#include <linux/list.h>
#include <linux/fs.h>
+#include "trace.h"
+
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ * This has two bits: ON, DISABLED
+ *
+ * ON DISABLED
+ * ---- ----------
+ * 0 0 : ring buffers are off
+ * 1 0 : ring buffers are on
+ * X 1 : ring buffers are permanently disabled
+ */
+
+enum {
+ RB_BUFFERS_ON_BIT = 0,
+ RB_BUFFERS_DISABLED_BIT = 1,
+};
+
+enum {
+ RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT,
+ RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
+
+/**
+ * tracing_on - enable all tracing buffers
+ *
+ * This function enables all tracing buffers that may have been
+ * disabled with tracing_off.
+ */
+void tracing_on(void)
+{
+ set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+EXPORT_SYMBOL_GPL(tracing_on);
+
+/**
+ * tracing_off - turn off all tracing buffers
+ *
+ * This function stops all tracing buffers from recording data.
+ * It does not disable any overhead the tracers themselves may
+ * be causing. This function simply causes all recording to
+ * the ring buffers to fail.
+ */
+void tracing_off(void)
+{
+ clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+EXPORT_SYMBOL_GPL(tracing_off);
+
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanenty.
+ */
+void tracing_off_permanent(void)
+{
+ set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
+}
+
+#include "trace.h"
+
/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0
/* FIXME!!! */
u64 ring_buffer_time_stamp(int cpu)
{
+ u64 time;
+
+ preempt_disable_notrace();
/* shift to debug/test normalization and TIME_EXTENTS */
- return sched_clock() << DEBUG_SHIFT;
+ time = sched_clock() << DEBUG_SHIFT;
+ preempt_enable_no_resched_notrace();
+
+ return time;
}
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
{
/* Just stupid testing the normalize function and deltas */
*ts >>= DEBUG_SHIFT;
}
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
#define RB_ALIGNMENT_SHIFT 2
*/
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
- return rb_event_length(event);
+ unsigned length = rb_event_length(event);
+ if (event->type != RINGBUF_TYPE_DATA)
+ return length;
+ length -= RB_EVNT_HDR_SIZE;
+ if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
+ length -= sizeof(event->array[0]);
+ return length;
}
+EXPORT_SYMBOL_GPL(ring_buffer_event_length);
/* inline for ring buffer fast paths */
static inline void *
{
return rb_event_data(event);
}
+EXPORT_SYMBOL_GPL(ring_buffer_event_data);
#define for_each_buffer_cpu(buffer, cpu) \
- for_each_cpu_mask(cpu, buffer->cpumask)
+ for_each_cpu(cpu, buffer->cpumask)
#define TS_SHIFT 27
#define TS_MASK ((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST (~TS_MASK)
-/*
- * This hack stolen from mm/slob.c.
- * We can store per page timing information in the page frame of the page.
- * Thanks to Peter Zijlstra for suggesting this idea.
- */
+struct buffer_data_page {
+ u64 time_stamp; /* page time stamp */
+ local_t commit; /* write commited index */
+ unsigned char data[]; /* data of buffer page */
+};
+
struct buffer_page {
- union {
- struct {
- unsigned long flags; /* mandatory */
- atomic_t _count; /* mandatory */
- u64 time_stamp; /* page time stamp */
- unsigned size; /* size of page data */
- struct list_head list; /* list of free pages */
- };
- struct page page;
- };
+ local_t write; /* index for next write */
+ unsigned read; /* index for next read */
+ struct list_head list; /* list of free pages */
+ struct buffer_data_page *page; /* Actual data page */
};
+static void rb_init_page(struct buffer_data_page *bpage)
+{
+ local_set(&bpage->commit, 0);
+}
+
/*
* Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
* this issue out.
*/
static inline void free_buffer_page(struct buffer_page *bpage)
{
- reset_page_mapcount(&bpage->page);
- bpage->page.mapping = NULL;
- __free_page(&bpage->page);
+ if (bpage->page)
+ free_page((unsigned long)bpage->page);
+ kfree(bpage);
}
/*
return 0;
}
-#define BUF_PAGE_SIZE PAGE_SIZE
+#define BUF_PAGE_SIZE (PAGE_SIZE - offsetof(struct buffer_data_page, data))
/*
* head_page == tail_page && head == tail then buffer is empty.
struct ring_buffer_per_cpu {
int cpu;
struct ring_buffer *buffer;
- spinlock_t lock;
+ spinlock_t reader_lock; /* serialize readers */
+ raw_spinlock_t lock;
struct lock_class_key lock_key;
struct list_head pages;
- unsigned long head; /* read from head */
- unsigned long tail; /* write to tail */
- struct buffer_page *head_page;
- struct buffer_page *tail_page;
+ struct buffer_page *head_page; /* read from head */
+ struct buffer_page *tail_page; /* write to tail */
+ struct buffer_page *commit_page; /* commited pages */
+ struct buffer_page *reader_page;
unsigned long overrun;
unsigned long entries;
u64 write_stamp;
};
struct ring_buffer {
- unsigned long size;
unsigned pages;
unsigned flags;
int cpus;
- cpumask_t cpumask;
+ cpumask_var_t cpumask;
atomic_t record_disabled;
struct mutex mutex;
u64 read_stamp;
};
-#define RB_WARN_ON(buffer, cond) \
- if (unlikely(cond)) { \
- atomic_inc(&buffer->record_disabled); \
- WARN_ON(1); \
- return -1; \
- }
+/* buffer may be either ring_buffer or ring_buffer_per_cpu */
+#define RB_WARN_ON(buffer, cond) \
+ ({ \
+ int _____ret = unlikely(cond); \
+ if (_____ret) { \
+ atomic_inc(&buffer->record_disabled); \
+ WARN_ON(1); \
+ } \
+ _____ret; \
+ })
/**
* check_pages - integrity check of buffer pages
static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
- RB_WARN_ON(cpu_buffer, head->next->prev != head);
- RB_WARN_ON(cpu_buffer, head->prev->next != head);
+ if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
+ return -1;
- list_for_each_entry_safe(page, tmp, head, list) {
- RB_WARN_ON(cpu_buffer, page->list.next->prev != &page->list);
- RB_WARN_ON(cpu_buffer, page->list.prev->next != &page->list);
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.next->prev != &bpage->list))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.prev->next != &bpage->list))
+ return -1;
}
return 0;
}
-static unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
-{
- return cpu_buffer->head_page->size;
-}
-
static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
unsigned nr_pages)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
unsigned long addr;
LIST_HEAD(pages);
unsigned i;
for (i = 0; i < nr_pages; i++) {
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+ if (!bpage)
+ goto free_pages;
+ list_add(&bpage->list, &pages);
+
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page = (struct buffer_page *)virt_to_page(addr);
- list_add(&page->list, &pages);
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
}
list_splice(&pages, head);
return 0;
free_pages:
- list_for_each_entry_safe(page, tmp, &pages, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
return -ENOMEM;
}
rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ struct buffer_page *bpage;
+ unsigned long addr;
int ret;
cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
cpu_buffer->cpu = cpu;
cpu_buffer->buffer = buffer;
- spin_lock_init(&cpu_buffer->lock);
+ spin_lock_init(&cpu_buffer->reader_lock);
+ cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
INIT_LIST_HEAD(&cpu_buffer->pages);
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!bpage)
+ goto fail_free_buffer;
+
+ cpu_buffer->reader_page = bpage;
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ goto fail_free_reader;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
+
+ INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+
ret = rb_allocate_pages(cpu_buffer, buffer->pages);
if (ret < 0)
- goto fail_free_buffer;
+ goto fail_free_reader;
cpu_buffer->head_page
= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
- cpu_buffer->tail_page
- = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+ cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
return cpu_buffer;
+ fail_free_reader:
+ free_buffer_page(cpu_buffer->reader_page);
+
fail_free_buffer:
kfree(cpu_buffer);
return NULL;
static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
+
+ list_del_init(&cpu_buffer->reader_page->list);
+ free_buffer_page(cpu_buffer->reader_page);
- list_for_each_entry_safe(page, tmp, head, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
kfree(cpu_buffer);
}
/**
* ring_buffer_alloc - allocate a new ring_buffer
- * @size: the size in bytes that is needed.
+ * @size: the size in bytes per cpu that is needed.
* @flags: attributes to set for the ring buffer.
*
* Currently the only flag that is available is the RB_FL_OVERWRITE
if (!buffer)
return NULL;
+ if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+ goto fail_free_buffer;
+
buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
buffer->flags = flags;
if (buffer->pages == 1)
buffer->pages++;
- buffer->cpumask = cpu_possible_map;
+ cpumask_copy(buffer->cpumask, cpu_possible_mask);
buffer->cpus = nr_cpu_ids;
bsize = sizeof(void *) * nr_cpu_ids;
buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
GFP_KERNEL);
if (!buffer->buffers)
- goto fail_free_buffer;
+ goto fail_free_cpumask;
for_each_buffer_cpu(buffer, cpu) {
buffer->buffers[cpu] =
}
kfree(buffer->buffers);
+ fail_free_cpumask:
+ free_cpumask_var(buffer->cpumask);
+
fail_free_buffer:
kfree(buffer);
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc);
/**
* ring_buffer_free - free a ring buffer.
for_each_buffer_cpu(buffer, cpu)
rb_free_cpu_buffer(buffer->buffers[cpu]);
+ free_cpumask_var(buffer->cpumask);
+
kfree(buffer);
}
+EXPORT_SYMBOL_GPL(ring_buffer_free);
static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
static void
rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
{
- struct buffer_page *page;
+ struct buffer_page *bpage;
struct list_head *p;
unsigned i;
synchronize_sched();
for (i = 0; i < nr_pages; i++) {
- BUG_ON(list_empty(&cpu_buffer->pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+ return;
p = cpu_buffer->pages.next;
- page = list_entry(p, struct buffer_page, list);
- list_del_init(&page->list);
- free_buffer_page(page);
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
- BUG_ON(list_empty(&cpu_buffer->pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+ return;
rb_reset_cpu(cpu_buffer);
rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
struct list_head *pages, unsigned nr_pages)
{
- struct buffer_page *page;
+ struct buffer_page *bpage;
struct list_head *p;
unsigned i;
synchronize_sched();
for (i = 0; i < nr_pages; i++) {
- BUG_ON(list_empty(pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
+ return;
p = pages->next;
- page = list_entry(p, struct buffer_page, list);
- list_del_init(&page->list);
- list_add_tail(&page->list, &cpu_buffer->pages);
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ list_add_tail(&bpage->list, &cpu_buffer->pages);
}
rb_reset_cpu(cpu_buffer);
{
struct ring_buffer_per_cpu *cpu_buffer;
unsigned nr_pages, rm_pages, new_pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
unsigned long buffer_size;
unsigned long addr;
LIST_HEAD(pages);
int i, cpu;
+ /*
+ * Always succeed at resizing a non-existent buffer:
+ */
+ if (!buffer)
+ return size;
+
size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
size *= BUF_PAGE_SIZE;
buffer_size = buffer->pages * BUF_PAGE_SIZE;
if (size < buffer_size) {
/* easy case, just free pages */
- BUG_ON(nr_pages >= buffer->pages);
+ if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
rm_pages = buffer->pages - nr_pages;
* add these pages to the cpu_buffers. Otherwise we just free
* them all and return -ENOMEM;
*/
- BUG_ON(nr_pages <= buffer->pages);
+ if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
+
new_pages = nr_pages - buffer->pages;
for_each_buffer_cpu(buffer, cpu) {
for (i = 0; i < new_pages; i++) {
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage),
+ cache_line_size()),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!bpage)
+ goto free_pages;
+ list_add(&bpage->list, &pages);
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page = (struct buffer_page *)virt_to_page(addr);
- list_add(&page->list, &pages);
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
}
}
rb_insert_pages(cpu_buffer, &pages, new_pages);
}
- BUG_ON(!list_empty(&pages));
+ if (RB_WARN_ON(buffer, !list_empty(&pages))) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
out:
buffer->pages = nr_pages;
return size;
free_pages:
- list_for_each_entry_safe(page, tmp, &pages, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
+ mutex_unlock(&buffer->mutex);
return -ENOMEM;
}
+EXPORT_SYMBOL_GPL(ring_buffer_resize);
-static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+static inline int rb_null_event(struct ring_buffer_event *event)
{
- return cpu_buffer->head_page == cpu_buffer->tail_page &&
- cpu_buffer->head == cpu_buffer->tail;
+ return event->type == RINGBUF_TYPE_PADDING;
}
-static inline int rb_null_event(struct ring_buffer_event *event)
+static inline void *
+__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
{
- return event->type == RINGBUF_TYPE_PADDING;
+ return bpage->data + index;
}
-static inline void *rb_page_index(struct buffer_page *page, unsigned index)
+static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
{
- void *addr = page_address(&page->page);
+ return bpage->page->data + index;
+}
- return addr + index;
+static inline struct ring_buffer_event *
+rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return __rb_page_index(cpu_buffer->reader_page,
+ cpu_buffer->reader_page->read);
}
static inline struct ring_buffer_event *
rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
{
- return rb_page_index(cpu_buffer->head_page,
- cpu_buffer->head);
+ return __rb_page_index(cpu_buffer->head_page,
+ cpu_buffer->head_page->read);
}
static inline struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
- return rb_page_index(iter->head_page,
- iter->head);
+ return __rb_page_index(iter->head_page, iter->head);
+}
+
+static inline unsigned rb_page_write(struct buffer_page *bpage)
+{
+ return local_read(&bpage->write);
+}
+
+static inline unsigned rb_page_commit(struct buffer_page *bpage)
+{
+ return local_read(&bpage->page->commit);
+}
+
+/* Size is determined by what has been commited */
+static inline unsigned rb_page_size(struct buffer_page *bpage)
+{
+ return rb_page_commit(bpage);
+}
+
+static inline unsigned
+rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return rb_page_commit(cpu_buffer->commit_page);
+}
+
+static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ return rb_page_commit(cpu_buffer->head_page);
}
/*
for (head = 0; head < rb_head_size(cpu_buffer);
head += rb_event_length(event)) {
- event = rb_page_index(cpu_buffer->head_page, head);
- BUG_ON(rb_null_event(event));
+ event = __rb_page_index(cpu_buffer->head_page, head);
+ if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+ return;
/* Only count data entries */
if (event->type != RINGBUF_TYPE_DATA)
continue;
}
static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
- struct buffer_page **page)
+ struct buffer_page **bpage)
{
- struct list_head *p = (*page)->list.next;
+ struct list_head *p = (*bpage)->list.next;
if (p == &cpu_buffer->pages)
p = p->next;
- *page = list_entry(p, struct buffer_page, list);
+ *bpage = list_entry(p, struct buffer_page, list);
+}
+
+static inline unsigned
+rb_event_index(struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+
+ return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
+}
+
+static inline int
+rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+ unsigned long index;
+
+ index = rb_event_index(event);
+ addr &= PAGE_MASK;
+
+ return cpu_buffer->commit_page->page == (void *)addr &&
+ rb_commit_index(cpu_buffer) == index;
}
static inline void
-rb_add_stamp(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event)
+{
+ unsigned long addr = (unsigned long)event;
+ unsigned long index;
+
+ index = rb_event_index(event);
+ addr &= PAGE_MASK;
+
+ while (cpu_buffer->commit_page->page != (void *)addr) {
+ if (RB_WARN_ON(cpu_buffer,
+ cpu_buffer->commit_page == cpu_buffer->tail_page))
+ return;
+ cpu_buffer->commit_page->page->commit =
+ cpu_buffer->commit_page->write;
+ rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
+ }
+
+ /* Now set the commit to the event's index */
+ local_set(&cpu_buffer->commit_page->page->commit, index);
+}
+
+static inline void
+rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
- cpu_buffer->tail_page->time_stamp = *ts;
- cpu_buffer->write_stamp = *ts;
+ /*
+ * We only race with interrupts and NMIs on this CPU.
+ * If we own the commit event, then we can commit
+ * all others that interrupted us, since the interruptions
+ * are in stack format (they finish before they come
+ * back to us). This allows us to do a simple loop to
+ * assign the commit to the tail.
+ */
+ again:
+ while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
+ cpu_buffer->commit_page->page->commit =
+ cpu_buffer->commit_page->write;
+ rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
+ /* add barrier to keep gcc from optimizing too much */
+ barrier();
+ }
+ while (rb_commit_index(cpu_buffer) !=
+ rb_page_write(cpu_buffer->commit_page)) {
+ cpu_buffer->commit_page->page->commit =
+ cpu_buffer->commit_page->write;
+ barrier();
+ }
+
+ /* again, keep gcc from optimizing */
+ barrier();
+
+ /*
+ * If an interrupt came in just after the first while loop
+ * and pushed the tail page forward, we will be left with
+ * a dangling commit that will never go forward.
+ */
+ if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+ goto again;
}
-static void rb_reset_read_page(struct ring_buffer_per_cpu *cpu_buffer)
+static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
- cpu_buffer->read_stamp = cpu_buffer->head_page->time_stamp;
- cpu_buffer->head = 0;
+ cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
+ cpu_buffer->reader_page->read = 0;
}
-static void
-rb_reset_iter_read_page(struct ring_buffer_iter *iter)
+static inline void rb_inc_iter(struct ring_buffer_iter *iter)
{
- iter->read_stamp = iter->head_page->time_stamp;
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+ /*
+ * The iterator could be on the reader page (it starts there).
+ * But the head could have moved, since the reader was
+ * found. Check for this case and assign the iterator
+ * to the head page instead of next.
+ */
+ if (iter->head_page == cpu_buffer->reader_page)
+ iter->head_page = cpu_buffer->head_page;
+ else
+ rb_inc_page(cpu_buffer, &iter->head_page);
+
+ iter->read_stamp = iter->head_page->page->time_stamp;
iter->head = 0;
}
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
unsigned type, unsigned long length, u64 *ts)
{
- struct buffer_page *head_page, *tail_page;
- unsigned long tail;
+ struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
+ unsigned long tail, write;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
+ unsigned long flags;
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
tail_page = cpu_buffer->tail_page;
- head_page = cpu_buffer->head_page;
- tail = cpu_buffer->tail;
+ write = local_add_return(length, &tail_page->write);
+ tail = write - length;
- if (tail + length > BUF_PAGE_SIZE) {
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE) {
struct buffer_page *next_page = tail_page;
+ local_irq_save(flags);
+ __raw_spin_lock(&cpu_buffer->lock);
+
rb_inc_page(cpu_buffer, &next_page);
+ head_page = cpu_buffer->head_page;
+ reader_page = cpu_buffer->reader_page;
+
+ /* we grabbed the lock before incrementing */
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_unlock;
+
+ /*
+ * If for some reason, we had an interrupt storm that made
+ * it all the way around the buffer, bail, and warn
+ * about it.
+ */
+ if (unlikely(next_page == commit_page)) {
+ WARN_ON_ONCE(1);
+ goto out_unlock;
+ }
+
if (next_page == head_page) {
if (!(buffer->flags & RB_FL_OVERWRITE))
- return NULL;
+ goto out_unlock;
+
+ /* tail_page has not moved yet? */
+ if (tail_page == cpu_buffer->tail_page) {
+ /* count overflows */
+ rb_update_overflow(cpu_buffer);
- /* count overflows */
- rb_update_overflow(cpu_buffer);
+ rb_inc_page(cpu_buffer, &head_page);
+ cpu_buffer->head_page = head_page;
+ cpu_buffer->head_page->read = 0;
+ }
+ }
- rb_inc_page(cpu_buffer, &head_page);
- cpu_buffer->head_page = head_page;
- rb_reset_read_page(cpu_buffer);
+ /*
+ * If the tail page is still the same as what we think
+ * it is, then it is up to us to update the tail
+ * pointer.
+ */
+ if (tail_page == cpu_buffer->tail_page) {
+ local_set(&next_page->write, 0);
+ local_set(&next_page->page->commit, 0);
+ cpu_buffer->tail_page = next_page;
+
+ /* reread the time stamp */
+ *ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+ cpu_buffer->tail_page->page->time_stamp = *ts;
}
- if (tail != BUF_PAGE_SIZE) {
- event = rb_page_index(tail_page, tail);
- /* page padding */
+ /*
+ * The actual tail page has moved forward.
+ */
+ if (tail < BUF_PAGE_SIZE) {
+ /* Mark the rest of the page with padding */
+ event = __rb_page_index(tail_page, tail);
event->type = RINGBUF_TYPE_PADDING;
}
- tail_page->size = tail;
- tail_page = next_page;
- tail_page->size = 0;
- tail = 0;
- cpu_buffer->tail_page = tail_page;
- cpu_buffer->tail = tail;
- rb_add_stamp(cpu_buffer, ts);
+ if (tail <= BUF_PAGE_SIZE)
+ /* Set the write back to the previous setting */
+ local_set(&tail_page->write, tail);
+
+ /*
+ * If this was a commit entry that failed,
+ * increment that too
+ */
+ if (tail_page == cpu_buffer->commit_page &&
+ tail == rb_commit_index(cpu_buffer)) {
+ rb_set_commit_to_write(cpu_buffer);
+ }
+
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ /* fail and let the caller try again */
+ return ERR_PTR(-EAGAIN);
}
- BUG_ON(tail + length > BUF_PAGE_SIZE);
+ /* We reserved something on the buffer */
+
+ if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
+ return NULL;
- event = rb_page_index(tail_page, tail);
+ event = __rb_page_index(tail_page, tail);
rb_update_event(event, type, length);
+ /*
+ * If this is a commit and the tail is zero, then update
+ * this page's time stamp.
+ */
+ if (!tail && rb_is_commit(cpu_buffer, event))
+ cpu_buffer->commit_page->page->time_stamp = *ts;
+
return event;
+
+ out_unlock:
+ /* reset write */
+ if (tail <= BUF_PAGE_SIZE)
+ local_set(&tail_page->write, tail);
+
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+ return NULL;
}
static int
{
struct ring_buffer_event *event;
static int once;
+ int ret;
if (unlikely(*delta > (1ULL << 59) && !once++)) {
printk(KERN_WARNING "Delta way too big! %llu"
" ts=%llu write stamp = %llu\n",
- *delta, *ts, cpu_buffer->write_stamp);
+ (unsigned long long)*delta,
+ (unsigned long long)*ts,
+ (unsigned long long)cpu_buffer->write_stamp);
WARN_ON(1);
}
RB_LEN_TIME_EXTEND,
ts);
if (!event)
- return -1;
+ return -EBUSY;
- /* check to see if we went to the next page */
- if (cpu_buffer->tail) {
- /* Still on same page, update timestamp */
- event->time_delta = *delta & TS_MASK;
- event->array[0] = *delta >> TS_SHIFT;
- /* commit the time event */
- cpu_buffer->tail +=
- rb_event_length(event);
+ if (PTR_ERR(event) == -EAGAIN)
+ return -EAGAIN;
+
+ /* Only a commited time event can update the write stamp */
+ if (rb_is_commit(cpu_buffer, event)) {
+ /*
+ * If this is the first on the page, then we need to
+ * update the page itself, and just put in a zero.
+ */
+ if (rb_event_index(event)) {
+ event->time_delta = *delta & TS_MASK;
+ event->array[0] = *delta >> TS_SHIFT;
+ } else {
+ cpu_buffer->commit_page->page->time_stamp = *ts;
+ event->time_delta = 0;
+ event->array[0] = 0;
+ }
cpu_buffer->write_stamp = *ts;
- *delta = 0;
+ /* let the caller know this was the commit */
+ ret = 1;
+ } else {
+ /* Darn, this is just wasted space */
+ event->time_delta = 0;
+ event->array[0] = 0;
+ ret = 0;
}
- return 0;
+ *delta = 0;
+
+ return ret;
}
static struct ring_buffer_event *
{
struct ring_buffer_event *event;
u64 ts, delta;
+ int commit = 0;
+ int nr_loops = 0;
+
+ again:
+ /*
+ * We allow for interrupts to reenter here and do a trace.
+ * If one does, it will cause this original code to loop
+ * back here. Even with heavy interrupts happening, this
+ * should only happen a few times in a row. If this happens
+ * 1000 times in a row, there must be either an interrupt
+ * storm or we have something buggy.
+ * Bail!
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
+ return NULL;
ts = ring_buffer_time_stamp(cpu_buffer->cpu);
- if (cpu_buffer->tail) {
+ /*
+ * Only the first commit can update the timestamp.
+ * Yes there is a race here. If an interrupt comes in
+ * just after the conditional and it traces too, then it
+ * will also check the deltas. More than one timestamp may
+ * also be made. But only the entry that did the actual
+ * commit will be something other than zero.
+ */
+ if (cpu_buffer->tail_page == cpu_buffer->commit_page &&
+ rb_page_write(cpu_buffer->tail_page) ==
+ rb_commit_index(cpu_buffer)) {
+
delta = ts - cpu_buffer->write_stamp;
+ /* make sure this delta is calculated here */
+ barrier();
+
+ /* Did the write stamp get updated already? */
+ if (unlikely(ts < cpu_buffer->write_stamp))
+ delta = 0;
+
if (test_time_stamp(delta)) {
- int ret;
- ret = rb_add_time_stamp(cpu_buffer, &ts, &delta);
- if (ret < 0)
+ commit = rb_add_time_stamp(cpu_buffer, &ts, &delta);
+
+ if (commit == -EBUSY)
return NULL;
+
+ if (commit == -EAGAIN)
+ goto again;
+
+ RB_WARN_ON(cpu_buffer, commit < 0);
}
- } else {
- rb_add_stamp(cpu_buffer, &ts);
+ } else
+ /* Non commits have zero deltas */
delta = 0;
- }
event = __rb_reserve_next(cpu_buffer, type, length, &ts);
- if (!event)
+ if (PTR_ERR(event) == -EAGAIN)
+ goto again;
+
+ if (!event) {
+ if (unlikely(commit))
+ /*
+ * Ouch! We needed a timestamp and it was commited. But
+ * we didn't get our event reserved.
+ */
+ rb_set_commit_to_write(cpu_buffer);
return NULL;
+ }
- /* If the reserve went to the next page, our delta is zero */
- if (!cpu_buffer->tail)
+ /*
+ * If the timestamp was commited, make the commit our entry
+ * now so that we will update it when needed.
+ */
+ if (commit)
+ rb_set_commit_event(cpu_buffer, event);
+ else if (!rb_is_commit(cpu_buffer, event))
delta = 0;
event->time_delta = delta;
return event;
}
+static DEFINE_PER_CPU(int, rb_need_resched);
+
/**
* ring_buffer_lock_reserve - reserve a part of the buffer
* @buffer: the ring buffer to reserve from
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
- int cpu;
+ int cpu, resched;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ return NULL;
if (atomic_read(&buffer->record_disabled))
return NULL;
- local_irq_save(*flags);
+ /* If we are tracing schedule, we don't want to recurse */
+ resched = ftrace_preempt_disable();
+
cpu = raw_smp_processor_id();
- if (!cpu_isset(cpu, buffer->cpumask))
- goto out_irq;
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
cpu_buffer = buffer->buffers[cpu];
- spin_lock(&cpu_buffer->lock);
if (atomic_read(&cpu_buffer->record_disabled))
- goto no_record;
+ goto out;
length = rb_calculate_event_length(length);
if (length > BUF_PAGE_SIZE)
- return NULL;
+ goto out;
event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
if (!event)
- goto no_record;
+ goto out;
+
+ /*
+ * Need to store resched state on this cpu.
+ * Only the first needs to.
+ */
+
+ if (preempt_count() == 1)
+ per_cpu(rb_need_resched, cpu) = resched;
return event;
- no_record:
- spin_unlock(&cpu_buffer->lock);
- out_irq:
- local_irq_restore(*flags);
+ out:
+ ftrace_preempt_enable(resched);
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
- cpu_buffer->tail += rb_event_length(event);
- cpu_buffer->tail_page->size = cpu_buffer->tail;
- cpu_buffer->write_stamp += event->time_delta;
cpu_buffer->entries++;
+
+ /* Only process further if we own the commit */
+ if (!rb_is_commit(cpu_buffer, event))
+ return;
+
+ cpu_buffer->write_stamp += event->time_delta;
+
+ rb_set_commit_to_write(cpu_buffer);
}
/**
cpu_buffer = buffer->buffers[cpu];
- assert_spin_locked(&cpu_buffer->lock);
-
rb_commit(cpu_buffer, event);
- spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ /*
+ * Only the last preempt count needs to restore preemption.
+ */
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
+ preempt_enable_no_resched_notrace();
return 0;
}
+EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
/**
* ring_buffer_write - write data to the buffer without reserving
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
- unsigned long event_length, flags;
+ unsigned long event_length;
void *body;
int ret = -EBUSY;
- int cpu;
+ int cpu, resched;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ return -EBUSY;
if (atomic_read(&buffer->record_disabled))
return -EBUSY;
- local_irq_save(flags);
+ resched = ftrace_preempt_disable();
+
cpu = raw_smp_processor_id();
- if (!cpu_isset(cpu, buffer->cpumask))
- goto out_irq;
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
cpu_buffer = buffer->buffers[cpu];
- spin_lock(&cpu_buffer->lock);
if (atomic_read(&cpu_buffer->record_disabled))
goto out;
ret = 0;
out:
- spin_unlock(&cpu_buffer->lock);
- out_irq:
- local_irq_restore(flags);
+ ftrace_preempt_enable(resched);
return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_write);
-/**
- * ring_buffer_lock - lock the ring buffer
- * @buffer: The ring buffer to lock
- * @flags: The place to store the interrupt flags
- *
- * This locks all the per CPU buffers.
- *
- * Must be unlocked by ring_buffer_unlock.
- */
-void ring_buffer_lock(struct ring_buffer *buffer, unsigned long *flags)
-{
- struct ring_buffer_per_cpu *cpu_buffer;
- int cpu;
-
- local_irq_save(*flags);
-
- for_each_buffer_cpu(buffer, cpu) {
- cpu_buffer = buffer->buffers[cpu];
- spin_lock(&cpu_buffer->lock);
- }
-}
-
-/**
- * ring_buffer_unlock - unlock a locked buffer
- * @buffer: The locked buffer to unlock
- * @flags: The interrupt flags received by ring_buffer_lock
- */
-void ring_buffer_unlock(struct ring_buffer *buffer, unsigned long flags)
+static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
{
- struct ring_buffer_per_cpu *cpu_buffer;
- int cpu;
+ struct buffer_page *reader = cpu_buffer->reader_page;
+ struct buffer_page *head = cpu_buffer->head_page;
+ struct buffer_page *commit = cpu_buffer->commit_page;
- for (cpu = buffer->cpus - 1; cpu >= 0; cpu--) {
- if (!cpu_isset(cpu, buffer->cpumask))
- continue;
- cpu_buffer = buffer->buffers[cpu];
- spin_unlock(&cpu_buffer->lock);
- }
-
- local_irq_restore(flags);
+ return reader->read == rb_page_commit(reader) &&
+ (commit == reader ||
+ (commit == head &&
+ head->read == rb_page_commit(commit)));
}
/**
{
atomic_inc(&buffer->record_disabled);
}
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
/**
* ring_buffer_record_enable - enable writes to the buffer
{
atomic_dec(&buffer->record_disabled);
}
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
{
struct ring_buffer_per_cpu *cpu_buffer;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
cpu_buffer = buffer->buffers[cpu];
atomic_inc(&cpu_buffer->record_disabled);
}
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
/**
* ring_buffer_record_enable_cpu - enable writes to the buffer
{
struct ring_buffer_per_cpu *cpu_buffer;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
cpu_buffer = buffer->buffers[cpu];
atomic_dec(&cpu_buffer->record_disabled);
}
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
/**
* ring_buffer_entries_cpu - get the number of entries in a cpu buffer
{
struct ring_buffer_per_cpu *cpu_buffer;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 0;
cpu_buffer = buffer->buffers[cpu];
return cpu_buffer->entries;
}
+EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
/**
* ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
{
struct ring_buffer_per_cpu *cpu_buffer;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 0;
cpu_buffer = buffer->buffers[cpu];
return cpu_buffer->overrun;
}
+EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
/**
* ring_buffer_entries - get the number of entries in a buffer
return entries;
}
+EXPORT_SYMBOL_GPL(ring_buffer_entries);
/**
* ring_buffer_overrun_cpu - get the number of overruns in buffer
return overruns;
}
+EXPORT_SYMBOL_GPL(ring_buffer_overruns);
+
+static void rb_iter_reset(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+ /* Iterator usage is expected to have record disabled */
+ if (list_empty(&cpu_buffer->reader_page->list)) {
+ iter->head_page = cpu_buffer->head_page;
+ iter->head = cpu_buffer->head_page->read;
+ } else {
+ iter->head_page = cpu_buffer->reader_page;
+ iter->head = cpu_buffer->reader_page->read;
+ }
+ if (iter->head)
+ iter->read_stamp = cpu_buffer->read_stamp;
+ else
+ iter->read_stamp = iter->head_page->page->time_stamp;
+}
/**
* ring_buffer_iter_reset - reset an iterator
void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
{
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
- iter->head_page = cpu_buffer->head_page;
- iter->head = cpu_buffer->head;
- rb_reset_iter_read_page(iter);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ rb_iter_reset(iter);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
/**
* ring_buffer_iter_empty - check if an iterator has no more to read
cpu_buffer = iter->cpu_buffer;
- return iter->head_page == cpu_buffer->tail_page &&
- iter->head == cpu_buffer->tail;
+ return iter->head_page == cpu_buffer->commit_page &&
+ iter->head == rb_commit_index(cpu_buffer);
}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
static void
rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
return;
}
-static void rb_advance_head(struct ring_buffer_per_cpu *cpu_buffer)
+static struct buffer_page *
+rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
- struct ring_buffer_event *event;
- unsigned length;
+ struct buffer_page *reader = NULL;
+ unsigned long flags;
+ int nr_loops = 0;
+
+ local_irq_save(flags);
+ __raw_spin_lock(&cpu_buffer->lock);
+ again:
/*
- * Check if we are at the end of the buffer.
+ * This should normally only loop twice. But because the
+ * start of the reader inserts an empty page, it causes
+ * a case where we will loop three times. There should be no
+ * reason to loop four times (that I know of).
*/
- if (cpu_buffer->head >= cpu_buffer->head_page->size) {
- BUG_ON(cpu_buffer->head_page == cpu_buffer->tail_page);
- rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
- rb_reset_read_page(cpu_buffer);
- return;
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
+ reader = NULL;
+ goto out;
}
- event = rb_head_event(cpu_buffer);
+ reader = cpu_buffer->reader_page;
- if (event->type == RINGBUF_TYPE_DATA)
- cpu_buffer->entries--;
+ /* If there's more to read, return this page */
+ if (cpu_buffer->reader_page->read < rb_page_size(reader))
+ goto out;
- length = rb_event_length(event);
+ /* Never should we have an index greater than the size */
+ if (RB_WARN_ON(cpu_buffer,
+ cpu_buffer->reader_page->read > rb_page_size(reader)))
+ goto out;
+
+ /* check if we caught up to the tail */
+ reader = NULL;
+ if (cpu_buffer->commit_page == cpu_buffer->reader_page)
+ goto out;
/*
- * This should not be called to advance the header if we are
- * at the tail of the buffer.
+ * Splice the empty reader page into the list around the head.
+ * Reset the reader page to size zero.
*/
- BUG_ON((cpu_buffer->head_page == cpu_buffer->tail_page) &&
- (cpu_buffer->head + length > cpu_buffer->tail));
- rb_update_read_stamp(cpu_buffer, event);
+ reader = cpu_buffer->head_page;
+ cpu_buffer->reader_page->list.next = reader->list.next;
+ cpu_buffer->reader_page->list.prev = reader->list.prev;
+
+ local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
+
+ /* Make the reader page now replace the head */
+ reader->list.prev->next = &cpu_buffer->reader_page->list;
+ reader->list.next->prev = &cpu_buffer->reader_page->list;
+
+ /*
+ * If the tail is on the reader, then we must set the head
+ * to the inserted page, otherwise we set it one before.
+ */
+ cpu_buffer->head_page = cpu_buffer->reader_page;
+
+ if (cpu_buffer->commit_page != reader)
+ rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+
+ /* Finally update the reader page to the new head */
+ cpu_buffer->reader_page = reader;
+ rb_reset_reader_page(cpu_buffer);
- cpu_buffer->head += length;
+ goto again;
- /* check for end of page */
- if ((cpu_buffer->head >= cpu_buffer->head_page->size) &&
- (cpu_buffer->head_page != cpu_buffer->tail_page))
- rb_advance_head(cpu_buffer);
+ out:
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
+
+ return reader;
+}
+
+static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
+{
+ struct ring_buffer_event *event;
+ struct buffer_page *reader;
+ unsigned length;
+
+ reader = rb_get_reader_page(cpu_buffer);
+
+ /* This function should not be called when buffer is empty */
+ if (RB_WARN_ON(cpu_buffer, !reader))
+ return;
+
+ event = rb_reader_event(cpu_buffer);
+
+ if (event->type == RINGBUF_TYPE_DATA)
+ cpu_buffer->entries--;
+
+ rb_update_read_stamp(cpu_buffer, event);
+
+ length = rb_event_length(event);
+ cpu_buffer->reader_page->read += length;
}
static void rb_advance_iter(struct ring_buffer_iter *iter)
/*
* Check if we are at the end of the buffer.
*/
- if (iter->head >= iter->head_page->size) {
- BUG_ON(iter->head_page == cpu_buffer->tail_page);
- rb_inc_page(cpu_buffer, &iter->head_page);
- rb_reset_iter_read_page(iter);
+ if (iter->head >= rb_page_size(iter->head_page)) {
+ if (RB_WARN_ON(buffer,
+ iter->head_page == cpu_buffer->commit_page))
+ return;
+ rb_inc_iter(iter);
return;
}
* This should not be called to advance the header if we are
* at the tail of the buffer.
*/
- BUG_ON((iter->head_page == cpu_buffer->tail_page) &&
- (iter->head + length > cpu_buffer->tail));
+ if (RB_WARN_ON(cpu_buffer,
+ (iter->head_page == cpu_buffer->commit_page) &&
+ (iter->head + length > rb_commit_index(cpu_buffer))))
+ return;
rb_update_iter_read_stamp(iter, event);
iter->head += length;
/* check for end of page padding */
- if ((iter->head >= iter->head_page->size) &&
- (iter->head_page != cpu_buffer->tail_page))
+ if ((iter->head >= rb_page_size(iter->head_page)) &&
+ (iter->head_page != cpu_buffer->commit_page))
rb_advance_iter(iter);
}
-/**
- * ring_buffer_peek - peek at the next event to be read
- * @buffer: The ring buffer to read
- * @cpu: The cpu to peak at
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not consume the data.
- */
-struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+static struct ring_buffer_event *
+rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
+ struct buffer_page *reader;
+ int nr_loops = 0;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
cpu_buffer = buffer->buffers[cpu];
again:
- if (rb_per_cpu_empty(cpu_buffer))
+ /*
+ * We repeat when a timestamp is encountered. It is possible
+ * to get multiple timestamps from an interrupt entering just
+ * as one timestamp is about to be written. The max times
+ * that this can happen is the number of nested interrupts we
+ * can have. Nesting 10 deep of interrupts is clearly
+ * an anomaly.
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+ return NULL;
+
+ reader = rb_get_reader_page(cpu_buffer);
+ if (!reader)
return NULL;
- event = rb_head_event(cpu_buffer);
+ event = rb_reader_event(cpu_buffer);
switch (event->type) {
case RINGBUF_TYPE_PADDING:
- rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
- rb_reset_read_page(cpu_buffer);
- goto again;
+ RB_WARN_ON(cpu_buffer, 1);
+ rb_advance_reader(cpu_buffer);
+ return NULL;
case RINGBUF_TYPE_TIME_EXTEND:
/* Internal data, OK to advance */
- rb_advance_head(cpu_buffer);
+ rb_advance_reader(cpu_buffer);
goto again;
case RINGBUF_TYPE_TIME_STAMP:
/* FIXME: not implemented */
- rb_advance_head(cpu_buffer);
+ rb_advance_reader(cpu_buffer);
goto again;
case RINGBUF_TYPE_DATA:
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_peek);
-/**
- * ring_buffer_iter_peek - peek at the next event to be read
- * @iter: The ring buffer iterator
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not increment the iterator.
- */
-struct ring_buffer_event *
-ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+static struct ring_buffer_event *
+rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
{
struct ring_buffer *buffer;
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
+ int nr_loops = 0;
if (ring_buffer_iter_empty(iter))
return NULL;
buffer = cpu_buffer->buffer;
again:
+ /*
+ * We repeat when a timestamp is encountered. It is possible
+ * to get multiple timestamps from an interrupt entering just
+ * as one timestamp is about to be written. The max times
+ * that this can happen is the number of nested interrupts we
+ * can have. Nesting 10 deep of interrupts is clearly
+ * an anomaly.
+ */
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
+ return NULL;
+
if (rb_per_cpu_empty(cpu_buffer))
return NULL;
switch (event->type) {
case RINGBUF_TYPE_PADDING:
- rb_inc_page(cpu_buffer, &iter->head_page);
- rb_reset_iter_read_page(iter);
+ rb_inc_iter(iter);
goto again;
case RINGBUF_TYPE_TIME_EXTEND:
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
+
+/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_buffer_peek(buffer, cpu, ts);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return event;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ struct ring_buffer_event *event;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_iter_peek(iter, ts);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return event;
+}
/**
* ring_buffer_consume - return an event and consume it
struct ring_buffer_event *
ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
{
- struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct ring_buffer_event *event;
+ unsigned long flags;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
- event = ring_buffer_peek(buffer, cpu, ts);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ event = rb_buffer_peek(buffer, cpu, ts);
if (!event)
- return NULL;
+ goto out;
- cpu_buffer = buffer->buffers[cpu];
- rb_advance_head(cpu_buffer);
+ rb_advance_reader(cpu_buffer);
+
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return event;
}
+EXPORT_SYMBOL_GPL(ring_buffer_consume);
/**
* ring_buffer_read_start - start a non consuming read of the buffer
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_iter *iter;
+ unsigned long flags;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
iter = kmalloc(sizeof(*iter), GFP_KERNEL);
atomic_inc(&cpu_buffer->record_disabled);
synchronize_sched();
- spin_lock(&cpu_buffer->lock);
- iter->head = cpu_buffer->head;
- iter->head_page = cpu_buffer->head_page;
- rb_reset_iter_read_page(iter);
- spin_unlock(&cpu_buffer->lock);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ __raw_spin_lock(&cpu_buffer->lock);
+ rb_iter_reset(iter);
+ __raw_spin_unlock(&cpu_buffer->lock);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return iter;
}
+EXPORT_SYMBOL_GPL(ring_buffer_read_start);
/**
* ring_buffer_finish - finish reading the iterator of the buffer
atomic_dec(&cpu_buffer->record_disabled);
kfree(iter);
}
+EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
/**
* ring_buffer_read - read the next item in the ring buffer by the iterator
ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
{
struct ring_buffer_event *event;
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
- event = ring_buffer_iter_peek(iter, ts);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_iter_peek(iter, ts);
if (!event)
- return NULL;
+ goto out;
rb_advance_iter(iter);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return event;
}
+EXPORT_SYMBOL_GPL(ring_buffer_read);
/**
* ring_buffer_size - return the size of the ring buffer (in bytes)
{
return BUF_PAGE_SIZE * buffer->pages;
}
+EXPORT_SYMBOL_GPL(ring_buffer_size);
static void
rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
{
cpu_buffer->head_page
= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
- cpu_buffer->tail_page
- = list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+ local_set(&cpu_buffer->head_page->write, 0);
+ local_set(&cpu_buffer->head_page->page->commit, 0);
+
+ cpu_buffer->head_page->read = 0;
+
+ cpu_buffer->tail_page = cpu_buffer->head_page;
+ cpu_buffer->commit_page = cpu_buffer->head_page;
+
+ INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+ local_set(&cpu_buffer->reader_page->write, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
+ cpu_buffer->reader_page->read = 0;
- cpu_buffer->head = cpu_buffer->tail = 0;
cpu_buffer->overrun = 0;
cpu_buffer->entries = 0;
}
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
unsigned long flags;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return;
- local_irq_save(flags);
- spin_lock(&cpu_buffer->lock);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ __raw_spin_lock(&cpu_buffer->lock);
rb_reset_cpu(cpu_buffer);
- spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ __raw_spin_unlock(&cpu_buffer->lock);
+
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
/**
* ring_buffer_reset - reset a ring buffer
*/
void ring_buffer_reset(struct ring_buffer *buffer)
{
- unsigned long flags;
int cpu;
- ring_buffer_lock(buffer, &flags);
-
for_each_buffer_cpu(buffer, cpu)
- rb_reset_cpu(buffer->buffers[cpu]);
-
- ring_buffer_unlock(buffer, flags);
+ ring_buffer_reset_cpu(buffer, cpu);
}
+EXPORT_SYMBOL_GPL(ring_buffer_reset);
/**
* rind_buffer_empty - is the ring buffer empty?
}
return 1;
}
+EXPORT_SYMBOL_GPL(ring_buffer_empty);
/**
* ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
{
struct ring_buffer_per_cpu *cpu_buffer;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 1;
cpu_buffer = buffer->buffers[cpu];
return rb_per_cpu_empty(cpu_buffer);
}
+EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
/**
* ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
struct ring_buffer_per_cpu *cpu_buffer_a;
struct ring_buffer_per_cpu *cpu_buffer_b;
- if (!cpu_isset(cpu, buffer_a->cpumask) ||
- !cpu_isset(cpu, buffer_b->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
+ !cpumask_test_cpu(cpu, buffer_b->cpumask))
return -EINVAL;
/* At least make sure the two buffers are somewhat the same */
- if (buffer_a->size != buffer_b->size ||
- buffer_a->pages != buffer_b->pages)
+ if (buffer_a->pages != buffer_b->pages)
return -EINVAL;
cpu_buffer_a = buffer_a->buffers[cpu];
return 0;
}
+EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+
+static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_data_page *bpage)
+{
+ struct ring_buffer_event *event;
+ unsigned long head;
+
+ __raw_spin_lock(&cpu_buffer->lock);
+ for (head = 0; head < local_read(&bpage->commit);
+ head += rb_event_length(event)) {
+
+ event = __rb_data_page_index(bpage, head);
+ if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+ return;
+ /* Only count data entries */
+ if (event->type != RINGBUF_TYPE_DATA)
+ continue;
+ cpu_buffer->entries--;
+ }
+ __raw_spin_unlock(&cpu_buffer->lock);
+}
+
+/**
+ * ring_buffer_alloc_read_page - allocate a page to read from buffer
+ * @buffer: the buffer to allocate for.
+ *
+ * This function is used in conjunction with ring_buffer_read_page.
+ * When reading a full page from the ring buffer, these functions
+ * can be used to speed up the process. The calling function should
+ * allocate a few pages first with this function. Then when it
+ * needs to get pages from the ring buffer, it passes the result
+ * of this function into ring_buffer_read_page, which will swap
+ * the page that was allocated, with the read page of the buffer.
+ *
+ * Returns:
+ * The page allocated, or NULL on error.
+ */
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
+{
+ unsigned long addr;
+ struct buffer_data_page *bpage;
+
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ return NULL;
+
+ bpage = (void *)addr;
+
+ return bpage;
+}
+
+/**
+ * ring_buffer_free_read_page - free an allocated read page
+ * @buffer: the buffer the page was allocate for
+ * @data: the page to free
+ *
+ * Free a page allocated from ring_buffer_alloc_read_page.
+ */
+void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
+{
+ free_page((unsigned long)data);
+}
+
+/**
+ * ring_buffer_read_page - extract a page from the ring buffer
+ * @buffer: buffer to extract from
+ * @data_page: the page to use allocated from ring_buffer_alloc_read_page
+ * @cpu: the cpu of the buffer to extract
+ * @full: should the extraction only happen when the page is full.
+ *
+ * This function will pull out a page from the ring buffer and consume it.
+ * @data_page must be the address of the variable that was returned
+ * from ring_buffer_alloc_read_page. This is because the page might be used
+ * to swap with a page in the ring buffer.
+ *
+ * for example:
+ * rpage = ring_buffer_alloc_page(buffer);
+ * if (!rpage)
+ * return error;
+ * ret = ring_buffer_read_page(buffer, &rpage, cpu, 0);
+ * if (ret)
+ * process_page(rpage);
+ *
+ * When @full is set, the function will not return true unless
+ * the writer is off the reader page.
+ *
+ * Note: it is up to the calling functions to handle sleeps and wakeups.
+ * The ring buffer can be used anywhere in the kernel and can not
+ * blindly call wake_up. The layer that uses the ring buffer must be
+ * responsible for that.
+ *
+ * Returns:
+ * 1 if data has been transferred
+ * 0 if no data has been transferred.
+ */
+int ring_buffer_read_page(struct ring_buffer *buffer,
+ void **data_page, int cpu, int full)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ struct buffer_data_page *bpage;
+ unsigned long flags;
+ int ret = 0;
+
+ if (!data_page)
+ return 0;
+
+ bpage = *data_page;
+ if (!bpage)
+ return 0;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ /*
+ * rb_buffer_peek will get the next ring buffer if
+ * the current reader page is empty.
+ */
+ event = rb_buffer_peek(buffer, cpu, NULL);
+ if (!event)
+ goto out;
+
+ /* check for data */
+ if (!local_read(&cpu_buffer->reader_page->page->commit))
+ goto out;
+ /*
+ * If the writer is already off of the read page, then simply
+ * switch the read page with the given page. Otherwise
+ * we need to copy the data from the reader to the writer.
+ */
+ if (cpu_buffer->reader_page == cpu_buffer->commit_page) {
+ unsigned int read = cpu_buffer->reader_page->read;
+
+ if (full)
+ goto out;
+ /* The writer is still on the reader page, we must copy */
+ bpage = cpu_buffer->reader_page->page;
+ memcpy(bpage->data,
+ cpu_buffer->reader_page->page->data + read,
+ local_read(&bpage->commit) - read);
+
+ /* consume what was read */
+ cpu_buffer->reader_page += read;
+
+ } else {
+ /* swap the pages */
+ rb_init_page(bpage);
+ bpage = cpu_buffer->reader_page->page;
+ cpu_buffer->reader_page->page = *data_page;
+ cpu_buffer->reader_page->read = 0;
+ *data_page = bpage;
+ }
+ ret = 1;
+
+ /* update the entry counter */
+ rb_remove_entries(cpu_buffer, bpage);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return ret;
+}
+
+static ssize_t
+rb_simple_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ long *p = filp->private_data;
+ char buf[64];
+ int r;
+
+ if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+ r = sprintf(buf, "permanently disabled\n");
+ else
+ r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+rb_simple_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ long *p = filp->private_data;
+ char buf[64];
+ long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val)
+ set_bit(RB_BUFFERS_ON_BIT, p);
+ else
+ clear_bit(RB_BUFFERS_ON_BIT, p);
+
+ (*ppos)++;
+
+ return cnt;
+}
+
+static struct file_operations rb_simple_fops = {
+ .open = tracing_open_generic,
+ .read = rb_simple_read,
+ .write = rb_simple_write,
+};
+
+
+static __init int rb_init_debugfs(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+
+ entry = debugfs_create_file("tracing_on", 0644, d_tracer,
+ &ring_buffer_flags, &rb_simple_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs 'tracing_on' entry\n");
+
+ return 0;
+}
+fs_initcall(rb_init_debugfs);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff