Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
truncate: use new helpers
truncate: new helpers
fs: fix overflow in sys_mount() for in-kernel calls
fs: Make unload_nls() NULL pointer safe
freeze_bdev: grab active reference to frozen superblocks
freeze_bdev: kill bd_mount_sem
exofs: remove BKL from super operations
fs/romfs: correct error-handling code
vfs: seq_file: add helpers for data filling
vfs: remove redundant position check in do_sendfile
vfs: change sb->s_maxbytes to a loff_t
vfs: explicitly cast s_maxbytes in fiemap_check_ranges
libfs: return error code on failed attr set
seq_file: return a negative error code when seq_path_root() fails.
vfs: optimize touch_time() too
vfs: optimization for touch_atime()
vfs: split generic_forget_inode() so that hugetlbfs does not have to copy it
fs/inode.c: add dev-id and inode number for debugging in init_special_inode()
libfs: make simple_read_from_buffer conventional
diff --git a/Documentation/vm/locking b/Documentation/vm/locking
index f366fa9..25fadb4 100644
--- a/Documentation/vm/locking
+++ b/Documentation/vm/locking
@@ -80,7 +80,7 @@
mm start up ... this is a loose form of stability on mm_users. For
example, it is used in copy_mm to protect against a racing tlb_gather_mmu
single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might
+truncate) does not lose sending ipi's to cloned threads that might
be spawned underneath it and go to user mode to drag in pte's into tlbs.
swap_lock
diff --git a/fs/attr.c b/fs/attr.c
index 9fe1b1b..96d394b 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -18,7 +18,7 @@
/* Taken over from the old code... */
/* POSIX UID/GID verification for setting inode attributes. */
-int inode_change_ok(struct inode *inode, struct iattr *attr)
+int inode_change_ok(const struct inode *inode, struct iattr *attr)
{
int retval = -EPERM;
unsigned int ia_valid = attr->ia_valid;
@@ -60,9 +60,51 @@
error:
return retval;
}
-
EXPORT_SYMBOL(inode_change_ok);
+/**
+ * inode_newsize_ok - may this inode be truncated to a given size
+ * @inode: the inode to be truncated
+ * @offset: the new size to assign to the inode
+ * @Returns: 0 on success, -ve errno on failure
+ *
+ * inode_newsize_ok will check filesystem limits and ulimits to check that the
+ * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
+ * when necessary. Caller must not proceed with inode size change if failure is
+ * returned. @inode must be a file (not directory), with appropriate
+ * permissions to allow truncate (inode_newsize_ok does NOT check these
+ * conditions).
+ *
+ * inode_newsize_ok must be called with i_mutex held.
+ */
+int inode_newsize_ok(const struct inode *inode, loff_t offset)
+{
+ if (inode->i_size < offset) {
+ unsigned long limit;
+
+ limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+ if (limit != RLIM_INFINITY && offset > limit)
+ goto out_sig;
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_big;
+ } else {
+ /*
+ * truncation of in-use swapfiles is disallowed - it would
+ * cause subsequent swapout to scribble on the now-freed
+ * blocks.
+ */
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+ }
+
+ return 0;
+out_sig:
+ send_sig(SIGXFSZ, current, 0);
+out_big:
+ return -EFBIG;
+}
+EXPORT_SYMBOL(inode_newsize_ok);
+
int inode_setattr(struct inode * inode, struct iattr * attr)
{
unsigned int ia_valid = attr->ia_valid;
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index dd376c1..33baf27 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -737,12 +737,7 @@
{
kfree(BEFS_SB(sb)->mount_opts.iocharset);
BEFS_SB(sb)->mount_opts.iocharset = NULL;
-
- if (BEFS_SB(sb)->nls) {
- unload_nls(BEFS_SB(sb)->nls);
- BEFS_SB(sb)->nls = NULL;
- }
-
+ unload_nls(BEFS_SB(sb)->nls);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5d1ed50..9cf4b92 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -216,8 +216,6 @@
* freeze_bdev -- lock a filesystem and force it into a consistent state
* @bdev: blockdevice to lock
*
- * This takes the block device bd_mount_sem to make sure no new mounts
- * happen on bdev until thaw_bdev() is called.
* If a superblock is found on this device, we take the s_umount semaphore
* on it to make sure nobody unmounts until the snapshot creation is done.
* The reference counter (bd_fsfreeze_count) guarantees that only the last
@@ -232,46 +230,55 @@
int error = 0;
mutex_lock(&bdev->bd_fsfreeze_mutex);
- if (bdev->bd_fsfreeze_count > 0) {
- bdev->bd_fsfreeze_count++;
+ if (++bdev->bd_fsfreeze_count > 1) {
+ /*
+ * We don't even need to grab a reference - the first call
+ * to freeze_bdev grab an active reference and only the last
+ * thaw_bdev drops it.
+ */
sb = get_super(bdev);
+ drop_super(sb);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return sb;
}
- bdev->bd_fsfreeze_count++;
- down(&bdev->bd_mount_sem);
- sb = get_super(bdev);
- if (sb && !(sb->s_flags & MS_RDONLY)) {
- sb->s_frozen = SB_FREEZE_WRITE;
- smp_wmb();
-
- sync_filesystem(sb);
-
- sb->s_frozen = SB_FREEZE_TRANS;
- smp_wmb();
-
- sync_blockdev(sb->s_bdev);
-
- if (sb->s_op->freeze_fs) {
- error = sb->s_op->freeze_fs(sb);
- if (error) {
- printk(KERN_ERR
- "VFS:Filesystem freeze failed\n");
- sb->s_frozen = SB_UNFROZEN;
- drop_super(sb);
- up(&bdev->bd_mount_sem);
- bdev->bd_fsfreeze_count--;
- mutex_unlock(&bdev->bd_fsfreeze_mutex);
- return ERR_PTR(error);
- }
- }
+ sb = get_active_super(bdev);
+ if (!sb)
+ goto out;
+ if (sb->s_flags & MS_RDONLY) {
+ deactivate_locked_super(sb);
+ mutex_unlock(&bdev->bd_fsfreeze_mutex);
+ return sb;
}
+ sb->s_frozen = SB_FREEZE_WRITE;
+ smp_wmb();
+
+ sync_filesystem(sb);
+
+ sb->s_frozen = SB_FREEZE_TRANS;
+ smp_wmb();
+
+ sync_blockdev(sb->s_bdev);
+
+ if (sb->s_op->freeze_fs) {
+ error = sb->s_op->freeze_fs(sb);
+ if (error) {
+ printk(KERN_ERR
+ "VFS:Filesystem freeze failed\n");
+ sb->s_frozen = SB_UNFROZEN;
+ deactivate_locked_super(sb);
+ bdev->bd_fsfreeze_count--;
+ mutex_unlock(&bdev->bd_fsfreeze_mutex);
+ return ERR_PTR(error);
+ }
+ }
+ up_write(&sb->s_umount);
+
+ out:
sync_blockdev(bdev);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
-
- return sb; /* thaw_bdev releases s->s_umount and bd_mount_sem */
+ return sb; /* thaw_bdev releases s->s_umount */
}
EXPORT_SYMBOL(freeze_bdev);
@@ -284,44 +291,44 @@
*/
int thaw_bdev(struct block_device *bdev, struct super_block *sb)
{
- int error = 0;
+ int error = -EINVAL;
mutex_lock(&bdev->bd_fsfreeze_mutex);
- if (!bdev->bd_fsfreeze_count) {
- mutex_unlock(&bdev->bd_fsfreeze_mutex);
- return -EINVAL;
- }
+ if (!bdev->bd_fsfreeze_count)
+ goto out_unlock;
- bdev->bd_fsfreeze_count--;
- if (bdev->bd_fsfreeze_count > 0) {
- if (sb)
- drop_super(sb);
- mutex_unlock(&bdev->bd_fsfreeze_mutex);
- return 0;
- }
+ error = 0;
+ if (--bdev->bd_fsfreeze_count > 0)
+ goto out_unlock;
- if (sb) {
- BUG_ON(sb->s_bdev != bdev);
- if (!(sb->s_flags & MS_RDONLY)) {
- if (sb->s_op->unfreeze_fs) {
- error = sb->s_op->unfreeze_fs(sb);
- if (error) {
- printk(KERN_ERR
- "VFS:Filesystem thaw failed\n");
- sb->s_frozen = SB_FREEZE_TRANS;
- bdev->bd_fsfreeze_count++;
- mutex_unlock(&bdev->bd_fsfreeze_mutex);
- return error;
- }
- }
- sb->s_frozen = SB_UNFROZEN;
- smp_wmb();
- wake_up(&sb->s_wait_unfrozen);
+ if (!sb)
+ goto out_unlock;
+
+ BUG_ON(sb->s_bdev != bdev);
+ down_write(&sb->s_umount);
+ if (sb->s_flags & MS_RDONLY)
+ goto out_deactivate;
+
+ if (sb->s_op->unfreeze_fs) {
+ error = sb->s_op->unfreeze_fs(sb);
+ if (error) {
+ printk(KERN_ERR
+ "VFS:Filesystem thaw failed\n");
+ sb->s_frozen = SB_FREEZE_TRANS;
+ bdev->bd_fsfreeze_count++;
+ mutex_unlock(&bdev->bd_fsfreeze_mutex);
+ return error;
}
- drop_super(sb);
}
- up(&bdev->bd_mount_sem);
+ sb->s_frozen = SB_UNFROZEN;
+ smp_wmb();
+ wake_up(&sb->s_wait_unfrozen);
+
+out_deactivate:
+ if (sb)
+ deactivate_locked_super(sb);
+out_unlock:
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return 0;
}
@@ -430,7 +437,6 @@
memset(bdev, 0, sizeof(*bdev));
mutex_init(&bdev->bd_mutex);
- sema_init(&bdev->bd_mount_sem, 1);
INIT_LIST_HEAD(&bdev->bd_inodes);
INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
diff --git a/fs/buffer.c b/fs/buffer.c
index 209f7f1..24afd74 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2239,16 +2239,10 @@
struct address_space *mapping = inode->i_mapping;
struct page *page;
void *fsdata;
- unsigned long limit;
int err;
- err = -EFBIG;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && size > (loff_t)limit) {
- send_sig(SIGXFSZ, current, 0);
- goto out;
- }
- if (size > inode->i_sb->s_maxbytes)
+ err = inode_newsize_ok(inode, size);
+ if (err)
goto out;
err = pagecache_write_begin(NULL, mapping, size, 0,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d79ce2e..90c5b39 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -185,8 +185,7 @@
cifs_sb->mountdata = NULL;
}
#endif
- if (cifs_sb->local_nls)
- unload_nls(cifs_sb->local_nls);
+ unload_nls(cifs_sb->local_nls);
kfree(cifs_sb);
}
return rc;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 1f09c761..5e24925 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1557,57 +1557,24 @@
static int cifs_vmtruncate(struct inode *inode, loff_t offset)
{
- struct address_space *mapping = inode->i_mapping;
- unsigned long limit;
+ loff_t oldsize;
+ int err;
spin_lock(&inode->i_lock);
- if (inode->i_size < offset)
- goto do_expand;
- /*
- * truncation of in-use swapfiles is disallowed - it would cause
- * subsequent swapout to scribble on the now-freed blocks.
- */
- if (IS_SWAPFILE(inode)) {
+ err = inode_newsize_ok(inode, offset);
+ if (err) {
spin_unlock(&inode->i_lock);
- goto out_busy;
+ goto out;
}
- i_size_write(inode, offset);
- spin_unlock(&inode->i_lock);
- /*
- * unmap_mapping_range is called twice, first simply for efficiency
- * so that truncate_inode_pages does fewer single-page unmaps. However
- * after this first call, and before truncate_inode_pages finishes,
- * it is possible for private pages to be COWed, which remain after
- * truncate_inode_pages finishes, hence the second unmap_mapping_range
- * call must be made for correctness.
- */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- goto out_truncate;
-do_expand:
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit) {
- spin_unlock(&inode->i_lock);
- goto out_sig;
- }
- if (offset > inode->i_sb->s_maxbytes) {
- spin_unlock(&inode->i_lock);
- goto out_big;
- }
+ oldsize = inode->i_size;
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
-out_truncate:
+ truncate_pagecache(inode, oldsize, offset);
if (inode->i_op->truncate)
inode->i_op->truncate(inode);
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out_big:
- return -EFBIG;
-out_busy:
- return -ETXTBSY;
+out:
+ return err;
}
static int
diff --git a/fs/compat.c b/fs/compat.c
index 3aa4883..d576b55 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -768,13 +768,13 @@
char __user * type, unsigned long flags,
void __user * data)
{
- unsigned long type_page;
+ char *kernel_type;
unsigned long data_page;
- unsigned long dev_page;
+ char *kernel_dev;
char *dir_page;
int retval;
- retval = copy_mount_options (type, &type_page);
+ retval = copy_mount_string(type, &kernel_type);
if (retval < 0)
goto out;
@@ -783,38 +783,38 @@
if (IS_ERR(dir_page))
goto out1;
- retval = copy_mount_options (dev_name, &dev_page);
+ retval = copy_mount_string(dev_name, &kernel_dev);
if (retval < 0)
goto out2;
- retval = copy_mount_options (data, &data_page);
+ retval = copy_mount_options(data, &data_page);
if (retval < 0)
goto out3;
retval = -EINVAL;
- if (type_page && data_page) {
- if (!strcmp((char *)type_page, SMBFS_NAME)) {
+ if (kernel_type && data_page) {
+ if (!strcmp(kernel_type, SMBFS_NAME)) {
do_smb_super_data_conv((void *)data_page);
- } else if (!strcmp((char *)type_page, NCPFS_NAME)) {
+ } else if (!strcmp(kernel_type, NCPFS_NAME)) {
do_ncp_super_data_conv((void *)data_page);
- } else if (!strcmp((char *)type_page, NFS4_NAME)) {
+ } else if (!strcmp(kernel_type, NFS4_NAME)) {
if (do_nfs4_super_data_conv((void *) data_page))
goto out4;
}
}
- retval = do_mount((char*)dev_page, dir_page, (char*)type_page,
+ retval = do_mount(kernel_dev, dir_page, kernel_type,
flags, (void*)data_page);
out4:
free_page(data_page);
out3:
- free_page(dev_page);
+ kfree(kernel_dev);
out2:
putname(dir_page);
out1:
- free_page(type_page);
+ kfree(kernel_type);
out:
return retval;
}
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 5ab10c3..9f500de 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -214,7 +214,6 @@
}
lock_super(sb);
- lock_kernel();
sbi = sb->s_fs_info;
fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
fscb->s_numfiles = cpu_to_le32(sbi->s_numfiles);
@@ -245,7 +244,6 @@
out:
if (or)
osd_end_request(or);
- unlock_kernel();
unlock_super(sb);
kfree(fscb);
return ret;
@@ -268,8 +266,6 @@
int num_pend;
struct exofs_sb_info *sbi = sb->s_fs_info;
- lock_kernel();
-
if (sb->s_dirt)
exofs_write_super(sb);
@@ -286,8 +282,6 @@
osduld_put_device(sbi->s_dev);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
-
- unlock_kernel();
}
/*
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 8970d8c..04629d1 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -470,19 +470,11 @@
iput(sbi->fat_inode);
- if (sbi->nls_disk) {
- unload_nls(sbi->nls_disk);
- sbi->nls_disk = NULL;
- sbi->options.codepage = fat_default_codepage;
- }
- if (sbi->nls_io) {
- unload_nls(sbi->nls_io);
- sbi->nls_io = NULL;
- }
- if (sbi->options.iocharset != fat_default_iocharset) {
+ unload_nls(sbi->nls_disk);
+ unload_nls(sbi->nls_io);
+
+ if (sbi->options.iocharset != fat_default_iocharset)
kfree(sbi->options.iocharset);
- sbi->options.iocharset = fat_default_iocharset;
- }
sb->s_fs_info = NULL;
kfree(sbi);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index e703654..992f6c9 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1276,14 +1276,9 @@
return 0;
if (attr->ia_valid & ATTR_SIZE) {
- unsigned long limit;
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && attr->ia_size > (loff_t) limit) {
- send_sig(SIGXFSZ, current, 0);
- return -EFBIG;
- }
+ err = inode_newsize_ok(inode, attr->ia_size);
+ if (err)
+ return err;
is_truncate = true;
}
@@ -1350,8 +1345,7 @@
* FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
*/
if (S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
- if (outarg.attr.size < oldsize)
- fuse_truncate(inode->i_mapping, outarg.attr.size);
+ truncate_pagecache(inode, oldsize, outarg.attr.size);
invalidate_inode_pages2(inode->i_mapping);
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fc9c79f..01cc462 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -606,8 +606,6 @@
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid);
-void fuse_truncate(struct address_space *mapping, loff_t offset);
-
/**
* Initialize the client device
*/
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6da947d..1a822ce 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -140,14 +140,6 @@
return 0;
}
-void fuse_truncate(struct address_space *mapping, loff_t offset)
-{
- /* See vmtruncate() */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-}
-
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
@@ -205,8 +197,7 @@
spin_unlock(&fc->lock);
if (S_ISREG(inode->i_mode) && oldsize != attr->size) {
- if (attr->size < oldsize)
- fuse_truncate(inode->i_mapping, attr->size);
+ truncate_pagecache(inode, oldsize, attr->size);
invalidate_inode_pages2(inode->i_mapping);
}
}
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 7b6165f..8bbe03c 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -344,10 +344,8 @@
brelse(HFS_SB(sb)->mdb_bh);
brelse(HFS_SB(sb)->alt_mdb_bh);
- if (HFS_SB(sb)->nls_io)
- unload_nls(HFS_SB(sb)->nls_io);
- if (HFS_SB(sb)->nls_disk)
- unload_nls(HFS_SB(sb)->nls_disk);
+ unload_nls(HFS_SB(sb)->nls_io);
+ unload_nls(HFS_SB(sb)->nls_disk);
free_pages((unsigned long)HFS_SB(sb)->bitmap, PAGE_SIZE < 8192 ? 1 : 0);
kfree(HFS_SB(sb));
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index c0759fe..43022f3 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -229,8 +229,7 @@
iput(HFSPLUS_SB(sb).alloc_file);
iput(HFSPLUS_SB(sb).hidden_dir);
brelse(HFSPLUS_SB(sb).s_vhbh);
- if (HFSPLUS_SB(sb).nls)
- unload_nls(HFSPLUS_SB(sb).nls);
+ unload_nls(HFSPLUS_SB(sb).nls);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
@@ -464,8 +463,7 @@
cleanup:
hfsplus_put_super(sb);
- if (nls)
- unload_nls(nls);
+ unload_nls(nls);
return err;
}
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 1333354..87a1258 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -380,36 +380,11 @@
static void hugetlbfs_forget_inode(struct inode *inode) __releases(inode_lock)
{
- struct super_block *sb = inode->i_sb;
-
- if (!hlist_unhashed(&inode->i_hash)) {
- if (!(inode->i_state & (I_DIRTY|I_SYNC)))
- list_move(&inode->i_list, &inode_unused);
- inodes_stat.nr_unused++;
- if (!sb || (sb->s_flags & MS_ACTIVE)) {
- spin_unlock(&inode_lock);
- return;
- }
- inode->i_state |= I_WILL_FREE;
- spin_unlock(&inode_lock);
- /*
- * write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK
- * in our backing_dev_info.
- */
- write_inode_now(inode, 1);
- spin_lock(&inode_lock);
- inode->i_state &= ~I_WILL_FREE;
- inodes_stat.nr_unused--;
- hlist_del_init(&inode->i_hash);
+ if (generic_detach_inode(inode)) {
+ truncate_hugepages(inode, 0);
+ clear_inode(inode);
+ destroy_inode(inode);
}
- list_del_init(&inode->i_list);
- list_del_init(&inode->i_sb_list);
- inode->i_state |= I_FREEING;
- inodes_stat.nr_inodes--;
- spin_unlock(&inode_lock);
- truncate_hugepages(inode, 0);
- clear_inode(inode);
- destroy_inode(inode);
}
static void hugetlbfs_drop_inode(struct inode *inode)
diff --git a/fs/inode.c b/fs/inode.c
index 76582b0..4d8e3be 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1241,7 +1241,16 @@
}
EXPORT_SYMBOL(generic_delete_inode);
-static void generic_forget_inode(struct inode *inode)
+/**
+ * generic_detach_inode - remove inode from inode lists
+ * @inode: inode to remove
+ *
+ * Remove inode from inode lists, write it if it's dirty. This is just an
+ * internal VFS helper exported for hugetlbfs. Do not use!
+ *
+ * Returns 1 if inode should be completely destroyed.
+ */
+int generic_detach_inode(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
@@ -1251,7 +1260,7 @@
inodes_stat.nr_unused++;
if (sb->s_flags & MS_ACTIVE) {
spin_unlock(&inode_lock);
- return;
+ return 0;
}
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_WILL_FREE;
@@ -1269,6 +1278,14 @@
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
+ return 1;
+}
+EXPORT_SYMBOL_GPL(generic_detach_inode);
+
+static void generic_forget_inode(struct inode *inode)
+{
+ if (!generic_detach_inode(inode))
+ return;
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
@@ -1399,31 +1416,31 @@
struct inode *inode = dentry->d_inode;
struct timespec now;
- if (mnt_want_write(mnt))
- return;
if (inode->i_flags & S_NOATIME)
- goto out;
+ return;
if (IS_NOATIME(inode))
- goto out;
+ return;
if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
- goto out;
+ return;
if (mnt->mnt_flags & MNT_NOATIME)
- goto out;
+ return;
if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
- goto out;
+ return;
now = current_fs_time(inode->i_sb);
if (!relatime_need_update(mnt, inode, now))
- goto out;
+ return;
if (timespec_equal(&inode->i_atime, &now))
- goto out;
+ return;
+
+ if (mnt_want_write(mnt))
+ return;
inode->i_atime = now;
mark_inode_dirty_sync(inode);
-out:
mnt_drop_write(mnt);
}
EXPORT_SYMBOL(touch_atime);
@@ -1444,34 +1461,37 @@
{
struct inode *inode = file->f_path.dentry->d_inode;
struct timespec now;
- int sync_it = 0;
- int err;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+ /* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return;
- err = mnt_want_write_file(file);
- if (err)
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
return;
- now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_mtime, &now)) {
- inode->i_mtime = now;
- sync_it = 1;
- }
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return;
- if (!timespec_equal(&inode->i_ctime, &now)) {
- inode->i_ctime = now;
- sync_it = 1;
- }
-
- if (IS_I_VERSION(inode)) {
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
inode_inc_iversion(inode);
- sync_it = 1;
- }
-
- if (sync_it)
- mark_inode_dirty_sync(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ mark_inode_dirty_sync(inode);
mnt_drop_write(file->f_path.mnt);
}
EXPORT_SYMBOL(file_update_time);
@@ -1599,7 +1619,8 @@
else if (S_ISSOCK(mode))
inode->i_fop = &bad_sock_fops;
else
- printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o)\n",
- mode);
+ printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
+ " inode %s:%lu\n", mode, inode->i_sb->s_id,
+ inode->i_ino);
}
EXPORT_SYMBOL(init_special_inode);
diff --git a/fs/internal.h b/fs/internal.h
index d55ef56..515175b 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -57,6 +57,7 @@
* namespace.c
*/
extern int copy_mount_options(const void __user *, unsigned long *);
+extern int copy_mount_string(const void __user *, char **);
extern void free_vfsmnt(struct vfsmount *);
extern struct vfsmount *alloc_vfsmnt(const char *);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 5612880..7b17a14 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -162,20 +162,21 @@
static int fiemap_check_ranges(struct super_block *sb,
u64 start, u64 len, u64 *new_len)
{
+ u64 maxbytes = (u64) sb->s_maxbytes;
+
*new_len = len;
if (len == 0)
return -EINVAL;
- if (start > sb->s_maxbytes)
+ if (start > maxbytes)
return -EFBIG;
/*
* Shrink request scope to what the fs can actually handle.
*/
- if ((len > sb->s_maxbytes) ||
- (sb->s_maxbytes - len) < start)
- *new_len = sb->s_maxbytes - start;
+ if (len > maxbytes || (maxbytes - len) < start)
+ *new_len = maxbytes - start;
return 0;
}
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 85f96bc..6b4dcd4 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -46,10 +46,7 @@
#ifdef CONFIG_JOLIET
lock_kernel();
- if (sbi->s_nls_iocharset) {
- unload_nls(sbi->s_nls_iocharset);
- sbi->s_nls_iocharset = NULL;
- }
+ unload_nls(sbi->s_nls_iocharset);
unlock_kernel();
#endif
@@ -912,8 +909,7 @@
printk(KERN_WARNING "%s: get root inode failed\n", __func__);
out_no_inode:
#ifdef CONFIG_JOLIET
- if (sbi->s_nls_iocharset)
- unload_nls(sbi->s_nls_iocharset);
+ unload_nls(sbi->s_nls_iocharset);
#endif
goto out_freesbi;
out_no_read:
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 37e6dcd..2234c73 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -178,13 +178,11 @@
rc = jfs_umount(sb);
if (rc)
jfs_err("jfs_umount failed with return code %d", rc);
- if (sbi->nls_tab)
- unload_nls(sbi->nls_tab);
- sbi->nls_tab = NULL;
+
+ unload_nls(sbi->nls_tab);
truncate_inode_pages(sbi->direct_inode->i_mapping, 0);
iput(sbi->direct_inode);
- sbi->direct_inode = NULL;
kfree(sbi);
@@ -347,8 +345,7 @@
if (nls_map != (void *) -1) {
/* Discard old (if remount) */
- if (sbi->nls_tab)
- unload_nls(sbi->nls_tab);
+ unload_nls(sbi->nls_tab);
sbi->nls_tab = nls_map;
}
return 1;
diff --git a/fs/libfs.c b/fs/libfs.c
index dcec3d3..219576c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -527,14 +527,18 @@
const void *from, size_t available)
{
loff_t pos = *ppos;
+ size_t ret;
+
if (pos < 0)
return -EINVAL;
- if (pos >= available)
+ if (pos >= available || !count)
return 0;
if (count > available - pos)
count = available - pos;
- if (copy_to_user(to, from + pos, count))
+ ret = copy_to_user(to, from + pos, count);
+ if (ret == count)
return -EFAULT;
+ count -= ret;
*ppos = pos + count;
return count;
}
@@ -735,10 +739,11 @@
if (copy_from_user(attr->set_buf, buf, size))
goto out;
- ret = len; /* claim we got the whole input */
attr->set_buf[size] = '\0';
val = simple_strtol(attr->set_buf, NULL, 0);
- attr->set(attr->data, val);
+ ret = attr->set(attr->data, val);
+ if (ret == 0)
+ ret = len; /* on success, claim we got the whole input */
out:
mutex_unlock(&attr->mutex);
return ret;
diff --git a/fs/namespace.c b/fs/namespace.c
index 7230787..bdc3cb4 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1640,7 +1640,7 @@
{
struct vfsmount *mnt;
- if (!type || !memchr(type, 0, PAGE_SIZE))
+ if (!type)
return -EINVAL;
/* we need capabilities... */
@@ -1871,6 +1871,23 @@
return 0;
}
+int copy_mount_string(const void __user *data, char **where)
+{
+ char *tmp;
+
+ if (!data) {
+ *where = NULL;
+ return 0;
+ }
+
+ tmp = strndup_user(data, PAGE_SIZE);
+ if (IS_ERR(tmp))
+ return PTR_ERR(tmp);
+
+ *where = tmp;
+ return 0;
+}
+
/*
* Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
* be given to the mount() call (ie: read-only, no-dev, no-suid etc).
@@ -1900,8 +1917,6 @@
if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
return -EINVAL;
- if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))
- return -EINVAL;
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
@@ -2070,40 +2085,42 @@
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
{
- int retval;
+ int ret;
+ char *kernel_type;
+ char *kernel_dir;
+ char *kernel_dev;
unsigned long data_page;
- unsigned long type_page;
- unsigned long dev_page;
- char *dir_page;
- retval = copy_mount_options(type, &type_page);
- if (retval < 0)
- return retval;
+ ret = copy_mount_string(type, &kernel_type);
+ if (ret < 0)
+ goto out_type;
- dir_page = getname(dir_name);
- retval = PTR_ERR(dir_page);
- if (IS_ERR(dir_page))
- goto out1;
+ kernel_dir = getname(dir_name);
+ if (IS_ERR(kernel_dir)) {
+ ret = PTR_ERR(kernel_dir);
+ goto out_dir;
+ }
- retval = copy_mount_options(dev_name, &dev_page);
- if (retval < 0)
- goto out2;
+ ret = copy_mount_string(dev_name, &kernel_dev);
+ if (ret < 0)
+ goto out_dev;
- retval = copy_mount_options(data, &data_page);
- if (retval < 0)
- goto out3;
+ ret = copy_mount_options(data, &data_page);
+ if (ret < 0)
+ goto out_data;
- retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
- flags, (void *)data_page);
+ ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags,
+ (void *) data_page);
+
free_page(data_page);
-
-out3:
- free_page(dev_page);
-out2:
- putname(dir_page);
-out1:
- free_page(type_page);
- return retval;
+out_data:
+ kfree(kernel_dev);
+out_dev:
+ putname(kernel_dir);
+out_dir:
+ kfree(kernel_type);
+out_type:
+ return ret;
}
/*
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index b99ce20..cf98da1 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -746,16 +746,8 @@
#ifdef CONFIG_NCPFS_NLS
/* unload the NLS charsets */
- if (server->nls_vol)
- {
- unload_nls(server->nls_vol);
- server->nls_vol = NULL;
- }
- if (server->nls_io)
- {
- unload_nls(server->nls_io);
- server->nls_io = NULL;
- }
+ unload_nls(server->nls_vol);
+ unload_nls(server->nls_io);
#endif /* CONFIG_NCPFS_NLS */
if (server->info_filp)
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 53a7ed7..0d58caf 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -223,10 +223,8 @@
oldset_io = server->nls_io;
server->nls_io = iocharset;
- if (oldset_cp)
- unload_nls(oldset_cp);
- if (oldset_io)
- unload_nls(oldset_io);
+ unload_nls(oldset_cp);
+ unload_nls(oldset_io);
return 0;
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 060022b..faa0918 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -458,49 +458,21 @@
*/
static int nfs_vmtruncate(struct inode * inode, loff_t offset)
{
- if (i_size_read(inode) < offset) {
- unsigned long limit;
+ loff_t oldsize;
+ int err;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out_big;
- spin_lock(&inode->i_lock);
- i_size_write(inode, offset);
- spin_unlock(&inode->i_lock);
- } else {
- struct address_space *mapping = inode->i_mapping;
+ err = inode_newsize_ok(inode, offset);
+ if (err)
+ goto out;
- /*
- * truncation of in-use swapfiles is disallowed - it would
- * cause subsequent swapout to scribble on the now-freed
- * blocks.
- */
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
- spin_lock(&inode->i_lock);
- i_size_write(inode, offset);
- spin_unlock(&inode->i_lock);
+ spin_lock(&inode->i_lock);
+ oldsize = inode->i_size;
+ i_size_write(inode, offset);
+ spin_unlock(&inode->i_lock);
- /*
- * unmap_mapping_range is called twice, first simply for
- * efficiency so that truncate_inode_pages does fewer
- * single-page unmaps. However after this first call, and
- * before truncate_inode_pages finishes, it is possible for
- * private pages to be COWed, which remain after
- * truncate_inode_pages finishes, hence the second
- * unmap_mapping_range call must be made for correctness.
- */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- }
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out_big:
- return -EFBIG;
+ truncate_pagecache(inode, oldsize, offset);
+out:
+ return err;
}
/**
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 477d37d..2224b4d 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -270,7 +270,8 @@
void unload_nls(struct nls_table *nls)
{
- module_put(nls->owner);
+ if (nls)
+ module_put(nls->owner);
}
static const wchar_t charset2uni[256] = {
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index abaaa1c..80b0477 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -201,8 +201,7 @@
v, old_nls->charset);
nls_map = old_nls;
} else /* nls_map */ {
- if (old_nls)
- unload_nls(old_nls);
+ unload_nls(old_nls);
}
} else if (!strcmp(p, "utf8")) {
bool val = false;
@@ -2427,10 +2426,9 @@
ntfs_free(vol->upcase);
vol->upcase = NULL;
}
- if (vol->nls_map) {
- unload_nls(vol->nls_map);
- vol->nls_map = NULL;
- }
+
+ unload_nls(vol->nls_map);
+
sb->s_fs_info = NULL;
kfree(vol);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 11f0c06..32fae40 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -69,14 +69,11 @@
/* make various checks */
order = get_order(newsize);
if (unlikely(order >= MAX_ORDER))
- goto too_big;
+ return -EFBIG;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && newsize > limit)
- goto fsize_exceeded;
-
- if (newsize > inode->i_sb->s_maxbytes)
- goto too_big;
+ ret = inode_newsize_ok(inode, newsize);
+ if (ret)
+ return ret;
i_size_write(inode, newsize);
@@ -118,12 +115,7 @@
return 0;
- fsize_exceeded:
- send_sig(SIGXFSZ, current, 0);
- too_big:
- return -EFBIG;
-
- add_error:
+add_error:
while (loop < npages)
__free_page(pages + loop++);
return ret;
diff --git a/fs/read_write.c b/fs/read_write.c
index 6c8c55d..3ac2898 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -839,9 +839,6 @@
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
pos = *ppos;
- retval = -EINVAL;
- if (unlikely(pos < 0))
- goto fput_out;
if (unlikely(pos + count > max)) {
retval = -EOVERFLOW;
if (pos >= max)
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 6c95927..eae7d9d 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -429,20 +429,21 @@
*/
int seq_path(struct seq_file *m, struct path *path, char *esc)
{
- if (m->count < m->size) {
- char *s = m->buf + m->count;
- char *p = d_path(path, s, m->size - m->count);
+ char *buf;
+ size_t size = seq_get_buf(m, &buf);
+ int res = -1;
+
+ if (size) {
+ char *p = d_path(path, buf, size);
if (!IS_ERR(p)) {
- s = mangle_path(s, p, esc);
- if (s) {
- p = m->buf + m->count;
- m->count = s - m->buf;
- return s - p;
- }
+ char *end = mangle_path(buf, p, esc);
+ if (end)
+ res = end - buf;
}
}
- m->count = m->size;
- return -1;
+ seq_commit(m, res);
+
+ return res;
}
EXPORT_SYMBOL(seq_path);
@@ -454,26 +455,28 @@
int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
char *esc)
{
- int err = -ENAMETOOLONG;
- if (m->count < m->size) {
- char *s = m->buf + m->count;
+ char *buf;
+ size_t size = seq_get_buf(m, &buf);
+ int res = -ENAMETOOLONG;
+
+ if (size) {
char *p;
spin_lock(&dcache_lock);
- p = __d_path(path, root, s, m->size - m->count);
+ p = __d_path(path, root, buf, size);
spin_unlock(&dcache_lock);
- err = PTR_ERR(p);
+ res = PTR_ERR(p);
if (!IS_ERR(p)) {
- s = mangle_path(s, p, esc);
- if (s) {
- p = m->buf + m->count;
- m->count = s - m->buf;
- return 0;
- }
+ char *end = mangle_path(buf, p, esc);
+ if (end)
+ res = end - buf;
+ else
+ res = -ENAMETOOLONG;
}
}
- m->count = m->size;
- return err;
+ seq_commit(m, res);
+
+ return res < 0 ? res : 0;
}
/*
@@ -481,20 +484,21 @@
*/
int seq_dentry(struct seq_file *m, struct dentry *dentry, char *esc)
{
- if (m->count < m->size) {
- char *s = m->buf + m->count;
- char *p = dentry_path(dentry, s, m->size - m->count);
+ char *buf;
+ size_t size = seq_get_buf(m, &buf);
+ int res = -1;
+
+ if (size) {
+ char *p = dentry_path(dentry, buf, size);
if (!IS_ERR(p)) {
- s = mangle_path(s, p, esc);
- if (s) {
- p = m->buf + m->count;
- m->count = s - m->buf;
- return s - p;
- }
+ char *end = mangle_path(buf, p, esc);
+ if (end)
+ res = end - buf;
}
}
- m->count = m->size;
- return -1;
+ seq_commit(m, res);
+
+ return res;
}
int seq_bitmap(struct seq_file *m, const unsigned long *bits,
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index 1402d2d..1c4c8f0 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -459,14 +459,8 @@
static void
smb_unload_nls(struct smb_sb_info *server)
{
- if (server->remote_nls) {
- unload_nls(server->remote_nls);
- server->remote_nls = NULL;
- }
- if (server->local_nls) {
- unload_nls(server->local_nls);
- server->local_nls = NULL;
- }
+ unload_nls(server->remote_nls);
+ unload_nls(server->local_nls);
}
static void
diff --git a/fs/super.c b/fs/super.c
index 0e7207b..19eb70b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -465,6 +465,48 @@
}
EXPORT_SYMBOL(get_super);
+
+/**
+ * get_active_super - get an active reference to the superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device given. Returns the superblock with an active
+ * reference and s_umount held exclusively or %NULL if none was found.
+ */
+struct super_block *get_active_super(struct block_device *bdev)
+{
+ struct super_block *sb;
+
+ if (!bdev)
+ return NULL;
+
+ spin_lock(&sb_lock);
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ if (sb->s_bdev != bdev)
+ continue;
+
+ sb->s_count++;
+ spin_unlock(&sb_lock);
+ down_write(&sb->s_umount);
+ if (sb->s_root) {
+ spin_lock(&sb_lock);
+ if (sb->s_count > S_BIAS) {
+ atomic_inc(&sb->s_active);
+ sb->s_count--;
+ spin_unlock(&sb_lock);
+ return sb;
+ }
+ spin_unlock(&sb_lock);
+ }
+ up_write(&sb->s_umount);
+ put_super(sb);
+ yield();
+ spin_lock(&sb_lock);
+ }
+ spin_unlock(&sb_lock);
+ return NULL;
+}
struct super_block * user_get_super(dev_t dev)
{
@@ -527,11 +569,15 @@
{
int retval;
int remount_rw;
-
+
+ if (sb->s_frozen != SB_UNFROZEN)
+ return -EBUSY;
+
#ifdef CONFIG_BLOCK
if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
return -EACCES;
#endif
+
if (flags & MS_RDONLY)
acct_auto_close(sb);
shrink_dcache_sb(sb);
@@ -743,9 +789,14 @@
* will protect the lockfs code from trying to start a snapshot
* while we are mounting
*/
- down(&bdev->bd_mount_sem);
+ mutex_lock(&bdev->bd_fsfreeze_mutex);
+ if (bdev->bd_fsfreeze_count > 0) {
+ mutex_unlock(&bdev->bd_fsfreeze_mutex);
+ error = -EBUSY;
+ goto error_bdev;
+ }
s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
- up(&bdev->bd_mount_sem);
+ mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s))
goto error_s;
@@ -892,6 +943,16 @@
if (error)
goto out_sb;
+ /*
+ * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
+ * but s_maxbytes was an unsigned long long for many releases. Throw
+ * this warning for a little while to try and catch filesystems that
+ * violate this rule. This warning should be either removed or
+ * converted to a BUG() in 2.6.34.
+ */
+ WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
+ "negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes);
+
mnt->mnt_mountpoint = mnt->mnt_root;
mnt->mnt_parent = mnt;
up_write(&mnt->mnt_sb->s_umount);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 78e95b8..2adaa25 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -641,7 +641,6 @@
struct super_block * bd_super;
int bd_openers;
struct mutex bd_mutex; /* open/close mutex */
- struct semaphore bd_mount_sem;
struct list_head bd_inodes;
void * bd_holder;
int bd_holders;
@@ -1316,7 +1315,7 @@
unsigned long s_blocksize;
unsigned char s_blocksize_bits;
unsigned char s_dirt;
- unsigned long long s_maxbytes; /* Max file size */
+ loff_t s_maxbytes; /* Max file size */
struct file_system_type *s_type;
const struct super_operations *s_op;
const struct dquot_operations *dq_op;
@@ -2157,6 +2156,7 @@
extern int inode_needs_sync(struct inode *inode);
extern void generic_delete_inode(struct inode *inode);
extern void generic_drop_inode(struct inode *inode);
+extern int generic_detach_inode(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
@@ -2335,6 +2335,7 @@
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
+extern struct super_block *get_active_super(struct block_device *bdev);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);
@@ -2382,7 +2383,8 @@
#define buffer_migrate_page NULL
#endif
-extern int inode_change_ok(struct inode *, struct iattr *);
+extern int inode_change_ok(const struct inode *, struct iattr *);
+extern int inode_newsize_ok(const struct inode *, loff_t offset);
extern int __must_check inode_setattr(struct inode *, struct iattr *);
extern void file_update_time(struct file *file);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6953a5a..df08551 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -792,8 +792,9 @@
unmap_mapping_range(mapping, holebegin, holelen, 0);
}
-extern int vmtruncate(struct inode * inode, loff_t offset);
-extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
+extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+extern int vmtruncate(struct inode *inode, loff_t offset);
+extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
int generic_error_remove_page(struct address_space *mapping, struct page *page);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 0c6a86b..8366d8f 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -35,6 +35,44 @@
#define SEQ_SKIP 1
+/**
+ * seq_get_buf - get buffer to write arbitrary data to
+ * @m: the seq_file handle
+ * @bufp: the beginning of the buffer is stored here
+ *
+ * Return the number of bytes available in the buffer, or zero if
+ * there's no space.
+ */
+static inline size_t seq_get_buf(struct seq_file *m, char **bufp)
+{
+ BUG_ON(m->count > m->size);
+ if (m->count < m->size)
+ *bufp = m->buf + m->count;
+ else
+ *bufp = NULL;
+
+ return m->size - m->count;
+}
+
+/**
+ * seq_commit - commit data to the buffer
+ * @m: the seq_file handle
+ * @num: the number of bytes to commit
+ *
+ * Commit @num bytes of data written to a buffer previously acquired
+ * by seq_buf_get. To signal an error condition, or that the data
+ * didn't fit in the available space, pass a negative @num value.
+ */
+static inline void seq_commit(struct seq_file *m, int num)
+{
+ if (num < 0) {
+ m->count = m->size;
+ } else {
+ BUG_ON(m->count + num > m->size);
+ m->count += num;
+ }
+}
+
char *mangle_path(char *s, char *p, char *esc);
int seq_open(struct file *, const struct seq_operations *);
ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
diff --git a/mm/filemap.c b/mm/filemap.c
index c1fc205..6c84e59 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -58,7 +58,7 @@
/*
* Lock ordering:
*
- * ->i_mmap_lock (vmtruncate)
+ * ->i_mmap_lock (truncate_pagecache)
* ->private_lock (__free_pte->__set_page_dirty_buffers)
* ->swap_lock (exclusive_swap_page, others)
* ->mapping->tree_lock
diff --git a/mm/memory.c b/mm/memory.c
index 987389a..7e91b5f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -297,7 +297,8 @@
unsigned long addr = vma->vm_start;
/*
- * Hide vma from rmap and vmtruncate before freeing pgtables
+ * Hide vma from rmap and truncate_pagecache before freeing
+ * pgtables
*/
anon_vma_unlink(vma);
unlink_file_vma(vma);
@@ -2408,7 +2409,7 @@
* @mapping: the address space containing mmaps to be unmapped.
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
- * boundary. Note that this is different from vmtruncate(), which
+ * boundary. Note that this is different from truncate_pagecache(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
@@ -2459,63 +2460,6 @@
}
EXPORT_SYMBOL(unmap_mapping_range);
-/**
- * vmtruncate - unmap mappings "freed" by truncate() syscall
- * @inode: inode of the file used
- * @offset: file offset to start truncating
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode * inode, loff_t offset)
-{
- if (inode->i_size < offset) {
- unsigned long limit;
-
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out_big;
- i_size_write(inode, offset);
- } else {
- struct address_space *mapping = inode->i_mapping;
-
- /*
- * truncation of in-use swapfiles is disallowed - it would
- * cause subsequent swapout to scribble on the now-freed
- * blocks.
- */
- if (IS_SWAPFILE(inode))
- return -ETXTBSY;
- i_size_write(inode, offset);
-
- /*
- * unmap_mapping_range is called twice, first simply for
- * efficiency so that truncate_inode_pages does fewer
- * single-page unmaps. However after this first call, and
- * before truncate_inode_pages finishes, it is possible for
- * private pages to be COWed, which remain after
- * truncate_inode_pages finishes, hence the second
- * unmap_mapping_range call must be made for correctness.
- */
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- truncate_inode_pages(mapping, offset);
- unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
- }
-
- if (inode->i_op->truncate)
- inode->i_op->truncate(inode);
- return 0;
-
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out_big:
- return -EFBIG;
-}
-EXPORT_SYMBOL(vmtruncate);
-
int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
diff --git a/mm/mremap.c b/mm/mremap.c
index 20a07db..97bff25 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -86,8 +86,8 @@
if (vma->vm_file) {
/*
* Subtle point from Rajesh Venkatasubramanian: before
- * moving file-based ptes, we must lock vmtruncate out,
- * since it might clean the dst vma before the src vma,
+ * moving file-based ptes, we must lock truncate_pagecache
+ * out, since it might clean the dst vma before the src vma,
* and we propagate stale pages into the dst afterward.
*/
mapping = vma->vm_file->f_mapping;
diff --git a/mm/nommu.c b/mm/nommu.c
index 8d48424..56a446f 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -83,46 +83,6 @@
};
/*
- * Handle all mappings that got truncated by a "truncate()"
- * system call.
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page. Ugly, but necessary.
- */
-int vmtruncate(struct inode *inode, loff_t offset)
-{
- struct address_space *mapping = inode->i_mapping;
- unsigned long limit;
-
- if (inode->i_size < offset)
- goto do_expand;
- i_size_write(inode, offset);
-
- truncate_inode_pages(mapping, offset);
- goto out_truncate;
-
-do_expand:
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (limit != RLIM_INFINITY && offset > limit)
- goto out_sig;
- if (offset > inode->i_sb->s_maxbytes)
- goto out;
- i_size_write(inode, offset);
-
-out_truncate:
- if (inode->i_op->truncate)
- inode->i_op->truncate(inode);
- return 0;
-out_sig:
- send_sig(SIGXFSZ, current, 0);
-out:
- return -EFBIG;
-}
-
-EXPORT_SYMBOL(vmtruncate);
-
-/*
* Return the total memory allocated for this pointer, not
* just what the caller asked for.
*
diff --git a/mm/truncate.c b/mm/truncate.c
index a17b397..450cebd 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -497,3 +497,67 @@
return invalidate_inode_pages2_range(mapping, 0, -1);
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
+
+/**
+ * truncate_pagecache - unmap and remove pagecache that has been truncated
+ * @inode: inode
+ * @old: old file offset
+ * @new: new file offset
+ *
+ * inode's new i_size must already be written before truncate_pagecache
+ * is called.
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
+{
+ if (new < old) {
+ struct address_space *mapping = inode->i_mapping;
+
+ /*
+ * unmap_mapping_range is called twice, first simply for
+ * efficiency so that truncate_inode_pages does fewer
+ * single-page unmaps. However after this first call, and
+ * before truncate_inode_pages finishes, it is possible for
+ * private pages to be COWed, which remain after
+ * truncate_inode_pages finishes, hence the second
+ * unmap_mapping_range call must be made for correctness.
+ */
+ unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, new);
+ unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+ }
+}
+EXPORT_SYMBOL(truncate_pagecache);
+
+/**
+ * vmtruncate - unmap mappings "freed" by truncate() syscall
+ * @inode: inode of the file used
+ * @offset: file offset to start truncating
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page. Ugly, but necessary.
+ */
+int vmtruncate(struct inode *inode, loff_t offset)
+{
+ loff_t oldsize;
+ int error;
+
+ error = inode_newsize_ok(inode, offset);
+ if (error)
+ return error;
+ oldsize = inode->i_size;
+ i_size_write(inode, offset);
+ truncate_pagecache(inode, oldsize, offset);
+ if (inode->i_op->truncate)
+ inode->i_op->truncate(inode);
+
+ return error;
+}
+EXPORT_SYMBOL(vmtruncate);