implement async block discards and other ops via io_uring
Subsystems (4)
v5 cover implement async block discards and other ops via io_uring
There is an interest in having asynchronous block operations like discard and write zeroes. The series implements that as io_uring commands, which is an io_uring request type allowing to implement custom file specific operations.
First 4 are preparation patches. Patch 5 introduces the main chunk of cmd infrastructure and discard commands. Patches 6-8 implement write zeroes variants.
Branch with tests and docs:
https://github.com/isilence/liburing.git discard-cmd
The man page specifically (need to shuffle it to some cmd section):
https://github.com/isilence/liburing/commit/a6fa2bc2400bf7fcb80496e322b5db4c8b3191f0
v5: add uapi/linux/blkdev.h
number block cmd opcodes starting from IOC seq 0
don't export bio_discard_limit(), return to v2 and put bio if nowait
can't proceed
minor comment and stylistics changes
v4: fix failing to pass nowait (unused opf) in patch 7
v3: use GFP_NOWAIT for non-blocking allocation
fail oversized nowait discards in advance drop secure erase and add zero page writes renamed function name + other cosmetic changes use IOC / ioctl encoding for cmd opcodes
v2: move out of CONFIG_COMPAT
add write zeroes & secure erase
drop a note about interaction with page cache
Pavel Begunkov (8):
io_uring/cmd: expose iowq to cmds io_uring/cmd: give inline space in request to cmds
filemap: introduce filemap_invalidate_pages
block: introduce blk_validate_byte_range()
block: implement async io_uring discard cmd
block: implement write zeroes io_uring cmd
block: add nowait flag for __blkdev_issue_zero_pages
block: implement write zero pages cmd
block/blk-lib.c | 22 +++- block/blk.h | 1 + block/fops.c | 2 + block/ioctl.c | 242 ++++++++++++++++++++++++++++++++--- include/linux/bio.h | 4 + include/linux/blkdev.h | 1 + include/linux/io_uring/cmd.h | 15 +++ include/linux/pagemap.h | 2 + include/uapi/linux/blkdev.h | 16 +++ io_uring/io_uring.c | 11 ++ io_uring/io_uring.h | 1 + io_uring/uring_cmd.c | 7 + mm/filemap.c | 17 ++- 13 files changed, 314 insertions(+), 27 deletions(-) create mode 100644 include/uapi/linux/blkdev.h
Signature · 1 line
2.45.2
PATCH v5 1/8 io_uring/cmd: expose iowq to cmds
When an io_uring request needs blocking context we offload it to the io_uring's thread pool called io-wq. We can get there off ->uring_cmd by returning -EAGAIN, but there is no straightforward way of doing that from an asynchronous callback. Add a helper that would transfer a command to a blocking context.
Note, we do an extra hop via task_work before io_queue_iowq(), that's a limitation of io_uring infra we have that can likely be lifted later if that would ever become a problem.
--- include/linux/io_uring/cmd.h | 6 ++++++ io_uring/io_uring.c | 11 +++++++++++ io_uring/io_uring.h | 1 + io_uring/uring_cmd.c | 7 +++++++ 4 files changed, 25 insertions(+)
include/linux/io_uring/cmd.h +6 -0
@@ -48,6 +48,9 @@ void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,void io_uring_cmd_mark_cancelable (struct io_uring_cmd *cmd,unsigned int issue_flags); +/* Execute the request from a blocking context */ +void io_uring_cmd_issue_blocking (struct io_uring_cmd *ioucmd); +#else static inline int io_uring_cmd_import_fixed (u64 ubuf,unsigned long len,int rw,struct iov_iter *iter,void *ioucmd)
@@ -67,6 +70,9 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags) { } +static inline void io_uring_cmd_issue_blocking (struct io_uring_cmd *ioucmd) +{ +}#endif /*
io_uring/io_uring.c +11 -0
@@ -533,6 +533,17 @@ static void io_queue_iowq(struct io_kiocb *req)io_queue_linked_timeout (link); } +static void io_req_queue_iowq_tw (struct io_kiocb *req,struct io_tw_state *ts) +{ +io_queue_iowq (req); +} + +void io_req_queue_iowq (struct io_kiocb *req) +{ + req->io_task_work.func = io_req_queue_iowq_tw; +io_req_task_work_add (req); +} +static __cold void io_queue_deferred (struct io_ring_ctx *ctx) {while (!list_empty (&ctx->defer_list)) {
io_uring/io_uring.h +1 -0
@@ -94,6 +94,7 @@ int io_uring_alloc_task_context(struct task_struct *task,int io_ring_add_registered_file (struct io_uring_task *tctx,struct file *file,int start,int end); +void io_req_queue_iowq (struct io_kiocb *req);int io_poll_issue (struct io_kiocb *req,struct io_tw_state *ts);int io_submit_sqes (struct io_ring_ctx *ctx,unsigned int nr);
io_uring/uring_cmd.c +7 -0
@@ -277,6 +277,13 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, }EXPORT_SYMBOL_GPL (io_uring_cmd_import_fixed); +void io_uring_cmd_issue_blocking (struct io_uring_cmd *ioucmd) +{ +struct io_kiocb *req =cmd_to_io_kiocb (ioucmd); + +io_req_queue_iowq (req); +} +static inline int io_uring_cmd_getsockopt (struct socket *sock,struct io_uring_cmd *cmd,unsigned int issue_flags)
Signature · 1 line
2.45.2
PATCH v5 2/8 io_uring/cmd: give inline space in request to cmds
In reply to Pavel BegunkovSome io_uring commands can use some inline space in io_kiocb. We have 32 bytes in struct io_uring_cmd, expose it.
--- include/linux/io_uring/cmd.h | 9 +++++++++ 1 file changed, 9 insertions(+)
include/linux/io_uring/cmd.h +9 -0
@@ -23,6 +23,15 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)return sqe->cmd; } +static inline void io_uring_cmd_private_sz_check (size_t cmd_sz) +{ + BUILD_BUG_ON(cmd_sz > sizeof_field(struct io_uring_cmd, pdu)); +} +#define io_uring_cmd_to_pdu (cmd, pdu_type) ( \ + io_uring_cmd_private_sz_check(sizeof(pdu_type)), \ + ((pdu_type *)&(cmd)->pdu) \ +) +#if defined(CONFIG_IO_URING )int io_uring_cmd_import_fixed (u64 ubuf,unsigned long len,int rw,struct iov_iter *iter,void *ioucmd);
Signature · 1 line
2.45.2
PATCH v5 3/8 filemap: introduce filemap_invalidate_pages
In reply to Pavel Begunkovkiocb_invalidate_pages() is useful for the write path, however not everything is backed by kiocb and we want to reuse the function for bio based discard implementation. Extract and and reuse a new helper called filemap_invalidate_pages(), which takes a argument indicating whether it should be non-blocking and might return -EAGAIN.
--- include/linux/pagemap.h | 2 ++ mm/filemap.c | 17 ++++++++++++----- 2 files changed, 14 insertions(+), 5 deletions(-)
include/linux/pagemap.h +2 -0
@@ -32,6 +32,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end);int kiocb_invalidate_pages (struct kiocb *iocb,size_t count);void kiocb_invalidate_post_direct_write (struct kiocb *iocb,size_t count); +int filemap_invalidate_pages (struct address_space *mapping, +loff_t pos,loff_t end,bool nowait);int write_inode_now (struct inode *,int sync);int filemap_fdatawrite (struct address_space *);
mm/filemap.c +12 -5
@@ -2712,14 +2712,12 @@ int kiocb_write_and_wait(struct kiocb *iocb, size_t count) }EXPORT_SYMBOL_GPL (kiocb_write_and_wait); -int kiocb_invalidate_pages (struct kiocb *iocb,size_t count) +int filemap_invalidate_pages (struct address_space *mapping, +loff_t pos,loff_t end,bool nowait) { -struct address_space *mapping = iocb->ki_filp->f_mapping; -loff_t pos = iocb->ki_pos; -loff_t end = pos + count -1 ;int ret; -if (iocb->ki_flags &IOCB_NOWAIT ) { +if (nowait) {/* we could block if there are any pages in the range */ if (filemap_range_has_page (mapping, pos, end))return -EAGAIN ;
@@ -2738,6 +2736,15 @@ int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)return invalidate_inode_pages2_range (mapping, pos >>PAGE_SHIFT , end >>PAGE_SHIFT ); } + +int kiocb_invalidate_pages (struct kiocb *iocb,size_t count) +{ +struct address_space *mapping = iocb->ki_filp->f_mapping; + +return filemap_invalidate_pages (mapping, iocb->ki_pos, + iocb->ki_pos + count -1 , + iocb->ki_flags &IOCB_NOWAIT ); +}EXPORT_SYMBOL_GPL (kiocb_invalidate_pages);/**
Signature · 1 line
2.45.2
PATCH v5 4/8 block: introduce blk_validate_byte_range()
In reply to Pavel BegunkovIn preparation to further changes extract a helper function out of blk_ioctl_discard() that validates if we can do IO against the given range of disk byte addresses.
--- block/ioctl.c | 49 +++++++++++++++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 18 deletions(-)
block/ioctl.c +31 -18
@@ -92,38 +92,51 @@ static int compat_blkpg_ioctl(struct block_device *bdev, }#endif +/* +* Check that [start, start + len) is a valid range from the block device's +* perspective, including verifying that it can be correctly translated into +* logical block addresses. +*/ +static int blk_validate_byte_range (struct block_device *bdev, +uint64_t start,uint64_t len) +{ +unsigned int bs_mask =bdev_logical_block_size (bdev) -1 ; +uint64_t end; + +if ((start | len) & bs_mask) +return -EINVAL ; +if (!len) +return -EINVAL ; +if (check_add_overflow (start, len, &end) || end >bdev_nr_bytes (bdev)) +return -EINVAL ; + +return 0 ; +} +static int blk_ioctl_discard (struct block_device *bdev,blk_mode_t mode,unsigned long arg) { -unsigned int bs_mask =bdev_logical_block_size (bdev) -1 ; -uint64_t range[2 ], start, len, end; +uint64_t range[2 ], start, len;struct bio *prev =NULL , *bio;sector_t sector, nr_sects;struct blk_plug plug;int err; -if (!(mode &BLK_OPEN_WRITE )) -return -EBADF ; - -if (!bdev_max_discard_sectors (bdev)) -return -EOPNOTSUPP ; -if (bdev_read_only (bdev)) -return -EPERM ; -if (copy_from_user (range, (void __user *)arg,sizeof (range)))return -EFAULT ; - start = range[0 ]; len = range[1 ]; -if (!len) -return -EINVAL ; -if ((start | len) & bs_mask) -return -EINVAL ; +if (!bdev_max_discard_sectors (bdev)) +return -EOPNOTSUPP ; -if (check_add_overflow (start, len, &end) || - end >bdev_nr_bytes (bdev)) -return -EINVAL ; +if (!(mode &BLK_OPEN_WRITE )) +return -EBADF ; +if (bdev_read_only (bdev)) +return -EPERM ; + err =blk_validate_byte_range (bdev, start, len); +if (err) +return err;filemap_invalidate_lock (bdev->bd_mapping); err =truncate_bdev_range (bdev, mode, start, start + len -1 );
Signature · 1 line
2.45.2
Re: [PATCH v5 4/8] block: introduce blk_validate_byte_range()
Looks good:
PATCH v5 5/8 block: implement async io_uring discard cmd
In reply to Pavel Begunkovio_uring allows implementing custom file specific asynchronous operations via the fops->uring_cmd callback, a.k.a. IORING_OP_URING_CMD requests or just io_uring commands. Use it to add support for async discards.
Normally, it first tries to queue up bios in a non-blocking context, and if that fails, we'd retry from a blocking context by returning -EAGAIN to the core io_uring. We always get the result from bios asynchronously by setting a custom bi_end_io callback, at which point we drag the request into the task context to either reissue or complete it and post a completion to the user.
Unlike ioctl(BLKDISCARD) with stronger guarantees against races, we only do a best effort attempt to invalidate page cache, and it can race with any writes and reads and leave page cache stale. It's the same kind of races we allow to direct writes.
Also, apart from cases where discarding is not allowed at all, e.g. discards are not supported or the file/device is read only, the user should assume that the sector range on disk is not valid anymore, even when an error was returned to the user.
--- block/blk.h | 1 + block/fops.c | 2 + block/ioctl.c | 112 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/blkdev.h | 14 +++++ 4 files changed, 129 insertions(+) create mode 100644 include/uapi/linux/blkdev.h
block/blk.h +1 -0
@@ -605,6 +605,7 @@ blk_mode_t file_to_blk_mode(struct file *file);int truncate_bdev_range (struct block_device *bdev,blk_mode_t mode,loff_t lstart,loff_t lend);long blkdev_ioctl (struct file *file,unsigned cmd,unsigned long arg); +int blkdev_uring_cmd (struct io_uring_cmd *cmd,unsigned int issue_flags);long compat_blkdev_ioctl (struct file *file,unsigned cmd,unsigned long arg);extern const struct address_space_operations def_blk_aops;
block/fops.c +2 -0
@@ -17,6 +17,7 @@#include <linux/fs.h> #include <linux/iomap.h> #include <linux/module.h> +#include <linux/io_uring/cmd.h> #include "blk.h" static inline struct inode *bdev_file_inode (struct file *file)
@@ -873,6 +874,7 @@ const struct file_operations def_blk_fops = { .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = blkdev_fallocate, + .uring_cmd = blkdev_uring_cmd, .fop_flags = FOP_BUFFER_RASYNC, };
block/ioctl.c +112 -0
121 lines not on this page · raw message
include/uapi/linux/blkdev.h new file +14 -0
@@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_BLKDEV_H +#define _UAPI_LINUX_BLKDEV_H + +#include <linux/ioctl.h> +#include <linux/types.h> + +/* +* io_uring block file commands, see IORING_OP_URING_CMD. +* It's a different number space from ioctl(), reuse the block's code 0x12. +*/ +#define BLOCK_URING_CMD_DISCARD _IO(0x12, 0) + +#endif
Signature · 1 line
2.45.2
Re: [PATCH v5 5/8] block: implement async io_uring discard cmd
Quoted 4 lines
+ *
io_uringblock file commands, seeIORING_OP_URING_CMD.
+ * It's a different number space fromioctl(), reuse the block's code0x12.
+ */
+#defineBLOCK_URING_CMD_DISCARD_IO(0x12, 0)
Please just start out at some arbitrary boundary, but don't reuse the ioctl code from an ioctl that does something vaguely similar for no good reason.
The rest looks good.
Re: [PATCH v5 5/8] block: implement async io_uring discard cmd
Quoted 8 lines · Christoph Hellwig
Quoted 4 lines
+ *
io_uringblock file commands, seeIORING_OP_URING_CMD.
+ * It's a different number space fromioctl(), reuse the block's code0x12.
+ */
+#defineBLOCK_URING_CMD_DISCARD_IO(0x12, 0)Please just start out at some arbitrary boundary, but don't reuse the ioctl code from an ioctl that does something vaguely similar for no good reason.
It's a entirely different number space, it shouldn't care about ioctl numbering. Regardless, BLK* in fs.h start with 93. I don't even have a clue where is the rest.
Code Seq# Include File Comments 0x12 all linux/fs.h BLK* ioctls
linux/blkpg.h
Signature · 1 line
Pavel Begunkov
PATCH v5 6/8 block: implement write zeroes io_uring cmd
In reply to Pavel BegunkovAdd a second io_uring cmd for block layer implementing asynchronous write zeroes. It reuses helpers we've added for async discards, and inherits the code structure as well as all considerations in regards to page cache races. It has to be supported by underlying hardware to be used, otherwise the request will fail. A fallback version is implemented separately in a later patch.
--- block/ioctl.c | 66 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/blkdev.h | 1 + 2 files changed, 67 insertions(+)
block/ioctl.c +66 -0
@@ -778,6 +778,69 @@ static void bio_cmd_bio_end_io(struct bio *bio)bio_put (bio); } +static int blkdev_cmd_write_zeroes (struct io_uring_cmd *cmd, +struct block_device *bdev, +uint64_t start,uint64_t len,bool nowait) +{ + struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); +sector_t bs_mask = (bdev_logical_block_size (bdev) >>SECTOR_SHIFT ) -1 ; +sector_t limit =bdev_write_zeroes_sectors (bdev); +sector_t sector = start >>SECTOR_SHIFT ; +sector_t nr_sects = len >>SECTOR_SHIFT ; +struct bio *prev =NULL , *bio; +gfp_t gfp = nowait ?GFP_NOWAIT :GFP_KERNEL ; +int err; + +if (!(file_to_blk_mode (cmd->file) &BLK_OPEN_WRITE )) +return -EBADF ; +if (bdev_read_only (bdev)) +return -EPERM ; + err =blk_validate_byte_range (bdev, start, len); +if (err) +return err; + +if (!limit) +return -EOPNOTSUPP ; +/* +* Don't allow multi-bio non-blocking submissions as subsequent bios +* may fail but we won't get a direct indication of that. Normally, +* the caller should retry from a blocking context. +*/ +if (nowait && nr_sects > limit) +return -EAGAIN ; + + err =filemap_invalidate_pages (bdev->bd_mapping, start, + start + len -1 , nowait); +if (err) +return err; + + limit =min (limit, (UINT_MAX >>SECTOR_SHIFT ) & ~bs_mask); +while (nr_sects) { +sector_t bio_sects =min (nr_sects, limit); + + bio =bio_alloc (bdev,0 ,REQ_OP_WRITE_ZEROES |REQ_NOUNMAP , gfp); +if (!bio) +break ; +if (nowait) + bio->bi_opf |=REQ_NOWAIT ; + bio->bi_iter.bi_sector = sector; + bio->bi_iter.bi_size = bio_sects <<SECTOR_SHIFT ; + sector += bio_sects; + nr_sects -= bio_sects; + + prev =bio_chain_and_submit (prev, bio); + } +if (unlikely (!prev)) +return -EAGAIN ; +if (unlikely (nr_sects)) + bic->res = -EAGAIN ; + + prev->bi_private = cmd; + prev->bi_end_io = bio_cmd_bio_end_io; +submit_bio (prev); +return -EIOCBQUEUED ; +} +static int blkdev_cmd_discard (struct io_uring_cmd *cmd,struct block_device *bdev,uint64_t start,uint64_t len,bool nowait)
@@ -856,6 +919,9 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)switch (cmd_op) {case BLOCK_URING_CMD_DISCARD :return blkdev_cmd_discard (cmd, bdev, start, len, bic->nowait); +case BLOCK_URING_CMD_WRITE_ZEROES : +return blkdev_cmd_write_zeroes (cmd, bdev, start, len, + bic->nowait); }return -EINVAL ; }
include/uapi/linux/blkdev.h +1 -0
@@ -10,5 +10,6 @@* It's a different number space from ioctl(), reuse the block's code 0x12. */ #define BLOCK_URING_CMD_DISCARD _IO(0x12, 0) +#define BLOCK_URING_CMD_WRITE_ZEROES _IO(0x12, 1)#endif
Signature · 1 line
2.45.2
Re: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
Quoted 6 lines · Pavel Begunkov
Add a second
io_uringcmd for block layer implementing asynchronous write zeroes. It reuses helpers we've added for async discards, and inherits the code structure as well as all considerations in regards to page cache races. It has to be supported by underlying hardware to be used, otherwise the request will fail. A fallback version is implemented separately in a later patch.
Except that as far as I can tell it doesn't implement a fallback, but an entirely different command leading to applications breaking when just using the command and the hardware doesn't support it.
to this incomplete API that will just create incompatbilities.
Re: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
Quoted 9 lines · Christoph Hellwig
Quoted 6 lines · Pavel Begunkov
Add a second
io_uringcmd for block layer implementing asynchronous write zeroes. It reuses helpers we've added for async discards, and inherits the code structure as well as all considerations in regards to page cache races. It has to be supported by underlying hardware to be used, otherwise the request will fail. A fallback version is implemented separately in a later patch.Except that as far as I can tell it doesn't implement a fallback, but
I could've worded it better, but it doesn't say anything about implementing fallback for this opcode.
Quoted 6 lines
an entirely different command leading to applications breaking when just using the command and the hardware doesn't support it.
Nacked-by Christoph Hellwig <[email protected]>to this incomplete API that will just create incompatbilities.
That's fine, I'd rather take your nack than humouring the idea of having a worse api than it could be.
Signature · 1 line
Pavel Begunkov
Jens Axboe
maintainerRe: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
Quoted 9 lines · Pavel Begunkov
Quoted 6 lines
an entirely different command leading to applications breaking when just using the command and the hardware doesn't support it.
Nacked-by Christoph Hellwig <[email protected]>to this incomplete API that will just create incompatbilities.
That's fine, I'd rather take your nack than humouring the idea of having a worse api than it could be.
How about we just drop 6-8 for now, and just focus on getting the actual main discard operation in? That's (by far) the most important anyway, and we can always add the write-zeroes bit later.
Signature · 1 line
Jens Axboe
Re: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
Quoted 6 lines · Jens Axboe
Quoted 5 lines · Pavel Begunkov
Quoted 5 lines
an entirely different command leading to applications breaking when just using the command and the hardware doesn't support it.
Nacked-by Christoph Hellwig <[email protected]>
Quoted 8 lines
Quoted 4 lines
Quoted 1 line
to this incomplete API that will just create incompatbilities.
That's fine, I'd rather take your nack than humouring the idea of having a worse api than it could be.
How about we just drop 6-8 for now, and just focus on getting the actual main discard operation in? That's (by far) the most important anyway, and we can always add the write-zeroes bit later.
That's surely an option, and it's naturally up to you.
But to be clear, unless there are some new good arguments, I don't buy those requested changes for 6-8 and refuse to go with it, that's just creating a mess of flags cancelling each other down the line.
Signature · 1 line
Pavel Begunkov
Jens Axboe
maintainerRe: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
Quoted 9 lines · Pavel Begunkov
Quoted 8 lines · Jens Axboe
Quoted 7 lines · Pavel Begunkov
Quoted 6 lines
an entirely different command leading to applications breaking when just using the command and the hardware doesn't support it.
Nacked-by Christoph Hellwig <[email protected]>to this incomplete API that will just create incompatbilities.
Quoted 8 lines
Quoted 6 lines
Quoted 2 lines
That's fine, I'd rather take your nack than humouring the idea of having a worse api than it could be.
How about we just drop 6-8 for now, and just focus on getting the actual main discard operation in? That's (by far) the most important anyway, and we can always add the write-zeroes bit later.
That's surely an option, and it's naturally up to you.
Just trying to make forward progress - and since the actual discard is the most interesting bit (imho), seems silly to gate it on the latter bits.
Quoted 3 lines
But to be clear, unless there are some new good arguments, I don't buy those requested changes for 6-8 and refuse to go with it, that's just creating a mess of flags cancelling each other down the line.
That's something to hash out, might be easier to do in person at LPC next week.
For now I'll just drop 6-8.
Signature · 1 line
Jens Axboe
Re: [PATCH v5 6/8] block: implement write zeroes io_uring cmd
In reply to Jens AxboeQuoted 3 lines · Jens Axboe
How about we just drop 6-8 for now, and just focus on getting the actual main discard operation in? That's (by far) the most important anyway, and we can always add the write-zeroes bit later.
Sounds fine to me.
PATCH v5 7/8 block: add nowait flag for __blkdev_issue_zero_pages
In reply to Pavel BegunkovTo reuse __blkdev_issue_zero_pages() in the following patch, we need to make it work with non-blocking requests. Add a new nowait flag we can pass inside. Return errors if something went wrong, and check bio_alloc() for failures, which wasn't supposed to happen before because of what gfp flags the callers are passing. Note that there might be a bio passed back even when the function returned an error. To limit the scope of the patch, don't add return code handling to callers, that can be deferred to a follow up.
--- block/blk-lib.c | 22 ++++++++++++++++++---- include/linux/bio.h | 4 ++++ include/linux/blkdev.h | 1 + 3 files changed, 23 insertions(+), 4 deletions(-)
block/blk-lib.c +18 -4
@@ -192,20 +192,32 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)return min (pages, (sector_t )BIO_MAX_VECS ); } -static void __blkdev_issue_zero_pages (struct block_device *bdev, +int blkdev_issue_zero_pages_bio (struct block_device *bdev,sector_t sector,sector_t nr_sects,gfp_t gfp_mask,struct bio **biop,unsigned int flags) { +blk_opf_t opf =REQ_OP_WRITE ; + +if (flags &BLKDEV_ZERO_PAGES_NOWAIT ) { +sector_t max_bio_sectors =BIO_MAX_VECS <<PAGE_SECTORS_SHIFT ; + +if (nr_sects > max_bio_sectors) +return -EAGAIN ; + opf |=REQ_NOWAIT ; + } +while (nr_sects) {unsigned int nr_vecs =__blkdev_sectors_to_bio_pages (nr_sects);struct bio *bio; bio =bio_alloc (bdev, nr_vecs,REQ_OP_WRITE , gfp_mask); +if (!bio) +return -ENOMEM ; bio->bi_iter.bi_sector = sector;if ((flags &BLKDEV_ZERO_KILLABLE ) &&fatal_signal_pending (current)) -break ; +return -EINTR ; do { unsigned int len, added;
@@ -222,6 +234,8 @@ static void __blkdev_issue_zero_pages(struct block_device *bdev, *biop =bio_chain_and_submit (*biop, bio);cond_resched (); } + +return 0 ; } static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,
@@ -235,7 +249,7 @@ static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,return -EOPNOTSUPP ;blk_start_plug (&plug); -__blkdev_issue_zero_pages (bdev, sector, nr_sects, gfp, &bio, flags); +blkdev_issue_zero_pages_bio (bdev, sector, nr_sects, gfp, &bio, flags);if (bio) {if ((flags &BLKDEV_ZERO_KILLABLE ) &&fatal_signal_pending (current)) {
@@ -285,7 +299,7 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, }else {if (flags &BLKDEV_ZERO_NOFALLBACK )return -EOPNOTSUPP ; -__blkdev_issue_zero_pages (bdev, sector, nr_sects, gfp_mask, +blkdev_issue_zero_pages_bio (bdev, sector, nr_sects, gfp_mask, biop, flags); }return 0 ;
include/linux/bio.h +4 -0
@@ -684,4 +684,8 @@ struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new);struct bio *blk_alloc_discard_bio (struct block_device *bdev,sector_t *sector,sector_t *nr_sects,gfp_t gfp_mask); +int blkdev_issue_zero_pages_bio (struct block_device *bdev, +sector_t sector,sector_t nr_sects,gfp_t gfp_mask, +struct bio **biop,unsigned int flags); +#endif /* __LINUX_BIO_H */
include/linux/blkdev.h +1 -0
@@ -1098,6 +1098,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,#define BLKDEV_ZERO_NOUNMAP (1 << 0)/* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1)/* don't write explicit zeroes */ #define BLKDEV_ZERO_KILLABLE (1 << 2)/* interruptible by fatal signals */ +#define BLKDEV_ZERO_PAGES_NOWAIT (1 << 3)/* non-blocking submission */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
Signature · 1 line
2.45.2
PATCH v5 8/8 block: implement write zero pages cmd
In reply to Pavel BegunkovAdd a command that writes the zero page to the drive. Apart from passing the zero page instead of actual data it uses the normal write path and doesn't do any further acceleration. Subsequently, it doesn't requires any special hardware support, and for example can be used as a fallback option for BLOCK_URING_CMD_WRITE_ZEROES.
--- block/ioctl.c | 21 ++++++++++++++++++--- include/uapi/linux/blkdev.h | 1 + 2 files changed, 19 insertions(+), 3 deletions(-)
block/ioctl.c +18 -3
@@ -780,7 +780,8 @@ static void bio_cmd_bio_end_io(struct bio *bio)static int blkdev_cmd_write_zeroes (struct io_uring_cmd *cmd,struct block_device *bdev, -uint64_t start,uint64_t len,bool nowait) +uint64_t start,uint64_t len, +bool nowait,bool zero_pages) { struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);sector_t bs_mask = (bdev_logical_block_size (bdev) >>SECTOR_SHIFT ) -1 ;
@@ -799,6 +800,17 @@ static int blkdev_cmd_write_zeroes(struct io_uring_cmd *cmd,if (err)return err; +if (zero_pages) { + err =blkdev_issue_zero_pages_bio (bdev, sector, nr_sects, + gfp, &prev, +BLKDEV_ZERO_PAGES_NOWAIT ); +if (!prev) +return -EAGAIN ; +if (err) + bic->res = err; + goto out_submit; + } +if (!limit)return -EOPNOTSUPP ;/*
@@ -834,7 +846,7 @@ static int blkdev_cmd_write_zeroes(struct io_uring_cmd *cmd,return -EAGAIN ;if (unlikely (nr_sects)) bic->res = -EAGAIN ; - +out_submit: prev->bi_private = cmd; prev->bi_end_io = bio_cmd_bio_end_io;submit_bio (prev);
@@ -921,7 +933,10 @@ int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)return blkdev_cmd_discard (cmd, bdev, start, len, bic->nowait);case BLOCK_URING_CMD_WRITE_ZEROES :return blkdev_cmd_write_zeroes (cmd, bdev, start, len, - bic->nowait); + bic->nowait, false); +case BLOCK_URING_CMD_WRITE_ZERO_PAGE : +return blkdev_cmd_write_zeroes (cmd, bdev, start, len, + bic->nowait, true); }return -EINVAL ; }
include/uapi/linux/blkdev.h +1 -0
@@ -11,5 +11,6 @@*/ #define BLOCK_URING_CMD_DISCARD _IO(0x12, 0)#define BLOCK_URING_CMD_WRITE_ZEROES _IO(0x12, 1) +#define BLOCK_URING_CMD_WRITE_ZERO_PAGE _IO(0x12, 2)#endif
Signature · 1 line
2.45.2
Quoted 10 lines · Pavel Begunkov
There is an interest in having asynchronous block operations like discard and write zeroes. The series implements that as
io_uringcommands, which is anio_uringrequest type allowing to implement custom file specific operations.First 4 are preparation patches. Patch 5 introduces the main chunk of cmd infrastructure and discard commands. Patches 6-8 implement write zeroes variants.
[...]
Applied, thanks!
[1/8] io_uring/cmd: expose iowq to cmds
(no commit info)
[2/8] io_uring/cmd: give inline space in request to cmds
(no commit info)
[3/8] filemap: introduce filemap_invalidate_pages
(no commit info)
[4/8] block: introduce blk_validate_byte_range()
(no commit info)
[5/8] block: implement async io_uring discard cmd
(no commit info)
[6/8] block: implement write zeroes io_uring cmd
(no commit info)
[7/8] block: add nowait flag for __blkdev_issue_zero_pages
(no commit info)
[8/8] block: implement write zero pages cmd
(no commit info)
Best regards,
Signature · 1 line
Jens Axboe