[PATCH v3 0/8] implement async block discards and other ops via io_uring

[PATCH v3 0/8] implement async block discards and other ops via io_uring

[Pavel Begunkov]

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

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 discard as io_uring cmd
  block: implement async write zeroes command
  block: add nowait flag for __blkdev_issue_zero_pages
  block: implement async write zero pages command

 block/blk-lib.c              |  25 +++-
 block/blk.h                  |   1 +
 block/fops.c                 |   2 +
 block/ioctl.c                | 228 ++++++++++++++++++++++++++++++++---
 include/linux/bio.h          |   6 +
 include/linux/blkdev.h       |   1 +
 include/linux/io_uring/cmd.h |  15 +++
 include/linux/pagemap.h      |   2 +
 include/uapi/linux/fs.h      |   4 +
 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, 292 insertions(+), 28 deletions(-)

-- 
2.45.2

[PATCH v3 1/8] io_uring/cmd: expose iowq to cmds

[Pavel Begunkov]

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.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 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(+)

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 447fbfd32215..86ceb3383e49 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -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
 
 /*
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 1aca501efaf6..86cf31902841 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -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)) {
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 65078e641390..9d70b2cf7b1e 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -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);
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 8391c7c7c1ec..39c3c816ec78 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -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)
-- 
2.45.2

[PATCH v3 2/8] io_uring/cmd: give inline space in request to cmds

[Pavel Begunkov]

Some io_uring commands can use some inline space in io_kiocb. We have 32
bytes in struct io_uring_cmd, expose it.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 include/linux/io_uring/cmd.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 86ceb3383e49..c189d36ad55e 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -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);
-- 
2.45.2

[PATCH v3 3/8] filemap: introduce filemap_invalidate_pages

[Pavel Begunkov]

kiocb_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.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 include/linux/pagemap.h |  2 ++
 mm/filemap.c            | 17 ++++++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d9c7edb6422b..e39c3a7ce33c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -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 *);
diff --git a/mm/filemap.c b/mm/filemap.c
index d62150418b91..6843ed4847d4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -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);
 
 /**
-- 
2.45.2

[PATCH v3 4/8] block: introduce blk_validate_byte_range()

[Pavel Begunkov]

In 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.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/ioctl.c | 44 ++++++++++++++++++++++++++------------------
 1 file changed, 26 insertions(+), 18 deletions(-)

diff --git a/block/ioctl.c b/block/ioctl.c
index e8e4a4190f18..a820f692dd1c 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -92,38 +92,46 @@ static int compat_blkpg_ioctl(struct block_device *bdev,
 }
 #endif
 
+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);
-- 
2.45.2

[PATCH v3 5/8] block: implement async discard as io_uring cmd

[Pavel Begunkov]

io_uring allows to implement custom file specific operations via
fops->uring_cmd callback. Use it to wire up asynchronous discard
commands. Normally, first it tries to do a non-blocking issue, and if
fails we'd retry from a blocking context by returning -EAGAIN to
core io_uring.

Note, 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.

Suggested-by: Conrad Meyer <conradmeyer@meta.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/blk-lib.c         |   3 +-
 block/blk.h             |   1 +
 block/fops.c            |   2 +
 block/ioctl.c           | 102 ++++++++++++++++++++++++++++++++++++++++
 include/linux/bio.h     |   2 +
 include/uapi/linux/fs.h |   2 +
 6 files changed, 111 insertions(+), 1 deletion(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 83eb7761c2bf..c94c67a75f7e 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -10,7 +10,8 @@
 
 #include "blk.h"
 
-static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
+/* The maximum size of a discard that can be issued from a given sector. */
+sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
 {
 	unsigned int discard_granularity = bdev_discard_granularity(bdev);
 	sector_t granularity_aligned_sector;
diff --git a/block/blk.h b/block/blk.h
index 32f4e9f630a3..1a1a18d118f7 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -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;
diff --git a/block/fops.c b/block/fops.c
index 9825c1713a49..8154b10b5abf 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -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,
 };
 
diff --git a/block/ioctl.c b/block/ioctl.c
index a820f692dd1c..19fba8332eee 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -11,6 +11,8 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
 #include "blk.h"
 
 static int blkpg_do_ioctl(struct block_device *bdev,
@@ -742,3 +744,103 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return ret;
 }
 #endif
+
+struct blk_iou_cmd {
+	int res;
+	bool nowait;
+};
+
+static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (bic->res == -EAGAIN && bic->nowait)
+		io_uring_cmd_issue_blocking(cmd);
+	else
+		io_uring_cmd_done(cmd, bic->res, 0, issue_flags);
+}
+
+static void bio_cmd_bio_end_io(struct bio *bio)
+{
+	struct io_uring_cmd *cmd = bio->bi_private;
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+
+	if (unlikely(bio->bi_status) && !bic->res)
+		bic->res = blk_status_to_errno(bio->bi_status);
+
+	io_uring_cmd_do_in_task_lazy(cmd, blk_cmd_complete);
+	bio_put(bio);
+}
+
+static int blkdev_cmd_discard(struct io_uring_cmd *cmd,
+			      struct block_device *bdev,
+			      uint64_t start, uint64_t len, bool nowait)
+{
+	gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL;
+	sector_t sector = start >> SECTOR_SHIFT;
+	sector_t nr_sects = len >> SECTOR_SHIFT;
+	struct bio *prev = NULL, *bio;
+	int err;
+
+	if (!bdev_max_discard_sectors(bdev))
+		return -EOPNOTSUPP;
+
+	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;
+
+	/*
+	 * 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 > bio_discard_limit(bdev, sector))
+		return -EAGAIN;
+
+	err = filemap_invalidate_pages(bdev->bd_mapping, start,
+					start + len - 1, nowait);
+	if (err)
+		return err;
+
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects, gfp))) {
+		if (nowait)
+			bio->bi_opf |= REQ_NOWAIT;
+		prev = bio_chain_and_submit(prev, bio);
+	}
+	if (!prev)
+		return -EAGAIN;
+
+	prev->bi_private = cmd;
+	prev->bi_end_io = bio_cmd_bio_end_io;
+	submit_bio(prev);
+	return -EIOCBQUEUED;
+}
+
+int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host);
+	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
+	const struct io_uring_sqe *sqe = cmd->sqe;
+	u32 cmd_op = cmd->cmd_op;
+	uint64_t start, len;
+
+	if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len ||
+		     sqe->rw_flags || sqe->file_index))
+		return -EINVAL;
+
+	bic->res = 0;
+	bic->nowait = issue_flags & IO_URING_F_NONBLOCK;
+
+	start = READ_ONCE(sqe->addr);
+	len = READ_ONCE(sqe->addr3);
+
+	switch (cmd_op) {
+	case BLOCK_URING_CMD_DISCARD:
+		return blkdev_cmd_discard(cmd, bdev, start, len, bic->nowait);
+	}
+	return -EINVAL;
+}
diff --git a/include/linux/bio.h b/include/linux/bio.h
index faceadb040f9..78ead424484c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -684,4 +684,6 @@ 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);
 
+sector_t bio_discard_limit(struct block_device *bdev, sector_t sector);
+
 #endif /* __LINUX_BIO_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 753971770733..7ea41ca97158 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -208,6 +208,8 @@ struct fsxattr {
  * (see uapi/linux/blkzoned.h)
  */
 
+#define BLOCK_URING_CMD_DISCARD			_IO(0x12,137)
+
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
-- 
2.45.2

[PATCH v3 6/8] block: implement async write zeroes command

[Pavel Begunkov]

Add another 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.

Suggested-by: Conrad Meyer <conradmeyer@meta.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/ioctl.c           | 64 +++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/fs.h |  1 +
 2 files changed, 65 insertions(+)

diff --git a/block/ioctl.c b/block/ioctl.c
index 19fba8332eee..ef4b2a90ad79 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -772,6 +772,67 @@ 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)
+{
+
+	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 (!prev)
+		return -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)
@@ -841,6 +902,9 @@ 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;
 }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 7ea41ca97158..68b0fccebf92 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -209,6 +209,7 @@ struct fsxattr {
  */
 
 #define BLOCK_URING_CMD_DISCARD			_IO(0x12,137)
+#define BLOCK_URING_CMD_WRITE_ZEROES		_IO(0x12,138)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
-- 
2.45.2

[PATCH v3 7/8] block: add nowait flag for __blkdev_issue_zero_pages

[Pavel Begunkov]

To 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.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/blk-lib.c        | 22 ++++++++++++++++++----
 include/linux/bio.h    |  4 ++++
 include/linux/blkdev.h |  1 +
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index c94c67a75f7e..a16b7c7965e8 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -193,20 +193,32 @@ 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;
@@ -223,6 +235,8 @@ 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,
@@ -236,7 +250,7 @@ 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)) {
@@ -286,7 +300,7 @@ 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;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 78ead424484c..87d85b326e1e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -686,4 +686,8 @@ struct bio *blk_alloc_discard_bio(struct block_device *bdev,
 
 sector_t bio_discard_limit(struct block_device *bdev, sector_t sector);
 
+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 */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 643c9020a35a..bf1aa951fda2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -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,
-- 
2.45.2

[PATCH v3 8/8] block: implement async write zero pages command

[Pavel Begunkov]

Add 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, nor it requires any special
hardware support. The indended use is to have a fallback when
BLOCK_URING_CMD_WRITE_ZEROES is not supported.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 block/ioctl.c           | 24 +++++++++++++++++++++---
 include/uapi/linux/fs.h |  1 +
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/block/ioctl.c b/block/ioctl.c
index ef4b2a90ad79..3cb479192023 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -774,7 +774,8 @@ 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)
 {
 
 	sector_t bs_mask = (bdev_logical_block_size(bdev) >> SECTOR_SHIFT) - 1;
@@ -793,6 +794,20 @@ static int blkdev_cmd_write_zeroes(struct io_uring_cmd *cmd,
 	if (err)
 		return err;
 
+	if (zero_pages) {
+		struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd,
+						struct blk_iou_cmd);
+
+		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;
 	/*
@@ -826,7 +841,7 @@ static int blkdev_cmd_write_zeroes(struct io_uring_cmd *cmd,
 	}
 	if (!prev)
 		return -EAGAIN;
-
+out_submit:
 	prev->bi_private = cmd;
 	prev->bi_end_io = bio_cmd_bio_end_io;
 	submit_bio(prev);
@@ -904,7 +919,10 @@ 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;
 }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 68b0fccebf92..f4337b87d846 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -210,6 +210,7 @@ struct fsxattr {
 
 #define BLOCK_URING_CMD_DISCARD			_IO(0x12,137)
 #define BLOCK_URING_CMD_WRITE_ZEROES		_IO(0x12,138)
+#define BLOCK_URING_CMD_WRITE_ZERO_PAGE		_IO(0x12,139)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
-- 
2.45.2

Re: [PATCH v3 7/8] block: add nowait flag for __blkdev_issue_zero_pages

[kernel test robot]

Hi Pavel,

kernel test robot noticed the following build warnings:

[auto build test WARNING on axboe-block/for-next]
[also build test WARNING on akpm-mm/mm-everything linus/master v6.11-rc6 next-20240905]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Pavel-Begunkov/io_uring-cmd-expose-iowq-to-cmds/20240904-222012
base:   https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git for-next
patch link:    https://lore.kernel.org/r/292fa1c611adb064efe16ab741aad65c2128ada8.1725459175.git.asml.silence%40gmail.com
patch subject: [PATCH v3 7/8] block: add nowait flag for __blkdev_issue_zero_pages
config: i386-randconfig-141-20240906 (https://download.01.org/0day-ci/archive/20240906/202409061126.hKdAymJK-lkp@intel.com/config)
compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240906/202409061126.hKdAymJK-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409061126.hKdAymJK-lkp@intel.com/

All warnings (new ones prefixed by >>):

>> block/blk-lib.c:200:12: warning: variable 'opf' set but not used [-Wunused-but-set-variable]
     200 |         blk_opf_t opf = REQ_OP_WRITE;
         |                   ^
   1 warning generated.


vim +/opf +200 block/blk-lib.c

   195	
   196	int blkdev_issue_zero_pages_bio(struct block_device *bdev,
   197			sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
   198			struct bio **biop, unsigned int flags)
   199	{
 > 200		blk_opf_t opf = REQ_OP_WRITE;
   201	
   202		if (flags & BLKDEV_ZERO_PAGES_NOWAIT) {
   203			sector_t max_bio_sectors = BIO_MAX_VECS << PAGE_SECTORS_SHIFT;
   204	
   205			if (nr_sects > max_bio_sectors)
   206				return -EAGAIN;
   207			opf |= REQ_NOWAIT;
   208		}
   209	
   210		while (nr_sects) {
   211			unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects);
   212			struct bio *bio;
   213	
   214			bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask);
   215			if (!bio)
   216				return -ENOMEM;
   217			bio->bi_iter.bi_sector = sector;
   218	
   219			if ((flags & BLKDEV_ZERO_KILLABLE) &&
   220			    fatal_signal_pending(current))
   221				return -EINTR;
   222	
   223			do {
   224				unsigned int len, added;
   225	
   226				len = min_t(sector_t,
   227					PAGE_SIZE, nr_sects << SECTOR_SHIFT);
   228				added = bio_add_page(bio, ZERO_PAGE(0), len, 0);
   229				if (added < len)
   230					break;
   231				nr_sects -= added >> SECTOR_SHIFT;
   232				sector += added >> SECTOR_SHIFT;
   233			} while (nr_sects);
   234	
   235			*biop = bio_chain_and_submit(*biop, bio);
   236			cond_resched();
   237		}
   238	
   239		return 0;
   240	}
   241	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v3 7/8] block: add nowait flag for __blkdev_issue_zero_pages

[Jens Axboe]

On 9/4/24 8:18 AM, Pavel Begunkov wrote:
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index c94c67a75f7e..a16b7c7965e8 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -193,20 +193,32 @@ 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);

as per the kernel test bot, I guess this one should be using opf rather
than REQ_OP_WRITE.

-- 
Jens Axboe

Re: [PATCH v3 7/8] block: add nowait flag for __blkdev_issue_zero_pages

[Pavel Begunkov]

On 9/6/24 14:41, Jens Axboe wrote:
> On 9/4/24 8:18 AM, Pavel Begunkov wrote:
>> diff --git a/block/blk-lib.c b/block/blk-lib.c
>> index c94c67a75f7e..a16b7c7965e8 100644
>> --- a/block/blk-lib.c
>> +++ b/block/blk-lib.c
>> @@ -193,20 +193,32 @@ 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);
> 
> as per the kernel test bot, I guess this one should be using opf rather
> than REQ_OP_WRITE.

Right, I overlooked it. I'm going to resend the series later today.

-- 
Pavel Begunkov