perf tools: Add mem access sampling core support
This patch adds the sorting and histogram support
functions to enable profiling of memory accesses.
The following sorting orders are added:
- symbol_daddr: data address symbol (or raw address)
- dso_daddr: data address shared object
- locked: access uses locked transaction
- tlb : TLB access
- mem : memory level of the access (L1, L2, L3, RAM, ...)
- snoop: access snoop mode
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1359040242-8269-12-git-send-email-eranian@google.com
[ committer note: changed to cope with fc5871ed, the move of methods to
machine.[ch], and the rename of dsrc to data_src, to match the change
made in the PERF_SAMPLE_DSRC in a previous patch. ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d66bcd3..32a1ef1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -198,11 +198,19 @@
}
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
- if (sym)
- ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
- width - ret,
- sym->name);
- else {
+ if (sym && map) {
+ if (map->type == MAP__VARIABLE) {
+ ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
+ ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
+ ip - sym->start);
+ ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+ width - ret, "");
+ } else {
+ ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+ width - ret,
+ sym->name);
+ }
+ } else {
size_t len = BITS_PER_LONG / 4;
ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
len, ip);
@@ -457,6 +465,304 @@
return repsep_snprintf(bf, size, "%-*s", width, out);
}
+/* --sort daddr_sym */
+static int64_t
+sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ uint64_t l = 0, r = 0;
+
+ if (left->mem_info)
+ l = left->mem_info->daddr.addr;
+ if (right->mem_info)
+ r = right->mem_info->daddr.addr;
+
+ return (int64_t)(r - l);
+}
+
+static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ uint64_t addr = 0;
+ struct map *map = NULL;
+ struct symbol *sym = NULL;
+
+ if (self->mem_info) {
+ addr = self->mem_info->daddr.addr;
+ map = self->mem_info->daddr.map;
+ sym = self->mem_info->daddr.sym;
+ }
+ return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size,
+ width);
+}
+
+static int64_t
+sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ struct map *map_l = NULL;
+ struct map *map_r = NULL;
+
+ if (left->mem_info)
+ map_l = left->mem_info->daddr.map;
+ if (right->mem_info)
+ map_r = right->mem_info->daddr.map;
+
+ return _sort__dso_cmp(map_l, map_r);
+}
+
+static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ struct map *map = NULL;
+
+ if (self->mem_info)
+ map = self->mem_info->daddr.map;
+
+ return _hist_entry__dso_snprintf(map, bf, size, width);
+}
+
+static int64_t
+sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ union perf_mem_data_src data_src_l;
+ union perf_mem_data_src data_src_r;
+
+ if (left->mem_info)
+ data_src_l = left->mem_info->data_src;
+ else
+ data_src_l.mem_lock = PERF_MEM_LOCK_NA;
+
+ if (right->mem_info)
+ data_src_r = right->mem_info->data_src;
+ else
+ data_src_r.mem_lock = PERF_MEM_LOCK_NA;
+
+ return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock);
+}
+
+static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ const char *out;
+ u64 mask = PERF_MEM_LOCK_NA;
+
+ if (self->mem_info)
+ mask = self->mem_info->data_src.mem_lock;
+
+ if (mask & PERF_MEM_LOCK_NA)
+ out = "N/A";
+ else if (mask & PERF_MEM_LOCK_LOCKED)
+ out = "Yes";
+ else
+ out = "No";
+
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ union perf_mem_data_src data_src_l;
+ union perf_mem_data_src data_src_r;
+
+ if (left->mem_info)
+ data_src_l = left->mem_info->data_src;
+ else
+ data_src_l.mem_dtlb = PERF_MEM_TLB_NA;
+
+ if (right->mem_info)
+ data_src_r = right->mem_info->data_src;
+ else
+ data_src_r.mem_dtlb = PERF_MEM_TLB_NA;
+
+ return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
+}
+
+static const char * const tlb_access[] = {
+ "N/A",
+ "HIT",
+ "MISS",
+ "L1",
+ "L2",
+ "Walker",
+ "Fault",
+};
+#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
+
+static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ char out[64];
+ size_t sz = sizeof(out) - 1; /* -1 for null termination */
+ size_t l = 0, i;
+ u64 m = PERF_MEM_TLB_NA;
+ u64 hit, miss;
+
+ out[0] = '\0';
+
+ if (self->mem_info)
+ m = self->mem_info->data_src.mem_dtlb;
+
+ hit = m & PERF_MEM_TLB_HIT;
+ miss = m & PERF_MEM_TLB_MISS;
+
+ /* already taken care of */
+ m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+ for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+ if (!(m & 0x1))
+ continue;
+ if (l) {
+ strcat(out, " or ");
+ l += 4;
+ }
+ strncat(out, tlb_access[i], sz - l);
+ l += strlen(tlb_access[i]);
+ }
+ if (*out == '\0')
+ strcpy(out, "N/A");
+ if (hit)
+ strncat(out, " hit", sz - l);
+ if (miss)
+ strncat(out, " miss", sz - l);
+
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ union perf_mem_data_src data_src_l;
+ union perf_mem_data_src data_src_r;
+
+ if (left->mem_info)
+ data_src_l = left->mem_info->data_src;
+ else
+ data_src_l.mem_lvl = PERF_MEM_LVL_NA;
+
+ if (right->mem_info)
+ data_src_r = right->mem_info->data_src;
+ else
+ data_src_r.mem_lvl = PERF_MEM_LVL_NA;
+
+ return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
+}
+
+static const char * const mem_lvl[] = {
+ "N/A",
+ "HIT",
+ "MISS",
+ "L1",
+ "LFB",
+ "L2",
+ "L3",
+ "Local RAM",
+ "Remote RAM (1 hop)",
+ "Remote RAM (2 hops)",
+ "Remote Cache (1 hop)",
+ "Remote Cache (2 hops)",
+ "I/O",
+ "Uncached",
+};
+#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
+
+static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ char out[64];
+ size_t sz = sizeof(out) - 1; /* -1 for null termination */
+ size_t i, l = 0;
+ u64 m = PERF_MEM_LVL_NA;
+ u64 hit, miss;
+
+ if (self->mem_info)
+ m = self->mem_info->data_src.mem_lvl;
+
+ out[0] = '\0';
+
+ hit = m & PERF_MEM_LVL_HIT;
+ miss = m & PERF_MEM_LVL_MISS;
+
+ /* already taken care of */
+ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+ for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+ if (!(m & 0x1))
+ continue;
+ if (l) {
+ strcat(out, " or ");
+ l += 4;
+ }
+ strncat(out, mem_lvl[i], sz - l);
+ l += strlen(mem_lvl[i]);
+ }
+ if (*out == '\0')
+ strcpy(out, "N/A");
+ if (hit)
+ strncat(out, " hit", sz - l);
+ if (miss)
+ strncat(out, " miss", sz - l);
+
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ union perf_mem_data_src data_src_l;
+ union perf_mem_data_src data_src_r;
+
+ if (left->mem_info)
+ data_src_l = left->mem_info->data_src;
+ else
+ data_src_l.mem_snoop = PERF_MEM_SNOOP_NA;
+
+ if (right->mem_info)
+ data_src_r = right->mem_info->data_src;
+ else
+ data_src_r.mem_snoop = PERF_MEM_SNOOP_NA;
+
+ return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
+}
+
+static const char * const snoop_access[] = {
+ "N/A",
+ "None",
+ "Miss",
+ "Hit",
+ "HitM",
+};
+#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
+
+static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf,
+ size_t size, unsigned int width)
+{
+ char out[64];
+ size_t sz = sizeof(out) - 1; /* -1 for null termination */
+ size_t i, l = 0;
+ u64 m = PERF_MEM_SNOOP_NA;
+
+ out[0] = '\0';
+
+ if (self->mem_info)
+ m = self->mem_info->data_src.mem_snoop;
+
+ for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+ if (!(m & 0x1))
+ continue;
+ if (l) {
+ strcat(out, " or ");
+ l += 4;
+ }
+ strncat(out, snoop_access[i], sz - l);
+ l += strlen(snoop_access[i]);
+ }
+
+ if (*out == '\0')
+ strcpy(out, "N/A");
+
+ return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
struct sort_entry sort_mispredict = {
.se_header = "Branch Mispredicted",
.se_cmp = sort__mispredict_cmp,
@@ -507,6 +813,48 @@
.se_width_idx = HISTC_GLOBAL_WEIGHT,
};
+struct sort_entry sort_mem_daddr_sym = {
+ .se_header = "Data Symbol",
+ .se_cmp = sort__daddr_cmp,
+ .se_snprintf = hist_entry__daddr_snprintf,
+ .se_width_idx = HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_daddr_dso = {
+ .se_header = "Data Object",
+ .se_cmp = sort__dso_daddr_cmp,
+ .se_snprintf = hist_entry__dso_daddr_snprintf,
+ .se_width_idx = HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_locked = {
+ .se_header = "Locked",
+ .se_cmp = sort__locked_cmp,
+ .se_snprintf = hist_entry__locked_snprintf,
+ .se_width_idx = HISTC_MEM_LOCKED,
+};
+
+struct sort_entry sort_mem_tlb = {
+ .se_header = "TLB access",
+ .se_cmp = sort__tlb_cmp,
+ .se_snprintf = hist_entry__tlb_snprintf,
+ .se_width_idx = HISTC_MEM_TLB,
+};
+
+struct sort_entry sort_mem_lvl = {
+ .se_header = "Memory access",
+ .se_cmp = sort__lvl_cmp,
+ .se_snprintf = hist_entry__lvl_snprintf,
+ .se_width_idx = HISTC_MEM_LVL,
+};
+
+struct sort_entry sort_mem_snoop = {
+ .se_header = "Snoop",
+ .se_cmp = sort__snoop_cmp,
+ .se_snprintf = hist_entry__snoop_snprintf,
+ .se_width_idx = HISTC_MEM_SNOOP,
+};
+
struct sort_dimension {
const char *name;
struct sort_entry *entry;
@@ -525,6 +873,12 @@
DIM(SORT_SRCLINE, "srcline", sort_srcline),
DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+ DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
+ DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
+ DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
+ DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
+ DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
+ DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
};
#undef DIM
@@ -561,7 +915,10 @@
return -EINVAL;
}
sort__has_parent = 1;
- } else if (sd->entry == &sort_sym) {
+ } else if (sd->entry == &sort_sym ||
+ sd->entry == &sort_sym_from ||
+ sd->entry == &sort_sym_to ||
+ sd->entry == &sort_mem_daddr_sym) {
sort__has_sym = 1;
}