linux/block/blk-merge.c

541 lines
13 KiB
C
Raw Normal View History

/*
* Functions related to segment and merge handling
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include "blk.h"
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
struct bio *bio)
{
struct bio_vec *bv, *bvprv = NULL;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
int cluster, i, high, highprv = 1;
unsigned int seg_size, nr_phys_segs;
struct bio *fbio, *bbio;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
if (!bio)
return 0;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
fbio = bio;
cluster = blk_queue_cluster(q);
seg_size = 0;
nr_phys_segs = 0;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
for_each_bio(bio) {
bio_for_each_segment(bv, bio, i) {
/*
* the trick here is making sure that a high page is
* never considered part of another segment, since that
* might change with the bounce page.
*/
high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
if (high || highprv)
goto new_segment;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
if (cluster) {
if (seg_size + bv->bv_len
> queue_max_segment_size(q))
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
goto new_segment;
if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
goto new_segment;
if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
goto new_segment;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
seg_size += bv->bv_len;
bvprv = bv;
continue;
}
new_segment:
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
if (nr_phys_segs == 1 && seg_size >
fbio->bi_seg_front_size)
fbio->bi_seg_front_size = seg_size;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
nr_phys_segs++;
bvprv = bv;
seg_size = bv->bv_len;
highprv = high;
}
bbio = bio;
}
if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
fbio->bi_seg_front_size = seg_size;
if (seg_size > bbio->bi_seg_back_size)
bbio->bi_seg_back_size = seg_size;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
return nr_phys_segs;
}
void blk_recalc_rq_segments(struct request *rq)
{
rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio);
}
void blk_recount_segments(struct request_queue *q, struct bio *bio)
{
struct bio *nxt = bio->bi_next;
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 09:03:10 +01:00
bio->bi_next = NULL;
bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
bio->bi_next = nxt;
bio->bi_flags |= (1 << BIO_SEG_VALID);
}
EXPORT_SYMBOL(blk_recount_segments);
static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
struct bio *nxt)
{
if (!blk_queue_cluster(q))
return 0;
if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
queue_max_segment_size(q))
return 0;
if (!bio_has_data(bio))
return 1;
if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
return 0;
/*
* bio and nxt are contiguous in memory; check if the queue allows
* these two to be merged into one
*/
if (BIO_SEG_BOUNDARY(q, bio, nxt))
return 1;
return 0;
}
static void
__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
struct scatterlist *sglist, struct bio_vec **bvprv,
struct scatterlist **sg, int *nsegs, int *cluster)
{
int nbytes = bvec->bv_len;
if (*bvprv && *cluster) {
if ((*sg)->length + nbytes > queue_max_segment_size(q))
goto new_segment;
if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec))
goto new_segment;
if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec))
goto new_segment;
(*sg)->length += nbytes;
} else {
new_segment:
if (!*sg)
*sg = sglist;
else {
/*
* If the driver previously mapped a shorter
* list, we could see a termination bit
* prematurely unless it fully inits the sg
* table on each mapping. We KNOW that there
* must be more entries here or the driver
* would be buggy, so force clear the
* termination bit to avoid doing a full
* sg_init_table() in drivers for each command.
*/
(*sg)->page_link &= ~0x02;
*sg = sg_next(*sg);
}
sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
(*nsegs)++;
}
*bvprv = bvec;
}
/*
* map a request to scatterlist, return number of sg entries setup. Caller
* must make sure sg can hold rq->nr_phys_segments entries
*/
int blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist)
{
struct bio_vec *bvec, *bvprv;
struct req_iterator iter;
struct scatterlist *sg;
int nsegs, cluster;
nsegs = 0;
cluster = blk_queue_cluster(q);
/*
* for each bio in rq
*/
bvprv = NULL;
sg = NULL;
rq_for_each_segment(bvec, rq, iter) {
__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
&nsegs, &cluster);
} /* segments in rq */
if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:41 +02:00
(blk_rq_bytes(rq) & q->dma_pad_mask)) {
unsigned int pad_len =
(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
sg->length += pad_len;
rq->extra_len += pad_len;
}
if (q->dma_drain_size && q->dma_drain_needed(rq)) {
if (rq->cmd_flags & REQ_WRITE)
memset(q->dma_drain_buffer, 0, q->dma_drain_size);
sg->page_link &= ~0x02;
sg = sg_next(sg);
sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
q->dma_drain_size,
((unsigned long)q->dma_drain_buffer) &
(PAGE_SIZE - 1));
nsegs++;
rq->extra_len += q->dma_drain_size;
}
if (sg)
sg_mark_end(sg);
return nsegs;
}
EXPORT_SYMBOL(blk_rq_map_sg);
/**
* blk_bio_map_sg - map a bio to a scatterlist
* @q: request_queue in question
* @bio: bio being mapped
* @sglist: scatterlist being mapped
*
* Note:
* Caller must make sure sg can hold bio->bi_phys_segments entries
*
* Will return the number of sg entries setup
*/
int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist)
{
struct bio_vec *bvec, *bvprv;
struct scatterlist *sg;
int nsegs, cluster;
unsigned long i;
nsegs = 0;
cluster = blk_queue_cluster(q);
bvprv = NULL;
sg = NULL;
bio_for_each_segment(bvec, bio, i) {
__blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
&nsegs, &cluster);
} /* segments in bio */
if (sg)
sg_mark_end(sg);
BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
return nsegs;
}
EXPORT_SYMBOL(blk_bio_map_sg);
static inline int ll_new_hw_segment(struct request_queue *q,
struct request *req,
struct bio *bio)
{
int nr_phys_segs = bio_phys_segments(q, bio);
if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q))
goto no_merge;
if (bio_integrity(bio) && blk_integrity_merge_bio(q, req, bio))
goto no_merge;
/*
* This will form the start of a new hw segment. Bump both
* counters.
*/
req->nr_phys_segments += nr_phys_segs;
return 1;
no_merge:
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
}
int ll_back_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio)
{
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req)) {
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
}
if (!bio_flagged(req->biotail, BIO_SEG_VALID))
blk_recount_segments(q, req->biotail);
if (!bio_flagged(bio, BIO_SEG_VALID))
blk_recount_segments(q, bio);
return ll_new_hw_segment(q, req, bio);
}
int ll_front_merge_fn(struct request_queue *q, struct request *req,
struct bio *bio)
{
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req)) {
req->cmd_flags |= REQ_NOMERGE;
if (req == q->last_merge)
q->last_merge = NULL;
return 0;
}
if (!bio_flagged(bio, BIO_SEG_VALID))
blk_recount_segments(q, bio);
if (!bio_flagged(req->bio, BIO_SEG_VALID))
blk_recount_segments(q, req->bio);
return ll_new_hw_segment(q, req, bio);
}
static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
struct request *next)
{
int total_phys_segments;
unsigned int seg_size =
req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
/*
* First check if the either of the requests are re-queued
* requests. Can't merge them if they are.
*/
if (req->special || next->special)
return 0;
/*
* Will it become too large?
*/
if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
blk_rq_get_max_sectors(req))
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
if (req->nr_phys_segments == 1)
req->bio->bi_seg_front_size = seg_size;
if (next->nr_phys_segments == 1)
next->biotail->bi_seg_back_size = seg_size;
total_phys_segments--;
}
if (total_phys_segments > queue_max_segments(q))
return 0;
if (blk_integrity_rq(req) && blk_integrity_merge_rq(q, req, next))
return 0;
/* Merge is OK... */
req->nr_phys_segments = total_phys_segments;
return 1;
}
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 10:48:17 +02:00
/**
* blk_rq_set_mixed_merge - mark a request as mixed merge
* @rq: request to mark as mixed merge
*
* Description:
* @rq is about to be mixed merged. Make sure the attributes
* which can be mixed are set in each bio and mark @rq as mixed
* merged.
*/
void blk_rq_set_mixed_merge(struct request *rq)
{
unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
struct bio *bio;
if (rq->cmd_flags & REQ_MIXED_MERGE)
return;
/*
* @rq will no longer represent mixable attributes for all the
* contained bios. It will just track those of the first one.
* Distributes the attributs to each bio.
*/
for (bio = rq->bio; bio; bio = bio->bi_next) {
WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) &&
(bio->bi_rw & REQ_FAILFAST_MASK) != ff);
bio->bi_rw |= ff;
}
rq->cmd_flags |= REQ_MIXED_MERGE;
}
static void blk_account_io_merge(struct request *req)
{
if (blk_do_io_stat(req)) {
struct hd_struct *part;
int cpu;
cpu = part_stat_lock();
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 16:57:38 +01:00
part = req->part;
part_round_stats(cpu, part);
part_dec_in_flight(part, rq_data_dir(req));
hd_struct_put(part);
part_stat_unlock();
}
}
/*
* Has to be called with the request spinlock acquired
*/
static int attempt_merge(struct request_queue *q, struct request *req,
struct request *next)
{
if (!rq_mergeable(req) || !rq_mergeable(next))
return 0;
if (!blk_check_merge_flags(req->cmd_flags, next->cmd_flags))
return 0;
/*
* not contiguous
*/
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 15:24:39 +02:00
if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
return 0;
if (rq_data_dir(req) != rq_data_dir(next)
|| req->rq_disk != next->rq_disk
|| next->special)
return 0;
if (req->cmd_flags & REQ_WRITE_SAME &&
!blk_write_same_mergeable(req->bio, next->bio))
return 0;
/*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
* will have updated segment counts, update sector
* counts here.
*/
if (!ll_merge_requests_fn(q, req, next))
return 0;
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 10:48:17 +02:00
/*
* If failfast settings disagree or any of the two is already
* a mixed merge, mark both as mixed before proceeding. This
* makes sure that all involved bios have mixable attributes
* set properly.
*/
if ((req->cmd_flags | next->cmd_flags) & REQ_MIXED_MERGE ||
(req->cmd_flags & REQ_FAILFAST_MASK) !=
(next->cmd_flags & REQ_FAILFAST_MASK)) {
blk_rq_set_mixed_merge(req);
blk_rq_set_mixed_merge(next);
}
/*
* At this point we have either done a back merge
* or front merge. We need the smaller start_time of
* the merged requests to be the current request
* for accounting purposes.
*/
if (time_after(req->start_time, next->start_time))
req->start_time = next->start_time;
req->biotail->bi_next = next->bio;
req->biotail = next->biotail;
req->__data_len += blk_rq_bytes(next);
elv_merge_requests(q, req, next);
/*
* 'next' is going away, so update stats accordingly
*/
blk_account_io_merge(next);
req->ioprio = ioprio_best(req->ioprio, next->ioprio);
if (blk_rq_cpu_valid(next))
req->cpu = next->cpu;
/* owner-ship of bio passed from next to req */
next->bio = NULL;
__blk_put_request(q, next);
return 1;
}
int attempt_back_merge(struct request_queue *q, struct request *rq)
{
struct request *next = elv_latter_request(q, rq);
if (next)
return attempt_merge(q, rq, next);
return 0;
}
int attempt_front_merge(struct request_queue *q, struct request *rq)
{
struct request *prev = elv_former_request(q, rq);
if (prev)
return attempt_merge(q, prev, rq);
return 0;
}
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next)
{
return attempt_merge(q, rq, next);
}
bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
{
if (!rq_mergeable(rq) || !bio_mergeable(bio))
return false;
if (!blk_check_merge_flags(rq->cmd_flags, bio->bi_rw))
return false;
/* different data direction or already started, don't merge */
if (bio_data_dir(bio) != rq_data_dir(rq))
return false;
/* must be same device and not a special request */
if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
return false;
/* only merge integrity protected bio into ditto rq */
if (bio_integrity(bio) != blk_integrity_rq(rq))
return false;
/* must be using the same buffer */
if (rq->cmd_flags & REQ_WRITE_SAME &&
!blk_write_same_mergeable(rq->bio, bio))
return false;
return true;
}
int blk_try_merge(struct request *rq, struct bio *bio)
{
if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_sector)
return ELEVATOR_BACK_MERGE;
else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_sector)
return ELEVATOR_FRONT_MERGE;
return ELEVATOR_NO_MERGE;
}