3 files changed, 83 insertions, 23 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6b7c444ab8f6..c0f4b364c711 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -131,12 +131,12 @@ struct ftrace_event_call {
         void                    *mod;
         void                    *data;
 
-        int                     profile_count;
-        int                     (*profile_enable)(struct ftrace_event_call *);
-        void                    (*profile_disable)(struct ftrace_event_call *);
+        int                     perf_refcount;
+        int                     (*perf_event_enable)(struct ftrace_event_call *);
+        void                    (*perf_event_disable)(struct ftrace_event_call *);
 };
 
-#define FTRACE_MAX_PROFILE_SIZE 2048
+#define PERF_MAX_TRACE_SIZE     2048
 
 #define MAX_FILTER_PRED         32
 #define MAX_FILTER_STR_VAL      256     /* Should handle KSYM_SYMBOL_LEN */
@@ -187,22 +187,25 @@ do {									\
 
 #ifdef CONFIG_PERF_EVENTS
 struct perf_event;
-extern int ftrace_profile_enable(int event_id);
-extern void ftrace_profile_disable(int event_id);
+
+DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+
+extern int perf_trace_enable(int event_id);
+extern void perf_trace_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
                                      char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *
-ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
                          unsigned long *irq_flags);
 
 static inline void
-ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-                       u64 count, unsigned long irq_flags)
+perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+                       u64 count, unsigned long irq_flags, struct pt_regs *regs)
 {
         struct trace_entry *entry = raw_data;
 
-        perf_tp_event(entry->type, addr, count, raw_data, size);
+        perf_tp_event(entry->type, addr, count, raw_data, size, regs);
         perf_swevent_put_recursion_context(rctx);
         local_irq_restore(irq_flags);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6f8cd7da1a01..95477038a72a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -452,6 +452,8 @@ enum perf_callchain_context {
 #include <linux/fs.h>
 #include <linux/pid_namespace.h>
 #include <linux/workqueue.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
 #include <asm/atomic.h>
 
 #define PERF_MAX_STACK_DEPTH            255
@@ -847,6 +849,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
                 __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+{
+        unsigned long ip;
+
+        memset(regs, 0, sizeof(*regs));
+
+        switch (skip) {
+        case 1 :
+                ip = CALLER_ADDR0;
+                break;
+        case 2 :
+                ip = CALLER_ADDR1;
+                break;
+        case 3 :
+                ip = CALLER_ADDR2;
+                break;
+        case 4:
+                ip = CALLER_ADDR3;
+                break;
+        /* No need to support further for now */
+        default:
+                ip = 0;
+        }
+
+        return perf_arch_fetch_caller_regs(regs, ip, skip);
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
@@ -880,7 +920,8 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+                          int entry_size, struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -936,5 +977,21 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_output_put(handle, x) \
         perf_output_copy((handle), &(x), sizeof(x))
 
+/*
+ * This has to have a higher priority than migration_notifier in sched.c.
+ */
+#define perf_cpu_notifier(fn)                                   \
+do {                                                            \
+        static struct notifier_block fn##_nb __cpuinitdata =    \
+                { .notifier_call = fn, .priority = 20 };        \
+        fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,             \
+                (void *)(unsigned long)smp_processor_id());     \
+        fn(&fn##_nb, (unsigned long)CPU_STARTING,               \
+                (void *)(unsigned long)smp_processor_id());     \
+        fn(&fn##_nb, (unsigned long)CPU_ONLINE,                 \
+                (void *)(unsigned long)smp_processor_id());     \
+        register_cpu_notifier(&fn##_nb);                        \
+} while (0)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 44f2ad0e8825..f994ae58a002 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -105,18 +105,18 @@ struct perf_event_attr;
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)                                    \
-        .profile_enable = prof_sysenter_enable,                                \
-        .profile_disable = prof_sysenter_disable,
+#define TRACE_SYS_ENTER_PERF_INIT(sname)                                       \
+        .perf_event_enable = perf_sysenter_enable,                             \
+        .perf_event_disable = perf_sysenter_disable,
 
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)                                     \
-        .profile_enable = prof_sysexit_enable,                                 \
-        .profile_disable = prof_sysexit_disable,
+#define TRACE_SYS_EXIT_PERF_INIT(sname)                                        \
+        .perf_event_enable = perf_sysexit_enable,                              \
+        .perf_event_disable = perf_sysexit_disable,
 #else
-#define TRACE_SYS_ENTER_PROFILE(sname)
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
-#define TRACE_SYS_EXIT_PROFILE(sname)
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#define TRACE_SYS_ENTER_PERF(sname)
+#define TRACE_SYS_ENTER_PERF_INIT(sname)
+#define TRACE_SYS_EXIT_PERF(sname)
+#define TRACE_SYS_EXIT_PERF_INIT(sname)
 #endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -153,7 +153,7 @@ struct perf_event_attr;
                 .regfunc                = reg_event_syscall_enter,      \
                 .unregfunc              = unreg_event_syscall_enter,    \
                 .data                   = (void *)&__syscall_meta_##sname,\
-                TRACE_SYS_ENTER_PROFILE_INIT(sname)                     \
+                TRACE_SYS_ENTER_PERF_INIT(sname)                        \
         }
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)                                 \
@@ -175,7 +175,7 @@ struct perf_event_attr;
                 .regfunc                = reg_event_syscall_exit,       \
                 .unregfunc              = unreg_event_syscall_exit,     \
                 .data                   = (void *)&__syscall_meta_##sname,\
-                TRACE_SYS_EXIT_PROFILE_INIT(sname)                      \
+                TRACE_SYS_EXIT_PERF_INIT(sname)                 \
         }
 
 #define SYSCALL_METADATA(sname, nb)                             \