summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorChristian Brauner <brauner@kernel.org>2024-03-04 18:35:21 +0100
committerChristian Brauner <brauner@kernel.org>2024-03-04 18:35:21 +0100
commit86835c39e08e6d92a9d66d51277b2676bc659743 (patch)
treec69dcd5774ef416b429c03515ecf4af289ea6ca8 /fs
parentdcd04ea587b210e78a85d6d4d7cc6765828496b0 (diff)
parent449813515d3e5efec85206bb91588a6249a421a3 (diff)
downloadlwn-86835c39e08e6d92a9d66d51277b2676bc659743.tar.gz
lwn-86835c39e08e6d92a9d66d51277b2676bc659743.zip
Merge tag 'vfs-6.9.rw_hint' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs
Pull write hint fix from Christian Brauner: UFS devices are widely used in mobile applications, e.g. in smartphones. UFS vendors need data lifetime information to achieve good performance. Providing data lifetime information to UFS devices can result in up to 40% lower write amplification. Hence this patch series that restores the bi_write_hint member in struct bio. After this patch series has been merged, patches that implement data lifetime support in the SCSI disk (sd) driver will be sent to the Linux kernel SCSI maintainer. The following changes are included in this patch series: - Improvements for the F_GET_RW_HINT and F_SET_RW_HINT fcntls. - Move enum rw_hint into a new header file. - Support F_SET_RW_HINT for block devices to make it easy to test data lifetime support. - Restore the bio.bi_write_hint member and restore support in the VFS layer and also in the block layer for data lifetime information. The shell script that has been used to test the patch series combined with the SCSI patches is available at the end of this cover letter. * tag 'vfs-6.9.rw_hint' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs: block, fs: Restore the per-bio/request data lifetime fields fs: Propagate write hints to the struct block_device inode fs: Move enum rw_hint into a new header file fs: Split fcntl_rw_hint() fs: Verify write lifetime constants at compile time fs: Fix rw_hint validation Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'fs')
-rw-r--r--fs/buffer.c12
-rw-r--r--fs/direct-io.c2
-rw-r--r--fs/f2fs/f2fs.h1
-rw-r--r--fs/fcntl.c64
-rw-r--r--fs/inode.c1
-rw-r--r--fs/iomap/buffered-io.c1
-rw-r--r--fs/iomap/direct-io.c1
-rw-r--r--fs/mpage.c1
8 files changed, 55 insertions, 28 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index d3bcf601d3e5..eb7d3ded2c33 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -55,7 +55,7 @@
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
- struct writeback_control *wbc);
+ enum rw_hint hint, struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
@@ -1889,7 +1889,8 @@ int __block_write_full_folio(struct inode *inode, struct folio *folio,
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+ inode->i_write_hint, wbc);
nr_underway++;
}
bh = next;
@@ -1944,7 +1945,8 @@ recover:
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh,
+ inode->i_write_hint, wbc);
nr_underway++;
}
bh = next;
@@ -2756,6 +2758,7 @@ static void end_bio_bh_io_sync(struct bio *bio)
}
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
+ enum rw_hint write_hint,
struct writeback_control *wbc)
{
const enum req_op op = opf & REQ_OP_MASK;
@@ -2783,6 +2786,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_write_hint = write_hint;
__bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
@@ -2802,7 +2806,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
void submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
- submit_bh_wbc(opf, bh, NULL);
+ submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL);
}
EXPORT_SYMBOL(submit_bh);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 60456263a338..62c97ff9e852 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -410,6 +410,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
bio->bi_end_io = dio_bio_end_io;
if (dio->is_pinned)
bio_set_flag(bio, BIO_PAGE_PINNED);
+ bio->bi_write_hint = file_inode(dio->iocb->ki_filp)->i_write_hint;
+
sdio->bio = bio;
sdio->logical_offset_in_bio = sdio->cur_page_fs_offset;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 65294e3b0bef..01fde6d44bf6 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -24,6 +24,7 @@
#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/part_stat.h>
+#include <linux/rw_hint.h>
#include <crypto/hash.h>
#include <linux/fscrypt.h>
diff --git a/fs/fcntl.c b/fs/fcntl.c
index c80a6acad742..8eb6d64a985b 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -27,6 +27,7 @@
#include <linux/memfd.h>
#include <linux/compat.h>
#include <linux/mount.h>
+#include <linux/rw_hint.h>
#include <linux/poll.h>
#include <asm/siginfo.h>
@@ -268,8 +269,15 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
}
#endif
-static bool rw_hint_valid(enum rw_hint hint)
+static bool rw_hint_valid(u64 hint)
{
+ BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET);
+ BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE);
+ BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT);
+ BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM);
+ BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG);
+ BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME);
+
switch (hint) {
case RWH_WRITE_LIFE_NOT_SET:
case RWH_WRITE_LIFE_NONE:
@@ -283,34 +291,40 @@ static bool rw_hint_valid(enum rw_hint hint)
}
}
-static long fcntl_rw_hint(struct file *file, unsigned int cmd,
- unsigned long arg)
+static long fcntl_get_rw_hint(struct file *file, unsigned int cmd,
+ unsigned long arg)
{
struct inode *inode = file_inode(file);
u64 __user *argp = (u64 __user *)arg;
- enum rw_hint hint;
- u64 h;
+ u64 hint = READ_ONCE(inode->i_write_hint);
- switch (cmd) {
- case F_GET_RW_HINT:
- h = inode->i_write_hint;
- if (copy_to_user(argp, &h, sizeof(*argp)))
- return -EFAULT;
- return 0;
- case F_SET_RW_HINT:
- if (copy_from_user(&h, argp, sizeof(h)))
- return -EFAULT;
- hint = (enum rw_hint) h;
- if (!rw_hint_valid(hint))
- return -EINVAL;
+ if (copy_to_user(argp, &hint, sizeof(*argp)))
+ return -EFAULT;
+ return 0;
+}
- inode_lock(inode);
- inode->i_write_hint = hint;
- inode_unlock(inode);
- return 0;
- default:
+static long fcntl_set_rw_hint(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct inode *inode = file_inode(file);
+ u64 __user *argp = (u64 __user *)arg;
+ u64 hint;
+
+ if (copy_from_user(&hint, argp, sizeof(hint)))
+ return -EFAULT;
+ if (!rw_hint_valid(hint))
return -EINVAL;
- }
+
+ WRITE_ONCE(inode->i_write_hint, hint);
+
+ /*
+ * file->f_mapping->host may differ from inode. As an example,
+ * blkdev_open() modifies file->f_mapping.
+ */
+ if (file->f_mapping->host != inode)
+ WRITE_ONCE(file->f_mapping->host->i_write_hint, hint);
+
+ return 0;
}
static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
@@ -416,8 +430,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
err = memfd_fcntl(filp, cmd, argi);
break;
case F_GET_RW_HINT:
+ err = fcntl_get_rw_hint(filp, cmd, arg);
+ break;
case F_SET_RW_HINT:
- err = fcntl_rw_hint(filp, cmd, arg);
+ err = fcntl_set_rw_hint(filp, cmd, arg);
break;
default:
break;
diff --git a/fs/inode.c b/fs/inode.c
index 91048c4c9c9e..1aba6c0bf26a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -20,6 +20,7 @@
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include <linux/iversion.h>
+#include <linux/rw_hint.h>
#include <trace/events/writeback.h>
#include "internal.h"
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ae4e2026e59e..4e8e41c8b3c0 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1690,6 +1690,7 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
bio->bi_end_io = iomap_writepage_end_bio;
wbc_init_bio(wbc, bio);
+ bio->bi_write_hint = inode->i_write_hint;
ioend = iomap_ioend_from_bio(bio);
INIT_LIST_HEAD(&ioend->io_list);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index bcd3f8cf5ea4..f3b43d223a46 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -380,6 +380,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
GFP_KERNEL);
bio->bi_iter.bi_sector = iomap_sector(iomap, pos);
+ bio->bi_write_hint = inode->i_write_hint;
bio->bi_ioprio = dio->iocb->ki_ioprio;
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
diff --git a/fs/mpage.c b/fs/mpage.c
index 738882e0766d..fa8b99a199fa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -605,6 +605,7 @@ alloc_new:
GFP_NOFS);
bio->bi_iter.bi_sector = first_block << (blkbits - 9);
wbc_init_bio(wbc, bio);
+ bio->bi_write_hint = inode->i_write_hint;
}
/*