Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

[cascardo/linux.git] / include / linux / perf_event.h

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bd9f55a..f325786 100644 (file)
--- 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
@@ -1075,11 +1132,14 @@ struct perf_sample_data {
        struct perf_branch_stack        *br_stack;
 };
 
-static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr)
+static inline void perf_sample_data_init(struct perf_sample_data *data,
+                                        u64 addr, u64 period)
 {
+       /* remaining struct members initialized in perf_prepare_sample() */
        data->addr = addr;
        data->raw  = NULL;
        data->br_stack = NULL;
+       data->period    = period;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -1291,5 +1351,18 @@ 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 */