From 1f0d69a9fc815db82f15722bf05227190b1d714d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 12 Nov 2008 00:14:39 -0500 Subject: tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt Cc: Andrew Morton Cc: Frederic Weisbecker Cc: Theodore Tso Cc: Arjan van de Ven Cc: Steven Rostedt Signed-off-by: Ingo Molnar --- include/asm-generic/vmlinux.lds.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 80744606bad1..e10beb5335c9 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -45,6 +45,17 @@ #define MCOUNT_REC() #endif +#ifdef CONFIG_TRACE_UNLIKELY_PROFILE +#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_likely_profile) = .; \ + *(_ftrace_likely) \ + VMLINUX_SYMBOL(__stop_likely_profile) = .; \ + VMLINUX_SYMBOL(__start_unlikely_profile) = .; \ + *(_ftrace_unlikely) \ + VMLINUX_SYMBOL(__stop_unlikely_profile) = .; +#else +#define LIKELY_PROFILE() +#endif + /* .data section */ #define DATA_DATA \ *(.data) \ @@ -62,7 +73,8 @@ VMLINUX_SYMBOL(__stop___markers) = .; \ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ - VMLINUX_SYMBOL(__stop___tracepoints) = .; + VMLINUX_SYMBOL(__stop___tracepoints) = .; \ + LIKELY_PROFILE() #define RO_DATA(align) \ . = ALIGN((align)); \ -- cgit v1.2.3 From 2ed84eeb8808cf3c9f039213ca137ffd7d753f0e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 12 Nov 2008 15:24:24 -0500 Subject: trace: rename unlikely profiler to branch profiler Impact: name change of unlikely tracer and profiler Ingo Molnar suggested changing the config from UNLIKELY_PROFILE to BRANCH_PROFILING. I never did like the "unlikely" name so I went one step farther, and renamed all the unlikely configurations to a "BRANCH" variant. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/vsyscall_64.c | 2 +- arch/x86/vdso/vclock_gettime.c | 2 +- include/asm-generic/vmlinux.lds.h | 2 +- include/linux/compiler.h | 19 ++++++++++--------- kernel/trace/Kconfig | 10 +++++----- kernel/trace/Makefile | 7 +++---- kernel/trace/trace.c | 2 +- kernel/trace/trace.h | 6 +++--- kernel/trace/trace_unlikely.c | 4 ++-- 9 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/asm-generic') diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index ece02932ea57..6f3d3d4cd973 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -18,7 +18,7 @@ */ /* Disable profiling for userspace code: */ -#define DISABLE_UNLIKELY_PROFILE +#define DISABLE_BRANCH_PROFILING #include #include diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6e667631e7dc..d9d35824c56f 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -10,7 +10,7 @@ */ /* Disable profiling for userspace code: */ -#define DISABLE_UNLIKELY_PROFILE +#define DISABLE_BRANCH_PROFILING #include #include diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index e10beb5335c9..a5e4ed9baec8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -45,7 +45,7 @@ #define MCOUNT_REC() #endif -#ifdef CONFIG_TRACE_UNLIKELY_PROFILE +#ifdef CONFIG_TRACE_BRANCH_PROFILING #define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_likely_profile) = .; \ *(_ftrace_likely) \ VMLINUX_SYMBOL(__stop_likely_profile) = .; \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 63b7d9089d6e..c7d804a7a4d6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -59,26 +59,27 @@ extern void __chk_io_ptr(const volatile void __iomem *); * specific implementations come from the above header files */ -/* - * Note: DISABLE_UNLIKELY_PROFILE can be used by special lowlevel code - * to disable branch tracing on a per file basis. - */ -#if defined(CONFIG_TRACE_UNLIKELY_PROFILE) && !defined(DISABLE_UNLIKELY_PROFILE) -struct ftrace_likely_data { +struct ftrace_branch_data { const char *func; const char *file; unsigned line; unsigned long correct; unsigned long incorrect; }; -void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect); + +/* + * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code + * to disable branch tracing on a per file basis. + */ +#if defined(CONFIG_TRACE_BRANCH_PROFILING) && !defined(DISABLE_BRANCH_PROFILING) +void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) #define likely_check(x) ({ \ int ______r; \ - static struct ftrace_likely_data \ + static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_likely"))) \ ______f = { \ @@ -93,7 +94,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect); }) #define unlikely_check(x) ({ \ int ______r; \ - static struct ftrace_likely_data \ + static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_unlikely"))) \ ______f = { \ diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8abcaf821beb..9c89526b6b7c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -159,7 +159,7 @@ config BOOT_TRACER selected, because the self-tests are an initcall as well and that would invalidate the boot trace. ) -config TRACE_UNLIKELY_PROFILE +config TRACE_BRANCH_PROFILING bool "Trace likely/unlikely profiler" depends on DEBUG_KERNEL select TRACING @@ -175,7 +175,7 @@ config TRACE_UNLIKELY_PROFILE Say N if unsure. -config TRACING_UNLIKELY +config TRACING_BRANCHES bool help Selected by tracers that will trace the likely and unlikely @@ -183,10 +183,10 @@ config TRACING_UNLIKELY profiled. Profiling the tracing infrastructure can only happen when the likelys and unlikelys are not being traced. -config UNLIKELY_TRACER +config BRANCH_TRACER bool "Trace likely/unlikely instances" - depends on TRACE_UNLIKELY_PROFILE - select TRACING_UNLIKELY + depends on TRACE_BRANCH_PROFILING + select TRACING_BRANCHES help This traces the events of likely and unlikely condition calls in the kernel. The difference between this and the diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c938d03516c0..0087df7ba44e 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -11,9 +11,8 @@ obj-y += trace_selftest_dynamic.o endif # If unlikely tracing is enabled, do not trace these files -ifdef CONFIG_TRACING_UNLIKELY -KBUILD_CFLAGS += '-Dlikely(x)=likely_notrace(x)' -KBUILD_CFLAGS += '-Dunlikely(x)=unlikely_notrace(x)' +ifdef CONFIG_TRACING_BRANCHES +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING endif obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o @@ -31,6 +30,6 @@ obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o obj-$(CONFIG_BOOT_TRACER) += trace_boot.o obj-$(CONFIG_FUNCTION_RET_TRACER) += trace_functions_return.o -obj-$(CONFIG_TRACE_UNLIKELY_PROFILE) += trace_unlikely.o +obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_unlikely.o libftrace-y := ftrace.o diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d842db14a59b..bad59d32a4a9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -258,7 +258,7 @@ static const char *trace_options[] = { "sched-tree", "ftrace_printk", "ftrace_preempt", -#ifdef CONFIG_UNLIKELY_TRACER +#ifdef CONFIG_BRANCH_TRACER "unlikely", #endif NULL diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9635aa2c4fc1..dccae6312941 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -468,7 +468,7 @@ enum trace_iterator_flags { TRACE_ITER_SCHED_TREE = 0x200, TRACE_ITER_PRINTK = 0x400, TRACE_ITER_PREEMPTONLY = 0x800, -#ifdef CONFIG_UNLIKELY_TRACER +#ifdef CONFIG_BRANCH_TRACER TRACE_ITER_UNLIKELY = 0x1000, #endif }; @@ -530,7 +530,7 @@ static inline void ftrace_preempt_enable(int resched) preempt_enable_notrace(); } -#ifdef CONFIG_UNLIKELY_TRACER +#ifdef CONFIG_BRANCH_TRACER extern int enable_unlikely_tracing(struct trace_array *tr); extern void disable_unlikely_tracing(void); static inline int trace_unlikely_enable(struct trace_array *tr) @@ -552,6 +552,6 @@ static inline int trace_unlikely_enable(struct trace_array *tr) static inline void trace_unlikely_disable(void) { } -#endif /* CONFIG_UNLIKELY_TRACER */ +#endif /* CONFIG_BRANCH_TRACER */ #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_unlikely.c b/kernel/trace/trace_unlikely.c index 7290e0e7b4e3..856eb3b7f694 100644 --- a/kernel/trace/trace_unlikely.c +++ b/kernel/trace/trace_unlikely.c @@ -15,7 +15,7 @@ #include #include "trace.h" -#ifdef CONFIG_UNLIKELY_TRACER +#ifdef CONFIG_BRANCH_TRACER static int unlikely_tracing_enabled __read_mostly; static DEFINE_MUTEX(unlikely_tracing_mutex); @@ -119,7 +119,7 @@ static inline void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect) { } -#endif /* CONFIG_UNLIKELY_TRACER */ +#endif /* CONFIG_BRANCH_TRACER */ void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect) { -- cgit v1.2.3 From 7e066fb870fcd1025ec3ba7bbde5d541094f4ce1 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 14 Nov 2008 17:47:47 -0500 Subject: tracepoints: add DECLARE_TRACE() and DEFINE_TRACE() Impact: API *CHANGE*. Must update all tracepoint users. Add DEFINE_TRACE() to tracepoints to let them declare the tracepoint structure in a single spot for all the kernel. It helps reducing memory consumption, especially when declaring a lot of tracepoints, e.g. for kmalloc tracing. *API CHANGE WARNING*: now, DECLARE_TRACE() must be used in headers for tracepoint declarations rather than DEFINE_TRACE(). This is the sane way to do it. The name previously used was misleading. Updates scheduler instrumentation to follow this API change. Signed-off-by: Mathieu Desnoyers Signed-off-by: Ingo Molnar --- Documentation/tracepoints.txt | 7 ++++++- include/asm-generic/vmlinux.lds.h | 1 + include/linux/tracepoint.h | 35 +++++++++++++++++++++++---------- include/trace/sched.h | 24 +++++++++++----------- kernel/exit.c | 4 ++++ kernel/fork.c | 2 ++ kernel/kthread.c | 3 +++ kernel/sched.c | 6 ++++++ kernel/signal.c | 2 ++ samples/tracepoints/tp-samples-trace.h | 4 ++-- samples/tracepoints/tracepoint-sample.c | 3 +++ 11 files changed, 66 insertions(+), 25 deletions(-) (limited to 'include/asm-generic') diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt index 5d354e167494..e8ad47b437f3 100644 --- a/Documentation/tracepoints.txt +++ b/Documentation/tracepoints.txt @@ -42,7 +42,7 @@ In include/trace/subsys.h : #include -DEFINE_TRACE(subsys_eventname, +DECLARE_TRACE(subsys_eventname, TPPTOTO(int firstarg, struct task_struct *p), TPARGS(firstarg, p)); @@ -50,6 +50,8 @@ In subsys/file.c (where the tracing statement must be added) : #include +DEFINE_TRACE(subsys_eventname); + void somefct(void) { ... @@ -86,6 +88,9 @@ to limit collisions. Tracepoint names are global to the kernel: they are considered as being the same whether they are in the core kernel image or in modules. +If the tracepoint has to be used in kernel modules, an +EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be used to +export the defined tracepoints. * Probe / tracepoint example diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index a5e4ed9baec8..3b46ae464933 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -71,6 +71,7 @@ VMLINUX_SYMBOL(__start___markers) = .; \ *(__markers) \ VMLINUX_SYMBOL(__stop___markers) = .; \ + . = ALIGN(32); \ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ VMLINUX_SYMBOL(__stop___tracepoints) = .; \ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7e9b42aeae0e..757005458366 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -24,8 +24,12 @@ struct tracepoint { const char *name; /* Tracepoint name */ int state; /* State. */ void **funcs; -} __attribute__((aligned(8))); - +} __attribute__((aligned(32))); /* + * Aligned on 32 bytes because it is + * globally visible and gcc happily + * align these on the structure size. + * Keep in sync with vmlinux.lds.h. + */ #define TPPROTO(args...) args #define TPARGS(args...) args @@ -55,15 +59,10 @@ struct tracepoint { * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define DEFINE_TRACE(name, proto, args) \ +#define DECLARE_TRACE(name, proto, args) \ + extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ - static const char __tpstrtab_##name[] \ - __attribute__((section("__tracepoints_strings"))) \ - = #name; \ - static struct tracepoint __tracepoint_##name \ - __attribute__((section("__tracepoints"), aligned(8))) = \ - { __tpstrtab_##name, 0, NULL }; \ if (unlikely(__tracepoint_##name.state)) \ __DO_TRACE(&__tracepoint_##name, \ TPPROTO(proto), TPARGS(args)); \ @@ -77,11 +76,23 @@ struct tracepoint { return tracepoint_probe_unregister(#name, (void *)probe);\ } +#define DEFINE_TRACE(name) \ + static const char __tpstrtab_##name[] \ + __attribute__((section("__tracepoints_strings"))) = #name; \ + struct tracepoint __tracepoint_##name \ + __attribute__((section("__tracepoints"), aligned(32))) = \ + { __tpstrtab_##name, 0, NULL } + +#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \ + EXPORT_SYMBOL_GPL(__tracepoint_##name) +#define EXPORT_TRACEPOINT_SYMBOL(name) \ + EXPORT_SYMBOL(__tracepoint_##name) + extern void tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end); #else /* !CONFIG_TRACEPOINTS */ -#define DEFINE_TRACE(name, proto, args) \ +#define DECLARE_TRACE(name, proto, args) \ static inline void _do_trace_##name(struct tracepoint *tp, proto) \ { } \ static inline void trace_##name(proto) \ @@ -95,6 +106,10 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin, return -ENOSYS; \ } +#define DEFINE_TRACE(name) +#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) +#define EXPORT_TRACEPOINT_SYMBOL(name) + static inline void tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end) { } diff --git a/include/trace/sched.h b/include/trace/sched.h index ad47369d01b5..9b2854abf7e2 100644 --- a/include/trace/sched.h +++ b/include/trace/sched.h @@ -4,52 +4,52 @@ #include #include -DEFINE_TRACE(sched_kthread_stop, +DECLARE_TRACE(sched_kthread_stop, TPPROTO(struct task_struct *t), TPARGS(t)); -DEFINE_TRACE(sched_kthread_stop_ret, +DECLARE_TRACE(sched_kthread_stop_ret, TPPROTO(int ret), TPARGS(ret)); -DEFINE_TRACE(sched_wait_task, +DECLARE_TRACE(sched_wait_task, TPPROTO(struct rq *rq, struct task_struct *p), TPARGS(rq, p)); -DEFINE_TRACE(sched_wakeup, +DECLARE_TRACE(sched_wakeup, TPPROTO(struct rq *rq, struct task_struct *p), TPARGS(rq, p)); -DEFINE_TRACE(sched_wakeup_new, +DECLARE_TRACE(sched_wakeup_new, TPPROTO(struct rq *rq, struct task_struct *p), TPARGS(rq, p)); -DEFINE_TRACE(sched_switch, +DECLARE_TRACE(sched_switch, TPPROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next), TPARGS(rq, prev, next)); -DEFINE_TRACE(sched_migrate_task, +DECLARE_TRACE(sched_migrate_task, TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu), TPARGS(rq, p, dest_cpu)); -DEFINE_TRACE(sched_process_free, +DECLARE_TRACE(sched_process_free, TPPROTO(struct task_struct *p), TPARGS(p)); -DEFINE_TRACE(sched_process_exit, +DECLARE_TRACE(sched_process_exit, TPPROTO(struct task_struct *p), TPARGS(p)); -DEFINE_TRACE(sched_process_wait, +DECLARE_TRACE(sched_process_wait, TPPROTO(struct pid *pid), TPARGS(pid)); -DEFINE_TRACE(sched_process_fork, +DECLARE_TRACE(sched_process_fork, TPPROTO(struct task_struct *parent, struct task_struct *child), TPARGS(parent, child)); -DEFINE_TRACE(sched_signal_send, +DECLARE_TRACE(sched_signal_send, TPPROTO(int sig, struct task_struct *p), TPARGS(sig, p)); diff --git a/kernel/exit.c b/kernel/exit.c index ae2b92be5fae..f995d2418668 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -54,6 +54,10 @@ #include #include +DEFINE_TRACE(sched_process_free); +DEFINE_TRACE(sched_process_exit); +DEFINE_TRACE(sched_process_wait); + static void exit_mm(struct task_struct * tsk); static inline int task_detached(struct task_struct *p) diff --git a/kernel/fork.c b/kernel/fork.c index f6083561dfe0..0837d0deee5f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -79,6 +79,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_TRACE(sched_process_fork); + int nr_processes(void) { int cpu; diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e7a7ce3ed0a..4fbc456f393d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +DEFINE_TRACE(sched_kthread_stop); +DEFINE_TRACE(sched_kthread_stop_ret); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/sched.c b/kernel/sched.c index 50a21f964679..327f91c63c99 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -118,6 +118,12 @@ */ #define RUNTIME_INF ((u64)~0ULL) +DEFINE_TRACE(sched_wait_task); +DEFINE_TRACE(sched_wakeup); +DEFINE_TRACE(sched_wakeup_new); +DEFINE_TRACE(sched_switch); +DEFINE_TRACE(sched_migrate_task); + #ifdef CONFIG_SMP /* * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc654455..e9afe63da24b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -41,6 +41,8 @@ static struct kmem_cache *sigqueue_cachep; +DEFINE_TRACE(sched_signal_send); + static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h index 0216b55bd640..01724e04c556 100644 --- a/samples/tracepoints/tp-samples-trace.h +++ b/samples/tracepoints/tp-samples-trace.h @@ -4,10 +4,10 @@ #include /* for struct inode and struct file */ #include -DEFINE_TRACE(subsys_event, +DECLARE_TRACE(subsys_event, TPPROTO(struct inode *inode, struct file *file), TPARGS(inode, file)); -DEFINE_TRACE(subsys_eventb, +DECLARE_TRACE(subsys_eventb, TPPROTO(void), TPARGS()); #endif diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c index 4ae4b7fcc043..00d169792a3e 100644 --- a/samples/tracepoints/tracepoint-sample.c +++ b/samples/tracepoints/tracepoint-sample.c @@ -13,6 +13,9 @@ #include #include "tp-samples-trace.h" +DEFINE_TRACE(subsys_event); +DEFINE_TRACE(subsys_eventb); + struct proc_dir_entry *pentry_example; static int my_open(struct inode *inode, struct file *file) -- cgit v1.2.3 From 45b797492a0758e64dff74e9db70e1f65e0603a5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 21 Nov 2008 00:40:40 -0500 Subject: trace: consolidate unlikely and likely profiler Impact: clean up to make one profiler of like and unlikely tracer The likely and unlikely profiler prints out the file and line numbers of the annotated branches that it is profiling. It shows the number of times it was correct or incorrect in its guess. Having two different files or sections for that matter to tell us if it was a likely or unlikely is pretty pointless. We really only care if it was correct or not. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/asm-generic/vmlinux.lds.h | 9 +++------ include/linux/compiler.h | 24 +++++------------------- kernel/trace/Kconfig | 3 +-- kernel/trace/trace_branch.c | 39 +++++++++++++-------------------------- 4 files changed, 22 insertions(+), 53 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 3b46ae464933..8bccb49981e5 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -46,12 +46,9 @@ #endif #ifdef CONFIG_TRACE_BRANCH_PROFILING -#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_likely_profile) = .; \ - *(_ftrace_likely) \ - VMLINUX_SYMBOL(__stop_likely_profile) = .; \ - VMLINUX_SYMBOL(__start_unlikely_profile) = .; \ - *(_ftrace_unlikely) \ - VMLINUX_SYMBOL(__stop_unlikely_profile) = .; +#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \ + *(_ftrace_annotated_branch) \ + VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .; #else #define LIKELY_PROFILE() #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c25e525121f0..0628a2013fae 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -77,32 +77,18 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) -#define likely_check(x) ({ \ +#define __branch_check__(x, expect) ({ \ int ______r; \ static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_likely"))) \ + __attribute__((section("_ftrace_annotated_branch"))) \ ______f = { \ .func = __func__, \ .file = __FILE__, \ .line = __LINE__, \ }; \ ______r = likely_notrace(x); \ - ftrace_likely_update(&______f, ______r, 1); \ - ______r; \ - }) -#define unlikely_check(x) ({ \ - int ______r; \ - static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_unlikely"))) \ - ______f = { \ - .func = __func__, \ - .file = __FILE__, \ - .line = __LINE__, \ - }; \ - ______r = unlikely_notrace(x); \ - ftrace_likely_update(&______f, ______r, 0); \ + ftrace_likely_update(&______f, ______r, expect); \ ______r; \ }) @@ -112,10 +98,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); * written by Daniel Walker. */ # ifndef likely -# define likely(x) (__builtin_constant_p(x) ? !!(x) : likely_check(x)) +# define likely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1)) # endif # ifndef unlikely -# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : unlikely_check(x)) +# define unlikely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0)) # endif #else # define likely(x) __builtin_expect(!!(x), 1) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index b8378fad29a3..7e3548705708 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -166,8 +166,7 @@ config TRACE_BRANCH_PROFILING This tracer profiles all the the likely and unlikely macros in the kernel. It will display the results in: - /debugfs/tracing/profile_likely - /debugfs/tracing/profile_unlikely + /debugfs/tracing/profile_annotated_branch Note: this will add a significant overhead, only turn this on if you need to profile the system's use of these macros. diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 23f9b02ce967..21dedc8b50a4 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -261,7 +261,7 @@ static struct seq_operations tracing_likely_seq_ops = { .show = t_show, }; -static int tracing_likely_open(struct inode *inode, struct file *file) +static int tracing_branch_open(struct inode *inode, struct file *file) { int ret; @@ -274,25 +274,18 @@ static int tracing_likely_open(struct inode *inode, struct file *file) return ret; } -static struct file_operations tracing_likely_fops = { - .open = tracing_likely_open, +static const struct file_operations tracing_branch_fops = { + .open = tracing_branch_open, .read = seq_read, .llseek = seq_lseek, }; -extern unsigned long __start_likely_profile[]; -extern unsigned long __stop_likely_profile[]; -extern unsigned long __start_unlikely_profile[]; -extern unsigned long __stop_unlikely_profile[]; +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; -static struct ftrace_pointer ftrace_likely_pos = { - .start = __start_likely_profile, - .stop = __stop_likely_profile, -}; - -static struct ftrace_pointer ftrace_unlikely_pos = { - .start = __start_unlikely_profile, - .stop = __stop_unlikely_profile, +static const struct ftrace_pointer ftrace_annotated_branch_pos = { + .start = __start_annotated_branch_profile, + .stop = __stop_annotated_branch_profile, }; static __init int ftrace_branch_init(void) @@ -302,18 +295,12 @@ static __init int ftrace_branch_init(void) d_tracer = tracing_init_dentry(); - entry = debugfs_create_file("profile_likely", 0444, d_tracer, - &ftrace_likely_pos, - &tracing_likely_fops); - if (!entry) - pr_warning("Could not create debugfs 'profile_likely' entry\n"); - - entry = debugfs_create_file("profile_unlikely", 0444, d_tracer, - &ftrace_unlikely_pos, - &tracing_likely_fops); + entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer, + &ftrace_annotated_branch_pos, + &tracing_branch_fops); if (!entry) - pr_warning("Could not create debugfs" - " 'profile_unlikely' entry\n"); + pr_warning("Could not create debugfs " + "'profile_annotatet_branch' entry\n"); return 0; } -- cgit v1.2.3 From 2bcd521a684cc94befbe2ce7d5b613c841b0d304 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 21 Nov 2008 01:30:54 -0500 Subject: trace: profile all if conditionals Impact: feature to profile if statements This patch adds a branch profiler for all if () statements. The results will be found in: /debugfs/tracing/profile_branch For example: miss hit % Function File Line ------- --------- - -------- ---- ---- 0 1 100 x86_64_start_reservations head64.c 127 0 1 100 copy_bootdata head64.c 69 1 0 0 x86_64_start_kernel head64.c 111 32 0 0 set_intr_gate desc.h 319 1 0 0 reserve_ebda_region head.c 51 1 0 0 reserve_ebda_region head.c 47 0 1 100 reserve_ebda_region head.c 42 0 0 X maxcpus main.c 165 Miss means the branch was not taken. Hit means the branch was taken. The percent is the percentage the branch was taken. This adds a significant amount of overhead and should only be used by those analyzing their system. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/asm-generic/vmlinux.lds.h | 11 ++++++++++- include/linux/compiler.h | 38 ++++++++++++++++++++++++++++++++++++-- kernel/trace/Kconfig | 16 ++++++++++++++++ kernel/trace/trace_branch.c | 33 +++++++++++++++++++++++++++++++-- 4 files changed, 93 insertions(+), 5 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8bccb49981e5..eba835a2c2cd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -53,6 +53,14 @@ #define LIKELY_PROFILE() #endif +#ifdef CONFIG_PROFILE_ALL_BRANCHES +#define BRANCH_PROFILE() VMLINUX_SYMBOL(__start_branch_profile) = .; \ + *(_ftrace_branch) \ + VMLINUX_SYMBOL(__stop_branch_profile) = .; +#else +#define BRANCH_PROFILE() +#endif + /* .data section */ #define DATA_DATA \ *(.data) \ @@ -72,7 +80,8 @@ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ VMLINUX_SYMBOL(__stop___tracepoints) = .; \ - LIKELY_PROFILE() + LIKELY_PROFILE() \ + BRANCH_PROFILE() #define RO_DATA(align) \ . = ALIGN((align)); \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 0628a2013fae..ea7c6be354b7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -63,8 +63,16 @@ struct ftrace_branch_data { const char *func; const char *file; unsigned line; - unsigned long correct; - unsigned long incorrect; + union { + struct { + unsigned long correct; + unsigned long incorrect; + }; + struct { + unsigned long miss; + unsigned long hit; + }; + }; }; /* @@ -103,6 +111,32 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # ifndef unlikely # define unlikely(x) (__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0)) # endif + +#ifdef CONFIG_PROFILE_ALL_BRANCHES +/* + * "Define 'is'", Bill Clinton + * "Define 'if'", Steven Rostedt + */ +#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) : \ + ({ \ + int ______r; \ + static struct ftrace_branch_data \ + __attribute__((__aligned__(4))) \ + __attribute__((section("_ftrace_branch"))) \ + ______f = { \ + .func = __func__, \ + .file = __FILE__, \ + .line = __LINE__, \ + }; \ + ______r = !!(cond); \ + if (______r) \ + ______f.hit++; \ + else \ + ______f.miss++; \ + ______r; \ + })) +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ + #else # define likely(x) __builtin_expect(!!(x), 1) # define unlikely(x) __builtin_expect(!!(x), 0) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 7e3548705708..61e8cca6ff45 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -173,6 +173,22 @@ config TRACE_BRANCH_PROFILING Say N if unsure. +config PROFILE_ALL_BRANCHES + bool "Profile all if conditionals" + depends on TRACE_BRANCH_PROFILING + help + This tracer profiles all branch conditions. Every if () + taken in the kernel is recorded whether it hit or miss. + The results will be displayed in: + + /debugfs/tracing/profile_branch + + This configuration, when enabled, will impose a great overhead + on the system. This should only be enabled when the system + is to be analyzed + + Say N if unsure. + config TRACING_BRANCHES bool help diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 142acb3b4e00..85792aec64d2 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -185,6 +185,7 @@ EXPORT_SYMBOL(ftrace_likely_update); struct ftrace_pointer { void *start; void *stop; + int hit; }; static void * @@ -223,13 +224,17 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { + struct ftrace_pointer *fp = m->private; struct ftrace_branch_data *p = v; const char *f; long percent; if (v == (void *)1) { - seq_printf(m, " correct incorrect %% " - " Function " + if (fp->hit) + seq_printf(m, " miss hit %% "); + else + seq_printf(m, " correct incorrect %% "); + seq_printf(m, " Function " " File Line\n" " ------- --------- - " " -------- " @@ -243,6 +248,9 @@ static int t_show(struct seq_file *m, void *v) f--; f++; + /* + * The miss is overlayed on correct, and hit on incorrect. + */ if (p->correct) { percent = p->incorrect * 100; percent /= p->correct + p->incorrect; @@ -284,6 +292,18 @@ static const struct file_operations tracing_branch_fops = { .llseek = seq_lseek, }; +#ifdef CONFIG_PROFILE_ALL_BRANCHES +extern unsigned long __start_branch_profile[]; +extern unsigned long __stop_branch_profile[]; + +static struct ftrace_pointer ftrace_branch_pos = { + .start = __start_branch_profile, + .stop = __stop_branch_profile, + .hit = 1, +}; + +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ + extern unsigned long __start_annotated_branch_profile[]; extern unsigned long __stop_annotated_branch_profile[]; @@ -306,6 +326,15 @@ static __init int ftrace_branch_init(void) pr_warning("Could not create debugfs " "'profile_annotatet_branch' entry\n"); +#ifdef CONFIG_PROFILE_ALL_BRANCHES + entry = debugfs_create_file("profile_branch", 0444, d_tracer, + &ftrace_branch_pos, + &tracing_branch_fops); + if (!entry) + pr_warning("Could not create debugfs" + " 'profile_branch' entry\n"); +#endif + return 0; } -- cgit v1.2.3 From a0343e823184070f55364d8359f832dcb33c57c7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 9 Dec 2008 23:53:16 +0100 Subject: tracing/function-graph-tracer: add a new .irqentry.text section Impact: let the function-graph-tracer be aware of the irq entrypoints Add a new .irqentry.text section to store the irq entrypoints functions inside the same section. This way, the tracer will be able to signal an interrupts triggering on output by recognizing these entrypoints. Also, make this section recordable for dynamic tracing. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- arch/x86/kernel/vmlinux_64.lds.S | 1 + include/asm-generic/vmlinux.lds.h | 10 ++++++++++ scripts/recordmcount.pl | 1 + 3 files changed, 12 insertions(+) (limited to 'include/asm-generic') diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S index 46e05447405b..1a614c0e6bef 100644 --- a/arch/x86/kernel/vmlinux_64.lds.S +++ b/arch/x86/kernel/vmlinux_64.lds.S @@ -35,6 +35,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT KPROBES_TEXT + IRQENTRY_TEXT *(.fixup) *(.gnu.warning) _etext = .; /* End of text section */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index eba835a2c2cd..c61fab1dd2f8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -288,6 +288,16 @@ *(.kprobes.text) \ VMLINUX_SYMBOL(__kprobes_text_end) = .; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#define IRQENTRY_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__irqentry_text_start) = .; \ + *(.irqentry.text) \ + VMLINUX_SYMBOL(__irqentry_text_end) = .; +#else +#define IRQENTRY_TEXT +#endif + /* Section used for early init (in .S files) */ #define HEAD_TEXT *(.head.text) diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 0b1dc9f9bb06..fe831412bea9 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -114,6 +114,7 @@ my %text_sections = ( ".text" => 1, ".sched.text" => 1, ".spinlock.text" => 1, + ".irqentry.text" => 1, ); $objdump = "objdump" if ((length $objdump) == 0); -- cgit v1.2.3 From b93a531e315e97ef00367099e6b5f19651936e20 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 16 Dec 2008 11:40:27 +0000 Subject: allow bug table entries to use relative pointers (and use it on x86-64) Impact: reduce bug table size This allows reducing the bug table size by half. Perhaps there are other 64-bit architectures that could also make use of this. Signed-off-by: Jan Beulich Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 4 ++++ arch/x86/include/asm/bug.h | 2 +- include/asm-generic/bug.h | 8 ++++++++ lib/bug.c | 19 +++++++++++++++++-- 4 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/asm-generic') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ac22bb7719f7..ab98cca84e1b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -87,6 +87,10 @@ config GENERIC_IOMAP config GENERIC_BUG def_bool y depends on BUG + select GENERIC_BUG_RELATIVE_POINTERS if X86_64 + +config GENERIC_BUG_RELATIVE_POINTERS + bool config GENERIC_HWEIGHT def_bool y diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 3def2065fcea..d9cf1cd156d2 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -9,7 +9,7 @@ #ifdef CONFIG_X86_32 # define __BUG_C0 "2:\t.long 1b, %c0\n" #else -# define __BUG_C0 "2:\t.quad 1b, %c0\n" +# define __BUG_C0 "2:\t.long 1b - 2b, %c0 - 2b\n" #endif #define BUG() \ diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 12c07c1866b2..4c794d73fb84 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -8,9 +8,17 @@ #ifdef CONFIG_GENERIC_BUG #ifndef __ASSEMBLY__ struct bug_entry { +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS unsigned long bug_addr; +#else + signed int bug_addr_disp; +#endif #ifdef CONFIG_DEBUG_BUGVERBOSE +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS const char *file; +#else + signed int file_disp; +#endif unsigned short line; #endif unsigned short flags; diff --git a/lib/bug.c b/lib/bug.c index bfeafd60ee9f..300e41afbf97 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -5,6 +5,8 @@ CONFIG_BUG - emit BUG traps. Nothing happens without this. CONFIG_GENERIC_BUG - enable this code. + CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to + the containing struct bug_entry for bug_addr and file. CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable @@ -43,6 +45,15 @@ extern const struct bug_entry __start___bug_table[], __stop___bug_table[]; +static inline unsigned long bug_addr(const struct bug_entry *bug) +{ +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + return bug->bug_addr; +#else + return (unsigned long)bug + bug->bug_addr_disp; +#endif +} + #ifdef CONFIG_MODULES static LIST_HEAD(module_bug_list); @@ -55,7 +66,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) unsigned i; for (i = 0; i < mod->num_bugs; ++i, ++bug) - if (bugaddr == bug->bug_addr) + if (bugaddr == bug_addr(bug)) return bug; } return NULL; @@ -108,7 +119,7 @@ const struct bug_entry *find_bug(unsigned long bugaddr) const struct bug_entry *bug; for (bug = __start___bug_table; bug < __stop___bug_table; ++bug) - if (bugaddr == bug->bug_addr) + if (bugaddr == bug_addr(bug)) return bug; return module_find_bug(bugaddr); @@ -133,7 +144,11 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (bug) { #ifdef CONFIG_DEBUG_BUGVERBOSE +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS file = bug->file; +#else + file = (const char *)bug + bug->file_disp; +#endif line = bug->line; #endif warning = (bug->flags & BUGFLAG_WARNING) != 0; -- cgit v1.2.3 From 2520bd3123c00272f818a176c92d03c7d0a113d6 Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Thu, 18 Dec 2008 11:41:32 -0800 Subject: x86: PAT: add pgprot_writecombine() interface for drivers - v3 Impact: New mm functionality. Add pgprot_writecombine. pgprot_writecombine will be aliased to pgprot_noncached when not supported by the architecture. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/pgtable.h | 3 +++ arch/x86/mm/pat.c | 8 ++++++++ include/asm-generic/pgtable.h | 4 ++++ 3 files changed, 15 insertions(+) (limited to 'include/asm-generic') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6968d4f6be3e..579f8ceee948 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -168,6 +168,9 @@ #ifndef __ASSEMBLY__ +#define pgprot_writecombine pgprot_writecombine +extern pgprot_t pgprot_writecombine(pgprot_t prot); + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 1069ffecf77d..d5254bae84f4 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -832,6 +832,14 @@ void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, } } +pgprot_t pgprot_writecombine(pgprot_t prot) +{ + if (pat_enabled) + return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC); + else + return pgprot_noncached(prot); +} + #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) /* get Nth element of the linked list */ diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index ef87f889ef62..b84633801fb6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres #define move_pte(pte, prot, old_addr, new_addr) (pte) #endif +#ifndef pgprot_writecombine +#define pgprot_writecombine pgprot_noncached +#endif + /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no -- cgit v1.2.3 From 34801ba9bf0381fcf0e2b08179d2c07f2c6ede74 Mon Sep 17 00:00:00 2001 From: "venkatesh.pallipadi@intel.com" Date: Fri, 19 Dec 2008 13:47:29 -0800 Subject: x86: PAT: move track untrack pfnmap stubs to asm-generic Impact: Cleanup and branch hints only. Move the track and untrack pfn stub routines from memory.c to asm-generic. Also add unlikely to pfnmap related calls in fork and exit path. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/pgtable.h | 6 ++---- include/asm-generic/pgtable.h | 46 ++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 6 ------ mm/memory.c | 48 ++---------------------------------------- 4 files changed, 50 insertions(+), 56 deletions(-) (limited to 'include/asm-generic') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2aa792bbd7e0..875192bf72cb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -339,12 +339,10 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask) +#ifndef __ASSEMBLY__ /* Indicate that x86 has its own track and untrack pfn vma functions */ -#define track_pfn_vma_new track_pfn_vma_new -#define track_pfn_vma_copy track_pfn_vma_copy -#define untrack_pfn_vma untrack_pfn_vma +#define __HAVE_PFNMAP_TRACKING -#ifndef __ASSEMBLY__ #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index b84633801fb6..72ebe91005a8 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -293,6 +293,52 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, #define arch_flush_lazy_cpu_mode() do {} while (0) #endif +#ifndef __HAVE_PFNMAP_TRACKING +/* + * Interface that can be used by architecture code to keep track of + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) + * + * track_pfn_vma_new is called when a _new_ pfn mapping is being established + * for physical range indicated by pfn and size. + */ +static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot, + unsigned long pfn, unsigned long size) +{ + return 0; +} + +/* + * Interface that can be used by architecture code to keep track of + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) + * + * track_pfn_vma_copy is called when vma that is covering the pfnmap gets + * copied through copy_page_range(). + */ +static inline int track_pfn_vma_copy(struct vm_area_struct *vma) +{ + return 0; +} + +/* + * Interface that can be used by architecture code to keep track of + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) + * + * untrack_pfn_vma is called while unmapping a pfnmap for a region. + * untrack can be called for a specific region indicated by pfn and size or + * can be for the entire vma (in which case size can be zero). + */ +static inline void untrack_pfn_vma(struct vm_area_struct *vma, + unsigned long pfn, unsigned long size) +{ +} +#else +extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot, + unsigned long pfn, unsigned long size); +extern int track_pfn_vma_copy(struct vm_area_struct *vma); +extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, + unsigned long size); +#endif + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 36f9b3fa5e15..d3ddd735e375 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -163,12 +163,6 @@ static inline int is_pfn_mapping(struct vm_area_struct *vma) return (vma->vm_flags & VM_PFNMAP); } -extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot, - unsigned long pfn, unsigned long size); -extern int track_pfn_vma_copy(struct vm_area_struct *vma); -extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size); - /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask diff --git a/mm/memory.c b/mm/memory.c index 6b29f39a5a3e..f01b7eed6e16 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -99,50 +99,6 @@ int randomize_va_space __read_mostly = 2; #endif -#ifndef track_pfn_vma_new -/* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * track_pfn_vma_new is called when a _new_ pfn mapping is being established - * for physical range indicated by pfn and size. - */ -int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot, - unsigned long pfn, unsigned long size) -{ - return 0; -} -#endif - -#ifndef track_pfn_vma_copy -/* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * track_pfn_vma_copy is called when vma that is covering the pfnmap gets - * copied through copy_page_range(). - */ -int track_pfn_vma_copy(struct vm_area_struct *vma) -{ - return 0; -} -#endif - -#ifndef untrack_pfn_vma -/* - * Interface that can be used by architecture code to keep track of - * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn) - * - * untrack_pfn_vma is called while unmapping a pfnmap for a region. - * untrack can be called for a specific region indicated by pfn and size or - * can be for the entire vma (in which case size can be zero). - */ -void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, - unsigned long size) -{ -} -#endif - static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -713,7 +669,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); - if (is_pfn_mapping(vma)) { + if (unlikely(is_pfn_mapping(vma))) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine @@ -969,7 +925,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (vma->vm_flags & VM_ACCOUNT) *nr_accounted += (end - start) >> PAGE_SHIFT; - if (is_pfn_mapping(vma)) + if (unlikely(is_pfn_mapping(vma))) untrack_pfn_vma(vma, 0, 0); while (start != end) { -- cgit v1.2.3 From 32272a26974d2027384fd4010cd1780fca425d94 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 25 Dec 2008 13:38:59 +0100 Subject: [S390] __page_to_pfn warnings For CONFIG_SPARSEMEM_VMEMMAP=y on s390 I get warnings like init/main.c: In function 'start_kernel': init/main.c:641: warning: format '%08lx' expects type 'long unsigned int', but argument 2 has type 'int' The warning can be suppressed with a cast to unsigned long in the CONFIG_SPARSEMEM_VMEMMAP=y version of __page_to_pfn. Signed-off-by: Martin Schwidefsky --- include/asm-generic/memory_model.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 18546d8eb78e..36fa286adad5 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -49,7 +49,7 @@ /* memmap is virtually contigious. */ #define __pfn_to_page(pfn) (vmemmap + (pfn)) -#define __page_to_pfn(page) ((page) - vmemmap) +#define __page_to_pfn(page) (unsigned long)((page) - vmemmap) #elif defined(CONFIG_SPARSEMEM) /* -- cgit v1.2.3