summaryrefslogtreecommitdiff
path: root/fs/direct-io.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/direct-io.c')
-rw-r--r--fs/direct-io.c137
1 files changed, 57 insertions, 80 deletions
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 03d381377ae1..2267f5ae7f77 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -37,13 +37,12 @@
#include <linux/rwsem.h>
#include <linux/uio.h>
#include <linux/atomic.h>
-#include <linux/prefetch.h>
#include "internal.h"
/*
- * How many user pages to map in one call to get_user_pages(). This determines
- * the size of a structure in the slab cache
+ * How many user pages to map in one call to iov_iter_extract_pages(). This
+ * determines the size of a structure in the slab cache
*/
#define DIO_PAGES 64
@@ -86,7 +85,6 @@ struct dio_submit {
sector_t final_block_in_request;/* doesn't change */
int boundary; /* prev block is at a boundary */
get_block_t *get_block; /* block mapping function */
- dio_submit_t *submit_io; /* IO submition function */
loff_t logical_offset_in_bio; /* current first logical block in bio */
sector_t final_block_in_bio; /* current final block in bio + 1 */
@@ -122,12 +120,13 @@ struct dio {
struct inode *inode;
loff_t i_size; /* i_size when submitted */
dio_iodone_t *end_io; /* IO completion function */
+ bool is_pinned; /* T if we have pins on the pages */
void *private; /* copy from map_bh.b_private */
/* BIO completion state */
spinlock_t bio_lock; /* protects BIO fields below */
- int page_errors; /* errno from get_user_pages() */
+ int page_errors; /* err from iov_iter_extract_pages() */
int is_async; /* is IO async ? */
bool defer_completion; /* defer AIO completion to workqueue? */
bool should_dirty; /* if pages should be dirtied */
@@ -151,7 +150,7 @@ struct dio {
};
} ____cacheline_aligned_in_smp;
-static struct kmem_cache *dio_cache __read_mostly;
+static struct kmem_cache *dio_cache __ro_after_init;
/*
* How many pages are in the queue?
@@ -166,14 +165,14 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio)
*/
static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
{
+ struct page **pages = dio->pages;
const enum req_op dio_op = dio->opf & REQ_OP_MASK;
ssize_t ret;
- ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
- &sdio->from);
+ ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX,
+ DIO_PAGES, 0, &sdio->from);
if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
- struct page *page = ZERO_PAGE(0);
/*
* A memory fault, but the filesystem has some outstanding
* mapped blocks. We need to use those blocks up to avoid
@@ -181,8 +180,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
*/
if (dio->page_errors == 0)
dio->page_errors = ret;
- get_page(page);
- dio->pages[0] = page;
+ dio->pages[0] = ZERO_PAGE(0);
sdio->head = 0;
sdio->tail = 1;
sdio->from = 0;
@@ -202,9 +200,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
/*
* Get another userspace page. Returns an ERR_PTR on error. Pages are
- * buffered inside the dio so that we can call get_user_pages() against a
- * decent number of pages, less frequently. To provide nicer use of the
- * L1 cache.
+ * buffered inside the dio so that we can call iov_iter_extract_pages()
+ * against a decent number of pages, less frequently. To provide nicer use of
+ * the L1 cache.
*/
static inline struct page *dio_get_page(struct dio *dio,
struct dio_submit *sdio)
@@ -220,6 +218,18 @@ static inline struct page *dio_get_page(struct dio *dio,
return dio->pages[sdio->head];
}
+static void dio_pin_page(struct dio *dio, struct page *page)
+{
+ if (dio->is_pinned)
+ folio_add_pin(page_folio(page));
+}
+
+static void dio_unpin_page(struct dio *dio, struct page *page)
+{
+ if (dio->is_pinned)
+ unpin_user_page(page);
+}
+
/*
* dio_complete() - called when all DIO BIO I/O has been completed
*
@@ -286,14 +296,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
* zeros from unwritten extents.
*/
if (flags & DIO_COMPLETE_INVALIDATE &&
- ret > 0 && dio_op == REQ_OP_WRITE &&
- dio->inode->i_mapping->nrpages) {
- err = invalidate_inode_pages2_range(dio->inode->i_mapping,
- offset >> PAGE_SHIFT,
- (offset + ret - 1) >> PAGE_SHIFT);
- if (err)
- dio_warn_stale_pagecache(dio->iocb->ki_filp);
- }
+ ret > 0 && dio_op == REQ_OP_WRITE)
+ kiocb_invalidate_post_direct_write(dio->iocb, ret);
inode_dio_end(dio->inode);
@@ -403,6 +407,10 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
bio->bi_end_io = dio_bio_end_aio;
else
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;
}
@@ -431,10 +439,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
dio->bio_disk = bio->bi_bdev->bd_disk;
- if (sdio->submit_io)
- sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
- else
- submit_bio(bio);
+ submit_bio(bio);
sdio->bio = NULL;
sdio->boundary = 0;
@@ -446,8 +451,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
*/
static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio)
{
- while (sdio->head < sdio->tail)
- put_page(dio->pages[sdio->head++]);
+ if (dio->is_pinned)
+ unpin_user_pages(dio->pages + sdio->head,
+ sdio->tail - sdio->head);
+ sdio->head = sdio->tail;
}
/*
@@ -558,30 +565,6 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio)
return ret;
}
-/*
- * Create workqueue for deferred direct IO completions. We allocate the
- * workqueue when it's first needed. This avoids creating workqueue for
- * filesystems that don't need it and also allows us to create the workqueue
- * late enough so the we can include s_id in the name of the workqueue.
- */
-int sb_init_dio_done_wq(struct super_block *sb)
-{
- struct workqueue_struct *old;
- struct workqueue_struct *wq = alloc_workqueue("dio/%s",
- WQ_MEM_RECLAIM, 0,
- sb->s_id);
- if (!wq)
- return -ENOMEM;
- /*
- * This has to be atomic as more DIOs can race to create the workqueue
- */
- old = cmpxchg(&sb->s_dio_done_wq, NULL, wq);
- /* Someone created workqueue before us? Free ours... */
- if (old)
- destroy_workqueue(wq);
- return 0;
-}
-
static int dio_set_defer_completion(struct dio *dio)
{
struct super_block *sb = dio->inode->i_sb;
@@ -702,7 +685,7 @@ out:
*
* Return zero on success. Non-zero means the caller needs to start a new BIO.
*/
-static inline int dio_bio_add_page(struct dio_submit *sdio)
+static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio)
{
int ret;
@@ -714,7 +697,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio)
*/
if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE)
sdio->pages_in_io--;
- get_page(sdio->cur_page);
+ dio_pin_page(dio, sdio->cur_page);
sdio->final_block_in_bio = sdio->cur_page_block +
(sdio->cur_page_len >> sdio->blkbits);
ret = 0;
@@ -769,11 +752,11 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio,
goto out;
}
- if (dio_bio_add_page(sdio) != 0) {
+ if (dio_bio_add_page(dio, sdio) != 0) {
dio_bio_submit(dio, sdio);
ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh);
if (ret == 0) {
- ret = dio_bio_add_page(sdio);
+ ret = dio_bio_add_page(dio, sdio);
BUG_ON(ret != 0);
}
}
@@ -830,13 +813,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
*/
if (sdio->cur_page) {
ret = dio_send_cur_page(dio, sdio, map_bh);
- put_page(sdio->cur_page);
+ dio_unpin_page(dio, sdio->cur_page);
sdio->cur_page = NULL;
if (ret)
return ret;
}
- get_page(page); /* It is in dio */
+ dio_pin_page(dio, page); /* It is in dio */
sdio->cur_page = page;
sdio->cur_page_offset = offset;
sdio->cur_page_len = len;
@@ -851,7 +834,7 @@ out:
ret = dio_send_cur_page(dio, sdio, map_bh);
if (sdio->bio)
dio_bio_submit(dio, sdio);
- put_page(sdio->cur_page);
+ dio_unpin_page(dio, sdio->cur_page);
sdio->cur_page = NULL;
}
return ret;
@@ -952,7 +935,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
ret = get_more_blocks(dio, sdio, map_bh);
if (ret) {
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
if (!buffer_mapped(map_bh))
@@ -997,7 +980,7 @@ do_holes:
/* AKPM: eargh, -ENOTBLK is a hack */
if (dio_op == REQ_OP_WRITE) {
- put_page(page);
+ dio_unpin_page(dio, page);
return -ENOTBLK;
}
@@ -1010,10 +993,10 @@ do_holes:
if (sdio->block_in_file >=
i_size_aligned >> blkbits) {
/* We hit eof */
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
- zero_user(page, from, 1 << blkbits);
+ memzero_page(page, from, 1 << blkbits);
sdio->block_in_file++;
from += 1 << blkbits;
dio->result += 1 << blkbits;
@@ -1050,7 +1033,7 @@ do_holes:
sdio->next_block_for_io,
map_bh);
if (ret) {
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
sdio->next_block_for_io += this_chunk_blocks;
@@ -1065,8 +1048,8 @@ next_block:
break;
}
- /* Drop the ref which was taken in get_user_pages() */
- put_page(page);
+ /* Drop the pin which was taken in get_user_pages() */
+ dio_unpin_page(dio, page);
}
out:
return ret;
@@ -1100,8 +1083,8 @@ static inline int drop_refcount(struct dio *dio)
* The locking rules are governed by the flags parameter:
* - if the flags value contains DIO_LOCKING we use a fancy locking
* scheme for dumb filesystems.
- * For writes this function is called under i_mutex and returns with
- * i_mutex held, for reads, i_mutex is not held on entry, but it is
+ * For writes this function is called under i_rwsem and returns with
+ * i_rwsem held, for reads, i_rwsem is not held on entry, but it is
* taken and dropped again before returning.
* - if the flags value does NOT contain DIO_LOCKING we don't use any
* internal locking but rather rely on the filesystem to synchronize
@@ -1111,7 +1094,7 @@ static inline int drop_refcount(struct dio *dio)
* counter before starting direct I/O, and decrement it once we are done.
* Truncate can wait for it to reach zero to provide exclusion. It is
* expected that filesystem provide exclusion between new direct I/O
- * and truncates. For DIO_LOCKING filesystems this is done by i_mutex,
+ * and truncates. For DIO_LOCKING filesystems this is done by i_rwsem,
* but other filesystems need to take care of this on their own.
*
* NOTE: if you pass "sdio" to anything by pointer make sure that function
@@ -1122,7 +1105,7 @@ static inline int drop_refcount(struct dio *dio)
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int flags)
+ int flags)
{
unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
unsigned blkbits = i_blkbits;
@@ -1132,16 +1115,11 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
loff_t offset = iocb->ki_pos;
const loff_t end = offset + count;
struct dio *dio;
- struct dio_submit sdio = { 0, };
+ struct dio_submit sdio = { NULL, };
struct buffer_head map_bh = { 0, };
struct blk_plug plug;
unsigned long align = offset | iov_iter_alignment(iter);
- /*
- * Avoid references to bdev if not absolutely needed to give
- * the early prefetch in the caller enough time.
- */
-
/* watch out for a 0 len io from a tricksy fs */
if (iov_iter_rw(iter) == READ && !count)
return 0;
@@ -1161,6 +1139,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
/* will be released by direct_io_worker */
inode_lock(inode);
}
+ dio->is_pinned = iov_iter_extract_will_pin(iter);
/* Once we sampled i_size check for reads beyond EOF */
dio->i_size = i_size_read(inode);
@@ -1232,14 +1211,12 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
*/
inode_dio_begin(inode);
- retval = 0;
sdio.blkbits = blkbits;
sdio.blkfactor = i_blkbits - blkbits;
sdio.block_in_file = offset >> blkbits;
sdio.get_block = get_block;
dio->end_io = end_io;
- sdio.submit_io = submit_io;
sdio.final_block_in_bio = -1;
sdio.next_block_for_io = -1;
@@ -1286,7 +1263,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
ret2 = dio_send_cur_page(dio, &sdio, &map_bh);
if (retval == 0)
retval = ret2;
- put_page(sdio.cur_page);
+ dio_unpin_page(dio, sdio.cur_page);
sdio.cur_page = NULL;
}
if (sdio.bio)
@@ -1302,7 +1279,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
/*
* All block lookups have been performed. For READ requests
- * we can let i_mutex go now that its achieved its purpose
+ * we can let i_rwsem go now that its achieved its purpose
* of protecting us from looking up uninitialized blocks.
*/
if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
generated by cgit (git 2.34.1) at 2025-12-21 18:31:49 +0000