| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1427092244-22764-3-git-send-email-namhyung@kernel.org>
Date: Mon, 23 Mar 2015 15:30:41 +0900
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Jiri Olsa <jolsa@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
David Ahern <dsahern@...il.com>,
Minchan Kim <minchan@...nel.org>,
Joonsoo Kim <js1304@...il.com>
Subject: [PATCH 2/5] perf kmem: Analyze page allocator events also
The perf kmem command records and analyze kernel memory allocation
only for SLAB objects. This patch implement a simple page allocator
analyzer using kmem:mm_page_alloc and kmem:mm_page_free events.
It adds two new options of --slab and --page. The --slab option is
for analyzing SLAB allocator and that's what perf kmem currently does.
The new --page option enables page allocator events and analyze kernel
memory usage in page unit. Currently, 'stat --alloc' subcommand is
implemented only.
If none of these --slab nor --page is specified, --slab is implied.
# perf kmem stat --page --alloc --line 10
-------------------------------------------------------------------------------------
Page | Total alloc (KB) | Hits | Order | Migration type | GFP flags
-------------------------------------------------------------------------------------
ffffea0015e48e00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea0015e47400 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea001440f600 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea001440cc00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c6300 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c5c00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c5000 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c4f00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c4e00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
ffffea00140c4d00 | 16 | 1 | 2 | RECLAIMABLE | 00285250
... | ... | ... | ... | ... | ...
-------------------------------------------------------------------------------------
SUMMARY (page allocator)
========================
Total allocation requests : 44,260 [ 177,256 KB ]
Total free requests : 117 [ 468 KB ]
Total alloc+freed requests : 49 [ 196 KB ]
Total alloc-only requests : 44,211 [ 177,060 KB ]
Total free-only requests : 68 [ 272 KB ]
Total allocation failures : 0 [ 0 KB ]
Order Unmovable Reclaimable Movable Reserved CMA/Isolated
----- ------------ ------------ ------------ ------------ ------------
0 32 . 44,210 . .
1 . . . . .
2 . 18 . . .
3 . . . . .
4 . . . . .
5 . . . . .
6 . . . . .
7 . . . . .
8 . . . . .
9 . . . . .
10 . . . . .
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
tools/perf/Documentation/perf-kmem.txt | 8 +-
tools/perf/builtin-kmem.c | 376 +++++++++++++++++++++++++++++++--
2 files changed, 368 insertions(+), 16 deletions(-)
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 150253cc3c97..23219c65c16f 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -3,7 +3,7 @@ perf-kmem(1)
NAME
----
-perf-kmem - Tool to trace/measure kernel memory(slab) properties
+perf-kmem - Tool to trace/measure kernel memory properties
SYNOPSIS
--------
@@ -46,6 +46,12 @@ OPTIONS
--raw-ip::
Print raw ip instead of symbol
+--slab::
+ Analyze SLAB allocator events.
+
+--page::
+ Analyze page allocator events
+
SEE ALSO
--------
linkperf:perf-record[1]
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 64d3623d45a0..76a527dc6ba1 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -22,6 +22,11 @@
#include <linux/string.h>
#include <locale.h>
+static int kmem_slab;
+static int kmem_page;
+
+static long kmem_page_size;
+
struct alloc_stat;
typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
@@ -226,6 +231,139 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
return 0;
}
+static u64 total_page_alloc_bytes;
+static u64 total_page_free_bytes;
+static u64 total_page_nomatch_bytes;
+static u64 total_page_fail_bytes;
+static unsigned long nr_page_allocs;
+static unsigned long nr_page_frees;
+static unsigned long nr_page_fails;
+static unsigned long nr_page_nomatch;
+
+#define MAX_MIGRATE_TYPES 6
+#define MAX_PAGE_ORDER 11
+
+static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
+
+struct page_stat {
+ struct rb_node node;
+ u64 page;
+ int order;
+ unsigned gfp_flags;
+ unsigned migrate_type;
+ u64 alloc_bytes;
+ u64 free_bytes;
+ int nr_alloc;
+ int nr_free;
+};
+
+static struct rb_root page_tree;
+static struct rb_root page_alloc_sorted;
+
+static struct page_stat *search_page_stat(unsigned long page, bool create)
+{
+ struct rb_node **node = &page_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct page_stat *data;
+
+ while (*node) {
+ s64 cmp;
+
+ parent = *node;
+ data = rb_entry(*node, struct page_stat, node);
+
+ cmp = data->page - page;
+ if (cmp < 0)
+ node = &parent->rb_left;
+ else if (cmp > 0)
+ node = &parent->rb_right;
+ else
+ return data;
+ }
+
+ if (!create)
+ return NULL;
+
+ data = zalloc(sizeof(*data));
+ if (data != NULL) {
+ data->page = page;
+
+ rb_link_node(&data->node, parent, node);
+ rb_insert_color(&data->node, &page_tree);
+ }
+
+ return data;
+}
+
+static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ u64 page = perf_evsel__intval(evsel, sample, "page");
+ unsigned int order = perf_evsel__intval(evsel, sample, "order");
+ unsigned int gfp_flags = perf_evsel__intval(evsel, sample, "gfp_flags");
+ unsigned int migrate_type = perf_evsel__intval(evsel, sample,
+ "migratetype");
+ u64 bytes = kmem_page_size << order;
+ struct page_stat *stat;
+
+ if (page == 0) {
+ nr_page_fails++;
+ total_page_fail_bytes += bytes;
+
+ return 0;
+ }
+
+ /*
+ * XXX: We'd better to use PFN instead of page pointer to deal
+ * with things like partial freeing. But AFAIK there's no way
+ * to convert a pointer to struct page into PFN in userspace.
+ */
+ stat = search_page_stat(page, true);
+ if (stat == NULL)
+ return -1;
+
+ stat->order = order;
+ stat->gfp_flags = gfp_flags;
+ stat->migrate_type = migrate_type;
+
+ stat->nr_alloc++;
+ nr_page_allocs++;
+ stat->alloc_bytes += bytes;
+ total_page_alloc_bytes += bytes;
+
+ order_stats[order][migrate_type]++;
+
+ return 0;
+}
+
+static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
+ struct perf_sample *sample)
+{
+ u64 page = perf_evsel__intval(evsel, sample, "page");
+ unsigned int order = perf_evsel__intval(evsel, sample, "order");
+ u64 bytes = kmem_page_size << order;
+ struct page_stat *stat;
+
+ nr_page_frees++;
+ total_page_free_bytes += bytes;
+
+ stat = search_page_stat(page, false);
+ if (stat == NULL) {
+ pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
+ page, order);
+
+ nr_page_nomatch++;
+ total_page_nomatch_bytes += bytes;
+
+ return 0;
+ }
+
+ stat->nr_free++;
+ stat->free_bytes += bytes;
+
+ return 0;
+}
+
typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
struct perf_sample *sample);
@@ -270,8 +408,9 @@ static double fragmentation(unsigned long n_req, unsigned long n_alloc)
return 100.0 - (100.0 * n_req / n_alloc);
}
-static void __print_result(struct rb_root *root, struct perf_session *session,
- int n_lines, int is_caller)
+static void __print_slab_result(struct rb_root *root,
+ struct perf_session *session,
+ int n_lines, int is_caller)
{
struct rb_node *next;
struct machine *machine = &session->machines.host;
@@ -323,9 +462,50 @@ static void __print_result(struct rb_root *root, struct perf_session *session,
printf("%.105s\n", graph_dotted_line);
}
-static void print_summary(void)
+static const char * const migrate_type_str[] = {
+ "UNMOVABLE",
+ "RECLAIMABLE",
+ "MOVABLE",
+ "RESERVED",
+ "CMA/ISOLATE",
+ "UNKNOWN",
+};
+
+static void __print_page_result(struct rb_root *root,
+ struct perf_session *session __maybe_unused,
+ int n_lines)
+{
+ struct rb_node *next = rb_first(root);
+
+ printf("\n%.86s\n", graph_dotted_line);
+ printf(" Page | Total alloc (KB) | Hits | Order | Migration type | GFP flags\n");
+ printf("%.86s\n", graph_dotted_line);
+
+ while (next && n_lines--) {
+ struct page_stat *data;
+
+ data = rb_entry(next, struct page_stat, node);
+
+ printf(" %016llx | %'16llu | %'9d | %5d | %14s | %08lx\n",
+ (unsigned long long)data->page,
+ (unsigned long long)data->alloc_bytes / 1024,
+ data->nr_alloc, data->order,
+ migrate_type_str[data->migrate_type],
+ (unsigned long)data->gfp_flags);
+
+ next = rb_next(next);
+ }
+
+ if (n_lines == -1)
+ printf(" ... | ... | ... | ... | ... | ... \n");
+
+ printf("%.86s\n", graph_dotted_line);
+}
+
+static void print_slab_summary(void)
{
- printf("\nSUMMARY\n=======\n");
+ printf("\nSUMMARY (SLAB allocator)");
+ printf("\n========================\n");
printf("Total bytes requested: %'lu\n", total_requested);
printf("Total bytes allocated: %'lu\n", total_allocated);
printf("Total bytes wasted on internal fragmentation: %'lu\n",
@@ -335,13 +515,73 @@ static void print_summary(void)
printf("Cross CPU allocations: %'lu/%'lu\n", nr_cross_allocs, nr_allocs);
}
-static void print_result(struct perf_session *session)
+static void print_page_summary(void)
+{
+ int o, m;
+ u64 nr_alloc_freed = nr_page_frees - nr_page_nomatch;
+ u64 total_alloc_freed_bytes = total_page_free_bytes - total_page_nomatch_bytes;
+
+ printf("\nSUMMARY (page allocator)");
+ printf("\n========================\n");
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation requests",
+ nr_page_allocs, total_page_alloc_bytes / 1024);
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free requests",
+ nr_page_frees, total_page_free_bytes / 1024);
+ printf("\n");
+
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
+ nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
+ nr_page_allocs - nr_alloc_freed,
+ (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free-only requests",
+ nr_page_nomatch, total_page_nomatch_bytes / 1024);
+ printf("\n");
+
+ printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total allocation failures",
+ nr_page_fails, total_page_fail_bytes / 1024);
+ printf("\n");
+
+ printf("%5s %12s %12s %12s %12s %12s\n", "Order", "Unmovable",
+ "Reclaimable", "Movable", "Reserved", "CMA/Isolated");
+ printf("%.5s %.12s %.12s %.12s %.12s %.12s\n", graph_dotted_line,
+ graph_dotted_line, graph_dotted_line, graph_dotted_line,
+ graph_dotted_line, graph_dotted_line);
+
+ for (o = 0; o < MAX_PAGE_ORDER; o++) {
+ printf("%5d", o);
+ for (m = 0; m < MAX_MIGRATE_TYPES - 1; m++) {
+ if (order_stats[o][m])
+ printf(" %'12d", order_stats[o][m]);
+ else
+ printf(" %12c", '.');
+ }
+ printf("\n");
+ }
+}
+
+static void print_slab_result(struct perf_session *session)
{
if (caller_flag)
- __print_result(&root_caller_sorted, session, caller_lines, 1);
+ __print_slab_result(&root_caller_sorted, session, caller_lines, 1);
if (alloc_flag)
- __print_result(&root_alloc_sorted, session, alloc_lines, 0);
- print_summary();
+ __print_slab_result(&root_alloc_sorted, session, alloc_lines, 0);
+ print_slab_summary();
+}
+
+static void print_page_result(struct perf_session *session)
+{
+ if (alloc_flag)
+ __print_page_result(&page_alloc_sorted, session, alloc_lines);
+ print_page_summary();
+}
+
+static void print_result(struct perf_session *session)
+{
+ if (kmem_slab)
+ print_slab_result(session);
+ if (kmem_page)
+ print_page_result(session);
}
struct sort_dimension {
@@ -353,8 +593,8 @@ struct sort_dimension {
static LIST_HEAD(caller_sort);
static LIST_HEAD(alloc_sort);
-static void sort_insert(struct rb_root *root, struct alloc_stat *data,
- struct list_head *sort_list)
+static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
+ struct list_head *sort_list)
{
struct rb_node **new = &(root->rb_node);
struct rb_node *parent = NULL;
@@ -383,8 +623,8 @@ static void sort_insert(struct rb_root *root, struct alloc_stat *data,
rb_insert_color(&data->node, root);
}
-static void __sort_result(struct rb_root *root, struct rb_root *root_sorted,
- struct list_head *sort_list)
+static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted,
+ struct list_head *sort_list)
{
struct rb_node *node;
struct alloc_stat *data;
@@ -396,26 +636,78 @@ static void __sort_result(struct rb_root *root, struct rb_root *root_sorted,
rb_erase(node, root);
data = rb_entry(node, struct alloc_stat, node);
- sort_insert(root_sorted, data, sort_list);
+ sort_slab_insert(root_sorted, data, sort_list);
+ }
+}
+
+static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+{
+ struct rb_node **new = &root->rb_node;
+ struct rb_node *parent = NULL;
+
+ while (*new) {
+ struct page_stat *this;
+ int cmp = 0;
+
+ this = rb_entry(*new, struct page_stat, node);
+ parent = *new;
+
+ /* TODO: support more sort key */
+ cmp = data->alloc_bytes - this->alloc_bytes;
+
+ if (cmp > 0)
+ new = &parent->rb_left;
+ else
+ new = &parent->rb_right;
+ }
+
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+}
+
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+{
+ struct rb_node *node;
+ struct page_stat *data;
+
+ for (;;) {
+ node = rb_first(root);
+ if (!node)
+ break;
+
+ rb_erase(node, root);
+ data = rb_entry(node, struct page_stat, node);
+ sort_page_insert(root_sorted, data);
}
}
static void sort_result(void)
{
- __sort_result(&root_alloc_stat, &root_alloc_sorted, &alloc_sort);
- __sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
+ if (kmem_slab) {
+ __sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
+ &alloc_sort);
+ __sort_slab_result(&root_caller_stat, &root_caller_sorted,
+ &caller_sort);
+ }
+ if (kmem_page) {
+ __sort_page_result(&page_tree, &page_alloc_sorted);
+ }
}
static int __cmd_kmem(struct perf_session *session)
{
int err = -EINVAL;
const struct perf_evsel_str_handler kmem_tracepoints[] = {
+ /* slab allocator */
{ "kmem:kmalloc", perf_evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", perf_evsel__process_alloc_event, },
{ "kmem:kmalloc_node", perf_evsel__process_alloc_node_event, },
{ "kmem:kmem_cache_alloc_node", perf_evsel__process_alloc_node_event, },
{ "kmem:kfree", perf_evsel__process_free_event, },
{ "kmem:kmem_cache_free", perf_evsel__process_free_event, },
+ /* page allocator */
+ { "kmem:mm_page_alloc", perf_evsel__process_page_alloc_event, },
+ { "kmem:mm_page_free", perf_evsel__process_page_free_event, },
};
if (!perf_session__has_traces(session, "kmem record"))
@@ -612,6 +904,22 @@ static int parse_alloc_opt(const struct option *opt __maybe_unused,
return 0;
}
+static int parse_slab_opt(const struct option *opt __maybe_unused,
+ const char *arg __maybe_unused,
+ int unset __maybe_unused)
+{
+ kmem_slab = (kmem_page + 1);
+ return 0;
+}
+
+static int parse_page_opt(const struct option *opt __maybe_unused,
+ const char *arg __maybe_unused,
+ int unset __maybe_unused)
+{
+ kmem_page = (kmem_slab + 1);
+ return 0;
+}
+
static int parse_line_opt(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
{
@@ -634,6 +942,8 @@ static int __cmd_record(int argc, const char **argv)
{
const char * const record_args[] = {
"record", "-a", "-R", "-c", "1",
+ };
+ const char * const slab_events[] = {
"-e", "kmem:kmalloc",
"-e", "kmem:kmalloc_node",
"-e", "kmem:kfree",
@@ -641,10 +951,19 @@ static int __cmd_record(int argc, const char **argv)
"-e", "kmem:kmem_cache_alloc_node",
"-e", "kmem:kmem_cache_free",
};
+ const char * const page_events[] = {
+ "-e", "kmem:mm_page_alloc",
+ "-e", "kmem:mm_page_free",
+ };
unsigned int rec_argc, i, j;
const char **rec_argv;
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+ if (kmem_slab)
+ rec_argc += ARRAY_SIZE(slab_events);
+ if (kmem_page)
+ rec_argc += ARRAY_SIZE(page_events);
+
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
@@ -653,6 +972,15 @@ static int __cmd_record(int argc, const char **argv)
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = strdup(record_args[i]);
+ if (kmem_slab) {
+ for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
+ rec_argv[i] = strdup(slab_events[j]);
+ }
+ if (kmem_page) {
+ for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
+ rec_argv[i] = strdup(page_events[j]);
+ }
+
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
@@ -675,6 +1003,10 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
+ OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
+ parse_slab_opt),
+ OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
+ parse_page_opt),
OPT_END()
};
const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -695,6 +1027,9 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (!argc)
usage_with_options(kmem_usage, kmem_options);
+ if (kmem_slab == 0 && kmem_page == 0)
+ kmem_slab = 1; /* for backward compatibility */
+
if (!strncmp(argv[0], "rec", 3)) {
symbol__init(NULL);
return __cmd_record(argc, argv);
@@ -704,6 +1039,17 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (session == NULL)
return -1;
+ if (kmem_page) {
+ struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+ if (evsel == NULL || evsel->tp_format == NULL) {
+ pr_err("invalid event found.. aborting\n");
+ return -1;
+ }
+
+ kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+ }
+
symbol__init(&session->header.env);
if (!strcmp(argv[0], "stat")) {
--
2.3.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists