From 6746ee4c3a189f8b60694f01e7e29bc5ff7972e0 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:37 +0100 Subject: [PATCH 1/5] 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. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f735f807d7c8ba50c9452c69dfe5d3e9e535037b.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- 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) From a6ccb48e13662bcb98282e051512b9686b02d353 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:38 +0100 Subject: [PATCH 2/5] io_uring/cmd: give inline space in request to cmds 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 Link: https://lore.kernel.org/r/7ca779a61ee5e166e535d70df9c7f07b15d8a0ce.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- 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); From a12c883a0a6a005cfb3ad01feaf783e2248bfc3e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:39 +0100 Subject: [PATCH 3/5] filemap: introduce filemap_invalidate_pages 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 Link: https://lore.kernel.org/r/f81374b52c92d0dce0f01a279d1eed42b54056aa.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- 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 0ca9c1377b68..497e802325c9 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); /** From 7a07210bbcb35c0075830bb94b5321978164cb60 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:40 +0100 Subject: [PATCH 4/5] block: introduce blk_validate_byte_range() 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 Link: https://lore.kernel.org/r/19a7779323c71e742a2f511e4cf49efcfd68cfd4.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- block/ioctl.c | 51 ++++++++++++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 19 deletions(-) diff --git a/block/ioctl.c b/block/ioctl.c index 44257bdfeacb..6eaa3f20bf34 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -92,41 +92,54 @@ 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, end - 1); + err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail; From 50c52250e2d74b098465841163c18f4b4e9ad430 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 11 Sep 2024 17:34:41 +0100 Subject: [PATCH 5/5] block: implement async io_uring discard cmd io_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. Suggested-by: Conrad Meyer Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/2b5210443e4fa0257934f73dfafcc18a77cd0e09.1726072086.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- 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 diff --git a/block/blk.h b/block/blk.h index 86affb583eb6..c718e4291db0 100644 --- a/block/blk.h +++ b/block/blk.h @@ -609,6 +609,7 @@ 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 #include #include +#include #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 6eaa3f20bf34..6554b728bae6 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -11,6 +11,9 @@ #include #include #include +#include +#include +#include #include "blk.h" static int blkpg_do_ioctl(struct block_device *bdev, @@ -748,3 +751,112 @@ 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) +{ + struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); + 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; + + err = filemap_invalidate_pages(bdev->bd_mapping, start, + start + len - 1, nowait); + if (err) + return err; + + while (true) { + bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, gfp); + if (!bio) + break; + if (nowait) { + /* + * 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 (unlikely(nr_sects)) { + bio_put(bio); + return -EAGAIN; + } + bio->bi_opf |= REQ_NOWAIT; + } + + 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; +} + +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/uapi/linux/blkdev.h b/include/uapi/linux/blkdev.h new file mode 100644 index 000000000000..66373cd1a83a --- /dev/null +++ b/include/uapi/linux/blkdev.h @@ -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 +#include + +/* + * 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