Skip to contentSkip to conversation

Add the page size in the perf record (user tools)

PATCH Superseded [email protected] 3 participants 16 messages Nov 17, 2020 – Nov 30, 2020 perf events

v1 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#2 lore raw

PATCH 2/12 perf record: Support new sample type for data page size

In reply to [email protected]

From: Kan Liang <[email protected]>

Support new sample type PERF_SAMPLE_DATA_PAGE_SIZE for page size.

Add new option --data-page-size to record sample data page size.

---
 tools/perf/Documentation/perf-record.txt  | 3 +++
 tools/perf/builtin-record.c               | 2 ++
 tools/perf/util/event.h                   | 1 +
 tools/perf/util/evsel.c                   | 9 +++++++++
 tools/perf/util/perf_event_attr_fprintf.c | 2 +-
 tools/perf/util/record.h                  | 1 +
 tools/perf/util/synthetic-events.c        | 8 ++++++++
 7 files changed, 25 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-record.txt +3 -0
index 768888b9326a..e6605b2ecd55 100644
@@ -293,6 +293,9 @@ OPTIONS
 --phys-data::
 	Record the sample physical addresses.
 
+--data-page-size::
+	Record the sampled data address data page size
+
 -T::
 --timestamp::
 	Record the sample timestamps. Use it with 'perf report -D' to see the
tools/perf/builtin-record.c +2 -0
index adf311d15d3d..29901f6a51bb 100644
@@ -2476,6 +2476,8 @@ static struct option __record_options[] = {
 	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, "data-page-size", &record.opts.sample_data_page_size,
+		    "Record the sampled data address data page size"),
 	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,
tools/perf/util/event.h +1 -0
index b828b99176f4..448ac30c2fc4 100644
@@ -135,6 +135,7 @@ struct perf_sample {
 	u32 raw_size;
 	u64 data_src;
 	u64 phys_addr;
+	u64 data_page_size;
 	u64 cgroup;
 	u32 flags;
 	u16 insn_len;
tools/perf/util/evsel.c +9 -0
index 1cad6051d8b0..3190cb165183 100644
@@ -1190,6 +1190,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 		evsel__set_sample_bit(evsel, CGROUP);
 	}
 
+	if (opts->sample_data_page_size)
+		evsel__set_sample_bit(evsel, DATA_PAGE_SIZE);
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -2365,6 +2368,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->data_page_size = 0;
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+		data->data_page_size = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		OVERFLOW_CHECK_u64(array);
 		sz = *array++;
tools/perf/util/perf_event_attr_fprintf.c +1 -1
index e67a227c0ce7..fb0bb6684438 100644
@@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		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(PHYS_ADDR), bit_name(AUX),
-		bit_name(CGROUP),
+		bit_name(CGROUP), bit_name(DATA_PAGE_SIZE),
 		{ .name = NULL, }
 	};
 #undef bit_name
tools/perf/util/record.h +1 -0
index 266760ac9143..694b351dcd27 100644
@@ -22,6 +22,7 @@ struct record_opts {
 	bool	      raw_samples;
 	bool	      sample_address;
 	bool	      sample_phys_addr;
+	bool	      sample_data_page_size;
 	bool	      sample_weight;
 	bool	      sample_time;
 	bool	      sample_time_set;
tools/perf/util/synthetic-events.c +8 -0
index 8a23391558cf..0884a19f313b 100644
@@ -1406,6 +1406,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_CGROUP)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		result += sizeof(u64);
+
 	if (type & PERF_SAMPLE_AUX) {
 		result += sizeof(u64);
 		result += sample->aux_sample.size;
@@ -1585,6 +1588,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE) {
+		*array = sample->data_page_size;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		sz = sample->aux_sample.size;
 		*array++ = sz;
Signature · 1 line
2.17.1
#4 lore raw

PATCH 4/12 perf sort: Add sort option for data page size

In reply to [email protected]

From: Kan Liang <[email protected]>

Add a new sort option "data_page_size" for --mem-mode sort. With this option applied, perf can sort and report by sample's data page size.

Here is an example.
perf report --stdio --mem-mode
--sort=comm,symbol,phys_daddr,data_page_size

# To display the perf.data header info, please use # --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 9K of event 'mem-loads:uP'
# Total weight : 9028
# Sort order : comm,symbol,phys_daddr,data_page_size
#
# Overhead Command Symbol Data Physical
# Address
# Data Page Size

 # ........  .......  ............................
 # ......................  ......................
 #
    11.19%  dtlb     [.] touch_buffer              [.]
0x00000003fec82ea8  4K
     8.61%  dtlb     [.] GetTickCount              [.]
0x00000003c4f2c8a8  4K
     4.52%  dtlb     [.] GetTickCount              [.]
0x00000003fec82f58  4K
     4.33%  dtlb     [.] __gettimeofday            [.]
0x00000003fec82f48  4K
     4.32%  dtlb     [.] GetTickCount              [.]
0x00000003fec82f78  4K
     4.28%  dtlb     [.] GetTickCount              [.]
0x00000003fec82f50  4K
     4.23%  dtlb     [.] GetTickCount              [.]
0x00000003fec82f70  4K
     4.11%  dtlb     [.] GetTickCount              [.]
0x00000003fec82f68  4K
     4.00%  dtlb     [.] Calibrate                 [.]
0x00000003fec82f98  4K
     3.91%  dtlb     [.] Calibrate                 [.]
0x00000003fec82f90  4K
     3.43%  dtlb     [.] touch_buffer              [.]
0x00000003fec82e98  4K
     3.42%  dtlb     [.] touch_buffer              [.]
0x00000003fec82e90  4K
     0.09%  dtlb     [.] DoDependentLoads          [.]
0x000000036ea084c0  2M
     0.08%  dtlb     [.] DoDependentLoads          [.]
0x000000032b010b80  2M
---
 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/map_symbol.h             |  1 +
 tools/perf/util/sort.c                   | 30 ++++++++++++++++++++++++
 tools/perf/util/sort.h                   |  1 +
 7 files changed, 42 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-report.txt +1 -0
index d068103690cc..8f7f4e9605d8 100644
@@ -150,6 +150,7 @@ OPTIONS
 	- 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
+	- data_page_size: the data page size 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'.
tools/perf/util/hist.c +3 -0
index 8a793e4c9400..7829ecd7ea59 100644
@@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
 				   unresolved_col_width + 4 + 2);
 
+		hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE,
+				   unresolved_col_width + 4 + 2);
+
 	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
tools/perf/util/hist.h +1 -0
index 96b1c13bbccc..e44cf5bb655f 100644
@@ -56,6 +56,7 @@ enum hist_column {
 	HISTC_MEM_DADDR_SYMBOL,
 	HISTC_MEM_DADDR_DSO,
 	HISTC_MEM_PHYS_DADDR,
+	HISTC_MEM_DATA_PAGE_SIZE,
 	HISTC_MEM_LOCKED,
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
tools/perf/util/machine.c +5 -2
index 15385ea00190..9e9a848a2746 100644
@@ -2019,11 +2019,12 @@ static void ip__resolve_ams(struct thread *thread,
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;
 	ams->phys_addr = 0;
+	ams->data_page_size = 0;
 }
 
 static void ip__resolve_data(struct thread *thread,
 			     u8 m, struct addr_map_symbol *ams,
-			     u64 addr, u64 phys_addr)
+			     u64 addr, u64 phys_addr, u64 daddr_page_size)
 {
 	struct addr_location al;
 
@@ -2037,6 +2038,7 @@ static void ip__resolve_data(struct thread *thread,
 	ams->ms.sym = al.sym;
 	ams->ms.map = al.map;
 	ams->phys_addr = phys_addr;
+	ams->data_page_size = daddr_page_size;
 }
 
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -2049,7 +2051,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 
 	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
 	ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
-			 sample->addr, sample->phys_addr);
+			 sample->addr, sample->phys_addr,
+			 sample->data_page_size);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
tools/perf/util/map_symbol.h +1 -0
index 5b8ca93798e9..7d22ade082c8 100644
@@ -19,5 +19,6 @@ struct addr_map_symbol {
 	u64	      addr;
 	u64	      al_addr;
 	u64	      phys_addr;
+	u64	      data_page_size;
 };
 #endif // __PERF_MAP_SYMBOL
tools/perf/util/sort.c +30 -0
index d42339df20f8..ad9666db07fb 100644
@@ -1462,6 +1462,35 @@ struct sort_entry sort_mem_phys_daddr = {
 	.se_width_idx	= HISTC_MEM_PHYS_DADDR,
 };
 
+static int64_t
+sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = left->mem_info->daddr.data_page_size;
+	if (right->mem_info)
+		r = right->mem_info->daddr.data_page_size;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+	char str[PAGE_SIZE_NAME_LEN];
+
+	return repsep_snprintf(bf, size, "%-*s", width,
+			       get_page_size_name(he->mem_info->daddr.data_page_size, str));
+}
+
+struct sort_entry sort_mem_data_page_size = {
+	.se_header	= "Data Page Size",
+	.se_cmp		= sort__data_page_size_cmp,
+	.se_snprintf	= hist_entry__data_page_size_snprintf,
+	.se_width_idx	= HISTC_MEM_DATA_PAGE_SIZE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	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),
+	DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size),
 };
 
 #undef DIM
tools/perf/util/sort.h +1 -0
index 66d39c4cfe2b..e50f2b695bc4 100644
@@ -255,6 +255,7 @@ enum sort_type {
 	SORT_MEM_DCACHELINE,
 	SORT_MEM_IADDR_SYMBOL,
 	SORT_MEM_PHYS_DADDR,
+	SORT_MEM_DATA_PAGE_SIZE,
 };
 
 /*
Signature · 1 line
2.17.1
#5 lore raw

PATCH 5/12 perf mem: Factor out a function to generate sort order

In reply to [email protected]

From: Kan Liang <[email protected]>

Now, "--phys-data" is the only option which impacts the sort order. A simple "if else" is enough to handle the option. But there will be more options added, e.g. "--data-page-size", which also impact the sort order. The code will become too complex to be maintained.

Divide the sort order string into several small pieces. The first piece is always the default sort string for LOAD/STORE. Appends the specific sort string if related option is applied.

No functional change.

---
 tools/perf/builtin-mem.c | 41 ++++++++++++++++++++++++++--------------
 1 file changed, 27 insertions(+), 14 deletions(-)
tools/perf/builtin-mem.c +27 -14
index 3523279af6af..7fb04f41cd99 100644
@@ -265,11 +265,35 @@ static int report_raw_events(struct perf_mem *mem)
 	perf_session__delete(session);
 	return ret;
 }
+static char *get_sort_order(struct perf_mem *mem)
+{
+	bool has_extra_options = mem->phys_addr ? true : false;
+	char sort[128];
+
+	/*
+	 * there is no weight (cost) associated with stores, so don't print
+	 * the column
+	 */
+	if (!(mem->operation & MEM_OPERATION_LOAD)) {
+		strcpy(sort, "--sort=mem,sym,dso,symbol_daddr,"
+			     "dso_daddr,tlb,locked");
+	} else if (has_extra_options) {
+		strcpy(sort, "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+			     "dso_daddr,snoop,tlb,locked");
+	} else
+		return NULL;
+
+	if (mem->phys_addr)
+		strcat(sort, ",phys_daddr");
+
+	return strdup(sort);
+}
 
 static int report_events(int argc, const char **argv, struct perf_mem *mem)
 {
 	const char **rep_argv;
 	int ret, i = 0, j, rep_argc;
+	char *new_sort_order;
 
 	if (mem->dump_raw)
 		return report_raw_events(mem);
@@ -283,20 +307,9 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	rep_argv[i++] = "--mem-mode";
 	rep_argv[i++] = "-n"; /* display number of samples */
 
-	/*
-	 * there is no weight (cost) associated with stores, so don't print
-	 * the column
-	 */
-	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";
+	new_sort_order = get_sort_order(mem);
+	if (new_sort_order)
+		rep_argv[i++] = new_sort_order;
 
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
Signature · 1 line
2.17.1
#6 lore raw

PATCH 6/12 perf mem: Clean up output format

In reply to [email protected]

From: Kan Liang <[email protected]>

Now, "--phys-data" is the only option which impacts the output format. A simple "if else" is enough to handle the option. But there will be more options added, e.g. "--data-page-size", which also impact the output format. The code will become too complex to be maintained.

Divide the big printf into several small pieces. Output the specific piece only if the related option is applied.

No functional change.

---
 tools/perf/builtin-mem.c | 93 ++++++++++++++++------------------------
 1 file changed, 38 insertions(+), 55 deletions(-)
tools/perf/builtin-mem.c +38 -55
index 7fb04f41cd99..200ff7c9d7b7 100644
@@ -147,7 +147,7 @@ dump_raw_samples(struct perf_tool *tool,
 {
 	struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
 	struct addr_location al;
-	const char *fmt;
+	const char *fmt, *field_sep;
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
@@ -161,60 +161,41 @@ dump_raw_samples(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	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 : "???");
+	field_sep = symbol_conf.field_sep;
+	if (field_sep) {
+		fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s";
 	} else {
-		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 = " ";
-		}
+		fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64"%s";
+		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);
 
-		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 : "???");
+	if (mem->phys_addr) {
+		printf("0x%016"PRIx64"%s",
+			sample->phys_addr,
+			symbol_conf.field_sep);
 	}
+
+	if (field_sep)
+		fmt = "%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+	else
+		fmt = "%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+
+	printf(fmt,
+		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;
@@ -254,10 +235,12 @@ static int report_raw_events(struct perf_mem *mem)
 	if (ret < 0)
 		goto out_delete;
 
+	printf("# PID, TID, IP, ADDR, ");
+
 	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");
+		printf("PHYS ADDR, ");
+
+	printf("LOCAL WEIGHT, DSRC, SYMBOL\n");
 
 	ret = perf_session__process_events(session);
 
Signature · 1 line
2.17.1
#7 lore raw

PATCH 7/12 perf mem: Support data page size

In reply to [email protected]

From: Kan Liang <[email protected]>

Add option --data-page-size in "perf mem" to record/report data page size.

Here are some examples.
perf mem --phys-data --data-page-size report -D

# PID, TID, IP, ADDR, PHYS ADDR, DATA PAGE SIZE, LOCAL WEIGHT, DSRC, # SYMBOL
20134 20134 0xffffffffb5bd2fd0 0x016ffff9a274e96a308 0x000000044e96a308 4K 1168 0x5080144 /lib/modules/4.18.0-rc7+/build/vmlinux:perf_ctx_unlock
20134 20134 0xffffffffb63f645c 0xffffffffb752b814 0xcfb52b814 2M 225 0x26a100142 /lib/modules/4.18.0-rc7+/build/vmlinux:_raw_spin_lock 20134 20134 0xffffffffb660300c 0xfffffe00016b8bb0 0x0 4K 0 0x5080144 /lib/modules/4.18.0-rc7+/build/vmlinux:__x86_indirect_thunk_rax

perf mem --phys-data --data-page-size report --stdio

# To display the perf.data header info, please use
# --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 5K of event 'cpu/mem-loads,ldlat=30/P'
# Total weight : 281234
# Sort order :
# mem,sym,dso,symbol_daddr,dso_daddr,tlb,locked,phys_daddr,data_page_size #
# Overhead Samples Memory access Symbol
# Shared Object Data Symbol Data
# Object TLB access Locked Data Physical
# Address Data Page Size

 # ........  ............  ........................
 # ................................  ................
 # ...........................................  .......................
 # ......................  ......  ......................
 # ......................
 #
    28.54%          1826  L1 or L1 hit              [k]
__x86_indirect_thunk_rax      [kernel.vmlinux]  [k] 0xffffb0df31b0ff28
[unknown]                L1 or L2 hit            No      [k]
0000000000000000    4K
     6.02%           256  L1 or L1 hit              [.] touch_buffer
dtlb              [.] 0x00007ffd50109da8                       [stack]
L1 or L2 hit            No      [.] 0x000000042454ada8  4K
     3.23%             5  L1 or L1 hit              [k] clear_huge_page
[kernel.vmlinux]  [k] 0xffff9a2753b8ce60                       [unknown]
L1 or L2 hit            No      [k] 0x0000000453b8ce60  2M
     2.98%             4  L1 or L1 hit              [k] clear_page_erms
[kernel.vmlinux]  [k] 0xffffb0df31b0fd00                       [unknown]
L1 or L2 hit            No      [k] 0000000000000000    4K
---
 tools/perf/Documentation/perf-mem.txt |  3 +++
 tools/perf/builtin-mem.c              | 20 +++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-mem.txt +3 -0
index 199ea0f0a6c0..66177511c5c4 100644
@@ -63,6 +63,9 @@ OPTIONS
 --phys-data::
 	Record/Report sample physical addresses
 
+--data-page-size::
+	Record/Report sample data address page size
+
 RECORD OPTIONS
 --------------
 -e::
tools/perf/builtin-mem.c +19 -1
index 200ff7c9d7b7..433e02ab45eb 100644
@@ -29,6 +29,7 @@ struct perf_mem {
 	bool			dump_raw;
 	bool			force;
 	bool			phys_addr;
+	bool			data_page_size;
 	int			operation;
 	const char		*cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -100,6 +101,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (mem->phys_addr)
 		rec_argv[i++] = "--phys-data";
 
+	if (mem->data_page_size)
+		rec_argv[i++] = "--data-page-size";
+
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		if (!perf_mem_events[j].record)
 			continue;
@@ -148,6 +152,7 @@ dump_raw_samples(struct perf_tool *tool,
 	struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
 	struct addr_location al;
 	const char *fmt, *field_sep;
+	char str[PAGE_SIZE_NAME_LEN];
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		fprintf(stderr, "problem processing %d event, skipping it.\n",
@@ -184,6 +189,12 @@ dump_raw_samples(struct perf_tool *tool,
 			symbol_conf.field_sep);
 	}
 
+	if (mem->data_page_size) {
+		printf("%s%s",
+			get_page_size_name(sample->data_page_size, str),
+			symbol_conf.field_sep);
+	}
+
 	if (field_sep)
 		fmt = "%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
 	else
@@ -240,6 +251,9 @@ static int report_raw_events(struct perf_mem *mem)
 	if (mem->phys_addr)
 		printf("PHYS ADDR, ");
 
+	if (mem->data_page_size)
+		printf("DATA PAGE SIZE, ");
+
 	printf("LOCAL WEIGHT, DSRC, SYMBOL\n");
 
 	ret = perf_session__process_events(session);
@@ -250,7 +264,7 @@ static int report_raw_events(struct perf_mem *mem)
 }
 static char *get_sort_order(struct perf_mem *mem)
 {
-	bool has_extra_options = mem->phys_addr ? true : false;
+	bool has_extra_options = (mem->phys_addr | mem->data_page_size) ? true : false;
 	char sort[128];
 
 	/*
@@ -269,6 +283,9 @@ static char *get_sort_order(struct perf_mem *mem)
 	if (mem->phys_addr)
 		strcat(sort, ",phys_daddr");
 
+	if (mem->data_page_size)
+		strcat(sort, ",data_page_size");
+
 	return strdup(sort);
 }
 
@@ -410,6 +427,7 @@ int cmd_mem(int argc, const char **argv)
 		   " 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_BOOLEAN(0, "data-page-size", &mem.data_page_size, "Record/Report sample data address page size"),
 	OPT_END()
 	};
 	const char *const mem_subcommands[] = { "record", "report", NULL };
Signature · 1 line
2.17.1
#9 lore raw

PATCH 9/12 perf tools: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

In reply to [email protected]

From: Stephane Eranian <[email protected]>

Adds the infrastructure to sample the code address page size.

Introduce a new --code-page-size option for perf record.

---
 tools/perf/Documentation/perf-record.txt  | 3 +++
 tools/perf/builtin-record.c               | 2 ++
 tools/perf/util/event.h                   | 1 +
 tools/perf/util/evsel.c                   | 9 +++++++++
 tools/perf/util/perf_event_attr_fprintf.c | 2 +-
 tools/perf/util/record.h                  | 1 +
 tools/perf/util/synthetic-events.c        | 8 ++++++++
 7 files changed, 25 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-record.txt +3 -0
index e6605b2ecd55..4d1531289124 100644
@@ -296,6 +296,9 @@ OPTIONS
 --data-page-size::
 	Record the sampled data address data page size
 
+--code-page-size::
+	Record the sampled code address (ip) page size
+
 -T::
 --timestamp::
 	Record the sample timestamps. Use it with 'perf report -D' to see the
tools/perf/builtin-record.c +2 -0
index 29901f6a51bb..50c2593623e3 100644
@@ -2478,6 +2478,8 @@ static struct option __record_options[] = {
 		    "Record the sample physical addresses"),
 	OPT_BOOLEAN(0, "data-page-size", &record.opts.sample_data_page_size,
 		    "Record the sampled data address data page size"),
+	OPT_BOOLEAN(0, "code-page-size", &record.opts.sample_code_page_size,
+		    "Record the sampled code address (ip) page size"),
 	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,
tools/perf/util/event.h +1 -0
index 2e5aec3ead9f..01bd26c78e69 100644
@@ -136,6 +136,7 @@ struct perf_sample {
 	u64 data_src;
 	u64 phys_addr;
 	u64 data_page_size;
+	u64 code_page_size;
 	u64 cgroup;
 	u32 flags;
 	u16 insn_len;
tools/perf/util/evsel.c +9 -0
index 3190cb165183..806b39b7988d 100644
@@ -1193,6 +1193,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	if (opts->sample_data_page_size)
 		evsel__set_sample_bit(evsel, DATA_PAGE_SIZE);
 
+	if (opts->sample_code_page_size)
+		evsel__set_sample_bit(evsel, CODE_PAGE_SIZE);
+
 	if (opts->record_switch_events)
 		attr->context_switch = track;
 
@@ -2374,6 +2377,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->code_page_size = 0;
+	if (type & PERF_SAMPLE_CODE_PAGE_SIZE) {
+		data->code_page_size = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		OVERFLOW_CHECK_u64(array);
 		sz = *array++;
tools/perf/util/perf_event_attr_fprintf.c +1 -1
index fb0bb6684438..3a2eb25d07a7 100644
@@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
 		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(PHYS_ADDR), bit_name(AUX),
-		bit_name(CGROUP), bit_name(DATA_PAGE_SIZE),
+		bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), bit_name(CODE_PAGE_SIZE),
 		{ .name = NULL, }
 	};
 #undef bit_name
tools/perf/util/record.h +1 -0
index 694b351dcd27..22dc86b1dab5 100644
@@ -23,6 +23,7 @@ struct record_opts {
 	bool	      sample_address;
 	bool	      sample_phys_addr;
 	bool	      sample_data_page_size;
+	bool	      sample_code_page_size;
 	bool	      sample_weight;
 	bool	      sample_time;
 	bool	      sample_time_set;
tools/perf/util/synthetic-events.c +8 -0
index 0884a19f313b..81bc174f83f3 100644
@@ -1409,6 +1409,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		result += sizeof(u64);
+
 	if (type & PERF_SAMPLE_AUX) {
 		result += sizeof(u64);
 		result += sample->aux_sample.size;
@@ -1593,6 +1596,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_CODE_PAGE_SIZE) {
+		*array = sample->code_page_size;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_AUX) {
 		sz = sample->aux_sample.size;
 		*array++ = sz;
Signature · 1 line
2.17.1
#10 lore raw

PATCH 10/12 perf script: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

In reply to [email protected]

From: Stephane Eranian <[email protected]>

Display sampled code page sizes when PERF_SAMPLE_CODE_PAGE_SIZE was set.

For example,
perf script --fields comm,event,ip,code_page_size

            dtlb mem-loads:uP:            445777 4K
            dtlb mem-loads:uP:            40f724 4K
            dtlb mem-loads:uP:            474926 4K
            dtlb mem-loads:uP:            401075 4K
            dtlb mem-loads:uP:            401095 4K
            dtlb mem-loads:uP:            401095 4K
            dtlb mem-loads:uP:            4010cc 4K
            dtlb mem-loads:uP:            440b6f 4K
---
 tools/perf/Documentation/perf-script.txt |  2 +-
 tools/perf/builtin-script.c              | 13 +++++++++++--
 tools/perf/util/session.c                |  3 +++
 3 files changed, 15 insertions(+), 3 deletions(-)
tools/perf/Documentation/perf-script.txt +1 -1
index ac4755727ca1..714b901f9d50 100644
@@ -118,7 +118,7 @@ OPTIONS
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
 	srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
 	brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr,
-	metric, misc, srccode, ipc, data_page_size.
+	metric, misc, srccode, ipc, data_page_size, code_page_size.
         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
tools/perf/builtin-script.c +11 -2
index a02a820398d7..24839b050afb 100644
@@ -117,6 +117,7 @@ enum perf_output_field {
 	PERF_OUTPUT_IPC             = 1ULL << 31,
 	PERF_OUTPUT_TOD             = 1ULL << 32,
 	PERF_OUTPUT_DATA_PAGE_SIZE  = 1ULL << 33,
+	PERF_OUTPUT_CODE_PAGE_SIZE  = 1ULL << 34,
 };
 
 struct perf_script {
@@ -182,6 +183,7 @@ struct output_option {
 	{.str = "ipc", .field = PERF_OUTPUT_IPC},
 	{.str = "tod", .field = PERF_OUTPUT_TOD},
 	{.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE},
+	{.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE},
 };
 
 enum {
@@ -255,7 +257,7 @@ static struct {
 			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
 			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
 			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR |
-			      PERF_OUTPUT_DATA_PAGE_SIZE,
+			      PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -507,6 +509,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	    evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE))
 		return -EINVAL;
 
+	if (PRINT_FIELD(CODE_PAGE_SIZE) &&
+	    evsel__check_stype(evsel, PERF_SAMPLE_CODE_PAGE_SIZE, "CODE_PAGE_SIZE", PERF_OUTPUT_CODE_PAGE_SIZE))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -2020,6 +2026,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(DATA_PAGE_SIZE))
 		fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str));
 
+	if (PRINT_FIELD(CODE_PAGE_SIZE))
+		fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str));
+
 	perf_sample__fprintf_ipc(sample, attr, fp);
 
 	fprintf(fp, "\n");
@@ -3519,7 +3528,7 @@ int cmd_script(int argc, const char **argv)
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
 		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod,"
-		     "data_page_size",
+		     "data_page_size,code_page_size",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
tools/perf/util/session.c +3 -0
index 6335deda28f6..fa6ffa6e0d66 100644
@@ -1307,6 +1307,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str));
 
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		printf(" .. code page size: %s\n", get_page_size_name(sample->code_page_size, str));
+
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
Signature · 1 line
2.17.1
#1 lore raw

PATCH 1/12 tools headers UAPI: Update tools's copy of linux/perf_event.h

In reply to [email protected]

From: Kan Liang <[email protected]>

To get the changes in:

commit 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE") commit 995f088efebe ("perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE")

This silences this perf tools build warning:

Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h'
differs from latest version at 'include/uapi/linux/perf_event.h'
diff -u tools/include/uapi/linux/perf_event.h
include/uapi/linux/perf_event.h

---
 tools/include/uapi/linux/perf_event.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
tools/include/uapi/linux/perf_event.h +5 -1
index 3e5dcdd48a49..fe404942f838 100644
@@ -143,8 +143,10 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 	PERF_SAMPLE_AUX				= 1U << 20,
 	PERF_SAMPLE_CGROUP			= 1U << 21,
+	PERF_SAMPLE_DATA_PAGE_SIZE		= 1U << 22,
+	PERF_SAMPLE_CODE_PAGE_SIZE		= 1U << 23,
 
-	PERF_SAMPLE_MAX = 1U << 22,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 24,		/* non-ABI */
 
 	__PERF_SAMPLE_CALLCHAIN_EARLY		= 1ULL << 63, /* non-ABI; internal use */
 };
@@ -896,6 +898,8 @@ enum perf_event_type {
 	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 *	{ u64			size;
 	 *	  char			data[size]; } && PERF_SAMPLE_AUX
+	 *	{ u64			data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE
+	 *	{ u64			code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
Signature · 1 line
2.17.1
#3 lore raw

PATCH 3/12 perf script: Support data page size

In reply to [email protected]

From: Kan Liang <[email protected]>

Display the data page size if it is available.

Can be configured by the user, for example:
perf script --fields comm,event,phys_addr,data_page_size

            dtlb mem-loads:uP:        3fec82ea8 4K
            dtlb mem-loads:uP:        3fec82e90 4K
            dtlb mem-loads:uP:        3e23700a4 4K
            dtlb mem-loads:uP:        3fec82f20 4K
            dtlb mem-loads:uP:        3e23700a4 4K
            dtlb mem-loads:uP:        3b4211bec 4K
            dtlb mem-loads:uP:        382205dc0 2M
            dtlb mem-loads:uP:        36fa082c0 2M
            dtlb mem-loads:uP:        377607340 2M
            dtlb mem-loads:uP:        330010180 2M
            dtlb mem-loads:uP:        33200fd80 2M
            dtlb mem-loads:uP:        31b012b80 2M
---
 tools/perf/Documentation/perf-script.txt |  5 +++--
 tools/perf/builtin-script.c              | 17 +++++++++++++++--
 tools/perf/util/event.h                  |  3 +++
 tools/perf/util/session.c                | 23 +++++++++++++++++++++++
 4 files changed, 44 insertions(+), 4 deletions(-)
tools/perf/Documentation/perf-script.txt +3 -2
index 4f712fb8f175..ac4755727ca1 100644
@@ -116,8 +116,9 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
-        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc.
+	srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
+	brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr,
+	metric, misc, srccode, ipc, data_page_size.
         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
tools/perf/builtin-script.c +15 -2
index 48588ccf902e..a02a820398d7 100644
@@ -30,6 +30,7 @@
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
 #include "util/path.h"
+#include "util/event.h"
 #include "ui/ui.h"
 #include "print_binary.h"
 #include "archinsn.h"
@@ -115,6 +116,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SRCCODE	    = 1ULL << 30,
 	PERF_OUTPUT_IPC             = 1ULL << 31,
 	PERF_OUTPUT_TOD             = 1ULL << 32,
+	PERF_OUTPUT_DATA_PAGE_SIZE  = 1ULL << 33,
 };
 
 struct perf_script {
@@ -179,6 +181,7 @@ struct output_option {
 	{.str = "srccode", .field = PERF_OUTPUT_SRCCODE},
 	{.str = "ipc", .field = PERF_OUTPUT_IPC},
 	{.str = "tod", .field = PERF_OUTPUT_TOD},
+	{.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE},
 };
 
 enum {
@@ -251,7 +254,8 @@ static struct {
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
 			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
 			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
-			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
+			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR |
+			      PERF_OUTPUT_DATA_PAGE_SIZE,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -499,6 +503,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 	    evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR))
 		return -EINVAL;
 
+	if (PRINT_FIELD(DATA_PAGE_SIZE) &&
+	    evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1920,6 +1928,7 @@ static void process_event(struct perf_script *script,
 	unsigned int type = output_type(attr->type);
 	struct evsel_script *es = evsel->priv;
 	FILE *fp = es->fp;
+	char str[PAGE_SIZE_NAME_LEN];
 
 	if (output[type].fields == 0)
 		return;
@@ -2008,6 +2017,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
 
+	if (PRINT_FIELD(DATA_PAGE_SIZE))
+		fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str));
+
 	perf_sample__fprintf_ipc(sample, attr, fp);
 
 	fprintf(fp, "\n");
@@ -3506,7 +3518,8 @@ int cmd_script(int argc, const char **argv)
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
-		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod",
+		     "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod,"
+		     "data_page_size",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
tools/perf/util/event.h +3 -0
index 448ac30c2fc4..2e5aec3ead9f 100644
@@ -409,4 +409,7 @@ extern int sysctl_perf_event_max_stack;
 extern int sysctl_perf_event_max_contexts_per_stack;
 extern unsigned int proc_map_timeout;
 
+#define PAGE_SIZE_NAME_LEN	10
+char *get_page_size_name(u64 size, char *str);
+
 #endif /* __PERF_RECORD_H */
tools/perf/util/session.c +23 -0
index 7a5f03764702..6335deda28f6 100644
@@ -1246,10 +1246,30 @@ static void dump_event(struct evlist *evlist, union perf_event *event,
 	       event->header.size, perf_event__name(event->header.type));
 }
 
+char *get_page_size_name(u64 size, char *str)
+{
+	const char suffixes[5] = { 'B', 'K', 'M', 'G', 'T' };
+	int i;
+
+	if (size == 0) {
+		snprintf(str, PAGE_SIZE_NAME_LEN, "%s", "N/A");
+		return str;
+	}
+	for (i = 0; i < 5; i++) {
+		if (size < 1024)
+			break;
+		size /= 1024;
+	}
+
+	snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
+	return str;
+}
+
 static void dump_sample(struct evsel *evsel, union perf_event *event,
 			struct perf_sample *sample)
 {
 	u64 sample_type;
+	char str[PAGE_SIZE_NAME_LEN];
 
 	if (!dump_trace)
 		return;
@@ -1284,6 +1304,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_PHYS_ADDR)
 		printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str));
+
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
Signature · 1 line
2.17.1
#8 lore raw

PATCH 8/12 perf test: Add test case for PERF_SAMPLE_DATA_PAGE_SIZE

In reply to [email protected]

From: Kan Liang <[email protected]>

Extend sample-parsing test cases to support new sample type PERF_SAMPLE_DATA_PAGE_SIZE.

---
 tools/perf/tests/sample-parsing.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
tools/perf/tests/sample-parsing.c +5 -1
index a0bdaf390ac8..6baed165c850 100644
@@ -154,6 +154,9 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_CGROUP)
 		COMP(cgroup);
 
+	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		COMP(data_page_size);
+
 	if (type & PERF_SAMPLE_AUX) {
 		COMP(aux_sample.size);
 		if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -234,6 +237,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		},
 		.phys_addr	= 113,
 		.cgroup		= 114,
+		.data_page_size	= 4096,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,
@@ -340,7 +344,7 @@ 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_CGROUP << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_DATA_PAGE_SIZE << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
Signature · 1 line
2.17.1
#11 lore raw

PATCH 11/12 perf report: Add support for PERF_SAMPLE_CODE_PAGE_SIZE

In reply to [email protected]

From: Stephane Eranian <[email protected]>

Add a new sort dimension "code_page_size" for common sort. With this option applied, perf can sort and report by sample's code page size.

For example,
perf report --stdio --sort=comm,symbol,code_page_size
# To display the perf.data header info, please use # --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 3K of event 'mem-loads:uP'
# Event count (approx.): 1470769
#
# Overhead Command Symbol Code Page Size IPC
# [IPC Coverage]

 # ........  .......  ............................  ..............
 # ....................
 #
     69.56%  dtlb     [.] GetTickCount              4K             -

17.93% dtlb [.] Calibrate 4K -
-
11.40% dtlb [.] __gettimeofday 4K -
-

---
 tools/perf/Documentation/perf-report.txt |  1 +
 tools/perf/util/hist.c                   |  2 ++
 tools/perf/util/hist.h                   |  1 +
 tools/perf/util/sort.c                   | 26 ++++++++++++++++++++++++
 tools/perf/util/sort.h                   |  2 ++
 5 files changed, 32 insertions(+)
tools/perf/Documentation/perf-report.txt +1 -0
index 8f7f4e9605d8..e44045842c5c 100644
@@ -108,6 +108,7 @@ OPTIONS
 	- period: Raw number of event count of sample
 	- time: Separate the samples by time stamp with the resolution specified by
 	--time-quantum (default 100ms). Specify with overhead and before it.
+	- code_page_size: the code page size of sampled code address (ip)
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
tools/perf/util/hist.c +2 -0
index 7829ecd7ea59..af948da14d94 100644
@@ -212,6 +212,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_TIME, 16);
 	else
 		hists__new_col_len(hists, HISTC_TIME, 12);
+	hists__new_col_len(hists, HISTC_CODE_PAGE_SIZE, 6);
 
 	if (h->srcline) {
 		len = MAX(strlen(h->srcline), strlen(sort_srcline.se_header));
@@ -718,6 +719,7 @@ __hists__add_entry(struct hists *hists,
 		.cpumode = al->cpumode,
 		.ip	 = al->addr,
 		.level	 = al->level,
+		.code_page_size = sample->code_page_size,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
tools/perf/util/hist.h +1 -0
index e44cf5bb655f..6500c00ae7be 100644
@@ -53,6 +53,7 @@ enum hist_column {
 	HISTC_DSO_TO,
 	HISTC_LOCAL_WEIGHT,
 	HISTC_GLOBAL_WEIGHT,
+	HISTC_CODE_PAGE_SIZE,
 	HISTC_MEM_DADDR_SYMBOL,
 	HISTC_MEM_DADDR_DSO,
 	HISTC_MEM_PHYS_DADDR,
tools/perf/util/sort.c +26 -0
index ad9666db07fb..bc79d446bcbd 100644
@@ -1491,6 +1491,31 @@ struct sort_entry sort_mem_data_page_size = {
 	.se_width_idx	= HISTC_MEM_DATA_PAGE_SIZE,
 };
 
+static int64_t
+sort__code_page_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = left->code_page_size;
+	uint64_t r = right->code_page_size;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__code_page_size_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+	char str[PAGE_SIZE_NAME_LEN];
+
+	return repsep_snprintf(bf, size, "%-*s", width,
+			       get_page_size_name(he->code_page_size, str));
+}
+
+struct sort_entry sort_code_page_size = {
+	.se_header	= "Code Page Size",
+	.se_cmp		= sort__code_page_size_cmp,
+	.se_snprintf	= hist_entry__code_page_size_snprintf,
+	.se_width_idx	= HISTC_CODE_PAGE_SIZE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1735,6 +1760,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 	DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
 	DIM(SORT_TIME, "time", sort_time),
+	DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
 };
 
 #undef DIM
tools/perf/util/sort.h +2 -0
index e50f2b695bc4..cab4172a6ec3 100644
@@ -106,6 +106,7 @@ struct hist_entry {
 	u64			transaction;
 	s32			socket;
 	s32			cpu;
+	u64			code_page_size;
 	u8			cpumode;
 	u8			depth;
 
@@ -229,6 +230,7 @@ enum sort_type {
 	SORT_CGROUP_ID,
 	SORT_SYM_IPC_NULL,
 	SORT_TIME,
+	SORT_CODE_PAGE_SIZE,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
Signature · 1 line
2.17.1
#12 lore raw

PATCH 12/12 perf test: Add test case for PERF_SAMPLE_CODE_PAGE_SIZE

In reply to [email protected]

From: Stephane Eranian <[email protected]>

Extend sample-parsing test cases to support new sample type PERF_SAMPLE_CODE_PAGE_SIZE.

---
 tools/perf/tests/sample-parsing.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
tools/perf/tests/sample-parsing.c +5 -1
index 6baed165c850..5e780b85d952 100644
@@ -157,6 +157,9 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_DATA_PAGE_SIZE)
 		COMP(data_page_size);
 
+	if (type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		COMP(code_page_size);
+
 	if (type & PERF_SAMPLE_AUX) {
 		COMP(aux_sample.size);
 		if (memcmp(s1->aux_sample.data, s2->aux_sample.data,
@@ -238,6 +241,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		.phys_addr	= 113,
 		.cgroup		= 114,
 		.data_page_size	= 4096,
+		.code_page_size	= 4096,
 		.aux_sample	= {
 			.size	= sizeof(aux_data),
 			.data	= (void *)aux_data,
@@ -344,7 +348,7 @@ 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_DATA_PAGE_SIZE << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_CODE_PAGE_SIZE << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
Signature · 1 line
2.17.1
#0 lore raw

cover Add the page size in the perf record (user tools)

From: Kan Liang <[email protected]>

Current perf can report both virtual addresses and physical addresses, but not the page size. Without the page size information of the utilized page, users cannot decide whether to promote/demote large pages to optimize memory usage.

The kernel patches have been merged into tip perf/core branch, commit 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE") commit 76a5433f95f3 ("perf/x86/intel: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 4cb6a42e4c4b ("powerpc/perf: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 995f088efebe ("perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE") commit 51b646b2d9f8 ("perf,mm: Handle non-page-table-aligned hugetlbfs")

and Peter's perf/core branch
commit 524680ce47a1 ("mm/gup: Provide gup_get_pte() more generic") commit 44a35d6937d2 ("mm: Introduce pXX_leaf_size()") commit 2f1e2f091ad0 ("perf/core: Fix arch_perf_get_page_size()") commit 7649e44aacdd ("arm64/mm: Implement pXX_leaf_size() support") commit 1df1ae7e262c ("sparc64/mm: Implement pXX_leaf_size() support")

This patch set is to enable the page size support in user tools.

Kan Liang (8):
tools headers UAPI: Update tools's copy of linux/perf_event.h perf record: Support new sample type for data page size perf script: Support data page size
perf sort: Add sort option for data page size
perf mem: Factor out a function to generate sort order perf mem: Clean up output format
perf mem: Support data page size
perf test: Add test case for PERF_SAMPLE_DATA_PAGE_SIZE

Stephane Eranian (4):
perf tools: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf script: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf report: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf test: Add test case for PERF_SAMPLE_CODE_PAGE_SIZE

 tools/include/uapi/linux/perf_event.h     |   6 +-
 tools/perf/Documentation/perf-mem.txt     |   3 +
 tools/perf/Documentation/perf-record.txt  |   6 +
 tools/perf/Documentation/perf-report.txt  |   2 +
 tools/perf/Documentation/perf-script.txt  |   5 +-
 tools/perf/builtin-mem.c                  | 150 ++++++++++++----------
 tools/perf/builtin-record.c               |   4 +
 tools/perf/builtin-script.c               |  26 +++-
 tools/perf/tests/sample-parsing.c         |  10 +-
 tools/perf/util/event.h                   |   5 +
 tools/perf/util/evsel.c                   |  18 +++
 tools/perf/util/hist.c                    |   5 +
 tools/perf/util/hist.h                    |   2 +
 tools/perf/util/machine.c                 |   7 +-
 tools/perf/util/map_symbol.h              |   1 +
 tools/perf/util/perf_event_attr_fprintf.c |   2 +-
 tools/perf/util/record.h                  |   2 +
 tools/perf/util/session.c                 |  26 ++++
 tools/perf/util/sort.c                    |  56 ++++++++
 tools/perf/util/sort.h                    |   3 +
 tools/perf/util/synthetic-events.c        |  16 +++
 21 files changed, 278 insertions(+), 77 deletions(-)
Signature · 1 line
2.17.1
maintainer Acked-by on the v1 series
#13 lore raw

Hi,

Quoted 34 lines · On Wed, Nov 18, 2020 at 4:57 AM <[email protected]> wrote:

From: Kan Liang <[email protected]>

Current perf can report both virtual addresses and physical addresses, but not the page size. Without the page size information of the utilized page, users cannot decide whether to promote/demote large pages to optimize memory usage.

The kernel patches have been merged into tip perf/core branch, commit 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE") commit 76a5433f95f3 ("perf/x86/intel: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 4cb6a42e4c4b ("powerpc/perf: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 995f088efebe ("perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE") commit 51b646b2d9f8 ("perf,mm: Handle non-page-table-aligned hugetlbfs")

and Peter's perf/core branch
commit 524680ce47a1 ("mm/gup: Provide gup_get_pte() more generic") commit 44a35d6937d2 ("mm: Introduce pXX_leaf_size()") commit 2f1e2f091ad0 ("perf/core: Fix arch_perf_get_page_size()") commit 7649e44aacdd ("arm64/mm: Implement pXX_leaf_size() support") commit 1df1ae7e262c ("sparc64/mm: Implement pXX_leaf_size() support")

This patch set is to enable the page size support in user tools.

Kan Liang (8):
tools headers UAPI: Update tools's copy of linux/perf_event.h perf record: Support new sample type for data page size perf script: Support data page size
perf sort: Add sort option for data page size
perf mem: Factor out a function to generate sort order perf mem: Clean up output format
perf mem: Support data page size
perf test: Add test case for PERF_SAMPLE_DATA_PAGE_SIZE

Quoted 5 lines

Stephane Eranian (4):
perf tools: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf script: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf report: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf test: Add test case for PERF_SAMPLE_CODE_PAGE_SIZE

For the patchset:

Thanks,
Namhyung

Quoted 27 lines
 tools/include/uapi/linux/perf_event.h     |   6 +-
 tools/perf/Documentation/perf-mem.txt     |   3 +
 tools/perf/Documentation/perf-record.txt  |   6 +
 tools/perf/Documentation/perf-report.txt  |   2 +
 tools/perf/Documentation/perf-script.txt  |   5 +-
 tools/perf/builtin-mem.c                  | 150 ++++++++++++----------
 tools/perf/builtin-record.c               |   4 +
 tools/perf/builtin-script.c               |  26 +++-
 tools/perf/tests/sample-parsing.c         |  10 +-
 tools/perf/util/event.h                   |   5 +
 tools/perf/util/evsel.c                   |  18 +++
 tools/perf/util/hist.c                    |   5 +
 tools/perf/util/hist.h                    |   2 +
 tools/perf/util/machine.c                 |   7 +-
 tools/perf/util/map_symbol.h              |   1 +
 tools/perf/util/perf_event_attr_fprintf.c |   2 +-
 tools/perf/util/record.h                  |   2 +
 tools/perf/util/session.c                 |  26 ++++
 tools/perf/util/sort.c                    |  56 ++++++++
 tools/perf/util/sort.h                    |   3 +
 tools/perf/util/synthetic-events.c        |  16 +++
 21 files changed, 278 insertions(+), 77 deletions(-)

--
2.17.1

#14 lore raw
In reply to [email protected]
Quoted 33 lines · On Tue, Nov 17, 2020 at 11:56:25AM -0800, [email protected] wrote:

From: Kan Liang <[email protected]>

Current perf can report both virtual addresses and physical addresses, but not the page size. Without the page size information of the utilized page, users cannot decide whether to promote/demote large pages to optimize memory usage.

The kernel patches have been merged into tip perf/core branch, commit 8d97e71811aa ("perf/core: Add PERF_SAMPLE_DATA_PAGE_SIZE") commit 76a5433f95f3 ("perf/x86/intel: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 4cb6a42e4c4b ("powerpc/perf: Support PERF_SAMPLE_DATA_PAGE_SIZE") commit 995f088efebe ("perf/core: Add support for PERF_SAMPLE_CODE_PAGE_SIZE") commit 51b646b2d9f8 ("perf,mm: Handle non-page-table-aligned hugetlbfs")

and Peter's perf/core branch
commit 524680ce47a1 ("mm/gup: Provide gup_get_pte() more generic") commit 44a35d6937d2 ("mm: Introduce pXX_leaf_size()") commit 2f1e2f091ad0 ("perf/core: Fix arch_perf_get_page_size()") commit 7649e44aacdd ("arm64/mm: Implement pXX_leaf_size() support") commit 1df1ae7e262c ("sparc64/mm: Implement pXX_leaf_size() support")

This patch set is to enable the page size support in user tools.

Kan Liang (8):
tools headers UAPI: Update tools's copy of linux/perf_event.h perf record: Support new sample type for data page size perf script: Support data page size
perf sort: Add sort option for data page size
perf mem: Factor out a function to generate sort order perf mem: Clean up output format
perf mem: Support data page size
perf test: Add test case for PERF_SAMPLE_DATA_PAGE_SIZE

Quoted 5 lines

Stephane Eranian (4):
perf tools: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf script: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf report: Add support for PERF_SAMPLE_CODE_PAGE_SIZE perf test: Add test case for PERF_SAMPLE_CODE_PAGE_SIZE

hi,
I can't compile this on Fedora 32, check the log below

jirka

---

$ make JOBS=1
  BUILD:   Doing 'make -j1' parallel build
Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h'
diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h
  CC       util/parse-events.o
  CC       util/session.o
util/session.c: In function ‘machines__deliver_event’:
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                 from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                 from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
   67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   68 |        __bos (__s), __fmt, __va_arg_pack ());
      |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                 from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                 from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
   67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   68 |        __bos (__s), __fmt, __va_arg_pack ());
      |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
util/session.c: In function ‘get_page_size_name’:
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
 1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
      |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                 from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                 from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
   67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
      |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   68 |        __bos (__s), __fmt, __va_arg_pack ());
      |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
make[4]: *** [/home/jolsa/kernel/linux-perf/tools/build/Makefile.build:97: util/session.o] Error 1
make[3]: *** [/home/jolsa/kernel/linux-perf/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:647: perf-in.o] Error 2
make[1]: *** [Makefile.perf:233: sub-make] Error 2
make: *** [Makefile:70: all] Error 2
author
#15 lore raw
Quoted 3 lines · Jiri Olsa

hi,
I can't compile this on Fedora 32, check the log below

The patch set was compiled with GCC 9. I will install a GCC 10 and fix all the warnings.

Thanks,
Kan

Quoted 60 lines

jirka

---

$ make JOBS=1
   BUILD:   Doing 'make -j1' parallel build
Warning: Kernel ABI header at 'tools/include/uapi/linux/perf_event.h' differs from latest version at 'include/uapi/linux/perf_event.h'
diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h
   CC       util/parse-events.o
   CC       util/session.o
util/session.c: In function ‘machines__deliver_event’:
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                  from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                  from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
    67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
       |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    68 |        __bos (__s), __fmt, __va_arg_pack ());
       |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                  from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                  from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
    67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
       |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    68 |        __bos (__s), __fmt, __va_arg_pack ());
       |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
util/session.c: In function ‘get_page_size_name’:
util/session.c:1278:37: error: ‘%lu’ directive output may be truncated writing between 1 and 20 bytes into a region of size 10 [-Werror=format-truncation=]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                     ^~~
util/session.c:1278:36: note: directive argument in the range [1, 18446744073709551615]
  1278 |  snprintf(str, PAGE_SIZE_NAME_LEN, "%lu%c", size, suffixes[i]);
       |                                    ^~~~~~~
In file included from /usr/include/stdio.h:867,
                  from /home/jolsa/kernel/linux-perf/tools/lib/perf/include/perf/cpumap.h:6,
                  from util/session.c:13:
/usr/include/bits/stdio2.h:67:10: note: ‘__builtin___snprintf_chk’ output between 3 and 22 bytes into a destination of size 10
    67 |   return __builtin___snprintf_chk (__s, __n, __USE_FORTIFY_LEVEL - 1,
       |          ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    68 |        __bos (__s), __fmt, __va_arg_pack ());
       |        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
make[4]: *** [/home/jolsa/kernel/linux-perf/tools/build/Makefile.build:97: util/session.o] Error 1
make[3]: *** [/home/jolsa/kernel/linux-perf/tools/build/Makefile.build:139: util] Error 2
make[2]: *** [Makefile.perf:647: perf-in.o] Error 2
make[1]: *** [Makefile.perf:233: sub-make] Error 2
make: *** [Makefile:70: all] Error 2