summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c16
-rw-r--r--fs/ext3/super.c11
-rw-r--r--fs/ext4/super.c11
-rw-r--r--fs/fuse/cuse.c10
-rw-r--r--fs/fuse/dev.c80
-rw-r--r--fs/fuse/dir.c17
-rw-r--r--fs/fuse/file.c272
-rw-r--r--fs/fuse/fuse_i.h36
-rw-r--r--fs/fuse/inode.c12
-rw-r--r--fs/hfs/dir.c2
-rw-r--r--fs/nfs/blocklayout/blocklayout.h2
-rw-r--r--fs/nfs/blocklayout/blocklayoutdev.c4
-rw-r--r--fs/nfs/blocklayout/blocklayoutdm.c8
-rw-r--r--fs/reiserfs/journal.c16
14 files changed, 380 insertions, 117 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 95ff88b54e9..d9871c1f089 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1046,7 +1046,7 @@ void bd_set_size(struct block_device *bdev, loff_t size)
}
EXPORT_SYMBOL(bd_set_size);
-static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
/*
* bd_mutex locking:
@@ -1401,9 +1401,8 @@ static int blkdev_open(struct inode * inode, struct file * filp)
return blkdev_get(bdev, filp->f_mode, filp);
}
-static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
+static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
{
- int ret = 0;
struct gendisk *disk = bdev->bd_disk;
struct block_device *victim = NULL;
@@ -1423,7 +1422,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
- ret = disk->fops->release(disk, mode);
+ disk->fops->release(disk, mode);
}
if (!bdev->bd_openers) {
struct module *owner = disk->fops->owner;
@@ -1442,10 +1441,9 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
bdput(bdev);
if (victim)
__blkdev_put(victim, mode, 1);
- return ret;
}
-int blkdev_put(struct block_device *bdev, fmode_t mode)
+void blkdev_put(struct block_device *bdev, fmode_t mode)
{
mutex_lock(&bdev->bd_mutex);
@@ -1489,15 +1487,15 @@ int blkdev_put(struct block_device *bdev, fmode_t mode)
mutex_unlock(&bdev->bd_mutex);
- return __blkdev_put(bdev, mode, 0);
+ __blkdev_put(bdev, mode, 0);
}
EXPORT_SYMBOL(blkdev_put);
static int blkdev_close(struct inode * inode, struct file * filp)
{
struct block_device *bdev = I_BDEV(filp->f_mapping->host);
-
- return blkdev_put(bdev, filp->f_mode);
+ blkdev_put(bdev, filp->f_mode);
+ return 0;
}
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 3dc48cc8b6e..6356665a74b 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -362,22 +362,19 @@ fail:
/*
* Release the journal device
*/
-static int ext3_blkdev_put(struct block_device *bdev)
+static void ext3_blkdev_put(struct block_device *bdev)
{
- return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
-static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
+static void ext3_blkdev_remove(struct ext3_sb_info *sbi)
{
struct block_device *bdev;
- int ret = -ENODEV;
-
bdev = sbi->journal_bdev;
if (bdev) {
- ret = ext3_blkdev_put(bdev);
+ ext3_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
- return ret;
}
static inline struct inode *orphan_list_entry(struct list_head *l)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 24a146bde74..94cc84db7c9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -703,22 +703,19 @@ fail:
/*
* Release the journal device
*/
-static int ext4_blkdev_put(struct block_device *bdev)
+static void ext4_blkdev_put(struct block_device *bdev)
{
- return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
-static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
+static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
- int ret = -ENODEV;
-
bdev = sbi->journal_bdev;
if (bdev) {
- ret = ext4_blkdev_put(bdev);
+ ext4_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
- return ret;
}
static inline struct inode *orphan_list_entry(struct list_head *l)
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 06b5e086ab3..aef34b1e635 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -93,8 +93,9 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
{
loff_t pos = 0;
struct iovec iov = { .iov_base = buf, .iov_len = count };
+ struct fuse_io_priv io = { .async = 0, .file = file };
- return fuse_direct_io(file, &iov, 1, count, &pos, 0);
+ return fuse_direct_io(&io, &iov, 1, count, &pos, 0);
}
static ssize_t cuse_write(struct file *file, const char __user *buf,
@@ -102,12 +103,13 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
{
loff_t pos = 0;
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
+ struct fuse_io_priv io = { .async = 0, .file = file };
/*
* No locking or generic_write_checks(), the server is
* responsible for locking and sanity checks.
*/
- return fuse_direct_io(file, &iov, 1, count, &pos, 1);
+ return fuse_direct_io(&io, &iov, 1, count, &pos, 1);
}
static int cuse_open(struct inode *inode, struct file *file)
@@ -423,7 +425,7 @@ static int cuse_send_init(struct cuse_conn *cc)
BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
- req = fuse_get_req(fc, 1);
+ req = fuse_get_req_for_background(fc, 1);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
goto err;
@@ -505,7 +507,7 @@ static int cuse_channel_open(struct inode *inode, struct file *file)
cc->fc.release = cuse_fc_release;
cc->fc.connected = 1;
- cc->fc.blocked = 0;
+ cc->fc.initialized = 1;
rc = cuse_send_init(cc);
if (rc) {
fuse_conn_put(&cc->fc);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index a45c19093eb..1d55f946540 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -112,7 +112,7 @@ static void restore_sigs(sigset_t *oldset)
sigprocmask(SIG_SETMASK, oldset, NULL);
}
-static void __fuse_get_request(struct fuse_req *req)
+void __fuse_get_request(struct fuse_req *req)
{
atomic_inc(&req->count);
}
@@ -131,20 +131,30 @@ static void fuse_req_init_context(struct fuse_req *req)
req->in.h.pid = current->pid;
}
-struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
+static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
+{
+ return !fc->initialized || (for_background && fc->blocked);
+}
+
+static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,
+ bool for_background)
{
struct fuse_req *req;
- sigset_t oldset;
- int intr;
int err;
-
atomic_inc(&fc->num_waiting);
- block_sigs(&oldset);
- intr = wait_event_interruptible(fc->blocked_waitq, !fc->blocked);
- restore_sigs(&oldset);
- err = -EINTR;
- if (intr)
- goto out;
+
+ if (fuse_block_alloc(fc, for_background)) {
+ sigset_t oldset;
+ int intr;
+
+ block_sigs(&oldset);
+ intr = wait_event_interruptible_exclusive(fc->blocked_waitq,
+ !fuse_block_alloc(fc, for_background));
+ restore_sigs(&oldset);
+ err = -EINTR;
+ if (intr)
+ goto out;
+ }
err = -ENOTCONN;
if (!fc->connected)
@@ -152,19 +162,35 @@ struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
req = fuse_request_alloc(npages);
err = -ENOMEM;
- if (!req)
+ if (!req) {
+ if (for_background)
+ wake_up(&fc->blocked_waitq);
goto out;
+ }
fuse_req_init_context(req);
req->waiting = 1;
+ req->background = for_background;
return req;
out:
atomic_dec(&fc->num_waiting);
return ERR_PTR(err);
}
+
+struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
+{
+ return __fuse_get_req(fc, npages, false);
+}
EXPORT_SYMBOL_GPL(fuse_get_req);
+struct fuse_req *fuse_get_req_for_background(struct fuse_conn *fc,
+ unsigned npages)
+{
+ return __fuse_get_req(fc, npages, true);
+}
+EXPORT_SYMBOL_GPL(fuse_get_req_for_background);
+
/*
* Return request in fuse_file->reserved_req. However that may
* currently be in use. If that is the case, wait for it to become
@@ -226,19 +252,31 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
struct fuse_req *req;
atomic_inc(&fc->num_waiting);
- wait_event(fc->blocked_waitq, !fc->blocked);
+ wait_event(fc->blocked_waitq, fc->initialized);
req = fuse_request_alloc(0);
if (!req)
req = get_reserved_req(fc, file);
fuse_req_init_context(req);
req->waiting = 1;
+ req->background = 0;
return req;
}
void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
if (atomic_dec_and_test(&req->count)) {
+ if (unlikely(req->background)) {
+ /*
+ * We get here in the unlikely case that a background
+ * request was allocated but not sent
+ */
+ spin_lock(&fc->lock);
+ if (!fc->blocked)
+ wake_up(&fc->blocked_waitq);
+ spin_unlock(&fc->lock);
+ }
+
if (req->waiting)
atomic_dec(&fc->num_waiting);
@@ -336,10 +374,15 @@ __releases(fc->lock)
list_del(&req->intr_entry);
req->state = FUSE_REQ_FINISHED;
if (req->background) {
- if (fc->num_background == fc->max_background) {
+ req->background = 0;
+
+ if (fc->num_background == fc->max_background)
fc->blocked = 0;
- wake_up_all(&fc->blocked_waitq);
- }
+
+ /* Wake up next waiter, if any */
+ if (!fc->blocked && waitqueue_active(&fc->blocked_waitq))
+ wake_up(&fc->blocked_waitq);
+
if (fc->num_background == fc->congestion_threshold &&
fc->connected && fc->bdi_initialized) {
clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
@@ -443,6 +486,7 @@ __acquires(fc->lock)
static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
+ BUG_ON(req->background);
spin_lock(&fc->lock);
if (!fc->connected)
req->out.h.error = -ENOTCONN;
@@ -470,7 +514,7 @@ EXPORT_SYMBOL_GPL(fuse_request_send);
static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
struct fuse_req *req)
{
- req->background = 1;
+ BUG_ON(!req->background);
fc->num_background++;
if (fc->num_background == fc->max_background)
fc->blocked = 1;
@@ -2072,6 +2116,7 @@ void fuse_abort_conn(struct fuse_conn *fc)
if (fc->connected) {
fc->connected = 0;
fc->blocked = 0;
+ fc->initialized = 1;
end_io_requests(fc);
end_queued_requests(fc);
end_polls(fc);
@@ -2090,6 +2135,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
spin_lock(&fc->lock);
fc->connected = 0;
fc->blocked = 0;
+ fc->initialized = 1;
end_queued_requests(fc);
end_polls(fc);
wake_up_all(&fc->blocked_waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index ff15522481d..254df56b847 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1562,10 +1562,9 @@ void fuse_release_nowrite(struct inode *inode)
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
-static int fuse_do_setattr(struct dentry *entry, struct iattr *attr,
- struct file *file)
+int fuse_do_setattr(struct inode *inode, struct iattr *attr,
+ struct file *file)
{
- struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
@@ -1574,9 +1573,6 @@ static int fuse_do_setattr(struct dentry *entry, struct iattr *attr,
loff_t oldsize;
int err;
- if (!fuse_allow_current_process(fc))
- return -EACCES;
-
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
attr->ia_valid |= ATTR_FORCE;
@@ -1671,10 +1667,15 @@ error:
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
{
+ struct inode *inode = entry->d_inode;
+
+ if (!fuse_allow_current_process(get_fuse_conn(inode)))
+ return -EACCES;
+
if (attr->ia_valid & ATTR_FILE)
- return fuse_do_setattr(entry, attr, attr->ia_file);
+ return fuse_do_setattr(inode, attr, attr->ia_file);
else
- return fuse_do_setattr(entry, attr, NULL);
+ return fuse_do_setattr(inode, attr, NULL);
}
static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 82f7ee58124..d1c9b85b3f5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -127,11 +127,13 @@ static void fuse_file_put(struct fuse_file *ff, bool sync)
struct fuse_req *req = ff->reserved_req;
if (sync) {
+ req->background = 0;
fuse_request_send(ff->fc, req);
path_put(&req->misc.release.path);
fuse_put_request(ff->fc, req);
} else {
req->end = fuse_release_end;
+ req->background = 1;
fuse_request_send_background(ff->fc, req);
}
kfree(ff);
@@ -283,6 +285,7 @@ void fuse_sync_release(struct fuse_file *ff, int flags)
WARN_ON(atomic_read(&ff->count) > 1);
fuse_prepare_release(ff, flags, FUSE_RELEASE);
ff->reserved_req->force = 1;
+ ff->reserved_req->background = 0;
fuse_request_send(ff->fc, ff->reserved_req);
fuse_put_request(ff->fc, ff->reserved_req);
kfree(ff);
@@ -492,9 +495,115 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
req->out.args[0].size = count;
}
-static size_t fuse_send_read(struct fuse_req *req, struct file *file,
+static void fuse_release_user_pages(struct fuse_req *req, int write)
+{
+ unsigned i;
+
+ for (i = 0; i < req->num_pages; i++) {
+ struct page *page = req->pages[i];
+ if (write)
+ set_page_dirty_lock(page);
+ put_page(page);
+ }
+}
+
+/**
+ * In case of short read, the caller sets 'pos' to the position of
+ * actual end of fuse request in IO request. Otherwise, if bytes_requested
+ * == bytes_transferred or rw == WRITE, the caller sets 'pos' to -1.
+ *
+ * An example:
+ * User requested DIO read of 64K. It was splitted into two 32K fuse requests,
+ * both submitted asynchronously. The first of them was ACKed by userspace as
+ * fully completed (req->out.args[0].size == 32K) resulting in pos == -1. The
+ * second request was ACKed as short, e.g. only 1K was read, resulting in
+ * pos == 33K.
+ *
+ * Thus, when all fuse requests are completed, the minimal non-negative 'pos'
+ * will be equal to the length of the longest contiguous fragment of
+ * transferred data starting from the beginning of IO request.
+ */
+static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
+{
+ int left;
+
+ spin_lock(&io->lock);
+ if (err)
+ io->err = io->err ? : err;
+ else if (pos >= 0 && (io->bytes < 0 || pos < io->bytes))
+ io->bytes = pos;
+
+ left = --io->reqs;
+ spin_unlock(&io->lock);
+
+ if (!left) {
+ long res;
+
+ if (io->err)
+ res = io->err;
+ else if (io->bytes >= 0 && io->write)
+ res = -EIO;
+ else {
+ res = io->bytes < 0 ? io->size : io->bytes;
+
+ if (!is_sync_kiocb(io->iocb)) {
+ struct path *path = &io->iocb->ki_filp->f_path;
+ struct inode *inode = path->dentry->d_inode;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fc->lock);
+ fi->attr_version = ++fc->attr_version;
+ spin_unlock(&fc->lock);
+ }
+ }
+
+ aio_complete(io->iocb, res, 0);
+ kfree(io);
+ }
+}
+
+static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
+{
+ struct fuse_io_priv *io = req->io;
+ ssize_t pos = -1;
+
+ fuse_release_user_pages(req, !io->write);
+
+ if (io->write) {
+ if (req->misc.write.in.size != req->misc.write.out.size)
+ pos = req->misc.write.in.offset - io->offset +
+ req->misc.write.out.size;
+ } else {
+ if (req->misc.read.in.size != req->out.args[0].size)
+ pos = req->misc.read.in.offset - io->offset +
+ req->out.args[0].size;
+ }
+
+ fuse_aio_complete(io, req->out.h.error, pos);
+}
+
+static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
+ size_t num_bytes, struct fuse_io_priv *io)
+{
+ spin_lock(&io->lock);
+ io->size += num_bytes;
+ io->reqs++;
+ spin_unlock(&io->lock);
+
+ req->io = io;
+ req->end = fuse_aio_complete_req;
+
+ __fuse_get_request(req);
+ fuse_request_send_background(fc, req);
+
+ return num_bytes;
+}
+
+static size_t fuse_send_read(struct fuse_req *req, struct fuse_io_priv *io,
loff_t pos, size_t count, fl_owner_t owner)
{
+ struct file *file = io->file;
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fc;
@@ -505,6 +614,10 @@ static size_t fuse_send_read(struct fuse_req *req, struct file *file,
inarg->read_flags |= FUSE_READ_LOCKOWNER;
inarg->lock_owner = fuse_lock_owner_id(fc, owner);
}
+
+ if (io->async)
+ return fuse_async_req_send(fc, req, count, io);
+
fuse_request_send(fc, req);
return req->out.args[0].size;
}
@@ -525,6 +638,7 @@ static void fuse_read_update_size(struct inode *inode, loff_t size,
static int fuse_readpage(struct file *file, struct page *page)
{
+ struct fuse_io_priv io = { .async = 0, .file = file };
struct inode *inode = page->mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
@@ -557,7 +671,7 @@ static int fuse_readpage(struct file *file, struct page *page)
req->num_pages = 1;
req->pages[0] = page;
req->page_descs[0].length = count;
- num_read = fuse_send_read(req, file, pos, count, NULL);
+ num_read = fuse_send_read(req, &io, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
@@ -662,7 +776,12 @@ static int fuse_readpages_fill(void *_data, struct page *page)
int nr_alloc = min_t(unsigned, data->nr_pages,
FUSE_MAX_PAGES_PER_REQ);
fuse_send_readpages(req, data->file);
- data->req = req = fuse_get_req(fc, nr_alloc);
+ if (fc->async_read)
+ req = fuse_get_req_for_background(fc, nr_alloc);
+ else
+ req = fuse_get_req(fc, nr_alloc);
+
+ data->req = req;
if (IS_ERR(req)) {
unlock_page(page);
return PTR_ERR(req);
@@ -697,7 +816,10 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
data.file = file;
data.inode = inode;
- data.req = fuse_get_req(fc, nr_alloc);
+ if (fc->async_read)
+ data.req = fuse_get_req_for_background(fc, nr_alloc);
+ else
+ data.req = fuse_get_req(fc, nr_alloc);
data.nr_pages = nr_pages;
err = PTR_ERR(data.req);
if (IS_ERR(data.req))
@@ -759,9 +881,10 @@ static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff,
req->out.args[0].value = outarg;
}
-static size_t fuse_send_write(struct fuse_req *req, struct file *file,
+static size_t fuse_send_write(struct fuse_req *req, struct fuse_io_priv *io,
loff_t pos, size_t count, fl_owner_t owner)
{
+ struct file *file = io->file;
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fc;
struct fuse_write_in *inarg = &req->misc.write.in;
@@ -772,6 +895,10 @@ static size_t fuse_send_write(struct fuse_req *req, struct file *file,
inarg->write_flags |= FUSE_WRITE_LOCKOWNER;
inarg->lock_owner = fuse_lock_owner_id(fc, owner);
}
+
+ if (io->async)
+ return fuse_async_req_send(fc, req, count, io);
+
fuse_request_send(fc, req);
return req->misc.write.out.size;
}
@@ -795,11 +922,12 @@ static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
size_t res;
unsigned offset;
unsigned i;
+ struct fuse_io_priv io = { .async = 0, .file = file };
for (i = 0; i < req->num_pages; i++)
fuse_wait_on_page_writeback(inode, req->pages[i]->index);
- res = fuse_send_write(req, file, pos, count, NULL);
+ res = fuse_send_write(req, &io, pos, count, NULL);
offset = req->page_descs[0].offset;
count = res;
@@ -1034,18 +1162,6 @@ out:
return written ? written : err;
}
-static void fuse_release_user_pages(struct fuse_req *req, int write)
-{
- unsigned i;
-
- for (i = 0; i < req->num_pages; i++) {
- struct page *page = req->pages[i];
- if (write)
- set_page_dirty_lock(page);
- put_page(page);
- }
-}
-
static inline void fuse_page_descs_length_init(struct fuse_req *req,
unsigned index, unsigned nr_pages)
{
@@ -1147,10 +1263,11 @@ static inline int fuse_iter_npages(const struct iov_iter *ii_p)
return min(npages, FUSE_MAX_PAGES_PER_REQ);
}
-ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
+ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
unsigned long nr_segs, size_t count, loff_t *ppos,
int write)
{
+ struct file *file = io->file;
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fc;
size_t nmax = write ? fc->max_write : fc->max_read;
@@ -1176,11 +1293,12 @@ ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
}
if (write)
- nres = fuse_send_write(req, file, pos, nbytes, owner);
+ nres = fuse_send_write(req, io, pos, nbytes, owner);
else
- nres = fuse_send_read(req, file, pos, nbytes, owner);
+ nres = fuse_send_read(req, io, pos, nbytes, owner);
- fuse_release_user_pages(req, !write);
+ if (!io->async)
+ fuse_release_user_pages(req, !write);
if (req->out.h.error) {
if (!res)
res = req->out.h.error;
@@ -1210,17 +1328,19 @@ ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
}
EXPORT_SYMBOL_GPL(fuse_direct_io);
-static ssize_t __fuse_direct_read(struct file *file, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos)
+static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
+ const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos,
+ size_t count)
{
ssize_t res;
+ struct file *file = io->file;
struct inode *inode = file_inode(file);
if (is_bad_inode(inode))
return -EIO;
- res = fuse_direct_io(file, iov, nr_segs, iov_length(iov, nr_segs),
- ppos, 0);
+ res = fuse_direct_io(io, iov, nr_segs, count, ppos, 0);
fuse_invalidate_attr(inode);
@@ -1230,23 +1350,23 @@ static ssize_t __fuse_direct_read(struct file *file, const struct iovec *iov,
static ssize_t fuse_direct_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
+ struct fuse_io_priv io = { .async = 0, .file = file };
struct iovec iov = { .iov_base = buf, .iov_len = count };
- return __fuse_direct_read(file, &iov, 1, ppos);
+ return __fuse_direct_read(&io, &iov, 1, ppos, count);
}
-static ssize_t __fuse_direct_write(struct file *file, const struct iovec *iov,
+static ssize_t __fuse_direct_write(struct fuse_io_priv *io,
+ const struct iovec *iov,
unsigned long nr_segs, loff_t *ppos)
{
+ struct file *file = io->file;
struct inode *inode = file_inode(file);
size_t count = iov_length(iov, nr_segs);
ssize_t res;
res = generic_write_checks(file, ppos, &count, 0);
- if (!res) {
- res = fuse_direct_io(file, iov, nr_segs, count, ppos, 1);
- if (res > 0)
- fuse_write_update_size(inode, *ppos);
- }
+ if (!res)
+ res = fuse_direct_io(io, iov, nr_segs, count, ppos, 1);
fuse_invalidate_attr(inode);
@@ -1259,13 +1379,16 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
struct inode *inode = file_inode(file);
ssize_t res;
+ struct fuse_io_priv io = { .async = 0, .file = file };
if (is_bad_inode(inode))
return -EIO;
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
- res = __fuse_direct_write(file, &iov, 1, ppos);
+ res = __fuse_direct_write(&io, &iov, 1, ppos);
+ if (res > 0)
+ fuse_write_update_size(inode, *ppos);
mutex_unlock(&inode->i_mutex);
return res;
@@ -1374,6 +1497,7 @@ static int fuse_writepage_locked(struct page *page)
if (!req)
goto err;
+ req->background = 1; /* writeback always goes to bg_queue */
tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (!tmp_page)
goto err_free;
@@ -2227,21 +2351,93 @@ int fuse_notify_poll_wakeup(struct fuse_conn *fc,
return 0;
}
+static void fuse_do_truncate(struct file *file)
+{
+ struct inode *inode = file->f_mapping->host;
+ struct iattr attr;
+
+ attr.ia_valid = ATTR_SIZE;
+ attr.ia_size = i_size_read(inode);
+
+ attr.ia_file = file;
+ attr.ia_valid |= ATTR_FILE;
+
+ fuse_do_setattr(inode, &attr, file);
+}
+
static ssize_t
fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
{
ssize_t ret = 0;
- struct file *file = NULL;
+ struct file *file = iocb->ki_filp;
+ struct fuse_file *ff = file->private_data;
loff_t pos = 0;
+ struct inode *inode;
+ loff_t i_size;
+ size_t count = iov_length(iov, nr_segs);
+ struct fuse_io_priv *io;
- file = iocb->ki_filp;
pos = offset;
+ inode = file->f_mapping->host;
+ i_size = i_size_read(inode);
+
+ /* optimization for short read */
+ if (rw != WRITE && offset + count > i_size) {
+ if (offset >= i_size)
+ return 0;
+ count = i_size - offset;
+ }
+
+ io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
+ if (!io)
+ return -ENOMEM;
+ spin_lock_init(&io->lock);
+ io->reqs = 1;
+ io->bytes = -1;
+ io->size = 0;
+ io->offset = offset;
+ io->write = (rw == WRITE);
+ io->err = 0;
+ io->file = file;
+ /*
+ * By default, we want to optimize all I/Os with async request
+ * submission to the client filesystem if supported.
+ */
+ io->async = ff->fc->async_dio;
+ io->iocb = iocb;
+
+ /*
+ * We cannot asynchronously extend the size of a file. We have no method
+ * to wait on real async I/O requests, so we must submit this request
+ * synchronously.
+ */
+ if (!is_sync_kiocb(iocb) && (offset + count > i_size))
+ io->async = false;
if (rw == WRITE)
- ret = __fuse_direct_write(file, iov, nr_segs, &pos);
+ ret = __fuse_direct_write(io, iov, nr_segs, &pos);
else
- ret = __fuse_direct_read(file, iov, nr_segs, &pos);
+ ret = __fuse_direct_read(io, iov, nr_segs, &pos, count);
+
+ if (io->async) {
+ fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
+
+ /* we have a non-extending, async request, so return */
+ if (ret > 0 && !is_sync_kiocb(iocb))
+ return -EIOCBQUEUED;
+
+ ret = wait_on_sync_kiocb(iocb);
+ } else {
+ kfree(io);
+ }
+
+ if (rw == WRITE) {
+ if (ret > 0)
+ fuse_write_update_size(inode, pos);
+ else if (ret < 0 && offset + count > i_size)
+ fuse_do_truncate(file);
+ }
return ret;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 6aeba864f07..fde7249a3a9 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -228,6 +228,20 @@ enum fuse_req_state {
FUSE_REQ_FINISHED
};
+/** The request IO state (for asynchronous processing) */
+struct fuse_io_priv {
+ int async;
+ spinlock_t lock;
+ unsigned reqs;
+ ssize_t bytes;
+ size_t size;
+ __u64 offset;
+ bool write;
+ int err;
+ struct kiocb *iocb;
+ struct file *file;
+};
+
/**
* A request to the client
*/
@@ -332,6 +346,9 @@ struct fuse_req {
/** Inode used in the request or NULL */
struct inode *inode;
+ /** AIO control block */
+ struct fuse_io_priv *io;
+
/** Link on fi->writepages */
struct list_head writepages_entry;
@@ -417,6 +434,10 @@ struct fuse_conn {
/** Batching of FORGET requests (positive indicates FORGET batch) */
int forget_batch;
+ /** Flag indicating that INIT reply has been received. Allocating
+ * any fuse request will be suspended until the flag is set */
+ int initialized;
+
/** Flag indicating if connection is blocked. This will be
the case before the INIT reply is received, and if there
are too many outstading backgrounds requests */
@@ -520,6 +541,9 @@ struct fuse_conn {
/** Does the filesystem want adaptive readdirplus? */
unsigned readdirplus_auto:1;
+ /** Does the filesystem support asynchronous direct-IO submission? */
+ unsigned async_dio:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -708,6 +732,13 @@ void fuse_request_free(struct fuse_req *req);
* caller should specify # elements in req->pages[] explicitly
*/
struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages);
+struct fuse_req *fuse_get_req_for_background(struct fuse_conn *fc,
+ unsigned npages);
+
+/*
+ * Increment reference count on request
+ */
+void __fuse_get_request(struct fuse_req *req);
/**
* Get a request, may fail with -ENOMEM,
@@ -823,7 +854,7 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
bool isdir);
-ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
+ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
unsigned long nr_segs, size_t count, loff_t *ppos,
int write);
long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
@@ -835,4 +866,7 @@ int fuse_dev_release(struct inode *inode, struct file *file);
void fuse_write_update_size(struct inode *inode, loff_t pos);
+int fuse_do_setattr(struct inode *inode, struct iattr *attr,
+ struct file *file);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 137185c3884..6201f81e4d3 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -346,6 +346,7 @@ static void fuse_send_destroy(struct fuse_conn *fc)
fc->destroy_req = NULL;
req->in.h.opcode = FUSE_DESTROY;
req->force = 1;
+ req->background = 0;
fuse_request_send(fc, req);
fuse_put_request(fc, req);
}
@@ -362,6 +363,7 @@ void fuse_conn_kill(struct fuse_conn *fc)
spin_lock(&fc->lock);
fc->connected = 0;
fc->blocked = 0;
+ fc->initialized = 1;
spin_unlock(&fc->lock);
/* Flush all readers on this fs */
kill_fasync(&fc->fasync, SIGIO, POLL_IN);
@@ -581,7 +583,8 @@ void fuse_conn_init(struct fuse_conn *fc)
fc->khctr = 0;
fc->polled_files = RB_ROOT;
fc->reqctr = 0;
- fc->blocked = 1;
+ fc->blocked = 0;
+ fc->initialized = 0;
fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
}
@@ -868,6 +871,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->do_readdirplus = 1;
if (arg->flags & FUSE_READDIRPLUS_AUTO)
fc->readdirplus_auto = 1;
+ if (arg->flags & FUSE_ASYNC_DIO)
+ fc->async_dio = 1;
} else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
fc->no_lock = 1;
@@ -880,7 +885,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->max_write = max_t(unsigned, 4096, fc->max_write);
fc->conn_init = 1;
}
- fc->blocked = 0;
+ fc->initialized = 1;
wake_up_all(&fc->blocked_waitq);
}
@@ -895,7 +900,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
- FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO;
+ FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
@@ -1043,6 +1048,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
init_req = fuse_request_alloc(0);
if (!init_req)
goto err_put_root;
+ init_req->background = 1;
if (is_bdev) {
fc->destroy_req = fuse_request_alloc(0);
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 17c22a8fd40..e0101b6fb0d 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -176,7 +176,9 @@ static int hfs_dir_release(struct inode *inode, struct file *file)
{
struct hfs_readdir_data *rd = file->private_data;
if (rd) {
+ mutex_lock(&inode->i_mutex);
list_del(&rd->list);
+ mutex_unlock(&inode->i_mutex);
kfree(rd);
}
return 0;
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index f4891bde885..8485978993e 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -173,7 +173,7 @@ struct bl_msg_hdr {
/* blocklayoutdev.c */
ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-int nfs4_blkdev_put(struct block_device *bdev);
+void nfs4_blkdev_put(struct block_device *bdev);
struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
struct pnfs_device *dev);
int nfs4_blk_process_layoutget(struct pnfs_layout_hdr *lo,
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index a86c5bdad9e..04303b5c936 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -56,11 +56,11 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
/*
* Release the block device
*/
-int nfs4_blkdev_put(struct block_device *bdev)
+void nfs4_blkdev_put(struct block_device *bdev)
{
dprintk("%s for device %d:%d\n", __func__, MAJOR(bdev->bd_dev),
MINOR(bdev->bd_dev));
- return blkdev_put(bdev, FMODE_READ);
+ blkdev_put(bdev, FMODE_READ);
}
ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index 6fc7b5cae92..8999cfddd86 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -88,14 +88,8 @@ out:
*/
static void nfs4_blk_metadev_release(struct pnfs_block_dev *bdev)
{
- int rv;
-
dprintk("%s Releasing\n", __func__);
- rv = nfs4_blkdev_put(bdev->bm_mdev);
- if (rv)
- printk(KERN_ERR "NFS: %s nfs4_blkdev_put returns %d\n",
- __func__, rv);
-
+ nfs4_blkdev_put(bdev->bm_mdev);
dev_remove(bdev->net, bdev->bm_mdev->bd_dev);
}
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index afcadcc03e8..742fdd4c209 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -97,7 +97,7 @@ static int flush_commit_list(struct super_block *s,
static int can_dirty(struct reiserfs_journal_cnode *cn);
static int journal_join(struct reiserfs_transaction_handle *th,
struct super_block *sb, unsigned long nblocks);
-static int release_journal_dev(struct super_block *super,
+static void release_journal_dev(struct super_block *super,
struct reiserfs_journal *journal);
static int dirty_one_transaction(struct super_block *s,
struct reiserfs_journal_list *jl);
@@ -2532,23 +2532,13 @@ static void journal_list_init(struct super_block *sb)
SB_JOURNAL(sb)->j_current_jl = alloc_journal_list(sb);
}
-static int release_journal_dev(struct super_block *super,
+static void release_journal_dev(struct super_block *super,
struct reiserfs_journal *journal)
{
- int result;
-
- result = 0;
-
if (journal->j_dev_bd != NULL) {
- result = blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
+ blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
journal->j_dev_bd = NULL;
}
-
- if (result != 0) {
- reiserfs_warning(super, "sh-457",
- "Cannot release journal device: %i", result);
- }
- return result;
}
static int journal_init_dev(struct super_block *super,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-29 18:35:45 +0000