* Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
*/
#include <linux/ring_buffer.h>
+#include <linux/trace_clock.h>
+#include <linux/ftrace_irq.h>
#include <linux/spinlock.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
+#include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
-#include <linux/sched.h> /* used for sched_clock() (for now) */
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/list.h>
+#include <linux/cpu.h>
#include <linux/fs.h>
#include "trace.h"
-/* Global flag to disable all recording to ring buffers */
-static int ring_buffers_off __read_mostly;
+/*
+ * The ring buffer header is special. We must manually up keep it.
+ */
+int ring_buffer_print_entry_header(struct trace_seq *s)
+{
+ int ret;
+
+ ret = trace_seq_printf(s, "# compressed entry header\n");
+ ret = trace_seq_printf(s, "\ttype_len : 5 bits\n");
+ ret = trace_seq_printf(s, "\ttime_delta : 27 bits\n");
+ ret = trace_seq_printf(s, "\tarray : 32 bits\n");
+ ret = trace_seq_printf(s, "\n");
+ ret = trace_seq_printf(s, "\tpadding : type == %d\n",
+ RINGBUF_TYPE_PADDING);
+ ret = trace_seq_printf(s, "\ttime_extend : type == %d\n",
+ RINGBUF_TYPE_TIME_EXTEND);
+ ret = trace_seq_printf(s, "\tdata max type_len == %d\n",
+ RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
+
+ return ret;
+}
+
+/*
+ * The ring buffer is made up of a list of pages. A separate list of pages is
+ * allocated for each CPU. A writer may only write to a buffer that is
+ * associated with the CPU it is currently executing on. A reader may read
+ * from any per cpu buffer.
+ *
+ * The reader is special. For each per cpu buffer, the reader has its own
+ * reader page. When a reader has read the entire reader page, this reader
+ * page is swapped with another page in the ring buffer.
+ *
+ * Now, as long as the writer is off the reader page, the reader can do what
+ * ever it wants with that page. The writer will never write to that page
+ * again (as long as it is out of the ring buffer).
+ *
+ * Here's some silly ASCII art.
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |
+ * +------+ +---+ +---+ +---+
+ * | |-->| |-->| |
+ * +---+ +---+ +---+
+ * ^ |
+ * | |
+ * +---------------+
+ *
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * | |-->| |-->| |
+ * +---+ +---+ +---+
+ * ^ |
+ * | |
+ * +---------------+
+ *
+ *
+ * +------+
+ * |reader| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * ^ | |-->| |-->| |
+ * | +---+ +---+ +---+
+ * | |
+ * | |
+ * +------------------------------+
+ *
+ *
+ * +------+
+ * |buffer| RING BUFFER
+ * |page |------------------v
+ * +------+ +---+ +---+ +---+
+ * ^ | | | |-->| |
+ * | New +---+ +---+ +---+
+ * | Reader------^ |
+ * | page |
+ * +------------------------------+
+ *
+ *
+ * After we make this swap, the reader can hand this page off to the splice
+ * code and be done with it. It can even allocate a new page if it needs to
+ * and swap that into the ring buffer.
+ *
+ * We will be using cmpxchg soon to make all this lockless.
+ *
+ */
+
+/*
+ * 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 unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
+
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
/**
* tracing_on - enable all tracing buffers
*/
void tracing_on(void)
{
- ring_buffers_off = 0;
+ set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
+EXPORT_SYMBOL_GPL(tracing_on);
/**
* tracing_off - turn off all tracing buffers
*/
void tracing_off(void)
{
- ring_buffers_off = 1;
+ clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
+EXPORT_SYMBOL_GPL(tracing_off);
-#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)
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanently.
+ */
+void tracing_off_permanent(void)
{
- u64 time;
-
- preempt_disable_notrace();
- /* shift to debug/test normalization and TIME_EXTENTS */
- time = sched_clock() << DEBUG_SHIFT;
- preempt_enable_notrace();
-
- return time;
+ set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
}
-void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
+/**
+ * tracing_is_on - show state of ring buffers enabled
+ */
+int tracing_is_on(void)
{
- /* Just stupid testing the normalize function and deltas */
- *ts >>= DEBUG_SHIFT;
+ return ring_buffer_flags == RB_BUFFERS_ON;
}
+EXPORT_SYMBOL_GPL(tracing_is_on);
-#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
-#define RB_ALIGNMENT_SHIFT 2
-#define RB_ALIGNMENT (1 << RB_ALIGNMENT_SHIFT)
-#define RB_MAX_SMALL_DATA 28
+#include "trace.h"
+
+#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
+#define RB_ALIGNMENT 4U
+#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+
+/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
+#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
enum {
RB_LEN_TIME_EXTEND = 8,
RB_LEN_TIME_STAMP = 16,
};
-/* inline for ring buffer fast paths */
-static inline unsigned
-rb_event_length(struct ring_buffer_event *event)
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+ return event->type_len == RINGBUF_TYPE_PADDING
+ && event->time_delta == 0;
+}
+
+static inline int rb_discarded_event(struct ring_buffer_event *event)
+{
+ return event->type_len == RINGBUF_TYPE_PADDING && event->time_delta;
+}
+
+static void rb_event_set_padding(struct ring_buffer_event *event)
+{
+ event->type_len = RINGBUF_TYPE_PADDING;
+ event->time_delta = 0;
+}
+
+static unsigned
+rb_event_data_length(struct ring_buffer_event *event)
{
unsigned length;
- switch (event->type) {
+ if (event->type_len)
+ length = event->type_len * RB_ALIGNMENT;
+ else
+ length = event->array[0];
+ return length + RB_EVNT_HDR_SIZE;
+}
+
+/* inline for ring buffer fast paths */
+static unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
- /* undefined */
- return -1;
+ if (rb_null_event(event))
+ /* undefined */
+ return -1;
+ return event->array[0] + RB_EVNT_HDR_SIZE;
case RINGBUF_TYPE_TIME_EXTEND:
return RB_LEN_TIME_EXTEND;
return RB_LEN_TIME_STAMP;
case RINGBUF_TYPE_DATA:
- if (event->len)
- length = event->len << RB_ALIGNMENT_SHIFT;
- else
- length = event->array[0];
- return length + RB_EVNT_HDR_SIZE;
+ return rb_event_data_length(event);
default:
BUG();
}
*/
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
- return rb_event_length(event);
+ unsigned length = rb_event_length(event);
+ if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
+ 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 *
+static void *
rb_event_data(struct ring_buffer_event *event)
{
- BUG_ON(event->type != RINGBUF_TYPE_DATA);
+ BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
/* If length is in len field, then array[0] has the data */
- if (event->len)
+ if (event->type_len)
return (void *)&event->array[0];
/* Otherwise length is in array[0] and array[1] has the data */
return (void *)&event->array[1];
{
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_page {
+struct buffer_data_page {
u64 time_stamp; /* page time stamp */
+ local_t commit; /* write committed index */
+ unsigned char data[]; /* data of buffer page */
+};
+
+struct buffer_page {
+ struct list_head list; /* list of buffer pages */
local_t write; /* index for next write */
- local_t commit; /* write commited index */
unsigned read; /* index for next read */
- struct list_head list; /* list of free pages */
- void *page; /* Actual data page */
+ local_t entries; /* entries on this page */
+ struct buffer_data_page *page; /* Actual data page */
};
+static void rb_init_page(struct buffer_data_page *bpage)
+{
+ local_set(&bpage->commit, 0);
+}
+
+/**
+ * ring_buffer_page_len - the size of data on the page.
+ * @page: The page to read
+ *
+ * Returns the amount of data on the page, including buffer page header.
+ */
+size_t ring_buffer_page_len(void *page)
+{
+ return local_read(&((struct buffer_data_page *)page)->commit)
+ + BUF_PAGE_HDR_SIZE;
+}
+
/*
* 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)
+static void free_buffer_page(struct buffer_page *bpage)
{
- if (bpage->page)
- free_page((unsigned long)bpage->page);
+ free_page((unsigned long)bpage->page);
kfree(bpage);
}
return 0;
}
-#define BUF_PAGE_SIZE PAGE_SIZE
+#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)
+
+/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
+#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))
+
+int ring_buffer_print_page_header(struct trace_seq *s)
+{
+ struct buffer_data_page field;
+ int ret;
+
+ ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+ "offset:0;\tsize:%u;\n",
+ (unsigned int)sizeof(field.time_stamp));
+
+ ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ (unsigned int)sizeof(field.commit));
+
+ ret = trace_seq_printf(s, "\tfield: char data;\t"
+ "offset:%u;\tsize:%u;\n",
+ (unsigned int)offsetof(typeof(field), data),
+ (unsigned int)BUF_PAGE_SIZE);
+
+ return ret;
+}
/*
* head_page == tail_page && head == tail then buffer is empty.
struct list_head pages;
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 *commit_page; /* committed pages */
struct buffer_page *reader_page;
+ unsigned long nmi_dropped;
+ unsigned long commit_overrun;
unsigned long overrun;
- unsigned long entries;
+ unsigned long read;
+ local_t entries;
u64 write_stamp;
u64 read_stamp;
atomic_t record_disabled;
};
struct ring_buffer {
- unsigned long size;
unsigned pages;
unsigned flags;
int cpus;
- cpumask_t cpumask;
atomic_t record_disabled;
+ cpumask_var_t cpumask;
struct mutex mutex;
struct ring_buffer_per_cpu **buffers;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ struct notifier_block cpu_notify;
+#endif
+ u64 (*clock)(void);
};
struct ring_buffer_iter {
_____ret; \
})
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
+{
+ u64 time;
+
+ preempt_disable_notrace();
+ /* shift to debug/test normalization and TIME_EXTENTS */
+ time = buffer->clock() << DEBUG_SHIFT;
+ preempt_enable_no_resched_notrace();
+
+ return time;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
+
+void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
+ int cpu, u64 *ts)
+{
+ /* Just stupid testing the normalize function and deltas */
+ *ts >>= DEBUG_SHIFT;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
+
/**
* check_pages - integrity check of buffer pages
* @cpu_buffer: CPU buffer with pages to test
*
- * As a safty measure we check to make sure the data pages have not
+ * As a safety measure we check to make sure the data pages have not
* been corrupted.
*/
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;
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) {
+ list_for_each_entry_safe(bpage, tmp, head, list) {
if (RB_WARN_ON(cpu_buffer,
- page->list.next->prev != &page->list))
+ bpage->list.next->prev != &bpage->list))
return -1;
if (RB_WARN_ON(cpu_buffer,
- page->list.prev->next != &page->list))
+ bpage->list.prev->next != &bpage->list))
return -1;
}
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++) {
- page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
- if (!page)
+ if (!bpage)
goto free_pages;
- list_add(&page->list, &pages);
+ list_add(&bpage->list, &pages);
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page->page = (void *)addr;
+ 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 *page;
+ struct buffer_page *bpage;
unsigned long addr;
int ret;
cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
INIT_LIST_HEAD(&cpu_buffer->pages);
- page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
- if (!page)
+ if (!bpage)
goto fail_free_buffer;
- cpu_buffer->reader_page = page;
+ cpu_buffer->reader_page = bpage;
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto fail_free_reader;
- page->page = (void *)addr;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
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);
}
*/
extern int ring_buffer_page_too_big(void);
+#ifdef CONFIG_HOTPLUG_CPU
+static int rb_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu);
+#endif
+
/**
* 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;
+ buffer->clock = trace_clock_local;
/* need at least two pages */
if (buffer->pages == 1)
buffer->pages++;
- buffer->cpumask = cpu_possible_map;
+ /*
+ * In case of non-hotplug cpu, if the ring-buffer is allocated
+ * in early initcall, it will not be notified of secondary cpus.
+ * In that off case, we need to allocate for all possible cpus.
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+ get_online_cpus();
+ cpumask_copy(buffer->cpumask, cpu_online_mask);
+#else
+ cpumask_copy(buffer->cpumask, cpu_possible_mask);
+#endif
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] =
goto fail_free_buffers;
}
+#ifdef CONFIG_HOTPLUG_CPU
+ buffer->cpu_notify.notifier_call = rb_cpu_notify;
+ buffer->cpu_notify.priority = 0;
+ register_cpu_notifier(&buffer->cpu_notify);
+#endif
+
+ put_online_cpus();
mutex_init(&buffer->mutex);
return buffer;
}
kfree(buffer->buffers);
+ fail_free_cpumask:
+ free_cpumask_var(buffer->cpumask);
+ put_online_cpus();
+
fail_free_buffer:
kfree(buffer);
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc);
/**
* ring_buffer_free - free a ring buffer.
{
int cpu;
+ get_online_cpus();
+
+#ifdef CONFIG_HOTPLUG_CPU
+ unregister_cpu_notifier(&buffer->cpu_notify);
+#endif
+
for_each_buffer_cpu(buffer, cpu)
rb_free_cpu_buffer(buffer->buffers[cpu]);
+ put_online_cpus();
+
+ free_cpumask_var(buffer->cpumask);
+
kfree(buffer);
}
+EXPORT_SYMBOL_GPL(ring_buffer_free);
+
+void ring_buffer_set_clock(struct ring_buffer *buffer,
+ u64 (*clock)(void))
+{
+ buffer->clock = clock;
+}
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;
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);
}
if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
return;
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;
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);
return size;
mutex_lock(&buffer->mutex);
+ get_online_cpus();
nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
if (size < buffer_size) {
/* easy case, just free pages */
- if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
- mutex_unlock(&buffer->mutex);
- return -1;
- }
+ if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
+ goto out_fail;
rm_pages = buffer->pages - nr_pages;
* add these pages to the cpu_buffers. Otherwise we just free
* them all and return -ENOMEM;
*/
- if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
- mutex_unlock(&buffer->mutex);
- return -1;
- }
+ if (RB_WARN_ON(buffer, nr_pages <= buffer->pages))
+ goto out_fail;
new_pages = nr_pages - buffer->pages;
for_each_buffer_cpu(buffer, cpu) {
for (i = 0; i < new_pages; i++) {
- page = kzalloc_node(ALIGN(sizeof(*page),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage),
cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
- if (!page)
+ if (!bpage)
goto free_pages;
- list_add(&page->list, &pages);
+ list_add(&bpage->list, &pages);
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page->page = (void *)addr;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
}
}
rb_insert_pages(cpu_buffer, &pages, new_pages);
}
- if (RB_WARN_ON(buffer, !list_empty(&pages))) {
- mutex_unlock(&buffer->mutex);
- return -1;
- }
+ if (RB_WARN_ON(buffer, !list_empty(&pages)))
+ goto out_fail;
out:
buffer->pages = nr_pages;
+ put_online_cpus();
mutex_unlock(&buffer->mutex);
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);
}
+ put_online_cpus();
+ mutex_unlock(&buffer->mutex);
return -ENOMEM;
+
+ /*
+ * Something went totally wrong, and we are too paranoid
+ * to even clean up the mess.
+ */
+ out_fail:
+ put_online_cpus();
+ mutex_unlock(&buffer->mutex);
+ return -1;
}
+EXPORT_SYMBOL_GPL(ring_buffer_resize);
-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)
{
- return page->page + index;
+ return bpage->page->data + index;
}
static inline struct ring_buffer_event *
static inline unsigned rb_page_commit(struct buffer_page *bpage)
{
- return local_read(&bpage->commit);
+ return local_read(&bpage->page->commit);
}
/* Size is determined by what has been commited */
return rb_page_commit(cpu_buffer->head_page);
}
-/*
- * When the tail hits the head and the buffer is in overwrite mode,
- * the head jumps to the next page and all content on the previous
- * page is discarded. But before doing so, we update the overrun
- * variable of the buffer.
- */
-static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
-{
- struct ring_buffer_event *event;
- unsigned long head;
-
- for (head = 0; head < rb_head_size(cpu_buffer);
- head += rb_event_length(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;
- cpu_buffer->overrun++;
- cpu_buffer->entries--;
- }
-}
-
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
return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
}
-static inline int
+static int
rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
rb_commit_index(cpu_buffer) == index;
}
-static inline void
+static void
rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
struct ring_buffer_event *event)
{
if (RB_WARN_ON(cpu_buffer,
cpu_buffer->commit_page == cpu_buffer->tail_page))
return;
- cpu_buffer->commit_page->commit =
+ 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->time_stamp;
+ 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->commit, index);
+ local_set(&cpu_buffer->commit_page->page->commit, index);
}
-static inline void
+static void
rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
/*
* 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->commit =
+ 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->time_stamp;
+ 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->commit =
+ 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_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
- cpu_buffer->read_stamp = cpu_buffer->reader_page->time_stamp;
+ cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
cpu_buffer->reader_page->read = 0;
}
-static inline void rb_inc_iter(struct ring_buffer_iter *iter)
+static void rb_inc_iter(struct ring_buffer_iter *iter)
{
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
else
rb_inc_page(cpu_buffer, &iter->head_page);
- iter->read_stamp = iter->head_page->time_stamp;
+ iter->read_stamp = iter->head_page->page->time_stamp;
iter->head = 0;
}
* and with this, we can determine what to place into the
* data field.
*/
-static inline void
+static void
rb_update_event(struct ring_buffer_event *event,
unsigned type, unsigned length)
{
- event->type = type;
+ event->type_len = type;
switch (type) {
case RINGBUF_TYPE_PADDING:
- break;
-
case RINGBUF_TYPE_TIME_EXTEND:
- event->len =
- (RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1))
- >> RB_ALIGNMENT_SHIFT;
- break;
-
case RINGBUF_TYPE_TIME_STAMP:
- event->len =
- (RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1))
- >> RB_ALIGNMENT_SHIFT;
break;
- case RINGBUF_TYPE_DATA:
+ case 0:
length -= RB_EVNT_HDR_SIZE;
- if (length > RB_MAX_SMALL_DATA) {
- event->len = 0;
+ if (length > RB_MAX_SMALL_DATA)
event->array[0] = length;
- } else
- event->len =
- (length + (RB_ALIGNMENT-1))
- >> RB_ALIGNMENT_SHIFT;
+ else
+ event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
break;
default:
BUG();
}
}
-static inline unsigned rb_calculate_event_length(unsigned length)
+static unsigned rb_calculate_event_length(unsigned length)
{
struct ring_buffer_event event; /* Used only for sizeof array */
return length;
}
+
static struct ring_buffer_event *
-__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length, u64 *ts)
+rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned long length, unsigned long tail,
+ struct buffer_page *commit_page,
+ struct buffer_page *tail_page, u64 *ts)
{
- struct buffer_page *tail_page, *head_page, *reader_page;
- unsigned long tail, write;
+ struct buffer_page *next_page, *head_page, *reader_page;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
+ bool lock_taken = false;
unsigned long flags;
- tail_page = cpu_buffer->tail_page;
- write = local_add_return(length, &tail_page->write);
- tail = write - length;
+ next_page = tail_page;
- /* 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);
+ local_irq_save(flags);
+ /*
+ * Since the write to the buffer is still not
+ * fully lockless, we must be careful with NMIs.
+ * The locks in the writers are taken when a write
+ * crosses to a new page. The locks protect against
+ * races with the readers (this will soon be fixed
+ * with a lockless solution).
+ *
+ * Because we can not protect against NMIs, and we
+ * want to keep traces reentrant, we need to manage
+ * what happens when we are in an NMI.
+ *
+ * NMIs can happen after we take the lock.
+ * If we are in an NMI, only take the lock
+ * if it is not already taken. Otherwise
+ * simply fail.
+ */
+ if (unlikely(in_nmi())) {
+ if (!__raw_spin_trylock(&cpu_buffer->lock)) {
+ cpu_buffer->nmi_dropped++;
+ goto out_reset;
+ }
+ } else
__raw_spin_lock(&cpu_buffer->lock);
- rb_inc_page(cpu_buffer, &next_page);
+ lock_taken = true;
- head_page = cpu_buffer->head_page;
- reader_page = cpu_buffer->reader_page;
+ rb_inc_page(cpu_buffer, &next_page);
- /* we grabbed the lock before incrementing */
- if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
- goto out_unlock;
+ head_page = cpu_buffer->head_page;
+ reader_page = cpu_buffer->reader_page;
- /*
- * 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 == cpu_buffer->commit_page)) {
- WARN_ON_ONCE(1);
- goto out_unlock;
- }
+ /* we grabbed the lock before incrementing */
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_reset;
- if (next_page == head_page) {
- if (!(buffer->flags & RB_FL_OVERWRITE)) {
- /* reset write */
- if (tail <= BUF_PAGE_SIZE)
- local_set(&tail_page->write, tail);
- goto out_unlock;
- }
-
- /* tail_page has not moved yet? */
- if (tail_page == cpu_buffer->tail_page) {
- /* 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;
- }
- }
+ /*
+ * 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)) {
+ cpu_buffer->commit_overrun++;
+ goto out_reset;
+ }
- /*
- * 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 (next_page == head_page) {
+ if (!(buffer->flags & RB_FL_OVERWRITE))
+ goto out_reset;
+
+ /* tail_page has not moved yet? */
if (tail_page == cpu_buffer->tail_page) {
- local_set(&next_page->write, 0);
- local_set(&next_page->commit, 0);
- cpu_buffer->tail_page = next_page;
+ /* count overflows */
+ cpu_buffer->overrun +=
+ local_read(&head_page->entries);
- /* reread the time stamp */
- *ts = ring_buffer_time_stamp(cpu_buffer->cpu);
- cpu_buffer->tail_page->time_stamp = *ts;
+ rb_inc_page(cpu_buffer, &head_page);
+ cpu_buffer->head_page = head_page;
+ cpu_buffer->head_page->read = 0;
}
+ }
- /*
- * 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;
- }
+ /*
+ * 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->entries, 0);
+ local_set(&next_page->page->commit, 0);
+ cpu_buffer->tail_page = next_page;
+
+ /* reread the time stamp */
+ *ts = ring_buffer_time_stamp(buffer, cpu_buffer->cpu);
+ cpu_buffer->tail_page->page->time_stamp = *ts;
+ }
- if (tail <= BUF_PAGE_SIZE)
- /* Set the write back to the previous setting */
- local_set(&tail_page->write, tail);
+ /*
+ * 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);
+ rb_event_set_padding(event);
+ }
- /*
- * 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);
- }
+ /* Set the write back to the previous setting */
+ local_sub(length, &tail_page->write);
+ /*
+ * 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);
+
+ out_reset:
+ /* reset write */
+ local_sub(length, &tail_page->write);
+
+ if (likely(lock_taken))
__raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
+ local_irq_restore(flags);
+ return NULL;
+}
- /* fail and let the caller try again */
- return ERR_PTR(-EAGAIN);
- }
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+ unsigned type, unsigned long length, u64 *ts)
+{
+ struct buffer_page *tail_page, *commit_page;
+ struct ring_buffer_event *event;
+ unsigned long tail, write;
+
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
+ tail_page = cpu_buffer->tail_page;
+ write = local_add_return(length, &tail_page->write);
+ tail = write - length;
+
+ /* See if we shot pass the end of this buffer page */
+ if (write > BUF_PAGE_SIZE)
+ return rb_move_tail(cpu_buffer, length, tail,
+ commit_page, tail_page, ts);
/* We reserved something on the buffer */
event = __rb_page_index(tail_page, tail);
rb_update_event(event, type, length);
+ /* The passed in type is zero for DATA */
+ if (likely(!type))
+ local_inc(&tail_page->entries);
+
/*
* 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->time_stamp = *ts;
+ cpu_buffer->commit_page->page->time_stamp = *ts;
return event;
-
- out_unlock:
- __raw_spin_unlock(&cpu_buffer->lock);
- local_irq_restore(flags);
- return NULL;
}
static int
event->time_delta = *delta & TS_MASK;
event->array[0] = *delta >> TS_SHIFT;
} else {
- cpu_buffer->commit_page->time_stamp = *ts;
+ cpu_buffer->commit_page->page->time_stamp = *ts;
event->time_delta = 0;
event->array[0] = 0;
}
static struct ring_buffer_event *
rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
- unsigned type, unsigned long length)
+ unsigned long length)
{
struct ring_buffer_event *event;
u64 ts, delta;
int commit = 0;
int nr_loops = 0;
+ length = rb_calculate_event_length(length);
again:
/*
* We allow for interrupts to reenter here and do a trace.
if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
return NULL;
- ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+ ts = ring_buffer_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu);
/*
* Only the first commit can update the timestamp.
/* Non commits have zero deltas */
delta = 0;
- event = __rb_reserve_next(cpu_buffer, type, length, &ts);
+ event = __rb_reserve_next(cpu_buffer, 0, length, &ts);
if (PTR_ERR(event) == -EAGAIN)
goto again;
return event;
}
+#define TRACE_RECURSIVE_DEPTH 16
+
+static int trace_recursive_lock(void)
+{
+ current->trace_recursion++;
+
+ if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+ return 0;
+
+ /* Disable all tracing before we do anything else */
+ tracing_off_permanent();
+
+ printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
+ "HC[%lu]:SC[%lu]:NMI[%lu]\n",
+ current->trace_recursion,
+ hardirq_count() >> HARDIRQ_SHIFT,
+ softirq_count() >> SOFTIRQ_SHIFT,
+ in_nmi());
+
+ WARN_ON_ONCE(1);
+ return -1;
+}
+
+static void trace_recursive_unlock(void)
+{
+ WARN_ON_ONCE(!current->trace_recursion);
+
+ current->trace_recursion--;
+}
+
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
* @length: the length of the data to reserve (excluding event header)
- * @flags: a pointer to save the interrupt flags
*
* Returns a reseverd event on the ring buffer to copy directly to.
* The user of this interface will need to get the body to write into
* If NULL is returned, then nothing has been allocated or locked.
*/
struct ring_buffer_event *
-ring_buffer_lock_reserve(struct ring_buffer *buffer,
- unsigned long length,
- unsigned long *flags)
+ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
int cpu, resched;
- if (ring_buffers_off)
+ if (ring_buffer_flags != RB_BUFFERS_ON)
return NULL;
if (atomic_read(&buffer->record_disabled))
/* If we are tracing schedule, we don't want to recurse */
resched = ftrace_preempt_disable();
+ if (trace_recursive_lock())
+ goto out_nocheck;
+
cpu = raw_smp_processor_id();
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
goto out;
cpu_buffer = buffer->buffers[cpu];
if (atomic_read(&cpu_buffer->record_disabled))
goto out;
- length = rb_calculate_event_length(length);
- if (length > BUF_PAGE_SIZE)
+ if (length > BUF_MAX_DATA_SIZE)
goto out;
- event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+ event = rb_reserve_next_event(cpu_buffer, length);
if (!event)
goto out;
return event;
out:
+ trace_recursive_unlock();
+
+ out_nocheck:
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->entries++;
+ local_inc(&cpu_buffer->entries);
/* Only process further if we own the commit */
if (!rb_is_commit(cpu_buffer, event))
* ring_buffer_unlock_commit - commit a reserved
* @buffer: The buffer to commit to
* @event: The event pointer to commit.
- * @flags: the interrupt flags received from ring_buffer_lock_reserve.
*
* This commits the data to the ring buffer, and releases any locks held.
*
* Must be paired with ring_buffer_lock_reserve.
*/
int ring_buffer_unlock_commit(struct ring_buffer *buffer,
- struct ring_buffer_event *event,
- unsigned long flags)
+ struct ring_buffer_event *event)
{
struct ring_buffer_per_cpu *cpu_buffer;
int cpu = raw_smp_processor_id();
rb_commit(cpu_buffer, event);
+ trace_recursive_unlock();
+
/*
* Only the last preempt count needs to restore preemption.
*/
return 0;
}
+EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
+
+static inline void rb_event_discard(struct ring_buffer_event *event)
+{
+ /* array[0] holds the actual length for the discarded event */
+ event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
+ event->type_len = RINGBUF_TYPE_PADDING;
+ /* time delta must be non zero */
+ if (!event->time_delta)
+ event->time_delta = 1;
+}
+
+/**
+ * ring_buffer_event_discard - discard any event in the ring buffer
+ * @event: the event to discard
+ *
+ * Sometimes a event that is in the ring buffer needs to be ignored.
+ * This function lets the user discard an event in the ring buffer
+ * and then that event will not be read later.
+ *
+ * Note, it is up to the user to be careful with this, and protect
+ * against races. If the user discards an event that has been consumed
+ * it is possible that it could corrupt the ring buffer.
+ */
+void ring_buffer_event_discard(struct ring_buffer_event *event)
+{
+ rb_event_discard(event);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_event_discard);
+
+/**
+ * ring_buffer_commit_discard - discard an event that has not been committed
+ * @buffer: the ring buffer
+ * @event: non committed event to discard
+ *
+ * This is similar to ring_buffer_event_discard but must only be
+ * performed on an event that has not been committed yet. The difference
+ * is that this will also try to free the event from the ring buffer
+ * if another event has not been added behind it.
+ *
+ * If another event has been added behind it, it will set the event
+ * up as discarded, and perform the commit.
+ *
+ * If this function is called, do not call ring_buffer_unlock_commit on
+ * the event.
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+ struct ring_buffer_event *event)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long new_index, old_index;
+ struct buffer_page *bpage;
+ unsigned long index;
+ unsigned long addr;
+ int cpu;
+
+ /* The event is discarded regardless */
+ rb_event_discard(event);
+
+ /*
+ * This must only be called if the event has not been
+ * committed yet. Thus we can assume that preemption
+ * is still disabled.
+ */
+ RB_WARN_ON(buffer, preemptible());
+
+ cpu = smp_processor_id();
+ cpu_buffer = buffer->buffers[cpu];
+
+ new_index = rb_event_index(event);
+ old_index = new_index + rb_event_length(event);
+ addr = (unsigned long)event;
+ addr &= PAGE_MASK;
+
+ bpage = cpu_buffer->tail_page;
+
+ if (bpage == (void *)addr && rb_page_write(bpage) == old_index) {
+ /*
+ * This is on the tail page. It is possible that
+ * a write could come in and move the tail page
+ * and write to the next page. That is fine
+ * because we just shorten what is on this page.
+ */
+ index = local_cmpxchg(&bpage->write, old_index, new_index);
+ if (index == old_index)
+ goto out;
+ }
+
+ /*
+ * The commit is still visible by the reader, so we
+ * must increment entries.
+ */
+ local_inc(&cpu_buffer->entries);
+ out:
+ /*
+ * If a write came in and pushed the tail page
+ * we still need to update the commit pointer
+ * if we were the commit.
+ */
+ if (rb_is_commit(cpu_buffer, event))
+ rb_set_commit_to_write(cpu_buffer);
+
+ trace_recursive_unlock();
+
+ /*
+ * 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();
+
+}
+EXPORT_SYMBOL_GPL(ring_buffer_discard_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;
void *body;
int ret = -EBUSY;
int cpu, resched;
- if (ring_buffers_off)
+ if (ring_buffer_flags != RB_BUFFERS_ON)
return -EBUSY;
if (atomic_read(&buffer->record_disabled))
cpu = raw_smp_processor_id();
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
goto out;
cpu_buffer = buffer->buffers[cpu];
if (atomic_read(&cpu_buffer->record_disabled))
goto out;
- event_length = rb_calculate_event_length(length);
- event = rb_reserve_next_event(cpu_buffer,
- RINGBUF_TYPE_DATA, event_length);
+ if (length > BUF_MAX_DATA_SIZE)
+ goto out;
+
+ event = rb_reserve_next_event(cpu_buffer, length);
if (!event)
goto out;
return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_write);
-static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
{
struct buffer_page *reader = cpu_buffer->reader_page;
struct buffer_page *head = cpu_buffer->head_page;
{
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
unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 0;
cpu_buffer = buffer->buffers[cpu];
- return cpu_buffer->entries;
+ ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+ - cpu_buffer->read;
+
+ return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
/**
* ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->overrun;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
+
+/**
+ * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return 0;
+
+ cpu_buffer = buffer->buffers[cpu];
+ ret = cpu_buffer->nmi_dropped;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
+
+/**
+ * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long
+ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+ struct ring_buffer_per_cpu *cpu_buffer;
+ unsigned long ret;
- if (!cpu_isset(cpu, buffer->cpumask))
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
return 0;
cpu_buffer = buffer->buffers[cpu];
- return cpu_buffer->overrun;
+ ret = cpu_buffer->commit_overrun;
+
+ return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);
/**
* ring_buffer_entries - get the number of entries in a buffer
/* if you care about this being correct, lock the buffer */
for_each_buffer_cpu(buffer, cpu) {
cpu_buffer = buffer->buffers[cpu];
- entries += cpu_buffer->entries;
+ entries += (local_read(&cpu_buffer->entries) -
+ cpu_buffer->overrun) - cpu_buffer->read;
}
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)
{
if (iter->head)
iter->read_stamp = cpu_buffer->read_stamp;
else
- iter->read_stamp = iter->head_page->time_stamp;
+ iter->read_stamp = iter->head_page->page->time_stamp;
}
/**
*/
void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
{
- struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ struct ring_buffer_per_cpu *cpu_buffer;
unsigned long flags;
+ if (!iter)
+ return;
+
+ cpu_buffer = iter->cpu_buffer;
+
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
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,
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
{
u64 delta;
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
return;
cpu_buffer->reader_page->list.prev = reader->list.prev;
local_set(&cpu_buffer->reader_page->write, 0);
- local_set(&cpu_buffer->reader_page->commit, 0);
+ local_set(&cpu_buffer->reader_page->entries, 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;
event = rb_reader_event(cpu_buffer);
- if (event->type == RINGBUF_TYPE_DATA)
- cpu_buffer->entries--;
+ if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX
+ || rb_discarded_event(event))
+ cpu_buffer->read++;
rb_update_read_stamp(cpu_buffer, event);
struct buffer_page *reader;
int nr_loops = 0;
- if (!cpu_isset(cpu, buffer->cpumask))
- return NULL;
-
cpu_buffer = buffer->buffers[cpu];
again:
event = rb_reader_event(cpu_buffer);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
- RB_WARN_ON(cpu_buffer, 1);
+ if (rb_null_event(event))
+ RB_WARN_ON(cpu_buffer, 1);
+ /*
+ * Because the writer could be discarding every
+ * event it creates (which would probably be bad)
+ * if we were to go back to "again" then we may never
+ * catch up, and will trigger the warn on, or lock
+ * the box. Return the padding, and we will release
+ * the current locks, and try again.
+ */
rb_advance_reader(cpu_buffer);
- return NULL;
+ return event;
case RINGBUF_TYPE_TIME_EXTEND:
/* Internal data, OK to advance */
case RINGBUF_TYPE_DATA:
if (ts) {
*ts = cpu_buffer->read_stamp + event->time_delta;
- ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+ ring_buffer_normalize_time_stamp(buffer,
+ cpu_buffer->cpu, ts);
}
return event;
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_peek);
static struct ring_buffer_event *
rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
event = rb_iter_head_event(iter);
- switch (event->type) {
+ switch (event->type_len) {
case RINGBUF_TYPE_PADDING:
- rb_inc_iter(iter);
- goto again;
+ if (rb_null_event(event)) {
+ rb_inc_iter(iter);
+ goto again;
+ }
+ rb_advance_iter(iter);
+ return event;
case RINGBUF_TYPE_TIME_EXTEND:
/* Internal data, OK to advance */
case RINGBUF_TYPE_DATA:
if (ts) {
*ts = iter->read_stamp + event->time_delta;
- ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+ ring_buffer_normalize_time_stamp(buffer,
+ cpu_buffer->cpu, ts);
}
return event;
return NULL;
}
+EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
/**
* ring_buffer_peek - peek at the next event to be read
struct ring_buffer_event *event;
unsigned long flags;
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return NULL;
+
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_buffer_peek(buffer, cpu, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
struct ring_buffer_event *event;
unsigned long flags;
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_iter_peek(iter, ts);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
struct ring_buffer_event *
ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
{
- struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
- struct ring_buffer_event *event;
+ struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_event *event = NULL;
unsigned long flags;
- if (!cpu_isset(cpu, buffer->cpumask))
- return NULL;
+ again:
+ /* might be called in atomic */
+ preempt_disable();
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+ cpu_buffer = buffer->buffers[cpu];
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_buffer_peek(buffer, cpu, ts);
if (!event)
- goto out;
+ goto out_unlock;
rb_advance_reader(cpu_buffer);
- out:
+ out_unlock:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ out:
+ preempt_enable();
+
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
return event;
}
+EXPORT_SYMBOL_GPL(ring_buffer_consume);
/**
* ring_buffer_read_start - start a non consuming read of the 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);
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
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
unsigned long flags;
+ again:
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
event = rb_iter_peek(iter, ts);
if (!event)
out:
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+ if (event && event->type_len == RINGBUF_TYPE_PADDING) {
+ cpu_relax();
+ goto again;
+ }
+
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);
local_set(&cpu_buffer->head_page->write, 0);
- local_set(&cpu_buffer->head_page->commit, 0);
+ local_set(&cpu_buffer->head_page->entries, 0);
+ local_set(&cpu_buffer->head_page->page->commit, 0);
cpu_buffer->head_page->read = 0;
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
local_set(&cpu_buffer->reader_page->write, 0);
- local_set(&cpu_buffer->reader_page->commit, 0);
+ local_set(&cpu_buffer->reader_page->entries, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
cpu_buffer->reader_page->read = 0;
+ cpu_buffer->nmi_dropped = 0;
+ cpu_buffer->commit_overrun = 0;
cpu_buffer->overrun = 0;
- cpu_buffer->entries = 0;
+ cpu_buffer->read = 0;
+ local_set(&cpu_buffer->entries, 0);
+
+ cpu_buffer->write_stamp = 0;
+ cpu_buffer->read_stamp = 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;
+ atomic_inc(&cpu_buffer->record_disabled);
+
spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
__raw_spin_lock(&cpu_buffer->lock);
__raw_spin_unlock(&cpu_buffer->lock);
spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ atomic_dec(&cpu_buffer->record_disabled);
}
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
/**
* ring_buffer_reset - reset a ring buffer
for_each_buffer_cpu(buffer, cpu)
ring_buffer_reset_cpu(buffer, cpu);
}
+EXPORT_SYMBOL_GPL(ring_buffer_reset);
/**
* rind_buffer_empty - is the ring buffer empty?
if (!rb_per_cpu_empty(cpu_buffer))
return 0;
}
+
return 1;
}
+EXPORT_SYMBOL_GPL(ring_buffer_empty);
/**
* ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ int ret;
- 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);
+ ret = rb_per_cpu_empty(cpu_buffer);
+
+
+ return ret;
}
+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;
+ int ret = -EINVAL;
- if (!cpu_isset(cpu, buffer_a->cpumask) ||
- !cpu_isset(cpu, buffer_b->cpumask))
- return -EINVAL;
+ if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
+ !cpumask_test_cpu(cpu, buffer_b->cpumask))
+ goto out;
/* At least make sure the two buffers are somewhat the same */
- if (buffer_a->size != buffer_b->size ||
- buffer_a->pages != buffer_b->pages)
- return -EINVAL;
+ if (buffer_a->pages != buffer_b->pages)
+ goto out;
+
+ ret = -EAGAIN;
+
+ if (ring_buffer_flags != RB_BUFFERS_ON)
+ goto out;
+
+ if (atomic_read(&buffer_a->record_disabled))
+ goto out;
+
+ if (atomic_read(&buffer_b->record_disabled))
+ goto out;
cpu_buffer_a = buffer_a->buffers[cpu];
cpu_buffer_b = buffer_b->buffers[cpu];
+ if (atomic_read(&cpu_buffer_a->record_disabled))
+ goto out;
+
+ if (atomic_read(&cpu_buffer_b->record_disabled))
+ goto out;
+
/*
* We can't do a synchronize_sched here because this
* function can be called in atomic context.
atomic_dec(&cpu_buffer_a->record_disabled);
atomic_dec(&cpu_buffer_b->record_disabled);
- return 0;
+ ret = 0;
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
+
+/**
+ * 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)
+{
+ struct buffer_data_page *bpage;
+ unsigned long addr;
+
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ return NULL;
+
+ bpage = (void *)addr;
+
+ rb_init_page(bpage);
+
+ return bpage;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
+
+/**
+ * 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);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
+
+/**
+ * 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
+ * @len: amount to extract
+ * @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_read_page(buffer);
+ * if (!rpage)
+ * return error;
+ * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
+ * if (ret >= 0)
+ * process_page(rpage, ret);
+ *
+ * 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:
+ * >=0 if data has been transferred, returns the offset of consumed data.
+ * <0 if no data has been transferred.
+ */
+int ring_buffer_read_page(struct ring_buffer *buffer,
+ void **data_page, size_t len, int cpu, int full)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ struct buffer_data_page *bpage;
+ struct buffer_page *reader;
+ unsigned long flags;
+ unsigned int commit;
+ unsigned int read;
+ u64 save_timestamp;
+ int ret = -1;
+
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ goto out;
+
+ /*
+ * If len is not big enough to hold the page header, then
+ * we can not copy anything.
+ */
+ if (len <= BUF_PAGE_HDR_SIZE)
+ goto out;
+
+ len -= BUF_PAGE_HDR_SIZE;
+
+ if (!data_page)
+ goto out;
+
+ bpage = *data_page;
+ if (!bpage)
+ goto out;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ reader = rb_get_reader_page(cpu_buffer);
+ if (!reader)
+ goto out_unlock;
+
+ event = rb_reader_event(cpu_buffer);
+
+ read = reader->read;
+ commit = rb_page_commit(reader);
+
+ /*
+ * If this page has been partially read or
+ * if len is not big enough to read the rest of the page or
+ * a writer is still on the page, then
+ * we must copy the data from the page to the buffer.
+ * Otherwise, we can simply swap the page with the one passed in.
+ */
+ if (read || (len < (commit - read)) ||
+ cpu_buffer->reader_page == cpu_buffer->commit_page) {
+ struct buffer_data_page *rpage = cpu_buffer->reader_page->page;
+ unsigned int rpos = read;
+ unsigned int pos = 0;
+ unsigned int size;
+
+ if (full)
+ goto out_unlock;
+
+ if (len > (commit - read))
+ len = (commit - read);
+
+ size = rb_event_length(event);
+
+ if (len < size)
+ goto out_unlock;
+
+ /* save the current timestamp, since the user will need it */
+ save_timestamp = cpu_buffer->read_stamp;
+
+ /* Need to copy one event at a time */
+ do {
+ memcpy(bpage->data + pos, rpage->data + rpos, size);
+
+ len -= size;
+
+ rb_advance_reader(cpu_buffer);
+ rpos = reader->read;
+ pos += size;
+
+ event = rb_reader_event(cpu_buffer);
+ size = rb_event_length(event);
+ } while (len > size);
+
+ /* update bpage */
+ local_set(&bpage->commit, pos);
+ bpage->time_stamp = save_timestamp;
+
+ /* we copied everything to the beginning */
+ read = 0;
+ } else {
+ /* update the entry counter */
+ cpu_buffer->read += local_read(&reader->entries);
+
+ /* swap the pages */
+ rb_init_page(bpage);
+ bpage = reader->page;
+ reader->page = *data_page;
+ local_set(&reader->write, 0);
+ local_set(&reader->entries, 0);
+ reader->read = 0;
+ *data_page = bpage;
+ }
+ ret = read;
+
+ out_unlock:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ out:
+ return ret;
}
+EXPORT_SYMBOL_GPL(ring_buffer_read_page);
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- int *p = filp->private_data;
+ unsigned long *p = filp->private_data;
char buf[64];
int r;
- /* !ring_buffers_off == tracing_on */
- r = sprintf(buf, "%d\n", !*p);
+ 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);
}
rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- int *p = filp->private_data;
+ unsigned long *p = filp->private_data;
char buf[64];
- long val;
+ unsigned long val;
int ret;
if (cnt >= sizeof(buf))
if (ret < 0)
return ret;
- /* !ring_buffers_off == tracing_on */
- *p = !val;
+ 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 = {
+static const 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_buffers_off, &rb_simple_fops);
- if (!entry)
- pr_warning("Could not create debugfs 'tracing_on' entry\n");
+ trace_create_file("tracing_on", 0644, d_tracer,
+ &ring_buffer_flags, &rb_simple_fops);
return 0;
}
fs_initcall(rb_init_debugfs);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int rb_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ struct ring_buffer *buffer =
+ container_of(self, struct ring_buffer, cpu_notify);
+ long cpu = (long)hcpu;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+ if (cpu_isset(cpu, *buffer->cpumask))
+ return NOTIFY_OK;
+
+ buffer->buffers[cpu] =
+ rb_allocate_cpu_buffer(buffer, cpu);
+ if (!buffer->buffers[cpu]) {
+ WARN(1, "failed to allocate ring buffer on CPU %ld\n",
+ cpu);
+ return NOTIFY_OK;
+ }
+ smp_wmb();
+ cpu_set(cpu, *buffer->cpumask);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ /*
+ * Do nothing.
+ * If we were to free the buffer, then the user would
+ * lose any trace that was in the buffer.
+ */
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+#endif