kernel-ark/mm/bounce.c
Li Zefan 55782138e4 tracing/events: convert block trace points to TRACE_EVENT()
TRACE_EVENT is a more generic way to define tracepoints. Doing so adds
these new capabilities to this tracepoint:

  - zero-copy and per-cpu splice() tracing
  - binary tracing without printf overhead
  - structured logging records exposed under /debug/tracing/events
  - trace events embedded in function tracer output and other plugins
  - user-defined, per tracepoint filter expressions
  ...

Cons:

  - no dev_t info for the output of plug, unplug_timer and unplug_io events.
    no dev_t info for getrq and sleeprq events if bio == NULL.
    no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL.

    This is mainly because we can't get the deivce from a request queue.
    But this may change in the future.

  - A packet command is converted to a string in TP_assign, not TP_print.
    While blktrace do the convertion just before output.

    Since pc requests should be rather rare, this is not a big issue.

  - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT
    has a unique format, which means we have some unused data in a trace entry.

    The overhead is minimized by using __dynamic_array() instead of __array().

I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing:

      dd                   dd + ioctl blktrace       dd + TRACE_EVENT (splice)
1     7.36s, 42.7 MB/s     7.50s, 42.0 MB/s          7.41s, 42.5 MB/s
2     7.43s, 42.3 MB/s     7.48s, 42.1 MB/s          7.43s, 42.4 MB/s
3     7.38s, 42.6 MB/s     7.45s, 42.2 MB/s          7.41s, 42.5 MB/s

So the overhead of tracing is very small, and no regression when using
those trace events vs blktrace.

And the binary output of TRACE_EVENT is much smaller than blktrace:

 # ls -l -h
 -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0
 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1
 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out

Following are some comparisons between TRACE_EVENT and blktrace:

plug:
  kjournald-480   [000]   303.084981: block_plug: [kjournald]
  kjournald-480   [000]   303.084981:   8,0    P   N [kjournald]

unplug_io:
  kblockd/0-118   [000]   300.052973: block_unplug_io: [kblockd/0] 1
  kblockd/0-118   [000]   300.052974:   8,0    U   N [kblockd/0] 1

remap:
  kjournald-480   [000]   303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384
  kjournald-480   [000]   303.085043:   8,0    A   W 102736992 + 8 <- (8,8) 33384

bio_backmerge:
  kjournald-480   [000]   303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald]
  kjournald-480   [000]   303.085086:   8,0    M   W 102737032 + 8 [kjournald]

getrq:
  kjournald-480   [000]   303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald]
  kjournald-480   [000]   303.084975:   8,0    G   W 102736984 + 8 [kjournald]

  bash-2066  [001]  1072.953770:   8,0    G   N [bash]
  bash-2066  [001]  1072.953773: block_getrq: 0,0 N 0 + 0 [bash]

rq_complete:
  konsole-2065  [001]   300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0]
  konsole-2065  [001]   300.053191:   8,0    C   W 103669040 + 16 [0]

  ksoftirqd/1-7   [001]  1072.953811:   8,0    C   N (5a 00 08 00 00 00 00 00 24 00) [0]
  ksoftirqd/1-7   [001]  1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0]

rq_insert:
  kjournald-480   [000]   303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald]
  kjournald-480   [000]   303.084986:   8,0    I   W 102736984 + 8 [kjournald]

Changelog from v2 -> v3:

- use the newly introduced __dynamic_array().

Changelog from v1 -> v2:

- use __string() instead of __array() to minimize the memory required
  to store hex dump of rq->cmd().

- support large pc requests.

- add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT.

- some cleanups.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 12:34:23 -04:00

301 lines
6.5 KiB
C

/* bounce buffer handling for block devices
*
* - Split from highmem.c
*/
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/blktrace_api.h>
#include <asm/tlbflush.h>
#include <trace/events/block.h>
#define POOL_SIZE 64
#define ISA_POOL_SIZE 16
static mempool_t *page_pool, *isa_page_pool;
#ifdef CONFIG_HIGHMEM
static __init int init_emergency_pool(void)
{
struct sysinfo i;
si_meminfo(&i);
si_swapinfo(&i);
if (!i.totalhigh)
return 0;
page_pool = mempool_create_page_pool(POOL_SIZE, 0);
BUG_ON(!page_pool);
printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
return 0;
}
__initcall(init_emergency_pool);
/*
* highmem version, map in to vec
*/
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
{
unsigned long flags;
unsigned char *vto;
local_irq_save(flags);
vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ);
memcpy(vto + to->bv_offset, vfrom, to->bv_len);
kunmap_atomic(vto, KM_BOUNCE_READ);
local_irq_restore(flags);
}
#else /* CONFIG_HIGHMEM */
#define bounce_copy_vec(to, vfrom) \
memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)
#endif /* CONFIG_HIGHMEM */
/*
* allocate pages in the DMA region for the ISA pool
*/
static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
{
return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
}
/*
* gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
* as the max address, so check if the pool has already been created.
*/
int init_emergency_isa_pool(void)
{
if (isa_page_pool)
return 0;
isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
mempool_free_pages, (void *) 0);
BUG_ON(!isa_page_pool);
printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE);
return 0;
}
/*
* Simple bounce buffer support for highmem pages. Depending on the
* queue gfp mask set, *to may or may not be a highmem page. kmap it
* always, it will do the Right Thing
*/
static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
{
unsigned char *vfrom;
struct bio_vec *tovec, *fromvec;
int i;
__bio_for_each_segment(tovec, to, i, 0) {
fromvec = from->bi_io_vec + i;
/*
* not bounced
*/
if (tovec->bv_page == fromvec->bv_page)
continue;
/*
* fromvec->bv_offset and fromvec->bv_len might have been
* modified by the block layer, so use the original copy,
* bounce_copy_vec already uses tovec->bv_len
*/
vfrom = page_address(fromvec->bv_page) + tovec->bv_offset;
flush_dcache_page(tovec->bv_page);
bounce_copy_vec(tovec, vfrom);
}
}
static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
{
struct bio *bio_orig = bio->bi_private;
struct bio_vec *bvec, *org_vec;
int i;
if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
/*
* free up bounce indirect pages used
*/
__bio_for_each_segment(bvec, bio, i, 0) {
org_vec = bio_orig->bi_io_vec + i;
if (bvec->bv_page == org_vec->bv_page)
continue;
dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
mempool_free(bvec->bv_page, pool);
}
bio_endio(bio_orig, err);
bio_put(bio);
}
static void bounce_end_io_write(struct bio *bio, int err)
{
bounce_end_io(bio, page_pool, err);
}
static void bounce_end_io_write_isa(struct bio *bio, int err)
{
bounce_end_io(bio, isa_page_pool, err);
}
static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err)
{
struct bio *bio_orig = bio->bi_private;
if (test_bit(BIO_UPTODATE, &bio->bi_flags))
copy_to_high_bio_irq(bio_orig, bio);
bounce_end_io(bio, pool, err);
}
static void bounce_end_io_read(struct bio *bio, int err)
{
__bounce_end_io_read(bio, page_pool, err);
}
static void bounce_end_io_read_isa(struct bio *bio, int err)
{
__bounce_end_io_read(bio, isa_page_pool, err);
}
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
mempool_t *pool)
{
struct page *page;
struct bio *bio = NULL;
int i, rw = bio_data_dir(*bio_orig);
struct bio_vec *to, *from;
bio_for_each_segment(from, *bio_orig, i) {
page = from->bv_page;
/*
* is destination page below bounce pfn?
*/
if (page_to_pfn(page) <= q->bounce_pfn)
continue;
/*
* irk, bounce it
*/
if (!bio) {
unsigned int cnt = (*bio_orig)->bi_vcnt;
bio = bio_alloc(GFP_NOIO, cnt);
memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec));
}
to = bio->bi_io_vec + i;
to->bv_page = mempool_alloc(pool, q->bounce_gfp);
to->bv_len = from->bv_len;
to->bv_offset = from->bv_offset;
inc_zone_page_state(to->bv_page, NR_BOUNCE);
if (rw == WRITE) {
char *vto, *vfrom;
flush_dcache_page(from->bv_page);
vto = page_address(to->bv_page) + to->bv_offset;
vfrom = kmap(from->bv_page) + from->bv_offset;
memcpy(vto, vfrom, to->bv_len);
kunmap(from->bv_page);
}
}
/*
* no pages bounced
*/
if (!bio)
return;
trace_block_bio_bounce(q, *bio_orig);
/*
* at least one page was bounced, fill in possible non-highmem
* pages
*/
__bio_for_each_segment(from, *bio_orig, i, 0) {
to = bio_iovec_idx(bio, i);
if (!to->bv_page) {
to->bv_page = from->bv_page;
to->bv_len = from->bv_len;
to->bv_offset = from->bv_offset;
}
}
bio->bi_bdev = (*bio_orig)->bi_bdev;
bio->bi_flags |= (1 << BIO_BOUNCED);
bio->bi_sector = (*bio_orig)->bi_sector;
bio->bi_rw = (*bio_orig)->bi_rw;
bio->bi_vcnt = (*bio_orig)->bi_vcnt;
bio->bi_idx = (*bio_orig)->bi_idx;
bio->bi_size = (*bio_orig)->bi_size;
if (pool == page_pool) {
bio->bi_end_io = bounce_end_io_write;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read;
} else {
bio->bi_end_io = bounce_end_io_write_isa;
if (rw == READ)
bio->bi_end_io = bounce_end_io_read_isa;
}
bio->bi_private = *bio_orig;
*bio_orig = bio;
}
void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
{
mempool_t *pool;
/*
* Data-less bio, nothing to bounce
*/
if (!bio_has_data(*bio_orig))
return;
/*
* for non-isa bounce case, just check if the bounce pfn is equal
* to or bigger than the highest pfn in the system -- in that case,
* don't waste time iterating over bio segments
*/
if (!(q->bounce_gfp & GFP_DMA)) {
if (q->bounce_pfn >= blk_max_pfn)
return;
pool = page_pool;
} else {
BUG_ON(!isa_page_pool);
pool = isa_page_pool;
}
/*
* slow path
*/
__blk_queue_bounce(q, bio_orig, pool);
}
EXPORT_SYMBOL(blk_queue_bounce);