Merge branch 'perf/urgent' into perf/core

Conflicts:
	arch/x86/kernel/apic/hw_nmi.c

Merge reason: Resolve conflict, queue up dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 144 insertions, 46 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e8327686d3c5..e330da21b84f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,7 +21,7 @@ config X86
         select HAVE_UNSTABLE_SCHED_CLOCK
         select HAVE_IDE
         select HAVE_OPROFILE
-        select HAVE_PERF_EVENTS if (!M386 && !M486)
+        select HAVE_PERF_EVENTS
         select HAVE_IRQ_WORK
         select HAVE_IOREMAP_PROT
         select HAVE_KPROBES
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 3e25afe9a62a..a0e71cb4fa9c 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,9 +17,6 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(void)
 {
@@ -27,6 +24,10 @@ u64 hw_nmi_get_sample_period(void)
 }
 #endif
 
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
 #ifdef arch_trigger_all_cpu_backtrace
 void arch_trigger_all_cpu_backtrace(void)
 {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 5273c7b90b8b..7c1a4c35fd41 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -372,6 +372,20 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
+static bool check_hw_exists(void)
+{
+        u64 val, val_new = 0;
+        int ret = 0;
+
+        val = 0xabcdUL;
+        ret |= checking_wrmsrl(x86_pmu.perfctr, val);
+        ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+        if (ret || val != val_new)
+                return false;
+
+        return true;
+}
+
 static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
@@ -1363,6 +1377,12 @@ void __init init_hw_perf_events(void)
 
         pmu_check_apic();
 
+        /* sanity check that the hardware exists or is emulated */
+        if (!check_hw_exists()) {
+                pr_cont("Broken PMU hardware detected, software events only.\n");
+                return;
+        }
+
         pr_cont("%s PMU driver.\n", x86_pmu.name);
 
         if (x86_pmu.quirks)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index fe2690d71c0c..e3ba417e8697 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -295,6 +295,7 @@ ENDPROC(native_usergs_sysret64)
         .endm
 
 /* save partial stack frame */
+        .pushsection .kprobes.text, "ax"
 ENTRY(save_args)
         XCPT_FRAME
         cld
@@ -334,6 +335,7 @@ ENTRY(save_args)
         ret
         CFI_ENDPROC
 END(save_args)
+        .popsection
 
 ENTRY(save_rest)
         PARTIAL_FRAME 1 REST_SKIP+8
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index ff15c9dcc25d..42c594254507 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -433,6 +433,10 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
         dr6_p = (unsigned long *)ERR_PTR(args->err);
         dr6 = *dr6_p;
 
+        /* If it's a single step, TRAP bits are random */
+        if (dr6 & DR_STEP)
+                return NOTIFY_DONE;
+
         /* Do an early return if no trap bits are set in DR6 */
         if ((dr6 & DR_TRAP_BITS) == 0)
                 return NOTIFY_DONE;
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index a2d6ea49ec56..d1e55fed2c7d 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -33,6 +33,8 @@ enum bp_type_idx {
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
+extern int __init init_hw_breakpoint(void);
+
 static inline void hw_breakpoint_init(struct perf_event_attr *attr)
 {
         memset(attr, 0, sizeof(*attr));
@@ -108,6 +110,8 @@ static inline struct arch_hw_breakpoint *counter_arch_bp(struct perf_event *bp)
 
 #else /* !CONFIG_HAVE_HW_BREAKPOINT */
 
+static inline int __init init_hw_breakpoint(void) { return 0; }
+
 static inline struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
                             perf_overflow_handler_t triggered,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 40150f345982..de2c41758e29 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -850,6 +850,7 @@ struct perf_event_context {
         int                             nr_active;
         int                             is_active;
         int                             nr_stat;
+        int                             rotate_disable;
         atomic_t                        refcount;
         struct task_struct              *task;
 
@@ -908,20 +909,6 @@ extern int perf_num_counters(void);
 extern const char *perf_pmu_name(void);
 extern void __perf_event_task_sched_in(struct task_struct *task);
 extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-
-extern atomic_t perf_task_events;
-
-static inline void perf_event_task_sched_in(struct task_struct *task)
-{
-        COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
-}
-
-static inline
-void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
-{
-        COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
-}
-
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
@@ -1030,6 +1017,21 @@ have_event:
         __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+        COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+
+        COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
+
 extern void perf_event_mmap(struct vm_area_struct *vma);
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index 2c9120f0afca..e5325825aeb6 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -620,7 +620,7 @@ static struct pmu perf_breakpoint = {
         .read           = hw_breakpoint_pmu_read,
 };
 
-static int __init init_hw_breakpoint(void)
+int __init init_hw_breakpoint(void)
 {
         unsigned int **task_bp_pinned;
         int cpu, err_cpu;
@@ -655,6 +655,5 @@ static int __init init_hw_breakpoint(void)
 
         return -ENOMEM;
 }
-core_initcall(init_hw_breakpoint);
 
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f16763ff8481..90f881904bb1 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -145,7 +145,9 @@ void irq_work_run(void)
                  * Clear the BUSY bit and return to the free state if
                  * no-one else claimed it meanwhile.
                  */
-                cmpxchg(&entry->next, next_flags(NULL, IRQ_WORK_BUSY), NULL);
+                (void)cmpxchg(&entry->next,
+                              next_flags(NULL, IRQ_WORK_BUSY),
+                              NULL);
         }
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 40c3aab648a1..43f757ccf831 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -31,6 +31,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/perf_event.h>
 #include <linux/ftrace_event.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/irq_regs.h>
 
@@ -1286,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
         int ctxn;
 
-        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
         for_each_task_context_nr(ctxn)
                 perf_event_context_sched_out(task, ctxn, next);
 }
@@ -1621,8 +1620,12 @@ static void rotate_ctx(struct perf_event_context *ctx)
 {
         raw_spin_lock(&ctx->lock);
 
-        /* Rotate the first entry last of non-pinned groups */
-        list_rotate_left(&ctx->flexible_groups);
+        /*
+         * Rotate the first entry last of non-pinned groups. Rotation might be
+         * disabled by the inheritance code.
+         */
+        if (!ctx->rotate_disable)
+                list_rotate_left(&ctx->flexible_groups);
 
         raw_spin_unlock(&ctx->lock);
 }
@@ -2234,11 +2237,6 @@ int perf_event_release_kernel(struct perf_event *event)
         raw_spin_unlock_irq(&ctx->lock);
         mutex_unlock(&ctx->mutex);
 
-        mutex_lock(&event->owner->perf_event_mutex);
-        list_del_init(&event->owner_entry);
-        mutex_unlock(&event->owner->perf_event_mutex);
-        put_task_struct(event->owner);
-
         free_event(event);
 
         return 0;
@@ -2251,9 +2249,43 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 static int perf_release(struct inode *inode, struct file *file)
 {
         struct perf_event *event = file->private_data;
+        struct task_struct *owner;
 
         file->private_data = NULL;
 
+        rcu_read_lock();
+        owner = ACCESS_ONCE(event->owner);
+        /*
+         * Matches the smp_wmb() in perf_event_exit_task(). If we observe
+         * !owner it means the list deletion is complete and we can indeed
+         * free this event, otherwise we need to serialize on
+         * owner->perf_event_mutex.
+         */
+        smp_read_barrier_depends();
+        if (owner) {
+                /*
+                 * Since delayed_put_task_struct() also drops the last
+                 * task reference we can safely take a new reference
+                 * while holding the rcu_read_lock().
+                 */
+                get_task_struct(owner);
+        }
+        rcu_read_unlock();
+
+        if (owner) {
+                mutex_lock(&owner->perf_event_mutex);
+                /*
+                 * We have to re-check the event->owner field, if it is cleared
+                 * we raced with perf_event_exit_task(), acquiring the mutex
+                 * ensured they're done, and we can proceed with freeing the
+                 * event.
+                 */
+                if (event->owner)
+                        list_del_init(&event->owner_entry);
+                mutex_unlock(&owner->perf_event_mutex);
+                put_task_struct(owner);
+        }
+
         return perf_event_release_kernel(event);
 }
 
@@ -5668,7 +5700,7 @@ SYSCALL_DEFINE5(perf_event_open,
         mutex_unlock(&ctx->mutex);
 
         event->owner = current;
-        get_task_struct(current);
+
         mutex_lock(&current->perf_event_mutex);
         list_add_tail(&event->owner_entry, &current->perf_event_list);
         mutex_unlock(&current->perf_event_mutex);
@@ -5736,12 +5768,6 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
         ++ctx->generation;
         mutex_unlock(&ctx->mutex);
 
-        event->owner = current;
-        get_task_struct(current);
-        mutex_lock(&current->perf_event_mutex);
-        list_add_tail(&event->owner_entry, &current->perf_event_list);
-        mutex_unlock(&current->perf_event_mutex);
-
         return event;
 
 err_free:
@@ -5892,8 +5918,24 @@ again:
  */
 void perf_event_exit_task(struct task_struct *child)
 {
+        struct perf_event *event, *tmp;
         int ctxn;
 
+        mutex_lock(&child->perf_event_mutex);
+        list_for_each_entry_safe(event, tmp, &child->perf_event_list,
+                                 owner_entry) {
+                list_del_init(&event->owner_entry);
+
+                /*
+                 * Ensure the list deletion is visible before we clear
+                 * the owner, closes a race against perf_release() where
+                 * we need to serialize on the owner->perf_event_mutex.
+                 */
+                smp_wmb();
+                event->owner = NULL;
+        }
+        mutex_unlock(&child->perf_event_mutex);
+
         for_each_task_context_nr(ctxn)
                 perf_event_exit_task_context(child, ctxn);
 }
@@ -6113,6 +6155,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
         struct perf_event *event;
         struct task_struct *parent = current;
         int inherited_all = 1;
+        unsigned long flags;
         int ret = 0;
 
         child->perf_event_ctxp[ctxn] = NULL;
@@ -6153,6 +6196,15 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
                         break;
         }
 
+        /*
+         * We can't hold ctx->lock when iterating the ->flexible_group list due
+         * to allocations, but we need to prevent rotation because
+         * rotate_ctx() will change the list from interrupt context.
+         */
+        raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+        parent_ctx->rotate_disable = 1;
+        raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
         list_for_each_entry(event, &parent_ctx->flexible_groups, group_entry) {
                 ret = inherit_task_group(event, parent, parent_ctx,
                                          child, ctxn, &inherited_all);
@@ -6160,6 +6212,10 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
                         break;
         }
 
+        raw_spin_lock_irqsave(&parent_ctx->lock, flags);
+        parent_ctx->rotate_disable = 0;
+        raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+
         child_ctx = child->perf_event_ctxp[ctxn];
 
         if (child_ctx && inherited_all) {
@@ -6312,6 +6368,8 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 
 void __init perf_event_init(void)
 {
+        int ret;
+
         perf_event_init_all_cpus();
         init_srcu_struct(&pmus_srcu);
         perf_pmu_register(&perf_swevent);
@@ -6319,4 +6377,7 @@ void __init perf_event_init(void)
         perf_pmu_register(&perf_task_clock);
         perf_tp_register();
         perf_cpu_notifier(perf_cpu_notify);
+
+        ret = init_hw_breakpoint();
+        WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d9dd47885218..3d2cb4899807 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -697,17 +697,18 @@ static int __cmd_record(int argc, const char **argv)
         if (err < 0)
                 err = event__synthesize_kernel_mmap(process_synthesized_event,
                                                     session, machine, "_stext");
-        if (err < 0) {
-                pr_err("Couldn't record kernel reference relocation symbol.\n");
-                return err;
-        }
+        if (err < 0)
+                pr_err("Couldn't record kernel reference relocation symbol\n"
+                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                       "Check /proc/kallsyms permission or run as root.\n");
 
         err = event__synthesize_modules(process_synthesized_event,
                                         session, machine);
-        if (err < 0) {
-                pr_err("Couldn't record kernel reference relocation symbol.\n");
-                return err;
-        }
+        if (err < 0)
+                pr_err("Couldn't record kernel module information.\n"
+                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                       "Check /proc/modules permission or run as root.\n");
+
         if (perf_guest)
                 perf_session__process_machines(session, event__synthesize_guest_os);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index b39f499e575a..0500895a45af 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -295,7 +295,9 @@ static void symbols__insert_by_name(struct rb_root *self, struct symbol *sym)
 {
         struct rb_node **p = &self->rb_node;
         struct rb_node *parent = NULL;
-        struct symbol_name_rb_node *symn = ((void *)sym) - sizeof(*parent), *s;
+        struct symbol_name_rb_node *symn, *s;
+
+        symn = container_of(sym, struct symbol_name_rb_node, sym);
 
         while (*p != NULL) {
                 parent = *p;