summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/dev-ioctl.c2
-rw-r--r--fs/binfmt_elf.c60
-rw-r--r--fs/btrfs/inode.c24
-rw-r--r--fs/btrfs/super.c2
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/ceph/addr.c24
-rw-r--r--fs/ceph/cache.c12
-rw-r--r--fs/ceph/dir.c5
-rw-r--r--fs/cifs/dir.c18
-rw-r--r--fs/cifs/smb1ops.c9
-rw-r--r--fs/cifs/smb2ops.c4
-rw-r--r--fs/cifs/smb2pdu.c4
-rw-r--r--fs/cifs/smb2pdu.h4
-rw-r--r--fs/configfs/symlink.c3
-rw-r--r--fs/coredump.c18
-rw-r--r--fs/dcache.c32
-rw-r--r--fs/debugfs/inode.c10
-rw-r--r--fs/dlm/user.c4
-rw-r--r--fs/eventpoll.c37
-rw-r--r--fs/exec.c35
-rw-r--r--fs/ext4/file.c3
-rw-r--r--fs/ext4/resize.c3
-rw-r--r--fs/ext4/sysfs.c2
-rw-r--r--fs/f2fs/acl.c2
-rw-r--r--fs/f2fs/super.c16
-rw-r--r--fs/fcntl.c14
-rw-r--r--fs/fuse/file.c2
-rw-r--r--fs/gfs2/glock.c11
-rw-r--r--fs/gfs2/incore.h1
-rw-r--r--fs/hugetlbfs/inode.c2
-rw-r--r--fs/mount.h1
-rw-r--r--fs/namei.c8
-rw-r--r--fs/namespace.c1
-rw-r--r--fs/nfs/Kconfig1
-rw-r--r--fs/nfs/dir.c12
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c1
-rw-r--r--fs/nfs/inode.c4
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/nfs/pagelist.c26
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfsd/nfs4xdr.c6
-rw-r--r--fs/notify/fsnotify.c8
-rw-r--r--fs/ocfs2/cluster/heartbeat.c8
-rw-r--r--fs/open.c6
-rw-r--r--fs/pnode.c212
-rw-r--r--fs/proc/task_mmu.c4
-rw-r--r--fs/pstore/ram.c5
-rw-r--r--fs/pstore/ram_core.c25
-rw-r--r--fs/seq_file.c7
-rw-r--r--fs/udf/inode.c4
-rw-r--r--fs/xfs/xfs_aops.c21
-rw-r--r--fs/xfs/xfs_linux.h9
53 files changed, 538 insertions, 201 deletions
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index ac7d921ed984..257425511d10 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -331,7 +331,7 @@ static int autofs_dev_ioctl_fail(struct file *fp,
int status;
token = (autofs_wqt_t) param->fail.token;
- status = param->fail.status ? param->fail.status : -ENOENT;
+ status = param->fail.status < 0 ? param->fail.status : -ENOENT;
return autofs4_wait_release(sbi, token, status);
}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3a93755e880f..f44e93d2650d 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -905,17 +905,60 @@ static int load_elf_binary(struct linux_binprm *bprm)
elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
vaddr = elf_ppnt->p_vaddr;
+ /*
+ * If we are loading ET_EXEC or we have already performed
+ * the ET_DYN load_addr calculations, proceed normally.
+ */
if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
} else if (loc->elf_ex.e_type == ET_DYN) {
- /* Try and get dynamic programs out of the way of the
- * default mmap base, as well as whatever program they
- * might try to exec. This is because the brk will
- * follow the loader, and is not movable. */
- load_bias = ELF_ET_DYN_BASE - vaddr;
- if (current->flags & PF_RANDOMIZE)
- load_bias += arch_mmap_rnd();
- load_bias = ELF_PAGESTART(load_bias);
+ /*
+ * This logic is run once for the first LOAD Program
+ * Header for ET_DYN binaries to calculate the
+ * randomization (load_bias) for all the LOAD
+ * Program Headers, and to calculate the entire
+ * size of the ELF mapping (total_size). (Note that
+ * load_addr_set is set to true later once the
+ * initial mapping is performed.)
+ *
+ * There are effectively two types of ET_DYN
+ * binaries: programs (i.e. PIE: ET_DYN with INTERP)
+ * and loaders (ET_DYN without INTERP, since they
+ * _are_ the ELF interpreter). The loaders must
+ * be loaded away from programs since the program
+ * may otherwise collide with the loader (especially
+ * for ET_EXEC which does not have a randomized
+ * position). For example to handle invocations of
+ * "./ld.so someprog" to test out a new version of
+ * the loader, the subsequent program that the
+ * loader loads must avoid the loader itself, so
+ * they cannot share the same load range. Sufficient
+ * room for the brk must be allocated with the
+ * loader as well, since brk must be available with
+ * the loader.
+ *
+ * Therefore, programs are loaded offset from
+ * ELF_ET_DYN_BASE and loaders are loaded into the
+ * independently randomized mmap region (0 load_bias
+ * without MAP_FIXED).
+ */
+ if (elf_interpreter) {
+ load_bias = ELF_ET_DYN_BASE;
+ if (current->flags & PF_RANDOMIZE)
+ load_bias += arch_mmap_rnd();
+ elf_flags |= MAP_FIXED;
+ } else
+ load_bias = 0;
+
+ /*
+ * Since load_bias is used for all subsequent loading
+ * calculations, we must lower it by the first vaddr
+ * so that the remaining calculations based on the
+ * ELF vaddrs will be correctly offset. The result
+ * is then page aligned.
+ */
+ load_bias = ELF_PAGESTART(load_bias - vaddr);
+
total_size = total_mapping_size(elf_phdata,
loc->elf_ex.e_phnum);
if (!total_size) {
@@ -2295,6 +2338,7 @@ static int elf_core_dump(struct coredump_params *cprm)
goto end_coredump;
}
}
+ dump_truncate(cprm);
if (!elf_core_write_extra_data(cprm))
goto end_coredump;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 863fa0f1972b..bebd6517355d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4397,8 +4397,19 @@ search_again:
if (found_type > min_type) {
del_item = 1;
} else {
- if (item_end < new_size)
+ if (item_end < new_size) {
+ /*
+ * With NO_HOLES mode, for the following mapping
+ *
+ * [0-4k][hole][8k-12k]
+ *
+ * if truncating isize down to 6k, it ends up
+ * isize being 8k.
+ */
+ if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+ last_size = new_size;
break;
+ }
if (found_key.offset >= new_size)
del_item = 1;
else
@@ -7510,11 +7521,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode,
* within our reservation, otherwise we need to adjust our inode
* counter appropriately.
*/
- if (dio_data->outstanding_extents) {
+ if (dio_data->outstanding_extents >= num_extents) {
dio_data->outstanding_extents -= num_extents;
} else {
+ /*
+ * If dio write length has been split due to no large enough
+ * contiguous space, we need to compensate our inode counter
+ * appropriately.
+ */
+ u64 num_needed = num_extents - dio_data->outstanding_extents;
+
spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->outstanding_extents += num_extents;
+ BTRFS_I(inode)->outstanding_extents += num_needed;
spin_unlock(&BTRFS_I(inode)->lock);
}
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 5d34a062ca4f..3bd2233737ac 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1727,6 +1727,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
goto restore;
}
+ btrfs_qgroup_rescan_resume(fs_info);
+
if (!fs_info->uuid_root) {
btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9c62a6f9757a..600c67ef8a03 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
},
};
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
[BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
[BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c6a1ec110c01..22bae2b434e2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -189,7 +189,7 @@ static int ceph_releasepage(struct page *page, gfp_t g)
/*
* read a single page, without unlocking it.
*/
-static int readpage_nounlock(struct file *filp, struct page *page)
+static int ceph_do_readpage(struct file *filp, struct page *page)
{
struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -219,7 +219,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
err = ceph_readpage_from_fscache(inode, page);
if (err == 0)
- goto out;
+ return -EINPROGRESS;
dout("readpage inode %p file %p page %p index %lu\n",
inode, filp, page, page->index);
@@ -249,8 +249,11 @@ out:
static int ceph_readpage(struct file *filp, struct page *page)
{
- int r = readpage_nounlock(filp, page);
- unlock_page(page);
+ int r = ceph_do_readpage(filp, page);
+ if (r != -EINPROGRESS)
+ unlock_page(page);
+ else
+ r = 0;
return r;
}
@@ -1094,7 +1097,7 @@ retry_locked:
goto retry_locked;
r = writepage_nounlock(page, NULL);
if (r < 0)
- goto fail_nosnap;
+ goto fail_unlock;
goto retry_locked;
}
@@ -1122,11 +1125,14 @@ retry_locked:
}
/* we need to read it. */
- r = readpage_nounlock(file, page);
- if (r < 0)
- goto fail_nosnap;
+ r = ceph_do_readpage(file, page);
+ if (r < 0) {
+ if (r == -EINPROGRESS)
+ return -EAGAIN;
+ goto fail_unlock;
+ }
goto retry_locked;
-fail_nosnap:
+fail_unlock:
unlock_page(page);
return r;
}
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index a4766ded1ba7..ff1cfd7b1083 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -224,13 +224,7 @@ void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci)
fscache_relinquish_cookie(cookie, 0);
}
-static void ceph_vfs_readpage_complete(struct page *page, void *data, int error)
-{
- if (!error)
- SetPageUptodate(page);
-}
-
-static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error)
+static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error)
{
if (!error)
SetPageUptodate(page);
@@ -259,7 +253,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page)
return -ENOBUFS;
ret = fscache_read_or_alloc_page(ci->fscache, page,
- ceph_vfs_readpage_complete, NULL,
+ ceph_readpage_from_fscache_complete, NULL,
GFP_KERNEL);
switch (ret) {
@@ -288,7 +282,7 @@ int ceph_readpages_from_fscache(struct inode *inode,
return -ENOBUFS;
ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages,
- ceph_vfs_readpage_complete_unlock,
+ ceph_readpage_from_fscache_complete,
NULL, mapping_gfp_mask(mapping));
switch (ret) {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 9314b4ea2375..be7d187d53fd 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -247,6 +247,11 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx,
if (ret < 0)
err = ret;
dput(last);
+ /* last_name no longer match cache index */
+ if (fi->readdir_cache_idx >= 0) {
+ fi->readdir_cache_idx = -1;
+ fi->dir_release_count = 0;
+ }
}
return err;
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 26a3b389a265..297e05c9e2b0 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -183,15 +183,20 @@ cifs_bp_rename_retry:
}
/*
+ * Don't allow path components longer than the server max.
* Don't allow the separator character in a path component.
* The VFS will not allow "/", but "\" is allowed by posix.
*/
static int
-check_name(struct dentry *direntry)
+check_name(struct dentry *direntry, struct cifs_tcon *tcon)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
int i;
+ if (unlikely(direntry->d_name.len >
+ le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
+ return -ENAMETOOLONG;
+
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
for (i = 0; i < direntry->d_name.len; i++) {
if (direntry->d_name.name[i] == '\\') {
@@ -489,10 +494,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
return finish_no_open(file, res);
}
- rc = check_name(direntry);
- if (rc)
- return rc;
-
xid = get_xid();
cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
@@ -505,6 +506,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
}
tcon = tlink_tcon(tlink);
+
+ rc = check_name(direntry, tcon);
+ if (rc)
+ goto out_free_xid;
+
server = tcon->ses->server;
if (server->ops->new_lease_key)
@@ -765,7 +771,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
}
pTcon = tlink_tcon(tlink);
- rc = check_name(direntry);
+ rc = check_name(direntry, pTcon);
if (rc)
goto lookup_out;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 87b87e091e8e..efd72e1fae74 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid *fid, __u16 search_flags,
struct cifs_search_info *srch_inf)
{
- return CIFSFindFirst(xid, tcon, path, cifs_sb,
- &fid->netfid, search_flags, srch_inf, true);
+ int rc;
+
+ rc = CIFSFindFirst(xid, tcon, path, cifs_sb,
+ &fid->netfid, search_flags, srch_inf, true);
+ if (rc)
+ cifs_dbg(FYI, "find first failed=%d\n", rc);
+ return rc;
}
static int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 087918c4612a..1d125d3d0d89 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -909,7 +909,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
kfree(utf16_path);
if (rc) {
- cifs_dbg(VFS, "open dir failed\n");
+ cifs_dbg(FYI, "open dir failed rc=%d\n", rc);
return rc;
}
@@ -919,7 +919,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_query_directory(xid, tcon, fid->persistent_fid,
fid->volatile_fid, 0, srch_inf);
if (rc) {
- cifs_dbg(VFS, "query directory failed\n");
+ cifs_dbg(FYI, "query directory failed rc=%d\n", rc);
SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
}
return rc;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index f4afa3b1cc56..6c484ddf26a9 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2768,8 +2768,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits);
- kst->f_bfree = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits);
- kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
+ kst->f_bfree = kst->f_bavail =
+ le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits);
return;
}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index b8f553b32dda..aacb15bd56fe 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -82,8 +82,8 @@
#define NUMBER_OF_SMB2_COMMANDS 0x0013
-/* BB FIXME - analyze following length BB */
-#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
+/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
+#define MAX_SMB2_HDR_SIZE 0x00b0
#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index ec5c8325b503..0525ebc3aea2 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -83,14 +83,13 @@ static int create_link(struct config_item *parent_item,
ret = -ENOMEM;
sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
if (sl) {
- sl->sl_target = config_item_get(item);
spin_lock(&configfs_dirent_lock);
if (target_sd->s_type & CONFIGFS_USET_DROPPING) {
spin_unlock(&configfs_dirent_lock);
- config_item_put(item);
kfree(sl);
return -ENOENT;
}
+ sl->sl_target = config_item_get(item);
list_add(&sl->sl_list, &target_sd->s_links);
spin_unlock(&configfs_dirent_lock);
ret = configfs_create_link(sl, parent_item->ci_dentry,
diff --git a/fs/coredump.c b/fs/coredump.c
index 5d15c4975ba1..a8852293038a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -810,3 +810,21 @@ int dump_align(struct coredump_params *cprm, int align)
return mod ? dump_skip(cprm, align - mod) : 1;
}
EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+ struct file *file = cprm->file;
+ loff_t offset;
+
+ if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+ offset = file->f_op->llseek(file, 0, SEEK_CUR);
+ if (i_size_read(file->f_mapping->host) < offset)
+ do_truncate(file->f_path.dentry, offset, 0, file);
+ }
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/fs/dcache.c b/fs/dcache.c
index 849c1c1e787b..3ed642e0a0c2 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -269,6 +269,33 @@ static inline int dname_external(const struct dentry *dentry)
return dentry->d_name.name != dentry->d_iname;
}
+void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
+{
+ spin_lock(&dentry->d_lock);
+ if (unlikely(dname_external(dentry))) {
+ struct external_name *p = external_name(dentry);
+ atomic_inc(&p->u.count);
+ spin_unlock(&dentry->d_lock);
+ name->name = p->name;
+ } else {
+ memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
+ spin_unlock(&dentry->d_lock);
+ name->name = name->inline_name;
+ }
+}
+EXPORT_SYMBOL(take_dentry_name_snapshot);
+
+void release_dentry_name_snapshot(struct name_snapshot *name)
+{
+ if (unlikely(name->name != name->inline_name)) {
+ struct external_name *p;
+ p = container_of(name->name, struct external_name, name[0]);
+ if (unlikely(atomic_dec_and_test(&p->u.count)))
+ kfree_rcu(p, u.head);
+ }
+}
+EXPORT_SYMBOL(release_dentry_name_snapshot);
+
static inline void __d_set_inode_and_type(struct dentry *dentry,
struct inode *inode,
unsigned type_flags)
@@ -1128,11 +1155,12 @@ void shrink_dcache_sb(struct super_block *sb)
LIST_HEAD(dispose);
freed = list_lru_walk(&sb->s_dentry_lru,
- dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+ dentry_lru_isolate_shrink, &dispose, 1024);
this_cpu_sub(nr_dentry_unused, freed);
shrink_dentry_list(&dispose);
- } while (freed > 0);
+ cond_resched();
+ } while (list_lru_count(&sb->s_dentry_lru) > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 0f5d05bf2131..e49ba072bd64 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -669,7 +669,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
{
int error;
struct dentry *dentry = NULL, *trap;
- const char *old_name;
+ struct name_snapshot old_name;
trap = lock_rename(new_dir, old_dir);
/* Source or destination directories don't exist? */
@@ -684,19 +684,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
goto exit;
- old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+ take_dentry_name_snapshot(&old_name, old_dentry);
error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
dentry);
if (error) {
- fsnotify_oldname_free(old_name);
+ release_dentry_name_snapshot(&old_name);
goto exit;
}
d_move(old_dentry, dentry);
- fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name,
+ fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name,
d_is_dir(old_dentry),
NULL, old_dentry);
- fsnotify_oldname_free(old_name);
+ release_dentry_name_snapshot(&old_name);
unlock_rename(new_dir, old_dir);
dput(dentry);
return old_dentry;
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 173b3873a4f4..e40c440a4555 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -355,6 +355,10 @@ static int dlm_device_register(struct dlm_ls *ls, char *name)
error = misc_register(&ls->ls_device);
if (error) {
kfree(ls->ls_device.name);
+ /* this has to be set to NULL
+ * to avoid a double-free in dlm_device_deregister
+ */
+ ls->ls_device.name = NULL;
}
fail:
return error;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..1b08556776ce 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -518,8 +518,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq)
wait_queue_head_t *whead;
rcu_read_lock();
- /* If it is cleared by POLLFREE, it should be rcu-safe */
- whead = rcu_dereference(pwq->whead);
+ /*
+ * If it is cleared by POLLFREE, it should be rcu-safe.
+ * If we read NULL we need a barrier paired with
+ * smp_store_release() in ep_poll_callback(), otherwise
+ * we rely on whead->lock.
+ */
+ whead = smp_load_acquire(&pwq->whead);
if (whead)
remove_wait_queue(whead, &pwq->wait);
rcu_read_unlock();
@@ -1003,17 +1008,6 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
- if ((unsigned long)key & POLLFREE) {
- ep_pwq_from_wait(wait)->whead = NULL;
- /*
- * whead = NULL above can race with ep_remove_wait_queue()
- * which can do another remove_wait_queue() after us, so we
- * can't use __remove_wait_queue(). whead->lock is held by
- * the caller.
- */
- list_del_init(&wait->task_list);
- }
-
spin_lock_irqsave(&ep->lock, flags);
/*
@@ -1078,6 +1072,23 @@ out_unlock:
if (pwake)
ep_poll_safewake(&ep->poll_wait);
+
+ if ((unsigned long)key & POLLFREE) {
+ /*
+ * If we race with ep_remove_wait_queue() it can miss
+ * ->whead = NULL and do another remove_wait_queue() after
+ * us, so we can't use __remove_wait_queue().
+ */
+ list_del_init(&wait->task_list);
+ /*
+ * ->whead != NULL protects us from the race with ep_free()
+ * or ep_remove(), ep_remove_wait_queue() takes whead->lock
+ * held by the caller. Once we nullify it, nothing protects
+ * ep/epi or even wait.
+ */
+ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
+ }
+
return 1;
}
diff --git a/fs/exec.c b/fs/exec.c
index 3a6de10d3891..9c5ee2a880aa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -206,7 +206,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
if (write) {
unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
- struct rlimit *rlim;
+ unsigned long ptr_size, limit;
+
+ /*
+ * Since the stack will hold pointers to the strings, we
+ * must account for them as well.
+ *
+ * The size calculation is the entire vma while each arg page is
+ * built, so each time we get here it's calculating how far it
+ * is currently (rather than each call being just the newly
+ * added size from the arg page). As a result, we need to
+ * always add the entire size of the pointers, so that on the
+ * last call to get_arg_page() we'll actually have the entire
+ * correct size.
+ */
+ ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+ if (ptr_size > ULONG_MAX - size)
+ goto fail;
+ size += ptr_size;
acct_arg_size(bprm, size / PAGE_SIZE);
@@ -218,20 +235,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
return page;
/*
- * Limit to 1/4-th the stack size for the argv+env strings.
+ * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
+ * (whichever is smaller) for the argv+env strings.
* This ensures that:
* - the remaining binfmt code will not run out of stack space,
* - the program will have a reasonable amount of stack left
* to work from.
*/
- rlim = current->signal->rlim;
- if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
- put_page(page);
- return NULL;
- }
+ limit = _STK_LIM / 4 * 3;
+ limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+ if (size > limit)
+ goto fail;
}
return page;
+
+fail:
+ put_page(page);
+ return NULL;
}
static void put_arg_page(struct page *page)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8772bfc3415b..45ef9975caec 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -500,6 +500,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
lastoff = page_offset(page);
bh = head = page_buffers(page);
do {
+ if (lastoff + bh->b_size <= startoff)
+ goto next;
if (buffer_uptodate(bh) ||
buffer_unwritten(bh)) {
if (whence == SEEK_DATA)
@@ -514,6 +516,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
unlock_page(page);
goto out;
}
+next:
lastoff += bh->b_size;
bh = bh->b_this_page;
} while (bh != head);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 34038e3598d5..74516efd874c 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1926,7 +1926,8 @@ retry:
n_desc_blocks = o_desc_blocks +
le16_to_cpu(es->s_reserved_gdt_blocks);
n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
- n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb);
+ n_blocks_count = (ext4_fsblk_t)n_group *
+ EXT4_BLOCKS_PER_GROUP(sb);
n_group--; /* set to last group number */
}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 5d09ea585840..c2ee23acf359 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a,
int ret;
ret = kstrtoull(skip_spaces(buf), 0, &val);
- if (!ret || val >= clusters)
+ if (ret || val >= clusters)
return -EINVAL;
atomic64_set(&sbi->s_resv_clusters, val);
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e9a8d676c6bc..83dcf7bfd7b8 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -213,7 +213,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
switch (type) {
case ACL_TYPE_ACCESS:
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
- if (acl) {
+ if (acl && !ipage) {
error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
if (error)
return error;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 86e1cb899957..4f666368aa85 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1078,6 +1078,8 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ unsigned int main_segs, blocks_per_seg;
+ int i;
total = le32_to_cpu(raw_super->segment_count);
fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1089,6 +1091,20 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
if (unlikely(fsmeta >= total))
return 1;
+ main_segs = le32_to_cpu(raw_super->segment_count_main);
+ blocks_per_seg = sbi->blocks_per_seg;
+
+ for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+ if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+ le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
+ return 1;
+ }
+ for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
+ if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
+ le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
+ return 1;
+ }
+
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
return 1;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ee85cd4e136a..62376451bbce 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -740,16 +740,10 @@ static int __init fcntl_init(void)
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
- O_RDONLY | O_WRONLY | O_RDWR |
- O_CREAT | O_EXCL | O_NOCTTY |
- O_TRUNC | O_APPEND | /* O_NONBLOCK | */
- __O_SYNC | O_DSYNC | FASYNC |
- O_DIRECT | O_LARGEFILE | O_DIRECTORY |
- O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC | O_PATH | __O_TMPFILE |
- __FMODE_NONOTIFY
- ));
+ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+ HWEIGHT32(
+ (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
+ __FMODE_EXEC | __FMODE_NONOTIFY));
fasync_cache = kmem_cache_create("fasync_cache",
sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 11538a8be9f0..1a063cbfe503 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
{
struct fuse_file *ff;
- ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
+ ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL);
if (unlikely(!ff))
return NULL;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9cd8c92b953d..070901e76653 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = {
static struct rhashtable gl_hash_table;
-void gfs2_glock_free(struct gfs2_glock *gl)
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
{
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
if (gl->gl_ops->go_flags & GLOF_ASPACE) {
kmem_cache_free(gfs2_glock_aspace_cachep, gl);
@@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl)
kfree(gl->gl_lksb.sb_lvbptr);
kmem_cache_free(gfs2_glock_cachep, gl);
}
+}
+
+void gfs2_glock_free(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+ call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
if (atomic_dec_and_test(&sdp->sd_glock_disposal))
wake_up(&sdp->sd_glock_wait);
}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index be519416c112..4a9077ec9313 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -367,6 +367,7 @@ struct gfs2_glock {
loff_t end;
} gl_vm;
};
+ struct rcu_head gl_rcu;
struct rhash_head gl_node;
};
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 595ebdb41846..a17da8b57fc6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -191,7 +191,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
diff --git a/fs/mount.h b/fs/mount.h
index 13a4ebbbaa74..37c64bbe840c 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -57,6 +57,7 @@ struct mount {
struct mnt_namespace *mnt_ns; /* containing namespace */
struct mountpoint *mnt_mp; /* where is it mounted */
struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */
+ struct list_head mnt_umounting; /* list entry for umount propagation */
#ifdef CONFIG_FSNOTIFY
struct hlist_head mnt_fsnotify_marks;
__u32 mnt_fsnotify_mask;
diff --git a/fs/namei.c b/fs/namei.c
index 0b0acba72a71..3f96ae087488 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4179,11 +4179,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
{
int error;
bool is_dir = d_is_dir(old_dentry);
- const unsigned char *old_name;
struct inode *source = old_dentry->d_inode;
struct inode *target = new_dentry->d_inode;
bool new_is_dir = false;
unsigned max_links = new_dir->i_sb->s_max_links;
+ struct name_snapshot old_name;
/*
* Check source == target.
@@ -4237,7 +4237,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (error)
return error;
- old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+ take_dentry_name_snapshot(&old_name, old_dentry);
dget(new_dentry);
if (!is_dir || (flags & RENAME_EXCHANGE))
lock_two_nondirectories(source, target);
@@ -4298,14 +4298,14 @@ out:
mutex_unlock(&target->i_mutex);
dput(new_dentry);
if (!error) {
- fsnotify_move(old_dir, new_dir, old_name, is_dir,
+ fsnotify_move(old_dir, new_dir, old_name.name, is_dir,
!(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
if (flags & RENAME_EXCHANGE) {
fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
new_is_dir, NULL, new_dentry);
}
}
- fsnotify_oldname_free(old_name);
+ release_dentry_name_snapshot(&old_name);
return error;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index f26d18d69712..ec4078d16eb7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -237,6 +237,7 @@ static struct mount *alloc_vfsmnt(const char *name)
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
INIT_HLIST_NODE(&mnt->mnt_mp_list);
+ INIT_LIST_HEAD(&mnt->mnt_umounting);
#ifdef CONFIG_FSNOTIFY
INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
#endif
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f31fd0dd92c6..b1daeafbea92 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT
config PNFS_BLOCK
tristate
depends on NFS_V4_1 && BLK_DEV_DM
+ depends on 64BIT || LBDAF
default NFS_V4
config PNFS_OBJLAYOUT
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 5b21b1ca2341..348e0a05bd18 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1135,11 +1135,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
/* Force a full look up iff the parent directory has changed */
if (!nfs_is_exclusive_create(dir, flags) &&
nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
-
- if (nfs_lookup_verify_inode(inode, flags)) {
+ error = nfs_lookup_verify_inode(inode, flags);
+ if (error) {
if (flags & LOOKUP_RCU)
return -ECHILD;
- goto out_zap_parent;
+ if (error == -ESTALE)
+ goto out_zap_parent;
+ goto out_error;
}
goto out_valid;
}
@@ -1163,8 +1165,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
- if (error)
+ if (error == -ESTALE || error == -ENOENT)
goto out_bad;
+ if (error)
+ goto out_error;
if (nfs_compare_fh(NFS_FH(inode), fhandle))
goto out_bad;
if ((error = nfs_refresh_inode(inode, fattr)) != 0)
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e125e55de86d..2603d7589946 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -30,6 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
nfs4_print_deviceid(&mirror_ds->id_node.deviceid);
nfs4_pnfs_ds_put(mirror_ds->ds);
+ kfree(mirror_ds->ds_versions);
kfree_rcu(mirror_ds, id_node.rcu);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index f714b98cfd74..668ac19af58f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1241,9 +1241,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
return 0;
/* Has the inode gone and changed behind our back? */
if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
- return -EIO;
+ return -ESTALE;
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
- return -EIO;
+ return -ESTALE;
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
inode->i_version != fattr->change_attr)
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 9dea85f7f918..578350fd96e1 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -243,7 +243,6 @@ int nfs_iocounter_wait(struct nfs_io_counter *c);
extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
void nfs_pgio_header_free(struct nfs_pgio_header *);
-void nfs_pgio_data_destroy(struct nfs_pgio_header *);
int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4e3679b25b9b..8e425f2c5ddd 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2188,8 +2188,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
return 0;
- /* even though OPEN succeeded, access is denied. Close the file */
- nfs4_close_state(state, fmode);
return -EACCES;
}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 452a011ba0d8..8ebfdd00044b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -528,16 +528,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops)
}
EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc);
-/*
- * nfs_pgio_header_free - Free a read or write header
- * @hdr: The header to free
- */
-void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
-{
- hdr->rw_ops->rw_free_header(hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
-
/**
* nfs_pgio_data_destroy - make @hdr suitable for reuse
*
@@ -546,14 +536,24 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
*
* @hdr: A header that has had nfs_generic_pgio called
*/
-void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
+static void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
{
if (hdr->args.context)
put_nfs_open_context(hdr->args.context);
if (hdr->page_array.pagevec != hdr->page_array.page_array)
kfree(hdr->page_array.pagevec);
}
-EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy);
+
+/*
+ * nfs_pgio_header_free - Free a read or write header
+ * @hdr: The header to free
+ */
+void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
+{
+ nfs_pgio_data_destroy(hdr);
+ hdr->rw_ops->rw_free_header(hdr);
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
/**
* nfs_pgio_rpcsetup - Set up arguments for a pageio call
@@ -671,7 +671,6 @@ static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
u32 midx;
set_bit(NFS_IOHDR_REDO, &hdr->flags);
- nfs_pgio_data_destroy(hdr);
hdr->completion_ops->completion(hdr);
/* TODO: Make sure it's right to clean up all mirrors here
* and not just hdr->pgio_mirror_idx */
@@ -689,7 +688,6 @@ static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
static void nfs_pgio_release(void *calldata)
{
struct nfs_pgio_header *hdr = calldata;
- nfs_pgio_data_destroy(hdr);
hdr->completion_ops->completion(hdr);
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 3cae0726c1b1..7af7bedd7c02 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1943,7 +1943,6 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
nfs_pageio_reset_write_mds(desc);
mirror->pg_recoalesce = 1;
}
- nfs_pgio_data_destroy(hdr);
hdr->release(hdr);
}
@@ -2059,7 +2058,6 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
nfs_pageio_reset_read_mds(desc);
mirror->pg_recoalesce = 1;
}
- nfs_pgio_data_destroy(hdr);
hdr->release(hdr);
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 3f68a25f2169..544672b440de 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -129,7 +129,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp)
argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
if (argp->pagelen < PAGE_SIZE) {
- argp->end = argp->p + (argp->pagelen>>2);
+ argp->end = argp->p + XDR_QUADLEN(argp->pagelen);
argp->pagelen = 0;
} else {
argp->end = argp->p + (PAGE_SIZE>>2);
@@ -1246,9 +1246,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
argp->pagelen -= pages * PAGE_SIZE;
len -= pages * PAGE_SIZE;
- argp->p = (__be32 *)page_address(argp->pagelist[0]);
- argp->pagelist++;
- argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE);
+ next_decode_page(argp);
}
argp->p += XDR_QUADLEN(len);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index db39de2dd4cb..a64adc2fced9 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -104,16 +104,20 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
if (unlikely(!fsnotify_inode_watches_children(p_inode)))
__fsnotify_update_child_dentry_flags(p_inode);
else if (p_inode->i_fsnotify_mask & mask) {
+ struct name_snapshot name;
+
/* we are notifying a parent so come up with the new mask which
* specifies these are events which came from a child. */
mask |= FS_EVENT_ON_CHILD;
+ take_dentry_name_snapshot(&name, dentry);
if (path)
ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
- dentry->d_name.name, 0);
+ name.name, 0);
else
ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
- dentry->d_name.name, 0);
+ name.name, 0);
+ release_dentry_name_snapshot(&name);
}
dput(parent);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 709fbbd44c65..acebc350e98d 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -2070,13 +2070,13 @@ unlock:
spin_unlock(&o2hb_live_lock);
}
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
char *page)
{
return sprintf(page, "%u\n", o2hb_dead_threshold);
}
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
const char *page, size_t count)
{
unsigned long tmp;
@@ -2125,11 +2125,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
}
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
- &o2hb_heartbeat_group_attr_threshold,
+ &o2hb_heartbeat_group_attr_dead_threshold,
&o2hb_heartbeat_group_attr_mode,
NULL,
};
diff --git a/fs/open.c b/fs/open.c
index 157b9940dd73..fbc5c7b230b3 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -885,6 +885,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
int lookup_flags = 0;
int acc_mode;
+ /*
+ * Clear out all open flags we don't know about so that we don't report
+ * them in fcntl(F_GETFD) or similar interfaces.
+ */
+ flags &= VALID_OPEN_FLAGS;
+
if (flags & (O_CREAT | __O_TMPFILE))
op->mode = (mode & S_IALLUGO) | S_IFREG;
else
diff --git a/fs/pnode.c b/fs/pnode.c
index b394ca5307ec..d15c63e97ef1 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p)
return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
}
+static inline struct mount *last_slave(struct mount *p)
+{
+ return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
static inline struct mount *next_slave(struct mount *p)
{
return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -164,6 +169,19 @@ static struct mount *propagation_next(struct mount *m,
}
}
+static struct mount *skip_propagation_subtree(struct mount *m,
+ struct mount *origin)
+{
+ /*
+ * Advance m such that propagation_next will not return
+ * the slaves of m.
+ */
+ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+ m = last_slave(m);
+
+ return m;
+}
+
static struct mount *next_group(struct mount *m, struct mount *origin)
{
while (1) {
@@ -415,65 +433,104 @@ void propagate_mount_unlock(struct mount *mnt)
}
}
-/*
- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
- */
-static void mark_umount_candidates(struct mount *mnt)
+static void umount_one(struct mount *mnt, struct list_head *to_umount)
{
- struct mount *parent = mnt->mnt_parent;
- struct mount *m;
-
- BUG_ON(parent == mnt);
-
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
- struct mount *child = __lookup_mnt(&m->mnt,
- mnt->mnt_mountpoint);
- if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
- continue;
- if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
- SET_MNT_MARK(child);
- }
- }
+ CLEAR_MNT_MARK(mnt);
+ mnt->mnt.mnt_flags |= MNT_UMOUNT;
+ list_del_init(&mnt->mnt_child);
+ list_del_init(&mnt->mnt_umounting);
+ list_move_tail(&mnt->mnt_list, to_umount);
}
/*
* NOTE: unmounting 'mnt' naturally propagates to all other mounts its
* parent propagates to.
*/
-static void __propagate_umount(struct mount *mnt)
+static bool __propagate_umount(struct mount *mnt,
+ struct list_head *to_umount,
+ struct list_head *to_restore)
{
- struct mount *parent = mnt->mnt_parent;
- struct mount *m;
+ bool progress = false;
+ struct mount *child;
- BUG_ON(parent == mnt);
+ /*
+ * The state of the parent won't change if this mount is
+ * already unmounted or marked as without children.
+ */
+ if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
+ goto out;
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
- struct mount *topper;
- struct mount *child = __lookup_mnt(&m->mnt,
- mnt->mnt_mountpoint);
- /*
- * umount the child only if the child has no children
- * and the child is marked safe to unmount.
- */
- if (!child || !IS_MNT_MARKED(child))
+ /* Verify topper is the only grandchild that has not been
+ * speculatively unmounted.
+ */
+ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+ if (child->mnt_mountpoint == mnt->mnt.mnt_root)
continue;
- CLEAR_MNT_MARK(child);
+ if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
+ continue;
+ /* Found a mounted child */
+ goto children;
+ }
- /* If there is exactly one mount covering all of child
- * replace child with that mount.
- */
- topper = find_topper(child);
- if (topper)
- mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
- topper);
+ /* Mark mounts that can be unmounted if not locked */
+ SET_MNT_MARK(mnt);
+ progress = true;
+
+ /* If a mount is without children and not locked umount it. */
+ if (!IS_MNT_LOCKED(mnt)) {
+ umount_one(mnt, to_umount);
+ } else {
+children:
+ list_move_tail(&mnt->mnt_umounting, to_restore);
+ }
+out:
+ return progress;
+}
+
+static void umount_list(struct list_head *to_umount,
+ struct list_head *to_restore)
+{
+ struct mount *mnt, *child, *tmp;
+ list_for_each_entry(mnt, to_umount, mnt_list) {
+ list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
+ /* topper? */
+ if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+ list_move_tail(&child->mnt_umounting, to_restore);
+ else
+ umount_one(child, to_umount);
+ }
+ }
+}
- if (list_empty(&child->mnt_mounts)) {
- list_del_init(&child->mnt_child);
- child->mnt.mnt_flags |= MNT_UMOUNT;
- list_move_tail(&child->mnt_list, &mnt->mnt_list);
+static void restore_mounts(struct list_head *to_restore)
+{
+ /* Restore mounts to a clean working state */
+ while (!list_empty(to_restore)) {
+ struct mount *mnt, *parent;
+ struct mountpoint *mp;
+
+ mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
+ CLEAR_MNT_MARK(mnt);
+ list_del_init(&mnt->mnt_umounting);
+
+ /* Should this mount be reparented? */
+ mp = mnt->mnt_mp;
+ parent = mnt->mnt_parent;
+ while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+ mp = parent->mnt_mp;
+ parent = parent->mnt_parent;
}
+ if (parent != mnt->mnt_parent)
+ mnt_change_mountpoint(parent, mp, mnt);
+ }
+}
+
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+ while (!list_empty(visited)) {
+ struct mount *mnt =
+ list_first_entry(visited, struct mount, mnt_umounting);
+ list_del_init(&mnt->mnt_umounting);
}
}
@@ -487,11 +544,68 @@ static void __propagate_umount(struct mount *mnt)
int propagate_umount(struct list_head *list)
{
struct mount *mnt;
+ LIST_HEAD(to_restore);
+ LIST_HEAD(to_umount);
+ LIST_HEAD(visited);
+
+ /* Find candidates for unmounting */
+ list_for_each_entry_reverse(mnt, list, mnt_list) {
+ struct mount *parent = mnt->mnt_parent;
+ struct mount *m;
+
+ /*
+ * If this mount has already been visited it is known that it's
+ * entire peer group and all of their slaves in the propagation
+ * tree for the mountpoint has already been visited and there is
+ * no need to visit them again.
+ */
+ if (!list_empty(&mnt->mnt_umounting))
+ continue;
+
+ list_add_tail(&mnt->mnt_umounting, &visited);
+ for (m = propagation_next(parent, parent); m;
+ m = propagation_next(m, parent)) {
+ struct mount *child = __lookup_mnt(&m->mnt,
+ mnt->mnt_mountpoint);
+ if (!child)
+ continue;
+
+ if (!list_empty(&child->mnt_umounting)) {
+ /*
+ * If the child has already been visited it is
+ * know that it's entire peer group and all of
+ * their slaves in the propgation tree for the
+ * mountpoint has already been visited and there
+ * is no need to visit this subtree again.
+ */
+ m = skip_propagation_subtree(m, parent);
+ continue;
+ } else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+ /*
+ * We have come accross an partially unmounted
+ * mount in list that has not been visited yet.
+ * Remember it has been visited and continue
+ * about our merry way.
+ */
+ list_add_tail(&child->mnt_umounting, &visited);
+ continue;
+ }
+
+ /* Check the child and parents while progress is made */
+ while (__propagate_umount(child,
+ &to_umount, &to_restore)) {
+ /* Is the parent a umount candidate? */
+ child = child->mnt_parent;
+ if (list_empty(&child->mnt_umounting))
+ break;
+ }
+ }
+ }
- list_for_each_entry_reverse(mnt, list, mnt_list)
- mark_umount_candidates(mnt);
+ umount_list(&to_umount, &to_restore);
+ restore_mounts(&to_restore);
+ cleanup_umount_visitations(&visited);
+ list_splice_tail(&to_umount, list);
- list_for_each_entry(mnt, list, mnt_list)
- __propagate_umount(mnt);
return 0;
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index db1a1427c27a..07ef85e19fbc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -295,11 +295,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
/* We don't show the stack guard page in /proc/maps */
start = vma->vm_start;
- if (stack_guard_page_start(vma, start))
- start += PAGE_SIZE;
end = vma->vm_end;
- if (stack_guard_page_end(vma, end))
- end -= PAGE_SIZE;
seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 905caba36529..59d93acc29c7 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -413,7 +413,7 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt,
for (i = 0; i < cxt->max_dump_cnt; i++) {
cxt->przs[i] = persistent_ram_new(*paddr, cxt->record_size, 0,
&cxt->ecc_info,
- cxt->memtype);
+ cxt->memtype, 0);
if (IS_ERR(cxt->przs[i])) {
err = PTR_ERR(cxt->przs[i]);
dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -450,7 +450,8 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt,
return -ENOMEM;
}
- *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
+ *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info,
+ cxt->memtype, 0);
if (IS_ERR(*prz)) {
int err = PTR_ERR(*prz);
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 364d2dffe5a6..27300533c2dd 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -47,16 +47,15 @@ static inline size_t buffer_start(struct persistent_ram_zone *prz)
return atomic_read(&prz->buffer->start);
}
-static DEFINE_RAW_SPINLOCK(buffer_lock);
-
/* increase and wrap the start pointer, returning the old value */
static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a)
{
int old;
int new;
- unsigned long flags;
+ unsigned long flags = 0;
- raw_spin_lock_irqsave(&buffer_lock, flags);
+ if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+ raw_spin_lock_irqsave(&prz->buffer_lock, flags);
old = atomic_read(&prz->buffer->start);
new = old + a;
@@ -64,7 +63,8 @@ static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a)
new -= prz->buffer_size;
atomic_set(&prz->buffer->start, new);
- raw_spin_unlock_irqrestore(&buffer_lock, flags);
+ if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+ raw_spin_unlock_irqrestore(&prz->buffer_lock, flags);
return old;
}
@@ -74,9 +74,10 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a)
{
size_t old;
size_t new;
- unsigned long flags;
+ unsigned long flags = 0;
- raw_spin_lock_irqsave(&buffer_lock, flags);
+ if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+ raw_spin_lock_irqsave(&prz->buffer_lock, flags);
old = atomic_read(&prz->buffer->size);
if (old == prz->buffer_size)
@@ -88,7 +89,8 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a)
atomic_set(&prz->buffer->size, new);
exit:
- raw_spin_unlock_irqrestore(&buffer_lock, flags);
+ if (!(prz->flags & PRZ_FLAG_NO_LOCK))
+ raw_spin_unlock_irqrestore(&prz->buffer_lock, flags);
}
static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz,
@@ -448,6 +450,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
prz->buffer->sig);
}
+ /* Rewind missing or invalid memory area. */
prz->buffer->sig = sig;
persistent_ram_zap(prz);
@@ -474,7 +477,7 @@ void persistent_ram_free(struct persistent_ram_zone *prz)
struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
u32 sig, struct persistent_ram_ecc_info *ecc_info,
- unsigned int memtype)
+ unsigned int memtype, u32 flags)
{
struct persistent_ram_zone *prz;
int ret = -ENOMEM;
@@ -485,6 +488,10 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
goto err;
}
+ /* Initialize general buffer state. */
+ raw_spin_lock_init(&prz->buffer_lock);
+ prz->flags = flags;
+
ret = persistent_ram_buffer_map(start, size, prz, memtype);
if (ret)
goto err;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index d672e2fec459..6dc4296eed62 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -72,9 +72,10 @@ int seq_open(struct file *file, const struct seq_operations *op)
mutex_init(&p->lock);
p->op = op;
-#ifdef CONFIG_USER_NS
- p->user_ns = file->f_cred->user_ns;
-#endif
+
+ // No refcounting: the lifetime of 'p' is constrained
+ // to the lifetime of the file.
+ p->file = file;
/*
* Wrappers around seq_open(e.g. swaps_open) need to be
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 7be3166ba553..0e659d9c69a1 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1235,8 +1235,8 @@ int udf_setsize(struct inode *inode, loff_t newsize)
return err;
}
set_size:
- truncate_setsize(inode, newsize);
up_write(&iinfo->i_data_sem);
+ truncate_setsize(inode, newsize);
} else {
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
down_write(&iinfo->i_data_sem);
@@ -1253,9 +1253,9 @@ set_size:
udf_get_block);
if (err)
return err;
+ truncate_setsize(inode, newsize);
down_write(&iinfo->i_data_sem);
udf_clear_extent_cache(inode);
- truncate_setsize(inode, newsize);
udf_truncate_extents(inode);
up_write(&iinfo->i_data_sem);
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 187b80267ff9..a9063ac50c4e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1426,6 +1426,26 @@ __xfs_get_blocks(
if (error)
goto out_unlock;
+ /*
+ * The only time we can ever safely find delalloc blocks on direct I/O
+ * is a dio write to post-eof speculative preallocation. All other
+ * scenarios are indicative of a problem or misuse (such as mixing
+ * direct and mapped I/O).
+ *
+ * The file may be unmapped by the time we get here so we cannot
+ * reliably fail the I/O based on mapping. Instead, fail the I/O if this
+ * is a read or a write within eof. Otherwise, carry on but warn as a
+ * precuation if the file happens to be mapped.
+ */
+ if (direct && imap.br_startblock == DELAYSTARTBLOCK) {
+ if (!create || offset < i_size_read(VFS_I(ip))) {
+ WARN_ON_ONCE(1);
+ error = -EIO;
+ goto out_unlock;
+ }
+ WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping));
+ }
+
/* for DAX, we convert unwritten extents directly */
if (create &&
(!nimaps ||
@@ -1525,7 +1545,6 @@ __xfs_get_blocks(
set_buffer_new(bh_result);
if (imap.br_startblock == DELAYSTARTBLOCK) {
- BUG_ON(direct);
if (create) {
set_buffer_uptodate(bh_result);
set_buffer_mapped(bh_result);
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index ec0e239a0fa9..201aae0b2662 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -369,7 +369,14 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
#endif /* DEBUG */
#ifdef CONFIG_XFS_RT
-#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME)
+
+/*
+ * make sure we ignore the inode flag if the filesystem doesn't have a
+ * configured realtime device.
+ */
+#define XFS_IS_REALTIME_INODE(ip) \
+ (((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) && \
+ (ip)->i_mount->m_rtdev_targp)
#else
#define XFS_IS_REALTIME_INODE(ip) (0)
#endif