diff options
author | Ingo Molnar <mingo@elte.hu> | 2010-06-09 18:55:20 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2010-06-09 18:55:57 +0200 |
commit | c726b61c6a5acc54c55ed7a0e7638cc4c5a100a8 (patch) | |
tree | 3f44aa013d31d34951e9610e79ff14c1148ad6ac | |
parent | 7be7923633a142402266d642ccebf74f556a649b (diff) | |
parent | 018378c55b03f88ff513aba4e0e93b8d4a9cf241 (diff) | |
download | op-kernel-dev-c726b61c6a5acc54c55ed7a0e7638cc4c5a100a8.zip op-kernel-dev-c726b61c6a5acc54c55ed7a0e7638cc4c5a100a8.tar.gz |
Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core
35 files changed, 130 insertions, 1309 deletions
diff --git a/Documentation/ABI/testing/debugfs-kmemtrace b/Documentation/ABI/testing/debugfs-kmemtrace deleted file mode 100644 index 5e6a92a..0000000 --- a/Documentation/ABI/testing/debugfs-kmemtrace +++ /dev/null @@ -1,71 +0,0 @@ -What: /sys/kernel/debug/kmemtrace/ -Date: July 2008 -Contact: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> -Description: - -In kmemtrace-enabled kernels, the following files are created: - -/sys/kernel/debug/kmemtrace/ - cpu<n> (0400) Per-CPU tracing data, see below. (binary) - total_overruns (0400) Total number of bytes which were dropped from - cpu<n> files because of full buffer condition, - non-binary. (text) - abi_version (0400) Kernel's kmemtrace ABI version. (text) - -Each per-CPU file should be read according to the relay interface. That is, -the reader should set affinity to that specific CPU and, as currently done by -the userspace application (though there are other methods), use poll() with -an infinite timeout before every read(). Otherwise, erroneous data may be -read. The binary data has the following _core_ format: - - Event ID (1 byte) Unsigned integer, one of: - 0 - represents an allocation (KMEMTRACE_EVENT_ALLOC) - 1 - represents a freeing of previously allocated memory - (KMEMTRACE_EVENT_FREE) - Type ID (1 byte) Unsigned integer, one of: - 0 - this is a kmalloc() / kfree() - 1 - this is a kmem_cache_alloc() / kmem_cache_free() - 2 - this is a __get_free_pages() et al. - Event size (2 bytes) Unsigned integer representing the - size of this event. Used to extend - kmemtrace. Discard the bytes you - don't know about. - Sequence number (4 bytes) Signed integer used to reorder data - logged on SMP machines. Wraparound - must be taken into account, although - it is unlikely. - Caller address (8 bytes) Return address to the caller. - Pointer to mem (8 bytes) Pointer to target memory area. Can be - NULL, but not all such calls might be - recorded. - -In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow: - - Requested bytes (8 bytes) Total number of requested bytes, - unsigned, must not be zero. - Allocated bytes (8 bytes) Total number of actually allocated - bytes, unsigned, must not be lower - than requested bytes. - Requested flags (4 bytes) GFP flags supplied by the caller. - Target CPU (4 bytes) Signed integer, valid for event id 1. - If equal to -1, target CPU is the same - as origin CPU, but the reverse might - not be true. - -The data is made available in the same endianness the machine has. - -Other event ids and type ids may be defined and added. Other fields may be -added by increasing event size, but see below for details. -Every modification to the ABI, including new id definitions, are followed -by bumping the ABI version by one. - -Adding new data to the packet (features) is done at the end of the mandatory -data: - Feature size (2 byte) - Feature ID (1 byte) - Feature data (Feature size - 3 bytes) - - -Users: - kmemtrace-user - git://repo.or.cz/kmemtrace-user.git - diff --git a/Documentation/trace/kmemtrace.txt b/Documentation/trace/kmemtrace.txt deleted file mode 100644 index 6308735..0000000 --- a/Documentation/trace/kmemtrace.txt +++ /dev/null @@ -1,126 +0,0 @@ - kmemtrace - Kernel Memory Tracer - - by Eduard - Gabriel Munteanu - <eduard.munteanu@linux360.ro> - -I. Introduction -=============== - -kmemtrace helps kernel developers figure out two things: -1) how different allocators (SLAB, SLUB etc.) perform -2) how kernel code allocates memory and how much - -To do this, we trace every allocation and export information to the userspace -through the relay interface. We export things such as the number of requested -bytes, the number of bytes actually allocated (i.e. including internal -fragmentation), whether this is a slab allocation or a plain kmalloc() and so -on. - -The actual analysis is performed by a userspace tool (see section III for -details on where to get it from). It logs the data exported by the kernel, -processes it and (as of writing this) can provide the following information: -- the total amount of memory allocated and fragmentation per call-site -- the amount of memory allocated and fragmentation per allocation -- total memory allocated and fragmentation in the collected dataset -- number of cross-CPU allocation and frees (makes sense in NUMA environments) - -Moreover, it can potentially find inconsistent and erroneous behavior in -kernel code, such as using slab free functions on kmalloc'ed memory or -allocating less memory than requested (but not truly failed allocations). - -kmemtrace also makes provisions for tracing on some arch and analysing the -data on another. - -II. Design and goals -==================== - -kmemtrace was designed to handle rather large amounts of data. Thus, it uses -the relay interface to export whatever is logged to userspace, which then -stores it. Analysis and reporting is done asynchronously, that is, after the -data is collected and stored. By design, it allows one to log and analyse -on different machines and different arches. - -As of writing this, the ABI is not considered stable, though it might not -change much. However, no guarantees are made about compatibility yet. When -deemed stable, the ABI should still allow easy extension while maintaining -backward compatibility. This is described further in Documentation/ABI. - -Summary of design goals: - - allow logging and analysis to be done across different machines - - be fast and anticipate usage in high-load environments (*) - - be reasonably extensible - - make it possible for GNU/Linux distributions to have kmemtrace - included in their repositories - -(*) - one of the reasons Pekka Enberg's original userspace data analysis - tool's code was rewritten from Perl to C (although this is more than a - simple conversion) - - -III. Quick usage guide -====================== - -1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable -CONFIG_KMEMTRACE). - -2) Get the userspace tool and build it: -$ git clone git://repo.or.cz/kmemtrace-user.git # current repository -$ cd kmemtrace-user/ -$ ./autogen.sh -$ ./configure -$ make - -3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the -'single' runlevel (so that relay buffers don't fill up easily), and run -kmemtrace: -# '$' does not mean user, but root here. -$ mount -t debugfs none /sys/kernel/debug -$ mount -t proc none /proc -$ cd path/to/kmemtrace-user/ -$ ./kmemtraced -Wait a bit, then stop it with CTRL+C. -$ cat /sys/kernel/debug/kmemtrace/total_overruns # Check if we didn't - # overrun, should - # be zero. -$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to - check its correctness] -$ ./kmemtrace-report - -Now you should have a nice and short summary of how the allocator performs. - -IV. FAQ and known issues -======================== - -Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix -this? Should I worry? -A: If it's non-zero, this affects kmemtrace's accuracy, depending on how -large the number is. You can fix it by supplying a higher -'kmemtrace.subbufs=N' kernel parameter. ---- - -Q: kmemtrace_check reports errors, how do I fix this? Should I worry? -A: This is a bug and should be reported. It can occur for a variety of -reasons: - - possible bugs in relay code - - possible misuse of relay by kmemtrace - - timestamps being collected unorderly -Or you may fix it yourself and send us a patch. ---- - -Q: kmemtrace_report shows many errors, how do I fix this? Should I worry? -A: This is a known issue and I'm working on it. These might be true errors -in kernel code, which may have inconsistent behavior (e.g. allocating memory -with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed -out this behavior may work with SLAB, but may fail with other allocators. - -It may also be due to lack of tracing in some unusual allocator functions. - -We don't want bug reports regarding this issue yet. ---- - -V. See also -=========== - -Documentation/kernel-parameters.txt -Documentation/ABI/testing/debugfs-kmemtrace - diff --git a/MAINTAINERS b/MAINTAINERS index 13608bd..26da731 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3368,13 +3368,6 @@ F: include/linux/kmemleak.h F: mm/kmemleak.c F: mm/kmemleak-test.c -KMEMTRACE -M: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro> -S: Maintained -F: Documentation/trace/kmemtrace.txt -F: include/linux/kmemtrace.h -F: kernel/trace/kmemtrace.c - KPROBES M: Ananth N Mavinakayanahalli <ananth@in.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index e6d4ce6..5c16b89 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -21,3 +21,15 @@ #ifdef CONFIG_FSL_EMB_PERF_EVENT #include <asm/perf_event_fsl_emb.h> #endif + +#ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> +#include <asm/reg.h> + +#define perf_arch_fetch_caller_regs(regs, __ip) \ + do { \ + (regs)->nip = __ip; \ + (regs)->gpr[1] = *(unsigned long *)__get_SP(); \ + asm volatile("mfmsr %0" : "=r" ((regs)->msr)); \ + } while (0) +#endif diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S index 22e507c..2d29752 100644 --- a/arch/powerpc/kernel/misc.S +++ b/arch/powerpc/kernel/misc.S @@ -127,29 +127,3 @@ _GLOBAL(__setup_cpu_power7) _GLOBAL(__restore_cpu_power7) /* place holder */ blr - -/* - * Get a minimal set of registers for our caller's nth caller. - * r3 = regs pointer, r5 = n. - * - * We only get R1 (stack pointer), NIP (next instruction pointer) - * and LR (link register). These are all we can get in the - * general case without doing complicated stack unwinding, but - * fortunately they are enough to do a stack backtrace, which - * is all we need them for. - */ -_GLOBAL(perf_arch_fetch_caller_regs) - mr r6,r1 - cmpwi r5,0 - mflr r4 - ble 2f - mtctr r5 -1: PPC_LL r6,0(r6) - bdnz 1b - PPC_LL r4,PPC_LR_STKOFF(r6) -2: PPC_LL r7,0(r6) - PPC_LL r7,PPC_LR_STKOFF(r7) - PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3) - PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3) - PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3) - blr diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 7e26698..74c4e0c 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -6,7 +6,15 @@ extern void set_perf_event_pending(void); #define PERF_EVENT_INDEX_OFFSET 0 #ifdef CONFIG_PERF_EVENTS +#include <asm/ptrace.h> + extern void init_hw_perf_events(void); + +extern void +__perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); + +#define perf_arch_fetch_caller_regs(pt_regs, ip) \ + __perf_arch_fetch_caller_regs(pt_regs, ip, 1); #else static inline void init_hw_perf_events(void) { } #endif diff --git a/arch/sparc/kernel/helpers.S b/arch/sparc/kernel/helpers.S index 92090cc..682fee0 100644 --- a/arch/sparc/kernel/helpers.S +++ b/arch/sparc/kernel/helpers.S @@ -47,9 +47,9 @@ stack_trace_flush: .size stack_trace_flush,.-stack_trace_flush #ifdef CONFIG_PERF_EVENTS - .globl perf_arch_fetch_caller_regs - .type perf_arch_fetch_caller_regs,#function -perf_arch_fetch_caller_regs: + .globl __perf_arch_fetch_caller_regs + .type __perf_arch_fetch_caller_regs,#function +__perf_arch_fetch_caller_regs: /* We always read the %pstate into %o5 since we will use * that to construct a fake %tstate to store into the regs. */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6ed3ae4..6e742cc 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -141,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#include <asm/stacktrace.h> + +/* + * We abuse bit 3 from flags to pass exact information, see perf_misc_flags + * and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->bp = caller_frame_pointer(); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 4dab78e..2b16a2a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,6 +1,13 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H +#include <linux/uaccess.h> + extern int kstack_depth_to_print; struct thread_info; @@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) +#else +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) +#endif + +extern void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl); + +extern void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl); + +extern unsigned int code_bytes; + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +static inline unsigned long caller_frame_pointer(void) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + frame = frame->next_frame; +#endif + + return (unsigned long)frame; +} + #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2d0d290..f2da20f 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1613,8 +1613,6 @@ static const struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack_bp, }; -#include "../dumpstack.h" - static void perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) { @@ -1736,22 +1734,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return entry; } -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) -{ - regs->ip = ip; - /* - * perf_arch_fetch_caller_regs adds another call, we need to increment - * the skip level - */ - regs->bp = rewind_frame_pointer(skip + 1); - regs->cs = __KERNEL_CS; - /* - * We abuse bit 3 to pass exact information, see perf_misc_flags - * and the comment with PERF_EFLAGS_EXACT. - */ - regs->flags = 0; -} - unsigned long perf_instruction_pointer(struct pt_regs *regs) { unsigned long ip; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c89a386..6e8752c 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,7 +18,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" int panic_on_unrecovered_nmi; int panic_on_io_nmi; diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h deleted file mode 100644 index e1a93be..0000000 --- a/arch/x86/kernel/dumpstack.h +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - */ - -#ifndef DUMPSTACK_H -#define DUMPSTACK_H - -#ifdef CONFIG_X86_32 -#define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) -#else -#define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) -#endif - -#include <linux/uaccess.h> - -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); - -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); - -extern unsigned int code_bytes; - -/* The form of the top of the frame on the stack */ -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; -}; - -struct stack_frame_ia32 { - u32 next_frame; - u32 return_address; -}; - -static inline unsigned long rewind_frame_pointer(int n) -{ - struct stack_frame *frame; - - get_bp(frame); - -#ifdef CONFIG_FRAME_POINTER - while (n--) { - if (probe_kernel_address(&frame->next_frame, frame)) - break; - } -#endif - - return (unsigned long)frame; -} - -#endif /* DUMPSTACK_H */ diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 11540a1..0f6376f 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,8 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" - void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, unsigned long bp, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 272c9f1..57a21f1 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,7 +16,6 @@ #include <asm/stacktrace.h> -#include "dumpstack.h" #define N_EXCEPTION_STACKS_END \ (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 922eefb..b53c525 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -23,11 +23,16 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static void +__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; +#ifdef CONFIG_FRAME_POINTER if (!reliable) return; +#endif + if (nosched && in_sched_functions(addr)) + return; if (trace->skip > 0) { trace->skip--; return; @@ -36,20 +41,15 @@ static void save_stack_address(void *data, unsigned long addr, int reliable) trace->entries[trace->nr_entries++] = addr; } +static void save_stack_address(void *data, unsigned long addr, int reliable) +{ + return __save_stack_address(data, addr, reliable, false); +} + static void save_stack_address_nosched(void *data, unsigned long addr, int reliable) { - struct stack_trace *trace = (struct stack_trace *)data; - if (!reliable) - return; - if (in_sched_functions(addr)) - return; - if (trace->skip > 0) { - trace->skip--; - return; - } - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = addr; + return __save_stack_address(data, addr, reliable, true); } static const struct stacktrace_ops save_stack_ops = { @@ -96,12 +96,13 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk); /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */ -struct stack_frame { +struct stack_frame_user { const void __user *next_fp; unsigned long ret_addr; }; -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +static int +copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; @@ -126,7 +127,7 @@ static inline void __save_stack_trace_user(struct stack_trace *trace) trace->entries[trace->nr_entries++] = regs->ip; while (trace->nr_entries < trace->max_entries) { - struct stack_frame frame; + struct stack_frame_user frame; frame.next_fp = NULL; frame.ret_addr = 0; diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h deleted file mode 100644 index b616d39..0000000 --- a/include/linux/kmemtrace.h +++ /dev/null @@ -1,25 +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 <trace/events/kmem.h> - -#ifdef CONFIG_KMEMTRACE -extern void kmemtrace_init(void); -#else -static inline void kmemtrace_init(void) -{ -} -#endif - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_KMEMTRACE_H */ - diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1218d05..63b5aa5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -932,8 +932,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64); -extern void -perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); +#ifndef perf_arch_fetch_caller_regs +static inline void +perf_arch_fetch_caller_regs(struct regs *regs, unsigned long ip) { } +#endif /* * Take a snapshot of the regs. Skip ip and frame pointer to @@ -943,31 +945,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip); * - bp for callchains * - eflags, for future purposes, just in case */ -static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip) +static inline void perf_fetch_caller_regs(struct pt_regs *regs) { - unsigned long ip; - memset(regs, 0, sizeof(*regs)); - switch (skip) { - case 1 : - ip = CALLER_ADDR0; - break; - case 2 : - ip = CALLER_ADDR1; - break; - case 3 : - ip = CALLER_ADDR2; - break; - case 4: - ip = CALLER_ADDR3; - break; - /* No need to support further for now */ - default: - ip = 0; - } - - return perf_arch_fetch_caller_regs(regs, ip, skip); + perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static inline void @@ -977,7 +959,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr) struct pt_regs hot_regs; if (!regs) { - perf_fetch_caller_regs(&hot_regs, 1); + perf_fetch_caller_regs(&hot_regs); regs = &hot_regs; } __perf_sw_event(event_id, nr, nmi, regs, addr); diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 1812dac..1acfa73 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -14,7 +14,8 @@ #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/events/kmem.h> #ifndef ARCH_KMALLOC_MINALIGN /* diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 4ba59cf..6447a72 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,9 +10,10 @@ #include <linux/gfp.h> #include <linux/workqueue.h> #include <linux/kobject.h> -#include <linux/kmemtrace.h> #include <linux/kmemleak.h> +#include <trace/events/kmem.h> + enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */ diff --git a/include/trace/boot.h b/include/trace/boot.h deleted file mode 100644 index 088ea08..0000000 --- a/include/trace/boot.h +++ /dev/null @@ -1,60 +0,0 @@ -#ifndef _LINUX_TRACE_BOOT_H -#define _LINUX_TRACE_BOOT_H - -#include <linux/module.h> -#include <linux/kallsyms.h> -#include <linux/init.h> - -/* - * Structure which defines the trace of an initcall - * while it is called. - * You don't have to fill the func field since it is - * only used internally by the tracer. - */ -struct boot_trace_call { - pid_t caller; - char func[KSYM_SYMBOL_LEN]; -}; - -/* - * Structure which defines the trace of an initcall - * while it returns. - */ -struct boot_trace_ret { - char func[KSYM_SYMBOL_LEN]; - int result; - unsigned long long duration; /* nsecs */ -}; - -#ifdef CONFIG_BOOT_TRACER -/* Append the traces on the ring-buffer */ -extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn); -extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn); - -/* Tells the tracer that smp_pre_initcall is finished. - * So we can start the tracing - */ -extern void start_boot_trace(void); - -/* Resume the tracing of other necessary events - * such as sched switches - */ -extern void enable_boot_trace(void); - -/* Suspend this tracing. Actually, only sched_switches tracing have - * to be suspended. Initcalls doesn't need it.) - */ -extern void disable_boot_trace(void); -#else -static inline -void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { } - -static inline -void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { } - -static inline void start_boot_trace(void) { } -static inline void enable_boot_trace(void) { } -static inline void disable_boot_trace(void) { } -#endif /* CONFIG_BOOT_TRACER */ - -#endif /* __LINUX_TRACE_BOOT_H */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 5a64905..fc013a8 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -705,7 +705,7 @@ perf_trace_##call(void *__data, proto) \ int __data_size; \ int rctx; \ \ - perf_fetch_caller_regs(&__regs, 1); \ + perf_fetch_caller_regs(&__regs); \ \ __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\ diff --git a/init/main.c b/init/main.c index 3bdb152..e2a2bf3 100644 --- a/init/main.c +++ b/init/main.c @@ -66,11 +66,9 @@ #include <linux/ftrace.h> #include <linux/async.h> #include <linux/kmemcheck.h> -#include <linux/kmemtrace.h> #include <linux/sfi.h> #include <linux/shmem_fs.h> #include <linux/slab.h> -#include <trace/boot.h> #include <asm/io.h> #include <asm/bugs.h> @@ -653,7 +651,6 @@ asmlinkage void __init start_kernel(void) #endif page_cgroup_init(); enable_debug_pagealloc(); - kmemtrace_init(); kmemleak_init(); debug_objects_mem_init(); idr_init_cache(); @@ -715,38 +712,33 @@ int initcall_debug; core_param(initcall_debug, initcall_debug, bool, 0644); static char msgbuf[64]; -static struct boot_trace_call call; -static struct boot_trace_ret ret; int do_one_initcall(initcall_t fn) { int count = preempt_count(); ktime_t calltime, delta, rettime; + unsigned long long duration; + int ret; if (initcall_debug) { - call.caller = task_pid_nr(current); - printk("calling %pF @ %i\n", fn, call.caller); + printk("calling %pF @ %i\n", fn, task_pid_nr(current)); calltime = ktime_get(); - trace_boot_call(&call, fn); - enable_boot_trace(); } - ret.result = fn(); + ret = fn(); if (initcall_debug) { - disable_boot_trace(); rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10; - trace_boot_ret(&ret, fn); - printk("initcall %pF returned %d after %Ld usecs\n", fn, - ret.result, ret.duration); + duration = (unsigned long long) ktime_to_ns(delta) >> 10; + printk("initcall %pF returned %d after %lld usecs\n", fn, + ret, duration); } msgbuf[0] = 0; - if (ret.result && ret.result != -ENODEV && initcall_debug) - sprintf(msgbuf, "error code %d ", ret.result); + if (ret && ret != -ENODEV && initcall_debug) + sprintf(msgbuf, "error code %d ", ret); if (preempt_count() != count) { strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf)); @@ -760,7 +752,7 @@ int do_one_initcall(initcall_t fn) printk("initcall %pF returned with %s\n", fn, msgbuf); } - return ret.result; + return ret; } @@ -880,7 +872,6 @@ static int __init kernel_init(void * unused) smp_prepare_cpus(setup_max_cpus); do_pre_smp_initcalls(); - start_boot_trace(); smp_init(); sched_init_smp(); diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 97c7301..c772a3d4 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2946,11 +2946,6 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) return NULL; } -__weak -void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip) -{ -} - /* * We assume there is only KVM supporting the callbacks. diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8b1797c..f669092 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -229,23 +229,6 @@ config FTRACE_SYSCALLS help Basic tracer to catch the syscall entry and exit events. -config BOOT_TRACER - bool "Trace boot initcalls" - select GENERIC_TRACER - select CONTEXT_SWITCH_TRACER - help - This tracer helps developers to optimize boot times: it records - the timings of the initcalls and traces key events and the identity - of tasks that can cause boot delays, such as context-switches. - - Its aim is to be parsed by the scripts/bootgraph.pl tool to - produce pretty graphics about boot inefficiencies, giving a visual - representation of the delays during initcalls - but the raw - /debug/tracing/trace text output is readable too. - - You must pass in initcall_debug and ftrace=initcall to the kernel - command line to enable this on bootup. - config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER @@ -371,26 +354,6 @@ config STACK_TRACER Say N if unsure. -config KMEMTRACE - bool "Trace SLAB allocations" - select GENERIC_TRACER - 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/trace/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 WORKQUEUE_TRACER bool "Trace workqueues" select GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index ffb1a5b..469a1c7 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -38,10 +38,8 @@ obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o -obj-$(CONFIG_BOOT_TRACER) += trace_boot.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o -obj-$(CONFIG_KMEMTRACE) += kmemtrace.o obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o ifeq ($(CONFIG_BLOCK),y) diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c deleted file mode 100644 index bbfc1bb..0000000 --- a/kernel/trace/kmemtrace.c +++ /dev/null @@ -1,529 +0,0 @@ -/* - * 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/tracepoint.h> -#include <linux/seq_file.h> -#include <linux/debugfs.h> -#include <linux/dcache.h> -#include <linux/fs.h> - -#include <linux/kmemtrace.h> - -#include "trace_output.h" -#include "trace.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 struct trace_array *kmemtrace_array; - -/* Trace allocations */ -static inline void kmemtrace_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, - int node) -{ - struct ftrace_event_call *call = &event_kmem_alloc; - struct trace_array *tr = kmemtrace_array; - struct kmemtrace_alloc_entry *entry; - struct ring_buffer_event *event; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry)); - if (!event) - return; - - entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, 0, 0); - - entry->ent.type = TRACE_KMEM_ALLOC; - entry->type_id = type_id; - 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; - - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); - - trace_wake_up(); -} - -static inline void kmemtrace_free(enum kmemtrace_type_id type_id, - unsigned long call_site, - const void *ptr) -{ - struct ftrace_event_call *call = &event_kmem_free; - struct trace_array *tr = kmemtrace_array; - struct kmemtrace_free_entry *entry; - struct ring_buffer_event *event; - - event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry)); - 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; - - if (!filter_check_discard(call, entry, tr->buffer, event)) - ring_buffer_unlock_commit(tr->buffer, event); - - trace_wake_up(); -} - -static void kmemtrace_kmalloc(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, -1); -} - -static void kmemtrace_kmem_cache_alloc(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, -1); -} - -static void kmemtrace_kmalloc_node(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_KMALLOC, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, node); -} - -static void kmemtrace_kmem_cache_alloc_node(void *ignore, - unsigned long call_site, - const void *ptr, - size_t bytes_req, - size_t bytes_alloc, - gfp_t gfp_flags, - int node) -{ - kmemtrace_alloc(KMEMTRACE_TYPE_CACHE, call_site, ptr, - bytes_req, bytes_alloc, gfp_flags, node); -} - -static void -kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr) -{ - kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr); -} - -static void kmemtrace_kmem_cache_free(void *ignore, - unsigned long call_site, const void *ptr) -{ - kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr); -} - -static int kmemtrace_start_probes(void) -{ - int err; - - err = register_trace_kmalloc(kmemtrace_kmalloc, NULL); - if (err) - return err; - err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); - if (err) - return err; - err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); - if (err) - return err; - err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); - if (err) - return err; - err = register_trace_kfree(kmemtrace_kfree, NULL); - if (err) - return err; - err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); - - return err; -} - -static void kmemtrace_stop_probes(void) -{ - unregister_trace_kmalloc(kmemtrace_kmalloc, NULL); - unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL); - unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL); - unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL); - unregister_trace_kfree(kmemtrace_kfree, NULL); - unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL); -} - -static int kmem_trace_init(struct trace_array *tr) -{ - kmemtrace_array = tr; - - tracing_reset_online_cpus(tr); - - kmemtrace_start_probes(); - - return 0; -} - -static void kmem_trace_reset(struct trace_array *tr) -{ - kmemtrace_stop_probes(); -} - -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 following functions give the original output from kmemtrace, - * plus the origin CPU, since reordering occurs in-kernel now. - */ - -#define KMEMTRACE_USER_ALLOC 0 -#define KMEMTRACE_USER_FREE 1 - -struct kmemtrace_user_event { - u8 event_id; - u8 type_id; - u16 event_size; - u32 cpu; - u64 timestamp; - unsigned long call_site; - unsigned long ptr; -}; - -struct kmemtrace_user_event_alloc { - size_t bytes_req; - size_t bytes_alloc; - unsigned gfp_flags; - int node; -}; - -static enum print_line_t -kmemtrace_print_alloc(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_alloc_entry *entry; - int ret; - - trace_assign_type(entry, iter->ent); - - ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu " - "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n", - entry->type_id, (void *)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(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_free_entry *entry; - int ret; - - trace_assign_type(entry, iter->ent); - - ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n", - entry->type_id, (void *)entry->call_site, - (unsigned long)entry->ptr); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_alloc_entry *entry; - struct kmemtrace_user_event *ev; - struct kmemtrace_user_event_alloc *ev_alloc; - - trace_assign_type(entry, iter->ent); - - ev = trace_seq_reserve(s, sizeof(*ev)); - if (!ev) - return TRACE_TYPE_PARTIAL_LINE; - - ev->event_id = KMEMTRACE_USER_ALLOC; - ev->type_id = entry->type_id; - ev->event_size = sizeof(*ev) + sizeof(*ev_alloc); - ev->cpu = iter->cpu; - ev->timestamp = iter->ts; - ev->call_site = entry->call_site; - ev->ptr = (unsigned long)entry->ptr; - - ev_alloc = trace_seq_reserve(s, sizeof(*ev_alloc)); - if (!ev_alloc) - return TRACE_TYPE_PARTIAL_LINE; - - ev_alloc->bytes_req = entry->bytes_req; - ev_alloc->bytes_alloc = entry->bytes_alloc; - ev_alloc->gfp_flags = entry->gfp_flags; - ev_alloc->node = entry->node; - - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -kmemtrace_print_free_user(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - struct trace_seq *s = &iter->seq; - struct kmemtrace_free_entry *entry; - struct kmemtrace_user_event *ev; - - trace_assign_type(entry, iter->ent); - - ev = trace_seq_reserve(s, sizeof(*ev)); - if (!ev) - return TRACE_TYPE_PARTIAL_LINE; - - ev->event_id = KMEMTRACE_USER_FREE; - ev->type_id = entry->type_id; - ev->event_size = sizeof(*ev); - ev->cpu = iter->cpu; - ev->timestamp = iter->ts; - ev->call_site = entry->call_site; - ev->ptr = (unsigned long)entry->ptr; - - 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; - - trace_assign_type(entry, iter->ent); - - /* 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, "%4zu ", entry->bytes_req); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - /* Allocated */ - ret = trace_seq_printf(s, "%4zu ", 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 and call site*/ - ret = trace_seq_printf(s, "%4d %pf\n", entry->node, - (void *)entry->call_site); - if (!ret) - 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; - - trace_assign_type(entry, iter->ent); - - /* 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 and print call site*/ - ret = trace_seq_printf(s, " %pf\n", (void *)entry->call_site); - if (!ret) - 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; - - if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)) - return TRACE_TYPE_UNHANDLED; - - switch (entry->type) { - case TRACE_KMEM_ALLOC: - return kmemtrace_print_alloc_compress(iter); - case TRACE_KMEM_FREE: - return kmemtrace_print_free_compress(iter); - default: - return TRACE_TYPE_UNHANDLED; - } -} - -static struct trace_event_functions kmem_trace_alloc_funcs = { - .trace = kmemtrace_print_alloc, - .binary = kmemtrace_print_alloc_user, -}; - -static struct trace_event kmem_trace_alloc = { - .type = TRACE_KMEM_ALLOC, - .funcs = &kmem_trace_alloc_funcs, -}; - -static struct trace_event_functions kmem_trace_free_funcs = { - .trace = kmemtrace_print_free, - .binary = kmemtrace_print_free_user, -}; - -static struct trace_event kmem_trace_free = { - .type = TRACE_KMEM_FREE, - .funcs = &kmem_trace_free_funcs, -}; - -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 -}; - -void kmemtrace_init(void) -{ - /* earliest opportunity to start kmem tracing */ -} - -static int __init init_kmem_tracer(void) -{ - if (!register_ftrace_event(&kmem_trace_alloc)) { - pr_warning("Warning: could not register kmem events\n"); - return 1; - } - - if (!register_ftrace_event(&kmem_trace_free)) { - pr_warning("Warning: could not register kmem events\n"); - return 1; - } - - if (register_tracer(&kmem_tracer) != 0) { - pr_warning("Warning: could not register the kmem tracer\n"); - return 1; - } - - return 0; -} -device_initcall(init_kmem_tracer); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 644ab744..8683dec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4596,9 +4596,6 @@ __init static int tracer_alloc_buffers(void) register_tracer(&nop_trace); current_trace = &nop_trace; -#ifdef CONFIG_BOOT_TRACER - register_tracer(&boot_tracer); -#endif /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 6c45e55..01ce088 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,10 +9,7 @@ #include <linux/mmiotrace.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> -#include <trace/boot.h> -#include <linux/kmemtrace.h> #include <linux/hw_breakpoint.h> - #include <linux/trace_seq.h> #include <linux/ftrace_event.h> @@ -29,26 +26,15 @@ enum trace_type { TRACE_MMIO_RW, TRACE_MMIO_MAP, TRACE_BRANCH, - TRACE_BOOT_CALL, - TRACE_BOOT_RET, TRACE_GRAPH_RET, TRACE_GRAPH_ENT, TRACE_USER_STACK, - TRACE_KMEM_ALLOC, - TRACE_KMEM_FREE, TRACE_BLK, TRACE_KSYM, __TRACE_LAST_TYPE, }; -enum kmemtrace_type_id { - KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ - KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ - KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ -}; - -extern struct tracer boot_tracer; #undef __field #define __field(type, item) type item; @@ -209,17 +195,11 @@ extern void __ftrace_bad_type(void); TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ TRACE_MMIO_MAP); \ - IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\ - IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\ IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \ IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \ TRACE_GRAPH_ENT); \ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ TRACE_GRAPH_RET); \ - IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry, \ - TRACE_KMEM_ALLOC); \ - IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \ - TRACE_KMEM_FREE); \ IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\ __ftrace_bad_type(); \ } while (0) diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c deleted file mode 100644 index c21d5f3..0000000 --- a/kernel/trace/trace_boot.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * ring buffer based initcalls tracer - * - * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> - * - */ - -#include <linux/init.h> -#include <linux/debugfs.h> -#include <linux/ftrace.h> -#include <linux/kallsyms.h> -#include <linux/time.h> - -#include "trace.h" -#include "trace_output.h" - -static struct trace_array *boot_trace; -static bool pre_initcalls_finished; - -/* Tells the boot tracer that the pre_smp_initcalls are finished. - * So we are ready . - * It doesn't enable sched events tracing however. - * You have to call enable_boot_trace to do so. - */ -void start_boot_trace(void) -{ - pre_initcalls_finished = true; -} - -void enable_boot_trace(void) -{ - if (boot_trace && pre_initcalls_finished) - tracing_start_sched_switch_record(); -} - -void disable_boot_trace(void) -{ - if (boot_trace && pre_initcalls_finished) - tracing_stop_sched_switch_record(); -} - -static int boot_trace_init(struct trace_array *tr) -{ - boot_trace = tr; - - if (!tr) - return 0; - - tracing_reset_online_cpus(tr); - - tracing_sched_switch_assign_trace(tr); - return 0; -} - -static enum print_line_t -initcall_call_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - struct trace_seq *s = &iter->seq; - struct trace_boot_call *field; - struct boot_trace_call *call; - u64 ts; - unsigned long nsec_rem; - int ret; - - trace_assign_type(field, entry); - call = &field->boot_call; - ts = iter->ts; - nsec_rem = do_div(ts, NSEC_PER_SEC); - - ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n", - (unsigned long)ts, nsec_rem, call->func, call->caller); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - else - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t -initcall_ret_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - struct trace_seq *s = &iter->seq; - struct trace_boot_ret *field; - struct boot_trace_ret *init_ret; - u64 ts; - unsigned long nsec_rem; - int ret; - - trace_assign_type(field, entry); - init_ret = &field->boot_ret; - ts = iter->ts; - nsec_rem = do_div(ts, NSEC_PER_SEC); - - ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s " - "returned %d after %llu msecs\n", - (unsigned long) ts, - nsec_rem, - init_ret->func, init_ret->result, init_ret->duration); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - else - return TRACE_TYPE_HANDLED; -} - -static enum print_line_t initcall_print_line(struct trace_iterator *iter) -{ - struct trace_entry *entry = iter->ent; - - switch (entry->type) { - case TRACE_BOOT_CALL: - return initcall_call_print_line(iter); - case TRACE_BOOT_RET: - return initcall_ret_print_line(iter); - default: - return TRACE_TYPE_UNHANDLED; - } -} - -struct tracer boot_tracer __read_mostly = -{ - .name = "initcall", - .init = boot_trace_init, - .reset = tracing_reset_online_cpus, - .print_line = initcall_print_line, -}; - -void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) -{ - struct ftrace_event_call *call = &event_boot_call; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_boot_call *entry; - struct trace_array *tr = boot_trace; - - if (!tr || !pre_initcalls_finished) - return; - - /* Get its name now since this function could - * disappear because it is in the .init section. - */ - sprint_symbol(bt->func, (unsigned long)fn); - preempt_disable(); - - buffer = tr->buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->boot_call = *bt; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} - -void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) -{ - struct ftrace_event_call *call = &event_boot_ret; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - struct trace_boot_ret *entry; - struct trace_array *tr = boot_trace; - - if (!tr || !pre_initcalls_finished) - return; - - sprint_symbol(bt->func, (unsigned long)fn); - preempt_disable(); - - buffer = tr->buffer; - event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET, - sizeof(*entry), 0, 0); - if (!event) - goto out; - entry = ring_buffer_event_data(event); - entry->boot_ret = *bt; - if (!filter_check_discard(call, entry, buffer, event)) - trace_buffer_unlock_commit(buffer, event, 0, 0); - out: - preempt_enable(); -} diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index dc008c1..13abc15 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -271,33 +271,6 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __entry->map_id, __entry->opcode) ); -FTRACE_ENTRY(boot_call, trace_boot_call, - - TRACE_BOOT_CALL, - - F_STRUCT( - __field_struct( struct boot_trace_call, boot_call ) - __field_desc( pid_t, boot_call, caller ) - __array_desc( char, boot_call, func, KSYM_SYMBOL_LEN) - ), - - F_printk("%d %s", __entry->caller, __entry->func) -); - -FTRACE_ENTRY(boot_ret, trace_boot_ret, - - TRACE_BOOT_RET, - - F_STRUCT( - __field_struct( struct boot_trace_ret, boot_ret ) - __array_desc( char, boot_ret, func, KSYM_SYMBOL_LEN) - __field_desc( int, boot_ret, result ) - __field_desc( unsigned long, boot_ret, duration ) - ), - - F_printk("%s %d %lx", - __entry->func, __entry->result, __entry->duration) -); #define TRACE_FUNC_SIZE 30 #define TRACE_FILE_SIZE 20 @@ -318,41 +291,6 @@ FTRACE_ENTRY(branch, trace_branch, __entry->func, __entry->file, __entry->correct) ); -FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry, - - TRACE_KMEM_ALLOC, - - F_STRUCT( - __field( enum kmemtrace_type_id, type_id ) - __field( unsigned long, call_site ) - __field( const void *, ptr ) - __field( size_t, bytes_req ) - __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) - __field( int, node ) - ), - - F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi" - " flags:%x node:%d", - __entry->type_id, __entry->call_site, __entry->ptr, - __entry->bytes_req, __entry->bytes_alloc, - __entry->gfp_flags, __entry->node) -); - -FTRACE_ENTRY(kmem_free, kmemtrace_free_entry, - - TRACE_KMEM_FREE, - - F_STRUCT( - __field( enum kmemtrace_type_id, type_id ) - __field( unsigned long, call_site ) - __field( const void *, ptr ) - ), - - F_printk("type:%u call_site:%lx ptr:%p", - __entry->type_id, __entry->call_site, __entry->ptr) -); - FTRACE_ENTRY(ksym_trace, ksym_trace_entry, TRACE_KSYM, diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index e6f6588..4799d70 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -9,8 +9,6 @@ #include <linux/kprobes.h> #include "trace.h" -EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs); - static char *perf_trace_buf[4]; /* diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index a7974a5..c080956 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -33,12 +33,13 @@ static DEFINE_MUTEX(sample_timer_lock); */ static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer); -struct stack_frame { +struct stack_frame_user { const void __user *next_fp; unsigned long return_address; }; -static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +static int +copy_stack_frame(const void __user *fp, struct stack_frame_user *frame) { int ret; @@ -125,7 +126,7 @@ trace_kernel(struct pt_regs *regs, struct trace_array *tr, static void timer_notify(struct pt_regs *regs, int cpu) { struct trace_array_cpu *data; - struct stack_frame frame; + struct stack_frame_user frame; struct trace_array *tr; const void __user *fp; int is_user; @@ -102,7 +102,6 @@ #include <linux/cpu.h> #include <linux/sysctl.h> #include <linux/module.h> -#include <linux/kmemtrace.h> #include <linux/rcupdate.h> #include <linux/string.h> #include <linux/uaccess.h> @@ -66,8 +66,10 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/list.h> -#include <linux/kmemtrace.h> #include <linux/kmemleak.h> + +#include <trace/events/kmem.h> + #include <asm/atomic.h> /* @@ -17,7 +17,6 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> -#include <linux/kmemtrace.h> #include <linux/kmemcheck.h> #include <linux/cpu.h> #include <linux/cpuset.h> |