4 files changed, 94 insertions, 16 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index dd478fc8f9f5..5f3f3be5af09 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -144,12 +144,14 @@ struct event_filter;
 enum trace_reg {
         TRACE_REG_REGISTER,
         TRACE_REG_UNREGISTER,
+#ifdef CONFIG_PERF_EVENTS
         TRACE_REG_PERF_REGISTER,
         TRACE_REG_PERF_UNREGISTER,
         TRACE_REG_PERF_OPEN,
         TRACE_REG_PERF_CLOSE,
         TRACE_REG_PERF_ADD,
         TRACE_REG_PERF_DEL,
+#endif
 };
 
 struct ftrace_event_call;
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index a5375e7f3fea..645231c373c8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -430,16 +430,10 @@ extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
  * Most likely, you want to use tracing_on/tracing_off.
  */
 #ifdef CONFIG_RING_BUFFER
-void tracing_on(void);
-void tracing_off(void);
 /* trace_off_permanent stops recording with no way to bring it back */
 void tracing_off_permanent(void);
-int tracing_is_on(void);
 #else
-static inline void tracing_on(void) { }
-static inline void tracing_off(void) { }
 static inline void tracing_off_permanent(void) { }
-static inline int tracing_is_on(void) { return 0; }
 #endif
 
 enum ftrace_dump_mode {
@@ -449,6 +443,10 @@ enum ftrace_dump_mode {
 };
 
 #ifdef CONFIG_TRACING
+void tracing_on(void);
+void tracing_off(void);
+int tracing_is_on(void);
+
 extern void tracing_start(void);
 extern void tracing_stop(void);
 extern void ftrace_off_permanent(void);
@@ -533,6 +531,11 @@ static inline void tracing_start(void) { }
 static inline void tracing_stop(void) { }
 static inline void ftrace_off_permanent(void) { }
 static inline void trace_dump_stack(void) { }
+
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline int tracing_is_on(void) { return 0; }
+
 static inline int
 trace_printk(const char *fmt, ...)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bd9f55a5958d..ddbb6a901f65 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -299,18 +299,31 @@ struct perf_event_mmap_page {
         /*
          * Bits needed to read the hw events in user-space.
          *
-         *   u32 seq;
-         *   s64 count;
+         *   u32 seq, time_mult, time_shift, idx, width;
+         *   u64 count, enabled, running;
+         *   u64 cyc, time_offset;
+         *   s64 pmc = 0;
          *
          *   do {
          *     seq = pc->lock;
-         *
          *     barrier()
-         *     if (pc->index) {
-         *       count = pmc_read(pc->index - 1);
-         *       count += pc->offset;
-         *     } else
-         *       goto regular_read;
+         *
+         *     enabled = pc->time_enabled;
+         *     running = pc->time_running;
+         *
+         *     if (pc->cap_usr_time && enabled != running) {
+         *       cyc = rdtsc();
+         *       time_offset = pc->time_offset;
+         *       time_mult   = pc->time_mult;
+         *       time_shift  = pc->time_shift;
+         *     }
+         *
+         *     idx = pc->index;
+         *     count = pc->offset;
+         *     if (pc->cap_usr_rdpmc && idx) {
+         *       width = pc->pmc_width;
+         *       pmc = rdpmc(idx - 1);
+         *     }
          *
          *     barrier();
          *   } while (pc->lock != seq);
@@ -323,14 +336,57 @@ struct perf_event_mmap_page {
         __s64   offset;                 /* add to hardware event value */
         __u64   time_enabled;           /* time event active */
         __u64   time_running;           /* time event on cpu */
-        __u32   time_mult, time_shift;
+        union {
+                __u64   capabilities;
+                __u64   cap_usr_time  : 1,
+                        cap_usr_rdpmc : 1,
+                        cap_____res   : 62;
+        };
+
+        /*
+         * If cap_usr_rdpmc this field provides the bit-width of the value
+         * read using the rdpmc() or equivalent instruction. This can be used
+         * to sign extend the result like:
+         *
+         *   pmc <<= 64 - width;
+         *   pmc >>= 64 - width; // signed shift right
+         *   count += pmc;
+         */
+        __u16   pmc_width;
+
+        /*
+         * If cap_usr_time the below fields can be used to compute the time
+         * delta since time_enabled (in ns) using rdtsc or similar.
+         *
+         *   u64 quot, rem;
+         *   u64 delta;
+         *
+         *   quot = (cyc >> time_shift);
+         *   rem = cyc & ((1 << time_shift) - 1);
+         *   delta = time_offset + quot * time_mult +
+         *              ((rem * time_mult) >> time_shift);
+         *
+         * Where time_offset,time_mult,time_shift and cyc are read in the
+         * seqcount loop described above. This delta can then be added to
+         * enabled and possible running (if idx), improving the scaling:
+         *
+         *   enabled += delta;
+         *   if (idx)
+         *     running += delta;
+         *
+         *   quot = count / running;
+         *   rem  = count % running;
+         *   count = quot * enabled + (rem * enabled) / running;
+         */
+        __u16   time_shift;
+        __u32   time_mult;
         __u64   time_offset;
 
                 /*
                  * Hole for extension of the self monitor capabilities
                  */
 
-        __u64   __reserved[121];        /* align to 1k */
+        __u64   __reserved[120];        /* align to 1k */
 
         /*
          * Control data for the mmap() data buffer.
@@ -550,6 +606,7 @@ struct perf_guest_info_callbacks {
 #include <linux/irq_work.h>
 #include <linux/static_key.h>
 #include <linux/atomic.h>
+#include <linux/sysfs.h>
 #include <asm/local.h>
 
 #define PERF_MAX_STACK_DEPTH            255
@@ -1291,5 +1348,18 @@ do {									\
         register_cpu_notifier(&fn##_nb);                                \
 } while (0)
 
+
+#define PMU_FORMAT_ATTR(_name, _format)                                 \
+static ssize_t                                                          \
+_name##_show(struct device *dev,                                        \
+                               struct device_attribute *attr,           \
+                               char *page)                              \
+{                                                                       \
+        BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);                     \
+        return sprintf(page, _format "\n");                             \
+}                                                                       \
+                                                                        \
+static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 67be0376d8e3..7be2e88f23fd 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_record_disable(struct ring_buffer *buffer);
 void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_off(struct ring_buffer *buffer);
+void ring_buffer_record_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);