tracing/kmemtrace: normalize the raw tracer event to the unified tracing API

Impact: new tracer plugin

This patch adapts kmemtrace raw events tracing to the unified tracing API.

To enable and use this tracer, just do the following:

 echo kmemtrace > /debugfs/tracing/current_tracer
 cat /debugfs/tracing/trace

You will have the following output:

 # tracer: kmemtrace
 #
 #
 # ALLOC  TYPE  REQ   GIVEN  FLAGS           POINTER         NODE    CALLER
 # FREE   |      |     |       |              |   |            |        |
 # |

type_id 1 call_site 18446744071565527833 ptr 18446612134395152256
type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1
type_id 1 call_site 18446744071565585534 ptr 18446612134405955584
type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1
type_id 0 call_site 18446744071565636711 ptr 18446612134345164672 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1
type_id 1 call_site 18446744071565585534 ptr 18446612134405955584
type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1
type_id 0 call_site 18446744071565636711 ptr 18446612134345164912 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1
type_id 1 call_site 18446744071565585534 ptr 18446612134405955584
type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1
type_id 0 call_site 18446744071565636711 ptr 18446612134345165152 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1
type_id 0 call_site 18446744071566144042 ptr 18446612134346191680 bytes_req 1304 bytes_alloc 1312 gfp_flags 208 node -1
type_id 1 call_site 18446744071565585534 ptr 18446612134405955584
type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1
type_id 1 call_site 18446744071565585534 ptr 18446612134405955584

That was to stay backward compatible with the format output produced in
inux/tracepoint.h.

This is the default ouput, but note that I tried something else.

If you change an option:

echo kmem_minimalistic > /debugfs/trace_options

and then cat /debugfs/trace, you will have the following output:

 # tracer: kmemtrace
 #
 #
 # ALLOC  TYPE  REQ   GIVEN  FLAGS           POINTER         NODE    CALLER
 # FREE   |      |     |       |              |   |            |        |
 # |

   -      C                            0xffff88007c088780          file_free_rcu
   +      K   4096   4096   000000d0   0xffff88007cad6000     -1   getname
   -      C                            0xffff88007cad6000          putname
   +      K   4096   4096   000000d0   0xffff88007cad6000     -1   getname
   +      K    240    240   000000d0   0xffff8800790dc780     -1   d_alloc
   -      C                            0xffff88007cad6000          putname
   +      K   4096   4096   000000d0   0xffff88007cad6000     -1   getname
   +      K    240    240   000000d0   0xffff8800790dc870     -1   d_alloc
   -      C                            0xffff88007cad6000          putname
   +      K   4096   4096   000000d0   0xffff88007cad6000     -1   getname
   +      K    240    240   000000d0   0xffff8800790dc960     -1   d_alloc
   +      K   1304   1312   000000d0   0xffff8800791d7340     -1   reiserfs_alloc_inode
   -      C                            0xffff88007cad6000          putname
   +      K   4096   4096   000000d0   0xffff88007cad6000     -1   getname
   -      C                            0xffff88007cad6000          putname
   +      K    992   1000   000000d0   0xffff880079045b58     -1   alloc_inode
   +      K    768   1024   000080d0   0xffff88007c096400     -1   alloc_pipe_info
   +      K    240    240   000000d0   0xffff8800790dca50     -1   d_alloc
   +      K    272    320   000080d0   0xffff88007c088780     -1   get_empty_filp
   +      K    272    320   000080d0   0xffff88007c088000     -1   get_empty_filp

Yeah I shall confess kmem_minimalistic should be: kmem_alternative.

Whatever, I find it more readable but this a personal opinion of course.
We can drop it if you want.

On the ALLOC/FREE column, + means an allocation and - a free.

On the type column, you have K = kmalloc, C = cache, P = page

I would like the flags to be GFP_* strings but that would not be easy to not
break the column with strings....

About the node...it seems to always be -1. I don't know why but that shouldn't
be difficult to find.

I moved linux/tracepoint.h to trace/tracepoint.h as well. I think that would
be more easy to find the tracer headers if they are all in their common
directory.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Frederic Weisbecker 2008-12-29 13:42:23 -08:00 committed by Ingo Molnar
parent 7a51cffbd1
commit 36994e58a4
12 changed files with 401 additions and 41 deletions

View File

@ -14,7 +14,7 @@
#include <asm/page.h> /* kmalloc_sizes.h needs PAGE_SIZE */
#include <asm/cache.h> /* kmalloc_sizes.h needs L1_CACHE_BYTES */
#include <linux/compiler.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
/* Size description struct for general caches. */
struct cache_sizes {

View File

@ -10,7 +10,7 @@
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */

View File

@ -22,28 +22,17 @@ enum kmemtrace_type_id {
extern void kmemtrace_init(void);
static inline void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
extern void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags,
int node)
{
trace_mark(kmemtrace_alloc, "type_id %d call_site %lu ptr %lu "
"bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d",
type_id, call_site, (unsigned long) ptr,
(unsigned long) bytes_req, (unsigned long) bytes_alloc,
(unsigned long) gfp_flags, node);
}
int node);
static inline void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
extern void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
unsigned long call_site,
const void *ptr)
{
trace_mark(kmemtrace_free, "type_id %d call_site %lu ptr %lu",
type_id, call_site, (unsigned long) ptr);
}
const void *ptr);
#else /* CONFIG_KMEMTRACE */

View File

@ -70,7 +70,7 @@
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>

View File

@ -264,6 +264,28 @@ config HW_BRANCH_TRACER
This tracer records all branches on the system in a circular
buffer giving access to the last N branches for each cpu.
config KMEMTRACE
bool "Trace SLAB allocations"
select TRACING
depends on RELAY
help
kmemtrace provides tracing for slab allocator functions, such as
kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
data is then fed to the userspace application in order to analyse
allocation hotspots, internal fragmentation and so on, making it
possible to see how well an allocator performs, as well as debug
and profile kernel code.
This requires an userspace application to use. See
Documentation/vm/kmemtrace.txt for more information.
Saying Y will make the kernel somewhat larger and slower. However,
if you disable kmemtrace at run-time or boot-time, the performance
impact is minimal (depending on the arch the kernel is built for).
If unsure, say N.
config DYNAMIC_FTRACE
bool "enable/disable ftrace tracepoints dynamically"
depends on FUNCTION_TRACER

View File

@ -33,5 +33,6 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
obj-$(CONFIG_POWER_TRACER) += trace_power.o
obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
libftrace-y := ftrace.o

343
kernel/trace/kmemtrace.c Normal file
View File

@ -0,0 +1,343 @@
/*
* Memory allocator tracing
*
* Copyright (C) 2008 Eduard - Gabriel Munteanu
* Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
* Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
*/
#include <linux/dcache.h>
#include <linux/debugfs.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <trace/kmemtrace.h>
#include "trace.h"
#include "trace_output.h"
/* Select an alternative, minimalistic output than the original one */
#define TRACE_KMEM_OPT_MINIMAL 0x1
static struct tracer_opt kmem_opts[] = {
/* Default disable the minimalistic output */
{ TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
{ }
};
static struct tracer_flags kmem_tracer_flags = {
.val = 0,
.opts = kmem_opts
};
static bool kmem_tracing_enabled __read_mostly;
static struct trace_array *kmemtrace_array;
static int kmem_trace_init(struct trace_array *tr)
{
int cpu;
kmemtrace_array = tr;
for_each_cpu_mask(cpu, cpu_possible_map)
tracing_reset(tr, cpu);
kmem_tracing_enabled = true;
return 0;
}
static void kmem_trace_reset(struct trace_array *tr)
{
kmem_tracing_enabled = false;
}
static void kmemtrace_headers(struct seq_file *s)
{
/* Don't need headers for the original kmemtrace output */
if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
return;
seq_printf(s, "#\n");
seq_printf(s, "# ALLOC TYPE REQ GIVEN FLAGS "
" POINTER NODE CALLER\n");
seq_printf(s, "# FREE | | | | "
" | | | |\n");
seq_printf(s, "# |\n\n");
}
/*
* The two following functions give the original output from kmemtrace,
* or something close to....perhaps they need some missing things
*/
static enum print_line_t
kmemtrace_print_alloc_original(struct trace_iterator *iter,
struct kmemtrace_alloc_entry *entry)
{
struct trace_seq *s = &iter->seq;
int ret;
/* Taken from the old linux/kmemtrace.h */
ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
"bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
entry->type_id, entry->call_site, (unsigned long) entry->ptr,
(unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
(unsigned long) entry->gfp_flags, entry->node);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
kmemtrace_print_free_original(struct trace_iterator *iter,
struct kmemtrace_free_entry *entry)
{
struct trace_seq *s = &iter->seq;
int ret;
/* Taken from the old linux/kmemtrace.h */
ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
entry->type_id, entry->call_site, (unsigned long) entry->ptr);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
/* The two other following provide a more minimalistic output */
static enum print_line_t
kmemtrace_print_alloc_compress(struct trace_iterator *iter,
struct kmemtrace_alloc_entry *entry)
{
struct trace_seq *s = &iter->seq;
int ret;
/* Alloc entry */
ret = trace_seq_printf(s, " + ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Type */
switch (entry->type_id) {
case KMEMTRACE_TYPE_KMALLOC:
ret = trace_seq_printf(s, "K ");
break;
case KMEMTRACE_TYPE_CACHE:
ret = trace_seq_printf(s, "C ");
break;
case KMEMTRACE_TYPE_PAGES:
ret = trace_seq_printf(s, "P ");
break;
default:
ret = trace_seq_printf(s, "? ");
}
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Requested */
ret = trace_seq_printf(s, "%4d ", entry->bytes_req);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Allocated */
ret = trace_seq_printf(s, "%4d ", entry->bytes_alloc);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Flags
* TODO: would be better to see the name of the GFP flag names
*/
ret = trace_seq_printf(s, "%08x ", entry->gfp_flags);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Pointer to allocated */
ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Node */
ret = trace_seq_printf(s, "%4d ", entry->node);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Call site */
ret = seq_print_ip_sym(s, entry->call_site, 0);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
if (!trace_seq_printf(s, "\n"))
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
kmemtrace_print_free_compress(struct trace_iterator *iter,
struct kmemtrace_free_entry *entry)
{
struct trace_seq *s = &iter->seq;
int ret;
/* Free entry */
ret = trace_seq_printf(s, " - ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Type */
switch (entry->type_id) {
case KMEMTRACE_TYPE_KMALLOC:
ret = trace_seq_printf(s, "K ");
break;
case KMEMTRACE_TYPE_CACHE:
ret = trace_seq_printf(s, "C ");
break;
case KMEMTRACE_TYPE_PAGES:
ret = trace_seq_printf(s, "P ");
break;
default:
ret = trace_seq_printf(s, "? ");
}
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Skip requested/allocated/flags */
ret = trace_seq_printf(s, " ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Pointer to allocated */
ret = trace_seq_printf(s, "0x%tx ", (ptrdiff_t)entry->ptr);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Skip node */
ret = trace_seq_printf(s, " ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Call site */
ret = seq_print_ip_sym(s, entry->call_site, 0);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
if (!trace_seq_printf(s, "\n"))
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
{
struct trace_entry *entry = iter->ent;
switch (entry->type) {
case TRACE_KMEM_ALLOC: {
struct kmemtrace_alloc_entry *field;
trace_assign_type(field, entry);
if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
return kmemtrace_print_alloc_compress(iter, field);
else
return kmemtrace_print_alloc_original(iter, field);
}
case TRACE_KMEM_FREE: {
struct kmemtrace_free_entry *field;
trace_assign_type(field, entry);
if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
return kmemtrace_print_free_compress(iter, field);
else
return kmemtrace_print_free_original(iter, field);
}
default:
return TRACE_TYPE_UNHANDLED;
}
}
/* Trace allocations */
void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
gfp_t gfp_flags,
int node)
{
struct ring_buffer_event *event;
struct kmemtrace_alloc_entry *entry;
struct trace_array *tr = kmemtrace_array;
unsigned long irq_flags;
if (!kmem_tracing_enabled)
return;
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
if (!event)
return;
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, 0, 0);
entry->ent.type = TRACE_KMEM_ALLOC;
entry->call_site = call_site;
entry->ptr = ptr;
entry->bytes_req = bytes_req;
entry->bytes_alloc = bytes_alloc;
entry->gfp_flags = gfp_flags;
entry->node = node;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
trace_wake_up();
}
void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
unsigned long call_site,
const void *ptr)
{
struct ring_buffer_event *event;
struct kmemtrace_free_entry *entry;
struct trace_array *tr = kmemtrace_array;
unsigned long irq_flags;
if (!kmem_tracing_enabled)
return;
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
if (!event)
return;
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, 0, 0);
entry->ent.type = TRACE_KMEM_FREE;
entry->type_id = type_id;
entry->call_site = call_site;
entry->ptr = ptr;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
trace_wake_up();
}
static struct tracer kmem_tracer __read_mostly = {
.name = "kmemtrace",
.init = kmem_trace_init,
.reset = kmem_trace_reset,
.print_line = kmemtrace_print_line,
.print_header = kmemtrace_headers,
.flags = &kmem_tracer_flags
};
static int __init init_kmem_tracer(void)
{
return register_tracer(&kmem_tracer);
}
device_initcall(init_kmem_tracer);

View File

@ -9,6 +9,7 @@
#include <linux/mmiotrace.h>
#include <linux/ftrace.h>
#include <trace/boot.h>
#include <trace/kmemtrace.h>
enum trace_type {
__TRACE_FIRST_TYPE = 0,
@ -29,6 +30,8 @@ enum trace_type {
TRACE_GRAPH_ENT,
TRACE_USER_STACK,
TRACE_HW_BRANCHES,
TRACE_KMEM_ALLOC,
TRACE_KMEM_FREE,
TRACE_POWER,
__TRACE_LAST_TYPE
@ -170,6 +173,24 @@ struct trace_power {
struct power_trace state_data;
};
struct kmemtrace_alloc_entry {
struct trace_entry ent;
enum kmemtrace_type_id type_id;
unsigned long call_site;
const void *ptr;
size_t bytes_req;
size_t bytes_alloc;
gfp_t gfp_flags;
int node;
};
struct kmemtrace_free_entry {
struct trace_entry ent;
enum kmemtrace_type_id type_id;
unsigned long call_site;
const void *ptr;
};
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
@ -280,6 +301,10 @@ extern void __ftrace_bad_type(void);
TRACE_GRAPH_RET); \
IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \
TRACE_KMEM_ALLOC); \
IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
TRACE_KMEM_FREE); \
__ftrace_bad_type(); \
} while (0)

View File

@ -803,26 +803,6 @@ config FIREWIRE_OHCI_REMOTE_DMA
If unsure, say N.
config KMEMTRACE
bool "Kernel memory tracer (kmemtrace)"
depends on RELAY && DEBUG_FS && MARKERS
help
kmemtrace provides tracing for slab allocator functions, such as
kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
data is then fed to the userspace application in order to analyse
allocation hotspots, internal fragmentation and so on, making it
possible to see how well an allocator performs, as well as debug
and profile kernel code.
This requires an userspace application to use. See
Documentation/vm/kmemtrace.txt for more information.
Saying Y will make the kernel somewhat larger and slower. However,
if you disable kmemtrace at run-time or boot-time, the performance
impact is minimal (depending on the arch the kernel is built for).
If unsure, say N.
menuconfig BUILD_DOCSRC
bool "Build targets in Documentation/ tree"
depends on HEADERS_CHECK

View File

@ -10,7 +10,7 @@
#include <linux/module.h>
#include <linux/marker.h>
#include <linux/gfp.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
#define KMEMTRACE_SUBBUF_SIZE 524288
#define KMEMTRACE_DEF_N_SUBBUFS 20

View File

@ -65,7 +65,7 @@
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
#include <asm/atomic.h>
/*

View File

@ -16,7 +16,7 @@
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/kmemtrace.h>
#include <trace/kmemtrace.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>