mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 11:20:49 +07:00
d665e12aa7
Fix a regression introduced when removing bi_phys_segments for Write Zeroes
requests, which need to have a segment count of zero, as they don't have a
payload.
Fixes: 14ccb66b3f
("block: remove the bi_phys_segments field in struct bio")
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
843 lines
21 KiB
C
843 lines
21 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 inline bool bio_will_gap(struct request_queue *q,
|
|
struct request *prev_rq, struct bio *prev, struct bio *next)
|
|
{
|
|
struct bio_vec pb, nb;
|
|
|
|
if (!bio_has_data(prev) || !queue_virt_boundary(q))
|
|
return false;
|
|
|
|
/*
|
|
* Don't merge if the 1st bio starts with non-zero offset, otherwise it
|
|
* is quite difficult to respect the sg gap limit. We work hard to
|
|
* merge a huge number of small single bios in case of mkfs.
|
|
*/
|
|
if (prev_rq)
|
|
bio_get_first_bvec(prev_rq->bio, &pb);
|
|
else
|
|
bio_get_first_bvec(prev, &pb);
|
|
if (pb.bv_offset & queue_virt_boundary(q))
|
|
return true;
|
|
|
|
/*
|
|
* We don't need to worry about the situation that the merged segment
|
|
* ends in unaligned virt boundary:
|
|
*
|
|
* - if 'pb' ends aligned, the merged segment ends aligned
|
|
* - if 'pb' ends unaligned, the next bio must include
|
|
* one single bvec of 'nb', otherwise the 'nb' can't
|
|
* merge with 'pb'
|
|
*/
|
|
bio_get_last_bvec(prev, &pb);
|
|
bio_get_first_bvec(next, &nb);
|
|
if (biovec_phys_mergeable(q, &pb, &nb))
|
|
return false;
|
|
return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
|
|
}
|
|
|
|
static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
|
|
{
|
|
return bio_will_gap(req->q, req, req->biotail, bio);
|
|
}
|
|
|
|
static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
|
|
{
|
|
return bio_will_gap(req->q, NULL, bio, req->bio);
|
|
}
|
|
|
|
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,
|
|
bio_allowed_max_sectors(q));
|
|
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 = 0;
|
|
|
|
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 unsigned get_max_segment_size(struct request_queue *q,
|
|
unsigned offset)
|
|
{
|
|
unsigned long mask = queue_segment_boundary(q);
|
|
|
|
/* default segment boundary mask means no boundary limit */
|
|
if (mask == BLK_SEG_BOUNDARY_MASK)
|
|
return queue_max_segment_size(q);
|
|
|
|
return min_t(unsigned long, mask - (mask & offset) + 1,
|
|
queue_max_segment_size(q));
|
|
}
|
|
|
|
/*
|
|
* Split the bvec @bv into segments, and update all kinds of
|
|
* variables.
|
|
*/
|
|
static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
|
|
unsigned *nsegs, unsigned *sectors, unsigned max_segs)
|
|
{
|
|
unsigned len = bv->bv_len;
|
|
unsigned total_len = 0;
|
|
unsigned new_nsegs = 0, seg_size = 0;
|
|
|
|
/*
|
|
* Multi-page bvec may be too big to hold in one segment, so the
|
|
* current bvec has to be splitted as multiple segments.
|
|
*/
|
|
while (len && new_nsegs + *nsegs < max_segs) {
|
|
seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
|
|
seg_size = min(seg_size, len);
|
|
|
|
new_nsegs++;
|
|
total_len += seg_size;
|
|
len -= seg_size;
|
|
|
|
if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
|
|
break;
|
|
}
|
|
|
|
if (new_nsegs) {
|
|
*nsegs += new_nsegs;
|
|
if (sectors)
|
|
*sectors += total_len >> 9;
|
|
}
|
|
|
|
/* split in the middle of the bvec if len != 0 */
|
|
return !!len;
|
|
}
|
|
|
|
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 nsegs = 0, sectors = 0;
|
|
const unsigned max_sectors = get_max_io_size(q, bio);
|
|
const unsigned max_segs = queue_max_segments(q);
|
|
|
|
bio_for_each_bvec(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 < max_segs &&
|
|
sectors < max_sectors) {
|
|
/* split in the middle of bvec */
|
|
bv.bv_len = (max_sectors - sectors) << 9;
|
|
bvec_split_segs(q, &bv, &nsegs,
|
|
§ors, max_segs);
|
|
}
|
|
goto split;
|
|
}
|
|
|
|
if (nsegs == max_segs)
|
|
goto split;
|
|
|
|
bvprv = bv;
|
|
bvprvp = &bvprv;
|
|
|
|
if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
|
|
nsegs++;
|
|
sectors += bv.bv_len >> 9;
|
|
} else if (bvec_split_segs(q, &bv, &nsegs, §ors,
|
|
max_segs)) {
|
|
goto split;
|
|
}
|
|
}
|
|
|
|
*segs = nsegs;
|
|
return NULL;
|
|
split:
|
|
*segs = nsegs;
|
|
return bio_split(bio, sectors, GFP_NOIO, bs);
|
|
}
|
|
|
|
void __blk_queue_split(struct request_queue *q, struct bio **bio,
|
|
unsigned int *nr_segs)
|
|
{
|
|
struct bio *split;
|
|
|
|
switch (bio_op(*bio)) {
|
|
case REQ_OP_DISCARD:
|
|
case REQ_OP_SECURE_ERASE:
|
|
split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs);
|
|
break;
|
|
case REQ_OP_WRITE_ZEROES:
|
|
split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split,
|
|
nr_segs);
|
|
break;
|
|
case REQ_OP_WRITE_SAME:
|
|
split = blk_bio_write_same_split(q, *bio, &q->bio_split,
|
|
nr_segs);
|
|
break;
|
|
default:
|
|
split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
|
|
break;
|
|
}
|
|
|
|
if (split) {
|
|
/* there isn't chance to merge the splitted bio */
|
|
split->bi_opf |= REQ_NOMERGE;
|
|
|
|
/*
|
|
* Since we're recursing into make_request here, ensure
|
|
* that we mark this bio as already having entered the queue.
|
|
* If not, and the queue is going away, we can get stuck
|
|
* forever on waiting for the queue reference to drop. But
|
|
* that will never happen, as we're already holding a
|
|
* reference to it.
|
|
*/
|
|
bio_set_flag(*bio, BIO_QUEUE_ENTERED);
|
|
|
|
bio_chain(split, *bio);
|
|
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
|
|
generic_make_request(*bio);
|
|
*bio = split;
|
|
}
|
|
}
|
|
|
|
void blk_queue_split(struct request_queue *q, struct bio **bio)
|
|
{
|
|
unsigned int nr_segs;
|
|
|
|
__blk_queue_split(q, bio, &nr_segs);
|
|
}
|
|
EXPORT_SYMBOL(blk_queue_split);
|
|
|
|
unsigned int blk_recalc_rq_segments(struct request *rq)
|
|
{
|
|
unsigned int nr_phys_segs = 0;
|
|
struct req_iterator iter;
|
|
struct bio_vec bv;
|
|
|
|
if (!rq->bio)
|
|
return 0;
|
|
|
|
switch (bio_op(rq->bio)) {
|
|
case REQ_OP_DISCARD:
|
|
case REQ_OP_SECURE_ERASE:
|
|
case REQ_OP_WRITE_ZEROES:
|
|
return 0;
|
|
case REQ_OP_WRITE_SAME:
|
|
return 1;
|
|
}
|
|
|
|
rq_for_each_bvec(bv, rq, iter)
|
|
bvec_split_segs(rq->q, &bv, &nr_phys_segs, NULL, UINT_MAX);
|
|
return nr_phys_segs;
|
|
}
|
|
|
|
static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
|
|
struct scatterlist *sglist)
|
|
{
|
|
if (!*sg)
|
|
return sglist;
|
|
|
|
/*
|
|
* 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);
|
|
return sg_next(*sg);
|
|
}
|
|
|
|
static unsigned blk_bvec_map_sg(struct request_queue *q,
|
|
struct bio_vec *bvec, struct scatterlist *sglist,
|
|
struct scatterlist **sg)
|
|
{
|
|
unsigned nbytes = bvec->bv_len;
|
|
unsigned nsegs = 0, total = 0;
|
|
|
|
while (nbytes > 0) {
|
|
unsigned offset = bvec->bv_offset + total;
|
|
unsigned len = min(get_max_segment_size(q, offset), nbytes);
|
|
struct page *page = bvec->bv_page;
|
|
|
|
/*
|
|
* Unfortunately a fair number of drivers barf on scatterlists
|
|
* that have an offset larger than PAGE_SIZE, despite other
|
|
* subsystems dealing with that invariant just fine. For now
|
|
* stick to the legacy format where we never present those from
|
|
* the block layer, but the code below should be removed once
|
|
* these offenders (mostly MMC/SD drivers) are fixed.
|
|
*/
|
|
page += (offset >> PAGE_SHIFT);
|
|
offset &= ~PAGE_MASK;
|
|
|
|
*sg = blk_next_sg(sg, sglist);
|
|
sg_set_page(*sg, page, len, offset);
|
|
|
|
total += len;
|
|
nbytes -= len;
|
|
nsegs++;
|
|
}
|
|
|
|
return nsegs;
|
|
}
|
|
|
|
static inline int __blk_bvec_map_sg(struct bio_vec bv,
|
|
struct scatterlist *sglist, struct scatterlist **sg)
|
|
{
|
|
*sg = blk_next_sg(sg, sglist);
|
|
sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
|
|
return 1;
|
|
}
|
|
|
|
/* only try to merge bvecs into one sg if they are from two bios */
|
|
static inline bool
|
|
__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
|
|
struct bio_vec *bvprv, struct scatterlist **sg)
|
|
{
|
|
|
|
int nbytes = bvec->bv_len;
|
|
|
|
if (!*sg)
|
|
return false;
|
|
|
|
if ((*sg)->length + nbytes > queue_max_segment_size(q))
|
|
return false;
|
|
|
|
if (!biovec_phys_mergeable(q, bvprv, bvec))
|
|
return false;
|
|
|
|
(*sg)->length += nbytes;
|
|
|
|
return true;
|
|
}
|
|
|
|
static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
|
|
struct scatterlist *sglist,
|
|
struct scatterlist **sg)
|
|
{
|
|
struct bio_vec uninitialized_var(bvec), bvprv = { NULL };
|
|
struct bvec_iter iter;
|
|
int nsegs = 0;
|
|
bool new_bio = false;
|
|
|
|
for_each_bio(bio) {
|
|
bio_for_each_bvec(bvec, bio, iter) {
|
|
/*
|
|
* Only try to merge bvecs from two bios given we
|
|
* have done bio internal merge when adding pages
|
|
* to bio
|
|
*/
|
|
if (new_bio &&
|
|
__blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
|
|
goto next_bvec;
|
|
|
|
if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
|
|
nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
|
|
else
|
|
nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
|
|
next_bvec:
|
|
new_bio = false;
|
|
}
|
|
if (likely(bio->bi_iter.bi_size)) {
|
|
bvprv = bvec;
|
|
new_bio = true;
|
|
}
|
|
}
|
|
|
|
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(rq->special_vec, sglist, &sg);
|
|
else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
|
|
nsegs = __blk_bvec_map_sg(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 *req, struct bio *bio,
|
|
unsigned int nr_phys_segs)
|
|
{
|
|
if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(req->q))
|
|
goto no_merge;
|
|
|
|
if (blk_integrity_merge_bio(req->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(req->q, req);
|
|
return 0;
|
|
}
|
|
|
|
int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
|
|
{
|
|
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(req->q, req);
|
|
return 0;
|
|
}
|
|
|
|
return ll_new_hw_segment(req, bio, nr_segs);
|
|
}
|
|
|
|
int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
|
|
{
|
|
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(req->q, req);
|
|
return 0;
|
|
}
|
|
|
|
return ll_new_hw_segment(req, bio, nr_segs);
|
|
}
|
|
|
|
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;
|
|
|
|
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 (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;
|
|
|
|
part_stat_lock();
|
|
part = req->part;
|
|
|
|
part_dec_in_flight(req->q, part, rq_data_dir(req));
|
|
|
|
hd_struct_put(part);
|
|
part_stat_unlock();
|
|
}
|
|
}
|
|
/*
|
|
* Two cases of handling DISCARD merge:
|
|
* If max_discard_segments > 1, the driver takes every bio
|
|
* as a range and send them to controller together. The ranges
|
|
* needn't to be contiguous.
|
|
* Otherwise, the bios/requests will be handled as same as
|
|
* others which should be contiguous.
|
|
*/
|
|
static inline bool blk_discard_mergable(struct request *req)
|
|
{
|
|
if (req_op(req) == REQ_OP_DISCARD &&
|
|
queue_max_discard_segments(req->q) > 1)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
static enum elv_merge blk_try_req_merge(struct request *req,
|
|
struct request *next)
|
|
{
|
|
if (blk_discard_mergable(req))
|
|
return ELEVATOR_DISCARD_MERGE;
|
|
else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next))
|
|
return ELEVATOR_BACK_MERGE;
|
|
|
|
return ELEVATOR_NO_MERGE;
|
|
}
|
|
|
|
/*
|
|
* 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 (!rq_mergeable(req) || !rq_mergeable(next))
|
|
return NULL;
|
|
|
|
if (req_op(req) != req_op(next))
|
|
return NULL;
|
|
|
|
if (rq_data_dir(req) != rq_data_dir(next)
|
|
|| req->rq_disk != next->rq_disk)
|
|
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 (req->ioprio != next->ioprio)
|
|
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.
|
|
*/
|
|
|
|
switch (blk_try_req_merge(req, next)) {
|
|
case ELEVATOR_DISCARD_MERGE:
|
|
if (!req_attempt_discard_merge(q, req, next))
|
|
return NULL;
|
|
break;
|
|
case ELEVATOR_BACK_MERGE:
|
|
if (!ll_merge_requests_fn(q, req, next))
|
|
return NULL;
|
|
break;
|
|
default:
|
|
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_ns of the merged requests to be the
|
|
* current request for accounting purposes.
|
|
*/
|
|
if (next->start_time_ns < req->start_time_ns)
|
|
req->start_time_ns = next->start_time_ns;
|
|
|
|
req->biotail->bi_next = next->bio;
|
|
req->biotail = next->biotail;
|
|
|
|
req->__data_len += blk_rq_bytes(next);
|
|
|
|
if (!blk_discard_mergable(req))
|
|
elv_merge_requests(q, req, next);
|
|
|
|
/*
|
|
* 'next' is going away, so update stats accordingly
|
|
*/
|
|
blk_account_io_merge(next);
|
|
|
|
/*
|
|
* 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 request *free;
|
|
|
|
free = attempt_merge(q, rq, next);
|
|
if (free) {
|
|
blk_put_request(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 */
|
|
if (rq->rq_disk != bio->bi_disk)
|
|
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;
|
|
|
|
if (rq->ioprio != bio_prio(bio))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
|
|
{
|
|
if (blk_discard_mergable(rq))
|
|
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;
|
|
}
|