[PATCH 1/6] block: make bdev_ops->rw_page() take a REQ_OP instead of bool

From: Tejun Heo
Date: Wed Jul 18 2018 - 07:47:53 EST

Next message: Tejun Heo: "[PATCH 2/6] block: Add part_stat_read_accum to read across field entries."
Previous message: Tejun Heo: "[PATCHSET v3] block: Separating discards from writes in Linux IO statistics"
In reply to: Tejun Heo: "[PATCHSET v3] block: Separating discards from writes in Linux IO statistics"
Next in thread: Tejun Heo: "[PATCH 2/6] block: Add part_stat_read_accum to read across field entries."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

c11f0c0b5bb9 ("block/mm: make bdev_ops->rw_page() take a bool for
read/write") replaced @op with boolean @is_write, which limited the
amount of information going into ->rw_page() and more importantly
page_endio(), which removed the need to expose block internals to mm.

Unfortunately, we want to track discards separately and @is_write
isn't enough information. This patch updates bdev_ops->rw_page() to
take REQ_OP instead but leaves page_endio() to take bool @is_write.
This allows the block part of operations to have enough information
while not leaking it to mm.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Mike Christie <mchristi@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
---
drivers/block/brd.c | 14 +++++++-------
drivers/block/zram/zram_drv.c | 16 ++++++++--------
drivers/nvdimm/btt.c | 12 ++++++------
drivers/nvdimm/pmem.c | 13 ++++++-------
fs/block_dev.c | 6 ++++--
fs/mpage.c | 4 ++--
include/linux/blkdev.h | 2 +-
7 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
* Process a single bvec of a bio.
*/
static int brd_do_bvec(struct brd_device *brd, struct page *page,
- unsigned int len, unsigned int off, bool is_write,
+ unsigned int len, unsigned int off, unsigned int op,
sector_t sector)
{
void *mem;
int err = 0;

- if (is_write) {
+ if (op_is_write(op)) {
err = copy_to_brd_setup(brd, sector, len);
if (err)
goto out;
}

mem = kmap_atomic(page);
- if (!is_write) {
+ if (!op_is_write(op)) {
copy_from_brd(mem + off, brd, sector, len);
flush_dcache_page(page);
} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
int err;

err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
- op_is_write(bio_op(bio)), sector);
+ bio_op(bio), sector);
if (err)
goto io_error;
sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
}

static int brd_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
struct brd_device *brd = bdev->bd_disk->private_data;
int err;

if (PageTransHuge(page))
return -ENOTSUPP;
- err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
- page_endio(page, is_write, err);
+ err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+ page_endio(page, op_is_write(op), err);
return err;
}

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7436b2d27fa3..78c29044684a 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1274,17 +1274,17 @@ static void zram_bio_discard(struct zram *zram, u32 index,
* Returns 1 if IO request was successfully submitted.
*/
static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, bool is_write, struct bio *bio)
+ int offset, unsigned int op, struct bio *bio)
{
unsigned long start_time = jiffies;
- int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
+ int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ;
struct request_queue *q = zram->disk->queue;
int ret;

generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
&zram->disk->part0);

- if (!is_write) {
+ if (!op_is_write(op)) {
atomic64_inc(&zram->stats.num_reads);
ret = zram_bvec_read(zram, bvec, index, offset, bio);
flush_dcache_page(bvec->bv_page);
@@ -1300,7 +1300,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
zram_slot_unlock(zram, index);

if (unlikely(ret < 0)) {
- if (!is_write)
+ if (!op_is_write(op))
atomic64_inc(&zram->stats.failed_reads);
else
atomic64_inc(&zram->stats.failed_writes);
@@ -1338,7 +1338,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
unwritten);
if (zram_bvec_rw(zram, &bv, index, offset,
- op_is_write(bio_op(bio)), bio) < 0)
+ bio_op(bio), bio) < 0)
goto out;

bv.bv_offset += bv.bv_len;
@@ -1390,7 +1390,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
}

static int zram_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
int offset, ret;
u32 index;
@@ -1414,7 +1414,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
bv.bv_len = PAGE_SIZE;
bv.bv_offset = 0;

- ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+ ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
out:
/*
* If I/O fails, just return error(ie, non-zero) without
@@ -1429,7 +1429,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,

switch (ret) {
case 0:
- page_endio(page, is_write, 0);
+ page_endio(page, op_is_write(op), 0);
break;
case 1:
ret = 0;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,

static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
struct page *page, unsigned int len, unsigned int off,
- bool is_write, sector_t sector)
+ unsigned int op, sector_t sector)
{
int ret;

- if (!is_write) {
+ if (!op_is_write(op)) {
ret = btt_read_pg(btt, bip, page, off, sector, len);
flush_dcache_page(page);
} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
}

err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
- op_is_write(bio_op(bio)), iter.bi_sector);
+ bio_op(bio), iter.bi_sector);
if (err) {
dev_err(&btt->nd_btt->dev,
"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
}

static int btt_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
struct btt *btt = bdev->bd_disk->private_data;
int rc;
unsigned int len;

len = hpage_nr_pages(page) * PAGE_SIZE;
- rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+ rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
if (rc == 0)
- page_endio(page, is_write, 0);
+ page_endio(page, op_is_write(op), 0);

return rc;
}
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
}

static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
- unsigned int len, unsigned int off, bool is_write,
+ unsigned int len, unsigned int off, unsigned int op,
sector_t sector)
{
blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
bad_pmem = true;

- if (!is_write) {
+ if (!op_is_write(op)) {
if (unlikely(bad_pmem))
rc = BLK_STS_IOERR;
else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
do_acct = nd_iostat_start(bio, &start);
bio_for_each_segment(bvec, bio, iter) {
rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
- bvec.bv_offset, op_is_write(bio_op(bio)),
- iter.bi_sector);
+ bvec.bv_offset, bio_op(bio), iter.bi_sector);
if (rc) {
bio->bi_status = rc;
break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
}

static int pmem_rw_page(struct block_device *bdev, sector_t sector,
- struct page *page, bool is_write)
+ struct page *page, unsigned int op)
{
struct pmem_device *pmem = bdev->bd_queue->queuedata;
blk_status_t rc;

rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
- 0, is_write, sector);
+ 0, op, sector);

/*
* The ->rw_page interface is subtle and tricky. The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
* caused by double completion.
*/
if (rc == 0)
- page_endio(page, is_write, 0);
+ page_endio(page, op_is_write(op), 0);

return blk_status_to_errno(rc);
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0dd87aaeb39a..496fb51a1e1a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -665,7 +665,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
result = blk_queue_enter(bdev->bd_queue, 0);
if (result)
return result;
- result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+ REQ_OP_READ);
blk_queue_exit(bdev->bd_queue);
return result;
}
@@ -703,7 +704,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
return result;

set_page_writeback(page);
- result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+ REQ_OP_WRITE);
if (result) {
end_page_writeback(page);
} else {
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f570733a..b73638db9866 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio)

bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
- page_endio(page, op_is_write(bio_op(bio)),
- blk_status_to_errno(bio->bi_status));
+ page_endio(page, bio_op(bio),
+ blk_status_to_errno(bio->bi_status));
}

bio_put(bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1939ed95f936..331a6cb8805f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1943,7 +1943,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
struct block_device_operations {
int (*open) (struct block_device *, fmode_t);
void (*release) (struct gendisk *, fmode_t);
- int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+ int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
unsigned int (*check_events) (struct gendisk *disk,
--
2.17.1

Next message: Tejun Heo: "[PATCH 2/6] block: Add part_stat_read_accum to read across field entries."
Previous message: Tejun Heo: "[PATCHSET v3] block: Separating discards from writes in Linux IO statistics"
In reply to: Tejun Heo: "[PATCHSET v3] block: Separating discards from writes in Linux IO statistics"
Next in thread: Tejun Heo: "[PATCH 2/6] block: Add part_stat_read_accum to read across field entries."
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]