From b9ce08c01020eb28bfbfa6faf1c740281c5f418e Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Sun, 10 Aug 2008 20:14:03 +0300 Subject: kmemtrace: Core implementation. 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. Signed-off-by: Eduard - Gabriel Munteanu Signed-off-by: Pekka Enberg --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index 7e117a231af1..be1fe2242a55 100644 --- a/init/main.c +++ b/init/main.c @@ -69,6 +69,7 @@ #include #include #include +#include #ifdef CONFIG_X86_LOCAL_APIC #include @@ -653,6 +654,7 @@ asmlinkage void __init start_kernel(void) enable_debug_pagealloc(); cpu_hotplug_init(); kmem_cache_init(); + kmemtrace_init(); debug_objects_mem_init(); idr_init_cache(); setup_per_cpu_pageset(); -- cgit v1.2.3-70-g09d2 From 36994e58a48fb8f9651c7dc845a6de298aba5bfc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Dec 2008 13:42:23 -0800 Subject: 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 Signed-off-by: Ingo Molnar --- include/linux/kmemtrace.h | 86 ------------ include/linux/slab_def.h | 2 +- include/linux/slub_def.h | 2 +- include/trace/kmemtrace.h | 75 ++++++++++ init/main.c | 2 +- kernel/trace/Kconfig | 22 +++ kernel/trace/Makefile | 1 + kernel/trace/kmemtrace.c | 343 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/trace/trace.h | 25 ++++ lib/Kconfig.debug | 20 --- mm/kmemtrace.c | 2 +- mm/slob.c | 2 +- mm/slub.c | 2 +- 13 files changed, 472 insertions(+), 112 deletions(-) delete mode 100644 include/linux/kmemtrace.h create mode 100644 include/trace/kmemtrace.h create mode 100644 kernel/trace/kmemtrace.c (limited to 'init') diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h deleted file mode 100644 index 5bea8ead6a6b..000000000000 --- a/include/linux/kmemtrace.h +++ /dev/null @@ -1,86 +0,0 @@ -/* - * Copyright (C) 2008 Eduard - Gabriel Munteanu - * - * This file is released under GPL version 2. - */ - -#ifndef _LINUX_KMEMTRACE_H -#define _LINUX_KMEMTRACE_H - -#ifdef __KERNEL__ - -#include -#include - -enum kmemtrace_type_id { - KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ - KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ - KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ -}; - -#ifdef CONFIG_KMEMTRACE - -extern void kmemtrace_init(void); - -static inline 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); -} - -static inline 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); -} - -#else /* CONFIG_KMEMTRACE */ - -static inline void kmemtrace_init(void) -{ -} - -static inline 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) -{ -} - -static inline void kmemtrace_mark_free(enum kmemtrace_type_id type_id, - unsigned long call_site, - const void *ptr) -{ -} - -#endif /* CONFIG_KMEMTRACE */ - -static inline void kmemtrace_mark_alloc(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) -{ - kmemtrace_mark_alloc_node(type_id, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, -1); -} - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_KMEMTRACE_H */ - diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 7555ce99f6d2..455f9affea9a 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -14,7 +14,7 @@ #include /* kmalloc_sizes.h needs PAGE_SIZE */ #include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include -#include +#include /* Size description struct for general caches. */ struct cache_sizes { diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index dc28432b5b9a..6b657f7dcb2b 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,7 +10,7 @@ #include #include #include -#include +#include enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h new file mode 100644 index 000000000000..ad8b7857855a --- /dev/null +++ b/include/trace/kmemtrace.h @@ -0,0 +1,75 @@ +/* + * Copyright (C) 2008 Eduard - Gabriel Munteanu + * + * This file is released under GPL version 2. + */ + +#ifndef _LINUX_KMEMTRACE_H +#define _LINUX_KMEMTRACE_H + +#ifdef __KERNEL__ + +#include +#include + +enum kmemtrace_type_id { + KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ + KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ + KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ +}; + +#ifdef CONFIG_KMEMTRACE + +extern void kmemtrace_init(void); + +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); + +extern void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr); + +#else /* CONFIG_KMEMTRACE */ + +static inline void kmemtrace_init(void) +{ +} + +static inline 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) +{ +} + +static inline void kmemtrace_mark_free(enum kmemtrace_type_id type_id, + unsigned long call_site, + const void *ptr) +{ +} + +#endif /* CONFIG_KMEMTRACE */ + +static inline void kmemtrace_mark_alloc(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) +{ + kmemtrace_mark_alloc_node(type_id, call_site, ptr, + bytes_req, bytes_alloc, gfp_flags, -1); +} + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_KMEMTRACE_H */ + diff --git a/init/main.c b/init/main.c index 9711586aa7c9..beca7aaddb22 100644 --- a/init/main.c +++ b/init/main.c @@ -70,7 +70,7 @@ #include #include #include -#include +#include #ifdef CONFIG_X86_LOCAL_APIC #include diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e2a4ff6fc3a6..27fb74b06b3c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -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 diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 349d5a93653f..513dc86b5dfa 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -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 diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c new file mode 100644 index 000000000000..d69cbe3c2a4b --- /dev/null +++ b/kernel/trace/kmemtrace.c @@ -0,0 +1,343 @@ +/* + * Memory allocator tracing + * + * Copyright (C) 2008 Eduard - Gabriel Munteanu + * Copyright (C) 2008 Pekka Enberg + * Copyright (C) 2008 Frederic Weisbecker + */ + +#include +#include +#include +#include +#include + +#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); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index cc7a4f864036..534505bb39b0 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,6 +9,7 @@ #include #include #include +#include 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) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b5417e23ba94..b0f239e443bc 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -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 diff --git a/mm/kmemtrace.c b/mm/kmemtrace.c index 2a70a805027c..0573b5080cc4 100644 --- a/mm/kmemtrace.c +++ b/mm/kmemtrace.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #define KMEMTRACE_SUBBUF_SIZE 524288 #define KMEMTRACE_DEF_N_SUBBUFS 20 diff --git a/mm/slob.c b/mm/slob.c index 0f1a49f40690..4d1c0fc33b6b 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -65,7 +65,7 @@ #include #include #include -#include +#include #include /* diff --git a/mm/slub.c b/mm/slub.c index cc4001fee7ac..7bf8cf8ec082 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3-70-g09d2 From 91f73f90d97fa67effbb49e0a79c50cf26dfe324 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 20 Feb 2009 17:34:06 +0100 Subject: tracing/markers: make markers select tracepoints Sometimes it happens that KConfig dependencies are not handled like in the following scenario: - config A bool - config B bool depends on A - config C bool select B If one selects C, then it will select B without checking its dependency to A, if A hasn't been selected elsewhere, it will result in a build failure. This is what happens on the following build error: kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52f64): undefined reference to `tracepoint_probe_register_noupdate' kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52f74): undefined reference to `tracepoint_probe_unregister_noupdate' kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52fb9): undefined reference to `tracepoint_probe_unregister_noupdate' kernel/built-in.o: In function `marker_update_probes': marker.c:(.text+0x530ba): undefined reference to `tracepoint_probe_update_all' CONFIG_KVM_TRACE will select CONFIG_MARKER, but the latter depends on CONFIG_TRACEPOINTS which will not be selected. Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f068071fcc5d..26b5bab6f6e8 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -945,7 +945,7 @@ config TRACEPOINTS config MARKERS bool "Activate markers" - depends on TRACEPOINTS + select TRACEPOINTS help Place an empty function call at each marker site. Can be dynamically changed for a probe function. -- cgit v1.2.3-70-g09d2 From 759ee0915dd713361e72facb78b66600b5712d65 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 25 Mar 2009 17:06:30 +0800 Subject: init,cpuset: fix initialize order Impact: cpuset_wq should be initialized after init_workqueues() When I read /debugfs/tracing/trace_stat/workqueues, I got this: # CPU INSERTED EXECUTED NAME # | | | | 0 0 0 cpuset 0 285 285 events/0 0 2 2 work_on_cpu/0 0 1115 1115 khelper 0 325 325 kblockd/0 0 0 0 kacpid 0 0 0 kacpi_notify 0 0 0 ata/0 0 0 0 ata_aux 0 0 0 ksuspend_usbd 0 0 0 aio/0 0 0 0 nfsiod 0 0 0 kpsmoused 0 0 0 kstriped 0 0 0 kondemand/0 0 1 1 hid_compat 0 0 0 rpciod/0 1 64 64 events/1 1 2 2 work_on_cpu/1 1 5 5 kblockd/1 1 0 0 ata/1 1 0 0 aio/1 1 0 0 kondemand/1 1 0 0 rpciod/1 I found "cpuset" is at the earliest. I found a create_singlethread_workqueue() is earlier than init_workqueues(): kernel_init() ->cpuset_init_smp() ->create_singlethread_workqueue() ->do_basic_setup() ->init_workqueues() I think it's better that create_singlethread_workqueue() is called after workqueue subsystem has been initialized. Signed-off-by: Lai Jiangshan Acked-by: Steven Rostedt Acked-by: Frederic Weisbecker Cc: Paul Menage Cc: miaoxie Cc: Li Zefan Cc: Andrew Morton LKML-Reference: <49C9F416.1050707@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- init/main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 20d784ab5ef8..b0097d2b63ae 100644 --- a/init/main.c +++ b/init/main.c @@ -772,6 +772,7 @@ static void __init do_basic_setup(void) { rcu_init_sched(); /* needed by module_init stage. */ init_workqueues(); + cpuset_init_smp(); usermodehelper_init(); driver_init(); init_irq_proc(); @@ -865,8 +866,6 @@ static int __init kernel_init(void * unused) smp_init(); sched_init_smp(); - cpuset_init_smp(); - do_basic_setup(); /* -- cgit v1.2.3-70-g09d2