diff options
Diffstat (limited to 'target/linux/patches/4.4.107/patch-realtime')
| -rw-r--r-- | target/linux/patches/4.4.107/patch-realtime | 32228 |
1 files changed, 32228 insertions, 0 deletions
diff --git a/target/linux/patches/4.4.107/patch-realtime b/target/linux/patches/4.4.107/patch-realtime new file mode 100644 index 000000000..b49cd6f03 --- /dev/null +++ b/target/linux/patches/4.4.107/patch-realtime @@ -0,0 +1,32228 @@ +diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt +new file mode 100644 +index 000000000000..cb61516483d3 +--- /dev/null ++++ b/Documentation/hwlat_detector.txt +@@ -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 <timestamp> <latency observed usecs> ++ (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 --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt +index ca64ca566099..19bef799c902 100644 +--- a/Documentation/kernel-parameters.txt ++++ b/Documentation/kernel-parameters.txt +@@ -1640,6 +1640,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. + ip= [IP_PNP] + See Documentation/filesystems/nfs/nfsroot.txt. + ++ irqaffinity= [SMP] Set the default irq affinity mask ++ Format: ++ <cpu number>,...,<cpu number> ++ or ++ <cpu number>-<cpu number> ++ (must be a positive range in ascending order) ++ or a mixture ++ <cpu number>,...,<cpu number>-<cpu number> ++ + irqfixup [HW] + When an interrupt is not handled search all handlers + for it. Intended to get systems with badly broken +diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt +index 13f5619b2203..f64d075ba647 100644 +--- a/Documentation/sysrq.txt ++++ b/Documentation/sysrq.txt +@@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - <command key>, + 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 --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt +new file mode 100644 +index 000000000000..6f2aeabf7faa +--- /dev/null ++++ b/Documentation/trace/histograms.txt +@@ -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): ++<PID> <Priority> <Latency> (<Timeroffset>) <Command> \ ++<- <PID> <Priority> <Command> <Timestamp> ++ ++The value of <Timeroffset> 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 <Latency>. ++ ++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 <seconds>.<microseconds> after the most recent system boot ++is provided. ++ ++These data are also reset when the wakeup histogram is reset. +diff --git a/Makefile b/Makefile +index a5ecb29c6ed3..5521b0c3abf2 100644 +--- a/Makefile ++++ b/Makefile +@@ -785,6 +785,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=strict-prototypes) + # 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 --git a/arch/Kconfig b/arch/Kconfig +index 4e949e58b192..3b26d76933fb 100644 +--- a/arch/Kconfig ++++ b/arch/Kconfig +@@ -9,6 +9,7 @@ config OPROFILE + 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 KPROBES + 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 --git a/arch/arm/Kconfig b/arch/arm/Kconfig +index 34e1569a11ee..79c4603e9453 100644 +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -33,7 +33,7 @@ config ARM + 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 @@ config ARM + 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 --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h +index 12ebfcc1d539..c962084605bc 100644 +--- a/arch/arm/include/asm/switch_to.h ++++ b/arch/arm/include/asm/switch_to.h +@@ -3,6 +3,13 @@ + + #include <linux/thread_info.h> + ++#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 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info + #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 --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h +index 776757d1604a..1f36a4eccc72 100644 +--- a/arch/arm/include/asm/thread_info.h ++++ b/arch/arm/include/asm/thread_info.h +@@ -49,6 +49,7 @@ struct cpu_context_save { + 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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, + #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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, + #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 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *, + * 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 --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c +index 871b8267d211..4dbe70de7318 100644 +--- a/arch/arm/kernel/asm-offsets.c ++++ b/arch/arm/kernel/asm-offsets.c +@@ -65,6 +65,7 @@ int main(void) + 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 --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S +index 3ce377f7251f..d044cea59f54 100644 +--- a/arch/arm/kernel/entry-armv.S ++++ b/arch/arm/kernel/entry-armv.S +@@ -215,11 +215,18 @@ __irq_svc: + #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 @@ svc_preempt: + 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 --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S +index 30a7228eaceb..c3bd6cbfce4b 100644 +--- a/arch/arm/kernel/entry-common.S ++++ b/arch/arm/kernel/entry-common.S +@@ -36,7 +36,9 @@ ret_fast_syscall: + 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 @@ ret_fast_syscall: + 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 --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c +index 69bda1a5707e..1f665acaa6a9 100644 +--- a/arch/arm/kernel/patch.c ++++ b/arch/arm/kernel/patch.c +@@ -15,7 +15,7 @@ struct patch { + unsigned int insn; + }; + +-static DEFINE_SPINLOCK(patch_lock); ++static DEFINE_RAW_SPINLOCK(patch_lock); + + static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) + __acquires(&patch_lock) +@@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) + return addr; + + if (flags) +- spin_lock_irqsave(&patch_lock, *flags); ++ raw_spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); + +@@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) + clear_fixmap(fixmap); + + if (flags) +- spin_unlock_irqrestore(&patch_lock, *flags); ++ raw_spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); + } +diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c +index 4adfb46e3ee9..15f1d94b47c5 100644 +--- a/arch/arm/kernel/process.c ++++ b/arch/arm/kernel/process.c +@@ -319,6 +319,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) + } + + #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 --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c +index 7b8f2141427b..96541e00b74a 100644 +--- a/arch/arm/kernel/signal.c ++++ b/arch/arm/kernel/signal.c +@@ -572,7 +572,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) + */ + 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 --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c +index b26361355dae..e5754e3b03c4 100644 +--- a/arch/arm/kernel/smp.c ++++ b/arch/arm/kernel/smp.c +@@ -230,8 +230,6 @@ int __cpu_disable(void) + flush_cache_louis(); + local_flush_tlb_all(); + +- clear_tasks_mm_cpumask(cpu); +- + return 0; + } + +@@ -247,6 +245,9 @@ void __cpu_die(unsigned int cpu) + pr_err("CPU%u: cpu didn't die\n", cpu); + return; + } ++ ++ clear_tasks_mm_cpumask(cpu); ++ + pr_notice("CPU%u: shutdown\n", cpu); + + /* +diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c +index 0bee233fef9a..314cfb232a63 100644 +--- a/arch/arm/kernel/unwind.c ++++ b/arch/arm/kernel/unwind.c +@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[]; + 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 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr) + /* 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 @@ static const struct unwind_idx *unwind_find_idx(unsigned long addr) + 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 @@ struct unwind_table *unwind_table_add(unsigned long start, unsigned long size, + 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 @@ void unwind_table_del(struct unwind_table *tab) + 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 --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c +index d7bef2144760..36a3e51492f7 100644 +--- a/arch/arm/kvm/arm.c ++++ b/arch/arm/kvm/arm.c +@@ -496,18 +496,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm) + 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 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + * 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 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + local_irq_enable(); + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); +- preempt_enable(); ++ migrate_enable(); + continue; + } + +@@ -639,7 +639,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) + + kvm_vgic_sync_hwstate(vcpu); + +- preempt_enable(); ++ migrate_enable(); + + ret = handle_exit(vcpu, run, ret); + } +diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c +index 443db0c43d7c..a08d7a93aebb 100644 +--- a/arch/arm/kvm/psci.c ++++ b/arch/arm/kvm/psci.c +@@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) + { + 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 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) + 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 --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig +index 28656c2b54a0..3f501305ca26 100644 +--- a/arch/arm/mach-at91/Kconfig ++++ b/arch/arm/mach-at91/Kconfig +@@ -99,6 +99,7 @@ config HAVE_AT91_USB_CLK + config COMMON_CLK_AT91 + bool + select COMMON_CLK ++ select MFD_SYSCON + + config HAVE_AT91_SMD + bool +diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c +index c1a7c6cc00e1..63b4fa25b48a 100644 +--- a/arch/arm/mach-at91/at91rm9200.c ++++ b/arch/arm/mach-at91/at91rm9200.c +@@ -12,7 +12,6 @@ + #include <linux/of_platform.h> + + #include <asm/mach/arch.h> +-#include <asm/system_misc.h> + + #include "generic.h" + #include "soc.h" +@@ -33,7 +32,6 @@ static void __init at91rm9200_dt_device_init(void) + + of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev); + +- arm_pm_idle = at91rm9200_idle; + at91rm9200_pm_init(); + } + +diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c +index 7eb64f763034..cada2a6412b3 100644 +--- a/arch/arm/mach-at91/at91sam9.c ++++ b/arch/arm/mach-at91/at91sam9.c +@@ -62,8 +62,6 @@ static void __init at91sam9_common_init(void) + 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 --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h +index b0fa7dc7286d..28ca57a2060f 100644 +--- a/arch/arm/mach-at91/generic.h ++++ b/arch/arm/mach-at91/generic.h +@@ -11,27 +11,18 @@ + #ifndef _AT91_GENERIC_H + #define _AT91_GENERIC_H + +-#include <linux/of.h> +-#include <linux/reboot.h> +- +- /* 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 --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c +index d687f860a2da..ab53332a9637 100644 +--- a/arch/arm/mach-at91/pm.c ++++ b/arch/arm/mach-at91/pm.c +@@ -31,10 +31,13 @@ + #include <asm/mach/irq.h> + #include <asm/fncpy.h> + #include <asm/cacheflush.h> ++#include <asm/system_misc.h> + + #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 @@ static int at91_pm_verify_clocks(void) + 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 @@ static int at91_pm_verify_clocks(void) + + 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 @@ static void at91_pm_suspend(suspend_state_t state) + 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(); + } +@@ -369,6 +371,21 @@ static __init void at91_dt_ramc(void) + 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; +@@ -415,13 +432,36 @@ static void __init at91_pm_sram_init(void) + &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 +@@ -440,7 +480,7 @@ void __init at91rm9200_pm_init(void) + 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) +@@ -448,7 +488,7 @@ void __init at91sam9260_pm_init(void) + 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) +@@ -456,7 +496,7 @@ void __init at91sam9g45_pm_init(void) + 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) +@@ -464,5 +504,13 @@ void __init at91sam9x5_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; +- 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 --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c +index d9cf6799aec0..df8fdf1cf66d 100644 +--- a/arch/arm/mach-at91/sama5.c ++++ b/arch/arm/mach-at91/sama5.c +@@ -51,7 +51,7 @@ static void __init sama5_dt_device_init(void) + 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 --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c +index 98a2c0cbb833..310dce500d3e 100644 +--- a/arch/arm/mach-exynos/platsmp.c ++++ b/arch/arm/mach-exynos/platsmp.c +@@ -230,7 +230,7 @@ static void __iomem *scu_base_addr(void) + 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 @@ static void exynos_secondary_init(unsigned int cpu) + /* + * 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 |