Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1717572 > unrolled thread

[PATCH 0/5] support PERF_SAMPLE_PHYS_ADDR (user)

Back to article view | Back to linux.kernel

Contents

  [PATCH 0/5] support PERF_SAMPLE_PHYS_ADDR (user) kan.liang@intel.com - 2017-08-22 18:50 +0200
    [PATCH 3/5] perf mem: support physical address kan.liang@intel.com - 2017-08-22 18:50 +0200
    [PATCH 2/5] perf tools: add sort option phys_daddr kan.liang@intel.com - 2017-08-22 18:50 +0200
    [PATCH 4/5] perf script: support physical addresses kan.liang@intel.com - 2017-08-22 18:50 +0200

#1717572 — [PATCH 0/5] support PERF_SAMPLE_PHYS_ADDR (user)

From: Kan Liang <kan.liang@intel.com>

The patch series is to support PERF_SAMPLE_PHYS_ADDR in user perf tool.
The kernel patch can be found here.
http://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1472034.html

Kan Liang (5):
  perf tools: add option to record sample physical address
  perf tools: add sort option phys_daddr
  perf mem: support physical address
  perf script: support physical addresses
  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 |  6 +-
 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              |  9 +++
 tools/perf/builtin-script.c              | 21 ++++++-
 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                   |  3 +
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/machine.c                |  7 ++-
 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, 193 insertions(+), 34 deletions(-)

-- 
2.4.3

[toc] | [next] | [standalone]

#1717576 — [PATCH 3/5] perf mem: support physical address

From: Kan Liang <kan.liang@intel.com>

Add option phys-data in perf mem to record/report physical address.
The default mem sort order for physical addresses is changed
accordingly.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 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

[toc] | [prev] | [next] | [standalone]

#1717577 — [PATCH 2/5] perf tools: add sort option phys_daddr

From: Kan Liang <kan.liang@intel.com>

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 <kan.liang@intel.com>
---
 tools/perf/Documentation/perf-report.txt |  1 +
 tools/perf/util/hist.c                   |  3 +++
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/machine.c                |  7 ++++--
 tools/perf/util/sort.c                   | 42 ++++++++++++++++++++++++++++++++
 tools/perf/util/sort.h                   |  1 +
 tools/perf/util/symbol.h                 |  1 +
 7 files changed, 54 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..a014590 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -167,6 +167,9 @@ 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..f536d85 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 +1672,7 @@ 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/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

[toc] | [prev] | [next] | [standalone]

#1717579 — [PATCH 4/5] perf script: support physical addresses

From: Kan Liang <kan.liang@intel.com>

perf script print out physical addresses if phys_addr is applied in perf
record.
Only display physical address when virtual address is selected.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 tools/perf/Documentation/perf-script.txt |  2 +-
 tools/perf/builtin-script.c              | 21 +++++++++++++++++++--
 2 files changed, 20 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..4522138 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,
 	},
@@ -328,6 +331,12 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_WEIGHT))
 		return -EINVAL;
 
+	if (PRINT_FIELD(PHYS_ADDR) && !PRINT_FIELD(ADDR)) {
+		pr_err("Display of sample physical address"
+		       "but sample address is not selected.\n");
+		return -EINVAL;
+	}
+
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
 		pr_err("Display of symbols requested but neither sample IP nor "
 			   "sample address\nis selected. Hence, no addresses to convert "
@@ -382,6 +391,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_IREGS))
 		return -EINVAL;
 
+	if (PRINT_FIELD(PHYS_ADDR) &&
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+					   PERF_OUTPUT_PHYS_ADDR, allow_user_set))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1446,6 +1460,9 @@ 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 +2746,7 @@ 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

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web