Merge branch 'perf/core-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into perf/hw_breakpoints

Pull AMD range breakpoints support from Frederic Weisbecker:

" - Extend breakpoint tools and core to support address range through perf
    event with initial backend support for AMD extended breakpoints.

    Syntax is:

           perf record -e mem:addr/len:type

    For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)

           perf record -e mem:0x1000/512:w

 - Clean up a bit breakpoint code validation

 It has been acked by Jiri and Oleg. "

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 34 insertions, 18 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d07986f..486e84ccb1f9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,7 +79,7 @@ struct perf_branch_stack {
         struct perf_branch_entry        entries[0];
 };
 
-struct perf_regs_user {
+struct perf_regs {
         __u64           abi;
         struct pt_regs  *regs;
 };
@@ -580,34 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
 
 
 struct perf_sample_data {
-        u64                             type;
+        /*
+         * Fields set by perf_sample_data_init(), group so as to
+         * minimize the cachelines touched.
+         */
+        u64                             addr;
+        struct perf_raw_record          *raw;
+        struct perf_branch_stack        *br_stack;
+        u64                             period;
+        u64                             weight;
+        u64                             txn;
+        union  perf_mem_data_src        data_src;
 
+        /*
+         * The other fields, optionally {set,used} by
+         * perf_{prepare,output}_sample().
+         */
+        u64                             type;
         u64                             ip;
         struct {
                 u32     pid;
                 u32     tid;
         }                               tid_entry;
         u64                             time;
-        u64                             addr;
         u64                             id;
         u64                             stream_id;
         struct {
                 u32     cpu;
                 u32     reserved;
         }                               cpu_entry;
-        u64                             period;
-        union  perf_mem_data_src        data_src;
         struct perf_callchain_entry     *callchain;
-        struct perf_raw_record          *raw;
-        struct perf_branch_stack        *br_stack;
-        struct perf_regs_user           regs_user;
+        struct perf_regs                regs_user;
+        struct perf_regs                regs_intr;
         u64                             stack_user_size;
-        u64                             weight;
-        /*
-         * Transaction flags for abort events:
-         */
-        u64                             txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -624,9 +630,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
         data->raw  = NULL;
         data->br_stack = NULL;
         data->period = period;
-        data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-        data->regs_user.regs = NULL;
-        data->stack_user_size = 0;
         data->weight = 0;
         data->data_src.val = PERF_MEM_NA;
         data->txn = 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9d845404d875..9b79abbd1ab8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
         PERF_SAMPLE_DATA_SRC                    = 1U << 15,
         PERF_SAMPLE_IDENTIFIER                  = 1U << 16,
         PERF_SAMPLE_TRANSACTION                 = 1U << 17,
+        PERF_SAMPLE_REGS_INTR                   = 1U << 18,
 
-        PERF_SAMPLE_MAX = 1U << 18,             /* non-ABI */
+        PERF_SAMPLE_MAX = 1U << 19,             /* non-ABI */
 };
 
 /*
@@ -238,6 +239,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER2     80      /* add: branch_sample_type */
 #define PERF_ATTR_SIZE_VER3     96      /* add: sample_regs_user */
                                         /* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4     104     /* add: sample_regs_intr */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -334,6 +336,15 @@ struct perf_event_attr {
 
         /* Align to u64. */
         __u32   __reserved_2;
+        /*
+         * Defines set of regs to dump for each sample
+         * state captured on:
+         *  - precise = 0: PMU interrupt
+         *  - precise > 0: sampled instruction
+         *
+         * See asm/perf_regs.h for details.
+         */
+        __u64   sample_regs_intr;
 };
 
 #define perf_flags(attr)        (*(&(attr)->read_format + 1))
@@ -686,6 +697,8 @@ enum perf_event_type {
          *      { u64                   weight;   } && PERF_SAMPLE_WEIGHT
          *      { u64                   data_src; } && PERF_SAMPLE_DATA_SRC
          *      { u64                   transaction; } && PERF_SAMPLE_TRANSACTION
+         *      { u64                   abi; # enum perf_sample_regs_abi
+         *        u64                   regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
          * };
          */
         PERF_RECORD_SAMPLE                      = 9,