34 files changed, 154 insertions, 163 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
index 8b25ffb42562..3c1cc24361bd 100644
--- a/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
+++ b/Documentation/ABI/testing/sysfs-bus-event_source-devices-events
@@ -29,7 +29,7 @@ Description:	Generic performance monitoring events
 
 What:           /sys/devices/cpu/events/PM_1PLUS_PPC_CMPL
                 /sys/devices/cpu/events/PM_BRU_FIN
-                /sys/devices/cpu/events/PM_BRU_MPRED
+                /sys/devices/cpu/events/PM_BR_MPRED
                 /sys/devices/cpu/events/PM_CMPLU_STALL
                 /sys/devices/cpu/events/PM_CMPLU_STALL_BRU
                 /sys/devices/cpu/events/PM_CMPLU_STALL_DCACHE_MISS
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 13c3f0e547a2..d1821b8bbc4c 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -60,7 +60,7 @@
 #define PME_PM_LD_REF_L1                0xc880
 #define PME_PM_LD_MISS_L1               0x400f0
 #define PME_PM_BRU_FIN                  0x10068
-#define PME_PM_BRU_MPRED                0x400f6
+#define PME_PM_BR_MPRED                 0x400f6
 
 #define PME_PM_CMPLU_STALL_FXU                  0x20014
 #define PME_PM_CMPLU_STALL_DIV                  0x40014
@@ -349,7 +349,7 @@ static int power7_generic_events[] = {
         [PERF_COUNT_HW_CACHE_REFERENCES] =              PME_PM_LD_REF_L1,
         [PERF_COUNT_HW_CACHE_MISSES] =                  PME_PM_LD_MISS_L1,
         [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =           PME_PM_BRU_FIN,
-        [PERF_COUNT_HW_BRANCH_MISSES] =                 PME_PM_BRU_MPRED,
+        [PERF_COUNT_HW_BRANCH_MISSES] =                 PME_PM_BR_MPRED,
 };
 
 #define C(x)    PERF_COUNT_HW_CACHE_##x
@@ -405,7 +405,7 @@ GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
 GENERIC_EVENT_ATTR(cache-references,            LD_REF_L1);
 GENERIC_EVENT_ATTR(cache-misses,                LD_MISS_L1);
 GENERIC_EVENT_ATTR(branch-instructions,         BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses,               BRU_MPRED);
+GENERIC_EVENT_ATTR(branch-misses,               BR_MPRED);
 
 POWER_EVENT_ATTR(CYC,                           CYC);
 POWER_EVENT_ATTR(GCT_NOSLOT_CYC,                GCT_NOSLOT_CYC);
@@ -414,7 +414,7 @@ POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
 POWER_EVENT_ATTR(LD_REF_L1,                     LD_REF_L1);
 POWER_EVENT_ATTR(LD_MISS_L1,                    LD_MISS_L1);
 POWER_EVENT_ATTR(BRU_FIN,                       BRU_FIN)
-POWER_EVENT_ATTR(BRU_MPRED,                     BRU_MPRED);
+POWER_EVENT_ATTR(BR_MPRED,                      BR_MPRED);
 
 POWER_EVENT_ATTR(CMPLU_STALL_FXU,               CMPLU_STALL_FXU);
 POWER_EVENT_ATTR(CMPLU_STALL_DIV,               CMPLU_STALL_DIV);
@@ -449,7 +449,7 @@ static struct attribute *power7_events_attr[] = {
         GENERIC_EVENT_PTR(LD_REF_L1),
         GENERIC_EVENT_PTR(LD_MISS_L1),
         GENERIC_EVENT_PTR(BRU_FIN),
-        GENERIC_EVENT_PTR(BRU_MPRED),
+        GENERIC_EVENT_PTR(BR_MPRED),
 
         POWER_EVENT_PTR(CYC),
         POWER_EVENT_PTR(GCT_NOSLOT_CYC),
@@ -458,7 +458,7 @@ static struct attribute *power7_events_attr[] = {
         POWER_EVENT_PTR(LD_REF_L1),
         POWER_EVENT_PTR(LD_MISS_L1),
         POWER_EVENT_PTR(BRU_FIN),
-        POWER_EVENT_PTR(BRU_MPRED),
+        POWER_EVENT_PTR(BR_MPRED),
 
         POWER_EVENT_PTR(CMPLU_STALL_FXU),
         POWER_EVENT_PTR(CMPLU_STALL_DIV),
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 0920212e6159..ba77ebc2c353 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -111,7 +111,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
          */
         list_for_each_entry_rcu(a, &desc->head, list) {
                 u64 before, delta, whole_msecs;
-                int decimal_msecs, thishandled;
+                int remainder_ns, decimal_msecs, thishandled;
 
                 before = local_clock();
                 thishandled = a->handler(type, regs);
@@ -123,8 +123,9 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
                         continue;
 
                 nmi_longest_ns = delta;
-                whole_msecs = do_div(delta, (1000 * 1000));
-                decimal_msecs = do_div(delta, 1000) % 1000;
+                whole_msecs = delta;
+                remainder_ns = do_div(whole_msecs, (1000 * 1000));
+                decimal_msecs = remainder_ns / 1000;
                 printk_ratelimited(KERN_INFO
                         "INFO: NMI handler (%ps) took too long to run: "
                         "%lld.%03d msecs\n", a->handler, whole_msecs,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1833bc5a84a7..eba8fb5834ae 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -947,8 +947,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags)
 {
         struct perf_event_context *ctx;
 
-        rcu_read_lock();
 retry:
+        /*
+         * One of the few rules of preemptible RCU is that one cannot do
+         * rcu_read_unlock() while holding a scheduler (or nested) lock when
+         * part of the read side critical section was preemptible -- see
+         * rcu_read_unlock_special().
+         *
+         * Since ctx->lock nests under rq->lock we must ensure the entire read
+         * side critical section is non-preemptible.
+         */
+        preempt_disable();
+        rcu_read_lock();
         ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
         if (ctx) {
                 /*
@@ -964,6 +974,8 @@ retry:
                 raw_spin_lock_irqsave(&ctx->lock, *flags);
                 if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {