diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9286f88..13aaf5e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -27,6 +27,7 @@
#include <linux/cpu.h>
#include <linux/oom.h>
+#include <asm/local64.h>
#include <asm/local.h>
/*
@@ -317,6 +318,11 @@ struct buffer_data_page {
unsigned char data[] RB_ALIGN_DATA; /* data of buffer page */
};
+struct buffer_data_read_page {
+ unsigned order; /* order of the page */
+ struct buffer_data_page *data; /* actual data, stored in this page */
+};
+
/*
* Note, the buffer_page list must be first. The buffer pages
* are allocated in cache lines, which means that each buffer
@@ -331,6 +337,7 @@ struct buffer_page {
unsigned read; /* index for next read */
local_t entries; /* entries on this page */
unsigned long real_end; /* real end of data */
+ unsigned order; /* order of the page */
struct buffer_data_page *page; /* Actual data page */
};
@@ -361,7 +368,7 @@ static __always_inline unsigned int rb_page_commit(struct buffer_page *bpage)
static void free_buffer_page(struct buffer_page *bpage)
{
- free_page((unsigned long)bpage->page);
+ free_pages((unsigned long)bpage->page, bpage->order);
kfree(bpage);
}
@@ -373,41 +380,6 @@ static inline bool test_time_stamp(u64 delta)
return !!(delta & TS_DELTA_TEST);
}
-#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;
-
- trace_seq_printf(s, "\tfield: u64 timestamp;\t"
- "offset:0;\tsize:%u;\tsigned:%u;\n",
- (unsigned int)sizeof(field.time_stamp),
- (unsigned int)is_signed_type(u64));
-
- trace_seq_printf(s, "\tfield: local_t commit;\t"
- "offset:%u;\tsize:%u;\tsigned:%u;\n",
- (unsigned int)offsetof(typeof(field), commit),
- (unsigned int)sizeof(field.commit),
- (unsigned int)is_signed_type(long));
-
- trace_seq_printf(s, "\tfield: int overwrite;\t"
- "offset:%u;\tsize:%u;\tsigned:%u;\n",
- (unsigned int)offsetof(typeof(field), commit),
- 1,
- (unsigned int)is_signed_type(long));
-
- trace_seq_printf(s, "\tfield: char data;\t"
- "offset:%u;\tsize:%u;\tsigned:%u;\n",
- (unsigned int)offsetof(typeof(field), data),
- (unsigned int)BUF_PAGE_SIZE,
- (unsigned int)is_signed_type(char));
-
- return !trace_seq_has_overflowed(s);
-}
-
struct rb_irq_work {
struct irq_work work;
wait_queue_head_t waiters;
@@ -463,27 +435,9 @@ enum {
RB_CTX_MAX
};
-#if BITS_PER_LONG == 32
-#define RB_TIME_32
-#endif
-
-/* To test on 64 bit machines */
-//#define RB_TIME_32
-
-#ifdef RB_TIME_32
-
-struct rb_time_struct {
- local_t cnt;
- local_t top;
- local_t bottom;
- local_t msb;
-};
-#else
-#include <asm/local64.h>
struct rb_time_struct {
local64_t time;
};
-#endif
typedef struct rb_time_struct rb_time_t;
#define MAX_NEST 5
@@ -557,6 +511,10 @@ struct trace_buffer {
struct rb_irq_work irq_work;
bool time_stamp_abs;
+
+ unsigned int subbuf_size;
+ unsigned int subbuf_order;
+ unsigned int max_data_size;
};
struct ring_buffer_iter {
@@ -570,150 +528,48 @@ struct ring_buffer_iter {
u64 read_stamp;
u64 page_stamp;
struct ring_buffer_event *event;
+ size_t event_size;
int missed_events;
};
-#ifdef RB_TIME_32
-
-/*
- * On 32 bit machines, local64_t is very expensive. As the ring
- * buffer doesn't need all the features of a true 64 bit atomic,
- * on 32 bit, it uses these functions (64 still uses local64_t).
- *
- * For the ring buffer, 64 bit required operations for the time is
- * the following:
- *
- * - Reads may fail if it interrupted a modification of the time stamp.
- * It will succeed if it did not interrupt another write even if
- * the read itself is interrupted by a write.
- * It returns whether it was successful or not.
- *
- * - Writes always succeed and will overwrite other writes and writes
- * that were done by events interrupting the current write.
- *
- * - A write followed by a read of the same time stamp will always succeed,
- * but may not contain the same value.
- *
- * - A cmpxchg will fail if it interrupted another write or cmpxchg.
- * Other than that, it acts like a normal cmpxchg.
- *
- * The 60 bit time stamp is broken up by 30 bits in a top and bottom half
- * (bottom being the least significant 30 bits of the 60 bit time stamp).
- *
- * The two most significant bits of each half holds a 2 bit counter (0-3).
- * Each update will increment this counter by one.
- * When reading the top and bottom, if the two counter bits match then the
- * top and bottom together make a valid 60 bit number.
- */
-#define RB_TIME_SHIFT 30
-#define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1)
-#define RB_TIME_MSB_SHIFT 60
-
-static inline int rb_time_cnt(unsigned long val)
+int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s)
{
- return (val >> RB_TIME_SHIFT) & 3;
-}
-
-static inline u64 rb_time_val(unsigned long top, unsigned long bottom)
-{
- u64 val;
-
- val = top & RB_TIME_VAL_MASK;
- val <<= RB_TIME_SHIFT;
- val |= bottom & RB_TIME_VAL_MASK;
-
- return val;
-}
-
-static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt)
-{
- unsigned long top, bottom, msb;
- unsigned long c;
-
- /*
- * If the read is interrupted by a write, then the cnt will
- * be different. Loop until both top and bottom have been read
- * without interruption.
- */
- do {
- c = local_read(&t->cnt);
- top = local_read(&t->top);
- bottom = local_read(&t->bottom);
- msb = local_read(&t->msb);
- } while (c != local_read(&t->cnt));
-
- *cnt = rb_time_cnt(top);
-
- /* If top, msb or bottom counts don't match, this interrupted a write */
- if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom))
- return false;
-
- /* The shift to msb will lose its cnt bits */
- *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT);
- return true;
-}
-
-static bool rb_time_read(rb_time_t *t, u64 *ret)
-{
- unsigned long cnt;
-
- return __rb_time_read(t, ret, &cnt);
-}
-
-static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt)
-{
- return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT);
-}
-
-static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom,
- unsigned long *msb)
-{
- *top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK);
- *bottom = (unsigned long)(val & RB_TIME_VAL_MASK);
- *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT);
-}
+ struct buffer_data_page field;
-static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt)
-{
- val = rb_time_val_cnt(val, cnt);
- local_set(t, val);
-}
+ trace_seq_printf(s, "\tfield: u64 timestamp;\t"
+ "offset:0;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)sizeof(field.time_stamp),
+ (unsigned int)is_signed_type(u64));
-static void rb_time_set(rb_time_t *t, u64 val)
-{
- unsigned long cnt, top, bottom, msb;
+ trace_seq_printf(s, "\tfield: local_t commit;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ (unsigned int)sizeof(field.commit),
+ (unsigned int)is_signed_type(long));
- rb_time_split(val, &top, &bottom, &msb);
+ trace_seq_printf(s, "\tfield: int overwrite;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), commit),
+ 1,
+ (unsigned int)is_signed_type(long));
- /* Writes always succeed with a valid number even if it gets interrupted. */
- do {
- cnt = local_inc_return(&t->cnt);
- rb_time_val_set(&t->top, top, cnt);
- rb_time_val_set(&t->bottom, bottom, cnt);
- rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt);
- } while (cnt != local_read(&t->cnt));
-}
+ trace_seq_printf(s, "\tfield: char data;\t"
+ "offset:%u;\tsize:%u;\tsigned:%u;\n",
+ (unsigned int)offsetof(typeof(field), data),
+ (unsigned int)buffer->subbuf_size,
+ (unsigned int)is_signed_type(char));
-static inline bool
-rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
-{
- return local_try_cmpxchg(l, &expect, set);
+ return !trace_seq_has_overflowed(s);
}
-#else /* 64 bits */
-
-/* local64_t always succeeds */
-
-static inline bool rb_time_read(rb_time_t *t, u64 *ret)
+static inline void rb_time_read(rb_time_t *t, u64 *ret)
{
*ret = local64_read(&t->time);
- return true;
}
static void rb_time_set(rb_time_t *t, u64 val)
{
local64_set(&t->time, val);
}
-#endif
/*
* Enable this to make sure that the event passed to
@@ -820,10 +676,7 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer,
WARN_ONCE(1, "nest (%d) greater than max", nest);
fail:
- /* Can only fail on 32 bit */
- if (!rb_time_read(&cpu_buffer->write_stamp, &ts))
- /* Screw it, just read the current time */
- ts = rb_time_stamp(cpu_buffer->buffer);
+ rb_time_read(&cpu_buffer->write_stamp, &ts);
return ts;
}
@@ -1619,10 +1472,12 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
list_add(&bpage->list, pages);
- page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0);
+ page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags,
+ cpu_buffer->buffer->subbuf_order);
if (!page)
goto free_pages;
bpage->page = page_address(page);
+ bpage->order = cpu_buffer->buffer->subbuf_order;
rb_init_page(bpage->page);
if (user_thread && fatal_signal_pending(current))
@@ -1701,7 +1556,8 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu)
rb_check_bpage(cpu_buffer, bpage);
cpu_buffer->reader_page = bpage;
- page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+
+ page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, cpu_buffer->buffer->subbuf_order);
if (!page)
goto fail_free_reader;
bpage->page = page_address(page);
@@ -1784,7 +1640,14 @@ struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
goto fail_free_buffer;
- nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+ /* Default buffer page size - one system page */
+ buffer->subbuf_order = 0;
+ buffer->subbuf_size = PAGE_SIZE - BUF_PAGE_HDR_SIZE;
+
+ /* Max payload is buffer page size - header (8bytes) */
+ buffer->max_data_size = buffer->subbuf_size - (sizeof(u32) * 2);
+
+ nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
buffer->flags = flags;
buffer->clock = trace_clock_local;
buffer->reader_lock_key = key;
@@ -2103,7 +1966,7 @@ static void update_pages_handler(struct work_struct *work)
* @size: the new size.
* @cpu_id: the cpu buffer to resize
*
- * Minimum size is 2 * BUF_PAGE_SIZE.
+ * Minimum size is 2 * buffer->subbuf_size.
*
* Returns 0 on success and < 0 on failure.
*/
@@ -2125,7 +1988,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
!cpumask_test_cpu(cpu_id, buffer->cpumask))
return 0;
- nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+ nr_pages = DIV_ROUND_UP(size, buffer->subbuf_size);
/* we need a minimum of two pages */
if (nr_pages < 2)
@@ -2372,7 +2235,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
*/
barrier();
- if ((iter->head + length) > commit || length > BUF_PAGE_SIZE)
+ if ((iter->head + length) > commit || length > iter->event_size)
/* Writer corrupted the read? */
goto reset;
@@ -2412,11 +2275,13 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
}
static __always_inline unsigned
-rb_event_index(struct ring_buffer_event *event)
+rb_event_index(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event)
{
unsigned long addr = (unsigned long)event;
- return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
+ addr &= (PAGE_SIZE << cpu_buffer->buffer->subbuf_order) - 1;
+
+ return addr - BUF_PAGE_HDR_SIZE;
}
static void rb_inc_iter(struct ring_buffer_iter *iter)
@@ -2605,6 +2470,7 @@ static inline void
rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
unsigned long tail, struct rb_event_info *info)
{
+ unsigned long bsize = READ_ONCE(cpu_buffer->buffer->subbuf_size);
struct buffer_page *tail_page = info->tail_page;
struct ring_buffer_event *event;
unsigned long length = info->length;
@@ -2613,13 +2479,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* Only the event that crossed the page boundary
* must fill the old tail_page with padding.
*/
- if (tail >= BUF_PAGE_SIZE) {
+ if (tail >= bsize) {
/*
* If the page was filled, then we still need
* to update the real_end. Reset it to zero
* and the reader will ignore it.
*/
- if (tail == BUF_PAGE_SIZE)
+ if (tail == bsize)
tail_page->real_end = 0;
local_sub(length, &tail_page->write);
@@ -2647,7 +2513,7 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
* If we are less than the minimum size, we don't need to
* worry about it.
*/
- if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
+ if (tail > (bsize - RB_EVNT_MIN_SIZE)) {
/* No room for any events */
/* Mark the rest of the page with padding */
@@ -2662,19 +2528,19 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
}
/* Put in a discarded event */
- event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
+ event->array[0] = (bsize - tail) - RB_EVNT_HDR_SIZE;
event->type_len = RINGBUF_TYPE_PADDING;
/* time delta must be non zero */
event->time_delta = 1;
/* account for padding bytes */
- local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+ local_add(bsize - tail, &cpu_buffer->entries_bytes);
/* Make sure the padding is visible before the tail_page->write update */
smp_wmb();
/* Set write to end of buffer */
- length = (tail + length) - BUF_PAGE_SIZE;
+ length = (tail + length) - bsize;
local_sub(length, &tail_page->write);
}
@@ -2788,7 +2654,8 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
/* Slow path */
static struct ring_buffer_event *
-rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+ struct ring_buffer_event *event, u64 delta, bool abs)
{
if (abs)
event->type_len = RINGBUF_TYPE_TIME_STAMP;
@@ -2796,7 +2663,7 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs)
event->type_len = RINGBUF_TYPE_TIME_EXTEND;
/* Not the first event on the page, or not delta? */