summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c166
-rw-r--r--fs/buffer.c145
-rw-r--r--fs/cifs/file.c6
-rw-r--r--fs/cifs/readdir.c5
-rw-r--r--fs/cifs/smb1ops.c3
-rw-r--r--fs/direct-io.c8
-rw-r--r--fs/ext3/balloc.c5
-rw-r--r--fs/file.c15
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/inode.c16
-rw-r--r--fs/internal.h1
-rw-r--r--fs/jbd/transaction.c2
-rw-r--r--fs/jffs2/file.c39
-rw-r--r--fs/namei.c5
-rw-r--r--fs/nfs/dir.c7
-rw-r--r--fs/notify/fanotify/fanotify_user.c3
-rw-r--r--fs/proc/base.c114
-rw-r--r--fs/pstore/platform.c3
-rw-r--r--fs/reiserfs/inode.c10
-rw-r--r--fs/reiserfs/stree.c4
-rw-r--r--fs/reiserfs/super.c60
-rw-r--r--fs/ubifs/find.c12
-rw-r--r--fs/ubifs/lprops.c6
-rw-r--r--fs/ubifs/ubifs.h3
-rw-r--r--fs/xfs/xfs_aops.c54
-rw-r--r--fs/xfs/xfs_attr_leaf.c20
-rw-r--r--fs/xfs/xfs_buf.c14
27 files changed, 463 insertions, 265 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1a1e5e3..ab3a456 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -70,19 +70,6 @@ static void bdev_inode_switch_bdi(struct inode *inode,
spin_unlock(&dst->wb.list_lock);
}
-sector_t blkdev_max_block(struct block_device *bdev)
-{
- sector_t retval = ~((sector_t)0);
- loff_t sz = i_size_read(bdev->bd_inode);
-
- if (sz) {
- unsigned int size = block_size(bdev);
- unsigned int sizebits = blksize_bits(size);
- retval = (sz >> sizebits);
- }
- return retval;
-}
-
/* Kill _all_ buffers and pagecache , dirty or not.. */
void kill_bdev(struct block_device *bdev)
{
@@ -116,8 +103,6 @@ EXPORT_SYMBOL(invalidate_bdev);
int set_blocksize(struct block_device *bdev, int size)
{
- struct address_space *mapping;
-
/* Size must be a power of two, and between 512 and PAGE_SIZE */
if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
return -EINVAL;
@@ -126,19 +111,6 @@ int set_blocksize(struct block_device *bdev, int size)
if (size < bdev_logical_block_size(bdev))
return -EINVAL;
- /* Prevent starting I/O or mapping the device */
- percpu_down_write(&bdev->bd_block_size_semaphore);
-
- /* Check that the block device is not memory mapped */
- mapping = bdev->bd_inode->i_mapping;
- mutex_lock(&mapping->i_mmap_mutex);
- if (mapping_mapped(mapping)) {
- mutex_unlock(&mapping->i_mmap_mutex);
- percpu_up_write(&bdev->bd_block_size_semaphore);
- return -EBUSY;
- }
- mutex_unlock(&mapping->i_mmap_mutex);
-
/* Don't change the size if it is same as current */
if (bdev->bd_block_size != size) {
sync_blockdev(bdev);
@@ -146,9 +118,6 @@ int set_blocksize(struct block_device *bdev, int size)
bdev->bd_inode->i_blkbits = blksize_bits(size);
kill_bdev(bdev);
}
-
- percpu_up_write(&bdev->bd_block_size_semaphore);
-
return 0;
}
@@ -181,52 +150,12 @@ static int
blkdev_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
- if (iblock >= blkdev_max_block(I_BDEV(inode))) {
- if (create)
- return -EIO;
-
- /*
- * for reads, we're just trying to fill a partial page.
- * return a hole, they will have to call get_block again
- * before they can fill it, and they will get -EIO at that
- * time
- */
- return 0;
- }
bh->b_bdev = I_BDEV(inode);
bh->b_blocknr = iblock;
set_buffer_mapped(bh);
return 0;
}
-static int
-blkdev_get_blocks(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create)
-{
- sector_t end_block = blkdev_max_block(I_BDEV(inode));
- unsigned long max_blocks = bh->b_size >> inode->i_blkbits;
-
- if ((iblock + max_blocks) > end_block) {
- max_blocks = end_block - iblock;
- if ((long)max_blocks <= 0) {
- if (create)
- return -EIO; /* write fully beyond EOF */
- /*
- * It is a read which is fully beyond EOF. We return
- * a !buffer_mapped buffer
- */
- max_blocks = 0;
- }
- }
-
- bh->b_bdev = I_BDEV(inode);
- bh->b_blocknr = iblock;
- bh->b_size = max_blocks << inode->i_blkbits;
- if (max_blocks)
- set_buffer_mapped(bh);
- return 0;
-}
-
static ssize_t
blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
@@ -235,7 +164,7 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
struct inode *inode = file->f_mapping->host;
return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
- nr_segs, blkdev_get_blocks, NULL, NULL, 0);
+ nr_segs, blkdev_get_block, NULL, NULL, 0);
}
int __sync_blockdev(struct block_device *bdev, int wait)
@@ -459,12 +388,6 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
if (!ei)
return NULL;
-
- if (unlikely(percpu_init_rwsem(&ei->bdev.bd_block_size_semaphore))) {
- kmem_cache_free(bdev_cachep, ei);
- return NULL;
- }
-
return &ei->vfs_inode;
}
@@ -473,8 +396,6 @@ static void bdev_i_callback(struct rcu_head *head)
struct inode *inode = container_of(head, struct inode, i_rcu);
struct bdev_inode *bdi = BDEV_I(inode);
- percpu_free_rwsem(&bdi->bdev.bd_block_size_semaphore);
-
kmem_cache_free(bdev_cachep, bdi);
}
@@ -1593,22 +1514,6 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
return blkdev_ioctl(bdev, mode, cmd, arg);
}
-ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
- unsigned long nr_segs, loff_t pos)
-{
- ssize_t ret;
- struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
-
- percpu_down_read(&bdev->bd_block_size_semaphore);
-
- ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
-
- percpu_up_read(&bdev->bd_block_size_semaphore);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(blkdev_aio_read);
-
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
@@ -1620,16 +1525,12 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct blk_plug plug;
ssize_t ret;
BUG_ON(iocb->ki_pos != pos);
blk_start_plug(&plug);
-
- percpu_down_read(&bdev->bd_block_size_semaphore);
-
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
if (ret > 0 || ret == -EIOCBQUEUED) {
ssize_t err;
@@ -1638,62 +1539,27 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
if (err < 0 && ret > 0)
ret = err;
}
-
- percpu_up_read(&bdev->bd_block_size_semaphore);
-
blk_finish_plug(&plug);
-
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_aio_write);
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
-{
- int ret;
- struct block_device *bdev = I_BDEV(file->f_mapping->host);
-
- percpu_down_read(&bdev->bd_block_size_semaphore);
-
- ret = generic_file_mmap(file, vma);
-
- percpu_up_read(&bdev->bd_block_size_semaphore);
-
- return ret;
-}
-
-static ssize_t blkdev_splice_read(struct file *file, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
-{
- ssize_t ret;
- struct block_device *bdev = I_BDEV(file->f_mapping->host);
-
- percpu_down_read(&bdev->bd_block_size_semaphore);
-
- ret = generic_file_splice_read(file, ppos, pipe, len, flags);
-
- percpu_up_read(&bdev->bd_block_size_semaphore);
-
- return ret;
-}
-
-static ssize_t blkdev_splice_write(struct pipe_inode_info *pipe,
- struct file *file, loff_t *ppos, size_t len,
- unsigned int flags)
+static ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
{
- ssize_t ret;
- struct block_device *bdev = I_BDEV(file->f_mapping->host);
-
- percpu_down_read(&bdev->bd_block_size_semaphore);
-
- ret = generic_file_splice_write(pipe, file, ppos, len, flags);
+ struct file *file = iocb->ki_filp;
+ struct inode *bd_inode = file->f_mapping->host;
+ loff_t size = i_size_read(bd_inode);
- percpu_up_read(&bdev->bd_block_size_semaphore);
+ if (pos >= size)
+ return 0;
- return ret;
+ size -= pos;
+ if (size < INT_MAX)
+ nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size);
+ return generic_file_aio_read(iocb, iov, nr_segs, pos);
}
-
/*
* Try to release a page associated with block device when the system
* is under memory pressure.
@@ -1724,16 +1590,16 @@ const struct file_operations def_blk_fops = {
.llseek = block_llseek,
.read = do_sync_read,
.write = do_sync_write,
- .aio_read = blkdev_aio_read,
+ .aio_read = blkdev_aio_read,
.aio_write = blkdev_aio_write,
- .mmap = blkdev_mmap,
+ .mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
- .splice_read = blkdev_splice_read,
- .splice_write = blkdev_splice_write,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
};
int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
diff --git a/fs/buffer.c b/fs/buffer.c
index b5f0442..ec0aca8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -911,6 +911,18 @@ link_dev_buffers(struct page *page, struct buffer_head *head)
attach_page_buffers(page, head);
}
+static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size)
+{
+ sector_t retval = ~((sector_t)0);
+ loff_t sz = i_size_read(bdev->bd_inode);
+
+ if (sz) {
+ unsigned int sizebits = blksize_bits(size);
+ retval = (sz >> sizebits);
+ }
+ return retval;
+}
+
/*
* Initialise the state of a blockdev page's buffers.
*/
@@ -921,7 +933,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
int uptodate = PageUptodate(page);
- sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode));
+ sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size);
do {
if (!buffer_mapped(bh)) {
@@ -1553,6 +1565,28 @@ void unmap_underlying_metadata(struct block_device *bdev, sector_t block)
EXPORT_SYMBOL(unmap_underlying_metadata);
/*
+ * Size is a power-of-two in the range 512..PAGE_SIZE,
+ * and the case we care about most is PAGE_SIZE.
+ *
+ * So this *could* possibly be written with those
+ * constraints in mind (relevant mostly if some
+ * architecture has a slow bit-scan instruction)
+ */
+static inline int block_size_bits(unsigned int blocksize)
+{
+ return ilog2(blocksize);
+}
+
+static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state)
+{
+ BUG_ON(!PageLocked(page));
+
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state);
+ return page_buffers(page);
+}
+
+/*
* NOTE! All mapped/uptodate combinations are valid:
*
* Mapped Uptodate Meaning
@@ -1589,19 +1623,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
sector_t block;
sector_t last_block;
struct buffer_head *bh, *head;
- const unsigned blocksize = 1 << inode->i_blkbits;
+ unsigned int blocksize, bbits;
int nr_underway = 0;
int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC : WRITE);
- BUG_ON(!PageLocked(page));
-
- last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
-
- if (!page_has_buffers(page)) {
- create_empty_buffers(page, blocksize,
+ head = create_page_buffers(page, inode,
(1 << BH_Dirty)|(1 << BH_Uptodate));
- }
/*
* Be very careful. We have no exclusion from __set_page_dirty_buffers
@@ -1613,9 +1641,12 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
* handle that here by just cleaning them.
*/
- block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- head = page_buffers(page);
bh = head;
+ blocksize = bh->b_size;
+ bbits = block_size_bits(blocksize);
+
+ block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+ last_block = (i_size_read(inode) - 1) >> bbits;
/*
* Get all the dirty buffers mapped to disk addresses and
@@ -1806,12 +1837,10 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
BUG_ON(to > PAGE_CACHE_SIZE);
BUG_ON(from > to);
- blocksize = 1 << inode->i_blkbits;
- if (!page_has_buffers(page))
- create_empty_buffers(page, blocksize, 0);
- head = page_buffers(page);
+ head = create_page_buffers(page, inode, 0);
+ blocksize = head->b_size;
+ bbits = block_size_bits(blocksize);
- bbits = inode->i_blkbits;
block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
for(bh = head, block_start = 0; bh != head || !block_start;
@@ -1881,11 +1910,11 @@ static int __block_commit_write(struct inode *inode, struct page *page,
unsigned blocksize;
struct buffer_head *bh, *head;
- blocksize = 1 << inode->i_blkbits;
+ bh = head = page_buffers(page);
+ blocksize = bh->b_size;
- for(bh = head = page_buffers(page), block_start = 0;
- bh != head || !block_start;
- block_start=block_end, bh = bh->b_this_page) {
+ block_start = 0;
+ do {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
@@ -1895,7 +1924,10 @@ static int __block_commit_write(struct inode *inode, struct page *page,
mark_buffer_dirty(bh);
}
clear_buffer_new(bh);
- }
+
+ block_start = block_end;
+ bh = bh->b_this_page;
+ } while (bh != head);
/*
* If this is a partial write which happened to make all buffers
@@ -2020,7 +2052,6 @@ EXPORT_SYMBOL(generic_write_end);
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
unsigned long from)
{
- struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
unsigned to;
struct buffer_head *bh, *head;
@@ -2029,13 +2060,13 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
if (!page_has_buffers(page))
return 0;
- blocksize = 1 << inode->i_blkbits;
+ head = page_buffers(page);
+ blocksize = head->b_size;
to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
to = from + to;
if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
return 0;
- head = page_buffers(page);
bh = head;
block_start = 0;
do {
@@ -2068,18 +2099,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
struct inode *inode = page->mapping->host;
sector_t iblock, lblock;
struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
- unsigned int blocksize;
+ unsigned int blocksize, bbits;
int nr, i;
int fully_mapped = 1;
- BUG_ON(!PageLocked(page));
- blocksize = 1 << inode->i_blkbits;
- if (!page_has_buffers(page))
- create_empty_buffers(page, blocksize, 0);
- head = page_buffers(page);
+ head = create_page_buffers(page, inode, 0);
+ blocksize = head->b_size;
+ bbits = block_size_bits(blocksize);
- iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits;
+ iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits);
+ lblock = (i_size_read(inode)+blocksize-1) >> bbits;
bh = head;
nr = 0;
i = 0;
@@ -2864,6 +2893,55 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
bio_put(bio);
}
+/*
+ * This allows us to do IO even on the odd last sectors
+ * of a device, even if the bh block size is some multiple
+ * of the physical sector size.
+ *
+ * We'll just truncate the bio to the size of the device,
+ * and clear the end of the buffer head manually.
+ *
+ * Truly out-of-range accesses will turn into actual IO
+ * errors, this only handles the "we need to be able to
+ * do IO at the final sector" case.
+ */
+static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
+{
+ sector_t maxsector;
+ unsigned bytes;
+
+ maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
+ if (!maxsector)
+ return;
+
+ /*
+ * If the *whole* IO is past the end of the device,
+ * let it through, and the IO layer will turn it into
+ * an EIO.
+ */
+ if (unlikely(bio->bi_sector >= maxsector))
+ return;
+
+ maxsector -= bio->bi_sector;
+ bytes = bio->bi_size;
+ if (likely((bytes >> 9) <= maxsector))
+ return;
+
+ /* Uhhuh. We've got a bh that straddles the device size! */
+ bytes = maxsector << 9;
+
+ /* Truncate the bio.. */
+ bio->bi_size = bytes;
+ bio->bi_io_vec[0].bv_len = bytes;
+
+ /* ..and clear the end of the buffer for reads */
+ if ((rw & RW_MASK) == READ) {
+ void *kaddr = kmap_atomic(bh->b_page);
+ memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes);
+ kunmap_atomic(kaddr);
+ }
+}
+
int submit_bh(int rw, struct buffer_head * bh)
{
struct bio *bio;
@@ -2900,6 +2978,9 @@ int submit_bh(int rw, struct buffer_head * bh)
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
+ /* Take care of bh's that straddle the end of the device */
+ guard_bh_eod(rw, bio, bh);
+
bio_get(bio);
submit_bio(rw, bio);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index edb25b4..70b6f4c 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1794,7 +1794,6 @@ static int cifs_writepages(struct address_space *mapping,
struct TCP_Server_Info *server;
struct page *page;
int rc = 0;
- loff_t isize = i_size_read(mapping->host);
/*
* If wsize is smaller than the page cache size, default to writing
@@ -1899,7 +1898,7 @@ retry:
*/
set_page_writeback(page);
- if (page_offset(page) >= isize) {
+ if (page_offset(page) >= i_size_read(mapping->host)) {
done = true;
unlock_page(page);
end_page_writeback(page);
@@ -1932,7 +1931,8 @@ retry:
wdata->offset = page_offset(wdata->pages[0]);
wdata->pagesz = PAGE_CACHE_SIZE;
wdata->tailsz =
- min(isize - page_offset(wdata->pages[nr_pages - 1]),
+ min(i_size_read(mapping->host) -
+ page_offset(wdata->pages[nr_pages - 1]),
(loff_t)PAGE_CACHE_SIZE);
wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) +
wdata->tailsz;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index f9b5d3d..1c576e8 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -86,14 +86,17 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
dentry = d_lookup(parent, name);
if (dentry) {
+ int err;
inode = dentry->d_inode;
/* update inode in place if i_ino didn't change */
if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) {
cifs_fattr_to_inode(inode, fattr);
return dentry;
}
- d_drop(dentry);
+ err = d_invalidate(dentry);
dput(dentry);
+ if (err)
+ return NULL;
}
dentry = d_alloc(parent, name);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 56cc4be..34cea27 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -766,7 +766,6 @@ smb_set_file_info(struct inode *inode, const char *full_path,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
struct cifs_tcon *tcon;
- FILE_BASIC_INFO info_buf;
/* if the file is already open for write, just use that fileid */
open_file = find_writable_file(cinode, true);
@@ -817,7 +816,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
netpid = current->tgid;
set_via_filehandle:
- rc = CIFSSMBSetFileInfo(xid, tcon, &info_buf, netfid, netpid);
+ rc = CIFSSMBSetFileInfo(xid, tcon, buf, netfid, netpid);
if (!rc)
cinode->cifsAttrs = le32_to_cpu(buf->Attributes);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index f86c720..cf5b44b 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -540,6 +540,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
sector_t fs_endblk; /* Into file, in filesystem-sized blocks */
unsigned long fs_count; /* Number of filesystem-sized blocks */
int create;
+ unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor;
/*
* If there was a memory error and we've overwritten all the
@@ -554,7 +555,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
fs_count = fs_endblk - fs_startblk + 1;
map_bh->b_state = 0;
- map_bh->b_size = fs_count << dio->inode->i_blkbits;
+ map_bh->b_size = fs_count << i_blkbits;
/*
* For writes inside i_size on a DIO_SKIP_HOLES filesystem we
@@ -1053,7 +1054,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
int seg;
size_t size;
unsigned long addr;
- unsigned blkbits = inode->i_blkbits;
+ unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
+ unsigned blkbits = i_blkbits;
unsigned blocksize_mask = (1 << blkbits) - 1;
ssize_t retval = -EINVAL;
loff_t end = offset;
@@ -1149,7 +1151,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
dio->inode = inode;
dio->rw = rw;
sdio.blkbits = blkbits;
- sdio.blkfactor = inode->i_blkbits - blkbits;
+ sdio.blkfactor = i_blkbits - blkbits;
sdio.block_in_file = offset >> blkbits;
sdio.get_block = get_block;
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 7320a66..22548f5 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -2101,8 +2101,9 @@ int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
end = start + (range->len >> sb->s_blocksize_bits) - 1;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) ||
- unlikely(start >= max_blks))
+ if (minlen > EXT3_BLOCKS_PER_GROUP(sb) ||
+ start >= max_blks ||
+ range->len < sb->s_blocksize)
return -EINVAL;
if (end >= max_blks)
end = max_blks - 1;
diff --git a/fs/file.c b/fs/file.c
index 708d997..eff2316 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -685,7 +685,6 @@ void do_close_on_exec(struct files_struct *files)
struct fdtable *fdt;
/* exec unshares first */
- BUG_ON(atomic_read(&files->count) != 1);
spin_lock(&files->file_lock);
for (i = 0; ; i++) {
unsigned long set;
@@ -995,16 +994,18 @@ int iterate_fd(struct files_struct *files, unsigned n,
const void *p)
{
struct fdtable *fdt;
- struct file *file;
int res = 0;
if (!files)
return 0;
spin_lock(&files->file_lock);
- fdt = files_fdtable(files);
- while (!res && n < fdt->max_fds) {
- file = rcu_dereference_check_fdtable(files, fdt->fd[n++]);
- if (file)
- res = f(p, file, n);
+ for (fdt = files_fdtable(files); n < fdt->max_fds; n++) {
+ struct file *file;
+ file = rcu_dereference_check_fdtable(files, fdt->fd[n]);
+ if (!file)
+ continue;
+ res = f(p, file, n);
+ if (res)
+ break;
}
spin_unlock(&files->file_lock);
return res;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 51ea267..3e3422f 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -228,6 +228,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
static void inode_sync_complete(struct inode *inode)
{
inode->i_state &= ~I_SYNC;
+ /* If inode is clean an unused, put it into LRU now... */
+ inode_add_lru(inode);
/* Waiters must see I_SYNC cleared before being woken up */
smp_mb();
wake_up_bit(&inode->i_state, __I_SYNC);
diff --git a/fs/inode.c b/fs/inode.c
index b03c719..64999f1 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -408,6 +408,19 @@ static void inode_lru_list_add(struct inode *inode)
spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
+/*
+ * Add inode to LRU if needed (inode is unused and clean).
+ *
+ * Needs inode->i_lock held.
+ */
+void inode_add_lru(struct inode *inode)
+{
+ if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) &&
+ !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE)
+ inode_lru_list_add(inode);
+}
+
+
static void inode_lru_list_del(struct inode *inode)
{
spin_lock(&inode->i_sb->s_inode_lru_lock);
@@ -1390,8 +1403,7 @@ static void iput_final(struct inode *inode)
if (!drop && (sb->s_flags & MS_ACTIVE)) {
inode->i_state |= I_REFERENCED;
- if (!(inode->i_state & (I_DIRTY|I_SYNC)))
- inode_lru_list_add(inode);
+ inode_add_lru(inode);
spin_unlock(&inode->i_lock);
return;
}
diff --git a/fs/internal.h b/fs/internal.h
index 916b7cb..2f6af7f 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -110,6 +110,7 @@ extern int open_check_o_direct(struct file *f);
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
+extern void inode_add_lru(struct inode *inode);
/*
* fs-writeback.c
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 78b7f84..7f5120b 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1961,7 +1961,9 @@ retry:
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
spin_unlock(&journal->j_state_lock);
+ unlock_buffer(bh);
log_wait_commit(journal, tid);
+ lock_buffer(bh);
goto retry;
}
/*
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 60ef3fb..1506673 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
struct page *pg;
struct inode *inode = mapping->host;
struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
+ struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+ struct jffs2_raw_inode ri;
+ uint32_t alloc_len = 0;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
uint32_t pageofs = index << PAGE_CACHE_SHIFT;
int ret = 0;
+ jffs2_dbg(1, "%s()\n", __func__);
+
+ if (pageofs > inode->i_size) {
+ ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+ ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+ if (ret)
+ return ret;
+ }
+
+ mutex_lock(&f->sem);
pg = grab_cache_page_write_begin(mapping, index, flags);
- if (!pg)
+ if (!pg) {
+ if (alloc_len)
+ jffs2_complete_reservation(c);
+ mutex_unlock(&f->sem);
return -ENOMEM;
+ }
*pagep = pg;
- jffs2_dbg(1, "%s()\n", __func__);
-
- if (pageofs > inode->i_size) {
+ if (alloc_len) {
/* Make new hole frag from old EOF to new page */
- struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
- struct jffs2_raw_inode ri;
struct jffs2_full_dnode *fn;
- uint32_t alloc_len;
jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
(unsigned int)inode->i_size, pageofs);
- ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
- ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
- if (ret)
- goto out_page;
-
- mutex_lock(&f->sem);
memset(&ri, 0, sizeof(ri));
ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
if (IS_ERR(fn)) {
ret = PTR_ERR(fn);
jffs2_complete_reservation(c);
- mutex_unlock(&f->sem);
goto out_page;
}
ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
jffs2_mark_node_obsolete(c, fn->raw);
jffs2_free_full_dnode(fn);
jffs2_complete_reservation(c);
- mutex_unlock(&f->sem);
goto out_page;
}
jffs2_complete_reservation(c);
inode->i_size = pageofs;
- mutex_unlock(&f->sem);
}
/*
@@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
* case of a short-copy.
*/
if (!PageUptodate(pg)) {
- mutex_lock(&f->sem);
ret = jffs2_do_readpage_nolock(inode, pg);
- mutex_unlock(&f->sem);
if (ret)
goto out_page;
}
+ mutex_unlock(&f->sem);
jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
return ret;
out_page:
unlock_page(pg);
page_cache_release(pg);
+ mutex_unlock(&f->sem);
return ret;
}
diff --git a/fs/namei.c b/fs/namei.c
index 937f9d5..5f4cdf3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2131,6 +2131,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
if (!len)
return ERR_PTR(-EACCES);
+ if (unlikely(name[0] == '.')) {
+ if (len < 2 || (len == 2 && name[1] == '.'))
+ return ERR_PTR(-EACCES);
+ }
+
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ce8cb92..b9e66b7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -450,7 +450,8 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
nfs_refresh_inode(dentry->d_inode, entry->fattr);
goto out;
} else {
- d_drop(dentry);
+ if (d_invalidate(dentry) != 0)
+ goto out;
dput(dentry);
}
}
@@ -1100,6 +1101,8 @@ out_set_verifier:
out_zap_parent:
nfs_zap_caches(dir);
out_bad:
+ nfs_free_fattr(fattr);
+ nfs_free_fhandle(fhandle);
nfs_mark_for_revalidate(dir);
if (inode && S_ISDIR(inode->i_mode)) {
/* Purge readdir caches. */
@@ -1112,8 +1115,6 @@ out_zap_parent:
shrink_dcache_parent(dentry);
}
d_drop(dentry);
- nfs_free_fattr(fattr);
- nfs_free_fhandle(fhandle);
dput(parent);
dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n",
__func__, dentry->d_parent->d_name.name,
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 721d692..6fcaeb8 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -258,7 +258,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
if (ret)
goto out_close_fd;
- fd_install(fd, f);
+ if (fd != FAN_NOFD)
+ fd_install(fd, f);
return fanotify_event_metadata.event_len;
out_close_fd:
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 144a967..9e28356 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = {
.release = mem_release,
};
+static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ char buffer[PROC_NUMBUF];
+ int oom_adj = OOM_ADJUST_MIN;
+ size_t len;
+ unsigned long flags;
+
+ if (!task)
+ return -ESRCH;
+ if (lock_task_sighand(task, &flags)) {
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+ oom_adj = OOM_ADJUST_MAX;
+ else
+ oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+ OOM_SCORE_ADJ_MAX;
+ unlock_task_sighand(task, &flags);
+ }
+ put_task_struct(task);
+ len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_adj_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF];
+ int oom_adj;
+ unsigned long flags;
+ int err;
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count)) {
+ err = -EFAULT;
+ goto out;
+ }
+
+ err = kstrtoint(strstrip(buffer), 0, &oom_adj);
+ if (err)
+ goto out;
+ if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) &&
+ oom_adj != OOM_DISABLE) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task) {
+ err = -ESRCH;
+ goto out;
+ }
+
+ task_lock(task);
+ if (!task->mm) {
+ err = -EINVAL;
+ goto err_task_lock;
+ }
+
+ if (!lock_task_sighand(task, &flags)) {
+ err = -ESRCH;
+ goto err_task_lock;
+ }
+
+ /*
+ * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+ * value is always attainable.
+ */
+ if (oom_adj == OOM_ADJUST_MAX)
+ oom_adj = OOM_SCORE_ADJ_MAX;
+ else
+ oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
+
+ if (oom_adj < task->signal->oom_score_adj &&
+ !capable(CAP_SYS_RESOURCE)) {
+ err = -EACCES;
+ goto err_sighand;
+ }
+
+ /*
+ * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+ * /proc/pid/oom_score_adj instead.
+ */
+ printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+ current->comm, task_pid_nr(current), task_pid_nr(task),
+ task_pid_nr(task));
+
+ task->signal->oom_score_adj = oom_adj;
+ trace_oom_score_adj_update(task);
+err_sighand:
+ unlock_task_sighand(task, &flags);
+err_task_lock:
+ task_unlock(task);
+ put_task_struct(task);
+out:
+ return err < 0 ? err : count;
+}
+
+static const struct file_operations proc_oom_adj_operations = {
+ .read = oom_adj_read,
+ .write = oom_adj_write,
+ .llseek = generic_file_llseek,
+};
+
static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
@@ -1770,8 +1877,9 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
if (!vma)
goto out_no_vma;
- result = proc_map_files_instantiate(dir, dentry, task,
- (void *)(unsigned long)vma->vm_file->f_mode);
+ if (vma->vm_file)
+ result = proc_map_files_instantiate(dir, dentry, task,
+ (void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
up_read(&mm->mmap_sem);
@@ -2598,6 +2706,7 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
+ REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
@@ -2964,6 +3073,7 @@ static const struct pid_entry tid_base_stuff[] = {
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
+ REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index a40da07..947fbe0 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -161,6 +161,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
while (s < e) {
unsigned long flags;
+ u64 id;
if (c > psinfo->bufsize)
c = psinfo->bufsize;
@@ -172,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
spin_lock_irqsave(&psinfo->buf_lock, flags);
}
memcpy(psinfo->buf, s, c);
- psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo);
+ psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo);
spin_unlock_irqrestore(&psinfo->buf_lock, flags);
s += c;
c = e - s;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index f27f01a..d83736f 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1782,8 +1782,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
BUG_ON(!th->t_trans_id);
- dquot_initialize(inode);
+ reiserfs_write_unlock(inode->i_sb);
err = dquot_alloc_inode(inode);
+ reiserfs_write_lock(inode->i_sb);
if (err)
goto out_end_trans;
if (!dir->i_nlink) {
@@ -1979,8 +1980,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
out_end_trans:
journal_end(th, th->t_super, th->t_blocks_allocated);
+ reiserfs_write_unlock(inode->i_sb);
/* Drop can be outside and it needs more credits so it's better to have it outside */
dquot_drop(inode);
+ reiserfs_write_lock(inode->i_sb);
inode->i_flags |= S_NOQUOTA;
make_bad_inode(inode);
@@ -3103,10 +3106,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
/* must be turned off for recursive notify_change calls */
ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
- depth = reiserfs_write_lock_once(inode->i_sb);
if (is_quota_modification(inode, attr))
dquot_initialize(inode);
-
+ depth = reiserfs_write_lock_once(inode->i_sb);
if (attr->ia_valid & ATTR_SIZE) {
/* version 2 items will be caught by the s_maxbytes check
** done for us in vmtruncate
@@ -3170,7 +3172,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
error = journal_begin(&th, inode->i_sb, jbegin_count);
if (error)
goto out;
+ reiserfs_write_unlock_once(inode->i_sb, depth);
error = dquot_transfer(inode, attr);
+ depth = reiserfs_write_lock_once(inode->i_sb);
if (error) {
journal_end(&th, inode->i_sb, jbegin_count);
goto out;
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index f8afa4b..2f40a4c 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
key2type(&(key->on_disk_key)));
#endif
+ reiserfs_write_unlock(inode->i_sb);
retval = dquot_alloc_space_nodirty(inode, pasted_size);
+ reiserfs_write_lock(inode->i_sb);
if (retval) {
pathrelse(search_path);
return retval;
@@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
"reiserquota insert_item(): allocating %u id=%u type=%c",
quota_bytes, inode->i_uid, head2type(ih));
#endif
+ reiserfs_write_unlock(inode->i_sb);
/* We can't dirty inode here. It would be immediately written but
* appropriate stat item isn't inserted yet... */
retval = dquot_alloc_space_nodirty(inode, quota_bytes);
+ reiserfs_write_lock(inode->i_sb);
if (retval) {
pathrelse(path);
return retval;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 1078ae1..418bdc3 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -298,7 +298,9 @@ static int finish_unfinished(struct super_block *s)
retval = remove_save_link_only(s, &save_link_key, 0);
continue;
}
+ reiserfs_write_unlock(s);
dquot_initialize(inode);
+ reiserfs_write_lock(s);
if (truncate && S_ISDIR(inode->i_mode)) {
/* We got a truncate request for a dir which is impossible.
@@ -1335,7 +1337,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
kfree(qf_names[i]);
#endif
err = -EINVAL;
- goto out_err;
+ goto out_unlock;
}
#ifdef CONFIG_QUOTA
handle_quota_files(s, qf_names, &qfmt);
@@ -1379,7 +1381,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
if (blocks) {
err = reiserfs_resize(s, blocks);
if (err != 0)
- goto out_err;
+ goto out_unlock;
}
if (*mount_flags & MS_RDONLY) {
@@ -1389,9 +1391,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
/* it is read-only already */
goto out_ok;
+ /*
+ * Drop write lock. Quota will retake it when needed and lock
+ * ordering requires calling dquot_suspend() without it.
+ */
+ reiserfs_write_unlock(s);
err = dquot_suspend(s, -1);
if (err < 0)
goto out_err;
+ reiserfs_write_lock(s);
/* try to remount file system with read-only permissions */
if (sb_umount_state(rs) == REISERFS_VALID_FS
@@ -1401,7 +1409,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
err = journal_begin(&th, s, 10);
if (err)
- goto out_err;
+ goto out_unlock;
/* Mounting a rw partition read-only. */
reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
@@ -1416,7 +1424,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
if (reiserfs_is_journal_aborted(journal)) {
err = journal->j_errno;
- goto out_err;
+ goto out_unlock;
}
handle_data_mode(s, mount_options);
@@ -1425,7 +1433,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
s->s_flags &= ~MS_RDONLY; /* now it is safe to call journal_begin */
err = journal_begin(&th, s, 10);
if (err)
- goto out_err;
+ goto out_unlock;
/* Mount a partition which is read-only, read-write */
reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
@@ -1442,10 +1450,16 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
SB_JOURNAL(s)->j_must_wait = 1;
err = journal_end(&th, s, 10);
if (err)
- goto out_err;
+ goto out_unlock;
if (!(*mount_flags & MS_RDONLY)) {
+ /*
+ * Drop write lock. Quota will retake it when needed and lock
+ * ordering requires calling dquot_resume() without it.
+ */
+ reiserfs_write_unlock(s);
dquot_resume(s, -1);
+ reiserfs_write_lock(s);
finish_unfinished(s);
reiserfs_xattr_init(s, *mount_flags);
}
@@ -1455,9 +1469,10 @@ out_ok:
reiserfs_write_unlock(s);
return 0;
+out_unlock:
+ reiserfs_write_unlock(s);
out_err:
kfree(new_opts);
- reiserfs_write_unlock(s);
return err;
}
@@ -2095,13 +2110,15 @@ static int reiserfs_write_dquot(struct dquot *dquot)
REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (ret)
goto out;
+ reiserfs_write_unlock(dquot->dq_sb);
ret = dquot_commit(dquot);
+ reiserfs_write_lock(dquot->dq_sb);
err =
journal_end(&th, dquot->dq_sb,
REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (!ret && err)
ret = err;
- out:
+out:
reiserfs_write_unlock(dquot->dq_sb);
return ret;
}
@@ -2117,13 +2134,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot)
REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (ret)
goto out;
+ reiserfs_write_unlock(dquot->dq_sb);
ret = dquot_acquire(dquot);
+ reiserfs_write_lock(dquot->dq_sb);
err =
journal_end(&th, dquot->dq_sb,
REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (!ret && err)
ret = err;
- out:
+out:
reiserfs_write_unlock(dquot->dq_sb);
return ret;
}
@@ -2137,19 +2156,21 @@ static int reiserfs_release_dquot(struct dquot *dquot)
ret =
journal_begin(&th, dquot->dq_sb,
REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+ reiserfs_write_unlock(dquot->dq_sb);
if (ret) {
/* Release dquot anyway to avoid endless cycle in dqput() */
dquot_release(dquot);
goto out;
}
ret = dquot_release(dquot);
+ reiserfs_write_lock(dquot->dq_sb);
err =
journal_end(&th, dquot->dq_sb,
REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (!ret && err)
ret = err;
- out:
reiserfs_write_unlock(dquot->dq_sb);
+out:
return ret;
}
@@ -2174,11 +2195,13 @@ static int reiserfs_write_info(struct super_block *sb, int type)
ret = journal_begin(&th, sb, 2);
if (ret)
goto out;
+ reiserfs_write_unlock(sb);
ret = dquot_commit_info(sb, type);
+ reiserfs_write_lock(sb);
err = journal_end(&th, sb, 2);
if (!ret && err)
ret = err;
- out:
+out:
reiserfs_write_unlock(sb);
return ret;
}
@@ -2203,8 +2226,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
struct reiserfs_transaction_handle th;
int opt = type == USRQUOTA ? REISERFS_USRQUOTA : REISERFS_GRPQUOTA;
- if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt)))
- return -EINVAL;
+ reiserfs_write_lock(sb);
+ if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) {
+ err = -EINVAL;
+ goto out;
+ }
/* Quotafile not on the same filesystem? */
if (path->dentry->d_sb != sb) {
@@ -2246,8 +2272,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
if (err)
goto out;
}
- err = dquot_quota_on(sb, type, format_id, path);
+ reiserfs_write_unlock(sb);
+ return dquot_quota_on(sb, type, format_id, path);
out:
+ reiserfs_write_unlock(sb);
return err;
}
@@ -2320,7 +2348,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
tocopy = sb->s_blocksize - offset < towrite ?
sb->s_blocksize - offset : towrite;
tmp_bh.b_state = 0;
+ reiserfs_write_lock(sb);
err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE);
+ reiserfs_write_unlock(sb);
if (err)
goto out;
if (offset || tocopy != sb->s_blocksize)
@@ -2336,10 +2366,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
flush_dcache_page(bh->b_page);
set_buffer_uptodate(bh);
unlock_buffer(bh);
+ reiserfs_write_lock(sb);
reiserfs_prepare_for_journal(sb, bh, 1);
journal_mark_dirty(current->journal_info, sb, bh);
if (!journal_quota)
reiserfs_add_ordered_list(inode, bh);
+ reiserfs_write_unlock(sb);
brelse(bh);
offset = 0;
towrite -= tocopy;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 28ec13a..2dcf3d4 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c)
if (!lprops) {
lprops = ubifs_fast_find_freeable(c);
if (!lprops) {
- ubifs_assert(c->freeable_cnt == 0);
- if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+ /*
+ * The first condition means the following: go scan the
+ * LPT if there are uncategorized lprops, which means
+ * there may be freeable LEBs there (UBIFS does not
+ * store the information about freeable LEBs in the
+ * master node).
+ */
+ if (c->in_a_category_cnt != c->main_lebs ||
+ c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+ ubifs_assert(c->freeable_cnt == 0);
lprops = scan_for_leb_for_idx(c);
if (IS_ERR(lprops)) {
err = PTR_ERR(lprops);
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index e5a2a35..46190a7 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
default:
ubifs_assert(0);
}
+
lprops->flags &= ~LPROPS_CAT_MASK;
lprops->flags |= cat;
+ c->in_a_category_cnt += 1;
+ ubifs_assert(c->in_a_category_cnt <= c->main_lebs);
}
/**
@@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
default:
ubifs_assert(0);
}
+
+ c->in_a_category_cnt -= 1;
+ ubifs_assert(c->in_a_category_cnt >= 0);
}
/**
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 5486346..d133c27 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1183,6 +1183,8 @@ struct ubifs_debug_info;
* @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size)
* @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size)
* @freeable_cnt: number of freeable LEBs in @freeable_list
+ * @in_a_category_cnt: count of lprops which are in a certain category, which
+ * basically meants that they were loaded from the flash
*
* @ltab_lnum: LEB number of LPT's own lprops table
* @ltab_offs: offset of LPT's own lprops table
@@ -1412,6 +1414,7 @@ struct ubifs_info {
struct list_head freeable_list;
struct list_head frdi_idx_list;
int freeable_cnt;
+ int in_a_category_cnt;
int ltab_lnum;
int ltab_offs;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index e562dd4..e57e2da 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -481,11 +481,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh)
*
* The fix is two passes across the ioend list - one to start writeback on the
* buffer_heads, and then submit them for I/O on the second pass.
+ *
+ * If @fail is non-zero, it means that we have a situation where some part of
+ * the submission process has failed after we have marked paged for writeback
+ * and unlocked them. In this situation, we need to fail the ioend chain rather
+ * than submit it to IO. This typically only happens on a filesystem shutdown.
*/
STATIC void
xfs_submit_ioend(
struct writeback_control *wbc,
- xfs_ioend_t *ioend)
+ xfs_ioend_t *ioend,
+ int fail)
{
xfs_ioend_t *head = ioend;
xfs_ioend_t *next;
@@ -506,6 +512,18 @@ xfs_submit_ioend(
next = ioend->io_list;
bio = NULL;
+ /*
+ * If we are failing the IO now, just mark the ioend with an
+ * error and finish it. This will run IO completion immediately
+ * as there is only one reference to the ioend at this point in
+ * time.
+ */
+ if (fail) {
+ ioend->io_error = -fail;
+ xfs_finish_ioend(ioend);
+ continue;
+ }
+
for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
if (!bio) {
@@ -1060,7 +1078,18 @@ xfs_vm_writepage(
xfs_start_page_writeback(page, 1, count);
- if (ioend && imap_valid) {
+ /* if there is no IO to be submitted for this page, we are done */
+ if (!ioend)
+ return 0;
+
+ ASSERT(iohead);
+
+ /*
+ * Any errors from this point onwards need tobe reported through the IO
+ * completion path as we have marked the initial page as under writeback
+ * and unlocked it.
+ */
+ if (imap_valid) {
xfs_off_t end_index;
end_index = imap.br_startoff + imap.br_blockcount;
@@ -1079,20 +1108,15 @@ xfs_vm_writepage(
wbc, end_index);
}
- if (iohead) {
- /*
- * Reserve log space if we might write beyond the on-disk
- * inode size.
- */
- if (ioend->io_type != XFS_IO_UNWRITTEN &&
- xfs_ioend_is_append(ioend)) {
- err = xfs_setfilesize_trans_alloc(ioend);
- if (err)
- goto error;
- }
- xfs_submit_ioend(wbc, iohead);
- }
+ /*
+ * Reserve log space if we might write beyond the on-disk inode size.
+ */
+ err = 0;
+ if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend))
+ err = xfs_setfilesize_trans_alloc(ioend);
+
+ xfs_submit_ioend(wbc, iohead, err);
return 0;
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d330111..70eec18 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -1291,6 +1291,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
leaf2 = blk2->bp->b_addr;
ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
+ ASSERT(leaf2->hdr.count == 0);
args = state->args;
trace_xfs_attr_leaf_rebalance(args);
@@ -1361,6 +1362,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
* I assert that since all callers pass in an empty
* second buffer, this code should never execute.
*/
+ ASSERT(0);
/*
* Figure the total bytes to be added to the destination leaf.
@@ -1422,10 +1424,24 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
args->index2 = 0;
args->blkno2 = blk2->blkno;
} else {
+ /*
+ * On a double leaf split, the original attr location
+ * is already stored in blkno2/index2, so don't
+ * overwrite it overwise we corrupt the tree.
+ */
blk2->index = blk1->index
- be16_to_cpu(leaf1->hdr.count);
- args->index = args->index2 = blk2->index;
- args->blkno = args->blkno2 = blk2->blkno;
+ args->index = blk2->index;
+ args->blkno = blk2->blkno;
+ if (!state->extravalid) {
+ /*
+ * set the new attr location to match the old
+ * one and let the higher level split code
+ * decide where in the leaf to place it.
+ */
+ args->index2 = blk2->index;
+ args->blkno2 = blk2->blkno;
+ }
}
} else {
ASSERT(state->inleaf == 1);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 933b793..4b0b8dd 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1197,9 +1197,14 @@ xfs_buf_bio_end_io(
{
xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private;
- xfs_buf_ioerror(bp, -error);
+ /*
+ * don't overwrite existing errors - otherwise we can lose errors on
+ * buffers that require multiple bios to complete.
+ */
+ if (!bp->b_error)
+ xfs_buf_ioerror(bp, -error);
- if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+ if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
_xfs_buf_ioend(bp, 1);
@@ -1279,6 +1284,11 @@ next_chunk:
if (size)
goto next_chunk;
} else {
+ /*
+ * This is guaranteed not to be the last io reference count
+ * because the caller (xfs_buf_iorequest) holds a count itself.
+ */
+ atomic_dec(&bp->b_io_remaining);
xfs_buf_ioerror(bp, EIO);
bio_put(bio);
}
generated by cgit v0.10.2 at 2024-07-16 12:21:58 (GMT)