diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-11-26 08:22:50 +0100 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-11-26 08:22:50 +0100 |
commit | 7fbb8759eff9a348efa5f352ffaa51c364837c4b (patch) | |
tree | d40cd3f47b9f667ba94d9613270132080dcb6a1a /kernel/trace/trace.c | |
parent | 6003ab0bad4cc56f3c4fadf62a0d23a967b9c53b (diff) | |
parent | 13d428afc007fcfcd6deeb215618f54cf9c0cae6 (diff) | |
download | op-kernel-dev-7fbb8759eff9a348efa5f352ffaa51c364837c4b.zip op-kernel-dev-7fbb8759eff9a348efa5f352ffaa51c364837c4b.tar.gz |
Merge commit 'v2.6.28-rc6' into core/debug
Diffstat (limited to 'kernel/trace/trace.c')
-rw-r--r-- | kernel/trace/trace.c | 1902 |
1 files changed, 990 insertions, 912 deletions
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8f3fb3d..d86e325 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -14,6 +14,7 @@ #include <linux/utsrelease.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> +#include <linux/notifier.h> #include <linux/debugfs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> @@ -22,6 +23,7 @@ #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> +#include <linux/kdebug.h> #include <linux/ctype.h> #include <linux/init.h> #include <linux/poll.h> @@ -31,25 +33,37 @@ #include <linux/writeback.h> #include <linux/stacktrace.h> +#include <linux/ring_buffer.h> +#include <linux/irqflags.h> #include "trace.h" +#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE) + unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX; unsigned long __read_mostly tracing_thresh; -static unsigned long __read_mostly tracing_nr_buffers; +static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled); + +static inline void ftrace_disable_cpu(void) +{ + preempt_disable(); + local_inc(&__get_cpu_var(ftrace_cpu_disabled)); +} + +static inline void ftrace_enable_cpu(void) +{ + local_dec(&__get_cpu_var(ftrace_cpu_disabled)); + preempt_enable(); +} + static cpumask_t __read_mostly tracing_buffer_mask; #define for_each_tracing_cpu(cpu) \ for_each_cpu_mask(cpu, tracing_buffer_mask) -static int trace_alloc_page(void); -static int trace_free_page(void); - static int tracing_disabled = 1; -static unsigned long tracing_pages_allocated; - long ns2usecs(cycle_t nsec) { @@ -60,7 +74,9 @@ ns2usecs(cycle_t nsec) cycle_t ftrace_now(int cpu) { - return cpu_clock(cpu); + u64 ts = ring_buffer_time_stamp(cpu); + ring_buffer_normalize_time_stamp(cpu, &ts); + return ts; } /* @@ -100,11 +116,18 @@ static int tracer_enabled = 1; int ftrace_function_enabled; /* - * trace_nr_entries is the number of entries that is allocated - * for a buffer. Note, the number of entries is always rounded - * to ENTRIES_PER_PAGE. + * trace_buf_size is the size in bytes that is allocated + * for a buffer. Note, the number of bytes is always rounded + * to page size. + * + * This number is purposely set to a low number of 16384. + * If the dump on oops happens, it will be much appreciated + * to not have to wait for all that output. Anyway this can be + * boot time and run time configurable. */ -static unsigned long trace_nr_entries = 65536UL; +#define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */ + +static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; @@ -133,24 +156,6 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); /* trace_flags holds iter_ctrl options */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT; -static notrace void no_trace_init(struct trace_array *tr) -{ - int cpu; - - ftrace_function_enabled = 0; - if(tr->ctrl) - for_each_online_cpu(cpu) - tracing_reset(tr->data[cpu]); - tracer_enabled = 0; -} - -/* dummy trace to disable tracing */ -static struct tracer no_tracer __read_mostly = { - .name = "none", - .init = no_trace_init -}; - - /** * trace_wake_up - wake up tasks waiting for trace input * @@ -167,23 +172,21 @@ void trace_wake_up(void) wake_up(&trace_wait); } -#define ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(struct trace_entry)) - -static int __init set_nr_entries(char *str) +static int __init set_buf_size(char *str) { - unsigned long nr_entries; + unsigned long buf_size; int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &nr_entries); + ret = strict_strtoul(str, 0, &buf_size); /* nr_entries can not be zero */ - if (ret < 0 || nr_entries == 0) + if (ret < 0 || buf_size == 0) return 0; - trace_nr_entries = nr_entries; + trace_buf_size = buf_size; return 1; } -__setup("trace_entries=", set_nr_entries); +__setup("trace_buf_size=", set_buf_size); unsigned long nsecs_to_usecs(unsigned long nsecs) { @@ -191,21 +194,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs) } /* - * trace_flag_type is an enumeration that holds different - * states when a trace occurs. These are: - * IRQS_OFF - interrupts were disabled - * NEED_RESCED - reschedule is requested - * HARDIRQ - inside an interrupt handler - * SOFTIRQ - inside a softirq handler - */ -enum trace_flag_type { - TRACE_FLAG_IRQS_OFF = 0x01, - TRACE_FLAG_NEED_RESCHED = 0x02, - TRACE_FLAG_HARDIRQ = 0x04, - TRACE_FLAG_SOFTIRQ = 0x08, -}; - -/* * TRACE_ITER_SYM_MASK masks the options in trace_flags that * control the output of kernel symbols. */ @@ -224,6 +212,7 @@ static const char *trace_options[] = { "block", "stacktrace", "sched-tree", + "ftrace_printk", NULL }; @@ -266,54 +255,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) tracing_record_cmdline(current); } -#define CHECK_COND(cond) \ - if (unlikely(cond)) { \ - tracing_disabled = 1; \ - WARN_ON(1); \ - return -1; \ - } - -/** - * check_pages - integrity check of trace buffers - * - * As a safty measure we check to make sure the data pages have not - * been corrupted. - */ -int check_pages(struct trace_array_cpu *data) -{ - struct page *page, *tmp; - - CHECK_COND(data->trace_pages.next->prev != &data->trace_pages); - CHECK_COND(data->trace_pages.prev->next != &data->trace_pages); - - list_for_each_entry_safe(page, tmp, &data->trace_pages, lru) { - CHECK_COND(page->lru.next->prev != &page->lru); - CHECK_COND(page->lru.prev->next != &page->lru); - } - - return 0; -} - -/** - * head_page - page address of the first page in per_cpu buffer. - * - * head_page returns the page address of the first page in - * a per_cpu buffer. This also preforms various consistency - * checks to make sure the buffer has not been corrupted. - */ -void *head_page(struct trace_array_cpu *data) -{ - struct page *page; - - if (list_empty(&data->trace_pages)) - return NULL; - - page = list_entry(data->trace_pages.next, struct page, lru); - BUG_ON(&page->lru == &data->trace_pages); - - return page_address(page); -} - /** * trace_seq_printf - sequence printing of trace information * @s: trace sequence descriptor @@ -395,28 +336,23 @@ trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) return len; } -#define HEX_CHARS 17 -static const char hex2asc[] = "0123456789abcdef"; +#define MAX_MEMHEX_BYTES 8 +#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) static int trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) { unsigned char hex[HEX_CHARS]; unsigned char *data = mem; - unsigned char byte; int i, j; - BUG_ON(len >= HEX_CHARS); - #ifdef __BIG_ENDIAN for (i = 0, j = 0; i < len; i++) { #else for (i = len-1, j = 0; i >= 0; i--) { #endif - byte = data[i]; - - hex[j++] = hex2asc[byte & 0x0f]; - hex[j++] = hex2asc[byte >> 4]; + hex[j++] = hex_asc_hi(data[i]); + hex[j++] = hex_asc_lo(data[i]); } hex[j++] = ' '; @@ -460,34 +396,6 @@ trace_print_seq(struct seq_file *m, struct trace_seq *s) trace_seq_reset(s); } -/* - * flip the trace buffers between two trace descriptors. - * This usually is the buffers between the global_trace and - * the max_tr to record a snapshot of a current trace. - * - * The ftrace_max_lock must be held. - */ -static void -flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2) -{ - struct list_head flip_pages; - - INIT_LIST_HEAD(&flip_pages); - - memcpy(&tr1->trace_head_idx, &tr2->trace_head_idx, - sizeof(struct trace_array_cpu) - - offsetof(struct trace_array_cpu, trace_head_idx)); - - check_pages(tr1); - check_pages(tr2); - list_splice_init(&tr1->trace_pages, &flip_pages); - list_splice_init(&tr2->trace_pages, &tr1->trace_pages); - list_splice_init(&flip_pages, &tr2->trace_pages); - BUG_ON(!list_empty(&flip_pages)); - check_pages(tr1); - check_pages(tr2); -} - /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer @@ -500,17 +408,17 @@ flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2) void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_array_cpu *data; - int i; + struct ring_buffer *buf = tr->buffer; WARN_ON_ONCE(!irqs_disabled()); __raw_spin_lock(&ftrace_max_lock); - /* clear out all the previous traces */ - for_each_tracing_cpu(i) { - data = tr->data[i]; - flip_trace(max_tr.data[i], data); - tracing_reset(data); - } + + tr->buffer = max_tr.buffer; + max_tr.buffer = buf; + + ftrace_disable_cpu(); + ring_buffer_reset(tr->buffer); + ftrace_enable_cpu(); __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); @@ -527,16 +435,19 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_array_cpu *data = tr->data[cpu]; - int i; + int ret; WARN_ON_ONCE(!irqs_disabled()); __raw_spin_lock(&ftrace_max_lock); - for_each_tracing_cpu(i) - tracing_reset(max_tr.data[i]); - flip_trace(max_tr.data[cpu], data); - tracing_reset(data); + ftrace_disable_cpu(); + + ring_buffer_reset(max_tr.buffer); + ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); + + ftrace_enable_cpu(); + + WARN_ON_ONCE(ret); __update_max_tr(tr, tsk, cpu); __raw_spin_unlock(&ftrace_max_lock); @@ -573,7 +484,6 @@ int register_tracer(struct tracer *type) #ifdef CONFIG_FTRACE_STARTUP_TEST if (type->selftest) { struct tracer *saved_tracer = current_trace; - struct trace_array_cpu *data; struct trace_array *tr = &global_trace; int saved_ctrl = tr->ctrl; int i; @@ -585,10 +495,7 @@ int register_tracer(struct tracer *type) * If we fail, we do not register this tracer. */ for_each_tracing_cpu(i) { - data = tr->data[i]; - if (!head_page(data)) - continue; - tracing_reset(data); + tracing_reset(tr, i); } current_trace = type; tr->ctrl = 0; @@ -604,10 +511,7 @@ int register_tracer(struct tracer *type) } /* Only reset on passing, to avoid touching corrupted buffers */ for_each_tracing_cpu(i) { - data = tr->data[i]; - if (!head_page(data)) - continue; - tracing_reset(data); + tracing_reset(tr, i); } printk(KERN_CONT "PASSED\n"); } @@ -653,13 +557,11 @@ void unregister_tracer(struct tracer *type) mutex_unlock(&trace_types_lock); } -void tracing_reset(struct trace_array_cpu *data) +void tracing_reset(struct trace_array *tr, int cpu) { - data->trace_idx = 0; - data->overrun = 0; - data->trace_head = data->trace_tail = head_page(data); - data->trace_head_idx = 0; - data->trace_tail_idx = 0; + ftrace_disable_cpu(); + ring_buffer_reset_cpu(tr->buffer, cpu); + ftrace_enable_cpu(); } #define SAVED_CMDLINES 128 @@ -745,82 +647,20 @@ void tracing_record_cmdline(struct task_struct *tsk) trace_save_cmdline(tsk); } -static inline struct list_head * -trace_next_list(struct trace_array_cpu *data, struct list_head *next) -{ - /* - * Roundrobin - but skip the head (which is not a real page): - */ - next = next->next; - if (unlikely(next == &data->trace_pages)) - next = next->next; - BUG_ON(next == &data->trace_pages); - - return next; -} - -static inline void * -trace_next_page(struct trace_array_cpu *data, void *addr) -{ - struct list_head *next; - struct page *page; - - page = virt_to_page(addr); - - next = trace_next_list(data, &page->lru); - page = list_entry(next, struct page, lru); - - return page_address(page); -} - -static inline struct trace_entry * -tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data) -{ - unsigned long idx, idx_next; - struct trace_entry *entry; - - data->trace_idx++; - idx = data->trace_head_idx; - idx_next = idx + 1; - - BUG_ON(idx * TRACE_ENTRY_SIZE >= PAGE_SIZE); - - entry = data->trace_head + idx * TRACE_ENTRY_SIZE; - - if (unlikely(idx_next >= ENTRIES_PER_PAGE)) { - data->trace_head = trace_next_page(data, data->trace_head); - idx_next = 0; - } - - if (data->trace_head == data->trace_tail && - idx_next == data->trace_tail_idx) { - /* overrun */ - data->overrun++; - data->trace_tail_idx++; - if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { - data->trace_tail = - trace_next_page(data, data->trace_tail); - data->trace_tail_idx = 0; - } - } - - data->trace_head_idx = idx_next; - - return entry; -} - -static inline void -tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags) +void +tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, + int pc) { struct task_struct *tsk = current; - unsigned long pc; - - pc = preempt_count(); - entry->preempt_count = pc & 0xff; - entry->pid = (tsk) ? tsk->pid : 0; - entry->t = ftrace_now(raw_smp_processor_id()); - entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | + entry->preempt_count = pc & 0xff; + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT + (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | +#else + TRACE_FLAG_IRQS_NOSUPPORT | +#endif ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); @@ -828,145 +668,141 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags) void trace_function(struct trace_array *tr, struct trace_array_cpu *data, - unsigned long ip, unsigned long parent_ip, unsigned long flags) + unsigned long ip, unsigned long parent_ip, unsigned long flags, + int pc) { - struct trace_entry *entry; + struct ring_buffer_event *event; + struct ftrace_entry *entry; unsigned long irq_flags; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, flags); - entry->type = TRACE_FN; - entry->fn.ip = ip; - entry->fn.parent_ip = parent_ip; - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); + /* If we are reading the ring buffer, don't trace */ + if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) + return; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_FN; + entry->ip = ip; + entry->parent_ip = parent_ip; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); } void ftrace(struct trace_array *tr, struct trace_array_cpu *data, - unsigned long ip, unsigned long parent_ip, unsigned long flags) + unsigned long ip, unsigned long parent_ip, unsigned long flags, + int pc) { if (likely(!atomic_read(&data->disabled))) - trace_function(tr, data, ip, parent_ip, flags); + trace_function(tr, data, ip, parent_ip, flags, pc); } -#ifdef CONFIG_MMIOTRACE -void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data, - struct mmiotrace_rw *rw) +static void ftrace_trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip, int pc) { - struct trace_entry *entry; +#ifdef CONFIG_STACKTRACE + struct ring_buffer_event *event; + struct stack_entry *entry; + struct stack_trace trace; unsigned long irq_flags; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); - - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, 0); - entry->type = TRACE_MMIO_RW; - entry->mmiorw = *rw; - - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); - - trace_wake_up(); -} - -void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data, - struct mmiotrace_map *map) -{ - struct trace_entry *entry; - unsigned long irq_flags; + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_STACK; - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, 0); - entry->type = TRACE_MMIO_MAP; - entry->mmiomap = *map; + memset(&entry->caller, 0, sizeof(entry->caller)); - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = skip; + trace.entries = entry->caller; - trace_wake_up(); -} + save_stack_trace(&trace); + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); #endif +} void __trace_stack(struct trace_array *tr, struct trace_array_cpu *data, unsigned long flags, int skip) { - struct trace_entry *entry; - struct stack_trace trace; - - if (!(trace_flags & TRACE_ITER_STACKTRACE)) - return; - - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, flags); - entry->type = TRACE_STACK; - - memset(&entry->stack, 0, sizeof(entry->stack)); - - trace.nr_entries = 0; - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.skip = skip; - trace.entries = entry->stack.caller; - - save_stack_trace(&trace); + ftrace_trace_stack(tr, data, flags, skip, preempt_count()); } -void -__trace_special(void *__tr, void *__data, - unsigned long arg1, unsigned long arg2, unsigned long arg3) +static void +ftrace_trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3, + int pc) { + struct ring_buffer_event *event; struct trace_array_cpu *data = __data; struct trace_array *tr = __tr; - struct trace_entry *entry; + struct special_entry *entry; unsigned long irq_flags; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, 0); - entry->type = TRACE_SPECIAL; - entry->special.arg1 = arg1; - entry->special.arg2 = arg2; - entry->special.arg3 = arg3; - __trace_stack(tr, data, irq_flags, 4); - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, pc); + entry->ent.type = TRACE_SPECIAL; + entry->arg1 = arg1; + entry->arg2 = arg2; + entry->arg3 = arg3; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ftrace_trace_stack(tr, data, irq_flags, 4, pc); trace_wake_up(); } void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + ftrace_trace_special(__tr, __data, arg1, arg2, arg3, preempt_count()); +} + +void tracing_sched_switch_trace(struct trace_array *tr, struct trace_array_cpu *data, struct task_struct *prev, struct task_struct *next, - unsigned long flags) + unsigned long flags, int pc) { - struct trace_entry *entry; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; unsigned long irq_flags; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, flags); - entry->type = TRACE_CTX; - entry->ctx.prev_pid = prev->pid; - entry->ctx.prev_prio = prev->prio; - entry->ctx.prev_state = prev->state; - entry->ctx.next_pid = next->pid; - entry->ctx.next_prio = next->prio; - entry->ctx.next_state = next->state; - __trace_stack(tr, data, flags, 5); - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_CTX; + entry->prev_pid = prev->pid; + entry->prev_prio = prev->prio; + entry->prev_state = prev->state; + entry->next_pid = next->pid; + entry->next_prio = next->prio; + entry->next_state = next->state; + entry->next_cpu = task_cpu(next); + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ftrace_trace_stack(tr, data, flags, 5, pc); } void @@ -974,25 +810,28 @@ tracing_sched_wakeup_trace(struct trace_array *tr, struct trace_array_cpu *data, struct task_struct *wakee, struct task_struct *curr, - unsigned long flags) + unsigned long flags, int pc) { - struct trace_entry *entry; + struct ring_buffer_event *event; + struct ctx_switch_entry *entry; unsigned long irq_flags; - raw_local_irq_save(irq_flags); - __raw_spin_lock(&data->lock); - entry = tracing_get_trace_entry(tr, data); - tracing_generic_entry_update(entry, flags); - entry->type = TRACE_WAKE; - entry->ctx.prev_pid = curr->pid; - entry->ctx.prev_prio = curr->prio; - entry->ctx.prev_state = curr->state; - entry->ctx.next_pid = wakee->pid; - entry->ctx.next_prio = wakee->prio; - entry->ctx.next_state = wakee->state; - __trace_stack(tr, data, flags, 6); - __raw_spin_unlock(&data->lock); - raw_local_irq_restore(irq_flags); + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_WAKE; + entry->prev_pid = curr->pid; + entry->prev_prio = curr->prio; + entry->prev_state = curr->state; + entry->next_pid = wakee->pid; + entry->next_prio = wakee->prio; + entry->next_state = wakee->state; + entry->next_cpu = task_cpu(wakee); + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + ftrace_trace_stack(tr, data, flags, 6, pc); trace_wake_up(); } @@ -1002,26 +841,24 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { struct trace_array *tr = &global_trace; struct trace_array_cpu *data; - unsigned long flags; - long disabled; int cpu; + int pc; - if (tracing_disabled || current_trace == &no_tracer || !tr->ctrl) + if (tracing_disabled || !tr->ctrl) return; - local_irq_save(flags); + pc = preempt_count(); + preempt_disable_notrace(); cpu = raw_smp_processor_id(); data = tr->data[cpu]; - disabled = atomic_inc_return(&data->disabled); - if (likely(disabled == 1)) - __trace_special(tr, data, arg1, arg2, arg3); + if (likely(!atomic_read(&data->disabled))) + ftrace_trace_special(tr, data, arg1, arg2, arg3, pc); - atomic_dec(&data->disabled); - local_irq_restore(flags); + preempt_enable_notrace(); } -#ifdef CONFIG_FTRACE +#ifdef CONFIG_FUNCTION_TRACER static void function_trace_call(unsigned long ip, unsigned long parent_ip) { @@ -1029,24 +866,28 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) struct trace_array_cpu *data; unsigned long flags; long disabled; - int cpu; + int cpu, resched; + int pc; if (unlikely(!ftrace_function_enabled)) return; - if (skip_trace(ip)) - return; - - local_irq_save(flags); + pc = preempt_count(); + resched = need_resched(); + preempt_disable_notrace(); + local_save_flags(flags); cpu = raw_smp_processor_id(); data = tr->data[cpu]; disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) - trace_function(tr, data, ip, parent_ip, flags); + trace_function(tr, data, ip, parent_ip, flags, pc); atomic_dec(&data->disabled); - local_irq_restore(flags); + if (resched) + preempt_enable_no_resched_notrace(); + else + preempt_enable_notrace(); } static struct ftrace_ops trace_ops __read_mostly = @@ -1073,111 +914,96 @@ enum trace_file_type { TRACE_FILE_LAT_FMT = 1, }; -static struct trace_entry * -trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data, - struct trace_iterator *iter, int cpu) +static void trace_iterator_increment(struct trace_iterator *iter, int cpu) { - struct page *page; - struct trace_entry *array; + /* Don't allow ftrace to trace into the ring buffers */ + ftrace_disable_cpu(); - if (iter->next_idx[cpu] >= tr->entries || - iter->next_idx[cpu] >= data->trace_idx || - (data->trace_head == data->trace_tail && - data->trace_head_idx == data->trace_tail_idx)) - return NULL; + iter->idx++; + if (iter->buffer_iter[iter->cpu]) + ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); - if (!iter->next_page[cpu]) { - /* Initialize the iterator for this cpu trace buffer */ - WARN_ON(!data->trace_tail); - page = virt_to_page(data->trace_tail); - iter->next_page[cpu] = &page->lru; - iter->next_page_idx[cpu] = data->trace_tail_idx; - } + ftrace_enable_cpu(); +} - page = list_entry(iter->next_page[cpu], struct page, lru); - BUG_ON(&data->trace_pages == &page->lru); +static struct trace_entry * +peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts) +{ + struct ring_buffer_event *event; + struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; + + /* Don't allow ftrace to trace into the ring buffers */ + ftrace_disable_cpu(); + + if (buf_iter) + event = ring_buffer_iter_peek(buf_iter, ts); + else + event = ring_buffer_peek(iter->tr->buffer, cpu, ts); - array = page_address(page); + ftrace_enable_cpu(); - WARN_ON(iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE); - return &array[iter->next_page_idx[cpu]]; + return event ? ring_buffer_event_data(event) : NULL; } static struct trace_entry * -find_next_entry(struct trace_iterator *iter, int *ent_cpu) +__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { - struct trace_array *tr = iter->tr; + struct ring_buffer *buffer = iter->tr->buffer; struct trace_entry *ent, *next = NULL; + u64 next_ts = 0, ts; int next_cpu = -1; int cpu; for_each_tracing_cpu(cpu) { - if (!head_page(tr->data[cpu])) + + if (ring_buffer_empty_cpu(buffer, cpu)) continue; - ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu); + + ent = peek_next_entry(iter, cpu, &ts); + /* * Pick the entry with the smallest timestamp: */ - if (ent && (!next || ent->t < next->t)) { + if (ent && (!next || ts < next_ts)) { next = ent; next_cpu = cpu; + next_ts = ts; } } if (ent_cpu) *ent_cpu = next_cpu; + if (ent_ts) + *ent_ts = next_ts; + return next; } -static void trace_iterator_increment(struct trace_iterator *iter) +/* Find the next real entry, without updating the iterator itself */ +static struct trace_entry * +find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { - iter->idx++; - iter->next_idx[iter->cpu]++; - iter->next_page_idx[iter->cpu]++; - - if (iter->next_page_idx[iter->cpu] >= ENTRIES_PER_PAGE) { - struct trace_array_cpu *data = iter->tr->data[iter->cpu]; - - iter->next_page_idx[iter->cpu] = 0; - iter->next_page[iter->cpu] = - trace_next_list(data, iter->next_page[iter->cpu]); - } + return __find_next_entry(iter, ent_cpu, ent_ts); } -static void trace_consume(struct trace_iterator *iter) +/* Find the next real entry, and increment the iterator to the next entry */ +static void *find_next_entry_inc(struct trace_iterator *iter) { - struct trace_array_cpu *data = iter->tr->data[iter->cpu]; + iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts); - data->trace_tail_idx++; - if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { - data->trace_tail = trace_next_page(data, data->trace_tail); - data->trace_tail_idx = 0; - } + if (iter->ent) + trace_iterator_increment(iter, iter->cpu); - /* Check if we empty it, then reset the index */ - if (data->trace_head == data->trace_tail && - data->trace_head_idx == data->trace_tail_idx) - data->trace_idx = 0; + return iter->ent ? iter : NULL; } -static void *find_next_entry_inc(struct trace_iterator *iter) +static void trace_consume(struct trace_iterator *iter) { - struct trace_entry *next; - int next_cpu = -1; - - next = find_next_entry(iter, &next_cpu); - - iter->prev_ent = iter->ent; - iter->prev_cpu = iter->cpu; - - iter->ent = next; - iter->cpu = next_cpu; - - if (next) - trace_iterator_increment(iter); - - return next ? iter : NULL; + /* Don't allow ftrace to trace into the ring buffers */ + ftrace_disable_cpu(); + ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts); + ftrace_enable_cpu(); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) @@ -1210,7 +1036,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) struct trace_iterator *iter = m->private; void *p = NULL; loff_t l = 0; - int i; + int cpu; mutex_lock(&trace_types_lock); @@ -1229,14 +1055,15 @@ static void *s_start(struct seq_file *m, loff_t *pos) iter->ent = NULL; iter->cpu = 0; iter->idx = -1; - iter->prev_ent = NULL; - iter->prev_cpu = -1; - for_each_tracing_cpu(i) { - iter->next_idx[i] = 0; - iter->next_page[i] = NULL; + ftrace_disable_cpu(); + + for_each_tracing_cpu(cpu) { + ring_buffer_iter_reset(iter->buffer_iter[cpu]); } + ftrace_enable_cpu(); + for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; @@ -1261,17 +1088,20 @@ static void s_stop(struct seq_file *m, void *p) mutex_unlock(&trace_types_lock); } -#define KRETPROBE_MSG "[unknown/kretprobe'd]" - #ifdef CONFIG_KRETPROBES -static inline int kretprobed(unsigned long addr) +static inline const char *kretprobed(const char *name) { - return addr == (unsigned long)kretprobe_trampoline; + static const char tramp_name[] = "kretprobe_trampoline"; + int size = sizeof(tramp_name); + + if (strncmp(tramp_name, name, size) == 0) + return "[unknown/kretprobe'd]"; + return name; } #else -static inline int kretprobed(unsigned long addr) +static inline const char *kretprobed(const char *name) { - return 0; + return name; } #endif /* CONFIG_KRETPROBES */ @@ -1280,10 +1110,13 @@ seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) { #ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; + const char *name; kallsyms_lookup(address, NULL, NULL, NULL, str); - return trace_seq_printf(s, fmt, str); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); #endif return 1; } @@ -1294,9 +1127,12 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt, { #ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; + const char *name; sprint_symbol(str, address); - return trace_seq_printf(s, fmt, str); + name = kretprobed(str); + + return trace_seq_printf(s, fmt, name); #endif return 1; } @@ -1330,21 +1166,21 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n"); - seq_puts(m, "# / _-----=> irqs-off \n"); - seq_puts(m, "# | / _----=> need-resched \n"); - seq_puts(m, "# || / _---=> hardirq/softirq \n"); - seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| / \n"); - seq_puts(m, "# ||||| delay \n"); - seq_puts(m, "# cmd pid ||||| time | caller \n"); - seq_puts(m, "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _------=> CPU# \n"); + seq_puts(m, "# / _-----=> irqs-off \n"); + seq_puts(m, "# | / _----=> need-resched \n"); + seq_puts(m, "# || / _---=> hardirq/softirq \n"); + seq_puts(m, "# ||| / _--=> preempt-depth \n"); + seq_puts(m, "# |||| / \n"); + seq_puts(m, "# ||||| delay \n"); + seq_puts(m, "# cmd pid ||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); } static void print_func_help_header(struct seq_file *m) { - seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); - seq_puts(m, "# | | | | |\n"); + seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | | |\n"); } @@ -1355,23 +1191,16 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) struct trace_array *tr = iter->tr; struct trace_array_cpu *data = tr->data[tr->cpu]; struct tracer *type = current_trace; - unsigned long total = 0; - unsigned long entries = 0; - int cpu; + unsigned long total; + unsigned long entries; const char *name = "preemption"; if (type) name = type->name; - for_each_tracing_cpu(cpu) { - if (head_page(tr->data[cpu])) { - total += tr->data[cpu]->trace_idx; - if (tr->data[cpu]->trace_idx > tr->entries) - entries += tr->entries; - else - entries += tr->data[cpu]->trace_idx; - } - } + entries = ring_buffer_entries(iter->tr->buffer); + total = entries + + ring_buffer_overruns(iter->tr->buffer); seq_printf(m, "%s latency trace v1.1.5 on %s\n", name, UTS_RELEASE); @@ -1428,9 +1257,10 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) comm = trace_find_cmdline(entry->pid); trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); - trace_seq_printf(s, "%d", cpu); + trace_seq_printf(s, "%3d", cpu); trace_seq_printf(s, "%c%c", - (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); hardirq = entry->flags & TRACE_FLAG_HARDIRQ; @@ -1457,7 +1287,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) unsigned long preempt_mark_thresh = 100; static void -lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs, +lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, unsigned long rel_usecs) { trace_seq_printf(s, " %4lldus", abs_usecs); @@ -1471,34 +1301,76 @@ lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs, static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; -static int +/* + * The message is supposed to contain an ending newline. + * If the printing stops prematurely, try to add a newline of our own. + */ +void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter) +{ + struct trace_entry *ent; + struct trace_field_cont *cont; + bool ok = true; + + ent = peek_next_entry(iter, iter->cpu, NULL); + if (!ent || ent->type != TRACE_CONT) { + trace_seq_putc(s, '\n'); + return; + } + + do { + cont = (struct trace_field_cont *)ent; + if (ok) + ok = (trace_seq_printf(s, "%s", cont->buf) > 0); + + ftrace_disable_cpu(); + + if (iter->buffer_iter[iter->cpu]) + ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + else + ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL); + + ftrace_enable_cpu(); + + ent = peek_next_entry(iter, iter->cpu, NULL); + } while (ent && ent->type == TRACE_CONT); + + if (!ok) + trace_seq_putc(s, '\n'); +} + +static enum print_line_t print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) { struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); - struct trace_entry *next_entry = find_next_entry(iter, NULL); + struct trace_entry *next_entry; unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); struct trace_entry *entry = iter->ent; unsigned long abs_usecs; unsigned long rel_usecs; + u64 next_ts; char *comm; int S, T; int i; unsigned state; + if (entry->type == TRACE_CONT) + return TRACE_TYPE_HANDLED; + + next_entry = find_next_entry(iter, NULL, &next_ts); if (!next_entry) - next_entry = entry; - rel_usecs = ns2usecs(next_entry->t - entry->t); - abs_usecs = ns2usecs(entry->t - iter->tr->time_start); + next_ts = iter->ts; + rel_usecs = ns2usecs(next_ts - iter->ts); + abs_usecs = ns2usecs(iter->ts - iter->tr->time_start); if (verbose) { comm = trace_find_cmdline(entry->pid); - trace_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]" + trace_seq_printf(s, "%16s %5d %3d %d %08x %08x [%08lx]" " %ld.%03ldms (+%ld.%03ldms): ", comm, entry->pid, cpu, entry->flags, entry->preempt_count, trace_idx, - ns2usecs(entry->t), + ns2usecs(iter->ts), abs_usecs/1000, abs_usecs % 1000, rel_usecs/1000, rel_usecs % 1000); @@ -1507,52 +1379,82 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) lat_print_timestamp(s, abs_usecs, rel_usecs); } switch (entry->type) { - case TRACE_FN: - seq_print_ip_sym(s, entry->fn.ip, sym_flags); + case TRACE_FN: { + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + seq_print_ip_sym(s, field->ip, sym_flags); trace_seq_puts(s, " ("); - if (kretprobed(entry->fn.parent_ip)) - trace_seq_puts(s, KRETPROBE_MSG); - else - seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags); + seq_print_ip_sym(s, field->parent_ip, sym_flags); trace_seq_puts(s, ")\n"); break; + } case TRACE_CTX: - case TRACE_WAKE: - T = entry->ctx.next_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.next_state] : 'X'; + case TRACE_WAKE: { + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + T = field->next_state < sizeof(state_to_char) ? + state_to_char[field->next_state] : 'X'; - state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0; + state = field->prev_state ? + __ffs(field->prev_state) + 1 : 0; S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X'; - comm = trace_find_cmdline(entry->ctx.next_pid); - trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n", - entry->ctx.prev_pid, - entry->ctx.prev_prio, + comm = trace_find_cmdline(field->next_pid); + trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + field->prev_pid, + field->prev_prio, S, entry->type == TRACE_CTX ? "==>" : " +", - entry->ctx.next_pid, - entry->ctx.next_prio, + field->next_cpu, + field->next_pid, + field->next_prio, T, comm); break; - case TRACE_SPECIAL: + } + case TRACE_SPECIAL: { + struct special_entry *field; + + trace_assign_type(field, entry); + trace_seq_printf(s, "# %ld %ld %ld\n", - entry->special.arg1, - entry->special.arg2, - entry->special.arg3); + field->arg1, + field->arg2, + field->arg3); break; - case TRACE_STACK: + } + case TRACE_STACK: { + struct stack_entry *field; + + trace_assign_type(field, entry); + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { if (i) trace_seq_puts(s, " <= "); - seq_print_ip_sym(s, entry->stack.caller[i], sym_flags); + seq_print_ip_sym(s, field->caller[i], sym_flags); } trace_seq_puts(s, "\n"); break; + } + case TRACE_PRINT: { + struct print_entry *field; + + trace_assign_type(field, entry); + + seq_print_ip_sym(s, field->ip, sym_flags); + trace_seq_printf(s, ": %s", field->buf); + if (entry->flags & TRACE_FLAG_CONT) + trace_seq_print_cont(s, iter); + break; + } default: trace_seq_printf(s, "Unknown type %d\n", entry->type); } - return 1; + return TRACE_TYPE_HANDLED; } -static int print_trace_fmt(struct trace_iterator *iter) +static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); @@ -1567,90 +1469,123 @@ static int print_trace_fmt(struct trace_iterator *iter) entry = iter->ent; + if (entry->type == TRACE_CONT) + return TRACE_TYPE_HANDLED; + comm = trace_find_cmdline(iter->ent->pid); - t = ns2usecs(entry->t); + t = ns2usecs(iter->ts); usec_rem = do_div(t, 1000000ULL); secs = (unsigned long)t; ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); if (!ret) - return 0; - ret = trace_seq_printf(s, "[%02d] ", iter->cpu); + return TRACE_TYPE_PARTIAL_LINE; + ret = trace_seq_printf(s, "[%03d] ", iter->cpu); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; switch (entry->type) { - case TRACE_FN: - ret = seq_print_ip_sym(s, entry->fn.ip, sym_flags); + case TRACE_FN: { + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + ret = seq_print_ip_sym(s, field->ip, sym_flags); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; if ((sym_flags & TRACE_ITER_PRINT_PARENT) && - entry->fn.parent_ip) { + field->parent_ip) { ret = trace_seq_printf(s, " <-"); if (!ret) - return 0; - if (kretprobed(entry->fn.parent_ip)) - ret = trace_seq_puts(s, KRETPROBE_MSG); - else - ret = seq_print_ip_sym(s, entry->fn.parent_ip, - sym_flags); + return TRACE_TYPE_PARTIAL_LINE; + ret = seq_print_ip_sym(s, + field->parent_ip, + sym_flags); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; } ret = trace_seq_printf(s, "\n"); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; + } case TRACE_CTX: - case TRACE_WAKE: - S = entry->ctx.prev_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.prev_state] : 'X'; - T = entry->ctx.next_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.next_state] : 'X'; - ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c\n", - entry->ctx.prev_pid, - entry->ctx.prev_prio, + case TRACE_WAKE: { + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + S = field->prev_state < sizeof(state_to_char) ? + state_to_char[field->prev_state] : 'X'; + T = field->next_state < sizeof(state_to_char) ? + state_to_char[field->next_state] : 'X'; + ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n", + field->prev_pid, + field->prev_prio, S, entry->type == TRACE_CTX ? "==>" : " +", - entry->ctx.next_pid, - entry->ctx.next_prio, + field->next_cpu, + field->next_pid, + field->next_prio, T); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; - case TRACE_SPECIAL: + } + case TRACE_SPECIAL: { + struct special_entry *field; + + trace_assign_type(field, entry); + ret = trace_seq_printf(s, "# %ld %ld %ld\n", - entry->special.arg1, - entry->special.arg2, - entry->special.arg3); + field->arg1, + field->arg2, + field->arg3); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; - case TRACE_STACK: + } + case TRACE_STACK: { + struct stack_entry *field; + + trace_assign_type(field, entry); + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { if (i) { ret = trace_seq_puts(s, " <= "); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; } - ret = seq_print_ip_sym(s, entry->stack.caller[i], + ret = seq_print_ip_sym(s, field->caller[i], sym_flags); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; } ret = trace_seq_puts(s, "\n"); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; } - return 1; + case TRACE_PRINT: { + struct print_entry *field; + + trace_assign_type(field, entry); + + seq_print_ip_sym(s, field->ip, sym_flags); + trace_seq_printf(s, ": %s", field->buf); + if (entry->flags & TRACE_FLAG_CONT) + trace_seq_print_cont(s, iter); + break; + } + } + return TRACE_TYPE_HANDLED; } -static int print_raw_fmt(struct trace_iterator *iter) +static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; @@ -1659,47 +1594,77 @@ static int print_raw_fmt(struct trace_iterator *iter) entry = iter->ent; + if (entry->type == TRACE_CONT) + return TRACE_TYPE_HANDLED; + ret = trace_seq_printf(s, "%d %d %llu ", - entry->pid, iter->cpu, entry->t); + entry->pid, iter->cpu, iter->ts); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; switch (entry->type) { - case TRACE_FN: + case TRACE_FN: { + struct ftrace_entry *field; + + trace_assign_type(field, entry); + ret = trace_seq_printf(s, "%x %x\n", - entry->fn.ip, entry->fn.parent_ip); + field->ip, + field->parent_ip); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; + } case TRACE_CTX: - case TRACE_WAKE: - S = entry->ctx.prev_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.prev_state] : 'X'; - T = entry->ctx.next_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.next_state] : 'X'; + case TRACE_WAKE: { + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + S = field->prev_state < sizeof(state_to_char) ? + state_to_char[field->prev_state] : 'X'; + T = field->next_state < sizeof(state_to_char) ? + state_to_char[field->next_state] : 'X'; if (entry->type == TRACE_WAKE) S = '+'; - ret = trace_seq_printf(s, "%d %d %c %d %d %c\n", - entry->ctx.prev_pid, - entry->ctx.prev_prio, + ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n", + field->prev_pid, + field->prev_prio, S, - entry->ctx.next_pid, - entry->ctx.next_prio, + field->next_cpu, + field->next_pid, + field->next_prio, T); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; + } case TRACE_SPECIAL: - case TRACE_STACK: + case TRACE_STACK: { + struct special_entry *field; + + trace_assign_type(field, entry); + ret = trace_seq_printf(s, "# %ld %ld %ld\n", - entry->special.arg1, - entry->special.arg2, - entry->special.arg3); + field->arg1, + field->arg2, + field->arg3); if (!ret) - return 0; + return TRACE_TYPE_PARTIAL_LINE; break; } - return 1; + case TRACE_PRINT: { + struct print_entry *field; + + trace_assign_type(field, entry); + + trace_seq_printf(s, "# %lx %s", field->ip, field->buf); + if (entry->flags & TRACE_FLAG_CONT) + trace_seq_print_cont(s, iter); + break; + } + } + return TRACE_TYPE_HANDLED; } #define SEQ_PUT_FIELD_RET(s, x) \ @@ -1710,11 +1675,12 @@ do { \ #define SEQ_PUT_HEX_FIELD_RET(s, x) \ do { \ + BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ return 0; \ } while (0) -static int print_hex_fmt(struct trace_iterator *iter) +static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; @@ -1723,97 +1689,139 @@ static int print_hex_fmt(struct trace_iterator *iter) entry = iter->ent; + if (entry->type == TRACE_CONT) + return TRACE_TYPE_HANDLED; + SEQ_PUT_HEX_FIELD_RET(s, entry->pid); SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); - SEQ_PUT_HEX_FIELD_RET(s, entry->t); + SEQ_PUT_HEX_FIELD_RET(s, iter->ts); switch (entry->type) { - case TRACE_FN: - SEQ_PUT_HEX_FIELD_RET(s, entry->fn.ip); - SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + case TRACE_FN: { + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_HEX_FIELD_RET(s, field->ip); + SEQ_PUT_HEX_FIELD_RET(s, field->parent_ip); break; + } case TRACE_CTX: - case TRACE_WAKE: - S = entry->ctx.prev_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.prev_state] : 'X'; - T = entry->ctx.next_state < sizeof(state_to_char) ? - state_to_char[entry->ctx.next_state] : 'X'; + case TRACE_WAKE: { + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + S = field->prev_state < sizeof(state_to_char) ? + state_to_char[field->prev_state] : 'X'; + T = field->next_state < sizeof(state_to_char) ? + state_to_char[field->next_state] : 'X'; if (entry->type == TRACE_WAKE) S = '+'; - SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_pid); - SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_prio); + SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); SEQ_PUT_HEX_FIELD_RET(s, S); - SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_pid); - SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_prio); - SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + SEQ_PUT_HEX_FIELD_RET(s, field->next_cpu); + SEQ_PUT_HEX_FIELD_RET(s, field->next_pid); + SEQ_PUT_HEX_FIELD_RET(s, field->next_prio); SEQ_PUT_HEX_FIELD_RET(s, T); break; + } case TRACE_SPECIAL: - case TRACE_STACK: - SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg1); - SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg2); - SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg3); + case TRACE_STACK: { + struct special_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_HEX_FIELD_RET(s, field->arg1); + SEQ_PUT_HEX_FIELD_RET(s, field->arg2); + SEQ_PUT_HEX_FIELD_RET(s, field->arg3); break; } + } SEQ_PUT_FIELD_RET(s, newline); - return 1; + return TRACE_TYPE_HANDLED; } -static int print_bin_fmt(struct trace_iterator *iter) +static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_entry *entry; entry = iter->ent; + if (entry->type == TRACE_CONT) + return TRACE_TYPE_HANDLED; + SEQ_PUT_FIELD_RET(s, entry->pid); SEQ_PUT_FIELD_RET(s, entry->cpu); - SEQ_PUT_FIELD_RET(s, entry->t); + SEQ_PUT_FIELD_RET(s, iter->ts); switch (entry->type) { - case TRACE_FN: - SEQ_PUT_FIELD_RET(s, entry->fn.ip); - SEQ_PUT_FIELD_RET(s, entry->fn.parent_ip); + case TRACE_FN: { + struct ftrace_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->ip); + SEQ_PUT_FIELD_RET(s, field->parent_ip); break; - case TRACE_CTX: - SEQ_PUT_FIELD_RET(s, entry->ctx.prev_pid); - SEQ_PUT_FIELD_RET(s, entry->ctx.prev_prio); - SEQ_PUT_FIELD_RET(s, entry->ctx.prev_state); - SEQ_PUT_FIELD_RET(s, entry->ctx.next_pid); - SEQ_PUT_FIELD_RET(s, entry->ctx.next_prio); - SEQ_PUT_FIELD_RET(s, entry->ctx.next_state); + } + case TRACE_CTX: { + struct ctx_switch_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->prev_pid); + SEQ_PUT_FIELD_RET(s, field->prev_prio); + SEQ_PUT_FIELD_RET(s, field->prev_state); + SEQ_PUT_FIELD_RET(s, field->next_pid); + SEQ_PUT_FIELD_RET(s, field->next_prio); + SEQ_PUT_FIELD_RET(s, field->next_state); break; + } case TRACE_SPECIAL: - case TRACE_STACK: - SEQ_PUT_FIELD_RET(s, entry->special.arg1); - SEQ_PUT_FIELD_RET(s, entry->special.arg2); - SEQ_PUT_FIELD_RET(s, entry->special.arg3); + case TRACE_STACK: { + struct special_entry *field; + + trace_assign_type(field, entry); + + SEQ_PUT_FIELD_RET(s, field->arg1); + SEQ_PUT_FIELD_RET(s, field->arg2); + SEQ_PUT_FIELD_RET(s, field->arg3); break; } + } return 1; } static int trace_empty(struct trace_iterator *iter) { - struct trace_array_cpu *data; int cpu; for_each_tracing_cpu(cpu) { - data = iter->tr->data[cpu]; - - if (head_page(data) && data->trace_idx && - (data->trace_tail != data->trace_head || - data->trace_tail_idx != data->trace_head_idx)) - return 0; + if (iter->buffer_iter[cpu]) { + if (!ring_buffer_iter_empty(iter->buffer_iter[cpu])) + return 0; + } else { + if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu)) + return 0; + } } + return 1; } -static int print_trace_line(struct trace_iterator *iter) +static enum print_line_t print_trace_line(struct trace_iterator *iter) { - if (iter->trace && iter->trace->print_line) - return iter->trace->print_line(iter); + enum print_line_t ret; + + if (iter->trace && iter->trace->print_line) { + ret = iter->trace->print_line(iter); + if (ret != TRACE_TYPE_UNHANDLED) + return ret; + } if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); @@ -1869,6 +1877,8 @@ static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, int *ret) { struct trace_iterator *iter; + struct seq_file *m; + int cpu; if (tracing_disabled) { *ret = -ENODEV; @@ -1889,28 +1899,46 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) iter->trace = current_trace; iter->pos = -1; + for_each_tracing_cpu(cpu) { + + iter->buffer_iter[cpu] = + ring_buffer_read_start(iter->tr->buffer, cpu); + + if (!iter->buffer_iter[cpu]) + goto fail_buffer; + } + /* TODO stop tracer */ *ret = seq_open(file, &tracer_seq_ops); - if (!*ret) { - struct seq_file *m = file->private_data; - m->private = iter; + if (*ret) + goto fail_buffer; - /* stop the trace while dumping */ - if (iter->tr->ctrl) { - tracer_enabled = 0; - ftrace_function_enabled = 0; - } + m = file->private_data; + m->private = iter; - if (iter->trace && iter->trace->open) - iter->trace->open(iter); - } else { - kfree(iter); - iter = NULL; + /* stop the trace while dumping */ + if (iter->tr->ctrl) { + tracer_enabled = 0; + ftrace_function_enabled = 0; } + + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + mutex_unlock(&trace_types_lock); out: return iter; + + fail_buffer: + for_each_tracing_cpu(cpu) { + if (iter->buffer_iter[cpu]) + ring_buffer_read_finish(iter->buffer_iter[cpu]); + } + mutex_unlock(&trace_types_lock); + kfree(iter); + + return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) @@ -1926,8 +1954,14 @@ int tracing_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct trace_iterator *iter = m->private; + int cpu; mutex_lock(&trace_types_lock); + for_each_tracing_cpu(cpu) { + if (iter->buffer_iter[cpu]) + ring_buffer_read_finish(iter->buffer_iter[cpu]); + } + if (iter->trace && iter->trace->close) iter->trace->close(iter); @@ -2352,6 +2386,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, struct tracer *t; char buf[max_tracer_type_len+1]; int i; + size_t ret; + + ret = cnt; if (cnt > max_tracer_type_len) cnt = max_tracer_type_len; @@ -2370,7 +2407,11 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, if (strcmp(t->name, buf) == 0) break; } - if (!t || t == current_trace) + if (!t) { + ret = -EINVAL; + goto out; + } + if (t == current_trace) goto out; if (current_trace && current_trace->reset) @@ -2383,9 +2424,10 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, out: mutex_unlock(&trace_types_lock); - filp->f_pos += cnt; + if (ret > 0) + filp->f_pos += ret; - return cnt; + return ret; } static ssize_t @@ -2500,20 +2542,12 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; - struct trace_array_cpu *data; - static cpumask_t mask; - unsigned long flags; -#ifdef CONFIG_FTRACE - int ftrace_save; -#endif - int cpu; ssize_t sret; /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) return sret; - sret = 0; trace_seq_reset(&iter->seq); @@ -2524,6 +2558,8 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, goto out; } +waitagain: + sret = 0; while (trace_empty(iter)) { if ((filp->f_flags & O_NONBLOCK)) { @@ -2588,46 +2624,12 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, offsetof(struct trace_iterator, seq)); iter->pos = -1; - /* - * We need to stop all tracing on all CPUS to read the - * the next buffer. This is a bit expensive, but is - * not done often. We fill all what we can read, - * and then release the locks again. - */ - - cpus_clear(mask); - local_irq_save(flags); -#ifdef CONFIG_FTRACE - ftrace_save = ftrace_enabled; - ftrace_enabled = 0; -#endif - smp_wmb(); - for_each_tracing_cpu(cpu) { - data = iter->tr->data[cpu]; - - if (!head_page(data) || !data->trace_idx) - continue; - - atomic_inc(&data->disabled); - cpu_set(cpu, mask); - } - - for_each_cpu_mask(cpu, mask) { - data = iter->tr->data[cpu]; - __raw_spin_lock(&data->lock); - - if (data->overrun > iter->last_overrun[cpu]) - iter->overrun[cpu] += - data->overrun - iter->last_overrun[cpu]; - iter->last_overrun[cpu] = data->overrun; - } - while (find_next_entry_inc(iter) != NULL) { - int ret; + enum print_line_t ret; int len = iter->seq.len; ret = print_trace_line(iter); - if (!ret) { + if (ret == TRACE_TYPE_PARTIAL_LINE) { /* don't print partial lines */ iter->seq.len = len; break; @@ -2639,26 +2641,17 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, break; } - for_each_cpu_mask(cpu, mask) { - data = iter->tr->data[cpu]; - __raw_spin_unlock(&data->lock); - } - - for_each_cpu_mask(cpu, mask) { - data = iter->tr->data[cpu]; - atomic_dec(&data->disabled); - } -#ifdef CONFIG_FTRACE - ftrace_enabled = ftrace_save; -#endif - local_irq_restore(flags); - /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (iter->seq.readpos >= iter->seq.len) trace_seq_reset(&iter->seq); + + /* + * If there was nothing to send to user, inspite of consuming trace + * entries, go back to wait for more entries. + */ if (sret == -EBUSY) - sret = 0; + goto waitagain; out: mutex_unlock(&trace_types_lock); @@ -2684,7 +2677,8 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, { unsigned long val; char buf[64]; - int i, ret; + int ret, cpu; + struct trace_array *tr = filp->private_data; if (cnt >= sizeof(buf)) return -EINVAL; @@ -2704,71 +2698,111 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); - if (current_trace != &no_tracer) { + if (tr->ctrl) { cnt = -EBUSY; - pr_info("ftrace: set current_tracer to none" + pr_info("ftrace: please disable tracing" " before modifying buffer size\n"); goto out; } - if (val > global_trace.entries) { - long pages_requested; - unsigned long freeable_pages; - - /* make sure we have enough memory before mapping */ - pages_requested = - (val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE; - - /* account for each buffer (and max_tr) */ - pages_requested *= tracing_nr_buffers * 2; - - /* Check for overflow */ - if (pages_requested < 0) { - cnt = -ENOMEM; - goto out; - } - - freeable_pages = determine_dirtyable_memory(); + /* disable all cpu buffers */ + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_inc(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_inc(&max_tr.data[cpu]->disabled); + } - /* we only allow to request 1/4 of useable memory */ - if (pages_requested > - ((freeable_pages + tracing_pages_allocated) / 4)) { - cnt = -ENOMEM; + if (val != global_trace.entries) { + ret = ring_buffer_resize(global_trace.buffer, val); + if (ret < 0) { + cnt = ret; goto out; } - while (global_trace.entries < val) { - if (trace_alloc_page()) { - cnt = -ENOMEM; - goto out; + ret = ring_buffer_resize(max_tr.buffer, val); + if (ret < 0) { + int r; + cnt = ret; + r = ring_buffer_resize(global_trace.buffer, + global_trace.entries); + if (r < 0) { + /* AARGH! We are left with different + * size max buffer!!!! */ + WARN_ON(1); + tracing_disabled = 1; } - /* double check that we don't go over the known pages */ - if (tracing_pages_allocated > pages_requested) - break; + goto out; } - } else { - /* include the number of entries in val (inc of page entries) */ - while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1)) - trace_free_page(); + global_trace.entries = val; } - /* check integrity */ - for_each_tracing_cpu(i) - check_pages(global_trace.data[i]); - filp->f_pos += cnt; /* If check pages failed, return ENOMEM */ if (tracing_disabled) cnt = -ENOMEM; out: + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_dec(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_dec(&max_tr.data[cpu]->disabled); + } + max_tr.entries = global_trace.entries; mutex_unlock(&trace_types_lock); return cnt; } +static int mark_printk(const char *fmt, ...) +{ + int ret; + va_list args; + va_start(args, fmt); + ret = trace_vprintk(0, fmt, args); + va_end(args); + return ret; +} + +static ssize_t +tracing_mark_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *fpos) +{ + char *buf; + char *end; + struct trace_array *tr = &global_trace; + + if (!tr->ctrl || tracing_disabled) + return -EINVAL; + + if (cnt > TRACE_BUF_SIZE) + cnt = TRACE_BUF_SIZE; + + buf = kmalloc(cnt + 1, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + if (copy_from_user(buf, ubuf, cnt)) { + kfree(buf); + return -EFAULT; + } + + /* Cut from the first nil or newline. */ + buf[cnt] = '\0'; + end = strchr(buf, '\n'); + if (end) + *end = '\0'; + + cnt = mark_printk("%s\n", buf); + kfree(buf); + *fpos += cnt; + + return cnt; +} + static struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, @@ -2800,6 +2834,11 @@ static struct file_operations tracing_entries_fops = { .write = tracing_entries_write, }; +static struct file_operations tracing_mark_fops = { + .open = tracing_open_generic, + .write = tracing_mark_write, +}; + #ifdef CONFIG_DYNAMIC_FTRACE static ssize_t @@ -2846,7 +2885,7 @@ struct dentry *tracing_init_dentry(void) #include "trace_selftest.c" #endif -static __init void tracer_init_debugfs(void) +static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; struct dentry *entry; @@ -2881,12 +2920,12 @@ static __init void tracer_init_debugfs(void) entry = debugfs_create_file("available_tracers", 0444, d_tracer, &global_trace, &show_traces_fops); if (!entry) - pr_warning("Could not create debugfs 'trace' entry\n"); + pr_warning("Could not create debugfs 'available_tracers' entry\n"); entry = debugfs_create_file("current_tracer", 0444, d_tracer, &global_trace, &set_tracer_fops); if (!entry) - pr_warning("Could not create debugfs 'trace' entry\n"); + pr_warning("Could not create debugfs 'current_tracer' entry\n"); entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer, &tracing_max_latency, @@ -2899,7 +2938,7 @@ static __init void tracer_init_debugfs(void) &tracing_thresh, &tracing_max_lat_fops); if (!entry) pr_warning("Could not create debugfs " - "'tracing_threash' entry\n"); + "'tracing_thresh' entry\n"); entry = debugfs_create_file("README", 0644, d_tracer, NULL, &tracing_readme_fops); if (!entry) @@ -2909,13 +2948,19 @@ static __init void tracer_init_debugfs(void) NULL, &tracing_pipe_fops); if (!entry) pr_warning("Could not create debugfs " - "'tracing_threash' entry\n"); + "'trace_pipe' entry\n"); entry = debugfs_create_file("trace_entries", 0644, d_tracer, &global_trace, &tracing_entries_fops); if (!entry) pr_warning("Could not create debugfs " - "'tracing_threash' entry\n"); + "'trace_entries' entry\n"); + + entry = debugfs_create_file("trace_marker", 0220, d_tracer, + NULL, &tracing_mark_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'trace_marker' entry\n"); #ifdef CONFIG_DYNAMIC_FTRACE entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer, @@ -2928,230 +2973,263 @@ static __init void tracer_init_debugfs(void) #ifdef CONFIG_SYSPROF_TRACER init_tracer_sysprof_debugfs(d_tracer); #endif + return 0; } -static int trace_alloc_page(void) +int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { + static DEFINE_SPINLOCK(trace_buf_lock); + static char trace_buf[TRACE_BUF_SIZE]; + + struct ring_buffer_event *event; + struct trace_array *tr = &global_trace; struct trace_array_cpu *data; - struct page *page, *tmp; - LIST_HEAD(pages); - void *array; - unsigned pages_allocated = 0; - int i; + struct print_entry *entry; + unsigned long flags, irq_flags; + int cpu, len = 0, size, pc; - /* first allocate a page for each CPU */ - for_each_tracing_cpu(i) { - array = (void *)__get_free_page(GFP_KERNEL); - if (array == NULL) { - printk(KERN_ERR "tracer: failed to allocate page" - "for trace buffer!\n"); - goto free_pages; - } + if (!tr->ctrl || tracing_disabled) + return 0; - pages_allocated++; - page = virt_to_page(array); - list_add(&page->lru, &pages); + pc = preempt_count(); + preempt_disable_notrace(); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; -/* Only allocate if we are actually using the max trace */ -#ifdef CONFIG_TRACER_MAX_TRACE - array = (void *)__get_free_page(GFP_KERNEL); - if (array == NULL) { - printk(KERN_ERR "tracer: failed to allocate page" - "for trace buffer!\n"); - goto free_pages; - } - pages_allocated++; - page = virt_to_page(array); - list_add(&page->lru, &pages); -#endif - } + if (unlikely(atomic_read(&data->disabled))) + goto out; - /* Now that we successfully allocate a page per CPU, add them */ - for_each_tracing_cpu(i) { - data = global_trace.data[i]; - page = list_entry(pages.next, struct page, lru); - list_del_init(&page->lru); - list_add_tail(&page->lru, &data->trace_pages); - ClearPageLRU(page); + spin_lock_irqsave(&trace_buf_lock, flags); + len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); -#ifdef CONFIG_TRACER_MAX_TRACE - data = max_tr.data[i]; - page = list_entry(pages.next, struct page, lru); - list_del_init(&page->lru); - list_add_tail(&page->lru, &data->trace_pages); - SetPageLRU(page); -#endif - } - tracing_pages_allocated += pages_allocated; - global_trace.entries += ENTRIES_PER_PAGE; + len = min(len, TRACE_BUF_SIZE-1); + trace_buf[len] = 0; - return 0; + size = sizeof(*entry) + len + 1; + event = ring_buffer_lock_reserve(tr->buffer, size, &irq_flags); + if (!event) + goto out_unlock; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_PRINT; + entry->ip = ip; - free_pages: - list_for_each_entry_safe(page, tmp, &pages, lru) { - list_del_init(&page->lru); - __free_page(page); - } - return -ENOMEM; + memcpy(&entry->buf, trace_buf, len); + entry->buf[len] = 0; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + out_unlock: + spin_unlock_irqrestore(&trace_buf_lock, flags); + + out: + preempt_enable_notrace(); + + return len; } +EXPORT_SYMBOL_GPL(trace_vprintk); -static int trace_free_page(void) +int __ftrace_printk(unsigned long ip, const char *fmt, ...) { - struct trace_array_cpu *data; - struct page *page; - struct list_head *p; - int i; - int ret = 0; + int ret; + va_list ap; - /* free one page from each buffer */ - for_each_tracing_cpu(i) { - data = global_trace.data[i]; - p = data->trace_pages.next; - if (p == &data->trace_pages) { - /* should never happen */ - WARN_ON(1); - tracing_disabled = 1; - ret = -1; - break; - } - page = list_entry(p, struct page, lru); - ClearPageLRU(page); - list_del(&page->lru); - tracing_pages_allocated--; - tracing_pages_allocated--; - __free_page(page); + if (!(trace_flags & TRACE_ITER_PRINTK)) + return 0; - tracing_reset(data); + va_start(ap, fmt); + ret = trace_vprintk(ip, fmt, ap); + va_end(ap); + return ret; +} +EXPORT_SYMBOL_GPL(__ftrace_printk); -#ifdef CONFIG_TRACER_MAX_TRACE - data = max_tr.data[i]; - p = data->trace_pages.next; - if (p == &data->trace_pages) { - /* should never happen */ - WARN_ON(1); - tracing_disabled = 1; - ret = -1; - break; - } - page = list_entry(p, struct page, lru); - ClearPageLRU(page); - list_del(&page->lru); - __free_page(page); +static int trace_panic_handler(struct notifier_block *this, + unsigned long event, void *unused) +{ + ftrace_dump(); + return NOTIFY_OK; +} - tracing_reset(data); -#endif - } - global_trace.entries -= ENTRIES_PER_PAGE; +static struct notifier_block trace_panic_notifier = { + .notifier_call = trace_panic_handler, + .next = NULL, + .priority = 150 /* priority: INT_MAX >= x >= 0 */ +}; - return ret; +static int trace_die_handler(struct notifier_block *self, + unsigned long val, + void *data) +{ + switch (val) { + case DIE_OOPS: + ftrace_dump(); + break; + default: + break; + } + return NOTIFY_OK; } -__init static int tracer_alloc_buffers(void) +static struct notifier_block trace_die_notifier = { + .notifier_call = trace_die_handler, + .priority = 200 +}; + +/* + * printk is set to max of 1024, we really don't need it that big. + * Nothing should be printing 1000 characters anyway. + */ +#define TRACE_MAX_PRINT 1000 + +/* + * Define here KERN_TRACE so that we have one place to modify + * it if we decide to change what log level the ftrace dump + * should be at. + */ +#define KERN_TRACE KERN_INFO + +static void +trace_printk_seq(struct trace_seq *s) { - struct trace_array_cpu *data; - void *array; - struct page *page; - int pages = 0; - int ret = -ENOMEM; - int i; + /* Probably should print a warning here. */ + if (s->len >= 1000) + s->len = 1000; - /* TODO: make the number of buffers hot pluggable with CPUS */ - tracing_nr_buffers = num_possible_cpus(); - tracing_buffer_mask = cpu_possible_map; + /* should be zero ended, but we are paranoid. */ + s->buffer[s->len] = 0; - /* Allocate the first page for all buffers */ - for_each_tracing_cpu(i) { - data = global_trace.data[i] = &per_cpu(global_trace_cpu, i); - max_tr.data[i] = &per_cpu(max_data, i); + printk(KERN_TRACE "%s", s->buffer); + + trace_seq_reset(s); +} - array = (void *)__get_free_page(GFP_KERNEL); - if (array == NULL) { - printk(KERN_ERR "tracer: failed to allocate page" - "for trace buffer!\n"); - goto free_buffers; - } - /* set the array to the list */ - INIT_LIST_HEAD(&data->trace_pages); - page = virt_to_page(array); - list_add(&page->lru, &data->trace_pages); - /* use the LRU flag to differentiate the two buffers */ - ClearPageLRU(page); +void ftrace_dump(void) +{ + static DEFINE_SPINLOCK(ftrace_dump_lock); + /* use static because iter can be a bit big for the stack */ + static struct trace_iterator iter; + static cpumask_t mask; + static int dump_ran; + unsigned long flags; + int cnt = 0, cpu; - data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; - max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + /* only one dump */ + spin_lock_irqsave(&ftrace_dump_lock, flags); + if (dump_ran) + goto out; -/* Only allocate if we are actually using the max trace */ -#ifdef CONFIG_TRACER_MAX_TRACE - array = (void *)__get_free_page(GFP_KERNEL); - if (array == NULL) { - printk(KERN_ERR "tracer: failed to allocate page" - "for trace buffer!\n"); - goto free_buffers; - } + dump_ran = 1; - INIT_LIST_HEAD(&max_tr.data[i]->trace_pages); - page = virt_to_page(array); - list_add(&page->lru, &max_tr.data[i]->trace_pages); - SetPageLRU(page); -#endif + /* No turning back! */ + ftrace_kill(); + + for_each_tracing_cpu(cpu) { + atomic_inc(&global_trace.data[cpu]->disabled); } + printk(KERN_TRACE "Dumping ftrace buffer:\n"); + + iter.tr = &global_trace; + iter.trace = current_trace; + /* - * Since we allocate by orders of pages, we may be able to - * round up a bit. + * We need to stop all tracing on all CPUS to read the + * the next buffer. This is a bit expensive, but is + * not done often. We fill all what we can read, + * and then release the locks again. */ - global_trace.entries = ENTRIES_PER_PAGE; - pages++; - while (global_trace.entries < trace_nr_entries) { - if (trace_alloc_page()) - break; - pages++; + cpus_clear(mask); + + while (!trace_empty(&iter)) { + + if (!cnt) + printk(KERN_TRACE "---------------------------------\n"); + + cnt++; + + /* reset all but tr, trace, and overruns */ + memset(&iter.seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter.iter_flags |= TRACE_FILE_LAT_FMT; + iter.pos = -1; + + if (find_next_entry_inc(&iter) != NULL) { + print_trace_line(&iter); + trace_consume(&iter); + } + + trace_printk_seq(&iter.seq); } - max_tr.entries = global_trace.entries; - pr_info("tracer: %d pages allocated for %ld entries of %ld bytes\n", - pages, trace_nr_entries, (long)TRACE_ENTRY_SIZE); - pr_info(" actual entries %ld\n", global_trace.entries); + if (!cnt) + printk(KERN_TRACE " (ftrace buffer empty)\n"); + else + printk(KERN_TRACE "---------------------------------\n"); + + out: + spin_unlock_irqrestore(&ftrace_dump_lock, flags); +} + +__init static int tracer_alloc_buffers(void) +{ + struct trace_array_cpu *data; + int i; + + /* TODO: make the number of buffers hot pluggable with CPUS */ + tracing_buffer_mask = cpu_possible_map; + + global_trace.buffer = ring_buffer_alloc(trace_buf_size, + TRACE_BUFFER_FLAGS); + if (!global_trace.buffer) { + printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); + WARN_ON(1); + return 0; + } + global_trace.entries = ring_buffer_size(global_trace.buffer); + +#ifdef CONFIG_TRACER_MAX_TRACE + max_tr.buffer = ring_buffer_alloc(trace_buf_size, + TRACE_BUFFER_FLAGS); + if (!max_tr.buffer) { + printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); + WARN_ON(1); + ring_buffer_free(global_trace.buffer); + return 0; + } + max_tr.entries = ring_buffer_size(max_tr.buffer); + WARN_ON(max_tr.entries != global_trace.entries); +#endif - tracer_init_debugfs(); + /* Allocate the first page for all buffers */ + for_each_tracing_cpu(i) { + data = global_trace.data[i] = &per_cpu(global_trace_cpu, i); + max_tr.data[i] = &per_cpu(max_data, i); + } trace_init_cmdlines(); - register_tracer(&no_tracer); - current_trace = &no_tracer; + register_tracer(&nop_trace); +#ifdef CONFIG_BOOT_TRACER + register_tracer(&boot_tracer); + current_trace = &boot_tracer; + current_trace->init(&global_trace); +#else + current_trace = &nop_trace; +#endif /* All seems OK, enable tracing */ global_trace.ctrl = tracer_enabled; tracing_disabled = 0; - return 0; - - free_buffers: - for (i-- ; i >= 0; i--) { - struct page *page, *tmp; - struct trace_array_cpu *data = global_trace.data[i]; + atomic_notifier_chain_register(&panic_notifier_list, + &trace_panic_notifier); - if (data) { - list_for_each_entry_safe(page, tmp, - &data->trace_pages, lru) { - list_del_init(&page->lru); - __free_page(page); - } - } + register_die_notifier(&trace_die_notifier); -#ifdef CONFIG_TRACER_MAX_TRACE - data = max_tr.data[i]; - if (data) { - list_for_each_entry_safe(page, tmp, - &data->trace_pages, lru) { - list_del_init(&page->lru); - __free_page(page); - } - } -#endif - } - return ret; + return 0; } -fs_initcall(tracer_alloc_buffers); +early_initcall(tracer_alloc_buffers); +fs_initcall(tracer_init_debugfs); |