From b0f82b81fe6bbcf78d478071f33e44554726bc81 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 20 May 2010 07:47:21 +0200 Subject: perf: Drop the skip argument from perf_arch_fetch_regs_caller Drop this argument now that we always want to rewind only to the state of the first caller. It means frame pointers are not necessary anymore to reliably get the source of an event. But this also means we need this helper to be a macro now, as an inline function is not an option since we need to know when to provide a default implentation. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul Mackerras Cc: David Miller Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo --- include/trace/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 3d685d1f2a03..8ee8b6e6b25e 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),\ -- cgit v1.2.3 From 30dbb20e68e6f7df974b77d2350ebad5eb6f6c9e Mon Sep 17 00:00:00 2001 From: Américo Wang Date: Wed, 26 May 2010 18:57:53 +0800 Subject: tracing: Remove boot tracer The boot tracer is useless. It simply logs the initcalls but in fact these initcalls are also logged through printk while using the initcall_debug kernel parameter. Nobody seem to be using it so far. Then just remove it. Signed-off-by: WANG Cong Cc: Chase Douglas Cc: Steven Rostedt Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Li Zefan LKML-Reference: <20100526105753.GA5677@cr0.nay.redhat.com> [ remove the hooks in main.c, and the headers ] Signed-off-by: Frederic Weisbecker --- include/trace/boot.h | 60 -------------- init/main.c | 27 +++---- kernel/trace/Kconfig | 17 ---- kernel/trace/Makefile | 1 - kernel/trace/trace.c | 3 - kernel/trace/trace.h | 8 -- kernel/trace/trace_boot.c | 185 ------------------------------------------- kernel/trace/trace_entries.h | 27 ------- 8 files changed, 10 insertions(+), 318 deletions(-) delete mode 100644 include/trace/boot.h delete mode 100644 kernel/trace/trace_boot.c (limited to 'include/trace') diff --git a/include/trace/boot.h b/include/trace/boot.h deleted file mode 100644 index 088ea089e31d..000000000000 --- a/include/trace/boot.h +++ /dev/null @@ -1,60 +0,0 @@ -#ifndef _LINUX_TRACE_BOOT_H -#define _LINUX_TRACE_BOOT_H - -#include -#include -#include - -/* - * 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/init/main.c b/init/main.c index 3bdb152f412f..94f65efdc65a 100644 --- a/init/main.c +++ b/init/main.c @@ -70,7 +70,6 @@ #include #include #include -#include #include #include @@ -715,38 +714,33 @@ 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 +754,7 @@ int do_one_initcall(initcall_t fn) printk("initcall %pF returned with %s\n", fn, msgbuf); } - return ret.result; + return ret; } @@ -880,7 +874,6 @@ 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/trace/Kconfig b/kernel/trace/Kconfig index 8b1797c4545b..572992abc71c 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 diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index ffb1a5b0550e..c3aaeba82372 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -38,7 +38,6 @@ 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 diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 55e48511d7c8..036fbc22858b 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4603,9 +4603,6 @@ __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 2cd96399463f..75a5e800a737 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -9,10 +9,8 @@ #include #include #include -#include #include #include - #include #include @@ -29,8 +27,6 @@ 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, @@ -48,8 +44,6 @@ enum kmemtrace_type_id { KMEMTRACE_TYPE_PAGES, /* __get_free_pages() and friends. */ }; -extern struct tracer boot_tracer; - #undef __field #define __field(type, item) type item; @@ -209,8 +203,6 @@ 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); \ diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c deleted file mode 100644 index c21d5f3956ad..000000000000 --- a/kernel/trace/trace_boot.c +++ /dev/null @@ -1,185 +0,0 @@ -/* - * ring buffer based initcalls tracer - * - * Copyright (C) 2008 Frederic Weisbecker - * - */ - -#include -#include -#include -#include -#include - -#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 dc008c1240da..c293364c984f 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 -- cgit v1.2.3 From c9642c49aae1272d7c24008a40ae614470b957a6 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 24 May 2010 16:22:30 +0800 Subject: tracing: Use a global field list for all syscall exit events All syscall exit events have the same fields. The kernel size drops 2.5K: text data bss dec hex filename 7018612 2034376 7251132 16304120 f8c7f8 vmlinux.o.orig 7018612 2031888 7251132 16301632 f8be40 vmlinux.o Signed-off-by: Li Zefan LKML-Reference: <4BFA3746.8070100@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/syscalls.h | 2 -- include/trace/syscall.h | 1 - kernel/trace/trace_syscalls.c | 7 ++++--- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/trace') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7f614ce274a9..7994bd44eb56 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -165,7 +165,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \ }; #define SYSCALL_DEFINE0(sname) \ @@ -180,7 +179,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ - .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \ }; \ asmlinkage long sys_##sname(void) #else diff --git a/include/trace/syscall.h b/include/trace/syscall.h index 257e08960d7b..31966a4fb8cc 100644 --- a/include/trace/syscall.h +++ b/include/trace/syscall.h @@ -26,7 +26,6 @@ struct syscall_metadata { const char **types; const char **args; struct list_head enter_fields; - struct list_head exit_fields; struct ftrace_event_call *enter_event; struct ftrace_event_call *exit_event; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 34e35804304b..bac752f0cfb5 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -23,6 +23,9 @@ static int syscall_exit_register(struct ftrace_event_call *event, static int syscall_enter_define_fields(struct ftrace_event_call *call); static int syscall_exit_define_fields(struct ftrace_event_call *call); +/* All syscall exit events have the same fields */ +static LIST_HEAD(syscall_exit_fields); + static struct list_head * syscall_get_enter_fields(struct ftrace_event_call *call) { @@ -34,9 +37,7 @@ syscall_get_enter_fields(struct ftrace_event_call *call) static struct list_head * syscall_get_exit_fields(struct ftrace_event_call *call) { - struct syscall_metadata *entry = call->data; - - return &entry->exit_fields; + return &syscall_exit_fields; } struct trace_event_functions enter_syscall_print_funcs = { -- cgit v1.2.3 From 363d0f6490f319d0dd69b7ec7503c5f6cbab36d9 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 24 May 2010 16:23:15 +0800 Subject: tracing: Convert some timer events to DEFINE_EVENT Use DECLARE_EVENT_CLASS, and save ~2.3K: text data bss dec hex filename 7018823 2031888 7251132 16301843 f8bf13 vmlinux.o.orig 7016727 2031696 7251132 16299555 f8b623 vmlinux.o 5 events are converted: timer_class: timer_init, timer_expire_exit, timer_cancel hrtimer_class: hrtimer_init, hrtimer_cancel No change in functionality. Signed-off-by: Li Zefan LKML-Reference: <4BFA3773.3060200@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/trace/events/timer.h | 80 ++++++++++++++++++-------------------------- 1 file changed, 32 insertions(+), 48 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 9496b965d62a..c624126a9c8a 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -8,11 +8,7 @@ #include #include -/** - * timer_init - called when the timer is initialized - * @timer: pointer to struct timer_list - */ -TRACE_EVENT(timer_init, +DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), @@ -29,6 +25,17 @@ TRACE_EVENT(timer_init, TP_printk("timer=%p", __entry->timer) ); +/** + * timer_init - called when the timer is initialized + * @timer: pointer to struct timer_list + */ +DEFINE_EVENT(timer_class, timer_init, + + TP_PROTO(struct timer_list *timer), + + TP_ARGS(timer) +); + /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list @@ -94,42 +101,22 @@ TRACE_EVENT(timer_expire_entry, * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ -TRACE_EVENT(timer_expire_exit, +DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), - TP_ARGS(timer), - - TP_STRUCT__entry( - __field(void *, timer ) - ), - - TP_fast_assign( - __entry->timer = timer; - ), - - TP_printk("timer=%p", __entry->timer) + TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ -TRACE_EVENT(timer_cancel, +DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), - TP_ARGS(timer), - - TP_STRUCT__entry( - __field( void *, timer ) - ), - - TP_fast_assign( - __entry->timer = timer; - ), - - TP_printk("timer=%p", __entry->timer) + TP_ARGS(timer) ); /** @@ -224,14 +211,7 @@ TRACE_EVENT(hrtimer_expire_entry, (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now })) ); -/** - * hrtimer_expire_exit - called immediately after the hrtimer callback returns - * @timer: pointer to struct hrtimer - * - * When used in combination with the hrtimer_expire_entry tracepoint we can - * determine the runtime of the callback function. - */ -TRACE_EVENT(hrtimer_expire_exit, +DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), @@ -249,24 +229,28 @@ TRACE_EVENT(hrtimer_expire_exit, ); /** - * hrtimer_cancel - called when the hrtimer is canceled - * @hrtimer: pointer to struct hrtimer + * hrtimer_expire_exit - called immediately after the hrtimer callback returns + * @timer: pointer to struct hrtimer + * + * When used in combination with the hrtimer_expire_entry tracepoint we can + * determine the runtime of the callback function. */ -TRACE_EVENT(hrtimer_cancel, +DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), - TP_ARGS(hrtimer), + TP_ARGS(hrtimer) +); - TP_STRUCT__entry( - __field( void *, hrtimer ) - ), +/** + * hrtimer_cancel - called when the hrtimer is canceled + * @hrtimer: pointer to struct hrtimer + */ +DEFINE_EVENT(hrtimer_class, hrtimer_cancel, - TP_fast_assign( - __entry->hrtimer = hrtimer; - ), + TP_PROTO(struct hrtimer *hrtimer), - TP_printk("hrtimer=%p", __entry->hrtimer) + TP_ARGS(hrtimer) ); /** -- cgit v1.2.3 From 210f766915207636acccba7bec42248bfe882998 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 24 May 2010 16:23:35 +0800 Subject: tracing: Convert more sched events to DEFINE_EVENT Convert sched_wait_task to DEFINE_EVENT, and save ~1K: text data bss dec hex filename 104595 9424 4992 119011 1d0e3 kernel/sched.o.orig 103619 9344 4992 117955 1ccc3 kernel/sched.o No change in functionality. Signed-off-by: Li Zefan LKML-Reference: <4BFA3787.2040800@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/trace/events/sched.h | 32 +++++++------------------------- 1 file changed, 7 insertions(+), 25 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index b9e1dd6c6208..9208c92aeab5 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -49,31 +49,6 @@ TRACE_EVENT(sched_kthread_stop_ret, TP_printk("ret=%d", __entry->ret) ); -/* - * Tracepoint for waiting on task to unschedule: - */ -TRACE_EVENT(sched_wait_task, - - TP_PROTO(struct task_struct *p), - - TP_ARGS(p), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN ) - __field( pid_t, pid ) - __field( int, prio ) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->prio = p->prio; - ), - - TP_printk("comm=%s pid=%d prio=%d", - __entry->comm, __entry->pid, __entry->prio) -); - /* * Tracepoint for waking up a task: */ @@ -239,6 +214,13 @@ DEFINE_EVENT(sched_process_template, sched_process_exit, TP_PROTO(struct task_struct *p), TP_ARGS(p)); +/* + * Tracepoint for waiting on task to unschedule: + */ +DEFINE_EVENT(sched_process_template, sched_wait_task, + TP_PROTO(struct task_struct *p), + TP_ARGS(p)); + /* * Tracepoint for a waiting task: */ -- cgit v1.2.3 From a1d0ce8213e9ddf4046ef5ba95c55762d075f541 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 8 Jun 2010 11:22:06 -0400 Subject: tracing: Use class->reg() for all registering of events Because kprobes and syscalls need special processing to register events, the class->reg() method was created to handle the differences. But instead of creating a default ->reg for perf and ftrace events, the code was scattered with: if (class->reg) class->reg(); else default_reg(); This is messy and can also lead to bugs. This patch cleans up this code and creates a default reg() entry for the events allowing for the code to directly call the class->reg() without the condition. Reported-by: Peter Zijlstra Acked-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 3 +++ include/trace/ftrace.h | 2 ++ kernel/trace/trace_event_perf.c | 19 +++----------- kernel/trace/trace_events.c | 55 +++++++++++++++++++++++++++-------------- 4 files changed, 44 insertions(+), 35 deletions(-) (limited to 'include/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0af31cd335d6..01df7ca4ead7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -146,6 +146,9 @@ struct ftrace_event_class { int (*raw_init)(struct ftrace_event_call *); }; +extern int ftrace_event_reg(struct ftrace_event_call *event, + enum trace_reg type); + enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index fc013a8201e9..55c1fd1bbc3d 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -439,6 +439,7 @@ static inline notrace int ftrace_get_offsets_##call( \ * .fields = LIST_HEAD_INIT(event_class_##call.fields), * .raw_init = trace_event_raw_init, * .probe = ftrace_raw_event_##call, + * .reg = ftrace_event_reg, * }; * * static struct ftrace_event_call __used @@ -567,6 +568,7 @@ static struct ftrace_event_class __used event_class_##call = { \ .fields = LIST_HEAD_INIT(event_class_##call.fields),\ .raw_init = trace_event_raw_init, \ .probe = ftrace_raw_event_##call, \ + .reg = ftrace_event_reg, \ _TRACE_PERF_INIT(call) \ }; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 6053982dc302..23751659582e 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -54,13 +54,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, } } - if (tp_event->class->reg) - ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); - else - ret = tracepoint_probe_register(tp_event->name, - tp_event->class->perf_probe, - tp_event); - + ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER); if (ret) goto fail; @@ -94,9 +88,7 @@ int perf_trace_init(struct perf_event *p_event) mutex_lock(&event_mutex); list_for_each_entry(tp_event, &ftrace_events, list) { if (tp_event->event.type == event_id && - tp_event->class && - (tp_event->class->perf_probe || - tp_event->class->reg) && + tp_event->class && tp_event->class->reg && try_module_get(tp_event->mod)) { ret = perf_trace_event_init(tp_event, p_event); break; @@ -136,12 +128,7 @@ void perf_trace_destroy(struct perf_event *p_event) if (--tp_event->perf_refcount > 0) goto out; - if (tp_event->class->reg) - tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); - else - tracepoint_probe_unregister(tp_event->name, - tp_event->class->perf_probe, - tp_event); + tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER); /* * Ensure our callback won't be called anymore. See diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 69bee4cc0e10..e8e6043f4d29 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -141,6 +141,35 @@ int trace_event_raw_init(struct ftrace_event_call *call) } EXPORT_SYMBOL_GPL(trace_event_raw_init); +int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type) +{ + switch (type) { + case TRACE_REG_REGISTER: + return tracepoint_probe_register(call->name, + call->class->probe, + call); + case TRACE_REG_UNREGISTER: + tracepoint_probe_unregister(call->name, + call->class->probe, + call); + return 0; + +#ifdef CONFIG_PERF_EVENTS + case TRACE_REG_PERF_REGISTER: + return tracepoint_probe_register(call->name, + call->class->perf_probe, + call); + case TRACE_REG_PERF_UNREGISTER: + tracepoint_probe_unregister(call->name, + call->class->perf_probe, + call); + return 0; +#endif + } + return 0; +} +EXPORT_SYMBOL_GPL(ftrace_event_reg); + static int ftrace_event_enable_disable(struct ftrace_event_call *call, int enable) { @@ -151,23 +180,13 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call, if (call->flags & TRACE_EVENT_FL_ENABLED) { call->flags &= ~TRACE_EVENT_FL_ENABLED; tracing_stop_cmdline_record(); - if (call->class->reg) - call->class->reg(call, TRACE_REG_UNREGISTER); - else - tracepoint_probe_unregister(call->name, - call->class->probe, - call); + call->class->reg(call, TRACE_REG_UNREGISTER); } break; case 1: if (!(call->flags & TRACE_EVENT_FL_ENABLED)) { tracing_start_cmdline_record(); - if (call->class->reg) - ret = call->class->reg(call, TRACE_REG_REGISTER); - else - ret = tracepoint_probe_register(call->name, - call->class->probe, - call); + ret = call->class->reg(call, TRACE_REG_REGISTER); if (ret) { tracing_stop_cmdline_record(); pr_info("event trace: Could not enable event " @@ -205,8 +224,7 @@ static int __ftrace_set_clr_event(const char *match, const char *sub, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->class || - (!call->class->probe && !call->class->reg)) + if (!call->name || !call->class || !call->class->reg) continue; if (match && @@ -332,7 +350,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && (call->class->probe || call->class->reg)) + if (call->class && call->class->reg) return call; } @@ -485,8 +503,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(call, &ftrace_events, list) { - if (!call->name || !call->class || - (!call->class->probe && !call->class->reg)) + if (!call->name || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system) != 0) @@ -977,12 +994,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return -1; } - if (call->class->probe || call->class->reg) + if (call->class->reg) trace_create_file("enable", 0644, call->dir, call, enable); #ifdef CONFIG_PERF_EVENTS - if (call->event.type && (call->class->perf_probe || call->class->reg)) + if (call->event.type && call->class->reg) trace_create_file("id", 0444, call->dir, call, id); #endif -- cgit v1.2.3 From 64166699752006f1a23a9cf7c96ae36654ccfc2c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:11 +0200 Subject: workqueue: temporarily remove workqueue tracing Strip tracing code from workqueue and remove workqueue tracing. This is temporary measure till concurrency managed workqueue is complete. Signed-off-by: Tejun Heo Cc: Frederic Weisbecker --- include/trace/events/workqueue.h | 92 ---------------------------------------- kernel/trace/Kconfig | 11 ----- kernel/workqueue.c | 14 ++---- 3 files changed, 3 insertions(+), 114 deletions(-) delete mode 100644 include/trace/events/workqueue.h (limited to 'include/trace') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h deleted file mode 100644 index d6c974474e70..000000000000 --- a/include/trace/events/workqueue.h +++ /dev/null @@ -1,92 +0,0 @@ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM workqueue - -#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_WORKQUEUE_H - -#include -#include -#include - -DECLARE_EVENT_CLASS(workqueue, - - TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), - - TP_ARGS(wq_thread, work), - - TP_STRUCT__entry( - __array(char, thread_comm, TASK_COMM_LEN) - __field(pid_t, thread_pid) - __field(work_func_t, func) - ), - - TP_fast_assign( - memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN); - __entry->thread_pid = wq_thread->pid; - __entry->func = work->func; - ), - - TP_printk("thread=%s:%d func=%pf", __entry->thread_comm, - __entry->thread_pid, __entry->func) -); - -DEFINE_EVENT(workqueue, workqueue_insertion, - - TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), - - TP_ARGS(wq_thread, work) -); - -DEFINE_EVENT(workqueue, workqueue_execution, - - TP_PROTO(struct task_struct *wq_thread, struct work_struct *work), - - TP_ARGS(wq_thread, work) -); - -/* Trace the creation of one workqueue thread on a cpu */ -TRACE_EVENT(workqueue_creation, - - TP_PROTO(struct task_struct *wq_thread, int cpu), - - TP_ARGS(wq_thread, cpu), - - TP_STRUCT__entry( - __array(char, thread_comm, TASK_COMM_LEN) - __field(pid_t, thread_pid) - __field(int, cpu) - ), - - TP_fast_assign( - memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN); - __entry->thread_pid = wq_thread->pid; - __entry->cpu = cpu; - ), - - TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm, - __entry->thread_pid, __entry->cpu) -); - -TRACE_EVENT(workqueue_destruction, - - TP_PROTO(struct task_struct *wq_thread), - - TP_ARGS(wq_thread), - - TP_STRUCT__entry( - __array(char, thread_comm, TASK_COMM_LEN) - __field(pid_t, thread_pid) - ), - - TP_fast_assign( - memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN); - __entry->thread_pid = wq_thread->pid; - ), - - TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid) -); - -#endif /* _TRACE_WORKQUEUE_H */ - -/* This part must be outside protection */ -#include diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8b1797c4545b..a0d95c1f3f82 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -391,17 +391,6 @@ config KMEMTRACE If unsure, say N. -config WORKQUEUE_TRACER - bool "Trace workqueues" - select GENERIC_TRACER - help - The workqueue tracer provides some statistical information - 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 has 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 BLK_DEV_IO_TRACE bool "Support for tracing block IO actions" depends on SYSFS diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8e3082b76c7f..f7ab703285a6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -33,8 +33,6 @@ #include #include #include -#define CREATE_TRACE_POINTS -#include /* * Structure fields follow one of the following exclusion rules. @@ -243,10 +241,10 @@ static inline void clear_wq_data(struct work_struct *work) atomic_long_set(&work->data, work_static(work)); } -static inline -struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) +static inline struct cpu_workqueue_struct *get_wq_data(struct work_struct *work) { - return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK); + return (void *)(atomic_long_read(&work->data) & + WORK_STRUCT_WQ_DATA_MASK); } /** @@ -265,8 +263,6 @@ static void insert_work(struct cpu_workqueue_struct *cwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { - trace_workqueue_insertion(cwq->thread, work); - /* we own @work, set data and link */ set_wq_data(work, cwq, extra_flags); @@ -431,7 +427,6 @@ static void process_one_work(struct cpu_workqueue_struct *cwq, struct lockdep_map lockdep_map = work->lockdep_map; #endif /* claim and process */ - trace_workqueue_execution(cwq->thread, work); debug_work_deactivate(work); cwq->current_work = work; list_del_init(&work->entry); @@ -1017,8 +1012,6 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) return PTR_ERR(p); cwq->thread = p; - trace_workqueue_creation(cwq->thread, cpu); - return 0; } @@ -1123,7 +1116,6 @@ 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; } -- cgit v1.2.3 From bc289ae98b75d93228d24f521ef02a076e506e94 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 3 Jun 2010 18:26:24 +0800 Subject: tracing: Reduce latency and remove percpu trace_seq __print_flags() and __print_symbolic() use percpu trace_seq: 1) Its memory is allocated at compile time, it wastes memory if we don't use tracing. 2) It is percpu data and it wastes more memory for multi-cpus system. 3) It disables preemption when it executes its core routine "trace_seq_printf(s, "%s: ", #call);" and introduces latency. So we move this trace_seq to struct trace_iterator. Signed-off-by: Lai Jiangshan LKML-Reference: <4C078350.7090106@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 5 +++-- include/trace/ftrace.h | 12 +++--------- kernel/trace/trace_output.c | 3 --- 3 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/trace') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 2b7b1395b4d5..02b8b24f8f51 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -11,8 +11,6 @@ struct trace_array; struct tracer; struct dentry; -DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq); - struct trace_print_flags { unsigned long mask; const char *name; @@ -58,6 +56,9 @@ struct trace_iterator { struct ring_buffer_iter *buffer_iter[NR_CPUS]; unsigned long iter_flags; + /* trace_seq for __print_flags() and __print_symbolic() etc. */ + struct trace_seq tmp_seq; + /* The below is zeroed out in pipe_read */ struct trace_seq seq; struct trace_entry *ent; diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 55c1fd1bbc3d..fb783d94fc54 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -145,7 +145,7 @@ * struct trace_seq *s = &iter->seq; * struct ftrace_raw_ *field; <-- defined in stage 1 * struct trace_entry *entry; - * struct trace_seq *p; + * struct trace_seq *p = &iter->tmp_seq; * int ret; * * entry = iter->ent; @@ -157,12 +157,10 @@ * * field = (typeof(field))entry; * - * p = &get_cpu_var(ftrace_event_seq); * trace_seq_init(p); * ret = trace_seq_printf(s, "%s: ", ); * if (ret) * ret = trace_seq_printf(s, "\n"); - * put_cpu(); * if (!ret) * return TRACE_TYPE_PARTIAL_LINE; * @@ -216,7 +214,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##call *field; \ struct trace_entry *entry; \ - struct trace_seq *p; \ + struct trace_seq *p = &iter->tmp_seq; \ int ret; \ \ event = container_of(trace_event, struct ftrace_event_call, \ @@ -231,12 +229,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ \ field = (typeof(field))entry; \ \ - p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ ret = trace_seq_printf(s, "%s: ", event->name); \ if (ret) \ ret = trace_seq_printf(s, print); \ - put_cpu(); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ @@ -255,7 +251,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ struct trace_seq *s = &iter->seq; \ struct ftrace_raw_##template *field; \ struct trace_entry *entry; \ - struct trace_seq *p; \ + struct trace_seq *p = &iter->tmp_seq; \ int ret; \ \ entry = iter->ent; \ @@ -267,12 +263,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \ \ field = (typeof(field))entry; \ \ - p = &get_cpu_var(ftrace_event_seq); \ trace_seq_init(p); \ ret = trace_seq_printf(s, "%s: ", #call); \ if (ret) \ ret = trace_seq_printf(s, print); \ - put_cpu(); \ if (!ret) \ return TRACE_TYPE_PARTIAL_LINE; \ \ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 57c1b4596470..1ba64d3cc567 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -16,9 +16,6 @@ DECLARE_RWSEM(trace_event_mutex); -DEFINE_PER_CPU(struct trace_seq, ftrace_event_seq); -EXPORT_PER_CPU_SYMBOL(ftrace_event_seq); - static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; static int next_event_type = __TRACE_LAST_TYPE + 1; -- cgit v1.2.3 From 4c21adf26f8fcf86a755b9b9f55c2e9fd241e1fb Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Tue, 20 Jul 2010 16:59:34 -0700 Subject: x86 cpufreq, perf: Make trace_power_frequency cpufreq driver independent and fix the broken case if a core's frequency depends on others. trace_power_frequency was only implemented in a rather ungeneric way in acpi-cpufreq driver's target() function only. -> Move the call to trace_power_frequency to cpufreq.c:cpufreq_notify_transition() where CPUFREQ_POSTCHANGE notifier is triggered. This will support power frequency tracing by all cpufreq drivers. trace_power_frequency did not trace frequency changes correctly when the userspace governor was used or when CPU cores' frequency depend on each other. -> Moving this into the CPUFREQ_POSTCHANGE notifier and pass the cpu which gets switched automatically fixes this. Robert Schoene provided some important fixes on top of my initial quick shot version which are integrated in this patch: - Forgot some changes in power_end trace (TP_printk/variable names) - Variable dummy in power_end must now be cpu_id - Use static 64 bit variable instead of unsigned int for cpu_id [akpm@linux-foundation.org: build fix] Signed-off-by: Thomas Renninger Cc: davej@codemonkey.org.uk Signed-off-by: Ingo Molnar Cc: Dave Jones Acked-by: Arjan van de Ven Cc: Robert Schoene Tested-by: Robert Schoene Signed-off-by: Andrew Morton --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 3 --- arch/x86/kernel/process.c | 8 ++++---- drivers/cpufreq/cpufreq.c | 3 +++ drivers/cpuidle/cpuidle.c | 2 +- drivers/idle/intel_idle.c | 2 +- include/trace/events/power.h | 27 +++++++++++++++------------ tools/perf/builtin-timechart.c | 11 ++++++----- 7 files changed, 30 insertions(+), 26 deletions(-) (limited to 'include/trace') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 1d3cddaa40ee..cee5263927c1 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include @@ -324,8 +323,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy, } } - trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency); - switch (data->cpu_feature) { case SYSTEM_INTEL_MSR_CAPABLE: cmd.type = SYSTEM_INTEL_MSR_CAPABLE; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e7e35219b32f..787572d43d9c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -371,7 +371,7 @@ static inline int hlt_use_halt(void) void default_idle(void) { if (hlt_use_halt()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -441,7 +441,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); */ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { - trace_power_start(POWER_CSTATE, (ax>>4)+1); + trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -457,7 +457,7 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx) static void mwait_idle(void) { if (!need_resched()) { - trace_power_start(POWER_CSTATE, 1); + trace_power_start(POWER_CSTATE, 1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -478,7 +478,7 @@ static void mwait_idle(void) */ static void poll_idle(void) { - trace_power_start(POWER_CSTATE, 0); + trace_power_start(POWER_CSTATE, 0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 063b2184caf5..4ed665725cc5 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -29,6 +29,8 @@ #include #include +#include + #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ "cpufreq-core", msg) @@ -354,6 +356,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) case CPUFREQ_POSTCHANGE: adjust_jiffies(CPUFREQ_POSTCHANGE, freqs); + trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu); srcu_notifier_call_chain(&cpufreq_transition_notifier_list, CPUFREQ_POSTCHANGE, freqs); if (likely(policy) && likely(policy->cpu == freqs->cpu)) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 199488576a05..dbefe15bd582 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -95,7 +95,7 @@ static void cpuidle_idle_call(void) /* give the governor an opportunity to reflect on the outcome */ if (cpuidle_curr_governor->reflect) cpuidle_curr_governor->reflect(dev); - trace_power_end(0); + trace_power_end(smp_processor_id()); } /** diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 54f0fb4cd5d2..03d202b1ff27 100755 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -231,7 +231,7 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state) stop_critical_timings(); #ifndef MODULE - trace_power_start(POWER_CSTATE, (eax >> 4) + 1); + trace_power_start(POWER_CSTATE, (eax >> 4) + 1, cpu); #endif if (!need_resched()) { diff --git a/include/trace/events/power.h b/include/trace/events/power.h index c4efe9b8280d..35a2a6e7bf1e 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -18,52 +18,55 @@ enum { DECLARE_EVENT_CLASS(power, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state), + TP_ARGS(type, state, cpu_id), TP_STRUCT__entry( __field( u64, type ) __field( u64, state ) + __field( u64, cpu_id ) ), TP_fast_assign( __entry->type = type; __entry->state = state; + __entry->cpu_id = cpu_id; ), - TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state) + TP_printk("type=%lu state=%lu cpu_id=%lu", (unsigned long)__entry->type, + (unsigned long)__entry->state, (unsigned long)__entry->cpu_id) ); DEFINE_EVENT(power, power_start, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state) + TP_ARGS(type, state, cpu_id) ); DEFINE_EVENT(power, power_frequency, - TP_PROTO(unsigned int type, unsigned int state), + TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id), - TP_ARGS(type, state) + TP_ARGS(type, state, cpu_id) ); TRACE_EVENT(power_end, - TP_PROTO(int dummy), + TP_PROTO(unsigned int cpu_id), - TP_ARGS(dummy), + TP_ARGS(cpu_id), TP_STRUCT__entry( - __field( u64, dummy ) + __field( u64, cpu_id ) ), TP_fast_assign( - __entry->dummy = 0xffff; + __entry->cpu_id = cpu_id; ), - TP_printk("dummy=%lu", (unsigned long)__entry->dummy) + TP_printk("cpu_id=%lu", (unsigned long)__entry->cpu_id) ); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 5a52ed9fc10b..5161619d4714 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -300,8 +300,9 @@ struct trace_entry { struct power_entry { struct trace_entry te; - s64 type; - s64 value; + u64 type; + u64 value; + u64 cpu_id; }; #define TASK_COMM_LEN 16 @@ -498,13 +499,13 @@ static int process_sample_event(event_t *event, struct perf_session *session) return 0; if (strcmp(event_str, "power:power_start") == 0) - c_state_start(data.cpu, data.time, pe->value); + c_state_start(pe->cpu_id, data.time, pe->value); if (strcmp(event_str, "power:power_end") == 0) - c_state_end(data.cpu, data.time); + c_state_end(pe->cpu_id, data.time); if (strcmp(event_str, "power:power_frequency") == 0) - p_state_change(data.cpu, data.time, pe->value); + p_state_change(pe->cpu_id, data.time, pe->value); if (strcmp(event_str, "sched:sched_wakeup") == 0) sched_wakeup(data.cpu, data.time, data.pid, te); -- cgit v1.2.3 From e5880d76aea443b04e07da19830da0f6f7494eef Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 27 Jul 2010 11:56:04 -0400 Subject: ext4: fix potential NULL dereference while tracing The allocation_context pointer can be NULL. Signed-off-by: "Theodore Ts'o" --- fs/ext4/mballoc.c | 4 ++-- include/trace/events/ext4.h | 20 ++++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include/trace') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3dfad95f0f98..8b3b9344a595 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3575,7 +3575,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, trace_ext4_mballoc_discard(ac); } - trace_ext4_mb_release_inode_pa(ac, pa, grp_blk_start + bit, + trace_ext4_mb_release_inode_pa(sb, ac, pa, grp_blk_start + bit, next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; @@ -3606,7 +3606,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ext4_group_t group; ext4_grpblk_t bit; - trace_ext4_mb_release_group_pa(ac, pa); + trace_ext4_mb_release_group_pa(sb, ac, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index f3865c7b4166..01e9e0076a92 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -395,11 +395,12 @@ DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, ); TRACE_EVENT(ext4_mb_release_inode_pa, - TP_PROTO(struct ext4_allocation_context *ac, + TP_PROTO(struct super_block *sb, + struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), - TP_ARGS(ac, pa, block, count), + TP_ARGS(sb, ac, pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) @@ -410,8 +411,9 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_fast_assign( - __entry->dev = ac->ac_sb->s_dev; - __entry->ino = ac->ac_inode->i_ino; + __entry->dev = sb->s_dev; + __entry->ino = (ac && ac->ac_inode) ? + ac->ac_inode->i_ino : 0; __entry->block = block; __entry->count = count; ), @@ -422,10 +424,11 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ); TRACE_EVENT(ext4_mb_release_group_pa, - TP_PROTO(struct ext4_allocation_context *ac, + TP_PROTO(struct super_block *sb, + struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), - TP_ARGS(ac, pa), + TP_ARGS(sb, ac, pa), TP_STRUCT__entry( __field( dev_t, dev ) @@ -436,8 +439,9 @@ TRACE_EVENT(ext4_mb_release_group_pa, ), TP_fast_assign( - __entry->dev = ac->ac_sb->s_dev; - __entry->ino = ac->ac_inode->i_ino; + __entry->dev = sb->s_dev; + __entry->ino = (ac && ac->ac_inode) ? + ac->ac_inode->i_ino : 0; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), -- cgit v1.2.3 From 819ce45afebd77a9de736fa5304ba8352d11dff9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 20 Jul 2010 18:41:24 +0200 Subject: tracing: Drop cpparg() macro Drop the cpparg() macro that wraps CPP parameters. We already have the PARAM() macro for that, no need to have several versions. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Steven Rostedt Cc: Li Zefan --- include/trace/ftrace.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/trace') diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index fb783d94fc54..a9377c0083ad 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -75,15 +75,12 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) -#undef __cpparg -#define __cpparg(arg...) arg - /* Callbacks are meaningless to ftrace. */ #undef TRACE_EVENT_FN #define TRACE_EVENT_FN(name, proto, args, tstruct, \ assign, print, reg, unreg) \ - TRACE_EVENT(name, __cpparg(proto), __cpparg(args), \ - __cpparg(tstruct), __cpparg(assign), __cpparg(print)) \ + TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \ + PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -- cgit v1.2.3 From 33659ebbae262228eef4e0fe990f393d1f0ed941 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:17:56 +0200 Subject: block: remove wrappers for request type/flags Remove all the trivial wrappers for the cmd_type and cmd_flags fields in struct requests. This allows much easier grepping for different request types instead of unwinding through macros. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-barrier.c | 7 ++-- block/blk-core.c | 13 ++++---- block/blk-exec.c | 2 +- block/blk-merge.c | 4 +-- block/blk.h | 6 ++-- block/cfq-iosched.c | 19 ++++++----- block/elevator.c | 16 +++++---- drivers/ata/libata-scsi.c | 2 +- drivers/block/cciss.c | 49 ++++++++++++++++----------- drivers/block/hd.c | 2 +- drivers/block/mg_disk.c | 4 +-- drivers/block/nbd.c | 2 +- drivers/block/osdblk.c | 3 +- drivers/block/paride/pd.c | 2 +- drivers/block/ps3disk.c | 2 +- drivers/block/ub.c | 8 ++--- drivers/block/viodasd.c | 2 +- drivers/block/virtio_blk.c | 15 +++++---- drivers/block/xd.c | 2 +- drivers/block/xen-blkfront.c | 4 +-- drivers/block/xsysace.c | 2 +- drivers/cdrom/gdrom.c | 2 +- drivers/cdrom/viocd.c | 2 +- drivers/ide/ide-atapi.c | 17 ++++++---- drivers/ide/ide-cd.c | 66 ++++++++++++++++++++----------------- drivers/ide/ide-disk.c | 2 +- drivers/ide/ide-eh.c | 5 +-- drivers/ide/ide-floppy.c | 25 +++++++++----- drivers/ide/ide-io.c | 8 ++--- drivers/ide/ide-pm.c | 8 ++--- drivers/ide/ide-tape.c | 3 +- drivers/md/dm.c | 10 +++--- drivers/memstick/core/mspro_block.c | 3 +- drivers/message/i2o/i2o_block.c | 2 +- drivers/mmc/card/queue.c | 2 +- drivers/mtd/mtd_blkdevs.c | 4 +-- drivers/scsi/scsi_error.c | 10 +++--- drivers/scsi/scsi_lib.c | 5 +-- drivers/scsi/sd.c | 12 +++---- drivers/scsi/sun3_NCR5380.c | 2 +- drivers/scsi/sun3_scsi.c | 2 +- drivers/scsi/sun3_scsi_vme.c | 2 +- drivers/staging/hv/blkvsc_drv.c | 8 +++-- include/linux/blkdev.h | 41 ++++++++--------------- include/linux/blktrace_api.h | 2 +- include/trace/events/block.h | 15 ++++++--- kernel/trace/blktrace.c | 10 +++--- 47 files changed, 236 insertions(+), 198 deletions(-) (limited to 'include/trace') diff --git a/block/blk-barrier.c b/block/blk-barrier.c index 0d710c9d403b..74e404393172 100644 --- a/block/blk-barrier.c +++ b/block/blk-barrier.c @@ -79,7 +79,7 @@ unsigned blk_ordered_req_seq(struct request *rq) * * http://thread.gmane.org/gmane.linux.kernel/537473 */ - if (!blk_fs_request(rq)) + if (rq->cmd_type != REQ_TYPE_FS) return QUEUE_ORDSEQ_DRAIN; if ((rq->cmd_flags & REQ_ORDERED_COLOR) == @@ -236,7 +236,8 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp) bool blk_do_ordered(struct request_queue *q, struct request **rqp) { struct request *rq = *rqp; - const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq); + const int is_barrier = rq->cmd_type == REQ_TYPE_FS && + (rq->cmd_flags & REQ_HARDBARRIER); if (!q->ordseq) { if (!is_barrier) @@ -261,7 +262,7 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp) */ /* Special requests are not subject to ordering rules. */ - if (!blk_fs_request(rq) && + if (rq->cmd_type != REQ_TYPE_FS && rq != &q->pre_flush_rq && rq != &q->post_flush_rq) return true; diff --git a/block/blk-core.c b/block/blk-core.c index b4131d29148c..dca43a31e725 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -184,7 +184,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg) printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n", rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq)); - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { printk(KERN_INFO " cdb: "); for (bit = 0; bit < BLK_MAX_CDB; bit++) printk("%02x ", rq->cmd[bit]); @@ -1796,7 +1796,7 @@ struct request *blk_peek_request(struct request_queue *q) * sees this request (possibly after * requeueing). Notify IO scheduler. */ - if (blk_sorted_rq(rq)) + if (rq->cmd_flags & REQ_SORTED) elv_activate_rq(q, rq); /* @@ -1984,10 +1984,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) * TODO: tj: This is too subtle. It would be better to let * low level drivers do what they see fit. */ - if (blk_fs_request(req)) + if (req->cmd_type == REQ_TYPE_FS) req->errors = 0; - if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) { + if (error && req->cmd_type == REQ_TYPE_FS && + !(req->cmd_flags & REQ_QUIET)) { printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n", req->rq_disk ? req->rq_disk->disk_name : "?", (unsigned long long)blk_rq_pos(req)); @@ -2074,7 +2075,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) req->buffer = bio_data(req->bio); /* update sector only for requests with clear definition of sector */ - if (blk_fs_request(req) || blk_discard_rq(req)) + if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ @@ -2127,7 +2128,7 @@ static void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); - if (unlikely(laptop_mode) && blk_fs_request(req)) + if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS) laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); diff --git a/block/blk-exec.c b/block/blk-exec.c index 49557e91f0da..e1672f14840e 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -57,7 +57,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, __elv_add_request(q, rq, where, 1); __generic_unplug_device(q); /* the queue is stopped so it won't be plugged+unplugged */ - if (blk_pm_resume_request(rq)) + if (rq->cmd_type == REQ_TYPE_PM_RESUME) q->request_fn(q); spin_unlock_irq(q->queue_lock); } diff --git a/block/blk-merge.c b/block/blk-merge.c index 5e7dc9973458..87e4fb7d0e98 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -226,7 +226,7 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req, { unsigned short max_sectors; - if (unlikely(blk_pc_request(req))) + if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC)) max_sectors = queue_max_hw_sectors(q); else max_sectors = queue_max_sectors(q); @@ -250,7 +250,7 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req, { unsigned short max_sectors; - if (unlikely(blk_pc_request(req))) + if (unlikely(req->cmd_type == REQ_TYPE_BLOCK_PC)) max_sectors = queue_max_hw_sectors(q); else max_sectors = queue_max_sectors(q); diff --git a/block/blk.h b/block/blk.h index 5ee3d7e72feb..6e7dc87141e4 100644 --- a/block/blk.h +++ b/block/blk.h @@ -161,8 +161,10 @@ static inline int blk_cpu_to_group(int cpu) */ static inline int blk_do_io_stat(struct request *rq) { - return rq->rq_disk && blk_rq_io_stat(rq) && - (blk_fs_request(rq) || blk_discard_rq(rq)); + return rq->rq_disk && + (rq->cmd_flags & REQ_IO_STAT) && + (rq->cmd_type == REQ_TYPE_FS || + (rq->cmd_flags & REQ_DISCARD)); } #endif diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 7982b830db58..d4edeb8fceb8 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -646,9 +646,10 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, return rq1; else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) return rq2; - if (rq_is_meta(rq1) && !rq_is_meta(rq2)) + if ((rq1->cmd_flags & REQ_RW_META) && !(rq2->cmd_flags & REQ_RW_META)) return rq1; - else if (rq_is_meta(rq2) && !rq_is_meta(rq1)) + else if ((rq2->cmd_flags & REQ_RW_META) && + !(rq1->cmd_flags & REQ_RW_META)) return rq2; s1 = blk_rq_pos(rq1); @@ -1484,7 +1485,7 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); - if (rq_is_meta(rq)) { + if (rq->cmd_flags & REQ_RW_META) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; } @@ -3176,7 +3177,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if (rq_is_meta(rq) && !cfqq->meta_pending) + if ((rq->cmd_flags & REQ_RW_META) && !cfqq->meta_pending) return true; /* @@ -3230,7 +3231,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; - if (rq_is_meta(rq)) + if (rq->cmd_flags & REQ_RW_META) cfqq->meta_pending++; cfq_update_io_thinktime(cfqd, cic); @@ -3365,7 +3366,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) unsigned long now; now = jiffies; - cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq)); + cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", + !!(rq->cmd_flags & REQ_NOIDLE)); cfq_update_hw_tag(cfqd); @@ -3419,11 +3421,12 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfq_slice_expired(cfqd, 1); else if (sync && cfqq_empty && !cfq_close_cooperator(cfqd, cfqq)) { - cfqd->noidle_tree_requires_idle |= !rq_noidle(rq); + cfqd->noidle_tree_requires_idle |= + !(rq->cmd_flags & REQ_NOIDLE); /* * Idling is enabled for SYNC_WORKLOAD. * SYNC_NOIDLE_WORKLOAD idles at the end of the tree - * only if we processed at least one !rq_noidle request + * only if we processed at least one !REQ_NOIDLE request */ if (cfqd->serving_type == SYNC_WORKLOAD || cfqd->noidle_tree_requires_idle diff --git a/block/elevator.c b/block/elevator.c index 923a9139106c..aa99b59c03d6 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -428,7 +428,8 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if (blk_discard_rq(rq) != blk_discard_rq(pos)) + if ((rq->cmd_flags & REQ_DISCARD) != + (pos->cmd_flags & REQ_DISCARD)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; @@ -558,7 +559,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if (blk_sorted_rq(rq)) + if (rq->cmd_flags & REQ_SORTED) elv_deactivate_rq(q, rq); } @@ -644,7 +645,8 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) break; case ELEVATOR_INSERT_SORT: - BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq)); + BUG_ON(rq->cmd_type != REQ_TYPE_FS && + !(rq->cmd_flags & REQ_DISCARD)); rq->cmd_flags |= REQ_SORTED; q->nr_sorted++; if (rq_mergeable(rq)) { @@ -716,7 +718,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where, /* * toggle ordered color */ - if (blk_barrier_rq(rq)) + if (rq->cmd_flags & REQ_HARDBARRIER) q->ordcolor ^= 1; /* @@ -729,7 +731,8 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where, * this request is scheduling boundary, update * end_sector */ - if (blk_fs_request(rq) || blk_discard_rq(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || + (rq->cmd_flags & REQ_DISCARD)) { q->end_sector = rq_end_sector(rq); q->boundary_rq = rq; } @@ -843,7 +846,8 @@ void elv_completed_request(struct request_queue *q, struct request *rq) */ if (blk_account_rq(rq)) { q->in_flight[rq_is_sync(rq)]--; - if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn) + if ((rq->cmd_flags & REQ_SORTED) && + e->ops->elevator_completed_req_fn) e->ops->elevator_completed_req_fn(q, rq); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index a54273d2c3c6..a5c08b082edb 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1111,7 +1111,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev) */ static int atapi_drain_needed(struct request *rq) { - if (likely(!blk_pc_request(rq))) + if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC)) return 0; if (!blk_rq_bytes(rq) || (rq->cmd_flags & REQ_RW)) diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 10a0268a1f92..11b377762b8e 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1783,7 +1783,7 @@ static void cciss_softirq_done(struct request *rq) #endif /* CCISS_DEBUG */ /* set the residual count for pc requests */ - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) rq->resid_len = cmd->err_info->ResidualCnt; blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO); @@ -2983,7 +2983,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, driver_byte = DRIVER_OK; msg_byte = cmd->err_info->CommandStatus; /* correct? seems too device specific */ - if (blk_pc_request(cmd->rq)) + if (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) host_byte = DID_PASSTHROUGH; else host_byte = DID_OK; @@ -2992,7 +2992,7 @@ static inline int evaluate_target_status(ctlr_info_t *h, host_byte, driver_byte); if (cmd->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION) { - if (!blk_pc_request(cmd->rq)) + if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) printk(KERN_WARNING "cciss: cmd %p " "has SCSI Status 0x%x\n", cmd, cmd->err_info->ScsiStatus); @@ -3002,15 +3002,17 @@ static inline int evaluate_target_status(ctlr_info_t *h, /* check the sense key */ sense_key = 0xf & cmd->err_info->SenseInfo[2]; /* no status or recovered error */ - if (((sense_key == 0x0) || (sense_key == 0x1)) && !blk_pc_request(cmd->rq)) + if (((sense_key == 0x0) || (sense_key == 0x1)) && + (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC)) error_value = 0; if (check_for_unit_attention(h, cmd)) { - *retry_cmd = !blk_pc_request(cmd->rq); + *retry_cmd = !(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC); return 0; } - if (!blk_pc_request(cmd->rq)) { /* Not SG_IO or similar? */ + /* Not SG_IO or similar? */ + if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) { if (error_value != 0) printk(KERN_WARNING "cciss: cmd %p has CHECK CONDITION" " sense key = 0x%x\n", cmd, sense_key); @@ -3052,7 +3054,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, rq->errors = evaluate_target_status(h, cmd, &retry_cmd); break; case CMD_DATA_UNDERRUN: - if (blk_fs_request(cmd->rq)) { + if (cmd->rq->cmd_type == REQ_TYPE_FS) { printk(KERN_WARNING "cciss: cmd %p has" " completed with data underrun " "reported\n", cmd); @@ -3060,7 +3062,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, } break; case CMD_DATA_OVERRUN: - if (blk_fs_request(cmd->rq)) + if (cmd->rq->cmd_type == REQ_TYPE_FS) printk(KERN_WARNING "cciss: cmd %p has" " completed with data overrun " "reported\n", cmd); @@ -3070,42 +3072,48 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "reported invalid\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_PROTOCOL_ERR: printk(KERN_WARNING "cciss: cmd %p has " "protocol error \n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_HARDWARE_ERR: printk(KERN_WARNING "cciss: cmd %p had " " hardware error\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_CONNECTION_LOST: printk(KERN_WARNING "cciss: cmd %p had " "connection lost\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_ABORTED: printk(KERN_WARNING "cciss: cmd %p was " "aborted\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ABORT); break; case CMD_ABORT_FAILED: printk(KERN_WARNING "cciss: cmd %p reports " "abort failed\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; case CMD_UNSOLICITED_ABORT: printk(KERN_WARNING "cciss%d: unsolicited " @@ -3121,13 +3129,15 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, "many times\n", h->ctlr, cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ABORT); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ABORT); break; case CMD_TIMEOUT: printk(KERN_WARNING "cciss: cmd %p timedout\n", cmd); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); break; default: printk(KERN_WARNING "cciss: cmd %p returned " @@ -3135,7 +3145,8 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd, cmd->err_info->CommandStatus); rq->errors = make_status_bytes(SAM_STAT_GOOD, cmd->err_info->CommandStatus, DRIVER_OK, - blk_pc_request(cmd->rq) ? DID_PASSTHROUGH : DID_ERROR); + (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + DID_PASSTHROUGH : DID_ERROR); } after_error_processing: @@ -3294,7 +3305,7 @@ static void do_cciss_request(struct request_queue *q) c->Header.SGList = h->max_cmd_sgentries; set_performant_mode(h, c); - if (likely(blk_fs_request(creq))) { + if (likely(creq->cmd_type == REQ_TYPE_FS)) { if(h->cciss_read == CCISS_READ_10) { c->Request.CDB[1] = 0; c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */ @@ -3324,7 +3335,7 @@ static void do_cciss_request(struct request_queue *q) c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff; c->Request.CDB[14] = c->Request.CDB[15] = 0; } - } else if (blk_pc_request(creq)) { + } else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) { c->Request.CDBLen = creq->cmd_len; memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB); } else { diff --git a/drivers/block/hd.c b/drivers/block/hd.c index 81c78b3ce2df..30ec6b37424e 100644 --- a/drivers/block/hd.c +++ b/drivers/block/hd.c @@ -627,7 +627,7 @@ repeat: req_data_dir(req) == READ ? "read" : "writ", cyl, head, sec, nsect, req->buffer); #endif - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { switch (rq_data_dir(req)) { case READ: hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ, diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c index 28db925dbdad..b82c5ce5e9df 100644 --- a/drivers/block/mg_disk.c +++ b/drivers/block/mg_disk.c @@ -670,7 +670,7 @@ static void mg_request_poll(struct request_queue *q) break; } - if (unlikely(!blk_fs_request(host->req))) { + if (unlikely(host->req->cmd_type != REQ_TYPE_FS)) { mg_end_request_cur(host, -EIO); continue; } @@ -756,7 +756,7 @@ static void mg_request(struct request_queue *q) continue; } - if (unlikely(!blk_fs_request(req))) { + if (unlikely(req->cmd_type != REQ_TYPE_FS)) { mg_end_request_cur(host, -EIO); continue; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 218d091f3c52..2e74e7d475ca 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -448,7 +448,7 @@ static void nbd_clear_que(struct nbd_device *lo) static void nbd_handle_req(struct nbd_device *lo, struct request *req) { - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) goto error_out; nbd_cmd(req) = NBD_CMD_READ; diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c index 6cd8b705b11b..819002ba3433 100644 --- a/drivers/block/osdblk.c +++ b/drivers/block/osdblk.c @@ -310,7 +310,8 @@ static void osdblk_rq_fn(struct request_queue *q) break; /* filter out block requests we don't understand */ - if (!blk_fs_request(rq) && !blk_barrier_rq(rq)) { + if (rq->cmd_type != REQ_TYPE_FS && + !(rq->cmd_flags & REQ_HARDBARRIER)) { blk_end_request_all(rq, 0); continue; } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index c1e5cd029b23..4e8b9bff3abe 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -439,7 +439,7 @@ static char *pd_buf; /* buffer for request in progress */ static enum action do_pd_io_start(void) { - if (blk_special_request(pd_req)) { + if (pd_req->cmd_type == REQ_TYPE_SPECIAL) { phase = pd_special; return pd_special(); } diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 3b419e3fffa1..5f208c0bf156 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -196,7 +196,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev, dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__); while ((req = blk_fetch_request(q))) { - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { if (ps3disk_submit_request_sg(dev, req)) break; } else if (req->cmd_type == REQ_TYPE_LINUX_BLOCK && diff --git a/drivers/block/ub.c b/drivers/block/ub.c index 0536b5b29adc..034b34440ffa 100644 --- a/drivers/block/ub.c +++ b/drivers/block/ub.c @@ -648,7 +648,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq) return 0; } - if (lun->changed && !blk_pc_request(rq)) { + if (lun->changed && rq->cmd_type != REQ_TYPE_BLOCK_PC) blk_start_request(rq); ub_end_rq(rq, SAM_STAT_CHECK_CONDITION); return 0; @@ -684,7 +684,7 @@ static int ub_request_fn_1(struct ub_lun *lun, struct request *rq) } urq->nsg = n_elem; - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { ub_cmd_build_packet(sc, lun, cmd, urq); } else { ub_cmd_build_block(sc, lun, cmd, urq); @@ -781,7 +781,7 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd) rq = urq->rq; if (cmd->error == 0) { - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { if (cmd->act_len >= rq->resid_len) rq->resid_len = 0; else @@ -795,7 +795,7 @@ static void ub_rw_cmd_done(struct ub_dev *sc, struct ub_scsi_cmd *cmd) } } } else { - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { /* UB_SENSE_SIZE is smaller than SCSI_SENSE_BUFFERSIZE */ memcpy(rq->sense, sc->top_sense, UB_SENSE_SIZE); rq->sense_len = UB_SENSE_SIZE; diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c index 788d93882ab9..5663d3c284c8 100644 --- a/drivers/block/viodasd.c +++ b/drivers/block/viodasd.c @@ -361,7 +361,7 @@ static void do_viodasd_request(struct request_queue *q) if (req == NULL) return; /* check that request contains a valid command */ - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { viodasd_end_request(req, -EIO, blk_rq_sectors(req)); continue; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 258bc2ae2885..774144334ece 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -65,13 +65,16 @@ static void blk_done(struct virtqueue *vq) break; } - if (blk_pc_request(vbr->req)) { + switch (vbr->req->cmd_type) { + case REQ_TYPE_BLOCK_PC: vbr->req->resid_len = vbr->in_hdr.residual; vbr->req->sense_len = vbr->in_hdr.sense_len; vbr->req->errors = vbr->in_hdr.errors; - } - if (blk_special_request(vbr->req)) + break; + case REQ_TYPE_SPECIAL: vbr->req->errors = (error != 0); + break; + } __blk_end_request_all(vbr->req, error); list_del(&vbr->list); @@ -123,7 +126,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, BUG(); } - if (blk_barrier_rq(vbr->req)) + if (vbr->req->cmd_flags & REQ_HARDBARRIER) vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER; sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr)); @@ -134,12 +137,12 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk, * block, and before the normal inhdr we put the sense data and the * inhdr with additional status information before the normal inhdr. */ - if (blk_pc_request(vbr->req)) + if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) sg_set_buf(&vblk->sg[out++], vbr->req->cmd, vbr->req->cmd_len); num = blk_rq_map_sg(q, vbr->req, vblk->sg + out); - if (blk_pc_request(vbr->req)) { + if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) { sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96); sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr, sizeof(vbr->in_hdr)); diff --git a/drivers/block/xd.c b/drivers/block/xd.c index 18a80ff57ce8..4dc298376098 100644 --- a/drivers/block/xd.c +++ b/drivers/block/xd.c @@ -322,7 +322,7 @@ static void do_xd_request (struct request_queue * q) int res = -EIO; int retry; - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) { goto done; if (block + count > get_capacity(req->rq_disk)) goto done; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 82ed403147c0..495533e66542 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -238,7 +238,7 @@ static int blkif_queue_request(struct request *req) ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (blk_barrier_rq(req)) + if (req->cmd_flags & REQ_HARDBARRIER) ring_req->operation = BLKIF_OP_WRITE_BARRIER; ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg); @@ -309,7 +309,7 @@ static void do_blkif_request(struct request_queue *rq) blk_start_request(req); - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { __blk_end_request_all(req, -EIO); continue; } diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index a7b83c0a7eb5..ac278ac908d5 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -465,7 +465,7 @@ struct request *ace_get_next_request(struct request_queue * q) struct request *req; while ((req = blk_peek_request(q)) != NULL) { - if (blk_fs_request(req)) + if (req->cmd_type == REQ_TYPE_FS) break; blk_start_request(req); __blk_end_request_all(req, -EIO); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 03c71f7698cb..7c05ddc63ae8 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -643,7 +643,7 @@ static void gdrom_request(struct request_queue *rq) struct request *req; while ((req = blk_fetch_request(rq)) != NULL) { - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { printk(KERN_DEBUG "GDROM: Non-fs request ignored\n"); __blk_end_request_all(req, -EIO); continue; diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c index 451cd7071b1d..14e420168764 100644 --- a/drivers/cdrom/viocd.c +++ b/drivers/cdrom/viocd.c @@ -298,7 +298,7 @@ static void do_viocd_request(struct request_queue *q) struct request *req; while ((rwreq == 0) && ((req = blk_fetch_request(q)) != NULL)) { - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) __blk_end_request_all(req, -EIO); else if (send_request(req) < 0) { printk(VIOCD_KERN_WARNING diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index f9daffd7d0e3..3117a894d20e 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -190,7 +190,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq) BUG_ON(sense_len > sizeof(*sense)); - if (blk_sense_request(rq) || drive->sense_rq_armed) + if (rq->cmd_type == REQ_TYPE_SENSE || drive->sense_rq_armed) return; memset(sense, 0, sizeof(*sense)); @@ -307,13 +307,16 @@ EXPORT_SYMBOL_GPL(ide_cd_expiry); int ide_cd_get_xferlen(struct request *rq) { - if (blk_fs_request(rq)) + switch (rq->cmd_type) + case REQ_TYPE_FS: return 32768; - else if (blk_sense_request(rq) || blk_pc_request(rq) || - rq->cmd_type == REQ_TYPE_ATA_PC) + case REQ_TYPE_SENSE: + case REQ_TYPE_BLOCK_PC: + case REQ_TYPE_ATA_PC: return blk_rq_bytes(rq); - else + default: return 0; + } } EXPORT_SYMBOL_GPL(ide_cd_get_xferlen); @@ -474,12 +477,12 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive) if (uptodate == 0) drive->failed_pc = NULL; - if (blk_special_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SPECIAL) rq->errors = 0; error = 0; } else { - if (blk_fs_request(rq) == 0 && uptodate <= 0) { + if (req->cmd_type != REQ_TYPE_FS && uptodate <= 0) { if (rq->errors == 0) rq->errors = -EIO; } diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 64207df8da82..26a3688de467 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -176,7 +176,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive, if (!sense->valid) break; if (failed_command == NULL || - !blk_fs_request(failed_command)) + failed_command->cmd_type != REQ_TYPE_FS) break; sector = (sense->information[0] << 24) | (sense->information[1] << 16) | @@ -292,7 +292,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) "stat 0x%x", rq->cmd[0], rq->cmd_type, err, stat); - if (blk_sense_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SENSE) { /* * We got an error trying to get sense info from the drive * (probably while trying to recover from a former error). @@ -303,7 +303,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) } /* if we have an error, pass CHECK_CONDITION as the SCSI status byte */ - if (blk_pc_request(rq) && !rq->errors) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !rq->errors) rq->errors = SAM_STAT_CHECK_CONDITION; if (blk_noretry_request(rq)) @@ -311,13 +311,14 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) switch (sense_key) { case NOT_READY: - if (blk_fs_request(rq) && rq_data_dir(rq) == WRITE) { + if (rq->cmd_type == REQ_TYPE_FS && rq_data_dir(rq) == WRITE) { if (ide_cd_breathe(drive, rq)) return 1; } else { cdrom_saw_media_change(drive); - if (blk_fs_request(rq) && !blk_rq_quiet(rq)) + if (rq->cmd_type == REQ_TYPE_FS && + !(rq->cmd_flags & REQ_QUIET)) { printk(KERN_ERR PFX "%s: tray open\n", drive->name); } @@ -326,7 +327,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) case UNIT_ATTENTION: cdrom_saw_media_change(drive); - if (blk_fs_request(rq) == 0) + if (rq->cmd_type != REQ_TYPE_FS) return 0; /* @@ -352,7 +353,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in retrying after an illegal request or data * protect error. */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "command error", stat); do_end_request = 1; break; @@ -361,20 +362,20 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) * No point in re-trying a zillion times on a bad sector. * If we got here the error is not correctable. */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "media error " "(bad sector)", stat); do_end_request = 1; break; case BLANK_CHECK: /* disk appears blank? */ - if (!blk_rq_quiet(rq)) + if (!(rq->cmd_flags & REQ_QUIET)) ide_dump_status(drive, "media error (blank)", stat); do_end_request = 1; break; default: - if (blk_fs_request(rq) == 0) + if (req->cmd_type != REQ_TYPE_FS) break; if (err & ~ATA_ABORTED) { /* go to the default handler for other errors */ @@ -385,7 +386,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat) do_end_request = 1; } - if (blk_fs_request(rq) == 0) { + if (rq->cmd_type != REQ_TYPE_FS) { rq->cmd_flags |= REQ_FAILED; do_end_request = 1; } @@ -525,7 +526,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) ide_expiry_t *expiry = NULL; int dma_error = 0, dma, thislen, uptodate = 0; int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0; - int sense = blk_sense_request(rq); + int sense = (rq->cmd_type == REQ_TYPE_SENSE); unsigned int timeout; u16 len; u8 ireason, stat; @@ -568,7 +569,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) ide_read_bcount_and_ireason(drive, &len, &ireason); - thislen = blk_fs_request(rq) ? len : cmd->nleft; + thislen = (rq->cmd_type == REQ_TYPE_FS) ? len : cmd->nleft; if (thislen > len) thislen = len; @@ -577,7 +578,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* If DRQ is clear, the command has completed. */ if ((stat & ATA_DRQ) == 0) { - if (blk_fs_request(rq)) { + if (rq->cmd_type == REQ_TYPE_FS) { /* * If we're not done reading/writing, complain. * Otherwise, complete the command normally. @@ -591,7 +592,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) rq->cmd_flags |= REQ_FAILED; uptodate = 0; } - } else if (!blk_pc_request(rq)) { + } else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { ide_cd_request_sense_fixup(drive, cmd); uptodate = cmd->nleft ? 0 : 1; @@ -640,7 +641,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) /* pad, if necessary */ if (len > 0) { - if (blk_fs_request(rq) == 0 || write == 0) + if (rq->cmd_type != REQ_TYPE_FS || write == 0) ide_pad_transfer(drive, write, len); else { printk(KERN_ERR PFX "%s: confused, missing data\n", @@ -649,11 +650,11 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) } } - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { timeout = rq->timeout; } else { timeout = ATAPI_WAIT_PC; - if (!blk_fs_request(rq)) + if (rq->cmd_type != REQ_TYPE_FS) expiry = ide_cd_expiry; } @@ -662,7 +663,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive) return ide_started; out_end: - if (blk_pc_request(rq) && rc == 0) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) { rq->resid_len = 0; blk_end_request_all(rq, 0); hwif->rq = NULL; @@ -670,7 +671,7 @@ out_end: if (sense && uptodate) ide_cd_complete_failed_rq(drive, rq); - if (blk_fs_request(rq)) { + if (rq->cmd_type == REQ_TYPE_FS) { if (cmd->nleft == 0) uptodate = 1; } else { @@ -682,7 +683,7 @@ out_end: ide_cd_error_cmd(drive, cmd); /* make sure it's fully ended */ - if (blk_fs_request(rq) == 0) { + if (rq->cmd_type != REQ_TYPE_FS) { rq->resid_len -= cmd->nbytes - cmd->nleft; if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE)) rq->resid_len += cmd->last_xfer_len; @@ -742,7 +743,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq) ide_debug_log(IDE_DBG_PC, "rq->cmd[0]: 0x%x, rq->cmd_type: 0x%x", rq->cmd[0], rq->cmd_type); - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) rq->cmd_flags |= REQ_QUIET; else rq->cmd_flags &= ~REQ_FAILED; @@ -783,21 +784,26 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, if (drive->debug_mask & IDE_DBG_RQ) blk_dump_rq_flags(rq, "ide_cd_do_request"); - if (blk_fs_request(rq)) { + switch (rq->cmd_type) { + case REQ_TYPE_FS: if (cdrom_start_rw(drive, rq) == ide_stopped) goto out_end; - } else if (blk_sense_request(rq) || blk_pc_request(rq) || - rq->cmd_type == REQ_TYPE_ATA_PC) { + break; + case REQ_TYPE_SENSE: + case REQ_TYPE_BLOCK_PC: + case REQ_TYPE_ATA_PC: if (!rq->timeout) rq->timeout = ATAPI_WAIT_PC; cdrom_do_block_pc(drive, rq); - } else if (blk_special_request(rq)) { + break; + case REQ_TYPE_SPECIAL: /* right now this can only be a reset... */ uptodate = 1; goto out_end; - } else + default: BUG(); + } /* prepare sense request for this command */ ide_prep_sense(drive, rq); @@ -809,7 +815,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq, cmd.rq = rq; - if (blk_fs_request(rq) || blk_rq_bytes(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -1365,9 +1371,9 @@ static int ide_cdrom_prep_pc(struct request *rq) static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq) { - if (blk_fs_request(rq)) + if (rq->cmd_type == REQ_TYPE_FS) return ide_cdrom_prep_fs(q, rq); - else if (blk_pc_request(rq)) + else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) return ide_cdrom_prep_pc(rq); return 0; diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index 33d65039cce9..df3d91ba1c96 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -184,7 +184,7 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq, ide_hwif_t *hwif = drive->hwif; BUG_ON(drive->dev_flags & IDE_DFLAG_BLOCKED); - BUG_ON(!blk_fs_request(rq)); + BUG_ON(rq->cmd_type != REQ_TYPE_FS); ledtrig_ide_activity(); diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c index e9abf2c3c335..c0aa93fb7a60 100644 --- a/drivers/ide/ide-eh.c +++ b/drivers/ide/ide-eh.c @@ -122,7 +122,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat) return ide_stopped; /* retry only "normal" I/O: */ - if (!blk_fs_request(rq)) { + if (rq->cmd_type != REQ_TYPE_FS) { if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) { struct ide_cmd *cmd = rq->special; @@ -146,7 +146,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err) { struct request *rq = drive->hwif->rq; - if (rq && blk_special_request(rq) && rq->cmd[0] == REQ_DRIVE_RESET) { + if (rq && rq->cmd_type == REQ_TYPE_SPECIAL && + rq->cmd[0] == REQ_DRIVE_RESET) { if (err <= 0 && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq)); diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c index 4713bdca20b6..c7d0737bb18a 100644 --- a/drivers/ide/ide-floppy.c +++ b/drivers/ide/ide-floppy.c @@ -73,7 +73,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc) drive->failed_pc = NULL; if (pc->c[0] == GPCMD_READ_10 || pc->c[0] == GPCMD_WRITE_10 || - (rq && blk_pc_request(rq))) + (rq && rq->cmd_type == REQ_TYPE_BLOCK_PC)) uptodate = 1; /* FIXME */ else if (pc->c[0] == GPCMD_REQUEST_SENSE) { @@ -98,7 +98,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc) "Aborting request!\n"); } - if (blk_special_request(rq)) + if (rq->cmd_type == REQ_TYPE_SPECIAL) rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL; return uptodate; @@ -247,14 +247,16 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, } else printk(KERN_ERR PFX "%s: I/O error\n", drive->name); - if (blk_special_request(rq)) { + if (rq->cmd_type == REQ_TYPE_SPECIAL) { rq->errors = 0; ide_complete_rq(drive, 0, blk_rq_bytes(rq)); return ide_stopped; } else goto out_end; } - if (blk_fs_request(rq)) { + + switch (rq->cmd_type) { + case REQ_TYPE_FS: if (((long)blk_rq_pos(rq) % floppy->bs_factor) || (blk_rq_sectors(rq) % floppy->bs_factor)) { printk(KERN_ERR PFX "%s: unsupported r/w rq size\n", @@ -263,13 +265,18 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, } pc = &floppy->queued_pc; idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block); - } else if (blk_special_request(rq) || blk_sense_request(rq)) { + break; + case REQ_TYPE_SPECIAL: + case REQ_TYPE_SENSE: pc = (struct ide_atapi_pc *)rq->special; - } else if (blk_pc_request(rq)) { + break; + case REQ_TYPE_BLOCK_PC: pc = &floppy->queued_pc; idefloppy_blockpc_cmd(floppy, pc, rq); - } else + break; + default: BUG(); + } ide_prep_sense(drive, rq); @@ -280,7 +287,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, cmd.rq = rq; - if (blk_fs_request(rq) || blk_rq_bytes(rq)) { + if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) { ide_init_sg_cmd(&cmd, blk_rq_bytes(rq)); ide_map_sg(drive, &cmd); } @@ -290,7 +297,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, return ide_floppy_issue_pc(drive, &cmd, pc); out_end: drive->failed_pc = NULL; - if (blk_fs_request(rq) == 0 && rq->errors == 0) + if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) rq->errors = -EIO; ide_complete_rq(drive, -EIO, blk_rq_bytes(rq)); return ide_stopped; diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 172ac9218154..9304a7e54d9e 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq); void ide_kill_rq(ide_drive_t *drive, struct request *rq) { - u8 drv_req = blk_special_request(rq) && rq->rq_disk; + u8 drv_req = (rq->cmd_type == REQ_TYPE_SPECIAL) && rq->rq_disk; u8 media = drive->media; drive->failed_pc = NULL; @@ -145,7 +145,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq) } else { if (media == ide_tape) rq->errors = IDE_DRV_ERROR_GENERAL; - else if (blk_fs_request(rq) == 0 && rq->errors == 0) + else if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0) rq->errors = -EIO; } @@ -307,7 +307,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) { ide_startstop_t startstop; - BUG_ON(!blk_rq_started(rq)); + BUG_ON(!(rq->cmd_flags & REQ_STARTED)); #ifdef DEBUG printk("%s: start_request: current=0x%08lx\n", @@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq) pm->pm_step == IDE_PM_COMPLETED) ide_complete_pm_rq(drive, rq); return startstop; - } else if (!rq->rq_disk && blk_special_request(rq)) + } else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_SPECIAL) { /* * TODO: Once all ULDs have been modified to * check for specific op codes rather than diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 1c08311b0a0e..92406097efeb 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -191,10 +191,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq) #ifdef DEBUG_PM printk("%s: completing PM request, %s\n", drive->name, - blk_pm_suspend_request(rq) ? "suspend" : "resume"); + (rq->cmd_type == REQ_TYPE_PM_SUSPEND) ? "suspend" : "resume"); #endif spin_lock_irqsave(q->queue_lock, flags); - if (blk_pm_suspend_request(rq)) + if (rq->cmd_type == REQ_TYPE_PM_SUSPEND) blk_stop_queue(q); else drive->dev_flags &= ~IDE_DFLAG_BLOCKED; @@ -210,11 +210,11 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq) { struct request_pm_state *pm = rq->special; - if (blk_pm_suspend_request(rq) && + if (rq->cmd_type == REQ_TYPE_PM_SUSPEND && pm->pm_step == IDE_PM_START_SUSPEND) /* Mark drive blocked when starting the suspend sequence. */ drive->dev_flags |= IDE_DFLAG_BLOCKED; - else if (blk_pm_resume_request(rq) && + else if (rq->cmd_type == REQ_TYPE_PM_RESUME && pm->pm_step == IDE_PM_START_RESUME) { /* * The first thing we do on wakeup is to wait for BSY bit to diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index b07232880ec9..635fd72d4728 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -577,7 +577,8 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive, rq->cmd[0], (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq)); - BUG_ON(!(blk_special_request(rq) || blk_sense_request(rq))); + BUG_ON(!(rq->cmd_type == REQ_TYPE_SPECIAL || + rq->cmd_type == REQ_TYPE_SENSE)); /* Retry a failed packet command */ if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d21e1284604f..1e0e6dd51501 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -792,12 +792,12 @@ static void dm_end_request(struct request *clone, int error) { int rw = rq_data_dir(clone); int run_queue = 1; - bool is_barrier = blk_barrier_rq(clone); + bool is_barrier = clone->cmd_flags & REQ_HARDBARRIER; struct dm_rq_target_io *tio = clone->end_io_data; struct mapped_device *md = tio->md; struct request *rq = tio->orig; - if (blk_pc_request(rq) && !is_barrier) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !is_barrier) { rq->errors = clone->errors; rq->resid_len = clone->resid_len; @@ -844,7 +844,7 @@ void dm_requeue_unmapped_request(struct request *clone) struct request_queue *q = rq->q; unsigned long flags; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special @@ -943,7 +943,7 @@ static void dm_complete_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. So can't use * softirq_done with the original. @@ -972,7 +972,7 @@ void dm_kill_unmapped_request(struct request *clone, int error) struct dm_rq_target_io *tio = clone->end_io_data; struct request *rq = tio->orig; - if (unlikely(blk_barrier_rq(clone))) { + if (unlikely(clone->cmd_flags & REQ_HARDBARRIER)) { /* * Barrier clones share an original request. * Leave it to dm_end_request(), which handles this special diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index 8327e248520a..56645408d225 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -805,7 +805,8 @@ static void mspro_block_start(struct memstick_dev *card) static int mspro_block_prepare_req(struct request_queue *q, struct request *req) { - if (!blk_fs_request(req) && !blk_pc_request(req)) { + if (req->cmd_type != REQ_TYPE_FS && + req->cmd_type != REQ_TYPE_BLOCK_PC) { blk_dump_rq_flags(req, "MSPro unsupported request"); return BLKPREP_KILL; } diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c index fc593fbab696..108f0c2b2bfd 100644 --- a/drivers/message/i2o/i2o_block.c +++ b/drivers/message/i2o/i2o_block.c @@ -883,7 +883,7 @@ static void i2o_block_request_fn(struct request_queue *q) if (!req) break; - if (blk_fs_request(req)) { + if (req->cmd_type == REQ_TYPE_FS) { struct i2o_block_delayed_request *dreq; struct i2o_block_request *ireq = req->special; unsigned int queue_depth; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index d6ded247d941..ec92bcbdeddb 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -32,7 +32,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests. */ - if (!blk_fs_request(req)) { + if (req->cmd_type != REQ_TYPE_FS) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 03e19c1965cc..475af42745cb 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -73,14 +73,14 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr, buf = req->buffer; - if (!blk_fs_request(req)) + if (req->cmd_type != REQ_TYPE_FS) return -EIO; if (blk_rq_pos(req) + blk_rq_cur_sectors(req) > get_capacity(req->rq_disk)) return -EIO; - if (blk_discard_rq(req)) + if (req->cmd_flags & REQ_DISCARD) return tr->discard(dev, block, nsect); switch(rq_data_dir(req)) { diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a5d630f5f519..1b88af89d0c7 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -307,7 +307,7 @@ static int scsi_check_sense(struct scsi_cmnd *scmd) (sshdr.asc == 0x04) && (sshdr.ascq == 0x02)) return FAILED; - if (blk_barrier_rq(scmd->request)) + if (scmd->request->cmd_flags & REQ_HARDBARRIER) /* * barrier requests should always retry on UA * otherwise block will get a spurious error @@ -1318,16 +1318,16 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd) case DID_OK: break; case DID_BUS_BUSY: - return blk_failfast_transport(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_TRANSPORT); case DID_PARITY: - return blk_failfast_dev(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DEV); case DID_ERROR: if (msg_byte(scmd->result) == COMMAND_COMPLETE && status_byte(scmd->result) == RESERVATION_CONFLICT) return 0; /* fall through */ case DID_SOFT_ERROR: - return blk_failfast_driver(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DRIVER); } switch (status_byte(scmd->result)) { @@ -1336,7 +1336,7 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd) * assume caller has checked sense and determinted * the check condition was retryable. */ - return blk_failfast_dev(scmd->request); + return (scmd->request->cmd_flags & REQ_FAILFAST_DEV); } return 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 1646fe7cbd4b..5f1160841b0e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -722,7 +722,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) sense_deferred = scsi_sense_is_deferred(&sshdr); } - if (blk_pc_request(req)) { /* SG_IO ioctl from block level */ + if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */ req->errors = result; if (result) { if (sense_valid && req->sense) { @@ -757,7 +757,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) } } - BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */ + /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ + BUG_ON(blk_bidi_rq(req)); /* * Next deal with any sectors which we were able to correctly diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 8802e48bc063..a3fdf4dc59da 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -485,7 +485,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * Discard request come in as REQ_TYPE_FS but we turn them into * block PC requests to make life easier. */ - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) ret = sd_prepare_discard(rq); if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { @@ -636,7 +636,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD; SCpnt->cmnd[7] = 0x18; SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32; - SCpnt->cmnd[10] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[10] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); /* LBA */ SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; @@ -661,7 +661,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[31] = (unsigned char) this_count & 0xff; } else if (block > 0xffffffff) { SCpnt->cmnd[0] += READ_16 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0; SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0; @@ -682,7 +682,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) this_count = 0xffff; SCpnt->cmnd[0] += READ_10 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff; SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff; SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff; @@ -691,7 +691,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff; SCpnt->cmnd[8] = (unsigned char) this_count & 0xff; } else { - if (unlikely(blk_fua_rq(rq))) { + if (unlikely(rq->cmd_flags & REQ_FUA)) { /* * This happens only if this drive failed * 10byte rw command with ILLEGAL_REQUEST @@ -1112,7 +1112,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) u64 bad_lba; int info_valid; - if (!blk_fs_request(scmd->request)) + if (scmd->request->cmd_type != REQ_TYPE_FS) return 0; info_valid = scsi_get_sense_info_fld(scmd->sense_buffer, diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c index b5838d547c68..713620ed70d9 100644 --- a/drivers/scsi/sun3_NCR5380.c +++ b/drivers/scsi/sun3_NCR5380.c @@ -2022,7 +2022,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance) if((count > SUN3_DMA_MINSIZE) && (sun3_dma_setup_done != cmd)) { - if(blk_fs_request(cmd->request)) { + if (cmd->request->cmd_type == REQ_TYPE_FS) { sun3scsi_dma_setup(d, count, rq_data_dir(cmd->request)); sun3_dma_setup_done = cmd; diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c index e606cf0a2eb7..613f5880d135 100644 --- a/drivers/scsi/sun3_scsi.c +++ b/drivers/scsi/sun3_scsi.c @@ -524,7 +524,7 @@ static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted, struct scsi_cmnd *cmd, int write_flag) { - if(blk_fs_request(cmd->request)) + if (cmd->request->cmd_type == REQ_TYPE_FS) return wanted; else return 0; diff --git a/drivers/scsi/sun3_scsi_vme.c b/drivers/scsi/sun3_scsi_vme.c index aaa4fd0dd1b9..7c526b8e30ac 100644 --- a/drivers/scsi/sun3_scsi_vme.c +++ b/drivers/scsi/sun3_scsi_vme.c @@ -458,7 +458,7 @@ static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted, struct scsi_cmnd *cmd, int write_flag) { - if(blk_fs_request(cmd->request)) + if (cmd->request->cmd_type == REQ_TYPE_FS) return wanted; else return 0; diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index 61bd0be5fb18..a9aff90e58e0 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -823,7 +823,8 @@ static void blkvsc_init_rw(struct blkvsc_request *blkvsc_req) blkvsc_req->cmnd[0] = READ_16; } - blkvsc_req->cmnd[1] |= blk_fua_rq(blkvsc_req->req) ? 0x8 : 0; + blkvsc_req->cmnd[1] |= + (blkvsc_req->req->cmd_flags & REQ_FUA) ? 0x8 : 0; *(unsigned long long *)&blkvsc_req->cmnd[2] = cpu_to_be64(blkvsc_req->sector_start); @@ -839,7 +840,8 @@ static void blkvsc_init_rw(struct blkvsc_request *blkvsc_req) blkvsc_req->cmnd[0] = READ_10; } - blkvsc_req->cmnd[1] |= blk_fua_rq(blkvsc_req->req) ? 0x8 : 0; + blkvsc_req->cmnd[1] |= + (blkvsc_req->req->cmd_flags & REQ_FUA) ? 0x8 : 0; *(unsigned int *)&blkvsc_req->cmnd[2] = cpu_to_be32(blkvsc_req->sector_start); @@ -1286,7 +1288,7 @@ static void blkvsc_request(struct request_queue *queue) DPRINT_DBG(BLKVSC_DRV, "- req %p\n", req); blkdev = req->rq_disk->private_data; - if (blkdev->shutting_down || !blk_fs_request(req) || + if (blkdev->shutting_down || req->cmd_type != REQ_TYPE_FS || blkdev->media_not_present) { __blk_end_request_cur(req, 0); continue; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d7ae241a9e55..3ecd28ef9ba4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -604,33 +604,20 @@ enum { test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) -#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) -#define blk_special_request(rq) ((rq)->cmd_type == REQ_TYPE_SPECIAL) -#define blk_sense_request(rq) ((rq)->cmd_type == REQ_TYPE_SENSE) - -#define blk_failfast_dev(rq) ((rq)->cmd_flags & REQ_FAILFAST_DEV) -#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT) -#define blk_failfast_driver(rq) ((rq)->cmd_flags & REQ_FAILFAST_DRIVER) -#define blk_noretry_request(rq) (blk_failfast_dev(rq) || \ - blk_failfast_transport(rq) || \ - blk_failfast_driver(rq)) -#define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) -#define blk_rq_io_stat(rq) ((rq)->cmd_flags & REQ_IO_STAT) -#define blk_rq_quiet(rq) ((rq)->cmd_flags & REQ_QUIET) - -#define blk_account_rq(rq) (blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) - -#define blk_pm_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND) -#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME) +#define blk_noretry_request(rq) \ + ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ + REQ_FAILFAST_DRIVER)) + +#define blk_account_rq(rq) \ + (((rq)->cmd_flags & REQ_STARTED) && \ + ((rq)->cmd_type == REQ_TYPE_FS || \ + ((rq)->cmd_flags & REQ_DISCARD))) + #define blk_pm_request(rq) \ - (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq)) + ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_PM_RESUME) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) -#define blk_sorted_rq(rq) ((rq)->cmd_flags & REQ_SORTED) -#define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) -#define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) -#define blk_discard_rq(rq) ((rq)->cmd_flags & REQ_DISCARD) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) /* rq->queuelist of dequeued request must be list_empty() */ #define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) @@ -652,9 +639,6 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) -#define rq_noidle(rq) ((rq)->cmd_flags & REQ_NOIDLE) - static inline int blk_queue_full(struct request_queue *q, int sync) { if (sync) @@ -687,7 +671,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync) (REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ - (blk_discard_rq(rq) || blk_fs_request((rq)))) + (((rq)->cmd_flags & REQ_DISCARD) || \ + (rq)->cmd_type == REQ_TYPE_FS)) /* * q->prep_rq_fn return values diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 416bf62d6d46..23faa67e8022 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -224,7 +224,7 @@ static inline int blk_trace_init_sysfs(struct device *dev) static inline int blk_cmd_buf_len(struct request *rq) { - return blk_pc_request(rq) ? rq->cmd_len * 3 : 1; + return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1; } extern void blk_dump_cmd(char *buf, struct request *rq); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d870a918559c..d8ce278515c3 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -25,8 +25,10 @@ DECLARE_EVENT_CLASS(block_rq_with_error, TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); + __entry->sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_pos(rq); + __entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_sectors(rq); __entry->errors = rq->errors; blk_fill_rwbs_rq(__entry->rwbs, rq); @@ -109,9 +111,12 @@ DECLARE_EVENT_CLASS(block_rq, TP_fast_assign( __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; - __entry->sector = blk_pc_request(rq) ? 0 : blk_rq_pos(rq); - __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq); - __entry->bytes = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0; + __entry->sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_pos(rq); + __entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + 0 : blk_rq_sectors(rq); + __entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? + blk_rq_bytes(rq) : 0; blk_fill_rwbs_rq(__entry->rwbs, rq); blk_dump_cmd(__get_str(cmd), rq); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 638711c17504..4f149944cb89 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -661,10 +661,10 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (likely(!bt)) return; - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) rw |= (1 << BIO_RW_DISCARD); - if (blk_pc_request(rq)) { + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw, what, rq->errors, rq->cmd_len, rq->cmd); @@ -925,7 +925,7 @@ void blk_add_driver_data(struct request_queue *q, if (likely(!bt)) return; - if (blk_pc_request(rq)) + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) __blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, BLK_TA_DRV_DATA, rq->errors, len, data); else @@ -1730,7 +1730,7 @@ void blk_dump_cmd(char *buf, struct request *rq) int len = rq->cmd_len; unsigned char *cmd = rq->cmd; - if (!blk_pc_request(rq)) { + if (rq->cmd_type != REQ_TYPE_BLOCK_PC) { buf[0] = '\0'; return; } @@ -1779,7 +1779,7 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq) int rw = rq->cmd_flags & 0x03; int bytes; - if (blk_discard_rq(rq)) + if (rq->cmd_flags & REQ_DISCARD) rw |= (1 << BIO_RW_DISCARD); bytes = blk_rq_bytes(rq); -- cgit v1.2.3 From 455b2864686d3591b3b2f39eb46290c95f76471f Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 7 Jul 2010 13:24:06 +1000 Subject: writeback: Initial tracing support Trace queue/sched/exec parts of the writeback loop. This provides insight into when and why flusher threads are scheduled to run. e.g a sync invocation leaves traces like: sync-[...]: writeback_queue: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0 flush-8:0-[...]: writeback_exec: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0 This also lays the foundation for adding more writeback tracing to provide deeper insight into the whole writeback path. The original tracing code is from Jens Axboe, though this version is a rewrite as a result of the code being traced changing significantly. Signed-off-by: Dave Chinner Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 38 +++++++++++++---- include/trace/events/writeback.h | 91 ++++++++++++++++++++++++++++++++++++++++ mm/backing-dev.c | 3 ++ 3 files changed, 124 insertions(+), 8 deletions(-) create mode 100644 include/trace/events/writeback.h (limited to 'include/trace') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c8471b3ddccf..73acab4dc2b7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -26,15 +26,9 @@ #include #include #include +#include #include "internal.h" -#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) - -/* - * We don't actually have pdflush, but this one is exported though /proc... - */ -int nr_pdflush_threads; - /* * Passed into wb_writeback(), essentially a subset of writeback_control */ @@ -50,6 +44,21 @@ struct wb_writeback_work { struct completion *done; /* set if the caller waits */ }; +/* + * Include the creation of the trace points after defining the + * wb_writeback_work structure so that the definition remains local to this + * file. + */ +#define CREATE_TRACE_POINTS +#include + +#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) + +/* + * We don't actually have pdflush, but this one is exported though /proc... + */ +int nr_pdflush_threads; + /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. @@ -65,6 +74,8 @@ int writeback_in_progress(struct backing_dev_info *bdi) static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { + trace_writeback_queue(bdi, work); + spin_lock(&bdi->wb_lock); list_add_tail(&work->list, &bdi->work_list); spin_unlock(&bdi->wb_lock); @@ -74,6 +85,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, * it gets created and wakes up, we'll run this work. */ if (unlikely(!bdi->wb.task)) { + trace_writeback_nothread(bdi, work); wake_up_process(default_backing_dev_info.wb.task); } else { struct bdi_writeback *wb = &bdi->wb; @@ -95,8 +107,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, */ work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { - if (bdi->wb.task) + if (bdi->wb.task) { + trace_writeback_nowork(bdi); wake_up_process(bdi->wb.task); + } return; } @@ -751,6 +765,8 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait) if (force_wait) work->sync_mode = WB_SYNC_ALL; + trace_writeback_exec(bdi, work); + wrote += wb_writeback(wb, work); /* @@ -805,9 +821,13 @@ int bdi_writeback_thread(void *data) smp_mb__after_clear_bit(); wake_up_bit(&bdi->state, BDI_pending); + trace_writeback_thread_start(bdi); + while (!kthread_should_stop()) { pages_written = wb_do_writeback(wb, 0); + trace_writeback_pages_written(pages_written); + if (pages_written) last_active = jiffies; else if (wait_jiffies != -1UL) { @@ -845,6 +865,8 @@ int bdi_writeback_thread(void *data) */ if (!list_empty(&bdi->work_list)) wb_do_writeback(wb, 1); + + trace_writeback_thread_stop(bdi); return 0; } diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h new file mode 100644 index 000000000000..562fcae10d9d --- /dev/null +++ b/include/trace/events/writeback.h @@ -0,0 +1,91 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM writeback + +#if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_WRITEBACK_H + +#include +#include + +struct wb_writeback_work; + +DECLARE_EVENT_CLASS(writeback_work_class, + TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), + TP_ARGS(bdi, work), + TP_STRUCT__entry( + __array(char, name, 32) + __field(long, nr_pages) + __field(dev_t, sb_dev) + __field(int, sync_mode) + __field(int, for_kupdate) + __field(int, range_cyclic) + __field(int, for_background) + ), + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->nr_pages = work->nr_pages; + __entry->sb_dev = work->sb ? work->sb->s_dev : 0; + __entry->sync_mode = work->sync_mode; + __entry->for_kupdate = work->for_kupdate; + __entry->range_cyclic = work->range_cyclic; + __entry->for_background = work->for_background; + ), + TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " + "kupdate=%d range_cyclic=%d background=%d", + __entry->name, + MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), + __entry->nr_pages, + __entry->sync_mode, + __entry->for_kupdate, + __entry->range_cyclic, + __entry->for_background + ) +); +#define DEFINE_WRITEBACK_WORK_EVENT(name) \ +DEFINE_EVENT(writeback_work_class, name, \ + TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \ + TP_ARGS(bdi, work)) +DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread); +DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); +DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); + +TRACE_EVENT(writeback_pages_written, + TP_PROTO(long pages_written), + TP_ARGS(pages_written), + TP_STRUCT__entry( + __field(long, pages) + ), + TP_fast_assign( + __entry->pages = pages_written; + ), + TP_printk("%ld", __entry->pages) +); + +DECLARE_EVENT_CLASS(writeback_class, + TP_PROTO(struct backing_dev_info *bdi), + TP_ARGS(bdi), + TP_STRUCT__entry( + __array(char, name, 32) + ), + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + ), + TP_printk("bdi %s", + __entry->name + ) +); +#define DEFINE_WRITEBACK_EVENT(name) \ +DEFINE_EVENT(writeback_class, name, \ + TP_PROTO(struct backing_dev_info *bdi), \ + TP_ARGS(bdi)) + +DEFINE_WRITEBACK_EVENT(writeback_nowork); +DEFINE_WRITEBACK_EVENT(writeback_bdi_register); +DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); +DEFINE_WRITEBACK_EVENT(writeback_thread_start); +DEFINE_WRITEBACK_EVENT(writeback_thread_stop); + +#endif /* _TRACE_WRITEBACK_H */ + +/* This part must be outside protection */ +#include diff --git a/mm/backing-dev.c b/mm/backing-dev.c index bceac647e4d1..ac78a3336181 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -10,6 +10,7 @@ #include #include #include +#include static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); @@ -518,6 +519,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, bdi_debug_register(bdi, dev_name(dev)); set_bit(BDI_registered, &bdi->state); + trace_writeback_bdi_register(bdi); exit: return ret; } @@ -578,6 +580,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); if (!bdi_cap_flush_forker(bdi)) -- cgit v1.2.3 From 028c2dd184c097809986684f2f0627eea5529fea Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 7 Jul 2010 13:24:07 +1000 Subject: writeback: Add tracing to balance_dirty_pages Tracing high level background writeback events is good, but it doesn't give the entire picture. Add visibility into write throttling to catch IO dispatched by foreground throttling of processing dirtying lots of pages. Signed-off-by: Dave Chinner Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 5 ++++ include/trace/events/writeback.h | 64 ++++++++++++++++++++++++++++++++++++++++ mm/page-writeback.c | 4 +++ 3 files changed, 73 insertions(+) (limited to 'include/trace') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 73acab4dc2b7..bf10cbf379dd 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -656,10 +656,14 @@ static long wb_writeback(struct bdi_writeback *wb, wbc.more_io = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; + + trace_wbc_writeback_start(&wbc, wb->bdi); if (work->sb) __writeback_inodes_sb(work->sb, wb, &wbc); else writeback_inodes_wb(wb, &wbc); + trace_wbc_writeback_written(&wbc, wb->bdi); + work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; @@ -687,6 +691,7 @@ static long wb_writeback(struct bdi_writeback *wb, if (!list_empty(&wb->b_more_io)) { inode = list_entry(wb->b_more_io.prev, struct inode, i_list); + trace_wbc_writeback_wait(&wbc, wb->bdi); inode_wait_for_writeback(inode); } spin_unlock(&inode_lock); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 562fcae10d9d..0be26acae064 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -85,6 +85,70 @@ DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); DEFINE_WRITEBACK_EVENT(writeback_thread_start); DEFINE_WRITEBACK_EVENT(writeback_thread_stop); +DECLARE_EVENT_CLASS(wbc_class, + TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), + TP_ARGS(wbc, bdi), + TP_STRUCT__entry( + __array(char, name, 32) + __field(long, nr_to_write) + __field(long, pages_skipped) + __field(int, sync_mode) + __field(int, nonblocking) + __field(int, encountered_congestion) + __field(int, for_kupdate) + __field(int, for_background) + __field(int, for_reclaim) + __field(int, range_cyclic) + __field(int, more_io) + __field(unsigned long, older_than_this) + __field(long, range_start) + __field(long, range_end) + ), + + TP_fast_assign( + strncpy(__entry->name, dev_name(bdi->dev), 32); + __entry->nr_to_write = wbc->nr_to_write; + __entry->pages_skipped = wbc->pages_skipped; + __entry->sync_mode = wbc->sync_mode; + __entry->for_kupdate = wbc->for_kupdate; + __entry->for_background = wbc->for_background; + __entry->for_reclaim = wbc->for_reclaim; + __entry->range_cyclic = wbc->range_cyclic; + __entry->more_io = wbc->more_io; + __entry->older_than_this = wbc->older_than_this ? + *wbc->older_than_this : 0; + __entry->range_start = (long)wbc->range_start; + __entry->range_end = (long)wbc->range_end; + ), + + TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " + "bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx " + "start=0x%lx end=0x%lx", + __entry->name, + __entry->nr_to_write, + __entry->pages_skipped, + __entry->sync_mode, + __entry->for_kupdate, + __entry->for_background, + __entry->for_reclaim, + __entry->range_cyclic, + __entry->more_io, + __entry->older_than_this, + __entry->range_start, + __entry->range_end) +) + +#define DEFINE_WBC_EVENT(name) \ +DEFINE_EVENT(wbc_class, name, \ + TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ + TP_ARGS(wbc, bdi)) +DEFINE_WBC_EVENT(wbc_writeback_start); +DEFINE_WBC_EVENT(wbc_writeback_written); +DEFINE_WBC_EVENT(wbc_writeback_wait); +DEFINE_WBC_EVENT(wbc_balance_dirty_start); +DEFINE_WBC_EVENT(wbc_balance_dirty_written); +DEFINE_WBC_EVENT(wbc_balance_dirty_wait); + #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 37498ef61548..d556cd829af6 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -34,6 +34,7 @@ #include #include #include +#include /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited @@ -535,11 +536,13 @@ static void balance_dirty_pages(struct address_space *mapping, * threshold otherwise wait until the disk writes catch * up. */ + trace_wbc_balance_dirty_start(&wbc, bdi); if (bdi_nr_reclaimable > bdi_thresh) { writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); + trace_wbc_balance_dirty_written(&wbc, bdi); } /* @@ -565,6 +568,7 @@ static void balance_dirty_pages(struct address_space *mapping, if (pages_written >= write_chunk) break; /* We've done our duty */ + trace_wbc_balance_dirty_wait(&wbc, bdi); __set_current_state(TASK_INTERRUPTIBLE); io_schedule_timeout(pause); -- cgit v1.2.3 From 9e094383b60066996fbc3b53891324e5d2ec858d Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 7 Jul 2010 13:24:08 +1000 Subject: writeback: Add tracing to write_cache_pages Add a trace event to the ->writepage loop in write_cache_pages to give visibility into how the ->writepage call is changing variables within the writeback control structure. Of most interest is how wbc->nr_to_write changes from call to call, especially with filesystems that write multiple pages in ->writepage. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/trace/events/writeback.h | 1 + mm/page-writeback.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 0be26acae064..bde92e07fa4f 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -148,6 +148,7 @@ DEFINE_WBC_EVENT(wbc_writeback_wait); DEFINE_WBC_EVENT(wbc_balance_dirty_start); DEFINE_WBC_EVENT(wbc_balance_dirty_written); DEFINE_WBC_EVENT(wbc_balance_dirty_wait); +DEFINE_WBC_EVENT(wbc_writepage); #endif /* _TRACE_WRITEBACK_H */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d556cd829af6..3d2111a22236 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -933,6 +933,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; + trace_wbc_writepage(wbc, mapping->backing_dev_info); ret = (*writepage)(page, wbc, data); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { -- cgit v1.2.3 From 96dccab1d63cb35d3f5e75d2ef275fdbff4d5f3b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 19 Jul 2010 16:49:17 -0700 Subject: writeback.h: needs linux/device.h include/trace/events/writeback.h uses dev_name(), so it needs to include linux/device.h. include/trace/events/writeback.h:12: error: implicit declaration of function 'dev_name' Signed-off-by: Randy Dunlap Signed-off-by: Jens Axboe --- include/trace/events/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index bde92e07fa4f..84ab72df953c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -5,6 +5,7 @@ #define _TRACE_WRITEBACK_H #include +#include #include struct wb_writeback_work; -- cgit v1.2.3 From 603320239fb436f175c8b6bfa43d5023c47a6dc2 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:24 +0300 Subject: writeback: add new tracepoints Add 2 new trace points to the periodic write-back wake up case, just like we do in the 'bdi_queue_work()' function. Namely, introduce: 1. trace_writeback_wake_thread(bdi) 2. trace_writeback_wake_forker_thread(bdi) The first event is triggered every time we wake up a bdi thread to start periodic background write-out. The second event is triggered only when the bdi thread does not exist and should be created by the forker thread. This patch was suggested by Dave Chinner and Christoph Hellwig. Signed-off-by: Artem Bityutskiy Signed-off-by: Jens Axboe --- include/trace/events/writeback.h | 2 ++ mm/backing-dev.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 84ab72df953c..f345f66ae9d1 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -81,6 +81,8 @@ DEFINE_EVENT(writeback_class, name, \ TP_ARGS(bdi)) DEFINE_WRITEBACK_EVENT(writeback_nowork); +DEFINE_WRITEBACK_EVENT(writeback_wake_thread); +DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread); DEFINE_WRITEBACK_EVENT(writeback_bdi_register); DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister); DEFINE_WRITEBACK_EVENT(writeback_thread_start); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 99890831d557..9008c4e207f6 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -310,6 +310,7 @@ static void wakeup_timer_fn(unsigned long data) spin_lock_bh(&bdi->wb_lock); if (bdi->wb.task) { + trace_writeback_wake_thread(bdi); wake_up_process(bdi->wb.task); } else { /* @@ -317,6 +318,7 @@ static void wakeup_timer_fn(unsigned long data) * In this case we have to wake-up the forker thread which * should create and run the bdi thread. */ + trace_writeback_wake_forker_thread(bdi); wake_up_process(default_backing_dev_info.wb.task); } spin_unlock_bh(&bdi->wb_lock); -- cgit v1.2.3 From 33906bc5c87b50028364405ec425de9638afc719 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 9 Aug 2010 17:19:16 -0700 Subject: vmscan: tracing: add trace events for kswapd wakeup, sleeping and direct reclaim Add two trace events for kswapd waking up and going asleep for the purposes of tracking kswapd activity and two trace events for direct reclaim beginning and ending. The information can be used to work out how much time a process or the system is spending on the reclamation of pages and in the case of direct reclaim, how many pages were reclaimed for that process. High frequency triggering of these events could point to memory pressure problems. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: Larry Woodman Cc: Dave Chinner Cc: Chris Mason Cc: Nick Piggin Cc: Rik van Riel Cc: Johannes Weiner Cc: Christoph Hellwig Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Andrea Arcangeli Cc: Michael Rubin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/gfpflags.h | 37 +++++++++++++ include/trace/events/kmem.h | 38 +------------ include/trace/events/vmscan.h | 115 ++++++++++++++++++++++++++++++++++++++++ mm/vmscan.c | 24 +++++++-- 4 files changed, 173 insertions(+), 41 deletions(-) create mode 100644 include/trace/events/gfpflags.h create mode 100644 include/trace/events/vmscan.h (limited to 'include/trace') diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h new file mode 100644 index 000000000000..e3615c093741 --- /dev/null +++ b/include/trace/events/gfpflags.h @@ -0,0 +1,37 @@ +/* + * The order of these masks is important. Matching masks will be seen + * first and the left over flags will end up showing by themselves. + * + * For example, if we have GFP_KERNEL before GFP_USER we wil get: + * + * GFP_KERNEL|GFP_HARDWALL + * + * Thus most bits set go first. + */ +#define show_gfp_flags(flags) \ + (flags) ? __print_flags(flags, "|", \ + {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"}, \ + {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ + {(unsigned long)GFP_USER, "GFP_USER"}, \ + {(unsigned long)GFP_TEMPORARY, "GFP_TEMPORARY"}, \ + {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ + {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ + {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ + {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ + {(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \ + {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \ + {(unsigned long)__GFP_IO, "GFP_IO"}, \ + {(unsigned long)__GFP_COLD, "GFP_COLD"}, \ + {(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \ + {(unsigned long)__GFP_REPEAT, "GFP_REPEAT"}, \ + {(unsigned long)__GFP_NOFAIL, "GFP_NOFAIL"}, \ + {(unsigned long)__GFP_NORETRY, "GFP_NORETRY"}, \ + {(unsigned long)__GFP_COMP, "GFP_COMP"}, \ + {(unsigned long)__GFP_ZERO, "GFP_ZERO"}, \ + {(unsigned long)__GFP_NOMEMALLOC, "GFP_NOMEMALLOC"}, \ + {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \ + {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \ + {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ + {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"} \ + ) : "GFP_NOWAIT" + diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 3adca0ca9dbe..a9c87ad8331c 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -6,43 +6,7 @@ #include #include - -/* - * The order of these masks is important. Matching masks will be seen - * first and the left over flags will end up showing by themselves. - * - * For example, if we have GFP_KERNEL before GFP_USER we wil get: - * - * GFP_KERNEL|GFP_HARDWALL - * - * Thus most bits set go first. - */ -#define show_gfp_flags(flags) \ - (flags) ? __print_flags(flags, "|", \ - {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"}, \ - {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(unsigned long)GFP_USER, "GFP_USER"}, \ - {(unsigned long)GFP_TEMPORARY, "GFP_TEMPORARY"}, \ - {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \ - {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \ - {(unsigned long)__GFP_IO, "GFP_IO"}, \ - {(unsigned long)__GFP_COLD, "GFP_COLD"}, \ - {(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \ - {(unsigned long)__GFP_REPEAT, "GFP_REPEAT"}, \ - {(unsigned long)__GFP_NOFAIL, "GFP_NOFAIL"}, \ - {(unsigned long)__GFP_NORETRY, "GFP_NORETRY"}, \ - {(unsigned long)__GFP_COMP, "GFP_COMP"}, \ - {(unsigned long)__GFP_ZERO, "GFP_ZERO"}, \ - {(unsigned long)__GFP_NOMEMALLOC, "GFP_NOMEMALLOC"}, \ - {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \ - {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \ - {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"} \ - ) : "GFP_NOWAIT" +#include "gfpflags.h" DECLARE_EVENT_CLASS(kmem_alloc, diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h new file mode 100644 index 000000000000..f76521ffe7df --- /dev/null +++ b/include/trace/events/vmscan.h @@ -0,0 +1,115 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vmscan + +#if !defined(_TRACE_VMSCAN_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VMSCAN_H + +#include +#include +#include "gfpflags.h" + +TRACE_EVENT(mm_vmscan_kswapd_sleep, + + TP_PROTO(int nid), + + TP_ARGS(nid), + + TP_STRUCT__entry( + __field( int, nid ) + ), + + TP_fast_assign( + __entry->nid = nid; + ), + + TP_printk("nid=%d", __entry->nid) +); + +TRACE_EVENT(mm_vmscan_kswapd_wake, + + TP_PROTO(int nid, int order), + + TP_ARGS(nid, order), + + TP_STRUCT__entry( + __field( int, nid ) + __field( int, order ) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->order = order; + ), + + TP_printk("nid=%d order=%d", __entry->nid, __entry->order) +); + +TRACE_EVENT(mm_vmscan_wakeup_kswapd, + + TP_PROTO(int nid, int zid, int order), + + TP_ARGS(nid, zid, order), + + TP_STRUCT__entry( + __field( int, nid ) + __field( int, zid ) + __field( int, order ) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->zid = zid; + __entry->order = order; + ), + + TP_printk("nid=%d zid=%d order=%d", + __entry->nid, + __entry->zid, + __entry->order) +); + +TRACE_EVENT(mm_vmscan_direct_reclaim_begin, + + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + + TP_ARGS(order, may_writepage, gfp_flags), + + TP_STRUCT__entry( + __field( int, order ) + __field( int, may_writepage ) + __field( gfp_t, gfp_flags ) + ), + + TP_fast_assign( + __entry->order = order; + __entry->may_writepage = may_writepage; + __entry->gfp_flags = gfp_flags; + ), + + TP_printk("order=%d may_writepage=%d gfp_flags=%s", + __entry->order, + __entry->may_writepage, + show_gfp_flags(__entry->gfp_flags)) +); + +TRACE_EVENT(mm_vmscan_direct_reclaim_end, + + TP_PROTO(unsigned long nr_reclaimed), + + TP_ARGS(nr_reclaimed), + + TP_STRUCT__entry( + __field( unsigned long, nr_reclaimed ) + ), + + TP_fast_assign( + __entry->nr_reclaimed = nr_reclaimed; + ), + + TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) +); + +#endif /* _TRACE_VMSCAN_H */ + +/* This part must be outside protection */ +#include diff --git a/mm/vmscan.c b/mm/vmscan.c index 6dafa45d79e4..c99bc418c4cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -48,6 +48,9 @@ #include "internal.h" +#define CREATE_TRACE_POINTS +#include + struct scan_control { /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; @@ -1883,6 +1886,7 @@ out: unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { + unsigned long nr_reclaimed; struct scan_control sc = { .gfp_mask = gfp_mask, .may_writepage = !laptop_mode, @@ -1895,7 +1899,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, .nodemask = nodemask, }; - return do_try_to_free_pages(zonelist, &sc); + trace_mm_vmscan_direct_reclaim_begin(order, + sc.may_writepage, + gfp_mask); + + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + + trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); + + return nr_reclaimed; } #ifdef CONFIG_CGROUP_MEM_RES_CTLR @@ -2294,9 +2306,10 @@ static int kswapd(void *p) * premature sleep. If not, then go fully * to sleep until explicitly woken up */ - if (!sleeping_prematurely(pgdat, order, remaining)) + if (!sleeping_prematurely(pgdat, order, remaining)) { + trace_mm_vmscan_kswapd_sleep(pgdat->node_id); schedule(); - else { + } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else @@ -2316,8 +2329,10 @@ static int kswapd(void *p) * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ - if (!ret) + if (!ret) { + trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); balance_pgdat(pgdat, order); + } } return 0; } @@ -2337,6 +2352,7 @@ void wakeup_kswapd(struct zone *zone, int order) return; if (pgdat->kswapd_max_order < order) pgdat->kswapd_max_order = order; + trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order); if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) return; if (!waitqueue_active(&pgdat->kswapd_wait)) -- cgit v1.2.3 From a8a94d151521b248727c1f88756174e15260815a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 9 Aug 2010 17:19:17 -0700 Subject: vmscan: tracing: add trace events for LRU page isolation Add an event for when pages are isolated en-masse from the LRU lists. This event augments the information available on LRU traffic and can be used to evaluate lumpy reclaim. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: Larry Woodman Cc: Dave Chinner Cc: Chris Mason Cc: Nick Piggin Cc: Rik van Riel Cc: Johannes Weiner Cc: Christoph Hellwig Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Andrea Arcangeli Cc: Michael Rubin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 46 +++++++++++++++++++++++++++++++++++++++++++ mm/vmscan.c | 16 +++++++++++++++ 2 files changed, 62 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f76521ffe7df..c0552be1f50a 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -109,6 +109,52 @@ TRACE_EVENT(mm_vmscan_direct_reclaim_end, TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) ); +TRACE_EVENT(mm_vmscan_lru_isolate, + + TP_PROTO(int order, + unsigned long nr_requested, + unsigned long nr_scanned, + unsigned long nr_taken, + unsigned long nr_lumpy_taken, + unsigned long nr_lumpy_dirty, + unsigned long nr_lumpy_failed, + int isolate_mode), + + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode), + + TP_STRUCT__entry( + __field(int, order) + __field(unsigned long, nr_requested) + __field(unsigned long, nr_scanned) + __field(unsigned long, nr_taken) + __field(unsigned long, nr_lumpy_taken) + __field(unsigned long, nr_lumpy_dirty) + __field(unsigned long, nr_lumpy_failed) + __field(int, isolate_mode) + ), + + TP_fast_assign( + __entry->order = order; + __entry->nr_requested = nr_requested; + __entry->nr_scanned = nr_scanned; + __entry->nr_taken = nr_taken; + __entry->nr_lumpy_taken = nr_lumpy_taken; + __entry->nr_lumpy_dirty = nr_lumpy_dirty; + __entry->nr_lumpy_failed = nr_lumpy_failed; + __entry->isolate_mode = isolate_mode; + ), + + TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu contig_taken=%lu contig_dirty=%lu contig_failed=%lu", + __entry->isolate_mode, + __entry->order, + __entry->nr_requested, + __entry->nr_scanned, + __entry->nr_taken, + __entry->nr_lumpy_taken, + __entry->nr_lumpy_dirty, + __entry->nr_lumpy_failed) +); + #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/mm/vmscan.c b/mm/vmscan.c index c99bc418c4cf..3d006d91a526 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -919,6 +919,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, unsigned long *scanned, int order, int mode, int file) { unsigned long nr_taken = 0; + unsigned long nr_lumpy_taken = 0; + unsigned long nr_lumpy_dirty = 0; + unsigned long nr_lumpy_failed = 0; unsigned long scan; for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) { @@ -996,12 +999,25 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, list_move(&cursor_page->lru, dst); mem_cgroup_del_lru(cursor_page); nr_taken++; + nr_lumpy_taken++; + if (PageDirty(cursor_page)) + nr_lumpy_dirty++; scan++; + } else { + if (mode == ISOLATE_BOTH && + page_count(cursor_page)) + nr_lumpy_failed++; } } } *scanned = scan; + + trace_mm_vmscan_lru_isolate(order, + nr_to_scan, scan, + nr_taken, + nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, + mode); return nr_taken; } -- cgit v1.2.3 From 755f0225e8347b23a33ee6e3fb14a35310f95766 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 9 Aug 2010 17:19:18 -0700 Subject: vmscan: tracing: add trace event when a page is written Add a trace event for when page reclaim queues a page for IO and records whether it is synchronous or asynchronous. Excessive synchronous IO for a process can result in noticeable stalls during direct reclaim. Excessive IO from page reclaim may indicate that the system is seriously under provisioned for the amount of dirty pages that exist. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: Larry Woodman Cc: Dave Chinner Cc: Chris Mason Cc: Nick Piggin Cc: Rik van Riel Cc: Johannes Weiner Cc: Christoph Hellwig Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Andrea Arcangeli Cc: Michael Rubin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 41 +++++++++++++++++++++++++++++++++++++++++ mm/vmscan.c | 2 ++ 2 files changed, 43 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index c0552be1f50a..69789dc72100 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -8,6 +8,24 @@ #include #include "gfpflags.h" +#define RECLAIM_WB_ANON 0x0001u +#define RECLAIM_WB_FILE 0x0002u +#define RECLAIM_WB_SYNC 0x0004u +#define RECLAIM_WB_ASYNC 0x0008u + +#define show_reclaim_flags(flags) \ + (flags) ? __print_flags(flags, "|", \ + {RECLAIM_WB_ANON, "RECLAIM_WB_ANON"}, \ + {RECLAIM_WB_FILE, "RECLAIM_WB_FILE"}, \ + {RECLAIM_WB_SYNC, "RECLAIM_WB_SYNC"}, \ + {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ + ) : "RECLAIM_WB_NONE" + +#define trace_reclaim_flags(page, sync) ( \ + (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ + (sync == PAGEOUT_IO_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + ) + TRACE_EVENT(mm_vmscan_kswapd_sleep, TP_PROTO(int nid), @@ -155,6 +173,29 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_lumpy_failed) ); +TRACE_EVENT(mm_vmscan_writepage, + + TP_PROTO(struct page *page, + int reclaim_flags), + + TP_ARGS(page, reclaim_flags), + + TP_STRUCT__entry( + __field(struct page *, page) + __field(int, reclaim_flags) + ), + + TP_fast_assign( + __entry->page = page; + __entry->reclaim_flags = reclaim_flags; + ), + + TP_printk("page=%p pfn=%lu flags=%s", + __entry->page, + page_to_pfn(__entry->page), + show_reclaim_flags(__entry->reclaim_flags)) +); + #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 3d006d91a526..b7a4e6a3cf89 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -401,6 +401,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } + trace_mm_vmscan_writepage(page, + trace_reclaim_flags(page, sync_writeback)); inc_zone_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } -- cgit v1.2.3 From cf4dcc3e9b374e1b61a7c22faf868707ce78d6a9 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 9 Aug 2010 17:19:55 -0700 Subject: vmscan: convert direct reclaim tracepoint to DEFINE_TRACE Mel Gorman recently added some vmscan tracepoints. Unfortunately they are covered only global reclaim. But we want to trace memcg reclaim too. Thus, this patch convert them to DEFINE_TRACE macro. it help to reuse tracepoint definition for other similar usage (i.e. memcg). This patch have no functionally change. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 69789dc72100..f9f2747bc1c1 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -86,7 +86,7 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, __entry->order) ); -TRACE_EVENT(mm_vmscan_direct_reclaim_begin, +DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), @@ -110,7 +110,15 @@ TRACE_EVENT(mm_vmscan_direct_reclaim_begin, show_gfp_flags(__entry->gfp_flags)) ); -TRACE_EVENT(mm_vmscan_direct_reclaim_end, +DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, + + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + + TP_ARGS(order, may_writepage, gfp_flags) +); + + +DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, TP_PROTO(unsigned long nr_reclaimed), @@ -127,6 +135,13 @@ TRACE_EVENT(mm_vmscan_direct_reclaim_end, TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed) ); +DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end, + + TP_PROTO(unsigned long nr_reclaimed), + + TP_ARGS(nr_reclaimed) +); + TRACE_EVENT(mm_vmscan_lru_isolate, TP_PROTO(int order, -- cgit v1.2.3 From bdce6d9ebf52c1f6c23163d1a33320ce7c007f73 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 9 Aug 2010 17:19:56 -0700 Subject: memcg, vmscan: add memcg reclaim tracepoint Memcg also need to trace reclaim progress as direct reclaim. This patch add it. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 28 ++++++++++++++++++++++++++++ mm/vmscan.c | 20 +++++++++++++++++++- 2 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f9f2747bc1c1..028733be4f34 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -117,6 +117,19 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_b TP_ARGS(order, may_writepage, gfp_flags) ); +DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, + + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + + TP_ARGS(order, may_writepage, gfp_flags) +); + +DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, + + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + + TP_ARGS(order, may_writepage, gfp_flags) +); DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, @@ -142,6 +155,21 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end TP_ARGS(nr_reclaimed) ); +DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, + + TP_PROTO(unsigned long nr_reclaimed), + + TP_ARGS(nr_reclaimed) +); + +DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, + + TP_PROTO(unsigned long nr_reclaimed), + + TP_ARGS(nr_reclaimed) +); + + TRACE_EVENT(mm_vmscan_lru_isolate, TP_PROTO(int order, diff --git a/mm/vmscan.c b/mm/vmscan.c index 9789a2c92563..154b37a33731 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1951,6 +1951,11 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, sc.nodemask = &nm; sc.nr_reclaimed = 0; sc.nr_scanned = 0; + + trace_mm_vmscan_memcg_softlimit_reclaim_begin(0, + sc.may_writepage, + sc.gfp_mask); + /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. @@ -1959,6 +1964,9 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, * the priority and make it zero. */ shrink_zone(0, zone, &sc); + + trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + return sc.nr_reclaimed; } @@ -1968,6 +1976,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, unsigned int swappiness) { struct zonelist *zonelist; + unsigned long nr_reclaimed; struct scan_control sc = { .may_writepage = !laptop_mode, .may_unmap = 1, @@ -1982,7 +1991,16 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); zonelist = NODE_DATA(numa_node_id())->node_zonelists; - return do_try_to_free_pages(zonelist, &sc); + + trace_mm_vmscan_memcg_reclaim_begin(0, + sc.may_writepage, + sc.gfp_mask); + + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + + trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); + + return nr_reclaimed; } #endif -- cgit v1.2.3 From e17613c39b8894c164df782d0508c27ca559c24b Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 9 Aug 2010 17:19:57 -0700 Subject: vmscan: convert mm_vmscan_lru_isolate to DEFINE_EVENT Mel Gorman recently added some vmscan tracepoints. Unfortunately they are covered only global reclaim. But we want to trace memcg reclaim too. Thus, this patch convert them to DEFINE_TRACE macro. it help to reuse tracepoint definition for other similar usage (i.e. memcg). This patch have no functionally change. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 028733be4f34..d9656444a7ca 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -170,7 +170,7 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_re ); -TRACE_EVENT(mm_vmscan_lru_isolate, +DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, TP_PROTO(int order, unsigned long nr_requested, @@ -216,6 +216,21 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_lumpy_failed) ); +DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, + + TP_PROTO(int order, + unsigned long nr_requested, + unsigned long nr_scanned, + unsigned long nr_taken, + unsigned long nr_lumpy_taken, + unsigned long nr_lumpy_dirty, + unsigned long nr_lumpy_failed, + int isolate_mode), + + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) + +); + TRACE_EVENT(mm_vmscan_writepage, TP_PROTO(struct page *page, -- cgit v1.2.3 From cc8e970c3ce4d98afa8eb02dbd2526ce57f7611a Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Mon, 9 Aug 2010 17:19:57 -0700 Subject: memcg: add mm_vmscan_memcg_isolate tracepoint Memcg also need to trace page isolation information as global reclaim. This patch does it. Signed-off-by: KOSAKI Motohiro Reviewed-by: KAMEZAWA Hiroyuki Acked-by: Mel Gorman Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 15 +++++++++++++++ mm/memcontrol.c | 6 ++++++ 2 files changed, 21 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index d9656444a7ca..370aa5a87322 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -231,6 +231,21 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, ); +DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, + + TP_PROTO(int order, + unsigned long nr_requested, + unsigned long nr_scanned, + unsigned long nr_taken, + unsigned long nr_lumpy_taken, + unsigned long nr_lumpy_dirty, + unsigned long nr_lumpy_failed, + int isolate_mode), + + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode) + +); + TRACE_EVENT(mm_vmscan_writepage, TP_PROTO(struct page *page, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index de54ea0094a1..0576e9e64586 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -51,6 +51,8 @@ #include +#include + struct cgroup_subsys mem_cgroup_subsys __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 struct mem_cgroup *root_mem_cgroup __read_mostly; @@ -1007,6 +1009,10 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, } *scanned = scan; + + trace_mm_vmscan_memcg_isolate(0, nr_to_scan, scan, nr_taken, + 0, 0, 0, mode); + return nr_taken; } -- cgit v1.2.3