Re: [RFC 5/5] block: implement io_uring discard cmd
From: Jens Axboe <axboe@kernel.dk>
Date: 2024-08-15 14:42:58
Also in:
io-uring, linux-mm
On 8/14/24 4:45 AM, Pavel Begunkov wrote:
quoted hunk ↗ jump to hunk
diff --git a/block/ioctl.c b/block/ioctl.c index c7a3e6c6f5fa..f7f9c4c6d6b5 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,@@ -744,4 +746,96 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return ret; } + +struct blk_cmd { + blk_status_t status; + bool nowait; +}; + +static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct blk_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_cmd); + int res = blk_status_to_errno(bc->status); + + if (res == -EAGAIN && bc->nowait) + io_uring_cmd_issue_blocking(cmd); + else + io_uring_cmd_done(cmd, res, 0, issue_flags); +} + +static void bio_cmd_end(struct bio *bio) +{ + struct io_uring_cmd *cmd = bio->bi_private; + struct blk_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_cmd); + + if (unlikely(bio->bi_status) && !bc->status) + bc->status = 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) +{ + sector_t sector = start >> SECTOR_SHIFT; + sector_t nr_sects = len >> SECTOR_SHIFT; + struct bio *prev = NULL, *bio; + int err; + + err = blk_validate_discard(bdev, file_to_blk_mode(cmd->file), + start, len); + if (err) + return err; + err = filemap_invalidate_pages(bdev->bd_mapping, start, + start + len - 1, nowait); + if (err) + return err; + + while ((bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, + GFP_KERNEL))) { + if (nowait) { + if (unlikely(nr_sects)) { + bio_put(bio); + return -EAGAIN; + } + bio->bi_opf |= REQ_NOWAIT; + } + prev = bio_chain_and_submit(prev, bio); + } + if (!prev) + return -EFAULT; + + prev->bi_private = cmd; + prev->bi_end_io = bio_cmd_end; + 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_cmd *bc = io_uring_cmd_to_pdu(cmd, struct blk_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; + + bc->status = BLK_STS_OK; + bc->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, bc->nowait); + } + return -EINVAL; +}
This is inside the CONFIG_COMPAT section, which doesn't seem right. -- Jens Axboe