Messages in this thread Patch in this message | | | Date | Tue, 13 Jan 2009 11:54:07 -0500 (EST) | From | Steven Rostedt <> | Subject | Re: [PATCH 0/9] ftrace: updates for tip |
| |
On Tue, 13 Jan 2009, Steven Rostedt wrote:
> > > On Tue, 13 Jan 2009, Steven Rostedt wrote: > > > > > The following patches are in: > > > > git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git > > > > branch: tip/devel > > Ingo, > > Don't pull any of this yet please. I'm going to rebase some of the patches > to fix the change logs (typos). I'll let you know when that's finished. >
OK, I rebased in changing the change logs. Here's what I did:
s/destinct/distinct/ s/K?nig/Koenig/
Here's the changes:
The following patches are in:
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
branch: tip/devel
Frederic Weisbecker (2): tracing/ftrace: separate events tracing and stats tracing engine tracing: add a new workqueue tracer
Shaohua Li (6): ftrace, ia64: make recordmcount distinct module compile ftrace, ia64: explictly ignore a file in recordmcount.pl ftrace, ia64: Add macro for ftrace_caller ftrace, ia64: Add recordmcount for ia64 ftrace, ia64: IA64 static ftrace support ftrace, ia64: IA64 dynamic ftrace support
Uwe Kleine-Koenig (1): ftrace, trivial: fix typo "resgister" -> "register"
---- arch/ia64/Kconfig | 3 + arch/ia64/include/asm/ftrace.h | 28 ++++ arch/ia64/kernel/Makefile | 5 + arch/ia64/kernel/entry.S | 100 ++++++++++++++ arch/ia64/kernel/ftrace.c | 206 ++++++++++++++++++++++++++++ arch/ia64/kernel/ia64_ksyms.c | 6 + include/linux/ftrace.h | 4 + include/trace/workqueue.h | 25 ++++ kernel/trace/Kconfig | 11 ++ kernel/trace/Makefile | 1 + kernel/trace/ftrace.c | 14 +-- kernel/trace/trace.c | 2 - kernel/trace/trace.h | 20 --- kernel/trace/trace_branch.c | 108 +++++++++------- kernel/trace/trace_stat.c | 191 +++++++++++--------------- kernel/trace/trace_stat.h | 31 +++++ kernel/trace/trace_workqueue.c | 287 ++++++++++++++++++++++++++++++++++++++++ kernel/workqueue.c | 16 ++- scripts/Makefile.build | 13 +- scripts/recordmcount.pl | 18 ++- 20 files changed, 888 insertions(+), 201 deletions(-) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 3d31636..e20c1d4 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -21,6 +21,9 @@ config IA64 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE if (!ITANIUM) + select HAVE_FUNCTION_TRACER select HAVE_DMA_ATTRS select HAVE_KVM select HAVE_ARCH_TRACEHOOK diff --git a/arch/ia64/include/asm/ftrace.h b/arch/ia64/include/asm/ftrace.h new file mode 100644 index 0000000..d20db3c --- /dev/null +++ b/arch/ia64/include/asm/ftrace.h @@ -0,0 +1,28 @@ +#ifndef _ASM_IA64_FTRACE_H +#define _ASM_IA64_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER +#define MCOUNT_INSN_SIZE 32 /* sizeof mcount call */ + +#ifndef __ASSEMBLY__ +extern void _mcount(unsigned long pfs, unsigned long r1, unsigned long b0, unsigned long r0); +#define mcount _mcount + +#include <asm/kprobes.h> +/* In IA64, MCOUNT_ADDR is set in link time, so it's not a constant at compile time */ +#define MCOUNT_ADDR (((struct fnptr *)mcount)->ip) +#define FTRACE_ADDR (((struct fnptr *)ftrace_caller)->ip) + +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* second bundle, insn 2 */ + return addr - 0x12; +} + +struct dyn_arch_ftrace { +}; +#endif + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* _ASM_IA64_FTRACE_H */ diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index f2778f2..dc62df0 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -2,6 +2,10 @@ # Makefile for the linux kernel. # +ifdef CONFIG_DYNAMIC_FTRACE +CFLAGS_REMOVE_ftrace.o = -pg +endif + extra-y := head.o init_task.o vmlinux.lds obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \ @@ -28,6 +32,7 @@ obj-$(CONFIG_IA64_CYCLONE) += cyclone.o obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index d435f4a..e0be92a 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -47,6 +47,7 @@ #include <asm/processor.h> #include <asm/thread_info.h> #include <asm/unistd.h> +#include <asm/ftrace.h> #include "minstate.h" @@ -1404,6 +1405,105 @@ GLOBAL_ENTRY(unw_init_running) br.ret.sptk.many rp END(unw_init_running) +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE +GLOBAL_ENTRY(_mcount) + br ftrace_stub +END(_mcount) + +.here: + br.ret.sptk.many b0 + +GLOBAL_ENTRY(ftrace_caller) + alloc out0 = ar.pfs, 8, 0, 4, 0 + mov out3 = r0 + ;; + mov out2 = b0 + add r3 = 0x20, r3 + mov out1 = r1; + br.call.sptk.many b0 = ftrace_patch_gp + //this might be called from module, so we must patch gp +ftrace_patch_gp: + movl gp=__gp + mov b0 = r3 + ;; +.global ftrace_call; +ftrace_call: +{ + .mlx + nop.m 0x0 + movl r3 = .here;; +} + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(ftrace_caller) + +#else +GLOBAL_ENTRY(_mcount) + movl r2 = ftrace_stub + movl r3 = ftrace_trace_function;; + ld8 r3 = [r3];; + ld8 r3 = [r3];; + cmp.eq p7,p0 = r2, r3 +(p7) br.sptk.many ftrace_stub + ;; + + alloc loc0 = ar.pfs, 4, 4, 2, 0 + ;; + mov loc1 = b0 + mov out0 = b0 + mov loc2 = r8 + mov loc3 = r15 + ;; + adds out0 = -MCOUNT_INSN_SIZE, out0 + mov out1 = in2 + mov b6 = r3 + + br.call.sptk.many b0 = b6 + ;; + mov ar.pfs = loc0 + mov b0 = loc1 + mov r8 = loc2 + mov r15 = loc3 + br ftrace_stub + ;; +END(_mcount) +#endif + +GLOBAL_ENTRY(ftrace_stub) + mov r3 = b0 + movl r2 = _mcount_ret_helper + ;; + mov b6 = r2 + mov b7 = r3 + br.ret.sptk.many b6 + +_mcount_ret_helper: + mov b0 = r42 + mov r1 = r41 + mov ar.pfs = r40 + br b7 +END(ftrace_stub) + +#endif /* CONFIG_FUNCTION_TRACER */ + .rodata .align 8 .globl sys_call_table diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c new file mode 100644 index 0000000..7fc8c96 --- /dev/null +++ b/arch/ia64/kernel/ftrace.c @@ -0,0 +1,206 @@ +/* + * Dynamic function tracing support. + * + * Copyright (C) 2008 Shaohua Li <shaohua.li@intel.com> + * + * For licencing details, see COPYING. + * + * Defines low-level handling of mcount calls when the kernel + * is compiled with the -pg flag. When using dynamic ftrace, the + * mcount call-sites get patched lazily with NOP till they are + * enabled. All code mutation routines here take effect atomically. + */ + +#include <linux/uaccess.h> +#include <linux/ftrace.h> + +#include <asm/cacheflush.h> +#include <asm/patch.h> + +/* In IA64, each function will be added below two bundles with -pg option */ +static unsigned char __attribute__((aligned(8))) +ftrace_orig_code[MCOUNT_INSN_SIZE] = { + 0x02, 0x40, 0x31, 0x10, 0x80, 0x05, /* alloc r40=ar.pfs,12,8,0 */ + 0xb0, 0x02, 0x00, 0x00, 0x42, 0x40, /* mov r43=r0;; */ + 0x05, 0x00, 0xc4, 0x00, /* mov r42=b0 */ + 0x11, 0x48, 0x01, 0x02, 0x00, 0x21, /* mov r41=r1 */ + 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, /* nop.i 0x0 */ + 0x08, 0x00, 0x00, 0x50 /* br.call.sptk.many b0 = _mcount;; */ +}; + +struct ftrace_orig_insn { + u64 dummy1, dummy2, dummy3; + u64 dummy4:64-41+13; + u64 imm20:20; + u64 dummy5:3; + u64 sign:1; + u64 dummy6:4; +}; + +/* mcount stub will be converted below for nop */ +static unsigned char ftrace_nop_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* nop.x 0x0;; */ + 0x00, 0x00, 0x04, 0x00 +}; + +static unsigned char *ftrace_nop_replace(void) +{ + return ftrace_nop_code; +} + +/* + * mcount stub will be converted below for call + * Note: Just the last instruction is changed against nop + * */ +static unsigned char __attribute__((aligned(8))) +ftrace_call_code[MCOUNT_INSN_SIZE] = { + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MII] nop.m 0x0 */ + 0x30, 0x00, 0x00, 0x60, 0x00, 0x00, /* mov r3=ip */ + 0x00, 0x00, 0x04, 0x00, /* nop.i 0x0 */ + 0x05, 0x00, 0x00, 0x00, 0x01, 0x00, /* [MLX] nop.m 0x0 */ + 0xff, 0xff, 0xff, 0xff, 0x7f, 0x00, /* brl.many .;;*/ + 0xf8, 0xff, 0xff, 0xc8 +}; + +struct ftrace_call_insn { + u64 dummy1, dummy2; + u64 dummy3:48; + u64 imm39_l:16; + u64 imm39_h:23; + u64 dummy4:13; + u64 imm20:20; + u64 dummy5:3; + u64 i:1; + u64 dummy6:4; +}; + +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + struct ftrace_call_insn *code = (void *)ftrace_call_code; + unsigned long offset = addr - (ip + 0x10); + + code->imm39_l = offset >> 24; + code->imm39_h = offset >> 40; + code->imm20 = offset >> 4; + code->i = offset >> 63; + return ftrace_call_code; +} + +static int +ftrace_modify_code(unsigned long ip, unsigned char *old_code, + unsigned char *new_code, int do_check) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + + /* + * Note: Due to modules and __init, code can + * disappear and change, we need to protect against faulting + * as well as code changing. We do this by using the + * probe_kernel_* functions. + * + * No real locking needed, this code is run through + * kstop_machine, or before SMP starts. + */ + + if (!do_check) + goto skip_check; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + +skip_check: + /* replace the text with the new text */ + if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); + + return 0; +} + +static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; + unsigned long ip = rec->ip; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (rec->flags & FTRACE_FL_CONVERTED) { + struct ftrace_call_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_call_code; + tmp_call = (void *)replaced; + call_insn->imm39_l = tmp_call->imm39_l; + call_insn->imm39_h = tmp_call->imm39_h; + call_insn->imm20 = tmp_call->imm20; + call_insn->i = tmp_call->i; + if (memcmp(replaced, ftrace_call_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } else { + struct ftrace_orig_insn *call_insn, *tmp_call; + + call_insn = (void *)ftrace_orig_code; + tmp_call = (void *)replaced; + call_insn->sign = tmp_call->sign; + call_insn->imm20 = tmp_call->imm20; + if (memcmp(replaced, ftrace_orig_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + return 0; + } +} + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + int ret; + char *new; + + ret = ftrace_make_nop_check(rec, addr); + if (ret) + return ret; + new = ftrace_nop_replace(); + return ftrace_modify_code(rec->ip, NULL, new, 0); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + unsigned char *old, *new; + + old= ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new, 1); +} + +/* in IA64, _mcount can't directly call ftrace_stub. Only jump is ok */ +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip; + unsigned long addr = ((struct fnptr *)ftrace_call)->ip; + + if (func == ftrace_stub) + return 0; + ip = ((struct fnptr *)func)->ip; + + ia64_patch_imm64(addr + 2, ip); + + flush_icache_range(addr, addr + 16); + return 0; +} + +/* run from kstop_machine */ +int __init ftrace_dyn_arch_init(void *data) +{ + *(unsigned long *)data = 0; + + return 0; +} diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 6da1f20..2d31186 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -112,3 +112,9 @@ EXPORT_SYMBOL_GPL(esi_call_phys); #endif extern char ia64_ivt[]; EXPORT_SYMBOL(ia64_ivt); + +#include <asm/ftrace.h> +#ifdef CONFIG_FUNCTION_TRACER +/* mcount is defined in assembly */ +EXPORT_SYMBOL(_mcount); +#endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 677432b..0547214 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -126,6 +126,10 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func); extern void ftrace_caller(void); extern void ftrace_call(void); extern void mcount_call(void); + +#ifndef FTRACE_ADDR +#define FTRACE_ADDR ((unsigned long)ftrace_caller) +#endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_caller(void); extern int ftrace_enable_ftrace_graph_caller(void); diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h new file mode 100644 index 0000000..867829d --- /dev/null +++ b/include/trace/workqueue.h @@ -0,0 +1,25 @@ +#ifndef __TRACE_WORKQUEUE_H +#define __TRACE_WORKQUEUE_H + +#include <linux/tracepoint.h> +#include <linux/workqueue.h> +#include <linux/sched.h> + +DECLARE_TRACE(workqueue_insertion, + TPPROTO(struct task_struct *wq_thread, struct work_struct *work), + TPARGS(wq_thread, work)); + +DECLARE_TRACE(workqueue_execution, + TPPROTO(struct task_struct *wq_thread, struct work_struct *work), + TPARGS(wq_thread, work)); + +/* Trace the creation of one workqueue thread on a cpu */ +DECLARE_TRACE(workqueue_creation, + TPPROTO(struct task_struct *wq_thread, int cpu), + TPARGS(wq_thread, cpu)); + +DECLARE_TRACE(workqueue_destruction, + TPPROTO(struct task_struct *wq_thread), + TPARGS(wq_thread)); + +#endif /* __TRACE_WORKQUEUE_H */ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9442392..dde1d46 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -284,6 +284,17 @@ config KMEMTRACE If unsure, say N. +config WORKQUEUE_TRACER + bool "Trace workqueues" + select TRACING + help + The workqueue tracer provides some statistical informations + about each cpu workqueue thread such as the number of the + works inserted and executed since their creation. It can help + to evaluate the amount of work each of them have to perform. + For example it can help a developer to decide whether he should + choose a per cpu workqueue instead of a singlethreaded one. + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 05c9182..f76d48f 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -36,5 +36,6 @@ 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 +obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 9e54a6c..8c1c9c0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -263,14 +263,6 @@ static void ftrace_update_pid_func(void) # error Dynamic ftrace depends on MCOUNT_RECORD #endif -/* - * Since MCOUNT_ADDR may point to mcount itself, we do not want - * to get it confused by reading a reference in the code as we - * are parsing on objcopy output of text. Use a variable for - * it instead. - */ -static unsigned long mcount_addr = MCOUNT_ADDR; - enum { FTRACE_ENABLE_CALLS = (1 << 0), FTRACE_DISABLE_CALLS = (1 << 1), @@ -463,7 +455,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) unsigned long ip, fl; unsigned long ftrace_addr; - ftrace_addr = (unsigned long)ftrace_caller; + ftrace_addr = (unsigned long)FTRACE_ADDR; ip = rec->ip; @@ -575,7 +567,7 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; - ret = ftrace_make_nop(mod, rec, mcount_addr); + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); rec->flags |= FTRACE_FL_FAILED; @@ -1902,7 +1894,7 @@ int register_ftrace_function(struct ftrace_ops *ops) } /** - * unregister_ftrace_function - unresgister a function for profiling. + * unregister_ftrace_function - unregister a function for profiling. * @ops - ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 0418fc3..40217fb 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2353,7 +2353,6 @@ static int tracing_set_tracer(char *buf) if (ret) goto out; } - init_tracer_stat(t); trace_branch_enable(tr); out: @@ -3218,7 +3217,6 @@ __init static int tracer_alloc_buffers(void) #else current_trace = &nop_trace; #endif - init_tracer_stat(current_trace); /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index b3f9ad1..79c8721 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -334,24 +334,6 @@ struct tracer_flags { /* Makes more easy to define a tracer opt */ #define TRACER_OPT(s, b) .name = #s, .bit = b -/* - * If you want to provide a stat file (one-shot statistics), fill - * an iterator with stat_start/stat_next and a stat_show callbacks. - * The others callbacks are optional. - */ -struct tracer_stat { - /* The name of your stat file */ - const char *name; - /* Iteration over statistic entries */ - void *(*stat_start)(void); - void *(*stat_next)(void *prev, int idx); - /* Compare two entries for sorting (optional) for stats */ - int (*stat_cmp)(void *p1, void *p2); - /* Print a stat entry */ - int (*stat_show)(struct seq_file *s, void *p); - /* Print the headers of your stat entries */ - int (*stat_headers)(struct seq_file *s); -}; /* * A specific tracer, represented by methods that operate on a trace array: @@ -466,8 +448,6 @@ void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); -void init_tracer_stat(struct tracer *trace); - extern unsigned long nsecs_to_usecs(unsigned long nsecs); extern unsigned long tracing_max_latency; diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index da5cf3e..ca017e0 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -16,12 +16,12 @@ #include <asm/local.h> #include "trace.h" +#include "trace_stat.h" #include "trace_output.h" -static struct tracer branch_trace; - #ifdef CONFIG_BRANCH_TRACER +static struct tracer branch_trace; static int branch_tracing_enabled __read_mostly; static DEFINE_MUTEX(branch_tracing_mutex); @@ -191,6 +191,30 @@ static struct trace_event trace_branch_event = { .binary = trace_nop_print, }; +static struct tracer branch_trace __read_mostly = +{ + .name = "branch", + .init = branch_trace_init, + .reset = branch_trace_reset, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_branch, +#endif /* CONFIG_FTRACE_SELFTEST */ +}; + +__init static int init_branch_tracer(void) +{ + int ret; + + ret = register_ftrace_event(&trace_branch_event); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "branch events\n"); + return 1; + } + return register_tracer(&branch_trace); +} +device_initcall(init_branch_tracer); + #else static inline void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) @@ -305,6 +329,29 @@ static int annotated_branch_stat_cmp(void *p1, void *p2) return 0; } +static struct tracer_stat annotated_branch_stats = { + .name = "branch_annotated", + .stat_start = annotated_branch_stat_start, + .stat_next = annotated_branch_stat_next, + .stat_cmp = annotated_branch_stat_cmp, + .stat_headers = annotated_branch_stat_headers, + .stat_show = branch_stat_show +}; + +__init static int init_annotated_branch_stats(void) +{ + int ret; + + ret = register_stat_tracer(&annotated_branch_stats); + if (!ret) { + printk(KERN_WARNING "Warning: could not register " + "annotated branches stats\n"); + return 1; + } + return 0; +} +fs_initcall(init_annotated_branch_stats); + #ifdef CONFIG_PROFILE_ALL_BRANCHES extern unsigned long __start_branch_profile[]; @@ -339,60 +386,25 @@ all_branch_stat_next(void *v, int idx) return p; } -static struct tracer_stat branch_stats[] = { - {.name = "annotated", - .stat_start = annotated_branch_stat_start, - .stat_next = annotated_branch_stat_next, - .stat_cmp = annotated_branch_stat_cmp, - .stat_headers = annotated_branch_stat_headers, - .stat_show = branch_stat_show}, - - {.name = "all", +static struct tracer_stat all_branch_stats = { + .name = "branch_all", .stat_start = all_branch_stat_start, .stat_next = all_branch_stat_next, .stat_headers = all_branch_stat_headers, - .stat_show = branch_stat_show}, - - { } -}; -#else -static struct tracer_stat branch_stats[] = { - {.name = "annotated", - .stat_start = annotated_branch_stat_start, - .stat_next = annotated_branch_stat_next, - .stat_cmp = annotated_branch_stat_cmp, - .stat_headers = annotated_branch_stat_headers, - .stat_show = branch_stat_show}, - - { } + .stat_show = branch_stat_show }; -#endif /* CONFIG_PROFILE_ALL_BRANCHES */ - -static struct tracer branch_trace __read_mostly = +__init static int all_annotated_branch_stats(void) { - .name = "branch", -#ifdef CONFIG_BRANCH_TRACER - .init = branch_trace_init, - .reset = branch_trace_reset, -#ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_branch, -#endif /* CONFIG_FTRACE_SELFTEST */ -#endif - .stats = branch_stats -}; - -__init static int init_branch_trace(void) -{ -#ifdef CONFIG_BRANCH_TRACER int ret; - ret = register_ftrace_event(&trace_branch_event); + + ret = register_stat_tracer(&all_branch_stats); if (!ret) { - printk(KERN_WARNING "Warning: could not register branch events\n"); + printk(KERN_WARNING "Warning: could not register " + "all branches stats\n"); return 1; } -#endif - - return register_tracer(&branch_trace); + return 0; } -device_initcall(init_branch_trace); +fs_initcall(all_annotated_branch_stats); +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 1515f9e..cb29282 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -10,28 +10,32 @@ #include <linux/list.h> -#include <linux/seq_file.h> #include <linux/debugfs.h> +#include "trace_stat.h" #include "trace.h" /* List of stat entries from a tracer */ struct trace_stat_list { - struct list_head list; - void *stat; + struct list_head list; + void *stat; }; /* A stat session is the stats output in one file */ struct tracer_stat_session { - struct tracer_stat *ts; - struct list_head stat_list; - struct mutex stat_mutex; + struct list_head session_list; + struct tracer_stat *ts; + struct list_head stat_list; + struct mutex stat_mutex; + struct dentry *file; }; /* All of the sessions currently in use. Each stat file embeed one session */ -static struct tracer_stat_session **all_stat_sessions; -static int nb_sessions; -static struct dentry *stat_dir, **stat_files; +static LIST_HEAD(all_stat_sessions); +static DEFINE_MUTEX(all_stat_sessions_mutex); + +/* The root directory for all stat files */ +static struct dentry *stat_dir; static void reset_stat_session(struct tracer_stat_session *session) @@ -44,66 +48,77 @@ static void reset_stat_session(struct tracer_stat_session *session) INIT_LIST_HEAD(&session->stat_list); } -/* Called when a tracer is initialized */ -static int init_all_sessions(int nb, struct tracer_stat *ts) +static void destroy_session(struct tracer_stat_session *session) { - int i, j; - struct tracer_stat_session *session; + debugfs_remove(session->file); + reset_stat_session(session); + mutex_destroy(&session->stat_mutex); + kfree(session); +} - nb_sessions = 0; - if (all_stat_sessions) { - for (i = 0; i < nb_sessions; i++) { - session = all_stat_sessions[i]; - reset_stat_session(session); - mutex_destroy(&session->stat_mutex); - kfree(session); - } - } - all_stat_sessions = kmalloc(sizeof(struct tracer_stat_session *) * nb, - GFP_KERNEL); - if (!all_stat_sessions) - return -ENOMEM; +static int init_stat_file(struct tracer_stat_session *session); - for (i = 0; i < nb; i++) { - session = kmalloc(sizeof(struct tracer_stat_session) * nb, - GFP_KERNEL); - if (!session) - goto free_sessions; +int register_stat_tracer(struct tracer_stat *trace) +{ + struct tracer_stat_session *session, *node, *tmp; + int ret; + + if (!trace) + return -EINVAL; + + if (!trace->stat_start || !trace->stat_next || !trace->stat_show) + return -EINVAL; - INIT_LIST_HEAD(&session->stat_list); - mutex_init(&session->stat_mutex); - session->ts = &ts[i]; - all_stat_sessions[i] = session; + /* Already registered? */ + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) + return -EINVAL; } - nb_sessions = nb; - return 0; + mutex_unlock(&all_stat_sessions_mutex); + + /* Init the session */ + session = kmalloc(sizeof(struct tracer_stat_session), GFP_KERNEL); + if (!session) + return -ENOMEM; -free_sessions: + session->ts = trace; + INIT_LIST_HEAD(&session->session_list); + INIT_LIST_HEAD(&session->stat_list); + mutex_init(&session->stat_mutex); + session->file = NULL; - for (j = 0; j < i; j++) - kfree(all_stat_sessions[i]); + ret = init_stat_file(session); + if (ret) { + destroy_session(session); + return ret; + } - kfree(all_stat_sessions); - all_stat_sessions = NULL; + /* Register */ + mutex_lock(&all_stat_sessions_mutex); + list_add_tail(&session->session_list, &all_stat_sessions); + mutex_unlock(&all_stat_sessions_mutex); - return -ENOMEM; + return 0; } -static int basic_tracer_stat_checks(struct tracer_stat *ts) +void unregister_stat_tracer(struct tracer_stat *trace) { - int i; + struct tracer_stat_session *node, *tmp; - if (!ts) - return 0; - - for (i = 0; ts[i].name; i++) { - if (!ts[i].stat_start || !ts[i].stat_next || !ts[i].stat_show) - return -EBUSY; + mutex_lock(&all_stat_sessions_mutex); + list_for_each_entry_safe(node, tmp, &all_stat_sessions, session_list) { + if (node->ts == trace) { + list_del(&node->session_list); + destroy_session(node); + break; + } } - return i; + mutex_unlock(&all_stat_sessions_mutex); } + /* * For tracers that don't provide a stat_cmp callback. * This one will force an immediate insertion on tail of @@ -280,63 +295,7 @@ static const struct file_operations tracing_stat_fops = { .release = tracing_stat_release }; - -static void destroy_trace_stat_files(void) -{ - int i; - - if (stat_files) { - for (i = 0; i < nb_sessions; i++) - debugfs_remove(stat_files[i]); - kfree(stat_files); - stat_files = NULL; - } -} - -static void init_trace_stat_files(void) -{ - int i; - - if (!stat_dir || !nb_sessions) - return; - - stat_files = kmalloc(sizeof(struct dentry *) * nb_sessions, GFP_KERNEL); - - if (!stat_files) { - pr_warning("trace stat: not enough memory\n"); - return; - } - - for (i = 0; i < nb_sessions; i++) { - struct tracer_stat_session *session = all_stat_sessions[i]; - stat_files[i] = debugfs_create_file(session->ts->name, 0644, - stat_dir, - session, &tracing_stat_fops); - if (!stat_files[i]) - pr_warning("cannot create %s entry\n", - session->ts->name); - } -} - -void init_tracer_stat(struct tracer *trace) -{ - int nb = basic_tracer_stat_checks(trace->stats); - - destroy_trace_stat_files(); - - if (nb < 0) { - pr_warning("stat tracing: missing stat callback on %s\n", - trace->name); - return; - } - if (!nb) - return; - - init_all_sessions(nb, trace->stats); - init_trace_stat_files(); -} - -static int __init tracing_stat_init(void) +static int tracing_stat_init(void) { struct dentry *d_tracing; @@ -348,4 +307,16 @@ static int __init tracing_stat_init(void) "'trace_stat' entry\n"); return 0; } -fs_initcall(tracing_stat_init); + +static int init_stat_file(struct tracer_stat_session *session) +{ + if (!stat_dir && tracing_stat_init()) + return -ENODEV; + + session->file = debugfs_create_file(session->ts->name, 0644, + stat_dir, + session, &tracing_stat_fops); + if (!session->file) + return -ENOMEM; + return 0; +} diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h new file mode 100644 index 0000000..202274c --- /dev/null +++ b/kernel/trace/trace_stat.h @@ -0,0 +1,31 @@ +#ifndef __TRACE_STAT_H +#define __TRACE_STAT_H + +#include <linux/seq_file.h> + +/* + * If you want to provide a stat file (one-shot statistics), fill + * an iterator with stat_start/stat_next and a stat_show callbacks. + * The others callbacks are optional. + */ +struct tracer_stat { + /* The name of your stat file */ + const char *name; + /* Iteration over statistic entries */ + void *(*stat_start)(void); + void *(*stat_next)(void *prev, int idx); + /* Compare two entries for stats sorting */ + int (*stat_cmp)(void *p1, void *p2); + /* Print a stat entry */ + int (*stat_show)(struct seq_file *s, void *p); + /* Print the headers of your stat entries */ + int (*stat_headers)(struct seq_file *s); +}; + +/* + * Destroy or create a stat file + */ +extern int register_stat_tracer(struct tracer_stat *trace); +extern void unregister_stat_tracer(struct tracer_stat *trace); + +#endif /* __TRACE_STAT_H */ diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c new file mode 100644 index 0000000..f8118d3 --- /dev/null +++ b/kernel/trace/trace_workqueue.c @@ -0,0 +1,287 @@ +/* + * Workqueue statistical tracer. + * + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + */ + + +#include <trace/workqueue.h> +#include <linux/list.h> +#include "trace_stat.h" +#include "trace.h" + + +/* A cpu workqueue thread */ +struct cpu_workqueue_stats { + struct list_head list; +/* Useful to know if we print the cpu headers */ + bool first_entry; + int cpu; + pid_t pid; +/* Can be inserted from interrupt or user context, need to be atomic */ + atomic_t inserted; +/* + * Don't need to be atomic, works are serialized in a single workqueue thread + * on a single CPU. + */ + unsigned int executed; +}; + +/* List of workqueue threads on one cpu */ +struct workqueue_global_stats { + struct list_head list; + spinlock_t lock; +}; + +/* Don't need a global lock because allocated before the workqueues, and + * never freed. + */ +static struct workqueue_global_stats *all_workqueue_stat; + +/* Insertion of a work */ +static void +probe_workqueue_insertion(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + list_for_each_entry_safe(node, next, &all_workqueue_stat[cpu].list, + list) { + if (node->pid == wq_thread->pid) { + atomic_inc(&node->inserted); + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); +} + +/* Execution of a work */ +static void +probe_workqueue_execution(struct task_struct *wq_thread, + struct work_struct *work) +{ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + list_for_each_entry_safe(node, next, &all_workqueue_stat[cpu].list, + list) { + if (node->pid == wq_thread->pid) { + node->executed++; + goto found; + } + } + pr_debug("trace_workqueue: entry not found\n"); +found: + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); +} + +/* Creation of a cpu workqueue thread */ +static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu) +{ + struct cpu_workqueue_stats *cws; + unsigned long flags; + + WARN_ON(cpu < 0 || cpu >= num_possible_cpus()); + + /* Workqueues are sometimes created in atomic context */ + cws = kzalloc(sizeof(struct cpu_workqueue_stats), GFP_ATOMIC); + if (!cws) { + pr_warning("trace_workqueue: not enough memory\n"); + return; + } + tracing_record_cmdline(wq_thread); + + INIT_LIST_HEAD(&cws->list); + cws->cpu = cpu; + + cws->pid = wq_thread->pid; + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + if (list_empty(&all_workqueue_stat[cpu].list)) + cws->first_entry = true; + list_add_tail(&cws->list, &all_workqueue_stat[cpu].list); + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); +} + +/* Destruction of a cpu workqueue thread */ +static void probe_workqueue_destruction(struct task_struct *wq_thread) +{ + /* Workqueue only execute on one cpu */ + int cpu = cpumask_first(&wq_thread->cpus_allowed); + struct cpu_workqueue_stats *node, *next; + unsigned long flags; + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + list_for_each_entry_safe(node, next, &all_workqueue_stat[cpu].list, + list) { + if (node->pid == wq_thread->pid) { + list_del(&node->list); + kfree(node); + goto found; + } + } + + pr_debug("trace_workqueue: don't find workqueue to destroy\n"); +found: + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); + +} + +static struct cpu_workqueue_stats *workqueue_stat_start_cpu(int cpu) +{ + unsigned long flags; + struct cpu_workqueue_stats *ret = NULL; + + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + + if (!list_empty(&all_workqueue_stat[cpu].list)) + ret = list_entry(all_workqueue_stat[cpu].list.next, + struct cpu_workqueue_stats, list); + + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); + + return ret; +} + +static void *workqueue_stat_start(void) +{ + int cpu; + void *ret = NULL; + + for_each_possible_cpu(cpu) { + ret = workqueue_stat_start_cpu(cpu); + if (ret) + return ret; + } + return NULL; +} + +static void *workqueue_stat_next(void *prev, int idx) +{ + struct cpu_workqueue_stats *prev_cws = prev; + int cpu = prev_cws->cpu; + unsigned long flags; + void *ret = NULL; + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + if (list_is_last(&prev_cws->list, &all_workqueue_stat[cpu].list)) { + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); + for (++cpu ; cpu < num_possible_cpus(); cpu++) { + ret = workqueue_stat_start_cpu(cpu); + if (ret) + return ret; + } + return NULL; + } + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); + + return list_entry(prev_cws->list.next, struct cpu_workqueue_stats, + list); +} + +static int workqueue_stat_show(struct seq_file *s, void *p) +{ + struct cpu_workqueue_stats *cws = p; + unsigned long flags; + int cpu = cws->cpu; + + seq_printf(s, "%3d %6d %6u %s\n", cws->cpu, + atomic_read(&cws->inserted), + cws->executed, + trace_find_cmdline(cws->pid)); + + spin_lock_irqsave(&all_workqueue_stat[cpu].lock, flags); + if (&cws->list == all_workqueue_stat[cpu].list.next) + seq_printf(s, "\n"); + spin_unlock_irqrestore(&all_workqueue_stat[cpu].lock, flags); + + return 0; +} + +static int workqueue_stat_headers(struct seq_file *s) +{ + seq_printf(s, "# CPU INSERTED EXECUTED NAME\n"); + seq_printf(s, "# | | | |\n\n"); + return 0; +} + +struct tracer_stat workqueue_stats __read_mostly = { + .name = "workqueues", + .stat_start = workqueue_stat_start, + .stat_next = workqueue_stat_next, + .stat_show = workqueue_stat_show, + .stat_headers = workqueue_stat_headers +}; + + +int __init stat_workqueue_init(void) +{ + if (register_stat_tracer(&workqueue_stats)) { + pr_warning("Unable to register workqueue stat tracer\n"); + return 1; + } + + return 0; +} +fs_initcall(stat_workqueue_init); + +/* + * Workqueues are created very early, just after pre-smp initcalls. + * So we must register our tracepoints at this stage. + */ +int __init trace_workqueue_early_init(void) +{ + int ret, cpu; + + ret = register_trace_workqueue_insertion(probe_workqueue_insertion); + if (ret) + goto out; + + ret = register_trace_workqueue_execution(probe_workqueue_execution); + if (ret) + goto no_insertion; + + ret = register_trace_workqueue_creation(probe_workqueue_creation); + if (ret) + goto no_execution; + + ret = register_trace_workqueue_destruction(probe_workqueue_destruction); + if (ret) + goto no_creation; + + all_workqueue_stat = kmalloc(sizeof(struct workqueue_global_stats) + * num_possible_cpus(), GFP_KERNEL); + + if (!all_workqueue_stat) { + pr_warning("trace_workqueue: not enough memory\n"); + goto no_creation; + } + + for_each_possible_cpu(cpu) { + spin_lock_init(&all_workqueue_stat[cpu].lock); + INIT_LIST_HEAD(&all_workqueue_stat[cpu].list); + } + + return 0; + +no_creation: + unregister_trace_workqueue_creation(probe_workqueue_creation); +no_execution: + unregister_trace_workqueue_execution(probe_workqueue_execution); +no_insertion: + unregister_trace_workqueue_insertion(probe_workqueue_insertion); +out: + pr_warning("trace_workqueue: unable to trace workqueues\n"); + + return 1; +} +early_initcall(trace_workqueue_early_init); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2f44583..1fc2bc2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -33,6 +33,7 @@ #include <linux/kallsyms.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> +#include <trace/workqueue.h> /* * The per-CPU workqueue (if single thread, we always use the first @@ -125,9 +126,13 @@ struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); } +DEFINE_TRACE(workqueue_insertion); + static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head) { + trace_workqueue_insertion(cwq->thread, work); + set_wq_data(work, cwq); /* * Ensure that we get the right work->data if we see the @@ -259,6 +264,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, } EXPORT_SYMBOL_GPL(queue_delayed_work_on); +DEFINE_TRACE(workqueue_execution); + static void run_workqueue(struct cpu_workqueue_struct *cwq) { spin_lock_irq(&cwq->lock); @@ -284,7 +291,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq) */ struct lockdep_map lockdep_map = work->lockdep_map; #endif - + trace_workqueue_execution(cwq->thread, work); cwq->current_work = work; list_del_init(cwq->worklist.next); spin_unlock_irq(&cwq->lock); @@ -765,6 +772,8 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) return cwq; } +DEFINE_TRACE(workqueue_creation); + static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; @@ -787,6 +796,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; + trace_workqueue_creation(cwq->thread, cpu); + return 0; } @@ -868,6 +879,8 @@ struct workqueue_struct *__create_workqueue_key(const char *name, } EXPORT_SYMBOL_GPL(__create_workqueue_key); +DEFINE_TRACE(workqueue_destruction); + static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) { /* @@ -891,6 +904,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) * checks list_empty(), and a "normal" queue_work() can't use * a dead CPU. */ + trace_workqueue_destruction(cwq->thread); kthread_stop(cwq->thread); cwq->thread = NULL; } diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 5d90030..b5efa98 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -112,13 +112,13 @@ endif # --------------------------------------------------------------------------- # Default is built-in, unless we know otherwise -modkern_cflags := $(CFLAGS_KERNEL) +modkern_cflags = $(if $(part-of-module), $(CFLAGS_MODULE), $(CFLAGS_KERNEL)) quiet_modtag := $(empty) $(empty) -$(real-objs-m) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.i) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.s) : modkern_cflags := $(CFLAGS_MODULE) -$(real-objs-m:.o=.lst): modkern_cflags := $(CFLAGS_MODULE) +$(real-objs-m) : part-of-module := y +$(real-objs-m:.o=.i) : part-of-module := y +$(real-objs-m:.o=.s) : part-of-module := y +$(real-objs-m:.o=.lst): part-of-module := y $(real-objs-m) : quiet_modtag := [M] $(real-objs-m:.o=.i) : quiet_modtag := [M] @@ -215,7 +215,8 @@ endif ifdef CONFIG_FTRACE_MCOUNT_RECORD cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \ "$(if $(CONFIG_64BIT),64,32)" \ - "$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" "$(@)"; + "$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" \ + "$(if $(part-of-module),1,0)" "$(@)"; endif define rule_cc_o_c diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index fe83141..2ded5c8 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -100,14 +100,19 @@ $P =~ s@.*/@@g; my $V = '0.1'; -if ($#ARGV < 6) { - print "usage: $P arch objdump objcopy cc ld nm rm mv inputfile\n"; +if ($#ARGV < 7) { + print "usage: $P arch objdump objcopy cc ld nm rm mv is_module inputfile\n"; print "version: $V\n"; exit(1); } my ($arch, $bits, $objdump, $objcopy, $cc, - $ld, $nm, $rm, $mv, $inputfile) = @ARGV; + $ld, $nm, $rm, $mv, $is_module, $inputfile) = @ARGV; + +# This file refers to mcount and shouldn't be ftraced, so lets' ignore it +if ($inputfile eq "kernel/trace/ftrace.o") { + exit(0); +} # Acceptable sections to record. my %text_sections = ( @@ -201,6 +206,13 @@ if ($arch eq "x86_64") { $alignment = 2; $section_type = '%progbits'; +} elsif ($arch eq "ia64") { + $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$"; + $type = "data8"; + + if ($is_module eq "0") { + $cc .= " -mconstant-gp"; + } } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; }
| |