Merge tag 'for-6.12/io_uring-discard-20240913' of git://git.kernel.dk/linux

Pull io_uring async discard support from Jens Axboe:
 "Sitting on top of both the 6.12 block and io_uring core branches,
  here's support for async discard through io_uring.

  This allows applications to issue async discards, rather than rely on
  the blocking sync ioctl discards we already have. The sync support is
  difficult to use outside of idle/cleanup periods.

  On a real (but slow) device, testing shows the following results when
  compared to sync discard:

	qd64 sync discard: 21K IOPS, lat avg 3 msec (max 21 msec)
	qd64 async discard: 76K IOPS, lat avg 845 usec (max 2.2 msec)

	qd64 sync discard: 14K IOPS, lat avg 5 msec (max 25 msec)
	qd64 async discard: 56K IOPS, lat avg 1153 usec (max 3.6 msec)

  and synthetic null_blk testing with the same queue depth and block
  size settings as above shows:

	Type    Trim size       IOPS    Lat avg (usec)  Lat Max (usec)
	==============================================================
	sync    4k               144K       444            20314
	async   4k              1353K        47              595
	sync    1M                56K      1136            21031
	async   1M                94K       680              760"

* tag 'for-6.12/io_uring-discard-20240913' of git://git.kernel.dk/linux:
  block: implement async io_uring discard cmd
  block: introduce blk_validate_byte_range()
  filemap: introduce filemap_invalidate_pages
  io_uring/cmd: give inline space in request to cmds
  io_uring/cmd: expose iowq to cmds

Author: torvalds

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;

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)
@@ -865,6 +866,7 @@ 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

@@ -11,6 +11,9 @@
 #include <linux/blktrace_api.h>
 #include <linux/pr.h>
 #include <linux/uaccess.h>
+#include <linux/pagemap.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/blkdev.h>
 #include "blk.h"
 
 static int blkpg_do_ioctl(struct block_device *bdev,
@@ -92,41 +95,54 @@ 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;
 
@@ -735,3 +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, &sector, &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;
+}

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);
@@ -48,6 +57,9 @@ 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 +79,9 @@ 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
 
 /*

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 *);

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 <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

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)) {

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);

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)

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);
 
 /**