linux-4.4.28.orig/kernel/trace/Makefile linux-4.4.28/kernel/trace/Makefile +--- linux-4.4.28.orig/kernel/trace/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/Makefile 2016-11-01 21:26:58.804344090 +0100 +@@ -40,6 +40,10 @@ + obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o + obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o + obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o ++obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o ++obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o ++obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o + obj-$(CONFIG_NOP_TRACER) += trace_nop.o + obj-$(CONFIG_STACK_TRACER) += trace_stack.o + obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o +diff -Nur linux-4.4.28.orig/kernel/trace/trace.c linux-4.4.28/kernel/trace/trace.c +--- linux-4.4.28.orig/kernel/trace/trace.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/trace.c 2016-11-01 21:26:58.808344343 +0100 +@@ -1652,6 +1652,7 @@ + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; ++ entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +@@ -1661,8 +1662,11 @@ + #endif + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | +- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -2555,14 +2559,17 @@ + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off \n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / delay \n" +- "# cmd pid ||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +@@ -2588,11 +2595,14 @@ + print_event_info(buf, m); + seq_puts(m, "# _-----=> irqs-off\n" + "# / _----=> need-resched\n" +- "# | / _---=> hardirq/softirq\n" +- "# || / _--=> preempt-depth\n" +- "# ||| / delay\n" +- "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n" +- "# | | | |||| | |\n"); ++ "# |/ _-----=> need-resched_lazy\n" ++ "# || / _---=> hardirq/softirq\n" ++ "# ||| / _--=> preempt-depth\n" ++ "# |||| / _-=> preempt-lazy-depth\n" ++ "# ||||| / _-=> migrate-disable \n" ++ "# |||||| / delay\n" ++ "# TASK-PID CPU# ||||||| TIMESTAMP FUNCTION\n" ++ "# | | | ||||||| | |\n"); + } + + void +diff -Nur linux-4.4.28.orig/kernel/trace/trace_events.c linux-4.4.28/kernel/trace/trace_events.c +--- linux-4.4.28.orig/kernel/trace/trace_events.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/trace_events.c 2016-11-01 21:26:58.808344343 +0100 +@@ -188,6 +188,8 @@ + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +@@ -244,6 +246,14 @@ + + local_save_flags(fbuffer->flags); + fbuffer->pc = preempt_count(); ++ /* ++ * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables ++ * preemption (adding one to the preempt_count). Since we are ++ * interested in the preempt_count at the time the tracepoint was ++ * hit, we need to subtract one to offset the increment. ++ */ ++ if (IS_ENABLED(CONFIG_PREEMPT)) ++ fbuffer->pc--; + fbuffer->trace_file = trace_file; + + fbuffer->event = +diff -Nur linux-4.4.28.orig/kernel/trace/trace.h linux-4.4.28/kernel/trace/trace.h +--- linux-4.4.28.orig/kernel/trace/trace.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/trace.h 2016-11-01 21:26:58.808344343 +0100 +@@ -117,6 +117,7 @@ + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler ++ * NEED_RESCHED_LAZY - lazy reschedule is requested + */ + enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, +@@ -125,6 +126,7 @@ + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x40, + }; + + #define TRACE_BUF_SIZE 1024 +diff -Nur linux-4.4.28.orig/kernel/trace/trace_irqsoff.c linux-4.4.28/kernel/trace/trace_irqsoff.c +--- linux-4.4.28.orig/kernel/trace/trace_irqsoff.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/trace_irqsoff.c 2016-11-01 21:26:58.808344343 +0100 +@@ -13,6 +13,7 @@ + #include + #include + #include ++#include + + #include "trace.h" + +@@ -424,11 +425,13 @@ + { + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist_rcuidle(TRACE_START, 1); + } + EXPORT_SYMBOL_GPL(start_critical_timings); + + void stop_critical_timings(void) + { ++ trace_preemptirqsoff_hist_rcuidle(TRACE_STOP, 0); + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -438,6 +441,7 @@ + #ifdef CONFIG_PROVE_LOCKING + void time_hardirqs_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist_rcuidle(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); + } +@@ -446,6 +450,7 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); ++ trace_preemptirqsoff_hist_rcuidle(IRQS_OFF, 1); + } + + #else /* !CONFIG_PROVE_LOCKING */ +@@ -471,6 +476,7 @@ + */ + void trace_hardirqs_on(void) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); + } +@@ -480,11 +486,13 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off); + + __visible void trace_hardirqs_on_caller(unsigned long caller_addr) + { ++ trace_preemptirqsoff_hist(IRQS_ON, 0); + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); + } +@@ -494,6 +502,7 @@ + { + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); ++ trace_preemptirqsoff_hist(IRQS_OFF, 1); + } + EXPORT_SYMBOL(trace_hardirqs_off_caller); + +@@ -503,12 +512,14 @@ + #ifdef CONFIG_PREEMPT_TRACER + void trace_preempt_on(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 0); + if (preempt_trace() && !irq_trace()) + stop_critical_timing(a0, a1); + } + + void trace_preempt_off(unsigned long a0, unsigned long a1) + { ++ trace_preemptirqsoff_hist(PREEMPT_ON, 1); + if (preempt_trace() && !irq_trace()) + start_critical_timing(a0, a1); + } +diff -Nur linux-4.4.28.orig/kernel/trace/trace_output.c linux-4.4.28/kernel/trace/trace_output.c +--- linux-4.4.28.orig/kernel/trace/trace_output.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/trace/trace_output.c 2016-11-01 21:26:58.808344343 +0100 +@@ -386,6 +386,7 @@ + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -413,6 +414,8 @@ + need_resched = '.'; + break; + } ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; + + hardsoft_irq = + (hardirq && softirq) ? 'H' : +@@ -420,14 +423,25 @@ + softirq ? 's' : + '.'; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ ++ if (entry->migrate_disable) ++ trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ trace_seq_putc(s, '.'); ++ + return !trace_seq_has_overflowed(s); + } + +diff -Nur linux-4.4.28.orig/kernel/user.c linux-4.4.28/kernel/user.c +--- linux-4.4.28.orig/kernel/user.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/user.c 2016-11-01 21:26:58.808344343 +0100 +@@ -161,11 +161,11 @@ + if (!up) + return; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) + free_user(up, flags); + else +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + + struct user_struct *alloc_uid(kuid_t uid) +diff -Nur linux-4.4.28.orig/kernel/watchdog.c linux-4.4.28/kernel/watchdog.c +--- linux-4.4.28.orig/kernel/watchdog.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/watchdog.c 2016-11-01 21:26:58.808344343 +0100 +@@ -299,6 +299,8 @@ + + #ifdef CONFIG_HARDLOCKUP_DETECTOR + ++static DEFINE_RAW_SPINLOCK(watchdog_output_lock); ++ + static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, +@@ -333,6 +335,13 @@ + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); ++ ++ raw_spin_lock(&watchdog_output_lock); + + pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + print_modules(); +@@ -350,8 +359,9 @@ + !test_and_set_bit(0, &hardlockup_allcpu_dumped)) + trigger_allbutself_cpu_backtrace(); + ++ raw_spin_unlock(&watchdog_output_lock); + if (hardlockup_panic) +- panic("Hard LOCKUP"); ++ nmi_panic(regs, "Hard LOCKUP"); + + __this_cpu_write(hard_watchdog_warn, true); + return; +@@ -497,6 +507,7 @@ + /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; ++ hrtimer->irqsafe = 1; + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); +diff -Nur linux-4.4.28.orig/kernel/workqueue.c linux-4.4.28/kernel/workqueue.c +--- linux-4.4.28.orig/kernel/workqueue.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/workqueue.c 2016-11-01 21:26:58.812344600 +0100 +@@ -48,6 +48,8 @@ + #include + #include + #include ++#include ++#include + + #include "workqueue_internal.h" + +@@ -121,11 +123,16 @@ + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * ++ * On RT we need the extra protection via rt_lock_idle_list() for ++ * the list manipulations against read access from ++ * wq_worker_sleeping(). All other places are nicely serialized via ++ * pool->lock. ++ * + * A: pool->attach_mutex protected. + * + * PL: wq_pool_mutex protected. + * +- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. ++ * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * +@@ -134,7 +141,7 @@ + * + * WQ: wq->mutex protected. + * +- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. ++ * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ +@@ -183,7 +190,7 @@ + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* +- * Destruction of pool is sched-RCU protected to allow dereferences ++ * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +@@ -212,7 +219,7 @@ + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue +- * itself is also sched-RCU protected so that the first pwq can be ++ * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; +@@ -331,6 +338,8 @@ + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + ++static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); ++ + static int worker_thread(void *__worker); + static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + +@@ -338,20 +347,20 @@ + #include + + #define assert_rcu_or_pool_mutex() \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU or wq_pool_mutex should be held") ++ "RCU or wq_pool_mutex should be held") + + #define assert_rcu_or_wq_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex), \ +- "sched RCU or wq->mutex should be held") ++ "RCU or wq->mutex should be held") + + #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex) && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU, wq->mutex or wq_pool_mutex should be held") ++ "RCU, wq->mutex or wq_pool_mutex should be held") + + #define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ +@@ -363,7 +372,7 @@ + * @pool: iteration cursor + * @pi: integer used for iteration + * +- * This must be called either with wq_pool_mutex held or sched RCU read ++ * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * +@@ -395,7 +404,7 @@ + * @pwq: iteration cursor + * @wq: the target workqueue + * +- * This must be called either with wq->mutex held or sched RCU read locked. ++ * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -407,6 +416,31 @@ + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct worker_pool *pool) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct worker_pool *pool) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct worker_pool *pool) { } ++static inline void sched_unlock_idle_list(struct worker_pool *pool) { } ++#else ++static inline void rt_lock_idle_list(struct worker_pool *pool) { } ++static inline void rt_unlock_idle_list(struct worker_pool *pool) { } ++static inline void sched_lock_idle_list(struct worker_pool *pool) ++{ ++ spin_lock_irq(&pool->lock); ++} ++static inline void sched_unlock_idle_list(struct worker_pool *pool) ++{ ++ spin_unlock_irq(&pool->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -557,7 +591,7 @@ + * @wq: the target workqueue + * @node: the node ID + * +- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU ++ * This must be called with any of wq_pool_mutex, wq->mutex or RCU + * read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. +@@ -701,8 +735,8 @@ + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read +- * access under sched-RCU read lock. As such, this function should be +- * called under wq_pool_mutex or with preemption disabled. ++ * access under RCU read lock. As such, this function should be ++ * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used +@@ -839,51 +873,44 @@ + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker = first_idle_worker(pool); ++ struct worker *worker; ++ ++ rt_lock_idle_list(pool); ++ ++ worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(pool); + } + + /** +- * wq_worker_waking_up - a worker is waking up +- * @task: task waking up +- * @cpu: CPU @task is waking up to ++ * wq_worker_running - a worker is running again ++ * @task: task returning from sleep + * +- * This function is called during try_to_wake_up() when a worker is +- * being awoken. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) ++ * This function is called when a worker returns from schedule() + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + +- if (!(worker->flags & WORKER_NOT_RUNNING)) { +- WARN_ON_ONCE(worker->pool->cpu != cpu); ++ if (!worker->sleeping) ++ return; ++ if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); +- } ++ worker->sleeping = 0; + } + + /** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep +- * @cpu: CPU in question, must be the current CPU number +- * +- * This function is called during schedule() when a busy worker is +- * going to sleep. Worker on the same cpu can be woken up by +- * returning pointer to its task. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) +- * +- * Return: +- * Worker task on @cpu to wake up, %NULL if none. ++ * This function is called from schedule() when a busy worker is ++ * going to sleep. + */ +-struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; ++ struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -892,29 +919,26 @@ + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + + pool = worker->pool; + +- /* this can only happen on the local cpu */ +- if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu)) +- return NULL; ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; ++ ++ worker->sleeping = 1; + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. +- * +- * NOT_RUNNING is clear. This means that we're bound to and +- * running on the local cpu w/ rq lock held and preemption +- * disabled, which in turn means that none else could be +- * manipulating idle_list, so dereferencing idle_list without pool +- * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && +- !list_empty(&pool->worklist)) +- to_wakeup = first_idle_worker(pool); +- return to_wakeup ? to_wakeup->task : NULL; ++ !list_empty(&pool->worklist)) { ++ sched_lock_idle_list(pool); ++ wake_up_worker(pool); ++ sched_unlock_idle_list(pool); ++ } + } + + /** +@@ -1108,12 +1132,12 @@ + { + if (pwq) { + /* +- * As both pwqs and pools are sched-RCU protected, the ++ * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- spin_lock_irq(&pwq->pool->lock); ++ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); +- spin_unlock_irq(&pwq->pool->lock); ++ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); + } + } + +@@ -1215,7 +1239,7 @@ + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_irq_save(*flags); ++ local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1234,6 +1258,7 @@ + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + ++ rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. +@@ -1272,14 +1297,16 @@ + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); ++ rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); + fail: +- local_irq_restore(*flags); ++ rcu_read_unlock(); ++ local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_relax(); ++ cpu_chill(); + return -EAGAIN; + } + +@@ -1348,7 +1375,7 @@ + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ +- WARN_ON_ONCE(!irqs_disabled()); ++ WARN_ON_ONCE_NONRT(!irqs_disabled()); + + debug_work_activate(work); + +@@ -1356,6 +1383,8 @@ + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; ++ ++ rcu_read_lock(); + retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); +@@ -1412,10 +1441,8 @@ + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + +- if (WARN_ON(!list_empty(&work->entry))) { +- spin_unlock(&pwq->pool->lock); +- return; +- } ++ if (WARN_ON(!list_empty(&work->entry))) ++ goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); +@@ -1431,7 +1458,9 @@ + + insert_work(pwq, work, worklist, work_flags); + ++out: + spin_unlock(&pwq->pool->lock); ++ rcu_read_unlock(); + } + + /** +@@ -1451,14 +1480,14 @@ + bool ret = false; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1525,14 +1554,14 @@ + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1567,7 +1596,7 @@ + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -1600,7 +1629,9 @@ + worker->last_active = jiffies; + + /* idle_list is LIFO */ ++ rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); ++ rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1633,7 +1664,9 @@ + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1799,7 +1832,9 @@ + pool->nr_workers--; + pool->nr_idle--; + ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } +@@ -2716,14 +2751,14 @@ + + might_sleep(); + +- local_irq_disable(); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { +- local_irq_enable(); ++ rcu_read_unlock(); + return false; + } + +- spin_lock(&pool->lock); ++ spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2750,10 +2785,11 @@ + else + lock_map_acquire_read(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); +- ++ rcu_read_unlock(); + return true; + already_gone: + spin_unlock_irq(&pool->lock); ++ rcu_read_unlock(); + return false; + } + +@@ -2840,7 +2876,7 @@ + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + + flush_work(work); + clear_work_data(work); +@@ -2895,10 +2931,10 @@ + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_irq_disable(); ++ local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_irq_enable(); ++ local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -2933,7 +2969,7 @@ + + set_work_pool_and_clear_pending(&dwork->work, + get_work_pool_id(&dwork->work)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(cancel_delayed_work); +@@ -3161,7 +3197,7 @@ + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * +- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU ++ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). +@@ -3215,8 +3251,8 @@ + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + +- /* sched-RCU protected to allow dereferences from get_work_pool() */ +- call_rcu_sched(&pool->rcu, rcu_free_pool); ++ /* RCU protected to allow dereferences from get_work_pool() */ ++ call_rcu(&pool->rcu, rcu_free_pool); + } + + /** +@@ -3323,14 +3359,14 @@ + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + +- call_rcu_sched(&pwq->rcu, rcu_free_pwq); ++ call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } + + /** +@@ -3983,7 +4019,7 @@ + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly +@@ -4076,7 +4112,8 @@ + struct pool_workqueue *pwq; + bool ret; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); ++ preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); +@@ -4087,7 +4124,8 @@ + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); +- rcu_read_unlock_sched(); ++ preempt_enable(); ++ rcu_read_unlock(); + + return ret; + } +@@ -4113,15 +4151,15 @@ + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + +- local_irq_save(flags); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock(&pool->lock); ++ spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock(&pool->lock); ++ spin_unlock_irqrestore(&pool->lock, flags); + } +- local_irq_restore(flags); ++ rcu_read_unlock(); + + return ret; + } +@@ -4310,7 +4348,7 @@ + unsigned long flags; + int pi; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + +@@ -4361,7 +4399,7 @@ + spin_unlock_irqrestore(&pool->lock, flags); + } + +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + + /* +@@ -4722,16 +4760,16 @@ + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ +- rcu_read_lock_sched(); ++ rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + goto out_unlock; + } + } +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + out_unlock: + mutex_unlock(&wq_pool_mutex); +@@ -4921,7 +4959,8 @@ + const char *delim = ""; + int node, written = 0; + +- rcu_read_lock_sched(); ++ get_online_cpus(); ++ rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, +@@ -4929,7 +4968,8 @@ + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); ++ put_online_cpus(); + + return written; + } +diff -Nur linux-4.4.28.orig/kernel/workqueue_internal.h linux-4.4.28/kernel/workqueue_internal.h +--- linux-4.4.28.orig/kernel/workqueue_internal.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/kernel/workqueue_internal.h 2016-11-01 21:26:58.812344600 +0100 +@@ -43,6 +43,7 @@ + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ ++ int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task +@@ -68,7 +69,7 @@ + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); + + #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ +diff -Nur linux-4.4.28.orig/lib/debugobjects.c linux-4.4.28/lib/debugobjects.c +--- linux-4.4.28.orig/lib/debugobjects.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/debugobjects.c 2016-11-01 21:26:58.812344600 +0100 +@@ -309,7 +309,10 @@ + struct debug_obj *obj; + unsigned long flags; + +- fill_pool(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (preempt_count() == 0 && !irqs_disabled()) ++#endif ++ fill_pool(); + + db = get_bucket((unsigned long) addr); + +diff -Nur linux-4.4.28.orig/lib/idr.c linux-4.4.28/lib/idr.c +--- linux-4.4.28.orig/lib/idr.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/idr.c 2016-11-01 21:26:58.812344600 +0100 +@@ -30,6 +30,7 @@ + #include + #include + #include ++#include + + #define MAX_IDR_SHIFT (sizeof(int) * 8 - 1) + #define MAX_IDR_BIT (1U << MAX_IDR_SHIFT) +@@ -45,6 +46,37 @@ + static DEFINE_PER_CPU(int, idr_preload_cnt); + static DEFINE_SPINLOCK(simple_ida_lock); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static DEFINE_LOCAL_IRQ_LOCK(idr_lock); ++ ++static inline void idr_preload_lock(void) ++{ ++ local_lock(idr_lock); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ local_unlock(idr_lock); ++} ++ ++void idr_preload_end(void) ++{ ++ idr_preload_unlock(); ++} ++EXPORT_SYMBOL(idr_preload_end); ++#else ++static inline void idr_preload_lock(void) ++{ ++ preempt_disable(); ++} ++ ++static inline void idr_preload_unlock(void) ++{ ++ preempt_enable(); ++} ++#endif ++ ++ + /* the maximum ID which can be allocated given idr->layers */ + static int idr_max(int layers) + { +@@ -115,14 +147,14 @@ + * context. See idr_preload() for details. + */ + if (!in_interrupt()) { +- preempt_disable(); ++ idr_preload_lock(); + new = __this_cpu_read(idr_preload_head); + if (new) { + __this_cpu_write(idr_preload_head, new->ary[0]); + __this_cpu_dec(idr_preload_cnt); + new->ary[0] = NULL; + } +- preempt_enable(); ++ idr_preload_unlock(); + if (new) + return new; + } +@@ -366,7 +398,6 @@ + idr_mark_full(pa, id); + } + +- + /** + * idr_preload - preload for idr_alloc() + * @gfp_mask: allocation mask to use for preloading +@@ -401,7 +432,7 @@ + WARN_ON_ONCE(in_interrupt()); + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); + +- preempt_disable(); ++ idr_preload_lock(); + + /* + * idr_alloc() is likely to succeed w/o full idr_layer buffer and +@@ -413,9 +444,9 @@ + while (__this_cpu_read(idr_preload_cnt) < MAX_IDR_FREE) { + struct idr_layer *new; + +- preempt_enable(); ++ idr_preload_unlock(); + new = kmem_cache_zalloc(idr_layer_cache, gfp_mask); +- preempt_disable(); ++ idr_preload_lock(); + if (!new) + break; + +diff -Nur linux-4.4.28.orig/lib/Kconfig linux-4.4.28/lib/Kconfig +--- linux-4.4.28.orig/lib/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/Kconfig 2016-11-01 21:26:58.812344600 +0100 +@@ -397,6 +397,7 @@ + + config CPUMASK_OFFSTACK + bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS ++ depends on !PREEMPT_RT_FULL + help + Use dynamic allocation for cpumask_var_t, instead of putting + them on the stack. This is a bit more expensive, but avoids +diff -Nur linux-4.4.28.orig/lib/locking-selftest.c linux-4.4.28/lib/locking-selftest.c +--- linux-4.4.28.orig/lib/locking-selftest.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/locking-selftest.c 2016-11-01 21:26:58.816344864 +0100 +@@ -590,6 +590,8 @@ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) + +@@ -605,9 +607,12 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Enabling hardirqs with a softirq-safe lock held: + */ +@@ -640,6 +645,8 @@ + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -663,6 +670,8 @@ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) + +@@ -678,6 +687,8 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -709,6 +720,8 @@ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) + +@@ -724,6 +737,8 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -757,6 +772,8 @@ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) + +@@ -772,10 +789,14 @@ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock irq inversion. + * +@@ -838,6 +859,10 @@ + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -876,6 +901,8 @@ + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ +@@ -1858,6 +1885,7 @@ + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -1870,6 +1898,28 @@ + + DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); + // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); ++#else ++ /* On -rt, we only do hardirq context test for raw spinlock */ ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); ++#endif + + ww_tests(); + +diff -Nur linux-4.4.28.orig/lib/percpu_ida.c linux-4.4.28/lib/percpu_ida.c +--- linux-4.4.28.orig/lib/percpu_ida.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/percpu_ida.c 2016-11-01 21:26:58.816344864 +0100 +@@ -26,6 +26,9 @@ + #include + #include + #include ++#include ++ ++static DEFINE_LOCAL_IRQ_LOCK(irq_off_lock); + + struct percpu_ida_cpu { + /* +@@ -148,13 +151,13 @@ + unsigned long flags; + int tag; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + /* Fastpath */ + tag = alloc_local_tag(tags); + if (likely(tag >= 0)) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return tag; + } + +@@ -173,6 +176,7 @@ + + if (!tags->nr_free) + alloc_global_tags(pool, tags); ++ + if (!tags->nr_free) + steal_tags(pool, tags); + +@@ -184,7 +188,7 @@ + } + + spin_unlock(&pool->lock); +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + + if (tag >= 0 || state == TASK_RUNNING) + break; +@@ -196,7 +200,7 @@ + + schedule(); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + } + if (state != TASK_RUNNING) +@@ -221,7 +225,7 @@ + + BUG_ON(tag >= pool->nr_tags); + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + tags = this_cpu_ptr(pool->tag_cpu); + + spin_lock(&tags->lock); +@@ -253,7 +257,7 @@ + spin_unlock(&pool->lock); + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + } + EXPORT_SYMBOL_GPL(percpu_ida_free); + +@@ -345,7 +349,7 @@ + struct percpu_ida_cpu *remote; + unsigned cpu, i, err = 0; + +- local_irq_save(flags); ++ local_lock_irqsave(irq_off_lock, flags); + for_each_possible_cpu(cpu) { + remote = per_cpu_ptr(pool->tag_cpu, cpu); + spin_lock(&remote->lock); +@@ -367,7 +371,7 @@ + } + spin_unlock(&pool->lock); + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(irq_off_lock, flags); + return err; + } + EXPORT_SYMBOL_GPL(percpu_ida_for_each_free); +diff -Nur linux-4.4.28.orig/lib/radix-tree.c linux-4.4.28/lib/radix-tree.c +--- linux-4.4.28.orig/lib/radix-tree.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/radix-tree.c 2016-11-01 21:26:58.816344864 +0100 +@@ -196,13 +196,14 @@ + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = this_cpu_ptr(&radix_tree_preloads); ++ rtp = &get_cpu_var(radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes; + rtp->nodes = ret->private_data; + ret->private_data = NULL; + rtp->nr--; + } ++ put_cpu_var(radix_tree_preloads); + /* + * Update the allocation stack trace as this is more useful + * for debugging. +@@ -242,6 +243,7 @@ + call_rcu(&node->rcu_head, radix_tree_node_rcu_free); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Load up this CPU's radix_tree_node buffer with sufficient objects to + * ensure that the addition of a single element in the tree cannot fail. On +@@ -310,6 +312,7 @@ + return 0; + } + EXPORT_SYMBOL(radix_tree_maybe_preload); ++#endif + + /* + * Return the maximum key which can be store into a +diff -Nur linux-4.4.28.orig/lib/rbtree.c linux-4.4.28/lib/rbtree.c +--- linux-4.4.28.orig/lib/rbtree.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/rbtree.c 2016-11-01 21:26:58.816344864 +0100 +@@ -23,6 +23,7 @@ + + #include + #include ++#include + + /* + * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree +@@ -590,3 +591,13 @@ + return rb_left_deepest_node(root->rb_node); + } + EXPORT_SYMBOL(rb_first_postorder); ++ ++void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, ++ struct rb_node **rb_link) ++{ ++ node->__rb_parent_color = (unsigned long)parent; ++ node->rb_left = node->rb_right = NULL; ++ ++ rcu_assign_pointer(*rb_link, node); ++} ++EXPORT_SYMBOL(rb_link_node_rcu); +diff -Nur linux-4.4.28.orig/lib/scatterlist.c linux-4.4.28/lib/scatterlist.c +--- linux-4.4.28.orig/lib/scatterlist.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/scatterlist.c 2016-11-01 21:26:58.816344864 +0100 +@@ -620,7 +620,7 @@ + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON_ONCE(preemptible()); ++ WARN_ON_ONCE(!pagefault_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); +@@ -664,7 +664,7 @@ + if (!sg_miter_skip(&miter, skip)) + return false; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; +@@ -681,7 +681,7 @@ + + sg_miter_stop(&miter); + +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return offset; + } + EXPORT_SYMBOL(sg_copy_buffer); +diff -Nur linux-4.4.28.orig/lib/smp_processor_id.c linux-4.4.28/lib/smp_processor_id.c +--- linux-4.4.28.orig/lib/smp_processor_id.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/lib/smp_processor_id.c 2016-11-01 21:26:58.816344864 +0100 +@@ -39,8 +39,9 @@ + if (!printk_ratelimit()) + goto out_enable; + +- printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", +- what1, what2, preempt_count() - 1, current->comm, current->pid); ++ printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x %08x] code: %s/%d\n", ++ what1, what2, preempt_count() - 1, __migrate_disabled(current), ++ current->comm, current->pid); + + print_symbol("caller is %s\n", (long)__builtin_return_address(0)); + dump_stack(); +diff -Nur linux-4.4.28.orig/Makefile linux-4.4.28/Makefile +--- linux-4.4.28.orig/Makefile 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/Makefile 2016-11-01 21:26:56.688207681 +0100 +@@ -394,7 +394,7 @@ + KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ + -fno-strict-aliasing -fno-common \ + -Werror-implicit-function-declaration \ +- -Wno-format-security \ ++ -Wno-format-security -fno-PIE \ + -std=gnu89 + + KBUILD_AFLAGS_KERNEL := +@@ -783,6 +783,9 @@ + # Prohibit date/time macros, which would make the build non-deterministic + KBUILD_CFLAGS += $(call cc-option,-Werror=date-time) + ++# enforce correct pointer usage ++KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) ++ + # use the deterministic mode of AR if available + KBUILD_ARFLAGS := $(call ar-option,D) + +diff -Nur linux-4.4.28.orig/mm/backing-dev.c linux-4.4.28/mm/backing-dev.c +--- linux-4.4.28.orig/mm/backing-dev.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/backing-dev.c 2016-11-01 21:26:58.816344864 +0100 +@@ -457,9 +457,9 @@ + { + unsigned long flags; + +- local_irq_save(flags); ++ local_irq_save_nort(flags); + if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + return; + } + +diff -Nur linux-4.4.28.orig/mm/compaction.c linux-4.4.28/mm/compaction.c +--- linux-4.4.28.orig/mm/compaction.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/compaction.c 2016-11-01 21:26:58.816344864 +0100 +@@ -1430,10 +1430,12 @@ + cc->migrate_pfn & ~((1UL << cc->order) - 1); + + if (cc->last_migrated_pfn < current_block_start) { +- cpu = get_cpu(); ++ cpu = get_cpu_light(); ++ local_lock_irq(swapvec_lock); + lru_add_drain_cpu(cpu); ++ local_unlock_irq(swapvec_lock); + drain_local_pages(zone); +- put_cpu(); ++ put_cpu_light(); + /* No more flushing until we migrate again */ + cc->last_migrated_pfn = 0; + } +diff -Nur linux-4.4.28.orig/mm/filemap.c linux-4.4.28/mm/filemap.c +--- linux-4.4.28.orig/mm/filemap.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/filemap.c 2016-11-01 21:29:56.667809032 +0100 +@@ -144,9 +144,12 @@ + * node->private_list is protected by + * mapping->tree_lock. + */ +- if (!list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, +- &node->private_list); ++ if (!list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, ++ &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + } + return 0; + } +@@ -218,7 +221,9 @@ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; +- list_lru_add(&workingset_shadow_nodes, &node->private_list); ++ local_lock(workingset_shadow_lock); ++ list_lru_add(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); + } + } + +diff -Nur linux-4.4.28.orig/mm/highmem.c linux-4.4.28/mm/highmem.c +--- linux-4.4.28.orig/mm/highmem.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/highmem.c 2016-11-01 21:26:58.820345117 +0100 +@@ -29,10 +29,11 @@ + #include + #include + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + DEFINE_PER_CPU(int, __kmap_atomic_idx); + #endif ++#endif + + /* + * Virtual_count is not a pure "count". +@@ -107,8 +108,9 @@ + unsigned long totalhigh_pages __read_mostly; + EXPORT_SYMBOL(totalhigh_pages); + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); ++#endif + + unsigned int nr_free_highpages (void) + { +diff -Nur linux-4.4.28.orig/mm/Kconfig linux-4.4.28/mm/Kconfig +--- linux-4.4.28.orig/mm/Kconfig 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/Kconfig 2016-11-01 21:26:58.816344864 +0100 +@@ -392,7 +392,7 @@ + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE ++ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + select COMPACTION + help + Transparent Hugepages allows the kernel to use huge pages and +diff -Nur linux-4.4.28.orig/mm/memcontrol.c linux-4.4.28/mm/memcontrol.c +--- linux-4.4.28.orig/mm/memcontrol.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/memcontrol.c 2016-11-01 21:26:58.820345117 +0100 +@@ -67,6 +67,8 @@ + #include + #include + #include ++#include ++ + #include "slab.h" + + #include +@@ -87,6 +89,7 @@ + #define do_swap_account 0 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(event_lock); + static const char * const mem_cgroup_stat_names[] = { + "cache", + "rss", +@@ -1922,14 +1925,17 @@ + */ + static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages) + { +- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); ++ struct memcg_stock_pcp *stock; ++ int cpu = get_cpu_light(); ++ ++ stock = &per_cpu(memcg_stock, cpu); + + if (stock->cached != memcg) { /* reset if necessary */ + drain_stock(stock); + stock->cached = memcg; + } + stock->nr_pages += nr_pages; +- put_cpu_var(memcg_stock); ++ put_cpu_light(); + } + + /* +@@ -1945,7 +1951,7 @@ + return; + /* Notify other cpus that system-wide "drain" is running */ + get_online_cpus(); +- curcpu = get_cpu(); ++ curcpu = get_cpu_light(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; +@@ -1962,7 +1968,7 @@ + schedule_work_on(cpu, &stock->work); + } + } +- put_cpu(); ++ put_cpu_light(); + put_online_cpus(); + mutex_unlock(&percpu_charge_mutex); + } +@@ -4700,12 +4706,12 @@ + + ret = 0; + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(to, page, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, -nr_pages); + memcg_check_events(from, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + out_unlock: + unlock_page(page); + out: +@@ -5495,10 +5501,10 @@ + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + } + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(memcg, page, nr_pages); + memcg_check_events(memcg, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + + if (do_swap_account && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; +@@ -5554,14 +5560,14 @@ + memcg_oom_recover(memcg); + } + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file); + __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge); + __this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout); + __this_cpu_add(memcg->stat->nr_page_events, nr_pages); + memcg_check_events(memcg, dummy_page); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_pages); +@@ -5753,6 +5759,7 @@ + { + struct mem_cgroup *memcg, *swap_memcg; + unsigned short oldid; ++ unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); +@@ -5793,12 +5800,16 @@ + * important here to have the interrupts disabled because it is the + * only synchronisation we have for udpating the per-CPU variables. + */ ++ local_lock_irqsave(event_lock, flags); ++#ifndef CONFIG_PREEMPT_RT_BASE + VM_BUG_ON(!irqs_disabled()); ++#endif + mem_cgroup_charge_statistics(memcg, page, -1); + memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); ++ local_unlock_irqrestore(event_lock, flags); + } + + /** +diff -Nur linux-4.4.28.orig/mm/mmu_context.c linux-4.4.28/mm/mmu_context.c +--- linux-4.4.28.orig/mm/mmu_context.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/mmu_context.c 2016-11-01 21:26:58.820345117 +0100 +@@ -23,6 +23,7 @@ + struct task_struct *tsk = current; + + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + if (active_mm != mm) { + atomic_inc(&mm->mm_count); +@@ -30,6 +31,7 @@ + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + #ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); +diff -Nur linux-4.4.28.orig/mm/page_alloc.c linux-4.4.28/mm/page_alloc.c +--- linux-4.4.28.orig/mm/page_alloc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/page_alloc.c 2016-11-01 21:26:58.824345373 +0100 +@@ -60,6 +60,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -264,6 +265,18 @@ + EXPORT_SYMBOL(nr_online_nodes); + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pa_lock); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define cpu_lock_irqsave(cpu, flags) \ ++ local_lock_irqsave_on(pa_lock, flags, cpu) ++# define cpu_unlock_irqrestore(cpu, flags) \ ++ local_unlock_irqrestore_on(pa_lock, flags, cpu) ++#else ++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) ++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) ++#endif ++ + int page_group_by_mobility_disabled __read_mostly; + + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +@@ -786,7 +799,7 @@ + } + + /* +- * Frees a number of pages from the PCP lists ++ * Frees a number of pages which have been collected from the pcp lists. + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * +@@ -797,18 +810,53 @@ + * pinned" detection logic. + */ + static void free_pcppages_bulk(struct zone *zone, int count, +- struct per_cpu_pages *pcp) ++ struct list_head *list) + { +- int migratetype = 0; +- int batch_free = 0; + int to_free = count; + unsigned long nr_scanned; ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + +- spin_lock(&zone->lock); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + ++ while (!list_empty(list)) { ++ struct page *page = list_first_entry(list, struct page, lru); ++ int mt; /* migratetype of the to-be-freed page */ ++ ++ /* must delete as __free_one_page list manipulates */ ++ list_del(&page->lru); ++ ++ mt = get_pcppage_migratetype(page); ++ /* MIGRATE_ISOLATE page should not go to pcplists */ ++ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); ++ /* Pageblock could have been isolated meanwhile */ ++ if (unlikely(has_isolate_pageblock(zone))) ++ mt = get_pageblock_migratetype(page); ++ ++ __free_one_page(page, page_to_pfn(page), zone, 0, mt); ++ trace_mm_page_pcpu_drain(page, 0, mt); ++ to_free--; ++ } ++ WARN_ON(to_free != 0); ++ spin_unlock_irqrestore(&zone->lock, flags); ++} ++ ++/* ++ * Moves a number of pages from the PCP lists to free list which ++ * is freed outside of the locked region. ++ * ++ * Assumes all pages on list are in same zone, and of same order. ++ * count is the number of pages to free. ++ */ ++static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src, ++ struct list_head *dst) ++{ ++ int migratetype = 0; ++ int batch_free = 0; ++ + while (to_free) { + struct page *page; + struct list_head *list; +@@ -824,7 +872,7 @@ + batch_free++; + if (++migratetype == MIGRATE_PCPTYPES) + migratetype = 0; +- list = &pcp->lists[migratetype]; ++ list = &src->lists[migratetype]; + } while (list_empty(list)); + + /* This is the only non-empty list. Free them all. */ +@@ -832,24 +880,12 @@ + batch_free = to_free; + + do { +- int mt; /* migratetype of the to-be-freed page */ +- +- page = list_entry(list->prev, struct page, lru); +- /* must delete as __free_one_page list manipulates */ ++ page = list_last_entry(list, struct page, lru); + list_del(&page->lru); + +- mt = get_pcppage_migratetype(page); +- /* MIGRATE_ISOLATE page should not go to pcplists */ +- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); +- /* Pageblock could have been isolated meanwhile */ +- if (unlikely(has_isolate_pageblock(zone))) +- mt = get_pageblock_migratetype(page); +- +- __free_one_page(page, page_to_pfn(page), zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); ++ list_add(&page->lru, dst); + } while (--to_free && --batch_free && !list_empty(list)); + } +- spin_unlock(&zone->lock); + } + + static void free_one_page(struct zone *zone, +@@ -858,7 +894,9 @@ + int migratetype) + { + unsigned long nr_scanned; +- spin_lock(&zone->lock); ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); + nr_scanned = zone_page_state(zone, NR_PAGES_SCANNED); + if (nr_scanned) + __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); +@@ -868,7 +906,7 @@ + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype); +- spin_unlock(&zone->lock); ++ spin_unlock_irqrestore(&zone->lock, flags); + } + + static int free_tail_pages_check(struct page *head_page, struct page *page) +@@ -1019,10 +1057,10 @@ + return; + + migratetype = get_pfnblock_migratetype(page, pfn); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_events(PGFREE, 1 << order); + free_one_page(page_zone(page), page, pfn, order, migratetype); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + static void __init __free_pages_boot_core(struct page *page, +@@ -1879,16 +1917,18 @@ + void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) + { + unsigned long flags; ++ LIST_HEAD(dst); + int to_drain, batch; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) { +- free_pcppages_bulk(zone, to_drain, pcp); ++ isolate_pcp_pages(to_drain, pcp, &dst); + pcp->count -= to_drain; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, to_drain, &dst); + } + #endif + +@@ -1904,16 +1944,21 @@ + unsigned long flags; + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); ++ int count; + +- local_irq_save(flags); ++ cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +- if (pcp->count) { +- free_pcppages_bulk(zone, pcp->count, pcp); ++ count = pcp->count; ++ if (count) { ++ isolate_pcp_pages(count, pcp, &dst); + pcp->count = 0; + } +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); ++ if (count) ++ free_pcppages_bulk(zone, count, &dst); + } + + /* +@@ -1999,8 +2044,17 @@ + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages, + zone, 1); ++#else ++ for_each_cpu(cpu, &cpus_with_pcps) { ++ if (zone) ++ drain_pages_zone(cpu, zone); ++ else ++ drain_pages(cpu); ++ } ++#endif + } + + #ifdef CONFIG_HIBERNATION +@@ -2056,7 +2110,7 @@ + + migratetype = get_pfnblock_migratetype(page, pfn); + set_pcppage_migratetype(page, migratetype); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_event(PGFREE); + + /* +@@ -2082,12 +2136,17 @@ + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- free_pcppages_bulk(zone, batch, pcp); ++ LIST_HEAD(dst); ++ ++ isolate_pcp_pages(batch, pcp, &dst); + pcp->count -= batch; ++ local_unlock_irqrestore(pa_lock, flags); ++ free_pcppages_bulk(zone, batch, &dst); ++ return; + } + + out: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + /* +@@ -2222,7 +2281,7 @@ + struct per_cpu_pages *pcp; + struct list_head *list; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + if (list_empty(list)) { +@@ -2254,7 +2313,7 @@ + */ + WARN_ON_ONCE(order > 1); + } +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + + page = NULL; + if (alloc_flags & ALLOC_HARDER) { +@@ -2264,11 +2323,13 @@ + } + if (!page) + page = __rmqueue(zone, order, migratetype, gfp_flags); +- spin_unlock(&zone->lock); +- if (!page) ++ if (!page) { ++ spin_unlock(&zone->lock); + goto failed; ++ } + __mod_zone_freepage_state(zone, -(1 << order), + get_pcppage_migratetype(page)); ++ spin_unlock(&zone->lock); + } + + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); +@@ -2278,13 +2339,13 @@ + + __count_zone_vm_events(PGALLOC, zone, 1 << order); + zone_statistics(preferred_zone, zone, gfp_flags); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + VM_BUG_ON_PAGE(bad_range(zone, page), page); + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -5950,6 +6011,7 @@ + void __init page_alloc_init(void) + { + hotcpu_notifier(page_alloc_cpu_notify, 0); ++ local_irq_lock_init(pa_lock); + } + + /* +@@ -6844,7 +6906,7 @@ + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); +@@ -6853,7 +6915,7 @@ + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + #ifdef CONFIG_MEMORY_HOTREMOVE +diff -Nur linux-4.4.28.orig/mm/slab.h linux-4.4.28/mm/slab.h +--- linux-4.4.28.orig/mm/slab.h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/slab.h 2016-11-01 21:26:58.824345373 +0100 +@@ -324,7 +324,11 @@ + * The slab lists for all objects. + */ + struct kmem_cache_node { ++#ifdef CONFIG_SLUB ++ raw_spinlock_t list_lock; ++#else + spinlock_t list_lock; ++#endif + + #ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ +diff -Nur linux-4.4.28.orig/mm/slub.c linux-4.4.28/mm/slub.c +--- linux-4.4.28.orig/mm/slub.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/slub.c 2016-11-01 21:26:58.828345638 +0100 +@@ -1075,7 +1075,7 @@ + void *object = head; + int cnt = 0; + +- spin_lock_irqsave(&n->list_lock, *flags); ++ raw_spin_lock_irqsave(&n->list_lock, *flags); + slab_lock(page); + + if (!check_slab(s, page)) +@@ -1136,7 +1136,7 @@ + + fail: + slab_unlock(page); +- spin_unlock_irqrestore(&n->list_lock, *flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, *flags); + slab_fix(s, "Object at 0x%p not freed", object); + return NULL; + } +@@ -1263,6 +1263,12 @@ + + #endif /* CONFIG_SLUB_DEBUG */ + ++struct slub_free_list { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); ++ + /* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. +@@ -1399,10 +1405,17 @@ + gfp_t alloc_gfp; + void *start, *p; + int idx, order; ++ bool enableirqs = false; + + flags &= gfp_allowed_mask; + + if (gfpflags_allow_blocking(flags)) ++ enableirqs = true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (system_state == SYSTEM_RUNNING) ++ enableirqs = true; ++#endif ++ if (enableirqs) + local_irq_enable(); + + flags |= s->allocflags; +@@ -1473,7 +1486,7 @@ + page->frozen = 1; + + out: +- if (gfpflags_allow_blocking(flags)) ++ if (enableirqs) + local_irq_disable(); + if (!page) + return NULL; +@@ -1529,6 +1542,16 @@ + __free_kmem_pages(page, order); + } + ++static void free_delayed(struct list_head *h) ++{ ++ while(!list_empty(h)) { ++ struct page *page = list_first_entry(h, struct page, lru); ++ ++ list_del(&page->lru); ++ __free_slab(page->slab_cache, page); ++ } ++} ++ + #define need_reserve_slab_rcu \ + (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head)) + +@@ -1560,6 +1583,12 @@ + } + + call_rcu(head, rcu_free_slab); ++ } else if (irqs_disabled()) { ++ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); ++ ++ raw_spin_lock(&f->lock); ++ list_add(&page->lru, &f->list); ++ raw_spin_unlock(&f->lock); + } else + __free_slab(s, page); + } +@@ -1673,7 +1702,7 @@ + if (!n || !n->nr_partial) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t; + +@@ -1698,7 +1727,7 @@ + break; + + } +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return object; + } + +@@ -1944,7 +1973,7 @@ + * that acquire_slab() will see a slab page that + * is frozen + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +@@ -1955,7 +1984,7 @@ + * slabs from diagnostic functions will not see + * any frozen slabs. + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } + +@@ -1990,7 +2019,7 @@ + goto redo; + + if (lock) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); +@@ -2022,10 +2051,10 @@ + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + n = n2; +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + + do { +@@ -2054,7 +2083,7 @@ + } + + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; +@@ -2093,14 +2122,21 @@ + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { ++ struct slub_free_list *f; + unsigned long flags; ++ LIST_HEAD(tofree); + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + oldpage = NULL; + pobjects = 0; + pages = 0; +@@ -2172,7 +2208,22 @@ + + static void flush_all(struct kmem_cache *s) + { ++ LIST_HEAD(tofree); ++ int cpu; ++ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); ++ for_each_online_cpu(cpu) { ++ struct slub_free_list *f; ++ ++ if (!has_cpu_slab(cpu, s)) ++ continue; ++ ++ f = &per_cpu(slub_free_list, cpu); ++ raw_spin_lock_irq(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock_irq(&f->lock); ++ free_delayed(&tofree); ++ } + } + + /* +@@ -2208,10 +2259,10 @@ + unsigned long x = 0; + struct page *page; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return x; + } + #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +@@ -2349,8 +2400,10 @@ + * already disabled (which is the case for bulk allocation). + */ + static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +- unsigned long addr, struct kmem_cache_cpu *c) ++ unsigned long addr, struct kmem_cache_cpu *c, ++ struct list_head *to_free) + { ++ struct slub_free_list *f; + void *freelist; + struct page *page; + +@@ -2410,6 +2463,13 @@ + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); ++ ++out: ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, to_free); ++ raw_spin_unlock(&f->lock); ++ + return freelist; + + new_slab: +@@ -2441,7 +2501,7 @@ + deactivate_slab(s, page, get_freepointer(s, freelist)); + c->page = NULL; + c->freelist = NULL; +- return freelist; ++ goto out; + } + + /* +@@ -2453,6 +2513,7 @@ + { + void *p; + unsigned long flags; ++ LIST_HEAD(tofree); + + local_irq_save(flags); + #ifdef CONFIG_PREEMPT +@@ -2464,8 +2525,9 @@ + c = this_cpu_ptr(s->cpu_slab); + #endif + +- p = ___slab_alloc(s, gfpflags, node, addr, c); ++ p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree); + local_irq_restore(flags); ++ free_delayed(&tofree); + return p; + } + +@@ -2652,7 +2714,7 @@ + + do { + if (unlikely(n)) { +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; +@@ -2684,7 +2746,7 @@ + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + } + } +@@ -2726,7 +2788,7 @@ + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return; + + slab_empty: +@@ -2741,7 +2803,7 @@ + remove_full(s, n, page); + } + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); + } +@@ -2913,6 +2975,7 @@ + void **p) + { + struct kmem_cache_cpu *c; ++ LIST_HEAD(to_free); + int i; + + /* memcg and kmem_cache debug support */ +@@ -2936,7 +2999,7 @@ + * of re-populating per CPU c->freelist + */ + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, +- _RET_IP_, c); ++ _RET_IP_, c, &to_free); + if (unlikely(!p[i])) + goto error; + +@@ -2948,6 +3011,7 @@ + } + c->tid = next_tid(c->tid); + local_irq_enable(); ++ free_delayed(&to_free); + + /* Clear memory outside IRQ disabled fastpath loop */ + if (unlikely(flags & __GFP_ZERO)) { +@@ -3095,7 +3159,7 @@ + init_kmem_cache_node(struct kmem_cache_node *n) + { + n->nr_partial = 0; +- spin_lock_init(&n->list_lock); ++ raw_spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); + #ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); +@@ -3677,7 +3741,7 @@ + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. +@@ -3708,7 +3772,7 @@ + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, lru) +@@ -3884,6 +3948,12 @@ + { + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; ++ int cpu; ++ ++ for_each_possible_cpu(cpu) { ++ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); ++ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); ++ } + + if (debug_guardpage_minorder()) + slub_max_order = 0; +@@ -4127,7 +4197,7 @@ + struct page *page; + unsigned long flags; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, lru) { + validate_slab_slab(s, page, map); +@@ -4149,7 +4219,7 @@ + s->name, count, atomic_long_read(&n->nr_slabs)); + + out: +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return count; + } + +@@ -4337,12 +4407,12 @@ + if (!atomic_long_read(&n->nr_slabs)) + continue; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + process_slab(&t, s, page, alloc, map); + list_for_each_entry(page, &n->full, lru) + process_slab(&t, s, page, alloc, map); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { +diff -Nur linux-4.4.28.orig/mm/swap.c linux-4.4.28/mm/swap.c +--- linux-4.4.28.orig/mm/swap.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/swap.c 2016-11-01 21:26:58.828345638 +0100 +@@ -31,6 +31,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -46,6 +47,9 @@ + static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); + static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); + ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); ++ + /* + * This path almost never happens for VM activity - pages are normally + * freed via pagevecs. But it gets used by networking. +@@ -481,11 +485,11 @@ + unsigned long flags; + + page_cache_get(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = this_cpu_ptr(&lru_rotate_pvecs); + if (!pagevec_add(pvec, page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -536,12 +540,13 @@ + void activate_page(struct page *page) + { + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ activate_page_pvecs); + + page_cache_get(page); + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -567,7 +572,7 @@ + + static void __lru_cache_activate_page(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + int i; + + /* +@@ -589,7 +594,7 @@ + } + } + +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /* +@@ -630,13 +635,13 @@ + + static void __lru_cache_add(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + + page_cache_get(page); + if (!pagevec_space(pvec)) + __pagevec_lru_add(pvec); + pagevec_add(pvec, page); +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /** +@@ -816,9 +821,15 @@ + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ local_lock_irqsave_on(rotate_lock, flags, cpu); ++ pagevec_move_tail(pvec); ++ local_unlock_irqrestore_on(rotate_lock, flags, cpu); ++#else ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); ++#endif + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -846,26 +857,47 @@ + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_file_pvecs); + + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); +- put_cpu_var(lru_deactivate_file_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); + } + } + + void lru_add_drain(void) + { +- lru_add_drain_cpu(get_cpu()); +- put_cpu(); ++ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); ++ local_unlock_cpu(swapvec_lock); + } + ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ local_lock_on(swapvec_lock, cpu); ++ lru_add_drain_cpu(cpu); ++ local_unlock_on(swapvec_lock, cpu); ++} ++ ++#else ++ + static void lru_add_drain_per_cpu(struct work_struct *dummy) + { + lru_add_drain(); + } + + static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); ++ ++ INIT_WORK(work, lru_add_drain_per_cpu); ++ schedule_work_on(cpu, work); ++ cpumask_set_cpu(cpu, has_work); ++} ++#endif + + void lru_add_drain_all(void) + { +@@ -878,20 +910,17 @@ + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { +- struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); +- + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || +- need_activate_page_drain(cpu)) { +- INIT_WORK(work, lru_add_drain_per_cpu); +- schedule_work_on(cpu, work); +- cpumask_set_cpu(cpu, &has_work); +- } ++ need_activate_page_drain(cpu)) ++ remote_lru_add_drain(cpu, &has_work); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); ++#endif + + put_online_cpus(); + mutex_unlock(&lock); +diff -Nur linux-4.4.28.orig/mm/truncate.c linux-4.4.28/mm/truncate.c +--- linux-4.4.28.orig/mm/truncate.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/truncate.c 2016-11-01 21:26:58.828345638 +0100 +@@ -56,8 +56,11 @@ + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && +- !list_empty(&node->private_list)) +- list_lru_del(&workingset_shadow_nodes, &node->private_list); ++ !list_empty(&node->private_list)) { ++ local_lock(workingset_shadow_lock); ++ list_lru_del(&__workingset_shadow_nodes, &node->private_list); ++ local_unlock(workingset_shadow_lock); ++ } + __radix_tree_delete_node(&mapping->page_tree, node); + unlock: + spin_unlock_irq(&mapping->tree_lock); +diff -Nur linux-4.4.28.orig/mm/vmalloc.c linux-4.4.28/mm/vmalloc.c +--- linux-4.4.28.orig/mm/vmalloc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/vmalloc.c 2016-11-01 21:26:58.828345638 +0100 +@@ -821,7 +821,7 @@ + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + void *vaddr; + + node = numa_node_id(); +@@ -864,11 +864,12 @@ + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vaddr; + } +@@ -937,6 +938,7 @@ + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; ++ int cpu; + + BUG_ON(offset_in_page(size)); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -951,7 +953,8 @@ + order = get_order(size); + + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + +@@ -974,7 +977,7 @@ + break; + } + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ +diff -Nur linux-4.4.28.orig/mm/vmstat.c linux-4.4.28/mm/vmstat.c +--- linux-4.4.28.orig/mm/vmstat.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/vmstat.c 2016-11-01 21:26:58.828345638 +0100 +@@ -226,6 +226,7 @@ + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -235,6 +236,7 @@ + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -267,6 +269,7 @@ + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -275,6 +278,7 @@ + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +@@ -289,6 +293,7 @@ + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -297,6 +302,7 @@ + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) +diff -Nur linux-4.4.28.orig/mm/workingset.c linux-4.4.28/mm/workingset.c +--- linux-4.4.28.orig/mm/workingset.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/workingset.c 2016-11-01 21:26:58.832345891 +0100 +@@ -264,7 +264,8 @@ + * point where they would still be useful. + */ + +-struct list_lru workingset_shadow_nodes; ++struct list_lru __workingset_shadow_nodes; ++DEFINE_LOCAL_IRQ_LOCK(workingset_shadow_lock); + + static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +@@ -274,9 +275,9 @@ + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); +- local_irq_enable(); ++ local_lock_irq(workingset_shadow_lock); ++ shadow_nodes = list_lru_shrink_count(&__workingset_shadow_nodes, sc); ++ local_unlock_irq(workingset_shadow_lock); + + pages = node_present_pages(sc->nid); + /* +@@ -361,9 +362,9 @@ + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; + out: +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + cond_resched(); +- local_irq_disable(); ++ local_lock_irq(workingset_shadow_lock); + spin_lock(lru_lock); + return ret; + } +@@ -374,10 +375,10 @@ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ +- local_irq_disable(); +- ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc, ++ local_lock_irq(workingset_shadow_lock); ++ ret = list_lru_shrink_walk(&__workingset_shadow_nodes, sc, + shadow_lru_isolate, NULL); +- local_irq_enable(); ++ local_unlock_irq(workingset_shadow_lock); + return ret; + } + +@@ -398,7 +399,7 @@ + { + int ret; + +- ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); ++ ret = list_lru_init_key(&__workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); +@@ -406,7 +407,7 @@ + goto err_list_lru; + return 0; + err_list_lru: +- list_lru_destroy(&workingset_shadow_nodes); ++ list_lru_destroy(&__workingset_shadow_nodes); + err: + return ret; + } +diff -Nur linux-4.4.28.orig/mm/zsmalloc.c linux-4.4.28/mm/zsmalloc.c +--- linux-4.4.28.orig/mm/zsmalloc.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/mm/zsmalloc.c 2016-11-01 21:26:58.832345891 +0100 +@@ -64,6 +64,7 @@ + #include + #include + #include ++#include + + /* + * This must be power of 2 and greater than of equal to sizeof(link_free). +@@ -403,6 +404,7 @@ + + /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ + static DEFINE_PER_CPU(struct mapping_area, zs_map_area); ++static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); + + static int is_first_page(struct page *page) + { +@@ -1289,7 +1291,7 @@ + class = pool->size_class[class_idx]; + off = obj_idx_to_offset(page, obj_idx, class->size); + +- area = &get_cpu_var(zs_map_area); ++ area = &get_locked_var(zs_map_area_lock, zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ +@@ -1342,7 +1344,7 @@ + + __zs_unmap_object(area, pages, off, class->size); + } +- put_cpu_var(zs_map_area); ++ put_locked_var(zs_map_area_lock, zs_map_area); + unpin_tag(handle); + } + EXPORT_SYMBOL_GPL(zs_unmap_object); +diff -Nur linux-4.4.28.orig/net/core/dev.c linux-4.4.28/net/core/dev.c +--- linux-4.4.28.orig/net/core/dev.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/core/dev.c 2016-11-01 21:26:58.836346147 +0100 +@@ -186,6 +186,7 @@ + static DEFINE_HASHTABLE(napi_hash, 8); + + static seqcount_t devnet_rename_seq; ++static DEFINE_MUTEX(devnet_rename_mutex); + + static inline void dev_base_seq_inc(struct net *net) + { +@@ -207,14 +208,14 @@ + static inline void rps_lock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_lock(&sd->input_pkt_queue.lock); ++ raw_spin_lock(&sd->input_pkt_queue.raw_lock); + #endif + } + + static inline void rps_unlock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_unlock(&sd->input_pkt_queue.lock); ++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + #endif + } + +@@ -884,7 +885,8 @@ + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { +- cond_resched(); ++ mutex_lock(&devnet_rename_mutex); ++ mutex_unlock(&devnet_rename_mutex); + goto retry; + } + +@@ -1153,20 +1155,17 @@ + if (dev->flags & IFF_UP) + return -EBUSY; + +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + +- if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { +- write_seqcount_end(&devnet_rename_seq); +- return 0; +- } ++ if (strncmp(newname, dev->name, IFNAMSIZ) == 0) ++ goto outunlock; + + memcpy(oldname, dev->name, IFNAMSIZ); + + err = dev_get_valid_name(net, dev, newname); +- if (err < 0) { +- write_seqcount_end(&devnet_rename_seq); +- return err; +- } ++ if (err < 0) ++ goto outunlock; + + if (oldname[0] && !strchr(oldname, '%')) + netdev_info(dev, "renamed from %s\n", oldname); +@@ -1179,11 +1178,12 @@ + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +- write_seqcount_end(&devnet_rename_seq); +- return ret; ++ err = ret; ++ goto outunlock; + } + +- write_seqcount_end(&devnet_rename_seq); ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); + + netdev_adjacent_rename_links(dev, oldname); + +@@ -1204,7 +1204,8 @@ + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { + err = ret; +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +@@ -1217,6 +1218,11 @@ + } + + return err; ++ ++outunlock: ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); ++ return err; + } + + /** +@@ -2246,6 +2252,7 @@ + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + void __netif_schedule(struct Qdisc *q) +@@ -2327,6 +2334,7 @@ + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__dev_kfree_skb_irq); + +@@ -2883,7 +2891,11 @@ + * This permits __QDISC___STATE_RUNNING owner to get the lock more + * often and dequeue packets faster. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ contended = true; ++#else + contended = qdisc_is_running(q); ++#endif + if (unlikely(contended)) + spin_lock(&q->busylock); + +@@ -2943,9 +2955,44 @@ + #define skb_update_prio(skb) + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++static inline int xmit_rec_read(void) ++{ ++ return current->xmit_recursion; ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ current->xmit_recursion++; ++} ++ ++static inline void xmit_rec_dec(void) ++{ ++ current->xmit_recursion--; ++} ++ ++#else ++ + DEFINE_PER_CPU(int, xmit_recursion); + EXPORT_SYMBOL(xmit_recursion); + ++static inline int xmit_rec_read(void) ++{ ++ return __this_cpu_read(xmit_recursion); ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ __this_cpu_inc(xmit_recursion); ++} ++ ++static inline void xmit_rec_dec(void) ++{ ++ __this_cpu_dec(xmit_recursion); ++} ++#endif ++ + #define RECURSION_LIMIT 10 + + /** +@@ -3138,7 +3185,7 @@ + + if (txq->xmit_lock_owner != cpu) { + +- if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) ++ if (xmit_rec_read() > RECURSION_LIMIT) + goto recursion_alert; + + skb = validate_xmit_skb(skb, dev); +@@ -3148,9 +3195,9 @@ + HARD_TX_LOCK(dev, txq, cpu); + + if (!netif_xmit_stopped(txq)) { +- __this_cpu_inc(xmit_recursion); ++ xmit_rec_inc(); + skb = dev_hard_start_xmit(skb, dev, txq, &rc); +- __this_cpu_dec(xmit_recursion); ++ xmit_rec_dec(); + if (dev_xmit_complete(rc)) { + HARD_TX_UNLOCK(dev, txq); + goto out; +@@ -3524,6 +3571,7 @@ + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -3542,7 +3590,7 @@ + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -3552,13 +3600,13 @@ + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); +- preempt_enable(); ++ migrate_enable(); + } else + #endif + { + unsigned int qtail; +- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); +- put_cpu(); ++ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); ++ put_cpu_light(); + } + return ret; + } +@@ -3592,16 +3640,44 @@ + + trace_netif_rx_ni_entry(skb); + +- preempt_disable(); ++ local_bh_disable(); + err = netif_rx_internal(skb); +- if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ local_bh_enable(); + + return err; + } + EXPORT_SYMBOL(netif_rx_ni); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * RT runs ksoftirqd as a real time thread and the root_lock is a ++ * "sleeping spinlock". If the trylock fails then we can go into an ++ * infinite loop when ksoftirqd preempted the task which actually ++ * holds the lock, because we requeue q and raise NET_TX softirq ++ * causing ksoftirqd to loop forever. ++ * ++ * It's safe to use spin_lock on RT here as softirqs run in thread ++ * context and cannot deadlock against the thread which is holding ++ * root_lock. ++ * ++ * On !RT the trylock might fail, but there we bail out from the ++ * softirq loop after 10 attempts which we can't do on RT. And the ++ * task holding root_lock cannot be preempted, so the only downside of ++ * that trylock is that we need 10 loops to decide that we should have ++ * given up in the first one :) ++ */ ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ return 1; ++} ++#else ++static inline int take_root_lock(spinlock_t *lock) ++{ ++ return spin_trylock(lock); ++} ++#endif ++ + static void net_tx_action(struct softirq_action *h) + { + struct softnet_data *sd = this_cpu_ptr(&softnet_data); +@@ -3643,7 +3719,7 @@ + head = head->next_sched; + + root_lock = qdisc_lock(q); +- if (spin_trylock(root_lock)) { ++ if (take_root_lock(root_lock)) { + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); +@@ -4065,7 +4141,7 @@ + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->input_pkt_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } +@@ -4074,10 +4150,13 @@ + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->process_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } ++ ++ if (!skb_queue_empty(&sd->tofree_queue)) ++ raise_softirq_irqoff(NET_RX_SOFTIRQ); + } + + static int napi_gro_complete(struct sk_buff *skb) +@@ -4531,6 +4610,7 @@ + sd->rps_ipi_list = NULL; + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { +@@ -4544,6 +4624,7 @@ + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) +@@ -4625,6 +4706,7 @@ + local_irq_save(flags); + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + +@@ -4901,7 +4983,7 @@ + list_splice_tail(&repoll, &list); + list_splice(&list, &sd->poll_list); + if (!list_empty(&sd->poll_list)) +- __raise_softirq_irqoff(NET_RX_SOFTIRQ); ++ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); + + net_rps_action_and_irq_enable(sd); + } +@@ -7234,7 +7316,7 @@ + void synchronize_net(void) + { + might_sleep(); +- if (rtnl_is_locked()) ++ if (rtnl_is_locked() && !IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) + synchronize_rcu_expedited(); + else + synchronize_rcu(); +@@ -7475,16 +7557,20 @@ + + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Process offline CPU's input_pkt_queue */ + while ((skb = __skb_dequeue(&oldsd->process_queue))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } +- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { ++ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return NOTIFY_OK; + } +@@ -7786,8 +7872,9 @@ + for_each_possible_cpu(i) { + struct softnet_data *sd = &per_cpu(softnet_data, i); + +- skb_queue_head_init(&sd->input_pkt_queue); +- skb_queue_head_init(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->input_pkt_queue); ++ skb_queue_head_init_raw(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->tofree_queue); + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue_tailp = &sd->output_queue; + #ifdef CONFIG_RPS +diff -Nur linux-4.4.28.orig/net/core/skbuff.c linux-4.4.28/net/core/skbuff.c +--- linux-4.4.28.orig/net/core/skbuff.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/core/skbuff.c 2016-11-01 21:26:58.836346147 +0100 +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -351,6 +352,8 @@ + + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct page_frag_cache, napi_alloc_cache); ++static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); ++static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); + + static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +@@ -358,10 +361,10 @@ + unsigned long flags; + void *data; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, fragsz, gfp_mask); +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + return data; + } + +@@ -380,9 +383,13 @@ + + static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +- struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct page_frag_cache *nc; ++ void *data; + +- return __alloc_page_frag(nc, fragsz, gfp_mask); ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ data = __alloc_page_frag(nc, fragsz, gfp_mask); ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ return data; + } + + void *napi_alloc_frag(unsigned int fragsz) +@@ -429,13 +436,13 @@ + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, len, gfp_mask); + pfmemalloc = nc->pfmemalloc; + +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + + if (unlikely(!data)) + return NULL; +@@ -476,9 +483,10 @@ + struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + gfp_t gfp_mask) + { +- struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct page_frag_cache *nc; + struct sk_buff *skb; + void *data; ++ bool pfmemalloc; + + len += NET_SKB_PAD + NET_IP_ALIGN; + +@@ -496,7 +504,11 @@ + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + data = __alloc_page_frag(nc, len, gfp_mask); ++ pfmemalloc = nc->pfmemalloc; ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ + if (unlikely(!data)) + return NULL; + +@@ -507,7 +519,7 @@ + } + + /* use OR instead of assignment to avoid clearing of bits in mask */ +- if (nc->pfmemalloc) ++ if (pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +diff -Nur linux-4.4.28.orig/net/core/sock.c linux-4.4.28/net/core/sock.c +--- linux-4.4.28.orig/net/core/sock.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/core/sock.c 2016-11-01 21:26:58.836346147 +0100 +@@ -2435,12 +2435,11 @@ + if (sk->sk_lock.owned) + __lock_sock(sk); + sk->sk_lock.owned = 1; +- spin_unlock(&sk->sk_lock.slock); ++ spin_unlock_bh(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); +- local_bh_enable(); + } + EXPORT_SYMBOL(lock_sock_nested); + +diff -Nur linux-4.4.28.orig/net/ipv4/icmp.c linux-4.4.28/net/ipv4/icmp.c +--- linux-4.4.28.orig/net/ipv4/icmp.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/ipv4/icmp.c 2016-11-01 21:26:58.836346147 +0100 +@@ -69,6 +69,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -77,6 +78,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -204,6 +206,8 @@ + * + * On SMP we have one ICMP socket per-cpu. + */ ++static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); ++ + static struct sock *icmp_sk(struct net *net) + { + return *this_cpu_ptr(net->ipv4.icmp_sk); +@@ -215,12 +219,14 @@ + + local_bh_disable(); + ++ local_lock(icmp_sk_lock); + sk = icmp_sk(net); + + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { + /* This can happen if the output path signals a + * dst_link_failure() for an outgoing ICMP packet. + */ ++ local_unlock(icmp_sk_lock); + local_bh_enable(); + return NULL; + } +@@ -230,6 +236,7 @@ + static inline void icmp_xmit_unlock(struct sock *sk) + { + spin_unlock_bh(&sk->sk_lock.slock); ++ local_unlock(icmp_sk_lock); + } + + int sysctl_icmp_msgs_per_sec __read_mostly = 1000; +@@ -358,6 +365,7 @@ + struct sock *sk; + struct sk_buff *skb; + ++ local_lock(icmp_sk_lock); + sk = icmp_sk(dev_net((*rt)->dst.dev)); + if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, + icmp_param->data_len+icmp_param->head_len, +@@ -380,6 +388,7 @@ + skb->ip_summed = CHECKSUM_NONE; + ip_push_pending_frames(sk, fl4); + } ++ local_unlock(icmp_sk_lock); + } + + /* +@@ -891,6 +900,30 @@ + } + + /* ++ * 32bit and 64bit have different timestamp length, so we check for ++ * the cookie at offset 20 and verify it is repeated at offset 50 ++ */ ++#define CO_POS0 20 ++#define CO_POS1 50 ++#define CO_SIZE sizeof(int) ++#define ICMP_SYSRQ_SIZE 57 ++ ++/* ++ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie ++ * pattern and if it matches send the next byte as a trigger to sysrq. ++ */ ++static void icmp_check_sysrq(struct net *net, struct sk_buff *skb) ++{ ++ int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq); ++ char *p = skb->data; ++ ++ if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) && ++ !memcmp(&cookie, p + CO_POS1, CO_SIZE) && ++ p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE]) ++ handle_sysrq(p[CO_POS0 + CO_SIZE]); ++} ++ ++/* + * Handle ICMP_ECHO ("ping") requests. + * + * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo +@@ -917,6 +950,11 @@ + icmp_param.data_len = skb->len; + icmp_param.head_len = sizeof(struct icmphdr); + icmp_reply(&icmp_param, skb); ++ ++ if (skb->len == ICMP_SYSRQ_SIZE && ++ net->ipv4.sysctl_icmp_echo_sysrq) { ++ icmp_check_sysrq(net, skb); ++ } + } + /* should there be an ICMP stat for ignored echos? */ + return true; +diff -Nur linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c linux-4.4.28/net/ipv4/sysctl_net_ipv4.c +--- linux-4.4.28.orig/net/ipv4/sysctl_net_ipv4.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/ipv4/sysctl_net_ipv4.c 2016-11-01 21:26:58.836346147 +0100 +@@ -818,6 +818,13 @@ + .proc_handler = proc_dointvec + }, + { ++ .procname = "icmp_echo_sysrq", ++ .data = &init_net.ipv4.sysctl_icmp_echo_sysrq, ++ .maxlen = sizeof(int), ++ .mode = 0644, ++ .proc_handler = proc_dointvec ++ }, ++ { + .procname = "icmp_ignore_bogus_error_responses", + .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, + .maxlen = sizeof(int), +diff -Nur linux-4.4.28.orig/net/ipv4/tcp_ipv4.c linux-4.4.28/net/ipv4/tcp_ipv4.c +--- linux-4.4.28.orig/net/ipv4/tcp_ipv4.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/ipv4/tcp_ipv4.c 2016-11-01 21:26:58.840346411 +0100 +@@ -62,6 +62,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -566,6 +567,7 @@ + } + EXPORT_SYMBOL(tcp_v4_send_check); + ++static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); + /* + * This routine will send an RST to the other tcp. + * +@@ -687,10 +689,13 @@ + arg.bound_dev_if = sk->sk_bound_dev_if; + + arg.tos = ip_hdr(skb)->tos; ++ ++ local_lock(tcp_sk_lock); + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len); ++ local_unlock(tcp_sk_lock); + + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); +@@ -772,10 +777,12 @@ + if (oif) + arg.bound_dev_if = oif; + arg.tos = tos; ++ local_lock(tcp_sk_lock); + ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + skb, &TCP_SKB_CB(skb)->header.h4.opt, + ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, + &arg, arg.iov[0].iov_len); ++ local_unlock(tcp_sk_lock); + + TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); + } +diff -Nur linux-4.4.28.orig/net/mac80211/rx.c linux-4.4.28/net/mac80211/rx.c +--- linux-4.4.28.orig/net/mac80211/rx.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/mac80211/rx.c 2016-11-01 21:26:58.840346411 +0100 +@@ -3574,7 +3574,7 @@ + struct ieee80211_supported_band *sband; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + +- WARN_ON_ONCE(softirq_count() == 0); ++ WARN_ON_ONCE_NONRT(softirq_count() == 0); + + if (WARN_ON(status->band >= IEEE80211_NUM_BANDS)) + goto drop; +diff -Nur linux-4.4.28.orig/net/netfilter/core.c linux-4.4.28/net/netfilter/core.c +--- linux-4.4.28.orig/net/netfilter/core.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/netfilter/core.c 2016-11-01 21:26:58.840346411 +0100 +@@ -22,11 +22,17 @@ + #include + #include + #include ++#include + #include + #include + + #include "nf_internals.h" + ++#ifdef CONFIG_PREEMPT_RT_BASE ++DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); ++EXPORT_PER_CPU_SYMBOL(xt_write_lock); ++#endif ++ + static DEFINE_MUTEX(afinfo_mutex); + + const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly; +diff -Nur linux-4.4.28.orig/net/packet/af_packet.c linux-4.4.28/net/packet/af_packet.c +--- linux-4.4.28.orig/net/packet/af_packet.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/packet/af_packet.c 2016-11-01 21:26:58.844346664 +0100 +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -695,7 +696,7 @@ + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -957,7 +958,7 @@ + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + prb_close_block(pkc, pbd, po, status); +diff -Nur linux-4.4.28.orig/net/rds/ib_rdma.c linux-4.4.28/net/rds/ib_rdma.c +--- linux-4.4.28.orig/net/rds/ib_rdma.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/rds/ib_rdma.c 2016-11-01 21:26:58.844346664 +0100 +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + #include "rds.h" + #include "ib.h" +@@ -313,7 +314,7 @@ + for_each_online_cpu(cpu) { + flag = &per_cpu(clean_list_grace, cpu); + while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) +- cpu_relax(); ++ cpu_chill(); + } + } + +diff -Nur linux-4.4.28.orig/net/sched/sch_generic.c linux-4.4.28/net/sched/sch_generic.c +--- linux-4.4.28.orig/net/sched/sch_generic.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/sched/sch_generic.c 2016-11-01 21:26:58.844346664 +0100 +@@ -893,7 +893,7 @@ + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, close_list) + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + } + + void dev_deactivate(struct net_device *dev) +diff -Nur linux-4.4.28.orig/net/sunrpc/svc_xprt.c linux-4.4.28/net/sunrpc/svc_xprt.c +--- linux-4.4.28.orig/net/sunrpc/svc_xprt.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/net/sunrpc/svc_xprt.c 2016-11-01 21:26:58.844346664 +0100 +@@ -340,7 +340,7 @@ + goto out; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); + + atomic_long_inc(&pool->sp_stats.packets); +@@ -376,7 +376,7 @@ + + atomic_long_inc(&pool->sp_stats.threads_woken); + wake_up_process(rqstp->rq_task); +- put_cpu(); ++ put_cpu_light(); + goto out; + } + rcu_read_unlock(); +@@ -397,7 +397,7 @@ + goto redo_search; + } + rqstp = NULL; +- put_cpu(); ++ put_cpu_light(); + out: + trace_svc_xprt_do_enqueue(xprt, rqstp); + } +diff -Nur linux-4.4.28.orig/scripts/mkcompile_h linux-4.4.28/scripts/mkcompile_h +--- linux-4.4.28.orig/scripts/mkcompile_h 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/scripts/mkcompile_h 2016-11-01 21:26:58.844346664 +0100 +@@ -4,7 +4,8 @@ + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -57,6 +58,7 @@ + CONFIG_FLAGS="" + if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi + if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi ++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi + UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" + + # Truncate to maximum length +diff -Nur linux-4.4.28.orig/sound/core/pcm_native.c linux-4.4.28/sound/core/pcm_native.c +--- linux-4.4.28.orig/sound/core/pcm_native.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/sound/core/pcm_native.c 2016-11-01 21:26:58.844346664 +0100 +@@ -135,7 +135,7 @@ + void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream) + { + if (!substream->pcm->nonatomic) +- local_irq_disable(); ++ local_irq_disable_nort(); + snd_pcm_stream_lock(substream); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq); +@@ -150,7 +150,7 @@ + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_enable(); ++ local_irq_enable_nort(); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq); + +@@ -158,7 +158,7 @@ + { + unsigned long flags = 0; + if (!substream->pcm->nonatomic) +- local_irq_save(flags); ++ local_irq_save_nort(flags); + snd_pcm_stream_lock(substream); + return flags; + } +@@ -176,7 +176,7 @@ + { + snd_pcm_stream_unlock(substream); + if (!substream->pcm->nonatomic) +- local_irq_restore(flags); ++ local_irq_restore_nort(flags); + } + EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore); + +diff -Nur linux-4.4.28.orig/virt/kvm/async_pf.c linux-4.4.28/virt/kvm/async_pf.c +--- linux-4.4.28.orig/virt/kvm/async_pf.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/virt/kvm/async_pf.c 2016-11-01 21:26:58.844346664 +0100 +@@ -98,8 +98,8 @@ + * This memory barrier pairs with prepare_to_wait's set_current_state() + */ + smp_mb(); +- if (waitqueue_active(&vcpu->wq)) +- wake_up_interruptible(&vcpu->wq); ++ if (swait_active(&vcpu->wq)) ++ swake_up(&vcpu->wq); + + mmput(mm); + kvm_put_kvm(vcpu->kvm); +diff -Nur linux-4.4.28.orig/virt/kvm/kvm_main.c linux-4.4.28/virt/kvm/kvm_main.c +--- linux-4.4.28.orig/virt/kvm/kvm_main.c 2016-10-28 09:53:25.000000000 +0200 ++++ linux-4.4.28/virt/kvm/kvm_main.c 2016-11-01 21:26:58.848346921 +0100 +@@ -228,8 +228,7 @@ + vcpu->kvm = kvm; + vcpu->vcpu_id = id; + vcpu->pid = NULL; +- vcpu->halt_poll_ns = 0; +- init_waitqueue_head(&vcpu->wq); ++ init_swait_queue_head(&vcpu->wq); + kvm_async_pf_vcpu_init(vcpu); + + vcpu->pre_pcpu = -1; +@@ -2005,7 +2004,7 @@ + void kvm_vcpu_block(struct kvm_vcpu *vcpu) + { + ktime_t start, cur; +- DEFINE_WAIT(wait); ++ DECLARE_SWAITQUEUE(wait); + bool waited = false; + u64 block_ns; + +@@ -2030,7 +2029,7 @@ + kvm_arch_vcpu_blocking(vcpu); + + for (;;) { +- prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); ++ prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; +@@ -2039,7 +2038,7 @@ + schedule(); + } + +- finish_wait(&vcpu->wq, &wait); ++ finish_swait(&vcpu->wq, &wait); + cur = ktime_get(); + + kvm_arch_vcpu_unblocking(vcpu); +@@ -2071,11 +2070,11 @@ + { + int me; + int cpu = vcpu->cpu; +- wait_queue_head_t *wqp; ++ struct swait_queue_head *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); +- if (waitqueue_active(wqp)) { +- wake_up_interruptible(wqp); ++ if (swait_active(wqp)) { ++ swake_up(wqp); + ++vcpu->stat.halt_wakeup; + } + +@@ -2176,7 +2175,7 @@ + continue; + if (vcpu == me) + continue; +- if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) ++ if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + continue; + if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) + continue; diff --git a/target/linux/patches/4.4.30/revert-sparc.patch b/target/linux/patches/4.4.30/revert-sparc.patch new file mode 100644 index 000000000..296be0e4a --- /dev/null +++ b/target/linux/patches/4.4.30/revert-sparc.patch @@ -0,0 +1,319 @@ +From fff1ade5bd7576b053b6bbc9c9b72c2572092c06 Mon Sep 17 00:00:00 2001 +From: Waldemar Brodkorb +Date: Wed, 6 Jul 2016 08:16:59 +0200 +Subject: [PATCH] Revert "sparc: Harden signal return frame checks." + +This reverts commit 1fda90c39d8ef6acbedfd3cd9bd710a5bcc490c3. + +Signed-off-by: Waldemar Brodkorb +--- + arch/sparc/kernel/signal32.c | 46 ++++++++++++++-------------------------- + arch/sparc/kernel/signal_32.c | 41 +++++++++++++---------------------- + arch/sparc/kernel/signal_64.c | 31 ++++++++++----------------- + arch/sparc/kernel/sigutil_32.c | 9 +------- + arch/sparc/kernel/sigutil_64.c | 10 ++------- + 5 files changed, 45 insertions(+), 92 deletions(-) + +diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c +index 77655f0..4eed773 100644 +--- a/arch/sparc/kernel/signal32.c ++++ b/arch/sparc/kernel/signal32.c +@@ -138,24 +138,12 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) + return 0; + } + +-/* Checks if the fp is valid. We always build signal frames which are +- * 16-byte aligned, therefore we can always enforce that the restore +- * frame has that property as well. +- */ +-static bool invalid_frame_pointer(void __user *fp, int fplen) +-{ +- if ((((unsigned long) fp) & 15) || +- ((unsigned long)fp) > 0x100000000ULL - fplen) +- return true; +- return false; +-} +- + void do_sigreturn32(struct pt_regs *regs) + { + struct signal_frame32 __user *sf; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; +- unsigned int psr, ufp; ++ unsigned int psr; + unsigned pc, npc; + sigset_t set; + compat_sigset_t seta; +@@ -170,16 +158,11 @@ void do_sigreturn32(struct pt_regs *regs) + sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP]; + + /* 1. Make sure we are not getting garbage from the user */ +- if (invalid_frame_pointer(sf, sizeof(*sf))) +- goto segv; +- +- if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) +- goto segv; +- +- if (ufp & 0x7) ++ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || ++ (((unsigned long) sf) & 3)) + goto segv; + +- if (__get_user(pc, &sf->info.si_regs.pc) || ++ if (get_user(pc, &sf->info.si_regs.pc) || + __get_user(npc, &sf->info.si_regs.npc)) + goto segv; + +@@ -244,7 +227,7 @@ segv: + asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) + { + struct rt_signal_frame32 __user *sf; +- unsigned int psr, pc, npc, ufp; ++ unsigned int psr, pc, npc; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; + sigset_t set; +@@ -259,16 +242,11 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) + sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP]; + + /* 1. Make sure we are not getting garbage from the user */ +- if (invalid_frame_pointer(sf, sizeof(*sf))) ++ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || ++ (((unsigned long) sf) & 3)) + goto segv; + +- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) +- goto segv; +- +- if (ufp & 0x7) +- goto segv; +- +- if (__get_user(pc, &sf->regs.pc) || ++ if (get_user(pc, &sf->regs.pc) || + __get_user(npc, &sf->regs.npc)) + goto segv; + +@@ -329,6 +307,14 @@ segv: + force_sig(SIGSEGV, current); + } + ++/* Checks if the fp is valid */ ++static int invalid_frame_pointer(void __user *fp, int fplen) ++{ ++ if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen) ++ return 1; ++ return 0; ++} ++ + static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) + { + unsigned long sp; +diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c +index c3c12ef..52aa5e4 100644 +--- a/arch/sparc/kernel/signal_32.c ++++ b/arch/sparc/kernel/signal_32.c +@@ -60,22 +60,10 @@ struct rt_signal_frame { + #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) + #define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7))) + +-/* Checks if the fp is valid. We always build signal frames which are +- * 16-byte aligned, therefore we can always enforce that the restore +- * frame has that property as well. +- */ +-static inline bool invalid_frame_pointer(void __user *fp, int fplen) +-{ +- if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen)) +- return true; +- +- return false; +-} +- + asmlinkage void do_sigreturn(struct pt_regs *regs) + { +- unsigned long up_psr, pc, npc, ufp; + struct signal_frame __user *sf; ++ unsigned long up_psr, pc, npc; + sigset_t set; + __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; +@@ -89,13 +77,10 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) + sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; + + /* 1. Make sure we are not getting garbage from the user */ +- if (!invalid_frame_pointer(sf, sizeof(*sf))) +- goto segv_and_exit; +- +- if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) ++ if (!access_ok(VERIFY_READ, sf, sizeof(*sf))) + goto segv_and_exit; + +- if (ufp & 0x7) ++ if (((unsigned long) sf) & 3) + goto segv_and_exit; + + err = __get_user(pc, &sf->info.si_regs.pc); +@@ -142,7 +127,7 @@ segv_and_exit: + asmlinkage void do_rt_sigreturn(struct pt_regs *regs) + { + struct rt_signal_frame __user *sf; +- unsigned int psr, pc, npc, ufp; ++ unsigned int psr, pc, npc; + __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; + sigset_t set; +@@ -150,13 +135,8 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) + + synchronize_user_stack(); + sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; +- if (!invalid_frame_pointer(sf, sizeof(*sf))) +- goto segv; +- +- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) +- goto segv; +- +- if (ufp & 0x7) ++ if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || ++ (((unsigned long) sf) & 0x03)) + goto segv; + + err = __get_user(pc, &sf->regs.pc); +@@ -198,6 +178,15 @@ segv: + force_sig(SIGSEGV, current); + } + ++/* Checks if the fp is valid */ ++static inline int invalid_frame_pointer(void __user *fp, int fplen) ++{ ++ if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen)) ++ return 1; ++ ++ return 0; ++} ++ + static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) + { + unsigned long sp = regs->u_regs[UREG_FP]; +diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c +index 5ee930c..39aaec1 100644 +--- a/arch/sparc/kernel/signal_64.c ++++ b/arch/sparc/kernel/signal_64.c +@@ -234,17 +234,6 @@ do_sigsegv: + goto out; + } + +-/* Checks if the fp is valid. We always build rt signal frames which +- * are 16-byte aligned, therefore we can always enforce that the +- * restore frame has that property as well. +- */ +-static bool invalid_frame_pointer(void __user *fp) +-{ +- if (((unsigned long) fp) & 15) +- return true; +- return false; +-} +- + struct rt_signal_frame { + struct sparc_stackf ss; + siginfo_t info; +@@ -257,8 +246,8 @@ struct rt_signal_frame { + + void do_rt_sigreturn(struct pt_regs *regs) + { +- unsigned long tpc, tnpc, tstate, ufp; + struct rt_signal_frame __user *sf; ++ unsigned long tpc, tnpc, tstate; + __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; + sigset_t set; +@@ -272,16 +261,10 @@ void do_rt_sigreturn(struct pt_regs *regs) + (regs->u_regs [UREG_FP] + STACK_BIAS); + + /* 1. Make sure we are not getting garbage from the user */ +- if (invalid_frame_pointer(sf)) +- goto segv; +- +- if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) ++ if (((unsigned long) sf) & 3) + goto segv; + +- if ((ufp + STACK_BIAS) & 0x7) +- goto segv; +- +- err = __get_user(tpc, &sf->regs.tpc); ++ err = get_user(tpc, &sf->regs.tpc); + err |= __get_user(tnpc, &sf->regs.tnpc); + if (test_thread_flag(TIF_32BIT)) { + tpc &= 0xffffffff; +@@ -325,6 +308,14 @@ segv: + force_sig(SIGSEGV, current); + } + ++/* Checks if the fp is valid */ ++static int invalid_frame_pointer(void __user *fp) ++{ ++ if (((unsigned long) fp) & 15) ++ return 1; ++ return 0; ++} ++ + static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) + { + unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; +diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c +index e5fe8ce..0f6eebe 100644 +--- a/arch/sparc/kernel/sigutil_32.c ++++ b/arch/sparc/kernel/sigutil_32.c +@@ -48,10 +48,6 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) + int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) + { + int err; +- +- if (((unsigned long) fpu) & 3) +- return -EFAULT; +- + #ifdef CONFIG_SMP + if (test_tsk_thread_flag(current, TIF_USEDFPU)) + regs->psr &= ~PSR_EF; +@@ -101,10 +97,7 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + +- if (((unsigned long) rp) & 3) +- return -EFAULT; +- +- get_user(wsaved, &rp->wsaved); ++ __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + +diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c +index 36aadcb..387834a 100644 +--- a/arch/sparc/kernel/sigutil_64.c ++++ b/arch/sparc/kernel/sigutil_64.c +@@ -37,10 +37,7 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) + unsigned long fprs; + int err; + +- if (((unsigned long) fpu) & 7) +- return -EFAULT; +- +- err = get_user(fprs, &fpu->si_fprs); ++ err = __get_user(fprs, &fpu->si_fprs); + fprs_write(0); + regs->tstate &= ~TSTATE_PEF; + if (fprs & FPRS_DL) +@@ -75,10 +72,7 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + +- if (((unsigned long) rp) & 7) +- return -EFAULT; +- +- get_user(wsaved, &rp->wsaved); ++ __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + +-- +1.7.10.4 + diff --git a/target/linux/patches/4.4.30/startup.patch b/target/linux/patches/4.4.30/startup.patch new file mode 100644 index 000000000..e54ac19a6 --- /dev/null +++ b/target/linux/patches/4.4.30/startup.patch @@ -0,0 +1,34 @@ +diff -Nur linux-4.4.6.orig/init/initramfs.c linux-4.4.6/init/initramfs.c +--- linux-4.4.6.orig/init/initramfs.c 2016-03-16 16:43:17.000000000 +0100 ++++ linux-4.4.6/init/initramfs.c 2016-03-27 14:15:43.931044532 +0200 +@@ -653,6 +653,9 @@ + */ + load_default_modules(); + } ++#ifdef CONFIG_DEVTMPFS_MOUNT ++ devtmpfs_mount("dev"); ++#endif + return 0; + } + rootfs_initcall(populate_rootfs); +diff -Nur linux-4.4.6.orig/init/main.c linux-4.4.6/init/main.c +--- linux-4.4.6.orig/init/main.c 2016-03-16 16:43:17.000000000 +0100 ++++ linux-4.4.6/init/main.c 2016-03-27 14:15:43.935044783 +0200 +@@ -1011,6 +1011,8 @@ + if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + pr_err("Warning: unable to open an initial console.\n"); + ++ printk(KERN_WARNING "Starting Linux (built with OpenADK).\n"); ++ + (void) sys_dup(0); + (void) sys_dup(0); + /* +@@ -1019,7 +1021,7 @@ + */ + + if (!ramdisk_execute_command) +- ramdisk_execute_command = "/init"; ++ ramdisk_execute_command = "/sbin/init"; + + if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) { + ramdisk_execute_command = NULL; diff --git a/target/linux/patches/4.4.30/use-libgcc-for-sh.patch b/target/linux/patches/4.4.30/use-libgcc-for-sh.patch new file mode 100644 index 000000000..6420219b0 --- /dev/null +++ b/target/linux/patches/4.4.30/use-libgcc-for-sh.patch @@ -0,0 +1,29 @@ +diff -Nur linux-4.1.13.orig/arch/sh/Makefile linux-4.1.13/arch/sh/Makefile +--- linux-4.1.13.orig/arch/sh/Makefile 2015-11-09 23:34:10.000000000 +0100 ++++ linux-4.1.13/arch/sh/Makefile 2015-12-06 19:59:31.000000000 +0100 +@@ -200,7 +206,9 @@ + KBUILD_CFLAGS += -fasynchronous-unwind-tables + endif + +-libs-$(CONFIG_SUPERH32) := arch/sh/lib/ $(libs-y) ++LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libgcc.a) ++ ++libs-$(CONFIG_SUPERH32) := arch/sh/lib/ $(libs-y) $(LIBGCC) + libs-$(CONFIG_SUPERH64) := arch/sh/lib64/ $(libs-y) + + BOOT_TARGETS = uImage uImage.bz2 uImage.gz uImage.lzma uImage.xz uImage.lzo \ +diff -Nur linux-4.1.13.orig/arch/sh/lib/Makefile linux-4.1.13/arch/sh/lib/Makefile +--- linux-4.1.13.orig/arch/sh/lib/Makefile 2015-11-09 23:34:10.000000000 +0100 ++++ linux-4.1.13/arch/sh/lib/Makefile 2015-12-06 19:59:14.000000000 +0100 +@@ -5,11 +5,6 @@ + lib-y = delay.o memmove.o memchr.o \ + checksum.o strlen.o div64.o div64-generic.o + +-# Extracted from libgcc +-obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ +- ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \ +- udiv_qrnnd.o +- + udivsi3-y := udivsi3_i4i-Os.o + + ifneq ($(CONFIG_CC_OPTIMIZE_FOR_SIZE),y) diff --git a/target/linux/patches/4.4.30/versatile-nommu.patch b/target/linux/patches/4.4.30/versatile-nommu.patch new file mode 100644 index 000000000..96140b30c --- /dev/null +++ b/target/linux/patches/4.4.30/versatile-nommu.patch @@ -0,0 +1,16 @@ +diff -Nur linux-4.4.17.orig/arch/arm/mach-versatile/include/mach/hardware.h linux-4.4.17/arch/arm/mach-versatile/include/mach/hardware.h +--- linux-4.4.17.orig/arch/arm/mach-versatile/include/mach/hardware.h 2016-08-10 11:49:43.000000000 +0200 ++++ linux-4.4.17/arch/arm/mach-versatile/include/mach/hardware.h 2016-08-25 23:19:03.691716292 +0200 +@@ -30,8 +30,12 @@ + #define VERSATILE_PCI_VIRT_BASE (void __iomem *)0xe8000000ul + #define VERSATILE_PCI_CFG_VIRT_BASE (void __iomem *)0xe9000000ul + ++#ifdef CONFIG_MMU + /* macro to get at MMIO space when running virtually */ + #define IO_ADDRESS(x) (((x) & 0x0fffffff) + (((x) >> 4) & 0x0f000000) + 0xf0000000) ++#else ++#define IO_ADDRESS(x) (x) ++#endif + + #define __io_address(n) ((void __iomem __force *)IO_ADDRESS(n)) + -- cgit v1.2.3