[RFC PATCH 3/3] ftrace: hack in the ring buffer

From: Steven Rostedt
Date: Wed Sep 24 2008 - 01:14:58 EST


As a test case for the unified ring buffer, I wanted to try it out with
ftrace. This is a big patch that hacks up ftrace to get it to work.
Actually, I see areas that can be greatly improved with this new approach.
A lot of clean ups can follow this.

But before I go ahead and do all this work, I want to "release early
release often". This way I can get the feedback (whew, it's hot in here)
that will let me know what is expected.

Note, selftest is busted with this patch. I didn't have time to fixe it.

All these patches are busted, this is RFC remember!

Signed-off-by: Steven Rostedt <srostedt@xxxxxxxxxx>
---
arch/x86/kernel/Makefile | 1
include/linux/ftrace.h | 6
include/linux/mmiotrace.h | 3
kernel/trace/trace.c | 1326 ++++++++++----------------------------
kernel/trace/trace.h | 87 --
kernel/trace/trace_functions.c | 2
kernel/trace/trace_irqsoff.c | 38 -
kernel/trace/trace_mmiotrace.c | 73 --
kernel/trace/trace_sched_switch.c | 2
kernel/trace/trace_sched_wakeup.c | 3
10 files changed, 464 insertions(+), 1077 deletions(-)

Index: linux-compile.git/kernel/trace/trace.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace.c 2008-09-23 23:33:47.000000000 -0400
+++ linux-compile.git/kernel/trace/trace.c 2008-09-24 00:16:24.000000000 -0400
@@ -31,25 +31,24 @@
#include <linux/writeback.h>

#include <linux/stacktrace.h>
+#include <linux/ring_buffer.h>

#include "trace.h"

+#define FTRACE_BUF_NAME "ftrace"
+
+#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE | RB_FL_SNAPSHOT)
+
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 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)
{
@@ -79,20 +78,6 @@ static struct trace_array global_trace;

static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);

-/*
- * The max_tr is used to snapshot the global_trace when a maximum
- * latency is reached. Some tracers will use this to store a maximum
- * trace while it continues examining live traces.
- *
- * The buffers for the max_tr are set up the same as the global_trace.
- * When a snapshot is taken, the link list of the max_tr is swapped
- * with the link list of the global_trace and the buffers are reset for
- * the global_trace so the tracing can continue.
- */
-static struct trace_array max_tr;
-
-static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
-
/* tracer_enabled is used to toggle activation of a tracer */
static int tracer_enabled = 1;

@@ -100,11 +85,11 @@ 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.
*/
-static unsigned long trace_nr_entries = 65536UL;
+static unsigned long trace_buf_size = 65536UL;

/* trace_types holds a link list of available tracers. */
static struct tracer *trace_types __read_mostly;
@@ -140,7 +125,7 @@ static notrace void no_trace_init(struct
ftrace_function_enabled = 0;
if(tr->ctrl)
for_each_online_cpu(cpu)
- tracing_reset(tr->data[cpu]);
+ tracing_reset(tr, cpu);
tracer_enabled = 0;
}

@@ -167,23 +152,21 @@ 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)
{
@@ -249,245 +232,20 @@ __update_max_tr(struct trace_array *tr,
{
struct trace_array_cpu *data = tr->data[cpu];

- max_tr.cpu = cpu;
- max_tr.time_start = data->preempt_timestamp;
-
- data = max_tr.data[cpu];
- data->saved_latency = tracing_max_latency;
-
- memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
- data->pid = tsk->pid;
- data->uid = tsk->uid;
- data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
- data->policy = tsk->policy;
- data->rt_priority = tsk->rt_priority;
+ tr->cpu = cpu;
+ tr->time_start = data->preempt_timestamp;
+ tr->saved_latency = tracing_max_latency;
+ tr->pid = tsk->pid;
+ tr->uid = tsk->uid;
+ tr->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+ tr->policy = tsk->policy;
+ tr->rt_priority = tsk->rt_priority;
+ memcpy(tr->comm, tsk->comm, TASK_COMM_LEN);

/* record this tasks comm */
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
- * @fmt: printf format string
- *
- * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
- * trace_seq_printf is used to store strings into a special
- * buffer (@s). Then the output may be either used by
- * the sequencer or pulled into another buffer.
- */
-int
-trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-{
- int len = (PAGE_SIZE - 1) - s->len;
- va_list ap;
- int ret;
-
- if (!len)
- return 0;
-
- va_start(ap, fmt);
- ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
- va_end(ap);
-
- /* If we can't write it all, don't bother writing anything */
- if (ret >= len)
- return 0;
-
- s->len += ret;
-
- return len;
-}
-
-/**
- * trace_seq_puts - trace sequence printing of simple string
- * @s: trace sequence descriptor
- * @str: simple string to record
- *
- * The tracer may use either the sequence operations or its own
- * copy to user routines. This function records a simple string
- * into a special buffer (@s) for later retrieval by a sequencer
- * or other mechanism.
- */
-static int
-trace_seq_puts(struct trace_seq *s, const char *str)
-{
- int len = strlen(str);
-
- if (len > ((PAGE_SIZE - 1) - s->len))
- return 0;
-
- memcpy(s->buffer + s->len, str, len);
- s->len += len;
-
- return len;
-}
-
-static int
-trace_seq_putc(struct trace_seq *s, unsigned char c)
-{
- if (s->len >= (PAGE_SIZE - 1))
- return 0;
-
- s->buffer[s->len++] = c;
-
- return 1;
-}
-
-static int
-trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
-{
- if (len > ((PAGE_SIZE - 1) - s->len))
- return 0;
-
- memcpy(s->buffer + s->len, mem, len);
- s->len += len;
-
- return len;
-}
-
-#define HEX_CHARS 17
-static const char hex2asc[] = "0123456789abcdef";
-
-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++] = ' ';
-
- return trace_seq_putmem(s, hex, j);
-}
-
-static void
-trace_seq_reset(struct trace_seq *s)
-{
- s->len = 0;
- s->readpos = 0;
-}
-
-ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
-{
- int len;
- int ret;
-
- if (s->len <= s->readpos)
- return -EBUSY;
-
- len = s->len - s->readpos;
- if (cnt > len)
- cnt = len;
- ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
- if (ret)
- return -EFAULT;
-
- s->readpos += len;
- return cnt;
-}
-
-static void
-trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
- int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-
- s->buffer[len] = 0;
- seq_puts(m, s->buffer);
-
- 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
@@ -500,18 +258,9 @@ flip_trace(struct trace_array_cpu *tr1,
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct trace_array_cpu *data;
- int i;
-
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);
- }
-
+ ring_buffer_snapshot(tr->buffer);
__update_max_tr(tr, tsk, cpu);
__raw_spin_unlock(&ftrace_max_lock);
}
@@ -527,21 +276,20 @@ update_max_tr(struct trace_array *tr, st
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;
-
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);
-
+ ring_buffer_snapshot_one_cpu(tr->buffer, cpu);
__update_max_tr(tr, tsk, cpu);
__raw_spin_unlock(&ftrace_max_lock);
}

+#define CHECK_COND(cond) \
+ if (unlikely(cond)) { \
+ tracing_disabled = 1; \
+ WARN_ON(1); \
+ return -1; \
+ }
+
/**
* register_tracer - register a tracer with the ftrace system.
* @type - the plugin for the tracer
@@ -573,7 +321,6 @@ 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 +332,7 @@ 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 +348,7 @@ 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 +394,9 @@ void unregister_tracer(struct tracer *ty
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;
+ ring_buffer_reset_cpu(tr->buffer, cpu);
}

#define SAVED_CMDLINES 128
@@ -745,70 +482,6 @@ void tracing_record_cmdline(struct task_
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)
{
@@ -819,7 +492,6 @@ tracing_generic_entry_update(struct trac

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) |
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
@@ -830,18 +502,17 @@ void
trace_function(struct trace_array *tr, struct trace_array_cpu *data,
unsigned long ip, unsigned long parent_ip, unsigned long flags)
{
- struct trace_entry *entry;
+ 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);
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_FN, sizeof(*entry),
+ &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, flags);
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);
}

void
@@ -856,19 +527,16 @@ ftrace(struct trace_array *tr, struct tr
void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data,
struct mmiotrace_rw *rw)
{
- struct trace_entry *entry;
+ struct mmiotrace_rw *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_MMIO_RW;
- entry->mmiorw = *rw;
-
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_MMIO_RW,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, 0);
+ *entry = *rw;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);

trace_wake_up();
}
@@ -876,19 +544,16 @@ void __trace_mmiotrace_rw(struct trace_a
void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data,
struct mmiotrace_map *map)
{
- struct trace_entry *entry;
+ struct mmiotrace_map *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_MMIO_MAP;
- entry->mmiomap = *map;
-
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_MMIO_MAP,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, 0);
+ *entry = *map;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);

trace_wake_up();
}
@@ -899,24 +564,28 @@ void __trace_stack(struct trace_array *t
unsigned long flags,
int skip)
{
- struct trace_entry *entry;
+ struct stack_entry *entry;
struct stack_trace trace;
+ unsigned long irq_flags;

if (!(trace_flags & TRACE_ITER_STACKTRACE))
return;

- entry = tracing_get_trace_entry(tr, data);
- tracing_generic_entry_update(entry, flags);
- entry->type = TRACE_STACK;
+ entry = ring_buffer_lock_reserve(tr->buffer, FTRACE_STACK_ENTRIES,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, flags);

- memset(&entry->stack, 0, sizeof(entry->stack));
+ memset(&entry->caller, 0, sizeof(entry->caller));

trace.nr_entries = 0;
trace.max_entries = FTRACE_STACK_ENTRIES;
trace.skip = skip;
- trace.entries = entry->stack.caller;
+ trace.entries = entry->caller;

save_stack_trace(&trace);
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);
}

void
@@ -925,20 +594,19 @@ __trace_special(void *__tr, void *__data
{
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;
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_SPECIAL,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, 0);
+ entry->arg1 = arg1;
+ entry->arg2 = arg2;
+ entry->arg3 = arg3;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);
__trace_stack(tr, data, irq_flags, 4);
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);

trace_wake_up();
}
@@ -950,23 +618,22 @@ tracing_sched_switch_trace(struct trace_
struct task_struct *next,
unsigned long flags)
{
- struct trace_entry *entry;
+ 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;
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_CTX,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, flags);
+ 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;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);
__trace_stack(tr, data, flags, 5);
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);
}

void
@@ -976,23 +643,22 @@ tracing_sched_wakeup_trace(struct trace_
struct task_struct *curr,
unsigned long flags)
{
- struct trace_entry *entry;
+ 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;
+ entry = ring_buffer_lock_reserve(tr->buffer, TRACE_WAKE,
+ sizeof(*entry), &irq_flags);
+ if (!entry)
+ return;
+ tracing_generic_entry_update(&entry->ent, flags);
+ 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;
+ ring_buffer_unlock_commit(tr->buffer, entry, irq_flags);
__trace_stack(tr, data, flags, 6);
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);

trace_wake_up();
}
@@ -1070,112 +736,21 @@ void tracing_stop_function_trace(void)
#endif

enum trace_file_type {
- TRACE_FILE_LAT_FMT = 1,
+ TRACE_FILE_LAT_FMT = 1 << 0,
+ TRACE_FILE_USE_MAX = 1 << 1,
};

-static struct trace_entry *
-trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data,
- struct trace_iterator *iter, int cpu)
-{
- struct page *page;
- struct trace_entry *array;
-
- 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;
-
- 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;
- }
-
- page = list_entry(iter->next_page[cpu], struct page, lru);
- BUG_ON(&data->trace_pages == &page->lru);
-
- array = page_address(page);
-
- WARN_ON(iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE);
- return &array[iter->next_page_idx[cpu]];
-}
-
-static struct trace_entry *
-find_next_entry(struct trace_iterator *iter, int *ent_cpu)
-{
- struct trace_array *tr = iter->tr;
- struct trace_entry *ent, *next = NULL;
- int next_cpu = -1;
- int cpu;
-
- for_each_tracing_cpu(cpu) {
- if (!head_page(tr->data[cpu]))
- continue;
- ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
- /*
- * Pick the entry with the smallest timestamp:
- */
- if (ent && (!next || ent->t < next->t)) {
- next = ent;
- next_cpu = cpu;
- }
- }
-
- if (ent_cpu)
- *ent_cpu = next_cpu;
-
- return next;
-}
-
-static void trace_iterator_increment(struct trace_iterator *iter)
-{
- 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]);
- }
-}
-
-static void trace_consume(struct trace_iterator *iter)
-{
- struct trace_array_cpu *data = iter->tr->data[iter->cpu];
-
- 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;
- }
-
- /* 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;
-}
-
static void *find_next_entry_inc(struct trace_iterator *iter)
{
- struct trace_entry *next;
+ struct ring_buffer_event *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;
+ next = ring_buffer_read(iter->buffer_iter, &next_cpu);
+ iter->event = next;
iter->cpu = next_cpu;

if (next)
- trace_iterator_increment(iter);
+ iter->idx++;

return next ? iter : NULL;
}
@@ -1210,7 +785,6 @@ static void *s_start(struct seq_file *m,
struct trace_iterator *iter = m->private;
void *p = NULL;
loff_t l = 0;
- int i;

mutex_lock(&trace_types_lock);

@@ -1226,16 +800,9 @@ static void *s_start(struct seq_file *m,
current_trace->start(iter);

if (*pos != iter->pos) {
- iter->ent = NULL;
+ iter->event = 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;
- }

for (p = iter; p && l < *pos; p = s_next(m, p, &l))
;
@@ -1276,27 +843,27 @@ static inline int kretprobed(unsigned lo
#endif /* CONFIG_KRETPROBES */

static int
-seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
+seq_print_sym_short(struct ring_buffer_seq *s, const char *fmt, unsigned long address)
{
#ifdef CONFIG_KALLSYMS
char str[KSYM_SYMBOL_LEN];

kallsyms_lookup(address, NULL, NULL, NULL, str);

- return trace_seq_printf(s, fmt, str);
+ return ring_buffer_seq_printf(s, fmt, str);
#endif
return 1;
}

static int
-seq_print_sym_offset(struct trace_seq *s, const char *fmt,
+seq_print_sym_offset(struct ring_buffer_seq *s, const char *fmt,
unsigned long address)
{
#ifdef CONFIG_KALLSYMS
char str[KSYM_SYMBOL_LEN];

sprint_symbol(str, address);
- return trace_seq_printf(s, fmt, str);
+ return ring_buffer_seq_printf(s, fmt, str);
#endif
return 1;
}
@@ -1308,12 +875,12 @@ seq_print_sym_offset(struct trace_seq *s
#endif

static int
-seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
+seq_print_ip_sym(struct ring_buffer_seq *s, unsigned long ip, unsigned long sym_flags)
{
int ret;

if (!ip)
- return trace_seq_printf(s, "0");
+ return ring_buffer_seq_printf(s, "0");

if (sym_flags & TRACE_ITER_SYM_OFFSET)
ret = seq_print_sym_offset(s, "%s", ip);
@@ -1324,7 +891,7 @@ seq_print_ip_sym(struct trace_seq *s, un
return 0;

if (sym_flags & TRACE_ITER_SYM_ADDR)
- ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ ret = ring_buffer_seq_printf(s, " <" IP_FMT ">", ip);
return ret;
}

@@ -1357,21 +924,12 @@ print_trace_header(struct seq_file *m, s
struct tracer *type = current_trace;
unsigned long total = 0;
unsigned long entries = 0;
- int cpu;
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);

seq_printf(m, "%s latency trace v1.1.5 on %s\n",
name, UTS_RELEASE);
@@ -1379,7 +937,7 @@ print_trace_header(struct seq_file *m, s
"---------------------------------\n");
seq_printf(m, " latency: %lu us, #%lu/%lu, CPU#%d |"
" (M:%s VP:%d, KP:%d, SP:%d HP:%d",
- nsecs_to_usecs(data->saved_latency),
+ nsecs_to_usecs(tr->saved_latency),
entries,
total,
tr->cpu,
@@ -1402,17 +960,17 @@ print_trace_header(struct seq_file *m, s
seq_puts(m, " -----------------\n");
seq_printf(m, " | task: %.16s-%d "
"(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n",
- data->comm, data->pid, data->uid, data->nice,
- data->policy, data->rt_priority);
+ tr->comm, tr->pid, tr->uid, tr->nice,
+ tr->policy, tr->rt_priority);
seq_puts(m, " -----------------\n");

if (data->critical_start) {
seq_puts(m, " => started at: ");
- seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags);
- trace_print_seq(m, &iter->seq);
+ seq_print_ip_sym(iter->seq, data->critical_start, sym_flags);
+ ring_buffer_seq_to_seqfile(m, iter->seq);
seq_puts(m, "\n => ended at: ");
- seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
- trace_print_seq(m, &iter->seq);
+ seq_print_ip_sym(iter->seq, data->critical_end, sym_flags);
+ ring_buffer_seq_to_seqfile(m, iter->seq);
seq_puts(m, "\n");
}

@@ -1420,71 +978,71 @@ print_trace_header(struct seq_file *m, s
}

static void
-lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu)
+lat_print_generic(struct ring_buffer_seq *s, struct trace_entry *entry, int cpu)
{
int hardirq, softirq;
char *comm;

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, "%c%c",
+ ring_buffer_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid);
+ ring_buffer_seq_printf(s, "%d", cpu);
+ ring_buffer_seq_printf(s, "%c%c",
(entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.',
((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.'));

hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
if (hardirq && softirq) {
- trace_seq_putc(s, 'H');
+ ring_buffer_seq_putc(s, 'H');
} else {
if (hardirq) {
- trace_seq_putc(s, 'h');
+ ring_buffer_seq_putc(s, 'h');
} else {
if (softirq)
- trace_seq_putc(s, 's');
+ ring_buffer_seq_putc(s, 's');
else
- trace_seq_putc(s, '.');
+ ring_buffer_seq_putc(s, '.');
}
}

if (entry->preempt_count)
- trace_seq_printf(s, "%x", entry->preempt_count);
+ ring_buffer_seq_printf(s, "%x", entry->preempt_count);
else
- trace_seq_puts(s, ".");
+ ring_buffer_seq_puts(s, ".");
}

unsigned long preempt_mark_thresh = 100;

static void
-lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
+lat_print_timestamp(struct ring_buffer_seq *s, unsigned long long abs_usecs,
unsigned long rel_usecs)
{
- trace_seq_printf(s, " %4lldus", abs_usecs);
+ ring_buffer_seq_printf(s, " %4lldus", abs_usecs);
if (rel_usecs > preempt_mark_thresh)
- trace_seq_puts(s, "!: ");
+ ring_buffer_seq_puts(s, "!: ");
else if (rel_usecs > 1)
- trace_seq_puts(s, "+: ");
+ ring_buffer_seq_puts(s, "+: ");
else
- trace_seq_puts(s, " : ");
+ ring_buffer_seq_puts(s, " : ");
}

static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;

#define SEQ_PUT_FIELD_RET(s, x) \
do { \
- if (!trace_seq_putmem(s, &(x), sizeof(x))) \
+ if (!ring_buffer_seq_putmem(s, &(x), sizeof(x))) \
return 0; \
} while (0)

#define SEQ_PUT_HEX_FIELD_RET(s, x) \
do { \
- if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \
+ if (!ring_buffer_seq_putmem_hex(s, &(x), sizeof(x))) \
return 0; \
} while (0)

static int
-trace_print_func(struct trace_seq *s, struct ftrace_entry *entry,
+trace_print_func(struct ring_buffer_seq *s, struct ftrace_entry *entry,
int sym_flags, int print_type)
{
int ret = 1;
@@ -1499,17 +1057,17 @@ trace_print_func(struct trace_seq *s, st
SEQ_PUT_HEX_FIELD_RET(s, entry->parent_ip);
break;
case TRACE_ITER_RAW:
- ret = trace_seq_printf(s, "%x %x\n",
+ ret = ring_buffer_seq_printf(s, "%lx %lx\n",
entry->ip, entry->parent_ip);
break;
case TRACE_FILE_LAT_FMT:
seq_print_ip_sym(s, entry->ip, sym_flags);
- trace_seq_puts(s, " (");
+ ring_buffer_seq_puts(s, " (");
if (kretprobed(entry->parent_ip))
- trace_seq_puts(s, KRETPROBE_MSG);
+ ring_buffer_seq_puts(s, KRETPROBE_MSG);
else
seq_print_ip_sym(s, entry->parent_ip, sym_flags);
- trace_seq_puts(s, ")\n");
+ ring_buffer_seq_puts(s, ")\n");
break;
default:
ret = seq_print_ip_sym(s, entry->ip, sym_flags);
@@ -1517,25 +1075,25 @@ trace_print_func(struct trace_seq *s, st
return 0;
if ((sym_flags & TRACE_ITER_PRINT_PARENT) &&
entry->parent_ip) {
- ret = trace_seq_printf(s, " <-");
+ ret = ring_buffer_seq_printf(s, " <-");
if (!ret)
return 0;
if (kretprobed(entry->parent_ip))
- ret = trace_seq_puts(s, KRETPROBE_MSG);
+ ret = ring_buffer_seq_puts(s, KRETPROBE_MSG);
else
ret = seq_print_ip_sym(s, entry->parent_ip,
sym_flags);
if (!ret)
return 0;
}
- ret = trace_seq_printf(s, "\n");
+ ret = ring_buffer_seq_printf(s, "\n");
}

return ret;
}

static int
-trace_print_ctx(struct trace_seq *s, struct ctx_switch_entry *entry,
+trace_print_ctx(struct ring_buffer_seq *s, struct ctx_switch_entry *entry,
int type, int print_type)
{
unsigned state;
@@ -1571,7 +1129,7 @@ trace_print_ctx(struct trace_seq *s, str
case TRACE_ITER_RAW:
if (type == TRACE_WAKE)
S = '+';
- ret = trace_seq_printf(s, "%d %d %c %d %d %c\n",
+ ret = ring_buffer_seq_printf(s, "%d %d %c %d %d %c\n",
entry->prev_pid,
entry->prev_prio,
S,
@@ -1581,7 +1139,7 @@ trace_print_ctx(struct trace_seq *s, str
break;
default:
comm = trace_find_cmdline(entry->next_pid);
- ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n",
+ ret = ring_buffer_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n",
entry->prev_pid,
entry->prev_prio,
S, type == TRACE_CTX ? "==>" : " +",
@@ -1594,7 +1152,7 @@ trace_print_ctx(struct trace_seq *s, str
}

static int
-trace_print_special(struct trace_seq *s, struct special_entry *entry,
+trace_print_special(struct ring_buffer_seq *s, struct special_entry *entry,
int print_type)
{
int ret = 0;
@@ -1612,7 +1170,7 @@ trace_print_special(struct trace_seq *s,
break;
case TRACE_ITER_RAW:
default:
- ret = trace_seq_printf(s, "# %ld %ld %ld\n",
+ ret = ring_buffer_seq_printf(s, "# %ld %ld %ld\n",
entry->arg1,
entry->arg2,
entry->arg3);
@@ -1621,7 +1179,7 @@ trace_print_special(struct trace_seq *s,
}

static int
-trace_print_stack(struct trace_seq *s, struct stack_entry *entry, int sym_flags,
+trace_print_stack(struct ring_buffer_seq *s, struct stack_entry *entry, int sym_flags,
int print_type)
{
int i;
@@ -1634,7 +1192,7 @@ trace_print_stack(struct trace_seq *s, s
default:
for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
if (i) {
- ret = trace_seq_puts(s, " <= ");
+ ret = ring_buffer_seq_puts(s, " <= ");
if (!ret)
return 0;
}
@@ -1643,7 +1201,7 @@ trace_print_stack(struct trace_seq *s, s
if (!ret)
return 0;
}
- ret = trace_seq_puts(s, "\n");
+ ret = ring_buffer_seq_puts(s, "\n");
}

return ret;
@@ -1652,29 +1210,35 @@ trace_print_stack(struct trace_seq *s, s
static int
print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
{
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_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 ring_buffer_event *next_event = ring_buffer_peek(iter->buffer_iter, NULL);
unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE);
- struct trace_entry *entry = iter->ent;
+ struct trace_entry *entry = ring_buffer_event_data(iter->event);
+ unsigned long long ns1, ns2;
unsigned long abs_usecs;
unsigned long rel_usecs;
char *comm;
int print_type = TRACE_FILE_LAT_FMT;
+ int type;
+
+ if (!next_event)
+ next_event = iter->event;
+ ns1 = ring_buffer_event_counter(iter->event);
+ ns2 = ring_buffer_event_counter(next_event);
+ rel_usecs = ns2usecs(ns2 - ns1);
+ abs_usecs = ns2usecs(ns1 - iter->tr->time_start);

- if (!next_entry)
- next_entry = entry;
- rel_usecs = ns2usecs(next_entry->t - entry->t);
- abs_usecs = ns2usecs(entry->t - iter->tr->time_start);
+ type = ring_buffer_event_type(iter->event);

if (verbose) {
comm = trace_find_cmdline(entry->pid);
- trace_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]"
+ ring_buffer_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]"
" %ld.%03ldms (+%ld.%03ldms): ",
comm,
entry->pid, cpu, entry->flags,
entry->preempt_count, trace_idx,
- ns2usecs(entry->t),
+ ns2usecs(ns1),
abs_usecs/1000,
abs_usecs % 1000, rel_usecs/1000,
rel_usecs % 1000);
@@ -1682,74 +1246,77 @@ print_lat_fmt(struct trace_iterator *ite
lat_print_generic(s, entry, cpu);
lat_print_timestamp(s, abs_usecs, rel_usecs);
}
- switch (entry->type) {
+ switch (type) {
case TRACE_FN:
- trace_print_func(s, &entry->fn, sym_flags, print_type);
+ trace_print_func(s, (struct ftrace_entry *)entry, sym_flags, print_type);
break;
case TRACE_CTX:
case TRACE_WAKE:
- trace_print_ctx(s, &entry->ctx, entry->type, print_type);
+ trace_print_ctx(s, (struct ctx_switch_entry *)entry, type, print_type);
break;
case TRACE_SPECIAL:
- trace_print_special(s, &entry->special, print_type);
+ trace_print_special(s, (struct special_entry *)entry, print_type);
break;
case TRACE_STACK:
- trace_print_stack(s, &entry->stack, sym_flags, print_type);
+ trace_print_stack(s, (struct stack_entry *)entry, sym_flags, print_type);
break;
default:
- trace_seq_printf(s, "Unknown type %d\n", entry->type);
+ ring_buffer_seq_printf(s, "Unknown type %d\n", type);
}
return 1;
}

static int print_trace_fmt(struct trace_iterator *iter)
{
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
struct trace_entry *entry;
unsigned long usec_rem;
- unsigned long long t;
+ unsigned long long t, ns;
unsigned long secs;
char *comm;
+ int type;
int ret;

- entry = iter->ent;
+ entry = ring_buffer_event_data(iter->event);
+ type = ring_buffer_event_type(iter->event);
+ ns = ring_buffer_event_counter(iter->event);

- comm = trace_find_cmdline(iter->ent->pid);
+ comm = trace_find_cmdline(entry->pid);

- t = ns2usecs(entry->t);
+ t = ns2usecs(ns);
usec_rem = do_div(t, 1000000ULL);
secs = (unsigned long)t;

- ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+ ret = ring_buffer_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
if (!ret)
return 0;
- ret = trace_seq_printf(s, "[%02d] ", iter->cpu);
+ ret = ring_buffer_seq_printf(s, "[%02d] ", iter->cpu);
if (!ret)
return 0;
- ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem);
+ ret = ring_buffer_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem);
if (!ret)
return 0;

- switch (entry->type) {
+ switch (type) {
case TRACE_FN:
- ret = trace_print_func(s, &entry->fn, sym_flags, 0);
+ ret = trace_print_func(s, (struct ftrace_entry *)entry, sym_flags, 0);
if (!ret)
return 0;
break;
case TRACE_CTX:
case TRACE_WAKE:
- ret = trace_print_ctx(s, &entry->ctx, entry->type, 0);
+ ret = trace_print_ctx(s, (struct ctx_switch_entry *)entry, type, 0);
if (!ret)
return 0;
break;
case TRACE_SPECIAL:
- ret = trace_print_special(s, &entry->special, 0);
+ ret = trace_print_special(s, (struct special_entry *)entry, 0);
if (!ret)
return 0;
break;
case TRACE_STACK:
- ret = trace_print_stack(s, &entry->stack, sym_flags, 0);
+ ret = trace_print_stack(s, (struct stack_entry *)entry, sym_flags, 0);
if (!ret)
return 0;
break;
@@ -1759,33 +1326,37 @@ static int print_trace_fmt(struct trace_

static int print_raw_fmt(struct trace_iterator *iter)
{
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;
struct trace_entry *entry;
+ unsigned long long t;
+ int type;
int print_type = TRACE_ITER_RAW;
int ret;

- entry = iter->ent;
+ entry = ring_buffer_event_data(iter->event);
+ type = ring_buffer_event_type(iter->event);
+ t = ring_buffer_event_counter(iter->event);

- ret = trace_seq_printf(s, "%d %d %llu ",
- entry->pid, iter->cpu, entry->t);
+ ret = ring_buffer_seq_printf(s, "%d %d %llu ",
+ entry->pid, iter->cpu, t);
if (!ret)
return 0;

- switch (entry->type) {
+ switch (type) {
case TRACE_FN:
- ret = trace_print_func(s, &entry->fn, 0, print_type);
+ ret = trace_print_func(s, (struct ftrace_entry *)entry, 0, print_type);
if (!ret)
return 0;
break;
case TRACE_CTX:
case TRACE_WAKE:
- ret = trace_print_ctx(s, &entry->ctx, entry->type, print_type);
+ ret = trace_print_ctx(s, (struct ctx_switch_entry *)entry, type, print_type);
if (!ret)
return 0;
break;
case TRACE_SPECIAL:
case TRACE_STACK:
- ret = trace_print_special(s, &entry->special, print_type);
+ ret = trace_print_special(s, (struct special_entry *)entry, print_type);
if (!ret)
return 0;
break;
@@ -1795,28 +1366,32 @@ static int print_raw_fmt(struct trace_it

static int print_hex_fmt(struct trace_iterator *iter)
{
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;
unsigned char newline = '\n';
struct trace_entry *entry;
int print_type = TRACE_ITER_HEX;
+ unsigned long long t;
+ int type;

- entry = iter->ent;
+ entry = ring_buffer_event_data(iter->event);
+ type = ring_buffer_event_type(iter->event);
+ t = ring_buffer_event_counter(iter->event);

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, t);

- switch (entry->type) {
+ switch (type) {
case TRACE_FN:
- trace_print_func(s, &entry->fn, 0, print_type);
+ trace_print_func(s, (struct ftrace_entry *)entry, 0, print_type);
break;
case TRACE_CTX:
case TRACE_WAKE:
- trace_print_ctx(s, &entry->ctx, entry->type, print_type);
+ trace_print_ctx(s, (struct ctx_switch_entry *)entry, type, print_type);
break;
case TRACE_SPECIAL:
case TRACE_STACK:
- trace_print_special(s, &entry->special, print_type);
+ trace_print_special(s, (struct special_entry *)entry, print_type);
break;
}
SEQ_PUT_FIELD_RET(s, newline);
@@ -1826,26 +1401,30 @@ static int print_hex_fmt(struct trace_it

static int print_bin_fmt(struct trace_iterator *iter)
{
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;
struct trace_entry *entry;
int print_type = TRACE_ITER_BIN;
+ unsigned long long t;
+ int type;

- entry = iter->ent;
+ entry = ring_buffer_event_data(iter->event);
+ type = ring_buffer_event_type(iter->event);
+ t = ring_buffer_event_counter(iter->event);

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->cpu);
+ SEQ_PUT_FIELD_RET(s, t);

- switch (entry->type) {
+ switch (type) {
case TRACE_FN:
- trace_print_func(s, &entry->fn, 0, print_type);
+ trace_print_func(s, (struct ftrace_entry *)entry, 0, print_type);
break;
case TRACE_CTX:
- trace_print_ctx(s, &entry->ctx, entry->type, print_type);
+ trace_print_ctx(s, (struct ctx_switch_entry *)entry, type, print_type);
break;
case TRACE_SPECIAL:
case TRACE_STACK:
- trace_print_special(s, &entry->special, print_type);
+ trace_print_special(s, (struct special_entry *)entry, print_type);
break;
}
return 1;
@@ -1853,18 +1432,7 @@ static int print_bin_fmt(struct trace_it

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;
- }
- return 1;
+ return ring_buffer_empty(iter->tr->buffer);
}

static int print_trace_line(struct trace_iterator *iter)
@@ -1891,7 +1459,7 @@ static int s_show(struct seq_file *m, vo
{
struct trace_iterator *iter = v;

- if (iter->ent == NULL) {
+ if (iter->event == NULL) {
if (iter->tr) {
seq_printf(m, "# tracer: %s\n", iter->trace->name);
seq_puts(m, "#\n");
@@ -1909,7 +1477,7 @@ static int s_show(struct seq_file *m, vo
}
} else {
print_trace_line(iter);
- trace_print_seq(m, &iter->seq);
+ ring_buffer_seq_to_seqfile(m, iter->seq);
}

return 0;
@@ -1926,6 +1494,7 @@ static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, int *ret)
{
struct trace_iterator *iter;
+ unsigned buf_flags = 0;

if (tracing_disabled) {
*ret = -ENODEV;
@@ -1938,11 +1507,32 @@ __tracing_open(struct inode *inode, stru
goto out;
}

+
+
mutex_lock(&trace_types_lock);
- if (current_trace && current_trace->print_max)
- iter->tr = &max_tr;
- else
- iter->tr = inode->i_private;
+
+ iter->tr = inode->i_private;
+
+ if (current_trace && current_trace->print_max) {
+ iter->iter_flags |= TRACE_FILE_USE_MAX;
+ buf_flags = RB_ITER_FL_SNAP;
+ }
+
+ iter->buffer_iter = ring_buffer_start(iter->tr->buffer, buf_flags);
+ if (!iter->buffer_iter) {
+ kfree(iter);
+ iter = NULL;
+ goto out_unlock;
+ }
+
+ iter->seq = ring_buffer_seq_alloc(GFP_KERNEL);
+ if (!iter->seq) {
+ ring_buffer_finish(iter->buffer_iter);
+ kfree(iter);
+ iter = NULL;
+ goto out_unlock;
+ }
+
iter->trace = current_trace;
iter->pos = -1;

@@ -1964,6 +1554,7 @@ __tracing_open(struct inode *inode, stru
kfree(iter);
iter = NULL;
}
+ out_unlock:
mutex_unlock(&trace_types_lock);

out:
@@ -1985,6 +1576,10 @@ int tracing_release(struct inode *inode,
struct trace_iterator *iter = m->private;

mutex_lock(&trace_types_lock);
+
+ ring_buffer_seq_free(iter->seq);
+ ring_buffer_finish(iter->buffer_iter);
+
if (iter->trace && iter->trace->close)
iter->trace->close(iter);

@@ -2491,6 +2086,7 @@ static atomic_t tracing_reader;
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
struct trace_iterator *iter;
+ int max_event_size;

if (tracing_disabled)
return -ENODEV;
@@ -2506,6 +2102,13 @@ static int tracing_open_pipe(struct inod
if (!iter)
return -ENOMEM;

+ max_event_size = ring_buffer_max_event_size(global_trace.buffer);
+ iter->last_event = kmalloc(max_event_size, GFP_KERNEL);
+ if (!iter->last_event) {
+ kfree(iter);
+ return -ENOMEM;
+ }
+
mutex_lock(&trace_types_lock);
iter->tr = &global_trace;
iter->trace = current_trace;
@@ -2522,6 +2125,7 @@ static int tracing_release_pipe(struct i
{
struct trace_iterator *iter = file->private_data;

+ kfree(iter->last_event);
kfree(iter);
atomic_dec(&tracing_reader);

@@ -2557,22 +2161,30 @@ tracing_read_pipe(struct file *filp, cha
size_t cnt, loff_t *ppos)
{
struct trace_iterator *iter = filp->private_data;
- struct trace_array_cpu *data;
- static cpumask_t mask;
+ struct ring_buffer_event *event;
unsigned long flags;
#ifdef CONFIG_FTRACE
int ftrace_save;
#endif
- int cpu;
+ static int save_event;
ssize_t sret;

/* return any leftover data */
- sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ sret = ring_buffer_seq_copy_to_user(iter->seq, ubuf, cnt);
if (sret != -EBUSY)
return sret;
sret = 0;

- trace_seq_reset(&iter->seq);
+ ring_buffer_seq_reset(iter->seq);
+
+ /* Check to see if we over flowed the iterator */
+ if (save_event) {
+ iter->event = iter->last_event;
+ print_trace_line(iter);
+ save_event = 0;
+ sret = ring_buffer_seq_copy_to_user(iter->seq, ubuf, cnt);
+ return sret;
+ }

mutex_lock(&trace_types_lock);
if (iter->trace->read) {
@@ -2652,68 +2264,40 @@ tracing_read_pipe(struct file *filp, cha
* 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;
+ ring_buffer_lock(iter->tr->buffer, &flags);

- 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) {
+ while ((event = ring_buffer_consume(iter->tr->buffer))) {
int ret;
- int len = iter->seq.len;
+ int len = ring_buffer_seq_length(iter->seq);

+ iter->event = event;
ret = print_trace_line(iter);
if (!ret) {
/* don't print partial lines */
- iter->seq.len = len;
+ ring_buffer_seq_set_length(iter->seq, len);
+ save_event = 1;
+ memcpy(iter->last_event, event,
+ ring_buffer_event_length(event));
break;
}

- trace_consume(iter);
-
- if (iter->seq.len >= cnt)
+ len = ring_buffer_seq_length(iter->seq);
+ if (len >= cnt)
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);
+ ring_buffer_unlock(iter->tr->buffer, 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);
+ sret = ring_buffer_seq_copy_to_user(iter->seq, ubuf, cnt);
if (sret == -EBUSY)
sret = 0;

@@ -2731,17 +2315,28 @@ tracing_entries_read(struct file *filp,
char buf[64];
int r;

- r = sprintf(buf, "%lu\n", tr->entries);
+ r = sprintf(buf, "%lu\n", ring_buffer_size(tr->buffer));
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}

+static void
+trace_default_print(struct ring_buffer *buffer,
+ struct ring_buffer_seq *seq,
+ struct ring_buffer_event *event)
+{
+ /* just some garbage for now */
+ ring_buffer_seq_printf(seq, "found %d\n",
+ ring_buffer_event_type(event));
+}
+
static ssize_t
tracing_entries_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ struct ring_buffer *buffer;
unsigned long val;
char buf[64];
- int i, ret;
+ int ret;

if (cnt >= sizeof(buf))
return -EINVAL;
@@ -2768,59 +2363,28 @@ tracing_entries_write(struct file *filp,
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();
+ if (val == ring_buffer_size(global_trace.buffer))
+ goto out_same;

- /* we only allow to request 1/4 of useable memory */
- if (pages_requested >
- ((freeable_pages + tracing_pages_allocated) / 4)) {
- cnt = -ENOMEM;
- goto out;
- }
-
- while (global_trace.entries < val) {
- if (trace_alloc_page()) {
- cnt = -ENOMEM;
- goto out;
- }
- /* double check that we don't go over the known pages */
- if (tracing_pages_allocated > pages_requested)
- break;
- }
-
- } else {
- /* include the number of entries in val (inc of page entries) */
- while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
- trace_free_page();
+ buffer = ring_buffer_alloc(val,
+ TRACE_BUFFER_FLAGS, 0,
+ trace_default_print,
+ "ftrace_tmp");
+ if (!buffer) {
+ cnt = -ENOMEM;
+ goto out;
}

- /* check integrity */
- for_each_tracing_cpu(i)
- check_pages(global_trace.data[i]);
+ ring_buffer_free(global_trace.buffer);
+ ring_buffer_rename(buffer, FTRACE_BUF_NAME);

+ global_trace.buffer = buffer;
+
+ out_same:
filp->f_pos += cnt;

- /* If check pages failed, return ENOMEM */
- if (tracing_disabled)
- cnt = -ENOMEM;
out:
- max_tr.entries = global_trace.entries;
mutex_unlock(&trace_types_lock);

return cnt;
@@ -2883,17 +2447,23 @@ static struct dentry *d_tracer;
struct dentry *tracing_init_dentry(void)
{
static int once;
+ static DEFINE_MUTEX(mutex);

if (d_tracer)
return d_tracer;

+ mutex_lock(&mutex);
+ if (d_tracer)
+ goto out;
+
d_tracer = debugfs_create_dir("tracing", NULL);

if (!d_tracer && !once) {
once = 1;
pr_warning("Could not create debugfs directory 'tracing'\n");
- return NULL;
}
+ out:
+ mutex_unlock(&mutex);

return d_tracer;
}
@@ -2987,190 +2557,52 @@ static __init void tracer_init_debugfs(v
#endif
}

-static int trace_alloc_page(void)
+struct trace_array *
+trace_allocate_tracer(unsigned long size,
+ unsigned long flags,
+ unsigned long max_entry_size,
+ ring_buffer_print_func print_func,
+ char *name)
{
- struct trace_array_cpu *data;
- struct page *page, *tmp;
- LIST_HEAD(pages);
- void *array;
- unsigned pages_allocated = 0;
- int i;
-
- /* 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;
- }
-
- pages_allocated++;
- page = virt_to_page(array);
- list_add(&page->lru, &pages);
-
-/* 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
- }
+ struct trace_array *tr;

- /* 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);
-
-#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;
+ tr = kzalloc(ALIGN(sizeof(*tr), cache_line_size()), GFP_KERNEL);
+ if (!tr)
+ return NULL;

- return 0;
+ tr->buffer = ring_buffer_alloc(size, flags, max_entry_size,
+ print_func, name);

- free_pages:
- list_for_each_entry_safe(page, tmp, &pages, lru) {
- list_del_init(&page->lru);
- __free_page(page);
- }
- return -ENOMEM;
-}
+ if (!tr->buffer)
+ goto fail_free_trace;

-static int trace_free_page(void)
-{
- struct trace_array_cpu *data;
- struct page *page;
- struct list_head *p;
- int i;
- int ret = 0;
+ tr->ctrl = tracer_enabled;

- /* 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);
-
- tracing_reset(data);
-
-#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);
+ return tr;

- tracing_reset(data);
-#endif
- }
- global_trace.entries -= ENTRIES_PER_PAGE;
-
- return ret;
+ fail_free_trace:
+ kfree(tr);
+ return NULL;
}

__init static int tracer_alloc_buffers(void)
{
- struct trace_array_cpu *data;
- void *array;
- struct page *page;
- int pages = 0;
- int ret = -ENOMEM;
int i;

- /* TODO: make the number of buffers hot pluggable with CPUS */
- tracing_nr_buffers = num_possible_cpus();
tracing_buffer_mask = cpu_possible_map;

- /* 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);
-
- 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);
-
- data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
- max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-
-/* 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;
- }
-
- 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
+ global_trace.buffer = ring_buffer_alloc(trace_buf_size,
+ TRACE_BUFFER_FLAGS, 0,
+ trace_default_print,
+ FTRACE_BUF_NAME);
+ if (!global_trace.buffer) {
+ printk(KERN_ERR "tracer: failed to allocate buffer\n");
+ return -ENOMEM;
}

- /*
- * Since we allocate by orders of pages, we may be able to
- * round up a bit.
- */
- global_trace.entries = ENTRIES_PER_PAGE;
- pages++;
-
- while (global_trace.entries < trace_nr_entries) {
- if (trace_alloc_page())
- break;
- pages++;
- }
- max_tr.entries = global_trace.entries;
+ for_each_tracing_cpu(i)
+ global_trace.data[i] = &per_cpu(global_trace_cpu, i);

- 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);

tracer_init_debugfs();

@@ -3184,31 +2616,5 @@ __init static int tracer_alloc_buffers(v
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];
-
- if (data) {
- list_for_each_entry_safe(page, tmp,
- &data->trace_pages, lru) {
- list_del_init(&page->lru);
- __free_page(page);
- }
- }
-
-#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;
}
fs_initcall(tracer_alloc_buffers);
Index: linux-compile.git/kernel/trace/trace.h
===================================================================
--- linux-compile.git.orig/kernel/trace/trace.h 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace.h 2008-09-23 23:34:46.000000000 -0400
@@ -6,6 +6,7 @@
#include <linux/sched.h>
#include <linux/clocksource.h>
#include <linux/mmiotrace.h>
+#include <linux/ring_buffer.h>

enum trace_type {
__TRACE_FIRST_TYPE = 0,
@@ -25,6 +26,7 @@ enum trace_type {
* Function trace entry - function address and parent function addres:
*/
struct ftrace_entry {
+ struct trace_entry ent;
unsigned long ip;
unsigned long parent_ip;
};
@@ -33,6 +35,7 @@ struct ftrace_entry {
* Context switch trace entry - which task (and prio) we switched from/to:
*/
struct ctx_switch_entry {
+ struct trace_entry ent;
unsigned int prev_pid;
unsigned char prev_prio;
unsigned char prev_state;
@@ -45,6 +48,7 @@ struct ctx_switch_entry {
* Special (free-form) trace entry:
*/
struct special_entry {
+ struct trace_entry ent;
unsigned long arg1;
unsigned long arg2;
unsigned long arg3;
@@ -57,63 +61,23 @@ struct special_entry {
#define FTRACE_STACK_ENTRIES 8

struct stack_entry {
+ struct trace_entry ent;
unsigned long caller[FTRACE_STACK_ENTRIES];
};

/*
- * The trace entry - the most basic unit of tracing. This is what
- * is printed in the end as a single line in the trace output, such as:
- *
- * bash-15816 [01] 235.197585: idle_cpu <- irq_enter
- */
-struct trace_entry {
- char type;
- char cpu;
- char flags;
- char preempt_count;
- int pid;
- cycle_t t;
- union {
- struct ftrace_entry fn;
- struct ctx_switch_entry ctx;
- struct special_entry special;
- struct stack_entry stack;
- struct mmiotrace_rw mmiorw;
- struct mmiotrace_map mmiomap;
- };
-};
-
-#define TRACE_ENTRY_SIZE sizeof(struct trace_entry)
-
-/*
* The CPU trace array - it consists of thousands of trace entries
* plus some other descriptor data: (for example which task started
* the trace, etc.)
*/
struct trace_array_cpu {
- struct list_head trace_pages;
atomic_t disabled;
- raw_spinlock_t lock;
- struct lock_class_key lock_key;

/* these fields get copied into max-trace: */
- unsigned trace_head_idx;
- unsigned trace_tail_idx;
- void *trace_head; /* producer */
- void *trace_tail; /* consumer */
- unsigned long trace_idx;
- unsigned long overrun;
- unsigned long saved_latency;
unsigned long critical_start;
unsigned long critical_end;
unsigned long critical_sequence;
- unsigned long nice;
- unsigned long policy;
- unsigned long rt_priority;
cycle_t preempt_timestamp;
- pid_t pid;
- uid_t uid;
- char comm[TASK_COMM_LEN];
};

struct trace_iterator;
@@ -124,12 +88,20 @@ struct trace_iterator;
* They have on/off state as well:
*/
struct trace_array {
- unsigned long entries;
+ struct ring_buffer *buffer;
long ctrl;
int cpu;
cycle_t time_start;
struct task_struct *waiter;
struct trace_array_cpu *data[NR_CPUS];
+
+ unsigned long saved_latency;
+ unsigned long nice;
+ unsigned long policy;
+ unsigned long rt_priority;
+ pid_t pid;
+ uid_t uid;
+ char comm[TASK_COMM_LEN];
};

/*
@@ -137,6 +109,7 @@ struct trace_array {
*/
struct tracer {
const char *name;
+ struct trace_array *tr;
void (*init)(struct trace_array *tr);
void (*reset)(struct trace_array *tr);
void (*open)(struct trace_iterator *iter);
@@ -157,12 +130,6 @@ struct tracer {
int print_max;
};

-struct trace_seq {
- unsigned char buffer[PAGE_SIZE];
- unsigned int len;
- unsigned int readpos;
-};
-
/*
* Trace iterator - used by printout routines who present trace
* results to users and which routines might sleep, etc:
@@ -171,26 +138,21 @@ struct trace_iterator {
struct trace_array *tr;
struct tracer *trace;
void *private;
- long last_overrun[NR_CPUS];
- long overrun[NR_CPUS];

/* The below is zeroed out in pipe_read */
- struct trace_seq seq;
- struct trace_entry *ent;
+ struct ring_buffer_seq *seq;
int cpu;

- struct trace_entry *prev_ent;
- int prev_cpu;
+ struct ring_buffer_event *event;
+ struct ring_buffer_event *last_event;
+ struct ring_buffer_iter *buffer_iter;

unsigned long iter_flags;
loff_t pos;
- unsigned long next_idx[NR_CPUS];
- struct list_head *next_page[NR_CPUS];
- unsigned next_page_idx[NR_CPUS];
long idx;
};

-void tracing_reset(struct trace_array_cpu *data);
+void tracing_reset(struct trace_array *tr, int cpu);
int tracing_open_generic(struct inode *inode, struct file *filp);
struct dentry *tracing_init_dentry(void);
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
@@ -227,6 +189,11 @@ void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
int register_tracer(struct tracer *type);
void unregister_tracer(struct tracer *type);
+struct trace_array *trace_allocate_tracer(unsigned long size,
+ unsigned long flags,
+ unsigned long max_entry_size,
+ ring_buffer_print_func print_func,
+ char *name);

extern unsigned long nsecs_to_usecs(unsigned long nsecs);

@@ -308,10 +275,6 @@ extern int trace_selftest_startup_syspro
#endif
#endif /* CONFIG_FTRACE_STARTUP_TEST */

-extern void *head_page(struct trace_array_cpu *data);
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
- size_t cnt);
extern long ns2usecs(cycle_t nsec);

extern unsigned long trace_flags;
Index: linux-compile.git/include/linux/ftrace.h
===================================================================
--- linux-compile.git.orig/include/linux/ftrace.h 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/include/linux/ftrace.h 2008-09-23 23:34:46.000000000 -0400
@@ -162,4 +162,10 @@ static inline void
ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
#endif

+struct trace_entry {
+ char flags;
+ char preempt_count;
+ int pid;
+};
+
#endif /* _LINUX_FTRACE_H */
Index: linux-compile.git/include/linux/mmiotrace.h
===================================================================
--- linux-compile.git.orig/include/linux/mmiotrace.h 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/include/linux/mmiotrace.h 2008-09-23 23:34:46.000000000 -0400
@@ -1,6 +1,7 @@
#ifndef MMIOTRACE_H
#define MMIOTRACE_H

+#include <linux/ftrace.h>
#include <linux/types.h>
#include <linux/list.h>

@@ -60,6 +61,7 @@ enum mm_io_opcode {
};

struct mmiotrace_rw {
+ struct trace_entry ent;
resource_size_t phys; /* PCI address of register */
unsigned long value;
unsigned long pc; /* optional program counter */
@@ -69,6 +71,7 @@ struct mmiotrace_rw {
};

struct mmiotrace_map {
+ struct trace_entry ent;
resource_size_t phys; /* base address in PCI space */
unsigned long virt; /* base virtual address */
unsigned long len; /* mapping size */
Index: linux-compile.git/kernel/trace/trace_functions.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace_functions.c 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace_functions.c 2008-09-23 23:34:46.000000000 -0400
@@ -23,7 +23,7 @@ static void function_reset(struct trace_
tr->time_start = ftrace_now(tr->cpu);

for_each_online_cpu(cpu)
- tracing_reset(tr->data[cpu]);
+ tracing_reset(tr, cpu);
}

static void start_function_trace(struct trace_array *tr)
Index: linux-compile.git/kernel/trace/trace_irqsoff.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace_irqsoff.c 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace_irqsoff.c 2008-09-23 23:34:46.000000000 -0400
@@ -20,6 +20,7 @@

static struct trace_array *irqsoff_trace __read_mostly;
static int tracer_enabled __read_mostly;
+static int preemptirq_buffer_size = 10000;

static DEFINE_PER_CPU(int, tracing_cpu);

@@ -173,7 +174,7 @@ out_unlock:
out:
data->critical_sequence = max_sequence;
data->preempt_timestamp = ftrace_now(cpu);
- tracing_reset(data);
+ tracing_reset(tr, cpu);
trace_function(tr, data, CALLER_ADDR0, parent_ip, flags);
}

@@ -203,7 +204,7 @@ start_critical_timing(unsigned long ip,
data->critical_sequence = max_sequence;
data->preempt_timestamp = ftrace_now(cpu);
data->critical_start = parent_ip ? : ip;
- tracing_reset(data);
+ tracing_reset(tr, cpu);

local_save_flags(flags);

@@ -234,8 +235,7 @@ stop_critical_timing(unsigned long ip, u

data = tr->data[cpu];

- if (unlikely(!data) || unlikely(!head_page(data)) ||
- !data->critical_start || atomic_read(&data->disabled))
+ if (unlikely(!data) || !data->critical_start || atomic_read(&data->disabled))
return;

atomic_inc(&data->disabled);
@@ -399,6 +399,13 @@ static void irqsoff_tracer_close(struct
start_irqsoff_tracer(iter->tr);
}

+static void
+register_preemptirq_tracer(struct tracer *trace, struct trace_array *tr)
+{
+ trace->tr = tr;
+ register_tracer(trace);
+}
+
#ifdef CONFIG_IRQSOFF_TRACER
static void irqsoff_tracer_init(struct trace_array *tr)
{
@@ -419,7 +426,7 @@ static struct tracer irqsoff_tracer __re
.selftest = trace_selftest_startup_irqsoff,
#endif
};
-# define register_irqsoff(trace) register_tracer(&trace)
+# define register_irqsoff(trace, tr) register_preemptirq_tracer(trace, tr)
#else
# define register_irqsoff(trace) do { } while (0)
#endif
@@ -445,7 +452,7 @@ static struct tracer preemptoff_tracer _
.selftest = trace_selftest_startup_preemptoff,
#endif
};
-# define register_preemptoff(trace) register_tracer(&trace)
+# define register_preemptoff(trace, tr) register_preemptirq_tracer(trace, tr)
#else
# define register_preemptoff(trace) do { } while (0)
#endif
@@ -474,16 +481,25 @@ static struct tracer preemptirqsoff_trac
#endif
};

-# define register_preemptirqsoff(trace) register_tracer(&trace)
+# define register_preemptirqsoff(trace, tr) register_preemptirq_tracer(trace, tr)
#else
-# define register_preemptirqsoff(trace) do { } while (0)
+# define register_preemptirqsoff(trace, tr) do { } while (0)
#endif

__init static int init_irqsoff_tracer(void)
{
- register_irqsoff(irqsoff_tracer);
- register_preemptoff(preemptoff_tracer);
- register_preemptirqsoff(preemptirqsoff_tracer);
+ struct trace_array *tr = NULL;
+#if 0
+ tr = trace_allocate_tracer(preemptirq_buffer_size,
+ RB_FL_SNAPSHOT | RB_FL_OVERWRITE, 0,
+ NULL, "preemptirqs");
+ if (!tr)
+ return -ENOMEM;
+#endif
+
+ register_irqsoff(&irqsoff_tracer, tr);
+ register_preemptoff(&preemptoff_tracer, tr);
+ register_preemptirqsoff(&preemptirqsoff_tracer, tr);

return 0;
}
Index: linux-compile.git/kernel/trace/trace_mmiotrace.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace_mmiotrace.c 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace_mmiotrace.c 2008-09-23 23:34:46.000000000 -0400
@@ -27,7 +27,7 @@ static void mmio_reset_data(struct trace
tr->time_start = ftrace_now(tr->cpu);

for_each_online_cpu(cpu)
- tracing_reset(tr->data[cpu]);
+ tracing_reset(tr, cpu);
}

static void mmio_trace_init(struct trace_array *tr)
@@ -60,17 +60,17 @@ static void mmio_trace_ctrl_update(struc
}
}

-static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
+static int mmio_print_pcidev(struct ring_buffer_seq *s, const struct pci_dev *dev)
{
int ret = 0;
int i;
resource_size_t start, end;
const struct pci_driver *drv = pci_dev_driver(dev);

- /* XXX: incomplete checks for trace_seq_printf() return value */
- ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
- dev->bus->number, dev->devfn,
- dev->vendor, dev->device, dev->irq);
+ /* XXX: incomplete checks for ring_buffer_seq_printf() return value */
+ ret += ring_buffer_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
+ dev->bus->number, dev->devfn,
+ dev->vendor, dev->device, dev->irq);
/*
* XXX: is pci_resource_to_user() appropriate, since we are
* supposed to interpret the __ioremap() phys_addr argument based on
@@ -78,20 +78,20 @@ static int mmio_print_pcidev(struct trac
*/
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
- ret += trace_seq_printf(s, " %llx",
+ ret += ring_buffer_seq_printf(s, " %llx",
(unsigned long long)(start |
(dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
}
for (i = 0; i < 7; i++) {
pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
- ret += trace_seq_printf(s, " %llx",
+ ret += ring_buffer_seq_printf(s, " %llx",
dev->resource[i].start < dev->resource[i].end ?
(unsigned long long)(end - start) + 1 : 0);
}
if (drv)
- ret += trace_seq_printf(s, " %s\n", drv->name);
+ ret += ring_buffer_seq_printf(s, " %s\n", drv->name);
else
- ret += trace_seq_printf(s, " \n");
+ ret += ring_buffer_seq_printf(s, " \n");
return ret;
}

@@ -106,9 +106,9 @@ static void destroy_header_iter(struct h
static void mmio_pipe_open(struct trace_iterator *iter)
{
struct header_iter *hiter;
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;

- trace_seq_printf(s, "VERSION 20070824\n");
+ ring_buffer_seq_printf(s, "VERSION 20070824\n");

hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
if (!hiter)
@@ -128,13 +128,7 @@ static void mmio_close(struct trace_iter

static unsigned long count_overruns(struct trace_iterator *iter)
{
- int cpu;
- unsigned long cnt = 0;
- for_each_online_cpu(cpu) {
- cnt += iter->overrun[cpu];
- iter->overrun[cpu] = 0;
- }
- return cnt;
+ return ring_buffer_overruns(iter->tr->buffer);
}

static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
@@ -142,13 +136,13 @@ static ssize_t mmio_read(struct trace_it
{
ssize_t ret;
struct header_iter *hiter = iter->private;
- struct trace_seq *s = &iter->seq;
+ struct ring_buffer_seq *s = iter->seq;
unsigned long n;

n = count_overruns(iter);
if (n) {
/* XXX: This is later than where events were lost. */
- trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
+ ring_buffer_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
if (!overrun_detected)
pr_warning("mmiotrace has lost events.\n");
overrun_detected = true;
@@ -167,37 +161,37 @@ static ssize_t mmio_read(struct trace_it
}

print_out:
- ret = trace_seq_to_user(s, ubuf, cnt);
+ ret = ring_buffer_seq_copy_to_user(s, ubuf, cnt);
return (ret == -EBUSY) ? 0 : ret;
}

static int mmio_print_rw(struct trace_iterator *iter)
{
- struct trace_entry *entry = iter->ent;
- struct mmiotrace_rw *rw = &entry->mmiorw;
- struct trace_seq *s = &iter->seq;
- unsigned long long t = ns2usecs(entry->t);
+ struct ring_buffer_event *event = iter->event;
+ struct mmiotrace_rw *rw = ring_buffer_event_data(event);
+ struct ring_buffer_seq *s = iter->seq;
+ unsigned long long t = ns2usecs(ring_buffer_event_counter(event));
unsigned long usec_rem = do_div(t, 1000000ULL);
unsigned secs = (unsigned long)t;
int ret = 1;

- switch (entry->mmiorw.opcode) {
+ switch (rw->opcode) {
case MMIO_READ:
- ret = trace_seq_printf(s,
+ ret = ring_buffer_seq_printf(s,
"R %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
rw->width, secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
rw->value, rw->pc, 0);
break;
case MMIO_WRITE:
- ret = trace_seq_printf(s,
+ ret = ring_buffer_seq_printf(s,
"W %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n",
rw->width, secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
rw->value, rw->pc, 0);
break;
case MMIO_UNKNOWN_OP:
- ret = trace_seq_printf(s,
+ ret = ring_buffer_seq_printf(s,
"UNKNOWN %lu.%06lu %d 0x%llx %02x,%02x,%02x 0x%lx %d\n",
secs, usec_rem, rw->map_id,
(unsigned long long)rw->phys,
@@ -205,7 +199,7 @@ static int mmio_print_rw(struct trace_it
(rw->value >> 0) & 0xff, rw->pc, 0);
break;
default:
- ret = trace_seq_printf(s, "rw what?\n");
+ ret = ring_buffer_seq_printf(s, "rw what?\n");
break;
}
if (ret)
@@ -215,29 +209,28 @@ static int mmio_print_rw(struct trace_it

static int mmio_print_map(struct trace_iterator *iter)
{
- struct trace_entry *entry = iter->ent;
- struct mmiotrace_map *m = &entry->mmiomap;
- struct trace_seq *s = &iter->seq;
- unsigned long long t = ns2usecs(entry->t);
+ struct mmiotrace_map *m = ring_buffer_event_data(iter->event);
+ struct ring_buffer_seq *s = iter->seq;
+ unsigned long long t = ns2usecs(ring_buffer_event_counter(iter->event));
unsigned long usec_rem = do_div(t, 1000000ULL);
unsigned secs = (unsigned long)t;
int ret = 1;

- switch (entry->mmiorw.opcode) {
+ switch (m->opcode) {
case MMIO_PROBE:
- ret = trace_seq_printf(s,
+ ret = ring_buffer_seq_printf(s,
"MAP %lu.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n",
secs, usec_rem, m->map_id,
(unsigned long long)m->phys, m->virt, m->len,
0UL, 0);
break;
case MMIO_UNPROBE:
- ret = trace_seq_printf(s,
+ ret = ring_buffer_seq_printf(s,
"UNMAP %lu.%06lu %d 0x%lx %d\n",
secs, usec_rem, m->map_id, 0UL, 0);
break;
default:
- ret = trace_seq_printf(s, "map what?\n");
+ ret = ring_buffer_seq_printf(s, "map what?\n");
break;
}
if (ret)
@@ -248,7 +241,7 @@ static int mmio_print_map(struct trace_i
/* return 0 to abort printing without consuming current entry in pipe mode */
static int mmio_print_line(struct trace_iterator *iter)
{
- switch (iter->ent->type) {
+ switch (ring_buffer_event_type(iter->event)) {
case TRACE_MMIO_RW:
return mmio_print_rw(iter);
case TRACE_MMIO_MAP:
Index: linux-compile.git/kernel/trace/trace_sched_switch.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace_sched_switch.c 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace_sched_switch.c 2008-09-23 23:34:46.000000000 -0400
@@ -133,7 +133,7 @@ static void sched_switch_reset(struct tr
tr->time_start = ftrace_now(tr->cpu);

for_each_online_cpu(cpu)
- tracing_reset(tr->data[cpu]);
+ tracing_reset(tr, cpu);
}

static int tracing_sched_register(void)
Index: linux-compile.git/kernel/trace/trace_sched_wakeup.c
===================================================================
--- linux-compile.git.orig/kernel/trace/trace_sched_wakeup.c 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/kernel/trace/trace_sched_wakeup.c 2008-09-23 23:34:46.000000000 -0400
@@ -215,8 +215,7 @@ static void __wakeup_reset(struct trace_
int cpu;

for_each_possible_cpu(cpu) {
- data = tr->data[cpu];
- tracing_reset(data);
+ tracing_reset(tr, cpu);
}

wakeup_cpu = -1;
Index: linux-compile.git/arch/x86/kernel/Makefile
===================================================================
--- linux-compile.git.orig/arch/x86/kernel/Makefile 2008-09-23 23:33:29.000000000 -0400
+++ linux-compile.git/arch/x86/kernel/Makefile 2008-09-23 23:34:46.000000000 -0400
@@ -11,6 +11,7 @@ ifdef CONFIG_FTRACE
CFLAGS_REMOVE_tsc.o = -pg
CFLAGS_REMOVE_rtc.o = -pg
CFLAGS_REMOVE_paravirt.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
endif

#

--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/