forked from Minki/linux
445251d0f4
I ran into an issue on my laptop that triggered a bug on the discard path: WARNING: CPU: 2 PID: 207 at drivers/nvme/host/core.c:527 nvme_setup_cmd+0x3d3/0x430 Modules linked in: rfcomm fuse ctr ccm bnep arc4 binfmt_misc snd_hda_codec_hdmi nls_iso8859_1 nls_cp437 vfat snd_hda_codec_conexant fat snd_hda_codec_generic iwlmvm snd_hda_intel snd_hda_codec snd_hwdep mac80211 snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq x86_pkg_temp_thermal intel_powerclamp kvm_intel uvcvideo iwlwifi btusb snd_seq_device videobuf2_vmalloc btintel videobuf2_memops kvm snd_timer videobuf2_v4l2 bluetooth irqbypass videobuf2_core aesni_intel aes_x86_64 crypto_simd cryptd snd glue_helper videodev cfg80211 ecdh_generic soundcore hid_generic usbhid hid i915 psmouse e1000e ptp pps_core xhci_pci xhci_hcd intel_gtt CPU: 2 PID: 207 Comm: jbd2/nvme0n1p7- Tainted: G U 4.15.0+ #176 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET59W (1.33 ) 12/19/2017 RIP: 0010:nvme_setup_cmd+0x3d3/0x430 RSP: 0018:ffff880423e9f838 EFLAGS: 00010217 RAX: 0000000000000000 RBX: ffff880423e9f8c8 RCX: 0000000000010000 RDX: ffff88022b200010 RSI: 0000000000000002 RDI: 00000000327f0000 RBP: ffff880421251400 R08: ffff88022b200000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000ffff R13: ffff88042341e280 R14: 000000000000ffff R15: ffff880421251440 FS: 0000000000000000(0000) GS:ffff880441500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b684795030 CR3: 0000000002e09006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: nvme_queue_rq+0x40/0xa00 ? __sbitmap_queue_get+0x24/0x90 ? blk_mq_get_tag+0xa3/0x250 ? wait_woken+0x80/0x80 ? blk_mq_get_driver_tag+0x97/0xf0 blk_mq_dispatch_rq_list+0x7b/0x4a0 ? deadline_remove_request+0x49/0xb0 blk_mq_do_dispatch_sched+0x4f/0xc0 blk_mq_sched_dispatch_requests+0x106/0x170 __blk_mq_run_hw_queue+0x53/0xa0 __blk_mq_delay_run_hw_queue+0x83/0xa0 blk_mq_run_hw_queue+0x6c/0xd0 blk_mq_sched_insert_request+0x96/0x140 __blk_mq_try_issue_directly+0x3d/0x190 blk_mq_try_issue_directly+0x30/0x70 blk_mq_make_request+0x1a4/0x6a0 generic_make_request+0xfd/0x2f0 ? submit_bio+0x5c/0x110 submit_bio+0x5c/0x110 ? __blkdev_issue_discard+0x152/0x200 submit_bio_wait+0x43/0x60 ext4_process_freed_data+0x1cd/0x440 ? account_page_dirtied+0xe2/0x1a0 ext4_journal_commit_callback+0x4a/0xc0 jbd2_journal_commit_transaction+0x17e2/0x19e0 ? kjournald2+0xb0/0x250 kjournald2+0xb0/0x250 ? wait_woken+0x80/0x80 ? commit_timeout+0x10/0x10 kthread+0x111/0x130 ? kthread_create_worker_on_cpu+0x50/0x50 ? do_group_exit+0x3a/0xa0 ret_from_fork+0x1f/0x30 Code: 73 89 c1 83 ce 10 c1 e1 10 09 ca 83 f8 04 0f 87 0f ff ff ff 8b 4d 20 48 8b 7d 00 c1 e9 09 48 01 8c c7 00 08 00 00 e9 f8 fe ff ff <0f> ff 4c 89 c7 41 bc 0a 00 00 00 e8 0d 78 d6 ff e9 a1 fc ff ff ---[ end trace 50d361cc444506c8 ]--- print_req_error: I/O error, dev nvme0n1, sector 847167488 Decoding the assembly, the request claims to have 0xffff segments, while nvme counts two. This turns out to be because we don't check for a data carrying request on the mq scheduler path, and since blk_phys_contig_segment() returns true for a non-data request, we decrement the initial segment count of 0 and end up with 0xffff in the unsigned short. There are a few issues here: 1) We should initialize the segment count for a discard to 1. 2) The discard merging is currently using the data limits for segments and sectors. Fix this up by having attempt_merge() correctly identify the request, and by initializing the segment count correctly for discards. This can only be triggered with mq-deadline on discard capable devices right now, which isn't a common configuration. Signed-off-by: Jens Axboe <axboe@kernel.dk>
845 lines
20 KiB
C
845 lines
20 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* 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 <trace/events/block.h>
|
|
|
|
#include "blk.h"
|
|
|
|
static struct bio *blk_bio_discard_split(struct request_queue *q,
|
|
struct bio *bio,
|
|
struct bio_set *bs,
|
|
unsigned *nsegs)
|
|
{
|
|
unsigned int max_discard_sectors, granularity;
|
|
int alignment;
|
|
sector_t tmp;
|
|
unsigned split_sectors;
|
|
|
|
*nsegs = 1;
|
|
|
|
/* Zero-sector (unknown) and one-sector granularities are the same. */
|
|
granularity = max(q->limits.discard_granularity >> 9, 1U);
|
|
|
|
max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
|
|
max_discard_sectors -= max_discard_sectors % granularity;
|
|
|
|
if (unlikely(!max_discard_sectors)) {
|
|
/* XXX: warn */
|
|
return NULL;
|
|
}
|
|
|
|
if (bio_sectors(bio) <= max_discard_sectors)
|
|
return NULL;
|
|
|
|
split_sectors = max_discard_sectors;
|
|
|
|
/*
|
|
* If the next starting sector would be misaligned, stop the discard at
|
|
* the previous aligned sector.
|
|
*/
|
|
alignment = (q->limits.discard_alignment >> 9) % granularity;
|
|
|
|
tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
|
|
tmp = sector_div(tmp, granularity);
|
|
|
|
if (split_sectors > tmp)
|
|
split_sectors -= tmp;
|
|
|
|
return bio_split(bio, split_sectors, GFP_NOIO, bs);
|
|
}
|
|
|
|
static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
|
|
struct bio *bio, struct bio_set *bs, unsigned *nsegs)
|
|
{
|
|
*nsegs = 1;
|
|
|
|
if (!q->limits.max_write_zeroes_sectors)
|
|
return NULL;
|
|
|
|
if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
|
|
return NULL;
|
|
|
|
return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
|
|
}
|
|
|
|
static struct bio *blk_bio_write_same_split(struct request_queue *q,
|
|
struct bio *bio,
|
|
struct bio_set *bs,
|
|
unsigned *nsegs)
|
|
{
|
|
*nsegs = 1;
|
|
|
|
if (!q->limits.max_write_same_sectors)
|
|
return NULL;
|
|
|
|
if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
|
|
return NULL;
|
|
|
|
return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
|
|
}
|
|
|
|
static inline unsigned get_max_io_size(struct request_queue *q,
|
|
struct bio *bio)
|
|
{
|
|
unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
|
|
unsigned mask = queue_logical_block_size(q) - 1;
|
|
|
|
/* aligned to logical block size */
|
|
sectors &= ~(mask >> 9);
|
|
|
|
return sectors;
|
|
}
|
|
|
|
static struct bio *blk_bio_segment_split(struct request_queue *q,
|
|
struct bio *bio,
|
|
struct bio_set *bs,
|
|
unsigned *segs)
|
|
{
|
|
struct bio_vec bv, bvprv, *bvprvp = NULL;
|
|
struct bvec_iter iter;
|
|
unsigned seg_size = 0, nsegs = 0, sectors = 0;
|
|
unsigned front_seg_size = bio->bi_seg_front_size;
|
|
bool do_split = true;
|
|
struct bio *new = NULL;
|
|
const unsigned max_sectors = get_max_io_size(q, bio);
|
|
|
|
bio_for_each_segment(bv, bio, iter) {
|
|
/*
|
|
* If the queue doesn't support SG gaps and adding this
|
|
* offset would create a gap, disallow it.
|
|
*/
|
|
if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
|
|
goto split;
|
|
|
|
if (sectors + (bv.bv_len >> 9) > max_sectors) {
|
|
/*
|
|
* Consider this a new segment if we're splitting in
|
|
* the middle of this vector.
|
|
*/
|
|
if (nsegs < queue_max_segments(q) &&
|
|
sectors < max_sectors) {
|
|
nsegs++;
|
|
sectors = max_sectors;
|
|
}
|
|
goto split;
|
|
}
|
|
|
|
if (bvprvp && blk_queue_cluster(q)) {
|
|
if (seg_size + bv.bv_len > queue_max_segment_size(q))
|
|
goto new_segment;
|
|
if (!BIOVEC_PHYS_MERGEABLE(bvprvp, &bv))
|
|
goto new_segment;
|
|
if (!BIOVEC_SEG_BOUNDARY(q, bvprvp, &bv))
|
|
goto new_segment;
|
|
|
|
seg_size += bv.bv_len;
|
|
bvprv = bv;
|
|
bvprvp = &bvprv;
|
|
sectors += bv.bv_len >> 9;
|
|
|
|
continue;
|
|
}
|
|
new_segment:
|
|
if (nsegs == queue_max_segments(q))
|
|
goto split;
|
|
|
|
if (nsegs == 1 && seg_size > front_seg_size)
|
|
front_seg_size = seg_size;
|
|
|
|
nsegs++;
|
|
bvprv = bv;
|
|
bvprvp = &bvprv;
|
|
seg_size = bv.bv_len;
|
|
sectors += bv.bv_len >> 9;
|
|
|
|
}
|
|
|
|
do_split = false;
|
|
split:
|
|
*segs = nsegs;
|
|
|
|
if (do_split) {
|
|
new = bio_split(bio, sectors, GFP_NOIO, bs);
|
|
if (new)
|
|
bio = new;
|
|
}
|
|
|
|
if (nsegs == 1 && seg_size > front_seg_size)
|
|
front_seg_size = seg_size;
|
|
bio->bi_seg_front_size = front_seg_size;
|
|
if (seg_size > bio->bi_seg_back_size)
|
|
bio->bi_seg_back_size = seg_size;
|
|
|
|
return do_split ? new : NULL;
|
|
}
|
|
|
|
void blk_queue_split(struct request_queue *q, struct bio **bio)
|
|
{
|
|
struct bio *split, *res;
|
|
unsigned nsegs;
|
|
|
|
switch (bio_op(*bio)) {
|
|
case REQ_OP_DISCARD:
|
|
case REQ_OP_SECURE_ERASE:
|
|
split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
|
|
break;
|
|
case REQ_OP_WRITE_ZEROES:
|
|
split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
|
|
break;
|
|
case REQ_OP_WRITE_SAME:
|
|
split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
|
|
break;
|
|
default:
|
|
split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
|
|
break;
|
|
}
|
|
|
|
/* physical segments can be figured out during splitting */
|
|
res = split ? split : *bio;
|
|
res->bi_phys_segments = nsegs;
|
|
bio_set_flag(res, BIO_SEG_VALID);
|
|
|
|
if (split) {
|
|
/* there isn't chance to merge the splitted bio */
|
|
split->bi_opf |= REQ_NOMERGE;
|
|
|
|
bio_chain(split, *bio);
|
|
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
|
|
generic_make_request(*bio);
|
|
*bio = split;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_split);
|
|
|
|
static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
|
|
struct bio *bio,
|
|
bool no_sg_merge)
|
|
{
|
|
struct bio_vec bv, bvprv = { NULL };
|
|
int cluster, prev = 0;
|
|
unsigned int seg_size, nr_phys_segs;
|
|
struct bio *fbio, *bbio;
|
|
struct bvec_iter iter;
|
|
|
|
if (!bio)
|
|
return 0;
|
|
|
|
switch (bio_op(bio)) {
|
|
case REQ_OP_DISCARD:
|
|
case REQ_OP_SECURE_ERASE:
|
|
case REQ_OP_WRITE_ZEROES:
|
|
return 0;
|
|
case REQ_OP_WRITE_SAME:
|
|
return 1;
|
|
}
|
|
|
|
fbio = bio;
|
|
cluster = blk_queue_cluster(q);
|
|
seg_size = 0;
|
|
nr_phys_segs = 0;
|
|
for_each_bio(bio) {
|
|
bio_for_each_segment(bv, bio, iter) {
|
|
/*
|
|
* If SG merging is disabled, each bio vector is
|
|
* a segment
|
|
*/
|
|
if (no_sg_merge)
|
|
goto new_segment;
|
|
|
|
if (prev && cluster) {
|
|
if (seg_size + bv.bv_len
|
|
> queue_max_segment_size(q))
|
|
goto new_segment;
|
|
if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
|
|
goto new_segment;
|
|
if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
|
|
goto new_segment;
|
|
|
|
seg_size += bv.bv_len;
|
|
bvprv = bv;
|
|
continue;
|
|
}
|
|
new_segment:
|
|
if (nr_phys_segs == 1 && seg_size >
|
|
fbio->bi_seg_front_size)
|
|
fbio->bi_seg_front_size = seg_size;
|
|
|
|
nr_phys_segs++;
|
|
bvprv = bv;
|
|
prev = 1;
|
|
seg_size = bv.bv_len;
|
|
}
|
|
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;
|
|
|
|
return nr_phys_segs;
|
|
}
|
|
|
|
void blk_recalc_rq_segments(struct request *rq)
|
|
{
|
|
bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
|
|
&rq->q->queue_flags);
|
|
|
|
rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio,
|
|
no_sg_merge);
|
|
}
|
|
|
|
void blk_recount_segments(struct request_queue *q, struct bio *bio)
|
|
{
|
|
unsigned short seg_cnt;
|
|
|
|
/* estimate segment number by bi_vcnt for non-cloned bio */
|
|
if (bio_flagged(bio, BIO_CLONED))
|
|
seg_cnt = bio_segments(bio);
|
|
else
|
|
seg_cnt = bio->bi_vcnt;
|
|
|
|
if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
|
|
(seg_cnt < queue_max_segments(q)))
|
|
bio->bi_phys_segments = seg_cnt;
|
|
else {
|
|
struct bio *nxt = bio->bi_next;
|
|
|
|
bio->bi_next = NULL;
|
|
bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
|
|
bio->bi_next = nxt;
|
|
}
|
|
|
|
bio_set_flag(bio, BIO_SEG_VALID);
|
|
}
|
|
EXPORT_SYMBOL(blk_recount_segments);
|
|
|
|
static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
|
|
struct bio *nxt)
|
|
{
|
|
struct bio_vec end_bv = { NULL }, nxt_bv;
|
|
|
|
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;
|
|
|
|
bio_get_last_bvec(bio, &end_bv);
|
|
bio_get_first_bvec(nxt, &nxt_bv);
|
|
|
|
if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv))
|
|
return 0;
|
|
|
|
/*
|
|
* bio and nxt are contiguous in memory; check if the queue allows
|
|
* these two to be merged into one
|
|
*/
|
|
if (BIOVEC_SEG_BOUNDARY(q, &end_bv, &nxt_bv))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline 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 (*sg && *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_unmark_end(*sg);
|
|
*sg = sg_next(*sg);
|
|
}
|
|
|
|
sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
|
|
(*nsegs)++;
|
|
}
|
|
*bvprv = *bvec;
|
|
}
|
|
|
|
static inline int __blk_bvec_map_sg(struct request_queue *q, struct bio_vec bv,
|
|
struct scatterlist *sglist, struct scatterlist **sg)
|
|
{
|
|
*sg = sglist;
|
|
sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
|
|
return 1;
|
|
}
|
|
|
|
static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
|
|
struct scatterlist *sglist,
|
|
struct scatterlist **sg)
|
|
{
|
|
struct bio_vec bvec, bvprv = { NULL };
|
|
struct bvec_iter iter;
|
|
int cluster = blk_queue_cluster(q), nsegs = 0;
|
|
|
|
for_each_bio(bio)
|
|
bio_for_each_segment(bvec, bio, iter)
|
|
__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
|
|
&nsegs, &cluster);
|
|
|
|
return nsegs;
|
|
}
|
|
|
|
/*
|
|
* 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 scatterlist *sg = NULL;
|
|
int nsegs = 0;
|
|
|
|
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
|
|
nsegs = __blk_bvec_map_sg(q, rq->special_vec, sglist, &sg);
|
|
else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
|
|
nsegs = __blk_bvec_map_sg(q, bio_iovec(rq->bio), sglist, &sg);
|
|
else if (rq->bio)
|
|
nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
|
|
|
|
if (unlikely(rq->rq_flags & RQF_COPY_USER) &&
|
|
(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 (op_is_write(req_op(rq)))
|
|
memset(q->dma_drain_buffer, 0, q->dma_drain_size);
|
|
|
|
sg_unmark_end(sg);
|
|
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);
|
|
|
|
/*
|
|
* Something must have been wrong if the figured number of
|
|
* segment is bigger than number of req's physical segments
|
|
*/
|
|
WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
|
|
|
|
return nsegs;
|
|
}
|
|
EXPORT_SYMBOL(blk_rq_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 (blk_integrity_merge_bio(q, req, bio) == false)
|
|
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_set_nomerge(q, req);
|
|
return 0;
|
|
}
|
|
|
|
int ll_back_merge_fn(struct request_queue *q, struct request *req,
|
|
struct bio *bio)
|
|
{
|
|
if (req_gap_back_merge(req, bio))
|
|
return 0;
|
|
if (blk_integrity_rq(req) &&
|
|
integrity_req_gap_back_merge(req, bio))
|
|
return 0;
|
|
if (blk_rq_sectors(req) + bio_sectors(bio) >
|
|
blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
|
|
req_set_nomerge(q, req);
|
|
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 (req_gap_front_merge(req, bio))
|
|
return 0;
|
|
if (blk_integrity_rq(req) &&
|
|
integrity_req_gap_front_merge(req, bio))
|
|
return 0;
|
|
if (blk_rq_sectors(req) + bio_sectors(bio) >
|
|
blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
|
|
req_set_nomerge(q, req);
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* blk-mq uses req->special to carry normal driver per-request payload, it
|
|
* does not indicate a prepared command that we cannot merge with.
|
|
*/
|
|
static bool req_no_special_merge(struct request *req)
|
|
{
|
|
struct request_queue *q = req->q;
|
|
|
|
return !q->mq_ops && req->special;
|
|
}
|
|
|
|
static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
|
|
struct request *next)
|
|
{
|
|
unsigned short segments = blk_rq_nr_discard_segments(req);
|
|
|
|
if (segments >= queue_max_discard_segments(q))
|
|
goto no_merge;
|
|
if (blk_rq_sectors(req) + bio_sectors(next->bio) >
|
|
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
|
|
goto no_merge;
|
|
|
|
req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next);
|
|
return true;
|
|
no_merge:
|
|
req_set_nomerge(q, req);
|
|
return false;
|
|
}
|
|
|
|
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_no_special_merge(req) || req_no_special_merge(next))
|
|
return 0;
|
|
|
|
if (req_gap_back_merge(req, next->bio))
|
|
return 0;
|
|
|
|
/*
|
|
* Will it become too large?
|
|
*/
|
|
if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
|
|
blk_rq_get_max_sectors(req, blk_rq_pos(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_merge_rq(q, req, next) == false)
|
|
return 0;
|
|
|
|
/* Merge is OK... */
|
|
req->nr_phys_segments = total_phys_segments;
|
|
return 1;
|
|
}
|
|
|
|
/**
|
|
* 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->rq_flags & RQF_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_opf & REQ_FAILFAST_MASK) &&
|
|
(bio->bi_opf & REQ_FAILFAST_MASK) != ff);
|
|
bio->bi_opf |= ff;
|
|
}
|
|
rq->rq_flags |= RQF_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();
|
|
part = req->part;
|
|
|
|
part_round_stats(req->q, cpu, part);
|
|
part_dec_in_flight(req->q, part, rq_data_dir(req));
|
|
|
|
hd_struct_put(part);
|
|
part_stat_unlock();
|
|
}
|
|
}
|
|
|
|
/*
|
|
* For non-mq, this has to be called with the request spinlock acquired.
|
|
* For mq with scheduling, the appropriate queue wide lock should be held.
|
|
*/
|
|
static struct request *attempt_merge(struct request_queue *q,
|
|
struct request *req, struct request *next)
|
|
{
|
|
if (!q->mq_ops)
|
|
lockdep_assert_held(q->queue_lock);
|
|
|
|
if (!rq_mergeable(req) || !rq_mergeable(next))
|
|
return NULL;
|
|
|
|
if (req_op(req) != req_op(next))
|
|
return NULL;
|
|
|
|
/*
|
|
* not contiguous
|
|
*/
|
|
if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
|
|
return NULL;
|
|
|
|
if (rq_data_dir(req) != rq_data_dir(next)
|
|
|| req->rq_disk != next->rq_disk
|
|
|| req_no_special_merge(next))
|
|
return NULL;
|
|
|
|
if (req_op(req) == REQ_OP_WRITE_SAME &&
|
|
!blk_write_same_mergeable(req->bio, next->bio))
|
|
return NULL;
|
|
|
|
/*
|
|
* Don't allow merge of different write hints, or for a hint with
|
|
* non-hint IO.
|
|
*/
|
|
if (req->write_hint != next->write_hint)
|
|
return NULL;
|
|
|
|
/*
|
|
* 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. Handle DISCARDs separately, as they
|
|
* have separate settings.
|
|
*/
|
|
if (req_op(req) == REQ_OP_DISCARD) {
|
|
if (!req_attempt_discard_merge(q, req, next))
|
|
return NULL;
|
|
} else if (!ll_merge_requests_fn(q, req, next))
|
|
return NULL;
|
|
|
|
/*
|
|
* 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->rq_flags | next->rq_flags) & RQF_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);
|
|
|
|
if (req_op(req) != REQ_OP_DISCARD)
|
|
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;
|
|
|
|
/*
|
|
* ownership of bio passed from next to req, return 'next' for
|
|
* the caller to free
|
|
*/
|
|
next->bio = NULL;
|
|
return next;
|
|
}
|
|
|
|
struct request *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 NULL;
|
|
}
|
|
|
|
struct request *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 NULL;
|
|
}
|
|
|
|
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
|
|
struct request *next)
|
|
{
|
|
struct elevator_queue *e = q->elevator;
|
|
struct request *free;
|
|
|
|
if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
|
|
if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
|
|
return 0;
|
|
|
|
free = attempt_merge(q, rq, next);
|
|
if (free) {
|
|
__blk_put_request(q, free);
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
|
|
{
|
|
if (!rq_mergeable(rq) || !bio_mergeable(bio))
|
|
return false;
|
|
|
|
if (req_op(rq) != bio_op(bio))
|
|
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_disk || req_no_special_merge(rq))
|
|
return false;
|
|
|
|
/* only merge integrity protected bio into ditto rq */
|
|
if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
|
|
return false;
|
|
|
|
/* must be using the same buffer */
|
|
if (req_op(rq) == REQ_OP_WRITE_SAME &&
|
|
!blk_write_same_mergeable(rq->bio, bio))
|
|
return false;
|
|
|
|
/*
|
|
* Don't allow merge of different write hints, or for a hint with
|
|
* non-hint IO.
|
|
*/
|
|
if (rq->write_hint != bio->bi_write_hint)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
|
|
{
|
|
if (req_op(rq) == REQ_OP_DISCARD &&
|
|
queue_max_discard_segments(rq->q) > 1)
|
|
return ELEVATOR_DISCARD_MERGE;
|
|
else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
|
|
return ELEVATOR_BACK_MERGE;
|
|
else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
|
|
return ELEVATOR_FRONT_MERGE;
|
|
return ELEVATOR_NO_MERGE;
|
|
}
|