14 files changed, 162 insertions, 130 deletions

diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 942255310e6a..528a11e8d3e3 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -20,10 +20,10 @@ struct arch_hw_breakpoint {
 #include <linux/list.h>
 
 /* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_X            0x00
 #define X86_BREAKPOINT_LEN_1            0x40
 #define X86_BREAKPOINT_LEN_2            0x44
 #define X86_BREAKPOINT_LEN_4            0x4c
-#define X86_BREAKPOINT_LEN_EXECUTE      0x40
 
 #ifdef CONFIG_X86_64
 #define X86_BREAKPOINT_LEN_8            0x48
diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h
new file mode 100644
index 000000000000..36c93b5cc239
--- /dev/null
+++ b/arch/x86/include/asm/local64.h
@@ -0,0 +1 @@
+#include <asm-generic/local64.h>
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 254883d0c7e0..6e742cc4251b 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -68,8 +68,9 @@ union cpuid10_eax {
 
 union cpuid10_edx {
         struct {
-                unsigned int num_counters_fixed:4;
-                unsigned int reserved:28;
+                unsigned int num_counters_fixed:5;
+                unsigned int bit_width_fixed:8;
+                unsigned int reserved:19;
         } split;
         unsigned int full;
 };
@@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)   perf_misc_flags(regs)
 
+#include <asm/stacktrace.h>
+
+/*
+ * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
+ * and the comment with PERF_EFLAGS_EXACT.
+ */
+#define perf_arch_fetch_caller_regs(regs, __ip)         {       \
+        (regs)->ip = (__ip);                                    \
+        (regs)->bp = caller_frame_pointer();                    \
+        (regs)->cs = __KERNEL_CS;                               \
+        regs->flags = 0;                                        \
+}
+
 #else
 static inline void init_hw_perf_events(void)            { }
 static inline void perf_events_lapic_init(void) { }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 4dab78edbad9..2b16a2ad23dc 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -1,6 +1,13 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
 #ifndef _ASM_X86_STACKTRACE_H
 #define _ASM_X86_STACKTRACE_H
 
+#include <linux/uaccess.h>
+
 extern int kstack_depth_to_print;
 
 struct thread_info;
@@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data);
 
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+                unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+        struct stack_frame *next_frame;
+        unsigned long return_address;
+};
+
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
+static inline unsigned long caller_frame_pointer(void)
+{
+        struct stack_frame *frame;
+
+        get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+        frame = frame->next_frame;
+#endif
+
+        return (unsigned long)frame;
+}
+
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5db5b7d65a18..f2da20fda02d 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -220,6 +220,7 @@ struct x86_pmu {
                                                  struct perf_event *event);
         struct event_constraint *event_constraints;
         void            (*quirks)(void);
+        int             perfctr_second_write;
 
         int             (*cpu_prepare)(int cpu);
         void            (*cpu_starting)(int cpu);
@@ -295,10 +296,10 @@ x86_perf_event_update(struct perf_event *event)
          * count to the generic event atomically:
          */
 again:
-        prev_raw_count = atomic64_read(&hwc->prev_count);
+        prev_raw_count = local64_read(&hwc->prev_count);
         rdmsrl(hwc->event_base + idx, new_raw_count);
 
-        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+        if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
                                         new_raw_count) != prev_raw_count)
                 goto again;
 
@@ -313,8 +314,8 @@ again:
         delta = (new_raw_count << shift) - (prev_raw_count << shift);
         delta >>= shift;
 
-        atomic64_add(delta, &event->count);
-        atomic64_sub(delta, &hwc->period_left);
+        local64_add(delta, &event->count);
+        local64_sub(delta, &hwc->period_left);
 
         return new_raw_count;
 }
@@ -438,7 +439,7 @@ static int x86_setup_perfctr(struct perf_event *event)
         if (!hwc->sample_period) {
                 hwc->sample_period = x86_pmu.max_period;
                 hwc->last_period = hwc->sample_period;
-                atomic64_set(&hwc->period_left, hwc->sample_period);
+                local64_set(&hwc->period_left, hwc->sample_period);
         } else {
                 /*
                  * If we have a PMU initialized but no APIC
@@ -885,7 +886,7 @@ static int
 x86_perf_event_set_period(struct perf_event *event)
 {
         struct hw_perf_event *hwc = &event->hw;
-        s64 left = atomic64_read(&hwc->period_left);
+        s64 left = local64_read(&hwc->period_left);
         s64 period = hwc->sample_period;
         int ret = 0, idx = hwc->idx;
 
@@ -897,14 +898,14 @@ x86_perf_event_set_period(struct perf_event *event)
          */
         if (unlikely(left <= -period)) {
                 left = period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
 
         if (unlikely(left <= 0)) {
                 left += period;
-                atomic64_set(&hwc->period_left, left);
+                local64_set(&hwc->period_left, left);
                 hwc->last_period = period;
                 ret = 1;
         }
@@ -923,10 +924,19 @@ x86_perf_event_set_period(struct perf_event *event)
          * The hw event starts counting from this event offset,
          * mark it to be able to extra future deltas:
          */
-        atomic64_set(&hwc->prev_count, (u64)-left);
+        local64_set(&hwc->prev_count, (u64)-left);
 
-        wrmsrl(hwc->event_base + idx,
+        wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask);
+
+        /*
+         * Due to erratum on certan cpu we need
+         * a second write to be sure the register
+         * is updated properly
+         */
+        if (x86_pmu.perfctr_second_write) {
+                wrmsrl(hwc->event_base + idx,
                         (u64)(-left) & x86_pmu.cntval_mask);
+        }
 
         perf_event_update_userpage(event);
 
@@ -969,7 +979,7 @@ static int x86_pmu_enable(struct perf_event *event)
          * skip the schedulability test here, it will be peformed
          * at commit time(->commit_txn) as a whole
          */
-        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuc->group_flag & PERF_EVENT_TXN)
                 goto out;
 
         ret = x86_pmu.schedule_events(cpuc, n, assign);
@@ -1096,7 +1106,7 @@ static void x86_pmu_disable(struct perf_event *event)
          * The events never got scheduled and ->cancel_txn will truncate
          * the event_list.
          */
-        if (cpuc->group_flag & PERF_EVENT_TXN_STARTED)
+        if (cpuc->group_flag & PERF_EVENT_TXN)
                 return;
 
         x86_pmu_stop(event);
@@ -1388,7 +1398,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-        cpuc->group_flag |= PERF_EVENT_TXN_STARTED;
+        cpuc->group_flag |= PERF_EVENT_TXN;
         cpuc->n_txn = 0;
 }
 
@@ -1401,7 +1411,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-        cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED;
+        cpuc->group_flag &= ~PERF_EVENT_TXN;
         /*
          * Truncate the collected events.
          */
@@ -1435,11 +1445,7 @@ static int x86_pmu_commit_txn(const struct pmu *pmu)
          */
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
-        /*
-         * Clear out the txn count so that ->cancel_txn() which gets
-         * run after ->commit_txn() doesn't undo things.
-         */
-        cpuc->n_txn = 0;
+        cpuc->group_flag &= ~PERF_EVENT_TXN;
 
         return 0;
 }
@@ -1607,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = {
         .walk_stack             = print_context_stack_bp,
 };
 
-#include "../dumpstack.h"
-
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
@@ -1730,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
         return entry;
 }
 
-void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
-{
-        regs->ip = ip;
-        /*
-         * perf_arch_fetch_caller_regs adds another call, we need to increment
-         * the skip level
-         */
-        regs->bp = rewind_frame_pointer(skip + 1);
-        regs->cs = __KERNEL_CS;
-        /*
-         * We abuse bit 3 to pass exact information, see perf_misc_flags
-         * and the comment with PERF_EFLAGS_EXACT.
-         */
-        regs->flags = 0;
-}
-
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
         unsigned long ip;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ae85d69644d1..9286e736a70a 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -829,6 +829,15 @@ static __initconst const struct x86_pmu p4_pmu = {
         .max_period             = (1ULL << 39) - 1,
         .hw_config              = p4_hw_config,
         .schedule_events        = p4_pmu_schedule_events,
+        /*
+         * This handles erratum N15 in intel doc 249199-029,
+         * the counter may not be updated correctly on write
+         * so we need a second write operation to do the trick
+         * (the official workaround didn't work)
+         *
+         * the former idea is taken from OProfile code
+         */
+        .perfctr_second_write   = 1,
 };
 
 static __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c89a386930b7..6e8752c1bd52 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -18,7 +18,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
deleted file mode 100644
index e1a93be4fd44..000000000000
--- a/arch/x86/kernel/dumpstack.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
- */
-
-#ifndef DUMPSTACK_H
-#define DUMPSTACK_H
-
-#ifdef CONFIG_X86_32
-#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-#else
-#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-#endif
-
-#include <linux/uaccess.h>
-
-extern void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *stack, unsigned long bp, char *log_lvl);
-
-extern void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-                unsigned long *sp, unsigned long bp, char *log_lvl);
-
-extern unsigned int code_bytes;
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-        struct stack_frame *next_frame;
-        unsigned long return_address;
-};
-
-struct stack_frame_ia32 {
-    u32 next_frame;
-    u32 return_address;
-};
-
-static inline unsigned long rewind_frame_pointer(int n)
-{
-        struct stack_frame *frame;
-
-        get_bp(frame);
-
-#ifdef CONFIG_FRAME_POINTER
-        while (n--) {
-                if (probe_kernel_address(&frame->next_frame, frame))
-                        break;
-        }
-#endif
-
-        return (unsigned long)frame;
-}
-
-#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 11540a189d93..0f6376ffa2d9 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,8 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
-
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 272c9f1f05f3..57a21f11c791 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,7 +16,6 @@
 
 #include <asm/stacktrace.h>
 
-#include "dumpstack.h"
 
 #define N_EXCEPTION_STACKS_END \
                 (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2)
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index a8f1b803d2fd..a474ec37c32f 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -208,6 +208,9 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 {
         /* Len */
         switch (x86_len) {
+        case X86_BREAKPOINT_LEN_X:
+                *gen_len = sizeof(long);
+                break;
         case X86_BREAKPOINT_LEN_1:
                 *gen_len = HW_BREAKPOINT_LEN_1;
                 break;
@@ -251,6 +254,29 @@ static int arch_build_bp_info(struct perf_event *bp)
 
         info->address = bp->attr.bp_addr;
 
+        /* Type */
+        switch (bp->attr.bp_type) {
+        case HW_BREAKPOINT_W:
+                info->type = X86_BREAKPOINT_WRITE;
+                break;
+        case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
+                info->type = X86_BREAKPOINT_RW;
+                break;
+        case HW_BREAKPOINT_X:
+                info->type = X86_BREAKPOINT_EXECUTE;
+                /*
+                 * x86 inst breakpoints need to have a specific undefined len.
+                 * But we still need to check userspace is not trying to setup
+                 * an unsupported length, to get a range breakpoint for example.
+                 */
+                if (bp->attr.bp_len == sizeof(long)) {
+                        info->len = X86_BREAKPOINT_LEN_X;
+                        return 0;
+                }
+        default:
+                return -EINVAL;
+        }
+
         /* Len */
         switch (bp->attr.bp_len) {
         case HW_BREAKPOINT_LEN_1:
@@ -271,21 +297,6 @@ static int arch_build_bp_info(struct perf_event *bp)
                 return -EINVAL;
         }
 
-        /* Type */
-        switch (bp->attr.bp_type) {
-        case HW_BREAKPOINT_W:
-                info->type = X86_BREAKPOINT_WRITE;
-                break;
-        case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-                info->type = X86_BREAKPOINT_RW;
-                break;
-        case HW_BREAKPOINT_X:
-                info->type = X86_BREAKPOINT_EXECUTE;
-                break;
-        default:
-                return -EINVAL;
-        }
-
         return 0;
 }
 /*
@@ -305,6 +316,9 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
         ret = -EINVAL;
 
         switch (info->len) {
+        case X86_BREAKPOINT_LEN_X:
+                align = sizeof(long) -1;
+                break;
         case X86_BREAKPOINT_LEN_1:
                 align = 0;
                 break;
@@ -466,6 +480,13 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 
                 perf_bp_event(bp, args->regs);
 
+                /*
+                 * Set up resume flag to avoid breakpoint recursion when
+                 * returning back to origin.
+                 */
+                if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE)
+                        args->regs->flags |= X86_EFLAGS_RF;
+
                 rcu_read_unlock();
         }
         /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8d128783af47..96586c3cbbbf 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -57,6 +57,8 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 
+#include <trace/events/power.h>
+
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 /*
@@ -111,6 +113,8 @@ void cpu_idle(void)
                         stop_critical_timings();
                         pm_idle();
                         start_critical_timings();
+
+                        trace_power_end(smp_processor_id());
                 }
                 tick_nohz_restart_sched_tick();
                 preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3c2422a99f1f..3d9ea531ddd1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -51,6 +51,8 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 
+#include <trace/events/power.h>
+
 asmlinkage extern void ret_from_fork(void);
 
 DEFINE_PER_CPU(unsigned long, old_rsp);
@@ -138,6 +140,9 @@ void cpu_idle(void)
                         stop_critical_timings();
                         pm_idle();
                         start_critical_timings();
+
+                        trace_power_end(smp_processor_id());
+
                         /* In many cases the interrupt that ended idle
                            has already called exit_idle. But some idle
                            loops can be woken up without interrupt. */
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 922eefbb3f6c..b53c525368a7 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name)
         return 0;
 }
 
-static void save_stack_address(void *data, unsigned long addr, int reliable)
+static void
+__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
 {
         struct stack_trace *trace = data;
+#ifdef CONFIG_FRAME_POINTER
         if (!reliable)
                 return;
+#endif
+        if (nosched && in_sched_functions(addr))
+                return;
         if (trace->skip > 0) {
                 trace->skip--;
                 return;
@@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable)
                 trace->entries[trace->nr_entries++] = addr;
 }
 
+static void save_stack_address(void *data, unsigned long addr, int reliable)
+{
+        return __save_stack_address(data, addr, reliable, false);
+}
+
 static void
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
-        struct stack_trace *trace = (struct stack_trace *)data;
-        if (!reliable)
-                return;
-        if (in_sched_functions(addr))
-                return;
-        if (trace->skip > 0) {
-                trace->skip--;
-                return;
-        }
-        if (trace->nr_entries < trace->max_entries)
-                trace->entries[trace->nr_entries++] = addr;
+        return __save_stack_address(data, addr, reliable, true);
 }
 
 static const struct stacktrace_ops save_stack_ops = {
@@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
-struct stack_frame {
+struct stack_frame_user {
         const void __user       *next_fp;
         unsigned long           ret_addr;
 };
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+static int
+copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 {
         int ret;
 
@@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
                 trace->entries[trace->nr_entries++] = regs->ip;
 
         while (trace->nr_entries < trace->max_entries) {
-                struct stack_frame frame;
+                struct stack_frame_user frame;
 
                 frame.next_fp = NULL;
                 frame.ret_addr = 0;