From: Kan Liang <[email protected]>
The patch series is to support PERF_SAMPLE_PHYS_ADDR in user perf tool.
The kernel patch has been merged, which commit ID is
fc7ce9c74c3a ("perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR").
Changes since V1:
- Don't mandate SAMPLE_ADDR when SAMPLE_PHYS_ADDR
- Update change log
Kan Liang (5):
perf tools: support new sample type for physical address
perf tools: add sort option for physical address
perf mem: support physical address
perf script: support physical address
perf test: add test case for PERF_SAMPLE_PHYS_ADDR
tools/include/uapi/linux/perf_event.h | 4 +-
tools/perf/Documentation/perf-mem.txt | 4 ++
tools/perf/Documentation/perf-record.txt | 5 +-
tools/perf/Documentation/perf-report.txt | 1 +
tools/perf/Documentation/perf-script.txt | 2 +-
tools/perf/builtin-mem.c | 97 +++++++++++++++++++++++---------
tools/perf/builtin-record.c | 2 +
tools/perf/builtin-script.c | 15 ++++-
tools/perf/perf.h | 1 +
tools/perf/tests/sample-parsing.c | 6 +-
tools/perf/util/event.h | 1 +
tools/perf/util/evsel.c | 17 ++++++
tools/perf/util/hist.c | 4 ++
tools/perf/util/hist.h | 1 +
tools/perf/util/machine.c | 8 ++-
tools/perf/util/session.c | 3 +
tools/perf/util/sort.c | 42 ++++++++++++++
tools/perf/util/sort.h | 1 +
tools/perf/util/symbol.h | 1 +
19 files changed, 181 insertions(+), 34 deletions(-)
--
2.4.3
From: Kan Liang <[email protected]>
Add option phys-data in perf mem to record/report physical address.
The default mem sort order for physical address is changed accordingly.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/Documentation/perf-mem.txt | 4 ++
tools/perf/builtin-mem.c | 97 +++++++++++++++++++++++++----------
2 files changed, 75 insertions(+), 26 deletions(-)
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 7349632..4be08a1 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
--ldload::
Specify desired latency for loads event.
+-p::
+--phys-data::
+ Record/Report sample physical addresses
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c02..0f15634 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -23,6 +23,7 @@ struct perf_mem {
bool hide_unresolved;
bool dump_raw;
bool force;
+ bool phys_addr;
int operation;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
rec_argv[i++] = "-d";
+ if (mem->phys_addr)
+ rec_argv[i++] = "--phys-data";
+
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
if (!perf_mem_events[j].record)
continue;
@@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool,
if (al.map != NULL)
al.map->dso->hit = 1;
- if (symbol_conf.field_sep) {
- fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
- "%s0x%"PRIx64"%s%s:%s\n";
+ if (mem->phys_addr) {
+ if (symbol_conf.field_sep) {
+ fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+ "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+ } else {
+ fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+ "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+ "%s%s:%s\n";
+ symbol_conf.field_sep = " ";
+ }
+
+ printf(fmt,
+ sample->pid,
+ symbol_conf.field_sep,
+ sample->tid,
+ symbol_conf.field_sep,
+ sample->ip,
+ symbol_conf.field_sep,
+ sample->addr,
+ symbol_conf.field_sep,
+ sample->phys_addr,
+ symbol_conf.field_sep,
+ sample->weight,
+ symbol_conf.field_sep,
+ sample->data_src,
+ symbol_conf.field_sep,
+ al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+ al.sym ? al.sym->name : "???");
} else {
- fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
- "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
- symbol_conf.field_sep = " ";
- }
+ if (symbol_conf.field_sep) {
+ fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+ "%s0x%"PRIx64"%s%s:%s\n";
+ } else {
+ fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+ "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+ symbol_conf.field_sep = " ";
+ }
- printf(fmt,
- sample->pid,
- symbol_conf.field_sep,
- sample->tid,
- symbol_conf.field_sep,
- sample->ip,
- symbol_conf.field_sep,
- sample->addr,
- symbol_conf.field_sep,
- sample->weight,
- symbol_conf.field_sep,
- sample->data_src,
- symbol_conf.field_sep,
- al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
- al.sym ? al.sym->name : "???");
+ printf(fmt,
+ sample->pid,
+ symbol_conf.field_sep,
+ sample->tid,
+ symbol_conf.field_sep,
+ sample->ip,
+ symbol_conf.field_sep,
+ sample->addr,
+ symbol_conf.field_sep,
+ sample->weight,
+ symbol_conf.field_sep,
+ sample->data_src,
+ symbol_conf.field_sep,
+ al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+ al.sym ? al.sym->name : "???");
+ }
out_put:
addr_location__put(&al);
return 0;
@@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem)
if (ret < 0)
goto out_delete;
- printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+ if (mem->phys_addr)
+ printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+ else
+ printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
ret = perf_session__process_events(session);
@@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
* there is no weight (cost) associated with stores, so don't print
* the column
*/
- if (!(mem->operation & MEM_OPERATION_LOAD))
- rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
- "dso_daddr,tlb,locked";
+ if (!(mem->operation & MEM_OPERATION_LOAD)) {
+ if (mem->phys_addr)
+ rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+ "dso_daddr,tlb,locked,phys_daddr";
+ else
+ rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+ "dso_daddr,tlb,locked";
+ } else if (mem->phys_addr)
+ rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+ "dso_daddr,snoop,tlb,locked,phys_daddr";
for (j = 1; j < argc; j++, i++)
rep_argv[i] = argv[j];
@@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv)
"separator for columns, no spaces will be added"
" between columns '.' is reserved."),
OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+ OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
OPT_END()
};
const char *const mem_subcommands[] = { "record", "report", NULL };
--
2.4.3
From: Kan Liang <[email protected]>
Add a new sort option phys_daddr for --mem-mode sort.
With this option applied, perf can sort and report by sample's physical
address.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/Documentation/perf-report.txt | 1 +
tools/perf/util/hist.c | 4 +++
tools/perf/util/hist.h | 1 +
tools/perf/util/machine.c | 8 ++++--
tools/perf/util/session.c | 3 +++
tools/perf/util/sort.c | 42 ++++++++++++++++++++++++++++++++
tools/perf/util/sort.h | 1 +
tools/perf/util/symbol.h | 1 +
8 files changed, 59 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa8461..383a98d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
- mem: type of memory access for the data at the time of the sample
- snoop: type of snoop (if any) for the data at the time of the sample
- dcacheline: the cacheline the data address is on at the time of the sample
+ - phys_daddr: physical address of data being executed on at the time of sample
And the default sort keys are changed to local_weight, mem, sym, dso,
symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 9453b2e..e60d8d8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -167,6 +167,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
symlen = unresolved_col_width + 4 + 2;
hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
}
+
+ hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
+ unresolved_col_width + 4 + 2);
+
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee3670a..e60dda2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
HISTC_GLOBAL_WEIGHT,
HISTC_MEM_DADDR_SYMBOL,
HISTC_MEM_DADDR_DSO,
+ HISTC_MEM_PHYS_DADDR,
HISTC_MEM_LOCKED,
HISTC_MEM_TLB,
HISTC_MEM_LVL,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5c8eaca..879e64e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1635,10 +1635,12 @@ static void ip__resolve_ams(struct thread *thread,
ams->al_addr = al.addr;
ams->sym = al.sym;
ams->map = al.map;
+ ams->phys_addr = 0;
}
static void ip__resolve_data(struct thread *thread,
- u8 m, struct addr_map_symbol *ams, u64 addr)
+ u8 m, struct addr_map_symbol *ams,
+ u64 addr, u64 phys_addr)
{
struct addr_location al;
@@ -1658,6 +1660,7 @@ static void ip__resolve_data(struct thread *thread,
ams->al_addr = al.addr;
ams->sym = al.sym;
ams->map = al.map;
+ ams->phys_addr = phys_addr;
}
struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -1669,7 +1672,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
return NULL;
ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
- ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
+ ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+ sample->addr, sample->phys_addr);
mi->data_src.val = sample->data_src;
return mi;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index dc453f8..5348d5c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1120,6 +1120,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
if (sample_type & PERF_SAMPLE_DATA_SRC)
printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
+ if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+ printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+
if (sample_type & PERF_SAMPLE_TRANSACTION)
printf("... transaction: %" PRIx64 "\n", sample->transaction);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 12359bd..eb3ab90 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1316,6 +1316,47 @@ struct sort_entry sort_mem_dcacheline = {
};
static int64_t
+sort__phys_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.phys_addr;
+ if (right->mem_info)
+ r = right->mem_info->daddr.phys_addr;
+
+ return (int64_t)(r - l);
+}
+
+static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ uint64_t addr = 0;
+ size_t ret = 0;
+ size_t len = BITS_PER_LONG / 4;
+
+ addr = he->mem_info->daddr.phys_addr;
+
+ ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
+
+ ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr);
+
+ ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, "");
+
+ if (ret > width)
+ bf[width] = '\0';
+
+ return width;
+}
+
+struct sort_entry sort_mem_phys_daddr = {
+ .se_header = "Data Physical Address",
+ .se_cmp = sort__phys_daddr_cmp,
+ .se_snprintf = hist_entry__phys_daddr_snprintf,
+ .se_width_idx = HISTC_MEM_PHYS_DADDR,
+};
+
+static int64_t
sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (!left->branch_info || !right->branch_info)
@@ -1547,6 +1588,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+ DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
};
#undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b7c7559..f36dc49 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -245,6 +245,7 @@ enum sort_type {
SORT_MEM_SNOOP,
SORT_MEM_DCACHELINE,
SORT_MEM_IADDR_SYMBOL,
+ SORT_MEM_PHYS_DADDR,
};
/*
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index d00a012..2bd6a1f 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -186,6 +186,7 @@ struct addr_map_symbol {
struct symbol *sym;
u64 addr;
u64 al_addr;
+ u64 phys_addr;
};
struct branch_info {
--
2.4.3
From: Kan Liang <[email protected]>
Display the physical address at the tail if it is available.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/Documentation/perf-script.txt | 2 +-
tools/perf/builtin-script.c | 15 +++++++++++++--
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796..18dfcfa 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
- callindent, insn, insnlen, synth.
+ callindent, insn, insnlen, synth, phys_addr.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 378f76c..3d4c3b5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -87,6 +87,7 @@ enum perf_output_field {
PERF_OUTPUT_BRSTACKINSN = 1U << 23,
PERF_OUTPUT_BRSTACKOFF = 1U << 24,
PERF_OUTPUT_SYNTH = 1U << 25,
+ PERF_OUTPUT_PHYS_ADDR = 1U << 26,
};
struct output_option {
@@ -119,6 +120,7 @@ struct output_option {
{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
{.str = "synth", .field = PERF_OUTPUT_SYNTH},
+ {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
};
enum {
@@ -175,7 +177,8 @@ static struct {
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR |
- PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+ PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+ PERF_OUTPUT_PHYS_ADDR,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -382,6 +385,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
PERF_OUTPUT_IREGS))
return -EINVAL;
+ if (PRINT_FIELD(PHYS_ADDR) &&
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+ PERF_OUTPUT_PHYS_ADDR))
+ return -EINVAL;
+
return 0;
}
@@ -1446,6 +1454,9 @@ static void process_event(struct perf_script *script,
if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
print_sample_bpf_output(sample);
print_insn(sample, attr, thread, machine);
+
+ if (PRINT_FIELD(PHYS_ADDR))
+ printf("%16" PRIx64, sample->phys_addr);
printf("\n");
}
@@ -2729,7 +2740,7 @@ int cmd_script(int argc, const char **argv)
"Valid types: hw,sw,trace,raw,synth. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,period,iregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+ "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
--
2.4.3
From: Kan Liang <[email protected]>
Extend sample-parsing test cases to support new sample type
PERF_SAMPLE_PHYS_ADDR.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/tests/sample-parsing.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 6d028f4..c385848 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -141,6 +141,9 @@ static bool samples_same(const struct perf_sample *s1,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR)
+ COMP(phys_addr);
+
return true;
}
@@ -206,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
.mask = sample_regs,
.regs = regs,
},
+ .phys_addr = 113,
};
struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
struct perf_sample sample_out;
@@ -305,7 +309,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
* were added. Please actually update the test rather than just change
* the condition below.
*/
- if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+ if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) {
pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
return -1;
}
--
2.4.3
From: Kan Liang <[email protected]>
Support new sample type PERF_SAMPLE_PHYS_ADDR for physical address.
Add new option --phys-data to record sample physical address.
Signed-off-by: Kan Liang <[email protected]>
---
tools/include/uapi/linux/perf_event.h | 4 +++-
tools/perf/Documentation/perf-record.txt | 5 ++++-
tools/perf/builtin-record.c | 2 ++
tools/perf/perf.h | 1 +
tools/perf/util/event.h | 1 +
tools/perf/util/evsel.c | 17 +++++++++++++++++
6 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 2a37ae9..140ae63 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_IDENTIFIER = 1U << 16,
PERF_SAMPLE_TRANSACTION = 1U << 17,
PERF_SAMPLE_REGS_INTR = 1U << 18,
+ PERF_SAMPLE_PHYS_ADDR = 1U << 19,
- PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
};
/*
@@ -814,6 +815,7 @@ enum perf_event_type {
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+ * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR
* };
*/
PERF_RECORD_SAMPLE = 9,
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9bdea04..e397453 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -249,7 +249,10 @@ OPTIONS
-d::
--data::
- Record the sample addresses.
+ Record the sample virtual addresses.
+
+--phys-data::
+ Record the sample physical addresses.
-T::
--timestamp::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 36d7117..56f8142 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1604,6 +1604,8 @@ static struct option __record_options[] = {
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+ OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+ "Record the sample physical addresses"),
OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
&record.opts.sample_time_set,
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2c010dd..dc442ba 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -43,6 +43,7 @@ struct record_opts {
bool no_samples;
bool raw_samples;
bool sample_address;
+ bool sample_phys_addr;
bool sample_weight;
bool sample_time;
bool sample_time_set;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 423ac82..ee7bcc8 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -200,6 +200,7 @@ struct perf_sample {
u32 cpu;
u32 raw_size;
u64 data_src;
+ u64 phys_addr;
u32 flags;
u16 insn_len;
u8 cpumode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a5888c7..228a78d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -950,6 +950,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
if (opts->sample_address)
perf_evsel__set_sample_bit(evsel, DATA_SRC);
+ if (opts->sample_phys_addr)
+ perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+
if (opts->no_buffering) {
attr->watermark = 0;
attr->wakeup_events = 1;
@@ -2201,6 +2204,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
}
}
+ data->phys_addr = 0;
+ if (type & PERF_SAMPLE_PHYS_ADDR) {
+ data->phys_addr = *array;
+ array++;
+ }
+
return 0;
}
@@ -2306,6 +2315,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR)
+ result += sizeof(u64);
+
return result;
}
@@ -2495,6 +2507,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR) {
+ *array = sample->phys_addr;
+ array++;
+ }
+
return 0;
}
--
2.4.3
On Tue, Aug 29, 2017 at 01:11:08PM -0400, [email protected] wrote:
SNIP
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index a5888c7..228a78d 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -950,6 +950,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
> if (opts->sample_address)
> perf_evsel__set_sample_bit(evsel, DATA_SRC);
>
> + if (opts->sample_phys_addr)
> + perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
> +
> if (opts->no_buffering) {
> attr->watermark = 0;
> attr->wakeup_events = 1;
> @@ -2201,6 +2204,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
> }
> }
>
> + data->phys_addr = 0;
> + if (type & PERF_SAMPLE_PHYS_ADDR) {
> + data->phys_addr = *array;
> + array++;
> + }
> +
> return 0;
> }
>
> @@ -2306,6 +2315,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
> }
> }
>
> + if (type & PERF_SAMPLE_PHYS_ADDR)
> + result += sizeof(u64);
> +
> return result;
> }
>
> @@ -2495,6 +2507,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
> }
> }
>
> + if (type & PERF_SAMPLE_PHYS_ADDR) {
> + *array = sample->phys_addr;
> + array++;
> + }
> +
> return 0;
> }
>
missing the printing bits
jirka
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e705c0d59a69..4bb89373eb52 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1467,7 +1467,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
- bit_name(WEIGHT),
+ bit_name(WEIGHT), bit_name(PHYS_ADDR),
{ .name = NULL, }
};
#undef bit_name
Em Fri, Sep 01, 2017 at 05:28:27PM +0200, Jiri Olsa escreveu:
> On Tue, Aug 29, 2017 at 01:11:08PM -0400, [email protected] wrote:
>
> SNIP
>
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index a5888c7..228a78d 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -950,6 +950,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
> > if (opts->sample_address)
> > perf_evsel__set_sample_bit(evsel, DATA_SRC);
> >
> > + if (opts->sample_phys_addr)
> > + perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
> > +
> > if (opts->no_buffering) {
> > attr->watermark = 0;
> > attr->wakeup_events = 1;
> > @@ -2201,6 +2204,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
> > }
> > }
> >
> > + data->phys_addr = 0;
> > + if (type & PERF_SAMPLE_PHYS_ADDR) {
> > + data->phys_addr = *array;
> > + array++;
> > + }
> > +
> > return 0;
> > }
> >
> > @@ -2306,6 +2315,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
> > }
> > }
> >
> > + if (type & PERF_SAMPLE_PHYS_ADDR)
> > + result += sizeof(u64);
> > +
> > return result;
> > }
> >
> > @@ -2495,6 +2507,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
> > }
> > }
> >
> > + if (type & PERF_SAMPLE_PHYS_ADDR) {
> > + *array = sample->phys_addr;
> > + array++;
> > + }
> > +
> > return 0;
> > }
> >
>
> missing the printing bits
I'm folding this one there then,
- Arnaldo
> jirka
>
>
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index e705c0d59a69..4bb89373eb52 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1467,7 +1467,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
> bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
> bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
> bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
> - bit_name(WEIGHT),
> + bit_name(WEIGHT), bit_name(PHYS_ADDR),
> { .name = NULL, }
> };
> #undef bit_name
On Tue, Aug 29, 2017 at 01:11:07PM -0400, [email protected] wrote:
> From: Kan Liang <[email protected]>
>
> The patch series is to support PERF_SAMPLE_PHYS_ADDR in user perf tool.
> The kernel patch has been merged, which commit ID is
> fc7ce9c74c3a ("perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR").
>
> Changes since V1:
> - Don't mandate SAMPLE_ADDR when SAMPLE_PHYS_ADDR
> - Update change log
>
> Kan Liang (5):
> perf tools: support new sample type for physical address
> perf tools: add sort option for physical address
> perf mem: support physical address
> perf script: support physical address
> perf test: add test case for PERF_SAMPLE_PHYS_ADDR
apart from the nit in patch 1
Tested/Acked-by: Jiri Olsa <[email protected]>
thanks,
jirka
Em Fri, Sep 01, 2017 at 05:45:02PM +0200, Jiri Olsa escreveu:
> On Tue, Aug 29, 2017 at 01:11:07PM -0400, [email protected] wrote:
> > From: Kan Liang <[email protected]>
> >
> > The patch series is to support PERF_SAMPLE_PHYS_ADDR in user perf tool.
> > The kernel patch has been merged, which commit ID is
> > fc7ce9c74c3a ("perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR").
> >
> > Changes since V1:
> > - Don't mandate SAMPLE_ADDR when SAMPLE_PHYS_ADDR
> > - Update change log
> >
> > Kan Liang (5):
> > perf tools: support new sample type for physical address
> > perf tools: add sort option for physical address
> > perf mem: support physical address
> > perf script: support physical address
> > perf test: add test case for PERF_SAMPLE_PHYS_ADDR
>
> apart from the nit in patch 1
Which I folded your patch into
> Tested/Acked-by: Jiri Olsa <[email protected]>
I think in this case a Tested-by: is a super ack, right?
So I'll leave it as:
Tested-by: Jiri Olsa <[email protected]>
Ok?
- Arnaldo
On Fri, Sep 01, 2017 at 02:39:48PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Fri, Sep 01, 2017 at 05:45:02PM +0200, Jiri Olsa escreveu:
> > On Tue, Aug 29, 2017 at 01:11:07PM -0400, [email protected] wrote:
> > > From: Kan Liang <[email protected]>
> > >
> > > The patch series is to support PERF_SAMPLE_PHYS_ADDR in user perf tool.
> > > The kernel patch has been merged, which commit ID is
> > > fc7ce9c74c3a ("perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR").
> > >
> > > Changes since V1:
> > > - Don't mandate SAMPLE_ADDR when SAMPLE_PHYS_ADDR
> > > - Update change log
> > >
> > > Kan Liang (5):
> > > perf tools: support new sample type for physical address
> > > perf tools: add sort option for physical address
> > > perf mem: support physical address
> > > perf script: support physical address
> > > perf test: add test case for PERF_SAMPLE_PHYS_ADDR
> >
> > apart from the nit in patch 1
>
> Which I folded your patch into
>
> > Tested/Acked-by: Jiri Olsa <[email protected]>
>
> I think in this case a Tested-by: is a super ack, right?
>
> So I'll leave it as:
>
> Tested-by: Jiri Olsa <[email protected]>
>
> Ok?
ook ;-)
jirka
Commit-ID: 3b0a5daa061076b2b75ffc294e74483ad9bf241a
Gitweb: http://git.kernel.org/tip/3b0a5daa061076b2b75ffc294e74483ad9bf241a
Author: Kan Liang <[email protected]>
AuthorDate: Tue, 29 Aug 2017 13:11:08 -0400
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 1 Sep 2017 14:46:00 -0300
perf tools: Support new sample type for physical address
Support new sample type PERF_SAMPLE_PHYS_ADDR for physical address.
Add new option --phys-data to record sample physical address.
Signed-off-by: Kan Liang <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Acked-by: Stephane Eranian <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
[ Added missing printing in evsel.c patch sent by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/include/uapi/linux/perf_event.h | 4 +++-
tools/perf/Documentation/perf-record.txt | 5 ++++-
tools/perf/builtin-record.c | 2 ++
tools/perf/perf.h | 1 +
tools/perf/util/event.h | 1 +
tools/perf/util/evsel.c | 19 ++++++++++++++++++-
6 files changed, 29 insertions(+), 3 deletions(-)
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 2a37ae9..140ae63 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_IDENTIFIER = 1U << 16,
PERF_SAMPLE_TRANSACTION = 1U << 17,
PERF_SAMPLE_REGS_INTR = 1U << 18,
+ PERF_SAMPLE_PHYS_ADDR = 1U << 19,
- PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */
};
/*
@@ -814,6 +815,7 @@ enum perf_event_type {
* { u64 transaction; } && PERF_SAMPLE_TRANSACTION
* { u64 abi; # enum perf_sample_regs_abi
* u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+ * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR
* };
*/
PERF_RECORD_SAMPLE = 9,
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9bdea04..e397453 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -249,7 +249,10 @@ OPTIONS
-d::
--data::
- Record the sample addresses.
+ Record the sample virtual addresses.
+
+--phys-data::
+ Record the sample physical addresses.
-T::
--timestamp::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 36d7117..56f8142 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1604,6 +1604,8 @@ static struct option __record_options[] = {
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+ OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+ "Record the sample physical addresses"),
OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
&record.opts.sample_time_set,
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2c010dd..dc442ba 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -43,6 +43,7 @@ struct record_opts {
bool no_samples;
bool raw_samples;
bool sample_address;
+ bool sample_phys_addr;
bool sample_weight;
bool sample_time;
bool sample_time_set;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 423ac82..ee7bcc8 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -200,6 +200,7 @@ struct perf_sample {
u32 cpu;
u32 raw_size;
u64 data_src;
+ u64 phys_addr;
u32 flags;
u16 insn_len;
u8 cpumode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9bd632..4bb8937 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -955,6 +955,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
if (opts->sample_address)
perf_evsel__set_sample_bit(evsel, DATA_SRC);
+ if (opts->sample_phys_addr)
+ perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+
if (opts->no_buffering) {
attr->watermark = 0;
attr->wakeup_events = 1;
@@ -1464,7 +1467,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
- bit_name(WEIGHT),
+ bit_name(WEIGHT), bit_name(PHYS_ADDR),
{ .name = NULL, }
};
#undef bit_name
@@ -2206,6 +2209,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
}
}
+ data->phys_addr = 0;
+ if (type & PERF_SAMPLE_PHYS_ADDR) {
+ data->phys_addr = *array;
+ array++;
+ }
+
return 0;
}
@@ -2311,6 +2320,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR)
+ result += sizeof(u64);
+
return result;
}
@@ -2500,6 +2512,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR) {
+ *array = sample->phys_addr;
+ array++;
+ }
+
return 0;
}
Commit-ID: 8780fb25ab060bafa5a8149e79b703e0fc7ee847
Gitweb: http://git.kernel.org/tip/8780fb25ab060bafa5a8149e79b703e0fc7ee847
Author: Kan Liang <[email protected]>
AuthorDate: Tue, 29 Aug 2017 13:11:09 -0400
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 1 Sep 2017 14:46:11 -0300
perf sort: Add sort option for physical address
Add a new sort option "phys_daddr" for --mem-mode sort. With this
option applied, perf can sort and report by sample's physical address.
Signed-off-by: Kan Liang <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Acked-by: Stephane Eranian <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/perf/Documentation/perf-report.txt | 1 +
tools/perf/util/hist.c | 4 +++
tools/perf/util/hist.h | 1 +
tools/perf/util/machine.c | 8 ++++--
tools/perf/util/session.c | 3 +++
tools/perf/util/sort.c | 42 ++++++++++++++++++++++++++++++++
tools/perf/util/sort.h | 1 +
tools/perf/util/symbol.h | 1 +
8 files changed, 59 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa8461..383a98d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
- mem: type of memory access for the data at the time of the sample
- snoop: type of snoop (if any) for the data at the time of the sample
- dcacheline: the cacheline the data address is on at the time of the sample
+ - phys_daddr: physical address of data being executed on at the time of sample
And the default sort keys are changed to local_weight, mem, sym, dso,
symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 9453b2e..e60d8d8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -167,6 +167,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
symlen = unresolved_col_width + 4 + 2;
hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
}
+
+ hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
+ unresolved_col_width + 4 + 2);
+
} else {
symlen = unresolved_col_width + 4 + 2;
hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee3670a..e60dda2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
HISTC_GLOBAL_WEIGHT,
HISTC_MEM_DADDR_SYMBOL,
HISTC_MEM_DADDR_DSO,
+ HISTC_MEM_PHYS_DADDR,
HISTC_MEM_LOCKED,
HISTC_MEM_TLB,
HISTC_MEM_LVL,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9eaa953..df70936 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1635,10 +1635,12 @@ static void ip__resolve_ams(struct thread *thread,
ams->al_addr = al.addr;
ams->sym = al.sym;
ams->map = al.map;
+ ams->phys_addr = 0;
}
static void ip__resolve_data(struct thread *thread,
- u8 m, struct addr_map_symbol *ams, u64 addr)
+ u8 m, struct addr_map_symbol *ams,
+ u64 addr, u64 phys_addr)
{
struct addr_location al;
@@ -1658,6 +1660,7 @@ static void ip__resolve_data(struct thread *thread,
ams->al_addr = al.addr;
ams->sym = al.sym;
ams->map = al.map;
+ ams->phys_addr = phys_addr;
}
struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -1669,7 +1672,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
return NULL;
ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
- ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
+ ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+ sample->addr, sample->phys_addr);
mi->data_src.val = sample->data_src;
return mi;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ac86369..a7ebd9f 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1120,6 +1120,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
if (sample_type & PERF_SAMPLE_DATA_SRC)
printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
+ if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+ printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+
if (sample_type & PERF_SAMPLE_TRANSACTION)
printf("... transaction: %" PRIx64 "\n", sample->transaction);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 12359bd..eb3ab90 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1316,6 +1316,47 @@ struct sort_entry sort_mem_dcacheline = {
};
static int64_t
+sort__phys_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.phys_addr;
+ if (right->mem_info)
+ r = right->mem_info->daddr.phys_addr;
+
+ return (int64_t)(r - l);
+}
+
+static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ uint64_t addr = 0;
+ size_t ret = 0;
+ size_t len = BITS_PER_LONG / 4;
+
+ addr = he->mem_info->daddr.phys_addr;
+
+ ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
+
+ ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr);
+
+ ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, "");
+
+ if (ret > width)
+ bf[width] = '\0';
+
+ return width;
+}
+
+struct sort_entry sort_mem_phys_daddr = {
+ .se_header = "Data Physical Address",
+ .se_cmp = sort__phys_daddr_cmp,
+ .se_snprintf = hist_entry__phys_daddr_snprintf,
+ .se_width_idx = HISTC_MEM_PHYS_DADDR,
+};
+
+static int64_t
sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (!left->branch_info || !right->branch_info)
@@ -1547,6 +1588,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+ DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
};
#undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b7c7559..f36dc49 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -245,6 +245,7 @@ enum sort_type {
SORT_MEM_SNOOP,
SORT_MEM_DCACHELINE,
SORT_MEM_IADDR_SYMBOL,
+ SORT_MEM_PHYS_DADDR,
};
/*
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index d00a012..2bd6a1f 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -186,6 +186,7 @@ struct addr_map_symbol {
struct symbol *sym;
u64 addr;
u64 al_addr;
+ u64 phys_addr;
};
struct branch_info {
Commit-ID: c35aeb9dfe512422ca9ea28aae692c8f1d052b2d
Gitweb: http://git.kernel.org/tip/c35aeb9dfe512422ca9ea28aae692c8f1d052b2d
Author: Kan Liang <[email protected]>
AuthorDate: Tue, 29 Aug 2017 13:11:10 -0400
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 1 Sep 2017 14:46:23 -0300
perf mem: Support physical address
Add option phys-data in "perf mem" to record/report physical address.
The default mem sort order for physical address is changed accordingly.
Signed-off-by: Kan Liang <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Acked-by: Stephane Eranian <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/perf/Documentation/perf-mem.txt | 4 ++
tools/perf/builtin-mem.c | 97 +++++++++++++++++++++++++----------
2 files changed, 75 insertions(+), 26 deletions(-)
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 7349632..4be08a1 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
--ldload::
Specify desired latency for loads event.
+-p::
+--phys-data::
+ Record/Report sample physical addresses
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c02..0f15634 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -23,6 +23,7 @@ struct perf_mem {
bool hide_unresolved;
bool dump_raw;
bool force;
+ bool phys_addr;
int operation;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
rec_argv[i++] = "-d";
+ if (mem->phys_addr)
+ rec_argv[i++] = "--phys-data";
+
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
if (!perf_mem_events[j].record)
continue;
@@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool,
if (al.map != NULL)
al.map->dso->hit = 1;
- if (symbol_conf.field_sep) {
- fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
- "%s0x%"PRIx64"%s%s:%s\n";
+ if (mem->phys_addr) {
+ if (symbol_conf.field_sep) {
+ fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+ "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+ } else {
+ fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+ "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+ "%s%s:%s\n";
+ symbol_conf.field_sep = " ";
+ }
+
+ printf(fmt,
+ sample->pid,
+ symbol_conf.field_sep,
+ sample->tid,
+ symbol_conf.field_sep,
+ sample->ip,
+ symbol_conf.field_sep,
+ sample->addr,
+ symbol_conf.field_sep,
+ sample->phys_addr,
+ symbol_conf.field_sep,
+ sample->weight,
+ symbol_conf.field_sep,
+ sample->data_src,
+ symbol_conf.field_sep,
+ al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+ al.sym ? al.sym->name : "???");
} else {
- fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
- "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
- symbol_conf.field_sep = " ";
- }
+ if (symbol_conf.field_sep) {
+ fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+ "%s0x%"PRIx64"%s%s:%s\n";
+ } else {
+ fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+ "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+ symbol_conf.field_sep = " ";
+ }
- printf(fmt,
- sample->pid,
- symbol_conf.field_sep,
- sample->tid,
- symbol_conf.field_sep,
- sample->ip,
- symbol_conf.field_sep,
- sample->addr,
- symbol_conf.field_sep,
- sample->weight,
- symbol_conf.field_sep,
- sample->data_src,
- symbol_conf.field_sep,
- al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
- al.sym ? al.sym->name : "???");
+ printf(fmt,
+ sample->pid,
+ symbol_conf.field_sep,
+ sample->tid,
+ symbol_conf.field_sep,
+ sample->ip,
+ symbol_conf.field_sep,
+ sample->addr,
+ symbol_conf.field_sep,
+ sample->weight,
+ symbol_conf.field_sep,
+ sample->data_src,
+ symbol_conf.field_sep,
+ al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+ al.sym ? al.sym->name : "???");
+ }
out_put:
addr_location__put(&al);
return 0;
@@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem)
if (ret < 0)
goto out_delete;
- printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+ if (mem->phys_addr)
+ printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+ else
+ printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
ret = perf_session__process_events(session);
@@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
* there is no weight (cost) associated with stores, so don't print
* the column
*/
- if (!(mem->operation & MEM_OPERATION_LOAD))
- rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
- "dso_daddr,tlb,locked";
+ if (!(mem->operation & MEM_OPERATION_LOAD)) {
+ if (mem->phys_addr)
+ rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+ "dso_daddr,tlb,locked,phys_daddr";
+ else
+ rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+ "dso_daddr,tlb,locked";
+ } else if (mem->phys_addr)
+ rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+ "dso_daddr,snoop,tlb,locked,phys_daddr";
for (j = 1; j < argc; j++, i++)
rep_argv[i] = argv[j];
@@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv)
"separator for columns, no spaces will be added"
" between columns '.' is reserved."),
OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+ OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
OPT_END()
};
const char *const mem_subcommands[] = { "record", "report", NULL };
Commit-ID: 49d58f04eb6cdc18b3747fc4243a7114364f5420
Gitweb: http://git.kernel.org/tip/49d58f04eb6cdc18b3747fc4243a7114364f5420
Author: Kan Liang <[email protected]>
AuthorDate: Tue, 29 Aug 2017 13:11:11 -0400
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 1 Sep 2017 14:46:29 -0300
perf script: Support physical address
Display the physical address at the tail if it is available.
Signed-off-by: Kan Liang <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Acked-by: Stephane Eranian <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/perf/Documentation/perf-script.txt | 2 +-
tools/perf/builtin-script.c | 15 +++++++++++++--
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796..18dfcfa 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
- callindent, insn, insnlen, synth.
+ callindent, insn, insnlen, synth, phys_addr.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 378f76c..3d4c3b5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -87,6 +87,7 @@ enum perf_output_field {
PERF_OUTPUT_BRSTACKINSN = 1U << 23,
PERF_OUTPUT_BRSTACKOFF = 1U << 24,
PERF_OUTPUT_SYNTH = 1U << 25,
+ PERF_OUTPUT_PHYS_ADDR = 1U << 26,
};
struct output_option {
@@ -119,6 +120,7 @@ struct output_option {
{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
{.str = "synth", .field = PERF_OUTPUT_SYNTH},
+ {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
};
enum {
@@ -175,7 +177,8 @@ static struct {
PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR |
- PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+ PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+ PERF_OUTPUT_PHYS_ADDR,
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
},
@@ -382,6 +385,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
PERF_OUTPUT_IREGS))
return -EINVAL;
+ if (PRINT_FIELD(PHYS_ADDR) &&
+ perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+ PERF_OUTPUT_PHYS_ADDR))
+ return -EINVAL;
+
return 0;
}
@@ -1446,6 +1454,9 @@ static void process_event(struct perf_script *script,
if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
print_sample_bpf_output(sample);
print_insn(sample, attr, thread, machine);
+
+ if (PRINT_FIELD(PHYS_ADDR))
+ printf("%16" PRIx64, sample->phys_addr);
printf("\n");
}
@@ -2729,7 +2740,7 @@ int cmd_script(int argc, const char **argv)
"Valid types: hw,sw,trace,raw,synth. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,period,iregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+ "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
Commit-ID: fc33dccba39584e403436b9cda3edc9c34b62bce
Gitweb: http://git.kernel.org/tip/fc33dccba39584e403436b9cda3edc9c34b62bce
Author: Kan Liang <[email protected]>
AuthorDate: Tue, 29 Aug 2017 13:11:12 -0400
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Fri, 1 Sep 2017 14:46:34 -0300
perf test: Add test case for PERF_SAMPLE_PHYS_ADDR
Extend sample-parsing test cases to support new sample type
PERF_SAMPLE_PHYS_ADDR.
Signed-off-by: Kan Liang <[email protected]>
Tested-by: Jiri Olsa <[email protected]>
Acked-by: Stephane Eranian <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/perf/tests/sample-parsing.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 6d028f4..c385848 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -141,6 +141,9 @@ static bool samples_same(const struct perf_sample *s1,
}
}
+ if (type & PERF_SAMPLE_PHYS_ADDR)
+ COMP(phys_addr);
+
return true;
}
@@ -206,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
.mask = sample_regs,
.regs = regs,
},
+ .phys_addr = 113,
};
struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
struct perf_sample sample_out;
@@ -305,7 +309,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
* were added. Please actually update the test rather than just change
* the condition below.
*/
- if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+ if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) {
pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
return -1;
}