summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/acl.c2
-rw-r--r--fs/block_dev.c12
-rw-r--r--fs/btrfs/extent-tree.c1
-rw-r--r--fs/btrfs/file.c2
-rw-r--r--fs/btrfs/inode.c4
-rw-r--r--fs/buffer.c12
-rw-r--r--fs/ceph/acl.c4
-rw-r--r--fs/ceph/addr.c2
-rw-r--r--fs/ceph/inode.c27
-rw-r--r--fs/ceph/super.h1
-rw-r--r--fs/ceph/xattr.c3
-rw-r--r--fs/cifs/cifs_unicode.c6
-rw-r--r--fs/cifs/cifs_unicode.h5
-rw-r--r--fs/cifs/cifsglob.h12
-rw-r--r--fs/cifs/cifssmb.c7
-rw-r--r--fs/cifs/connect.c37
-rw-r--r--fs/cifs/file.c6
-rw-r--r--fs/cifs/ioctl.c2
-rw-r--r--fs/cifs/smb1ops.c10
-rw-r--r--fs/cifs/smb2misc.c44
-rw-r--r--fs/cifs/smb2ops.c4
-rw-r--r--fs/cifs/smb2pdu.c23
-rw-r--r--fs/cifs/smb2proto.h7
-rw-r--r--fs/cifs/smb2transport.c58
-rw-r--r--fs/cifs/transport.c2
-rw-r--r--fs/direct-io.c2
-rw-r--r--fs/ext4/crypto.c96
-rw-r--r--fs/ext4/crypto_fname.c2
-rw-r--r--fs/ext4/crypto_policy.c66
-rw-r--r--fs/ext4/dir.c6
-rw-r--r--fs/ext4/ext4.h7
-rw-r--r--fs/ext4/extents.c5
-rw-r--r--fs/ext4/file.c50
-rw-r--r--fs/ext4/inode.c19
-rw-r--r--fs/ext4/ioctl.c3
-rw-r--r--fs/ext4/move_extent.c2
-rw-r--r--fs/ext4/namei.c22
-rw-r--r--fs/ext4/page-io.c14
-rw-r--r--fs/ext4/readpage.c2
-rw-r--r--fs/ext4/xattr.c32
-rw-r--r--fs/f2fs/crypto_fname.c2
-rw-r--r--fs/f2fs/crypto_policy.c65
-rw-r--r--fs/f2fs/dir.c32
-rw-r--r--fs/f2fs/f2fs.h3
-rw-r--r--fs/f2fs/hash.c7
-rw-r--r--fs/f2fs/inline.c4
-rw-r--r--fs/f2fs/super.c105
-rw-r--r--fs/fscache/cookie.c5
-rw-r--r--fs/fscache/netfs.c1
-rw-r--r--fs/fscache/object.c32
-rw-r--r--fs/gfs2/dir.c4
-rw-r--r--fs/jfs/super.c4
-rw-r--r--fs/mount.h2
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/namespace.c50
-rw-r--r--fs/nfs/dir.c21
-rw-r--r--fs/nfs/nfs4state.c1
-rw-r--r--fs/nfsd/blocklayout.c4
-rw-r--r--fs/nfsd/nfs3xdr.c12
-rw-r--r--fs/nfsd/nfs4proc.c13
-rw-r--r--fs/nfsd/nfs4xdr.c21
-rw-r--r--fs/nfsd/nfssvc.c36
-rw-r--r--fs/nfsd/nfsxdr.c10
-rw-r--r--fs/nilfs2/btnode.c2
-rw-r--r--fs/nilfs2/inode.c4
-rw-r--r--fs/nilfs2/mdt.c4
-rw-r--r--fs/nilfs2/segment.c2
-rw-r--r--fs/ocfs2/aops.c2
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/pnode.c2
-rw-r--r--fs/pnode.h1
-rw-r--r--fs/proc/base.c2
-rw-r--r--fs/proc/generic.c1
-rw-r--r--fs/proc/task_mmu.c9
-rw-r--r--fs/reiserfs/file.c2
-rw-r--r--fs/reiserfs/inode.c2
-rw-r--r--fs/romfs/super.c23
-rw-r--r--fs/stat.c3
-rw-r--r--fs/sysfs/file.c6
-rw-r--r--fs/timerfd.c17
-rw-r--r--fs/udf/inode.c2
-rw-r--r--fs/ufs/balloc.c26
-rw-r--r--fs/ufs/inode.c9
-rw-r--r--fs/ufs/super.c18
-rw-r--r--fs/ufs/util.h10
-rw-r--r--fs/xattr.c2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c7
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/xfs_aops.c10
-rw-r--r--fs/xfs/xfs_attr.h1
-rw-r--r--fs/xfs/xfs_attr_list.c8
-rw-r--r--fs/xfs/xfs_bmap_util.c2
-rw-r--r--fs/xfs/xfs_buf.c24
-rw-r--r--fs/xfs/xfs_buf.h1
-rw-r--r--fs/xfs/xfs_dir2_readdir.c15
-rw-r--r--fs/xfs/xfs_file.c35
-rw-r--r--fs/xfs/xfs_icache.c58
-rw-r--r--fs/xfs/xfs_icache.h8
-rw-r--r--fs/xfs/xfs_inode.h4
-rw-r--r--fs/xfs/xfs_ioctl.c11
-rw-r--r--fs/xfs/xfs_qm.c7
-rw-r--r--fs/xfs/xfs_qm_syscalls.c3
-rw-r--r--fs/xfs/xfs_xattr.c16
103 files changed, 1112 insertions, 308 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 929b618da43b..c30c6ceac2c4 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -283,6 +283,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
case ACL_TYPE_ACCESS:
if (acl) {
struct iattr iattr;
+ struct posix_acl *old_acl = acl;
retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
if (retval)
@@ -293,6 +294,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
* by the mode bits. So don't
* update ACL.
*/
+ posix_acl_release(old_acl);
value = NULL;
size = 0;
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 198aea66fe71..26bbaaefdff4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -88,12 +88,11 @@ void invalidate_bdev(struct block_device *bdev)
{
struct address_space *mapping = bdev->bd_inode->i_mapping;
- if (mapping->nrpages == 0)
- return;
-
- invalidate_bh_lrus();
- lru_add_drain_all(); /* make sure all lru add caches are flushed */
- invalidate_mapping_pages(mapping, 0, -1);
+ if (mapping->nrpages) {
+ invalidate_bh_lrus();
+ lru_add_drain_all(); /* make sure all lru add caches are flushed */
+ invalidate_mapping_pages(mapping, 0, -1);
+ }
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
@@ -1098,7 +1097,6 @@ int revalidate_disk(struct gendisk *disk)
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
- blk_integrity_revalidate(disk);
bdev = bdget_disk(disk, 0);
if (!bdev)
return ret;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2a2e370399ba..c36a03fa7678 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3854,6 +3854,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
info->space_info_kobj, "%s",
alloc_name(found->flags));
if (ret) {
+ percpu_counter_destroy(&found->total_bytes_pinned);
kfree(found);
return ret;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 353f4bae658c..d4a6eef31854 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2771,7 +2771,7 @@ static long btrfs_fallocate(struct file *file, int mode,
if (!ret)
ret = btrfs_prealloc_file_range(inode, mode,
range->start,
- range->len, 1 << inode->i_blkbits,
+ range->len, i_blocksize(inode),
offset + len, &alloc_hint);
list_del(&range->list);
kfree(range);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3cff6523f27d..863fa0f1972b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7318,8 +7318,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
int found = false;
void **pagep = NULL;
struct page *page = NULL;
- int start_idx;
- int end_idx;
+ unsigned long start_idx;
+ unsigned long end_idx;
start_idx = start >> PAGE_CACHE_SHIFT;
diff --git a/fs/buffer.c b/fs/buffer.c
index 4f4cd959da7c..6f7d519a093b 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2298,7 +2298,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
loff_t pos, loff_t *bytes)
{
struct inode *inode = mapping->host;
- unsigned blocksize = 1 << inode->i_blkbits;
+ unsigned int blocksize = i_blocksize(inode);
struct page *page;
void *fsdata;
pgoff_t index, curidx;
@@ -2378,8 +2378,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
get_block_t *get_block, loff_t *bytes)
{
struct inode *inode = mapping->host;
- unsigned blocksize = 1 << inode->i_blkbits;
- unsigned zerofrom;
+ unsigned int blocksize = i_blocksize(inode);
+ unsigned int zerofrom;
int err;
err = cont_expand_zero(file, mapping, pos, bytes);
@@ -2741,7 +2741,7 @@ int nobh_truncate_page(struct address_space *mapping,
struct buffer_head map_bh;
int err;
- blocksize = 1 << inode->i_blkbits;
+ blocksize = i_blocksize(inode);
length = offset & (blocksize - 1);
/* Block boundary? Nothing to do */
@@ -2819,7 +2819,7 @@ int block_truncate_page(struct address_space *mapping,
struct buffer_head *bh;
int err;
- blocksize = 1 << inode->i_blkbits;
+ blocksize = i_blocksize(inode);
length = offset & (blocksize - 1);
/* Block boundary? Nothing to do */
@@ -2931,7 +2931,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
struct inode *inode = mapping->host;
tmp.b_state = 0;
tmp.b_blocknr = 0;
- tmp.b_size = 1 << inode->i_blkbits;
+ tmp.b_size = i_blocksize(inode);
get_block(inode, block, &tmp, 0);
return tmp.b_blocknr;
}
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 4d8caeb94a11..bdb9c94335f1 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -128,7 +128,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
if (new_mode != old_mode) {
newattrs.ia_mode = new_mode;
newattrs.ia_valid = ATTR_MODE;
- ret = ceph_setattr(dentry, &newattrs);
+ ret = __ceph_setattr(dentry, &newattrs);
if (ret)
goto out_dput;
}
@@ -138,7 +138,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
if (new_mode != old_mode) {
newattrs.ia_mode = old_mode;
newattrs.ia_valid = ATTR_MODE;
- ceph_setattr(dentry, &newattrs);
+ __ceph_setattr(dentry, &newattrs);
}
goto out_dput;
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index b7d218a168fb..c6a1ec110c01 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -697,7 +697,7 @@ static int ceph_writepages_start(struct address_space *mapping,
struct pagevec pvec;
int done = 0;
int rc = 0;
- unsigned wsize = 1 << inode->i_blkbits;
+ unsigned int wsize = i_blocksize(inode);
struct ceph_osd_request *req = NULL;
int do_sync = 0;
loff_t snap_size, i_size;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index d98536c8abfc..9f0d99094cc1 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1773,7 +1773,7 @@ static const struct inode_operations ceph_symlink_iops = {
/*
* setattr
*/
-int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+int __ceph_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1975,11 +1975,6 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
if (inode_dirty_flags)
__mark_inode_dirty(inode, inode_dirty_flags);
- if (ia_valid & ATTR_MODE) {
- err = posix_acl_chmod(inode, attr->ia_mode);
- if (err)
- goto out_put;
- }
if (mask) {
req->r_inode = inode;
@@ -1993,13 +1988,23 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
ceph_cap_string(dirtied), mask);
ceph_mdsc_put_request(req);
- if (mask & CEPH_SETATTR_SIZE)
- __ceph_do_pending_vmtruncate(inode);
ceph_free_cap_flush(prealloc_cf);
+
+ if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+ __ceph_do_pending_vmtruncate(inode);
+
return err;
-out_put:
- ceph_mdsc_put_request(req);
- ceph_free_cap_flush(prealloc_cf);
+}
+
+int ceph_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ int err;
+
+ err = __ceph_setattr(dentry, attr);
+
+ if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+ err = posix_acl_chmod(d_inode(dentry), attr->ia_mode);
+
return err;
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 75b7d125ce66..8c8cb8fe3d32 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -788,6 +788,7 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
return __ceph_do_getattr(inode, NULL, mask, force);
}
extern int ceph_permission(struct inode *inode, int mask);
+extern int __ceph_setattr(struct dentry *dentry, struct iattr *attr);
extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 819163d8313b..b24275ef97f7 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -369,6 +369,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
if (update_xattr) {
int err = 0;
+
if (xattr && (flags & XATTR_CREATE))
err = -EEXIST;
else if (!xattr && (flags & XATTR_REPLACE))
@@ -376,12 +377,14 @@ static int __set_xattr(struct ceph_inode_info *ci,
if (err) {
kfree(name);
kfree(val);
+ kfree(*newxattr);
return err;
}
if (update_xattr < 0) {
if (xattr)
__remove_xattr(ci, xattr);
kfree(name);
+ kfree(*newxattr);
return 0;
}
}
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 02b071bf3732..a0b3e7d1be48 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -83,6 +83,9 @@ convert_sfm_char(const __u16 src_char, char *target)
case SFM_COLON:
*target = ':';
break;
+ case SFM_DOUBLEQUOTE:
+ *target = '"';
+ break;
case SFM_ASTERISK:
*target = '*';
break;
@@ -418,6 +421,9 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
case ':':
dest_char = cpu_to_le16(SFM_COLON);
break;
+ case '"':
+ dest_char = cpu_to_le16(SFM_DOUBLEQUOTE);
+ break;
case '*':
dest_char = cpu_to_le16(SFM_ASTERISK);
break;
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 479bc0a941f3..07ade707fa60 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -57,6 +57,7 @@
* not conflict (although almost does) with the mapping above.
*/
+#define SFM_DOUBLEQUOTE ((__u16) 0xF020)
#define SFM_ASTERISK ((__u16) 0xF021)
#define SFM_QUESTION ((__u16) 0xF025)
#define SFM_COLON ((__u16) 0xF022)
@@ -64,8 +65,8 @@
#define SFM_LESSTHAN ((__u16) 0xF023)
#define SFM_PIPE ((__u16) 0xF027)
#define SFM_SLASH ((__u16) 0xF026)
-#define SFM_PERIOD ((__u16) 0xF028)
-#define SFM_SPACE ((__u16) 0xF029)
+#define SFM_SPACE ((__u16) 0xF028)
+#define SFM_PERIOD ((__u16) 0xF029)
/*
* Mapping mechanism to use when one of the seven reserved characters is
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b76883606e4b..e2f6a79e9b01 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -227,6 +227,7 @@ struct smb_version_operations {
/* verify the message */
int (*check_message)(char *, unsigned int);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+ int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
void (*downgrade_oplock)(struct TCP_Server_Info *,
struct cifsInodeInfo *, bool);
/* process transaction2 response */
@@ -906,7 +907,6 @@ struct cifs_tcon {
bool use_persistent:1; /* use persistent instead of durable handles */
#ifdef CONFIG_CIFS_SMB2
bool print:1; /* set if connection to printer share */
- bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
__le32 capabilities;
__u32 share_flags;
__u32 maximal_access;
@@ -1290,12 +1290,19 @@ struct mid_q_entry {
void *callback_data; /* general purpose pointer for callback */
void *resp_buf; /* pointer to received SMB header */
int mid_state; /* wish this were enum but can not pass to wait_event */
+ unsigned int mid_flags;
__le16 command; /* smb command code */
bool large_buf:1; /* if valid response, is pointer to large buf */
bool multiRsp:1; /* multiple trans2 responses for one request */
bool multiEnd:1; /* both received */
};
+struct close_cancelled_open {
+ struct cifs_fid fid;
+ struct cifs_tcon *tcon;
+ struct work_struct work;
+};
+
/* Make code in transport.c a little cleaner by moving
update of optional stats into function below */
#ifdef CONFIG_CIFS_STATS2
@@ -1427,6 +1434,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
#define MID_RESPONSE_MALFORMED 0x10
#define MID_SHUTDOWN 0x20
+/* Flags */
+#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */
+
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
#define CIFS_SMALL_BUFFER 1
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index b1104ed8f54c..b60150e5b5ce 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -717,6 +717,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
if (rc)
return rc;
+ if (server->capabilities & CAP_UNICODE)
+ smb->hdr.Flags2 |= SMBFLG2_UNICODE;
+
/* set up echo request */
smb->hdr.Tid = 0xffff;
smb->hdr.WordCount = 1;
@@ -1424,6 +1427,8 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
length = discard_remaining_data(server);
dequeue_mid(mid, rdata->result);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
@@ -1538,6 +1543,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
return cifs_readv_discard(server, mid);
dequeue_mid(mid, false);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5d59f25521ce..53a827c6d8b1 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -412,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
}
} while (server->tcpStatus == CifsNeedReconnect);
+ if (server->tcpStatus == CifsNeedNegotiate)
+ mod_delayed_work(cifsiod_wq, &server->echo, 0);
+
return rc;
}
@@ -421,18 +424,27 @@ cifs_echo_request(struct work_struct *work)
int rc;
struct TCP_Server_Info *server = container_of(work,
struct TCP_Server_Info, echo.work);
+ unsigned long echo_interval;
/*
- * We cannot send an echo if it is disabled or until the
- * NEGOTIATE_PROTOCOL request is done, which is indicated by
- * server->ops->need_neg() == true. Also, no need to ping if
- * we got a response recently.
+ * If we need to renegotiate, set echo interval to zero to
+ * immediately call echo service where we can renegotiate.
+ */
+ if (server->tcpStatus == CifsNeedNegotiate)
+ echo_interval = 0;
+ else
+ echo_interval = SMB_ECHO_INTERVAL;
+
+ /*
+ * We cannot send an echo if it is disabled.
+ * Also, no need to ping if we got a response recently.
*/
if (server->tcpStatus == CifsNeedReconnect ||
- server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew ||
+ server->tcpStatus == CifsExiting ||
+ server->tcpStatus == CifsNew ||
(server->ops->can_echo && !server->ops->can_echo(server)) ||
- time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+ time_before(jiffies, server->lstrp + echo_interval - HZ))
goto requeue_echo;
rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS;
@@ -924,10 +936,19 @@ cifs_demultiplex_thread(void *p)
server->lstrp = jiffies;
if (mid_entry != NULL) {
+ if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+ mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+ server->ops->handle_cancelled_mid)
+ server->ops->handle_cancelled_mid(
+ mid_entry->resp_buf,
+ server);
+
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break ||
- !server->ops->is_oplock_break(buf, server)) {
+ } else if (server->ops->is_oplock_break &&
+ server->ops->is_oplock_break(buf, server)) {
+ cifs_dbg(FYI, "Received oplock break\n");
+ } else {
cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 72f270d4bd17..a0c0a49b6620 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2545,7 +2545,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
wdata->credits = credits;
if (!wdata->cfile->invalidHandle ||
- !cifs_reopen_file(wdata->cfile, false))
+ !(rc = cifs_reopen_file(wdata->cfile, false)))
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
if (rc) {
@@ -2958,7 +2958,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
rdata->credits = credits;
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
error:
if (rc) {
@@ -3544,7 +3544,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
}
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
if (rc) {
add_credits_and_wake_if(server, rdata->credits, 0);
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 35cf990f87d3..a8f5b31636dc 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -272,6 +272,8 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
rc = -EOPNOTSUPP;
break;
case CIFS_IOC_GET_MNT_INFO:
+ if (pSMBFile == NULL)
+ break;
tcon = tlink_tcon(pSMBFile->tlink);
rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg);
break;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index fc537c29044e..87b87e091e8e 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile)
return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
}
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+ if (server->tcpStatus == CifsGood)
+ return true;
+
+ return false;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
@@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = {
.get_dfs_refer = CIFSGetDFSRefer,
.qfs_tcon = cifs_qfs_tcon,
.is_path_accessible = cifs_is_path_accessible,
+ .can_echo = cifs_can_echo,
.query_path_info = cifs_query_path_info,
.query_file_info = cifs_query_file_info,
.get_srv_inum = cifs_get_srv_inum,
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index e5bc85e49be7..76ccf20fbfb7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -630,3 +630,47 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
return false;
}
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+ struct close_cancelled_open *cancelled = container_of(work,
+ struct close_cancelled_open, work);
+
+ cifs_dbg(VFS, "Close unmatched open\n");
+
+ SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+ cancelled->fid.volatile_fid);
+ cifs_put_tcon(cancelled->tcon);
+ kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+ struct smb2_hdr *hdr = (struct smb2_hdr *)buffer;
+ struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+ struct cifs_tcon *tcon;
+ struct close_cancelled_open *cancelled;
+
+ if (hdr->Command != SMB2_CREATE || hdr->Status != STATUS_SUCCESS)
+ return 0;
+
+ cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+ if (!cancelled)
+ return -ENOMEM;
+
+ tcon = smb2_find_smb_tcon(server, hdr->SessionId, hdr->TreeId);
+ if (!tcon) {
+ kfree(cancelled);
+ return -ENOENT;
+ }
+
+ cancelled->fid.persistent_fid = rsp->PersistentFileId;
+ cancelled->fid.volatile_fid = rsp->VolatileFileId;
+ cancelled->tcon = tcon;
+ INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+ queue_work(cifsiod_wq, &cancelled->work);
+
+ return 0;
+}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index be34b4860675..087918c4612a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1511,6 +1511,7 @@ struct smb_version_operations smb20_operations = {
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
@@ -1589,6 +1590,7 @@ struct smb_version_operations smb21_operations = {
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
@@ -1670,6 +1672,7 @@ struct smb_version_operations smb30_operations = {
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
@@ -1757,6 +1760,7 @@ struct smb_version_operations smb311_operations = {
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2fa754c5fd62..f4afa3b1cc56 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -564,8 +564,12 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
}
if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
- cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
- return -EIO;
+ cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
+ rsplen);
+
+ /* relax check since Mac returns max bufsize allowed on ioctl */
+ if (rsplen > CIFSMaxBufSize)
+ return -EIO;
}
/* check validate negotiate info response matches what we got earlier */
@@ -932,9 +936,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
else
return -EIO;
- if (tcon && tcon->bad_network_name)
- return -ENOENT;
-
if ((tcon && tcon->seal) &&
((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
cifs_dbg(VFS, "encryption requested but no server support");
@@ -952,6 +953,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
return -EINVAL;
}
+ /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+ if (tcon)
+ tcon->tid = 0;
+
rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
if (rc) {
kfree(unc_path);
@@ -1032,8 +1037,6 @@ tcon_exit:
tcon_error_exit:
if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
- if (tcon)
- tcon->bad_network_name = true;
}
goto tcon_exit;
}
@@ -1519,8 +1522,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
* than one credit. Windows typically sets this smaller, but for some
* ioctls it may be useful to allow server to send more. No point
* limiting what the server can send as long as fits in one credit
+ * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
+ * (by default, note that it can be overridden to make max larger)
+ * in responses (except for read responses which can be bigger.
+ * We may want to bump this limit up
*/
- req->MaxOutputResponse = cpu_to_le32(0xFF00); /* < 64K uses 1 credit */
+ req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
if (is_fsctl)
req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 0a406ae78129..adc5234486c3 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -47,6 +47,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses,
struct smb_rqst *rqst);
extern struct mid_q_entry *smb2_setup_async_request(
struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+ __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+ __u64 ses_id, __u32 tid);
extern int smb2_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
extern int smb3_calc_signature(struct smb_rqst *rqst,
@@ -157,6 +161,9 @@ extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
const u64 persistent_fid, const u64 volatile_fid,
const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+ struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id,
struct kstatfs *FSData);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index d4c5b6f109a7..69e3b322bbfe 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -115,22 +115,68 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
}
static struct cifs_ses *
-smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
struct cifs_ses *ses;
- spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
- if (ses->Suid != smb2hdr->SessionId)
+ if (ses->Suid != ses_id)
continue;
- spin_unlock(&cifs_tcp_ses_lock);
return ses;
}
+
+ return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+ struct cifs_ses *ses;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
spin_unlock(&cifs_tcp_ses_lock);
+ return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid)
+{
+ struct cifs_tcon *tcon;
+
+ list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+ if (tcon->tid != tid)
+ continue;
+ ++tcon->tc_count;
+ return tcon;
+ }
+
return NULL;
}
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid)
+{
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
+ if (!ses) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ return NULL;
+ }
+ tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ return tcon;
+}
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
@@ -143,7 +189,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
- ses = smb2_find_smb_ses(smb2_pdu, server);
+ ses = smb2_find_smb_ses(server, smb2_pdu->SessionId);
if (!ses) {
cifs_dbg(VFS, "%s: Could not find session\n", __func__);
return 0;
@@ -314,7 +360,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
struct cifs_ses *ses;
- ses = smb2_find_smb_ses(smb2_pdu, server);
+ ses = smb2_find_smb_ses(server, smb2_pdu->SessionId);
if (!ses) {
cifs_dbg(VFS, "%s: Could not find session\n", __func__);
return 0;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 87abe8ed074c..54af10204e83 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -786,9 +786,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
+ cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid);
send_cancel(ses->server, buf, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+ midQ->mid_flags |= MID_WAIT_CANCELLED;
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
cifs_small_buf_release(buf);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 01171d8a6ee9..c772fdf36cd9 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -575,7 +575,7 @@ static int dio_set_defer_completion(struct dio *dio)
/*
* Call into the fs to map some more disk blocks. We record the current number
* of available blocks at sdio->blocks_available. These are in units of the
- * fs blocksize, (1 << inode->i_blkbits).
+ * fs blocksize, i_blocksize(inode).
*
* The fs is allowed to map lots of blocks at once. If it wants to do that,
* it uses the passed inode-relative block number as the file offset, as usual.
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index 1a0835073663..f240cef8b326 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -34,6 +34,7 @@
#include <linux/random.h>
#include <linux/scatterlist.h>
#include <linux/spinlock_types.h>
+#include <linux/namei.h>
#include "ext4_extents.h"
#include "xattr.h"
@@ -93,7 +94,8 @@ void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx)
* Return: An allocated and initialized encryption context on success; error
* value or NULL otherwise.
*/
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+ gfp_t gfp_flags)
{
struct ext4_crypto_ctx *ctx = NULL;
int res = 0;
@@ -120,7 +122,7 @@ struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
list_del(&ctx->free_list);
spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
if (!ctx) {
- ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
+ ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, gfp_flags);
if (!ctx) {
res = -ENOMEM;
goto out;
@@ -257,7 +259,8 @@ static int ext4_page_crypto(struct inode *inode,
ext4_direction_t rw,
pgoff_t index,
struct page *src_page,
- struct page *dest_page)
+ struct page *dest_page,
+ gfp_t gfp_flags)
{
u8 xts_tweak[EXT4_XTS_TWEAK_SIZE];
@@ -268,7 +271,7 @@ static int ext4_page_crypto(struct inode *inode,
struct crypto_ablkcipher *tfm = ci->ci_ctfm;
int res = 0;
- req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ req = ablkcipher_request_alloc(tfm, gfp_flags);
if (!req) {
printk_ratelimited(KERN_ERR
"%s: crypto_request_alloc() failed\n",
@@ -309,9 +312,10 @@ static int ext4_page_crypto(struct inode *inode,
return 0;
}
-static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
+static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx,
+ gfp_t gfp_flags)
{
- ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, GFP_NOWAIT);
+ ctx->w.bounce_page = mempool_alloc(ext4_bounce_page_pool, gfp_flags);
if (ctx->w.bounce_page == NULL)
return ERR_PTR(-ENOMEM);
ctx->flags |= EXT4_WRITE_PATH_FL;
@@ -334,7 +338,8 @@ static struct page *alloc_bounce_page(struct ext4_crypto_ctx *ctx)
* error value or NULL.
*/
struct page *ext4_encrypt(struct inode *inode,
- struct page *plaintext_page)
+ struct page *plaintext_page,
+ gfp_t gfp_flags)
{
struct ext4_crypto_ctx *ctx;
struct page *ciphertext_page = NULL;
@@ -342,17 +347,17 @@ struct page *ext4_encrypt(struct inode *inode,
BUG_ON(!PageLocked(plaintext_page));
- ctx = ext4_get_crypto_ctx(inode);
+ ctx = ext4_get_crypto_ctx(inode, gfp_flags);
if (IS_ERR(ctx))
return (struct page *) ctx;
/* The encryption operation will require a bounce page. */
- ciphertext_page = alloc_bounce_page(ctx);
+ ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
if (IS_ERR(ciphertext_page))
goto errout;
ctx->w.control_page = plaintext_page;
err = ext4_page_crypto(inode, EXT4_ENCRYPT, plaintext_page->index,
- plaintext_page, ciphertext_page);
+ plaintext_page, ciphertext_page, gfp_flags);
if (err) {
ciphertext_page = ERR_PTR(err);
errout:
@@ -380,8 +385,8 @@ int ext4_decrypt(struct page *page)
{
BUG_ON(!PageLocked(page));
- return ext4_page_crypto(page->mapping->host,
- EXT4_DECRYPT, page->index, page, page);
+ return ext4_page_crypto(page->mapping->host, EXT4_DECRYPT,
+ page->index, page, page, GFP_NOFS);
}
int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
@@ -402,11 +407,11 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
- ctx = ext4_get_crypto_ctx(inode);
+ ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- ciphertext_page = alloc_bounce_page(ctx);
+ ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
if (IS_ERR(ciphertext_page)) {
err = PTR_ERR(ciphertext_page);
goto errout;
@@ -414,11 +419,12 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
while (len--) {
err = ext4_page_crypto(inode, EXT4_ENCRYPT, lblk,
- ZERO_PAGE(0), ciphertext_page);
+ ZERO_PAGE(0), ciphertext_page,
+ GFP_NOFS);
if (err)
goto errout;
- bio = bio_alloc(GFP_KERNEL, 1);
+ bio = bio_alloc(GFP_NOWAIT, 1);
if (!bio) {
err = -ENOMEM;
goto errout;
@@ -469,3 +475,61 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size)
return size;
return 0;
}
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ struct dentry *dir;
+ struct ext4_crypt_info *ci;
+ int dir_has_key, cached_with_key;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ dir = dget_parent(dentry);
+ if (!ext4_encrypted_inode(d_inode(dir))) {
+ dput(dir);
+ return 0;
+ }
+ ci = EXT4_I(d_inode(dir))->i_crypt_info;
+
+ /* this should eventually be an flag in d_flags */
+ cached_with_key = dentry->d_fsdata != NULL;
+ dir_has_key = (ci != NULL);
+ dput(dir);
+
+ /*
+ * If the dentry was cached without the key, and it is a
+ * negative dentry, it might be a valid name. We can't check
+ * if the key has since been made available due to locking
+ * reasons, so we fail the validation so ext4_lookup() can do
+ * this check.
+ *
+ * We also fail the validation if the dentry was created with
+ * the key present, but we no longer have the key, or vice versa.
+ */
+ if ((!cached_with_key && d_is_negative(dentry)) ||
+ (!cached_with_key && dir_has_key) ||
+ (cached_with_key && !dir_has_key)) {
+#if 0 /* Revalidation debug */
+ char buf[80];
+ char *cp = simple_dname(dentry, buf, sizeof(buf));
+
+ if (IS_ERR(cp))
+ cp = (char *) "???";
+ pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
+ cached_with_key, d_is_negative(dentry),
+ dir_has_key);
+#endif
+ return 0;
+ }
+ return 1;
+}
+
+const struct dentry_operations ext4_encrypted_d_ops = {
+ .d_revalidate = ext4_d_revalidate,
+};
diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c
index 2fbef8a14760..2cfe3ffc276f 100644
--- a/fs/ext4/crypto_fname.c
+++ b/fs/ext4/crypto_fname.c
@@ -343,7 +343,7 @@ int _ext4_fname_disk_to_usr(struct inode *inode,
memcpy(buf+4, &hinfo->minor_hash, 4);
} else
memset(buf, 0, 8);
- memcpy(buf + 8, iname->name + iname->len - 16, 16);
+ memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
oname->name[0] = '_';
ret = digest_encode(buf, 24, oname->name+1);
oname->len = ret + 1;
diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c
index dd561f916f0b..e4f4fc4e56ab 100644
--- a/fs/ext4/crypto_policy.c
+++ b/fs/ext4/crypto_policy.c
@@ -148,26 +148,38 @@ int ext4_get_policy(struct inode *inode, struct ext4_encryption_policy *policy)
int ext4_is_child_context_consistent_with_parent(struct inode *parent,
struct inode *child)
{
- struct ext4_crypt_info *parent_ci, *child_ci;
+ const struct ext4_crypt_info *parent_ci, *child_ci;
+ struct ext4_encryption_context parent_ctx, child_ctx;
int res;
- if ((parent == NULL) || (child == NULL)) {
- pr_err("parent %p child %p\n", parent, child);
- WARN_ON(1); /* Should never happen */
- return 0;
- }
-
/* No restrictions on file types which are never encrypted */
if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
!S_ISLNK(child->i_mode))
return 1;
- /* no restrictions if the parent directory is not encrypted */
+ /* No restrictions if the parent directory is unencrypted */
if (!ext4_encrypted_inode(parent))
return 1;
- /* if the child directory is not encrypted, this is always a problem */
+
+ /* Encrypted directories must not contain unencrypted files */
if (!ext4_encrypted_inode(child))
return 0;
+
+ /*
+ * Both parent and child are encrypted, so verify they use the same
+ * encryption policy. Compare the fscrypt_info structs if the keys are
+ * available, otherwise retrieve and compare the fscrypt_contexts.
+ *
+ * Note that the fscrypt_context retrieval will be required frequently
+ * when accessing an encrypted directory tree without the key.
+ * Performance-wise this is not a big deal because we already don't
+ * really optimize for file access without the key (to the extent that
+ * such access is even possible), given that any attempted access
+ * already causes a fscrypt_context retrieval and keyring search.
+ *
+ * In any case, if an unexpected error occurs, fall back to "forbidden".
+ */
+
res = ext4_get_encryption_info(parent);
if (res)
return 0;
@@ -176,17 +188,35 @@ int ext4_is_child_context_consistent_with_parent(struct inode *parent,
return 0;
parent_ci = EXT4_I(parent)->i_crypt_info;
child_ci = EXT4_I(child)->i_crypt_info;
- if (!parent_ci && !child_ci)
- return 1;
- if (!parent_ci || !child_ci)
+ if (parent_ci && child_ci) {
+ return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+ (parent_ci->ci_filename_mode ==
+ child_ci->ci_filename_mode) &&
+ (parent_ci->ci_flags == child_ci->ci_flags);
+ }
+
+ res = ext4_xattr_get(parent, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &parent_ctx, sizeof(parent_ctx));
+ if (res != sizeof(parent_ctx))
+ return 0;
+
+ res = ext4_xattr_get(child, EXT4_XATTR_INDEX_ENCRYPTION,
+ EXT4_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &child_ctx, sizeof(child_ctx));
+ if (res != sizeof(child_ctx))
return 0;
- return (memcmp(parent_ci->ci_master_key,
- child_ci->ci_master_key,
- EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
- (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
- (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
- (parent_ci->ci_flags == child_ci->ci_flags));
+ return memcmp(parent_ctx.master_key_descriptor,
+ child_ctx.master_key_descriptor,
+ EXT4_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ctx.contents_encryption_mode ==
+ child_ctx.contents_encryption_mode) &&
+ (parent_ctx.filenames_encryption_mode ==
+ child_ctx.filenames_encryption_mode) &&
+ (parent_ctx.flags == child_ctx.flags);
}
/**
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d1bca74f844..6d17f31a31d7 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
int dir_has_error = 0;
struct ext4_str fname_crypto_str = {.name = NULL, .len = 0};
+ if (ext4_encrypted_inode(inode)) {
+ err = ext4_get_encryption_info(inode);
+ if (err && err != -ENOKEY)
+ return err;
+ }
+
if (is_dx_dir(inode)) {
err = ext4_dx_readdir(file, ctx);
if (err != ERR_BAD_DX_DIR) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 362d59b24f1d..c8ad14c697c4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2261,13 +2261,16 @@ extern struct kmem_cache *ext4_crypt_info_cachep;
bool ext4_valid_contents_enc_mode(uint32_t mode);
uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size);
extern struct workqueue_struct *ext4_read_workqueue;
-struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode);
+struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode,
+ gfp_t gfp_flags);
void ext4_release_crypto_ctx(struct ext4_crypto_ctx *ctx);
void ext4_restore_control_page(struct page *data_page);
struct page *ext4_encrypt(struct inode *inode,
- struct page *plaintext_page);
+ struct page *plaintext_page,
+ gfp_t gfp_flags);
int ext4_decrypt(struct page *page);
int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex);
+extern const struct dentry_operations ext4_encrypted_d_ops;
#ifdef CONFIG_EXT4_FS_ENCRYPTION
int ext4_init_crypto(void);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 8a456f9b8a44..61d5bfc7318c 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4902,6 +4902,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
if (file->f_flags & O_SYNC)
ext4_handle_sync(handle);
@@ -5597,6 +5599,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
@@ -5770,6 +5773,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0d24ebcd7c9e..8772bfc3415b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -463,47 +463,27 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
(pgoff_t)num);
- if (nr_pages == 0) {
- if (whence == SEEK_DATA)
- break;
-
- BUG_ON(whence != SEEK_HOLE);
- /*
- * If this is the first time to go into the loop and
- * offset is not beyond the end offset, it will be a
- * hole at this offset
- */
- if (lastoff == startoff || lastoff < endoff)
- found = 1;
+ if (nr_pages == 0)
break;
- }
-
- /*
- * If this is the first time to go into the loop and
- * offset is smaller than the first page offset, it will be a
- * hole at this offset.
- */
- if (lastoff == startoff && whence == SEEK_HOLE &&
- lastoff < page_offset(pvec.pages[0])) {
- found = 1;
- break;
- }
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
/*
- * If the current offset is not beyond the end of given
- * range, it will be a hole.
+ * If current offset is smaller than the page offset,
+ * there is a hole at this offset.
*/
- if (lastoff < endoff && whence == SEEK_HOLE &&
- page->index > end) {
+ if (whence == SEEK_HOLE && lastoff < endoff &&
+ lastoff < page_offset(pvec.pages[i])) {
found = 1;
*offset = lastoff;
goto out;
}
+ if (page->index > end)
+ goto out;
+
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping)) {
@@ -543,20 +523,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
unlock_page(page);
}
- /*
- * The no. of pages is less than our desired, that would be a
- * hole in there.
- */
- if (nr_pages < num && whence == SEEK_HOLE) {
- found = 1;
- *offset = lastoff;
+ /* The no. of pages is less than our desired, we are done. */
+ if (nr_pages < num)
break;
- }
index = pvec.pages[i - 1]->index + 1;
pagevec_release(&pvec);
} while (index <= end);
+ if (whence == SEEK_HOLE && lastoff < endoff) {
+ found = 1;
+ *offset = lastoff;
+ }
out:
pagevec_release(&pvec);
return found;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7dcc97eadb12..1796d1bd9a1d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -71,10 +71,9 @@ static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
csum_size);
offset += csum_size;
- csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
- EXT4_INODE_SIZE(inode->i_sb) -
- offset);
}
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+ EXT4_INODE_SIZE(inode->i_sb) - offset);
}
return csum;
@@ -2045,7 +2044,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
{
struct inode *inode = mpd->inode;
int err;
- ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+ ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
>> inode->i_blkbits;
do {
@@ -3794,6 +3793,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
+ if (ret >= 0)
+ ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
ext4_journal_stop(handle);
out_dio:
@@ -5163,8 +5164,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
- memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
- new_extra_isize);
+ memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize, 0,
+ new_extra_isize - EXT4_I(inode)->i_extra_isize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
return 0;
}
@@ -5394,6 +5396,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
+
+ ret = ext4_convert_inline_data(inode);
+ if (ret)
+ goto out_ret;
+
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 789e2d6724a9..bcd7c4788903 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -622,6 +622,9 @@ resizefs_out:
struct ext4_encryption_policy policy;
int err = 0;
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+
if (copy_from_user(&policy,
(struct ext4_encryption_policy __user *)arg,
sizeof(policy))) {
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 7861d801b048..05048fcfd602 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
if (PageUptodate(page))
return 0;
- blocksize = 1 << inode->i_blkbits;
+ blocksize = i_blocksize(inode);
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 573b4cbb0cb9..1d007e853f5c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1243,9 +1243,9 @@ static inline int ext4_match(struct ext4_filename *fname,
if (unlikely(!name)) {
if (fname->usr_fname->name[0] == '_') {
int ret;
- if (de->name_len < 16)
+ if (de->name_len <= 32)
return 0;
- ret = memcmp(de->name + de->name_len - 16,
+ ret = memcmp(de->name + ((de->name_len - 17) & ~15),
fname->crypto_buf.name + 8, 16);
return (ret == 0) ? 1 : 0;
}
@@ -1557,6 +1557,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
struct ext4_dir_entry_2 *de;
struct buffer_head *bh;
+ if (ext4_encrypted_inode(dir)) {
+ int res = ext4_get_encryption_info(dir);
+
+ /*
+ * This should be a properly defined flag for
+ * dentry->d_flags when we uplift this to the VFS.
+ * d_fsdata is set to (void *) 1 if if the dentry is
+ * created while the directory was encrypted and we
+ * don't have access to the key.
+ */
+ dentry->d_fsdata = NULL;
+ if (ext4_encryption_info(dir))
+ dentry->d_fsdata = (void *) 1;
+ d_set_d_op(dentry, &ext4_encrypted_d_ops);
+ if (res && res != -ENOKEY)
+ return ERR_PTR(res);
+ }
+
if (dentry->d_name.len > EXT4_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 17fbe3882b8e..6ca56f5f72b5 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -23,6 +23,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
+#include <linux/backing-dev.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -485,9 +486,20 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) &&
nr_to_submit) {
- data_page = ext4_encrypt(inode, page);
+ gfp_t gfp_flags = GFP_NOFS;
+
+ retry_encrypt:
+ data_page = ext4_encrypt(inode, page, gfp_flags);
if (IS_ERR(data_page)) {
ret = PTR_ERR(data_page);
+ if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
+ if (io->io_bio) {
+ ext4_io_submit(io);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ }
+ gfp_flags |= __GFP_NOFAIL;
+ goto retry_encrypt;
+ }
data_page = NULL;
goto out;
}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 5dc5e95063de..bc7642f57dc8 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -279,7 +279,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
if (ext4_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
- ctx = ext4_get_crypto_ctx(inode);
+ ctx = ext4_get_crypto_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
goto set_error_page;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 263002f0389d..7c23363ecf19 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -233,6 +233,27 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
return error;
}
+static int
+__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
+ void *end, const char *function, unsigned int line)
+{
+ struct ext4_xattr_entry *entry = IFIRST(header);
+ int error = -EFSCORRUPTED;
+
+ if (((void *) header >= end) ||
+ (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC)))
+ goto errout;
+ error = ext4_xattr_check_names(entry, end, entry);
+errout:
+ if (error)
+ __ext4_error_inode(inode, function, line, 0,
+ "corrupted in-inode xattr");
+ return error;
+}
+
+#define xattr_check_inode(inode, header, end) \
+ __xattr_check_inode((inode), (header), (end), __func__, __LINE__)
+
static inline int
ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
{
@@ -344,7 +365,7 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- error = ext4_xattr_check_names(entry, end, entry);
+ error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -475,7 +496,7 @@ ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
+ error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -991,8 +1012,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
- error = ext4_xattr_check_names(IFIRST(header), is->s.end,
- IFIRST(header));
+ error = xattr_check_inode(inode, header, is->s.end);
if (error)
return error;
/* Find the named attribute. */
@@ -1293,6 +1313,10 @@ retry:
last = entry;
total_ino = sizeof(struct ext4_xattr_ibody_header);
+ error = xattr_check_inode(inode, header, end);
+ if (error)
+ goto cleanup;
+
free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
if (free >= isize_diff) {
entry = IFIRST(header);
diff --git a/fs/f2fs/crypto_fname.c b/fs/f2fs/crypto_fname.c
index ab377d496a39..38349ed5ea51 100644
--- a/fs/f2fs/crypto_fname.c
+++ b/fs/f2fs/crypto_fname.c
@@ -333,7 +333,7 @@ int f2fs_fname_disk_to_usr(struct inode *inode,
memset(buf + 4, 0, 4);
} else
memset(buf, 0, 8);
- memcpy(buf + 8, iname->name + iname->len - 16, 16);
+ memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
oname->name[0] = '_';
ret = digest_encode(buf, 24, oname->name + 1);
oname->len = ret + 1;
diff --git a/fs/f2fs/crypto_policy.c b/fs/f2fs/crypto_policy.c
index 5bbd1989d5e6..884f3f0fe29d 100644
--- a/fs/f2fs/crypto_policy.c
+++ b/fs/f2fs/crypto_policy.c
@@ -141,25 +141,38 @@ int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
struct inode *child)
{
- struct f2fs_crypt_info *parent_ci, *child_ci;
+ const struct f2fs_crypt_info *parent_ci, *child_ci;
+ struct f2fs_encryption_context parent_ctx, child_ctx;
int res;
- if ((parent == NULL) || (child == NULL)) {
- pr_err("parent %p child %p\n", parent, child);
- BUG_ON(1);
- }
-
/* No restrictions on file types which are never encrypted */
if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
!S_ISLNK(child->i_mode))
return 1;
- /* no restrictions if the parent directory is not encrypted */
+ /* No restrictions if the parent directory is unencrypted */
if (!f2fs_encrypted_inode(parent))
return 1;
- /* if the child directory is not encrypted, this is always a problem */
+
+ /* Encrypted directories must not contain unencrypted files */
if (!f2fs_encrypted_inode(child))
return 0;
+
+ /*
+ * Both parent and child are encrypted, so verify they use the same
+ * encryption policy. Compare the fscrypt_info structs if the keys are
+ * available, otherwise retrieve and compare the fscrypt_contexts.
+ *
+ * Note that the fscrypt_context retrieval will be required frequently
+ * when accessing an encrypted directory tree without the key.
+ * Performance-wise this is not a big deal because we already don't
+ * really optimize for file access without the key (to the extent that
+ * such access is even possible), given that any attempted access
+ * already causes a fscrypt_context retrieval and keyring search.
+ *
+ * In any case, if an unexpected error occurs, fall back to "forbidden".
+ */
+
res = f2fs_get_encryption_info(parent);
if (res)
return 0;
@@ -168,17 +181,35 @@ int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
return 0;
parent_ci = F2FS_I(parent)->i_crypt_info;
child_ci = F2FS_I(child)->i_crypt_info;
- if (!parent_ci && !child_ci)
- return 1;
- if (!parent_ci || !child_ci)
+ if (parent_ci && child_ci) {
+ return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+ F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+ (parent_ci->ci_filename_mode ==
+ child_ci->ci_filename_mode) &&
+ (parent_ci->ci_flags == child_ci->ci_flags);
+ }
+
+ res = f2fs_getxattr(parent, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &parent_ctx, sizeof(parent_ctx), NULL);
+ if (res != sizeof(parent_ctx))
+ return 0;
+
+ res = f2fs_getxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ &child_ctx, sizeof(child_ctx), NULL);
+ if (res != sizeof(child_ctx))
return 0;
- return (memcmp(parent_ci->ci_master_key,
- child_ci->ci_master_key,
- F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
- (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
- (parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
- (parent_ci->ci_flags == child_ci->ci_flags));
+ return memcmp(parent_ctx.master_key_descriptor,
+ child_ctx.master_key_descriptor,
+ F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ctx.contents_encryption_mode ==
+ child_ctx.contents_encryption_mode) &&
+ (parent_ctx.filenames_encryption_mode ==
+ child_ctx.filenames_encryption_mode) &&
+ (parent_ctx.flags == child_ctx.flags);
}
/**
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 7c1678ba8f92..60972a559685 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -124,19 +124,29 @@ struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
de = &d->dentry[bit_pos];
- /* encrypted case */
+ if (de->hash_code != namehash)
+ goto not_match;
+
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
- /* show encrypted name */
- if (fname->hash) {
- if (de->hash_code == fname->hash)
- goto found;
- } else if (de_name.len == name->len &&
- de->hash_code == namehash &&
- !memcmp(de_name.name, name->name, name->len))
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (unlikely(!name->name)) {
+ if (fname->usr_fname->name[0] == '_') {
+ if (de_name.len > 32 &&
+ !memcmp(de_name.name + ((de_name.len - 17) & ~15),
+ fname->crypto_buf.name + 8, 16))
+ goto found;
+ goto not_match;
+ }
+ name->name = fname->crypto_buf.name;
+ name->len = fname->crypto_buf.len;
+ }
+#endif
+ if (de_name.len == name->len &&
+ !memcmp(de_name.name, name->name, name->len))
goto found;
-
+not_match:
if (max_slots && max_len > *max_slots)
*max_slots = max_len;
max_len = 0;
@@ -170,7 +180,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
int max_slots;
f2fs_hash_t namehash;
- namehash = f2fs_dentry_hash(&name);
+ namehash = f2fs_dentry_hash(&name, fname);
f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
@@ -547,7 +557,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
level = 0;
slots = GET_DENTRY_SLOTS(new_name.len);
- dentry_hash = f2fs_dentry_hash(&new_name);
+ dentry_hash = f2fs_dentry_hash(&new_name, NULL);
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b1aeca83f4be..2871576fbca4 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1722,7 +1722,8 @@ void f2fs_msg(struct super_block *, const char *, const char *, ...);
/*
* hash.c
*/
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+ struct f2fs_filename *fname);
/*
* node.c
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 71b7206c431e..b238d2fec3e5 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -70,7 +70,8 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
*buf++ = pad;
}
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+ struct f2fs_filename *fname)
{
__u32 hash;
f2fs_hash_t f2fs_hash;
@@ -79,6 +80,10 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
const unsigned char *name = name_info->name;
size_t len = name_info->len;
+ /* encrypted bigname case */
+ if (fname && !fname->disk_name.name)
+ return cpu_to_le32(fname->hash);
+
if (is_dot_dotdot(name_info))
return 0;
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index bda7126466c0..ad80f916b64d 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -303,7 +303,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
if (IS_ERR(ipage))
return NULL;
- namehash = f2fs_dentry_hash(&name);
+ namehash = f2fs_dentry_hash(&name, fname);
inline_dentry = inline_data_addr(ipage);
@@ -468,7 +468,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
f2fs_wait_on_page_writeback(ipage, NODE);
- name_hash = f2fs_dentry_hash(name);
+ name_hash = f2fs_dentry_hash(name, NULL);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3a65e0132352..86e1cb899957 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -918,6 +918,79 @@ static loff_t max_file_size(unsigned bits)
return result;
}
+static inline bool sanity_check_area_boundary(struct super_block *sb,
+ struct f2fs_super_block *raw_super)
+{
+ u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+ u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
+ u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
+ u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr);
+ u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+ u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+ u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt);
+ u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit);
+ u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat);
+ u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa);
+ u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+ u32 segment_count = le32_to_cpu(raw_super->segment_count);
+ u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+
+ if (segment0_blkaddr != cp_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+ segment0_blkaddr, cp_blkaddr);
+ return true;
+ }
+
+ if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) !=
+ sit_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong CP boundary, start(%u) end(%u) blocks(%u)",
+ cp_blkaddr, sit_blkaddr,
+ segment_count_ckpt << log_blocks_per_seg);
+ return true;
+ }
+
+ if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) !=
+ nat_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong SIT boundary, start(%u) end(%u) blocks(%u)",
+ sit_blkaddr, nat_blkaddr,
+ segment_count_sit << log_blocks_per_seg);
+ return true;
+ }
+
+ if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) !=
+ ssa_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong NAT boundary, start(%u) end(%u) blocks(%u)",
+ nat_blkaddr, ssa_blkaddr,
+ segment_count_nat << log_blocks_per_seg);
+ return true;
+ }
+
+ if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) !=
+ main_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong SSA boundary, start(%u) end(%u) blocks(%u)",
+ ssa_blkaddr, main_blkaddr,
+ segment_count_ssa << log_blocks_per_seg);
+ return true;
+ }
+
+ if (main_blkaddr + (segment_count_main << log_blocks_per_seg) !=
+ segment0_blkaddr + (segment_count << log_blocks_per_seg)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong MAIN_AREA boundary, start(%u) end(%u) blocks(%u)",
+ main_blkaddr,
+ segment0_blkaddr + (segment_count << log_blocks_per_seg),
+ segment_count_main << log_blocks_per_seg);
+ return true;
+ }
+
+ return false;
+}
+
static int sanity_check_raw_super(struct super_block *sb,
struct f2fs_super_block *raw_super)
{
@@ -947,6 +1020,14 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
+ /* check log blocks per segment */
+ if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid log blocks per segment (%u)\n",
+ le32_to_cpu(raw_super->log_blocks_per_seg));
+ return 1;
+ }
+
/* Currently, support 512/1024/2048/4096 bytes sector size */
if (le32_to_cpu(raw_super->log_sectorsize) >
F2FS_MAX_LOG_SECTOR_SIZE ||
@@ -965,6 +1046,30 @@ static int sanity_check_raw_super(struct super_block *sb,
le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
+
+ /* check reserved ino info */
+ if (le32_to_cpu(raw_super->node_ino) != 1 ||
+ le32_to_cpu(raw_super->meta_ino) != 2 ||
+ le32_to_cpu(raw_super->root_ino) != 3) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid Fs Meta Ino: node(%u) meta(%u) root(%u)",
+ le32_to_cpu(raw_super->node_ino),
+ le32_to_cpu(raw_super->meta_ino),
+ le32_to_cpu(raw_super->root_ino));
+ return 1;
+ }
+
+ if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid segment count (%u)",
+ le32_to_cpu(raw_super->segment_count));
+ return 1;
+ }
+
+ /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
+ if (sanity_check_area_boundary(sb, raw_super))
+ return 1;
+
return 0;
}
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 4304072161aa..40d61077bead 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -542,6 +542,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
if (invalidate)
set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
}
} else {
@@ -560,6 +561,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
TASK_UNINTERRUPTIBLE);
+ /* Make sure any pending writes are cancelled. */
+ if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+ fscache_invalidate_writes(cookie);
+
/* Reset the cookie state if it wasn't relinquished */
if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 9b28649df3a1..a8aa00be4444 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -48,6 +48,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
cookie->flags = 1 << FSCACHE_COOKIE_ENABLED;
spin_lock_init(&cookie->lock);
+ spin_lock_init(&cookie->stores_lock);
INIT_HLIST_HEAD(&cookie->backing_objects);
/* check the netfs type is not already present */
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9e792e30f4db..7a182c87f378 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -30,6 +30,7 @@ static const struct fscache_state *fscache_look_up_object(struct fscache_object
static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);
#define __STATE_NAME(n) fscache_osm_##n
#define STATE(n) (&__STATE_NAME(n))
@@ -91,7 +92,7 @@ static WORK_STATE(LOOKUP_FAILURE, "LCFL", fscache_lookup_failure);
static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object);
static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents);
static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object);
-static WORK_STATE(OBJECT_DEAD, "DEAD", (void*)2UL);
+static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead);
static WAIT_STATE(WAIT_FOR_INIT, "?INI",
TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD));
@@ -229,6 +230,10 @@ execute_work_state:
event = -1;
if (new_state == NO_TRANSIT) {
_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
+ _leave(" [dead]");
+ return;
+ }
fscache_enqueue_object(object);
event_mask = object->oob_event_mask;
goto unmask_events;
@@ -239,7 +244,7 @@ execute_work_state:
object->state = state = new_state;
if (state->work) {
- if (unlikely(state->work == ((void *)2UL))) {
+ if (unlikely(state == STATE(OBJECT_DEAD))) {
_leave(" [dead]");
return;
}
@@ -645,6 +650,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
fscache_mark_object_dead(object);
object->oob_event_mask = 0;
+ if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+ /* Reject any new read/write ops and abort any that are pending. */
+ clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+ fscache_cancel_all_ops(object);
+ }
+
if (list_empty(&object->dependents) &&
object->n_ops == 0 &&
object->n_children == 0)
@@ -1077,3 +1088,20 @@ void fscache_object_mark_killed(struct fscache_object *object,
}
}
EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead. We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+ int event)
+{
+ if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+ &object->flags))
+ return NO_TRANSIT;
+
+ WARN(true, "FS-Cache object redispatched after death");
+ return NO_TRANSIT;
+}
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index ad8a5b757cc7..a443c6e54412 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -760,7 +760,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index,
int error;
error = get_leaf_nr(dip, index, &leaf_no);
- if (!error)
+ if (!IS_ERR_VALUE(error))
error = get_leaf(dip, leaf_no, bh_out);
return error;
@@ -976,7 +976,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
index = name->hash >> (32 - dip->i_depth);
error = get_leaf_nr(dip, index, &leaf_no);
- if (error)
+ if (IS_ERR_VALUE(error))
return error;
/* Get the old leaf block */
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 8f9176caf098..c8d58c5ac8ae 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -758,7 +758,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
sb->s_blocksize - offset : toread;
tmp_bh.b_state = 0;
- tmp_bh.b_size = 1 << inode->i_blkbits;
+ tmp_bh.b_size = i_blocksize(inode);
err = jfs_get_block(inode, blk, &tmp_bh, 0);
if (err)
return err;
@@ -798,7 +798,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
sb->s_blocksize - offset : towrite;
tmp_bh.b_state = 0;
- tmp_bh.b_size = 1 << inode->i_blkbits;
+ tmp_bh.b_size = i_blocksize(inode);
err = jfs_get_block(inode, blk, &tmp_bh, 1);
if (err)
goto out;
diff --git a/fs/mount.h b/fs/mount.h
index 3dc7dea5a357..13a4ebbbaa74 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -13,6 +13,8 @@ struct mnt_namespace {
u64 seq; /* Sequence number to prevent loops */
wait_queue_head_t poll;
u64 event;
+ unsigned int mounts; /* # of mounts in the namespace */
+ unsigned int pending_mounts;
};
struct mnt_pcp {
diff --git a/fs/mpage.c b/fs/mpage.c
index 1480d3a18037..6ade29b19494 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -111,7 +111,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
SetPageUptodate(page);
return;
}
- create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+ create_empty_buffers(page, i_blocksize(inode), 0);
}
head = page_buffers(page);
page_bh = head;
diff --git a/fs/namespace.c b/fs/namespace.c
index 7df3d406d3e0..f26d18d69712 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,9 @@
#include "pnode.h"
#include "internal.h"
+/* Maximum number of mounts in a mount namespace */
+unsigned int sysctl_mount_max __read_mostly = 100000;
+
static unsigned int m_hash_mask __read_mostly;
static unsigned int m_hash_shift __read_mostly;
static unsigned int mp_hash_mask __read_mostly;
@@ -925,6 +928,9 @@ static void commit_tree(struct mount *mnt)
list_splice(&head, n->list.prev);
+ n->mounts += n->pending_mounts;
+ n->pending_mounts = 0;
+
__attach_mnt(mnt, parent);
touch_mnt_namespace(n);
}
@@ -1445,11 +1451,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
propagate_umount(&tmp_list);
while (!list_empty(&tmp_list)) {
+ struct mnt_namespace *ns;
bool disconnect;
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
- __touch_mnt_namespace(p->mnt_ns);
+ ns = p->mnt_ns;
+ if (ns) {
+ ns->mounts--;
+ __touch_mnt_namespace(ns);
+ }
p->mnt_ns = NULL;
if (how & UMOUNT_SYNC)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
@@ -1850,6 +1861,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse)
return 0;
}
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
+{
+ unsigned int max = READ_ONCE(sysctl_mount_max);
+ unsigned int mounts = 0, old, pending, sum;
+ struct mount *p;
+
+ for (p = mnt; p; p = next_mnt(p, mnt))
+ mounts++;
+
+ old = ns->mounts;
+ pending = ns->pending_mounts;
+ sum = old + pending;
+ if ((old > sum) ||
+ (pending > sum) ||
+ (max < sum) ||
+ (mounts > (max - sum)))
+ return -ENOSPC;
+
+ ns->pending_mounts = pending + mounts;
+ return 0;
+}
+
/*
* @source_mnt : mount tree to be attached
* @nd : place the mount tree @source_mnt is attached
@@ -1919,6 +1952,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
struct path *parent_path)
{
HLIST_HEAD(tree_list);
+ struct mnt_namespace *ns = dest_mnt->mnt_ns;
struct mountpoint *smp;
struct mount *child, *p;
struct hlist_node *n;
@@ -1931,6 +1965,13 @@ static int attach_recursive_mnt(struct mount *source_mnt,
if (IS_ERR(smp))
return PTR_ERR(smp);
+ /* Is there space to add these mounts to the mount namespace? */
+ if (!parent_path) {
+ err = count_mounts(ns, source_mnt);
+ if (err)
+ goto out;
+ }
+
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
@@ -1970,11 +2011,14 @@ static int attach_recursive_mnt(struct mount *source_mnt,
out_cleanup_ids:
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+ child->mnt_parent->mnt_ns->pending_mounts = 0;
umount_tree(child, UMOUNT_SYNC);
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
out:
+ ns->pending_mounts = 0;
+
read_seqlock_excl(&mount_lock);
put_mountpoint(smp);
read_sequnlock_excl(&mount_lock);
@@ -2804,6 +2848,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
init_waitqueue_head(&new_ns->poll);
new_ns->event = 0;
new_ns->user_ns = get_user_ns(user_ns);
+ new_ns->mounts = 0;
+ new_ns->pending_mounts = 0;
return new_ns;
}
@@ -2853,6 +2899,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
q = new;
while (p) {
q->mnt_ns = new_ns;
+ new_ns->mounts++;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
@@ -2891,6 +2938,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
new_ns->root = mnt;
+ new_ns->mounts++;
list_add(&mnt->mnt_list, &new_ns->list);
} else {
mntput(m);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 52ee0b73ab4a..5b21b1ca2341 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2421,6 +2421,20 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
}
EXPORT_SYMBOL_GPL(nfs_may_open);
+static int nfs_execute_ok(struct inode *inode, int mask)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ int ret;
+
+ if (mask & MAY_NOT_BLOCK)
+ ret = nfs_revalidate_inode_rcu(server, inode);
+ else
+ ret = nfs_revalidate_inode(server, inode);
+ if (ret == 0 && !execute_ok(inode))
+ ret = -EACCES;
+ return ret;
+}
+
int nfs_permission(struct inode *inode, int mask)
{
struct rpc_cred *cred;
@@ -2438,6 +2452,9 @@ int nfs_permission(struct inode *inode, int mask)
case S_IFLNK:
goto out;
case S_IFREG:
+ if ((mask & MAY_OPEN) &&
+ nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN))
+ return 0;
break;
case S_IFDIR:
/*
@@ -2470,8 +2487,8 @@ force_lookup:
res = PTR_ERR(cred);
}
out:
- if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
- res = -EACCES;
+ if (!res && (mask & MAY_EXEC))
+ res = nfs_execute_ok(inode, mask);
dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
inode->i_sb->s_id, inode->i_ino, mask, res);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 82dc3035ea45..e8d1d6c5000c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1072,6 +1072,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
case -NFS4ERR_BADXDR:
case -NFS4ERR_RESOURCE:
case -NFS4ERR_NOFILEHANDLE:
+ case -NFS4ERR_MOVED:
/* Non-seqid mutating errors */
return;
};
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index c29d9421bd5e..0976f8dad4ce 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -50,7 +50,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
{
struct nfsd4_layout_seg *seg = &args->lg_seg;
struct super_block *sb = inode->i_sb;
- u32 block_size = (1 << inode->i_blkbits);
+ u32 block_size = i_blocksize(inode);
struct pnfs_block_extent *bex;
struct iomap iomap;
u32 device_generation = 0;
@@ -151,7 +151,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
int error;
nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
- lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+ lcp->lc_up_len, &iomaps, i_blocksize(inode));
if (nr_iomaps < 0)
return nfserrno(nr_iomaps);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 00575d776d91..7162ab7bc093 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -358,6 +358,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
{
unsigned int len, v, hdr, dlen;
u32 max_blocksize = svc_max_payload(rqstp);
+ struct kvec *head = rqstp->rq_arg.head;
p = decode_fh(p, &args->fh);
if (!p)
@@ -367,6 +368,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
args->count = ntohl(*p++);
args->stable = ntohl(*p++);
len = args->len = ntohl(*p++);
+ if ((void *)p > head->iov_base + head->iov_len)
+ return 0;
/*
* The count must equal the amount of data passed.
*/
@@ -377,9 +380,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
* Check to make sure that we got the right number of
* bytes.
*/
- hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
- dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
- - hdr;
+ hdr = (void*)p - head->iov_base;
+ dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
/*
* Round the length of the data which was specified up to
* the next multiple of XDR units and then compare that
@@ -396,7 +398,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
len = args->len = max_blocksize;
}
rqstp->rq_vec[0].iov_base = (void*)p;
- rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+ rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
@@ -471,6 +473,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
/* first copy and check from the first page */
old = (char*)p;
vec = &rqstp->rq_arg.head[0];
+ if ((void *)old > vec->iov_base + vec->iov_len)
+ return 0;
avail = vec->iov_len - (old - (char*)vec->iov_base);
while (len && avail && *old) {
*new++ = *old++;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7d5351cd67fb..209dbfc50cd4 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1690,6 +1690,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
opdesc->op_get_currentstateid(cstate, &op->u);
op->status = opdesc->op_func(rqstp, cstate, &op->u);
+ /* Only from SEQUENCE */
+ if (cstate->status == nfserr_replay_cache) {
+ dprintk("%s NFS4.1 replay from cache\n", __func__);
+ status = op->status;
+ goto out;
+ }
if (!op->status) {
if (opdesc->op_set_currentstateid)
opdesc->op_set_currentstateid(cstate, &op->u);
@@ -1700,14 +1706,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
if (need_wrongsec_check(rqstp))
op->status = check_nfsd_access(current_fh->fh_export, rqstp);
}
-
encode_op:
- /* Only from SEQUENCE */
- if (cstate->status == nfserr_replay_cache) {
- dprintk("%s NFS4.1 replay from cache\n", __func__);
- status = op->status;
- goto out;
- }
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
nfsd4_encode_replay(&resp->xdr, op);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 12935209deca..3f68a25f2169 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2753,9 +2753,16 @@ out_acl:
}
#endif /* CONFIG_NFSD_PNFS */
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
- status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
- NFSD_SUPPATTR_EXCLCREAT_WORD1,
- NFSD_SUPPATTR_EXCLCREAT_WORD2);
+ u32 supp[3];
+
+ supp[0] = nfsd_suppattrs0(minorversion);
+ supp[1] = nfsd_suppattrs1(minorversion);
+ supp[2] = nfsd_suppattrs2(minorversion);
+ supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0;
+ supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1;
+ supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2;
+
+ status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]);
if (status)
goto out;
}
@@ -4041,8 +4048,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_getdeviceinfo *gdev)
{
struct xdr_stream *xdr = &resp->xdr;
- const struct nfsd4_layout_ops *ops =
- nfsd4_layout_ops[gdev->gd_layout_type];
+ const struct nfsd4_layout_ops *ops;
u32 starting_len = xdr->buf->len, needed_len;
__be32 *p;
@@ -4059,6 +4065,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
/* If maxcount is 0 then just update notifications */
if (gdev->gd_maxcount != 0) {
+ ops = nfsd4_layout_ops[gdev->gd_layout_type];
nfserr = ops->encode_getdeviceinfo(xdr, gdev);
if (nfserr) {
/*
@@ -4111,8 +4118,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutget *lgp)
{
struct xdr_stream *xdr = &resp->xdr;
- const struct nfsd4_layout_ops *ops =
- nfsd4_layout_ops[lgp->lg_layout_type];
+ const struct nfsd4_layout_ops *ops;
__be32 *p;
dprintk("%s: err %d\n", __func__, nfserr);
@@ -4135,6 +4141,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
*p++ = cpu_to_be32(lgp->lg_seg.iomode);
*p++ = cpu_to_be32(lgp->lg_layout_type);
+ ops = nfsd4_layout_ops[lgp->lg_layout_type];
nfserr = ops->encode_layoutget(xdr, lgp);
out:
kfree(lgp->lg_content);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ad4e2377dd63..5be1fa6b676d 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -656,6 +656,37 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
return nfserr;
}
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page. The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+ struct svc_procedure *proc)
+{
+ /*
+ * The ACL code has more careful bounds-checking and is not
+ * susceptible to this problem:
+ */
+ if (rqstp->rq_prog != NFS_PROGRAM)
+ return false;
+ /*
+ * Ditto NFSv4 (which can in theory have argument and reply both
+ * more than a page):
+ */
+ if (rqstp->rq_vers >= 4)
+ return false;
+ /* The reply will be small, we're OK: */
+ if (proc->pc_xdrressize > 0 &&
+ proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+ return false;
+
+ return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
int
nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
{
@@ -668,6 +699,11 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
rqstp->rq_vers, rqstp->rq_proc);
proc = rqstp->rq_procinfo;
+ if (nfs_request_too_big(rqstp, proc)) {
+ dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+ *statp = rpc_garbage_args;
+ return 1;
+ }
/*
* Give the xdr decoder a chance to change this if it wants
* (necessary in the NFSv4.0 compound case)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 79d964aa8079..bf913201a6ad 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -280,6 +280,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_writeargs *args)
{
unsigned int len, hdr, dlen;
+ struct kvec *head = rqstp->rq_arg.head;
int v;
p = decode_fh(p, &args->fh);
@@ -300,9 +301,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
* Check to make sure that we got the right number of
* bytes.
*/
- hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
- dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
- - hdr;
+ hdr = (void*)p - head->iov_base;
+ if (hdr > head->iov_len)
+ return 0;
+ dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
/*
* Round the length of the data which was specified up to
@@ -316,7 +318,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
return 0;
rqstp->rq_vec[0].iov_base = (void*)p;
- rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+ rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index a35ae35e6932..cd39b57288c2 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -55,7 +55,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
brelse(bh);
BUG();
}
- memset(bh->b_data, 0, 1 << inode->i_blkbits);
+ memset(bh->b_data, 0, i_blocksize(inode));
bh->b_bdev = inode->i_sb->s_bdev;
bh->b_blocknr = blocknr;
set_buffer_mapped(bh);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index ac2f64943ff4..00877ef0b120 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -55,7 +55,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
- inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
+ inode_add_bytes(inode, i_blocksize(inode) * n);
if (root)
atomic64_add(n, &root->blocks_count);
}
@@ -64,7 +64,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
- inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
+ inode_sub_bytes(inode, i_blocksize(inode) * n);
if (root)
atomic64_sub(n, &root->blocks_count);
}
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 1125f40233ff..612a2457243d 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -60,7 +60,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
set_buffer_mapped(bh);
kaddr = kmap_atomic(bh->b_page);
- memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits);
+ memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
if (init_block)
init_block(inode, bh, kaddr);
flush_dcache_page(bh->b_page);
@@ -503,7 +503,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned entry_size,
struct nilfs_mdt_info *mi = NILFS_MDT(inode);
mi->mi_entry_size = entry_size;
- mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size;
+ mi->mi_entries_per_block = i_blocksize(inode) / entry_size;
mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
}
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 3b65adaae7e4..2f27c935bd57 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -719,7 +719,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
lock_page(page);
if (!page_has_buffers(page))
- create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+ create_empty_buffers(page, i_blocksize(inode), 0);
unlock_page(page);
bh = head = page_buffers(page);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index e6795c7c76a8..e4184bd2a954 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1103,7 +1103,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
int ret = 0;
struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
unsigned int block_end, block_start;
- unsigned int bsize = 1 << inode->i_blkbits;
+ unsigned int bsize = i_blocksize(inode);
if (!page_has_buffers(page))
create_empty_buffers(page, bsize, 0);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 56dd3957cc91..1d738723a41a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
/* We know that zero_from is block aligned */
for (block_start = zero_from; block_start < zero_to;
block_start = block_end) {
- block_end = block_start + (1 << inode->i_blkbits);
+ block_end = block_start + i_blocksize(inode);
/*
* block_start is block-aligned. Bump it by one to force
diff --git a/fs/pnode.c b/fs/pnode.c
index b9f2af59b9a6..b394ca5307ec 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -259,7 +259,7 @@ static int propagate_one(struct mount *m)
read_sequnlock_excl(&mount_lock);
}
hlist_add_head(&child->mnt_hash, list);
- return 0;
+ return count_mounts(m->mnt_ns, child);
}
/*
diff --git a/fs/pnode.h b/fs/pnode.h
index 623f01772bec..dc87e65becd2 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -54,4 +54,5 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
struct mount *copy_tree(struct mount *, struct dentry *, int);
bool is_path_reachable(struct mount *, struct dentry *,
const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
#endif /* _LINUX_PNODE_H */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d2b8c754f627..dd732400578e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3058,6 +3058,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
iter.tgid += 1, iter = next_tgid(ns, iter)) {
char name[PROC_NUMBUF];
int len;
+
+ cond_resched();
if (!has_pid_permissions(ns, iter.task, 2))
continue;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index ff3ffc76a937..3773335791da 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -469,6 +469,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
ent->data = NULL;
ent->proc_fops = NULL;
ent->proc_iops = NULL;
+ parent->nlink++;
if (proc_register(parent, ent) < 0) {
kfree(ent);
parent->nlink--;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index d598b9c809c1..db1a1427c27a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -803,7 +803,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+ pmd_t pmd = *pmdp;
+
+ /* See comment in change_huge_pmd() */
+ pmdp_invalidate(vma, addr, pmdp);
+ if (pmd_dirty(*pmdp))
+ pmd = pmd_mkdirty(pmd);
+ if (pmd_young(*pmdp))
+ pmd = pmd_mkyoung(pmd);
pmd = pmd_wrprotect(pmd);
pmd = pmd_clear_soft_dirty(pmd);
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 8f5ccdf81c25..38187300a2b4 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
int ret = 0;
th.t_trans_id = 0;
- blocksize = 1 << inode->i_blkbits;
+ blocksize = i_blocksize(inode);
if (logit) {
reiserfs_write_lock(s);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 3d8e7e671d5b..60ba35087d12 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -524,7 +524,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
* referenced in convert_tail_for_hole() that may be called from
* reiserfs_get_block()
*/
- bh_result->b_size = (1 << inode->i_blkbits);
+ bh_result->b_size = i_blocksize(inode);
ret = reiserfs_get_block(inode, iblock, bh_result,
create | GET_BLOCK_NO_DANGLE);
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 268733cda397..5f4f1882dc7d 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
+#include <linux/major.h>
#include "internal.h"
static struct kmem_cache *romfs_inode_cachep;
@@ -415,7 +416,22 @@ static void romfs_destroy_inode(struct inode *inode)
static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
- u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+ u64 id = 0;
+
+ /* When calling huge_encode_dev(),
+ * use sb->s_bdev->bd_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK defined
+ * use sb->s_dev when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD defined
+ * leave id as 0 when,
+ * - CONFIG_ROMFS_ON_BLOCK undefined and
+ * - CONFIG_ROMFS_ON_MTD undefined
+ */
+ if (sb->s_bdev)
+ id = huge_encode_dev(sb->s_bdev->bd_dev);
+ else if (sb->s_dev)
+ id = huge_encode_dev(sb->s_dev);
buf->f_type = ROMFS_MAGIC;
buf->f_namelen = ROMFS_MAXFN;
@@ -488,6 +504,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_flags |= MS_RDONLY | MS_NOATIME;
sb->s_op = &romfs_super_ops;
+#ifdef CONFIG_ROMFS_ON_MTD
+ /* Use same dev ID from the underlying mtdblock device */
+ if (sb->s_mtd)
+ sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
/* read the image superblock and check it */
rsb = kmalloc(512, GFP_KERNEL);
if (!rsb)
diff --git a/fs/stat.c b/fs/stat.c
index d4a61d8dc021..004dd77c3b93 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -31,7 +31,7 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
stat->atime = inode->i_atime;
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
- stat->blksize = (1 << inode->i_blkbits);
+ stat->blksize = i_blocksize(inode);
stat->blocks = inode->i_blocks;
}
@@ -454,6 +454,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes)
inode->i_bytes -= 512;
}
}
+EXPORT_SYMBOL(__inode_add_bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes)
{
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b803213d1307..39c75a86c67f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
{
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
struct kobject *kobj = of->kn->parent->priv;
- size_t len;
+ ssize_t len;
/*
* If buf != of->prealloc_buf, we don't know how
@@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (len < 0)
+ return len;
if (pos) {
if (len <= pos)
return 0;
len -= pos;
memmove(buf, buf + pos, len);
}
- return min(count, len);
+ return min_t(ssize_t, count, len);
}
/* kernfs write callback for regular sysfs files */
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 053818dd6c18..1327a02ec778 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@ struct timerfd_ctx {
short unsigned settime_flags; /* to show in fdinfo */
struct rcu_head rcu;
struct list_head clist;
+ spinlock_t cancel_lock;
bool might_cancel;
};
@@ -112,7 +113,7 @@ void timerfd_clock_was_set(void)
rcu_read_unlock();
}
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
{
if (ctx->might_cancel) {
ctx->might_cancel = false;
@@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
}
}
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+ spin_lock(&ctx->cancel_lock);
+ __timerfd_remove_cancel(ctx);
+ spin_unlock(&ctx->cancel_lock);
+}
+
static bool timerfd_canceled(struct timerfd_ctx *ctx)
{
if (!ctx->might_cancel || ctx->moffs.tv64 != KTIME_MAX)
@@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
{
+ spin_lock(&ctx->cancel_lock);
if ((ctx->clockid == CLOCK_REALTIME ||
ctx->clockid == CLOCK_REALTIME_ALARM) &&
(flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
list_add_rcu(&ctx->clist, &cancel_list);
spin_unlock(&cancel_lock);
}
- } else if (ctx->might_cancel) {
- timerfd_remove_cancel(ctx);
+ } else {
+ __timerfd_remove_cancel(ctx);
}
+ spin_unlock(&ctx->cancel_lock);
}
static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -395,6 +405,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
return -ENOMEM;
init_waitqueue_head(&ctx->wqh);
+ spin_lock_init(&ctx->cancel_lock);
ctx->clockid = clockid;
if (isalarm(ctx))
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 566df9b5a6cb..7be3166ba553 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1206,7 +1206,7 @@ int udf_setsize(struct inode *inode, loff_t newsize)
{
int err;
struct udf_inode_info *iinfo;
- int bsize = 1 << inode->i_blkbits;
+ int bsize = i_blocksize(inode);
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index dc5fae601c24..637e17cb0edd 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -81,7 +81,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
ufs_error (sb, "ufs_free_fragments",
"bit already cleared for fragment %u", i);
}
-
+
+ inode_sub_bytes(inode, count << uspi->s_fshift);
fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
uspi->cs_total.cs_nffree += count;
fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
@@ -183,6 +184,7 @@ do_more:
ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
}
ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+ inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
ufs_clusteracct (sb, ucpi, blkno, 1);
@@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
return 0;
}
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+ unsigned size = frags * i_blocksize(inode);
+ spin_lock(&inode->i_lock);
+ __inode_add_bytes(inode, size);
+ if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+ __inode_sub_bytes(inode, size);
+ spin_unlock(&inode->i_lock);
+ return false;
+ }
+ spin_unlock(&inode->i_lock);
+ return true;
+}
+
static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
unsigned oldcount, unsigned newcount)
{
@@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
for (i = oldcount; i < newcount; i++)
if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
return 0;
+
+ if (!try_add_frags(inode, count))
+ return 0;
/*
* Block can be extended
*/
@@ -647,6 +666,7 @@ cg_found:
ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
i = uspi->s_fpb - count;
+ inode_sub_bytes(inode, i << uspi->s_fshift);
fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
uspi->cs_total.cs_nffree += i;
fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
@@ -657,6 +677,8 @@ cg_found:
result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
if (result == INVBLOCK)
return 0;
+ if (!try_add_frags(inode, count))
+ return 0;
for (i = 0; i < count; i++)
ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
@@ -716,6 +738,8 @@ norot:
return INVBLOCK;
ucpi->c_rotor = result;
gotit:
+ if (!try_add_frags(inode, uspi->s_fpb))
+ return 0;
blkno = ufs_fragstoblks(result);
ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index a064cf44b143..1f69bb9b1e9d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
p = ufs_get_direct_data_ptr(uspi, ufsi, block);
tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
- new_size, err, locked_page);
+ new_size - (lastfrag & uspi->s_fpbmask), err,
+ locked_page);
return tmp != 0;
}
@@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
goal += uspi->s_fpb;
}
tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
- goal, uspi->s_fpb, err, locked_page);
+ goal, nfrags, err, locked_page);
if (!tmp) {
*err = -ENOSPC;
@@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
if (!create) {
phys64 = ufs_frag_map(inode, offsets, depth);
- goto out;
+ if (phys64)
+ map_bh(bh_result, sb, phys64 + frag);
+ return 0;
}
/* This code entered only while writing ....? */
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f6390eec02ca..10f364490833 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb)
return;
}
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+ struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+ int bits = uspi->s_apbshift;
+ u64 res;
+
+ if (bits > 21)
+ res = ~0ULL;
+ else
+ res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+ (1LL << (3*bits));
+
+ if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+ return MAX_LFS_FILESIZE;
+ return res << uspi->s_bshift;
+}
+
static int ufs_fill_super(struct super_block *sb, void *data, int silent)
{
struct ufs_sb_info * sbi;
@@ -1212,6 +1229,7 @@ magic_found:
"fast symlink size (%u)\n", uspi->s_maxsymlinklen);
uspi->s_maxsymlinklen = maxsymlen;
}
+ sb->s_maxbytes = ufs_max_bytes(sb);
sb->s_max_links = UFS_LINK_MAX;
inode = ufs_iget(sb, UFS_ROOTINO);
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 954175928240..3f9463f8cf2f 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_(
static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
{
+ u8 mask;
switch (uspi->s_fpb) {
case 8:
return (*ubh_get_addr (ubh, begin + block) == 0xff);
case 4:
- return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+ mask = 0x0f << ((block & 0x01) << 2);
+ return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
case 2:
- return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+ mask = 0x03 << ((block & 0x03) << 1);
+ return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
case 1:
- return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+ mask = 0x01 << (block & 0x07);
+ return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
}
return 0;
}
diff --git a/fs/xattr.c b/fs/xattr.c
index 9b932b95d74e..f0da9d24e9ca 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -442,7 +442,7 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
size = XATTR_SIZE_MAX;
kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!kvalue) {
- vvalue = vmalloc(size);
+ vvalue = vzalloc(size);
if (!vvalue)
return -ENOMEM;
kvalue = vvalue;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 119c2422aac7..75884aecf920 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2179,8 +2179,10 @@ xfs_bmap_add_extent_delay_real(
}
temp = xfs_bmap_worst_indlen(bma->ip, temp);
temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
- diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
- (bma->cur ? bma->cur->bc_private.b.allocated : 0));
+ diff = (int)(temp + temp2 -
+ (startblockval(PREV.br_startblock) -
+ (bma->cur ?
+ bma->cur->bc_private.b.allocated : 0)));
if (diff > 0) {
error = xfs_mod_fdblocks(bma->ip->i_mount,
-((int64_t)diff), false);
@@ -2232,7 +2234,6 @@ xfs_bmap_add_extent_delay_real(
temp = da_new;
if (bma->cur)
temp += bma->cur->bc_private.b.allocated;
- ASSERT(temp <= da_old);
if (temp < da_old)
xfs_mod_fdblocks(bma->ip->i_mount,
(int64_t)(da_old - temp), false);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index af1bbee5586e..28bc5e78b110 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4064,7 +4064,7 @@ xfs_btree_change_owner(
xfs_btree_readahead_ptr(cur, ptr, 1);
/* save for the next iteration of the loop */
- lptr = *ptr;
+ xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
}
/* for each buffer in the level */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 29e7e5dd5178..187b80267ff9 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -288,7 +288,7 @@ xfs_map_blocks(
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- ssize_t count = 1 << inode->i_blkbits;
+ ssize_t count = i_blocksize(inode);
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
@@ -921,7 +921,7 @@ xfs_aops_discard_page(
break;
}
next_buffer:
- offset += 1 << inode->i_blkbits;
+ offset += i_blocksize(inode);
} while ((bh = bh->b_this_page) != head);
@@ -1363,7 +1363,7 @@ xfs_map_trim_size(
offset + mapping_size >= i_size_read(inode)) {
/* limit mapping to block that spans EOF */
mapping_size = roundup_64(i_size_read(inode) - offset,
- 1 << inode->i_blkbits);
+ i_blocksize(inode));
}
if (mapping_size > LONG_MAX)
mapping_size = LONG_MAX;
@@ -1395,7 +1395,7 @@ __xfs_get_blocks(
return -EIO;
offset = (xfs_off_t)iblock << inode->i_blkbits;
- ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
+ ASSERT(bh_result->b_size >= i_blocksize(inode));
size = bh_result->b_size;
if (!create && direct && offset >= i_size_read(inode))
@@ -1968,7 +1968,7 @@ xfs_vm_set_page_dirty(
if (offset < end_offset)
set_buffer_dirty(bh);
bh = bh->b_this_page;
- offset += 1 << inode->i_blkbits;
+ offset += i_blocksize(inode);
} while (bh != head);
}
/*
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index dd4824589470..234331227c0c 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -112,6 +112,7 @@ typedef struct attrlist_cursor_kern {
*========================================================================*/
+/* Return 0 on success, or -errno; other state communicated via *context */
typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int,
unsigned char *, int, int, unsigned char *);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 4fa14820e2e2..c8be331a3196 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -108,16 +108,14 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
(int)sfe->namelen,
(int)sfe->valuelen,
&sfe->nameval[sfe->namelen]);
-
+ if (error)
+ return error;
/*
* Either search callback finished early or
* didn't fit it all in the buffer after all.
*/
if (context->seen_enough)
break;
-
- if (error)
- return error;
sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
}
trace_xfs_attr_list_sf_all(context);
@@ -581,7 +579,7 @@ xfs_attr_put_listent(
trace_xfs_attr_list_full(context);
alist->al_more = 1;
context->seen_enough = 1;
- return 1;
+ return 0;
}
aep = (attrlist_ent_t *)&context->alist[context->firstu];
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 832764ee035a..863e1bff403b 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -682,7 +682,7 @@ xfs_getbmap(
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
- map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+ map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8146b0cf20ce..dcb70969ff1c 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -979,6 +979,8 @@ void
xfs_buf_unlock(
struct xfs_buf *bp)
{
+ ASSERT(xfs_buf_islocked(bp));
+
XB_CLEAR_OWNER(bp);
up(&bp->b_sema);
@@ -1713,6 +1715,28 @@ error:
}
/*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+ struct list_head *list)
+{
+ struct xfs_buf *bp;
+
+ while (!list_empty(list)) {
+ bp = list_first_entry(list, struct xfs_buf, b_list);
+
+ xfs_buf_lock(bp);
+ bp->b_flags &= ~_XBF_DELWRI_Q;
+ list_del_init(&bp->b_list);
+ xfs_buf_relse(bp);
+ }
+}
+
+/*
* Add a buffer to the delayed write list.
*
* This queues a buffer for writeout if it hasn't already been. Note that
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index c75721acd867..149bbd451731 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -304,6 +304,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
extern void *xfs_buf_offset(struct xfs_buf *, size_t);
/* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 642d55d10075..2fbf643fa10a 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -406,6 +406,7 @@ xfs_dir2_leaf_readbuf(
/*
* Do we need more readahead?
+ * Each loop tries to process 1 full dir blk; last may be partial.
*/
blk_start_plug(&plug);
for (mip->ra_index = mip->ra_offset = i = 0;
@@ -416,7 +417,8 @@ xfs_dir2_leaf_readbuf(
* Read-ahead a contiguous directory block.
*/
if (i > mip->ra_current &&
- map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+ (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
+ geo->fsbcount) {
xfs_dir3_data_readahead(dp,
map[mip->ra_index].br_startoff + mip->ra_offset,
XFS_FSB_TO_DADDR(dp->i_mount,
@@ -437,14 +439,19 @@ xfs_dir2_leaf_readbuf(
}
/*
- * Advance offset through the mapping table.
+ * Advance offset through the mapping table, processing a full
+ * dir block even if it is fragmented into several extents.
+ * But stop if we have consumed all valid mappings, even if
+ * it's not yet a full directory block.
*/
- for (j = 0; j < geo->fsbcount; j += length ) {
+ for (j = 0;
+ j < geo->fsbcount && mip->ra_index < mip->map_valid;
+ j += length ) {
/*
* The rest of this extent but not more than a dir
* block.
*/
- length = min_t(int, geo->fsbcount,
+ length = min_t(int, geo->fsbcount - j,
map[mip->ra_index].br_blockcount -
mip->ra_offset);
mip->ra_offset += length;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f5392ab2def1..3dd47307363f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -947,7 +947,7 @@ xfs_file_fallocate(
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
- unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+ unsigned int blksize_mask = i_blocksize(inode) - 1;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
@@ -969,7 +969,7 @@ xfs_file_fallocate(
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
- unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+ unsigned int blksize_mask = i_blocksize(inode) - 1;
new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
@@ -1208,7 +1208,7 @@ xfs_find_get_desired_pgoff(
unsigned nr_pages;
unsigned int i;
- want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+ want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
want);
/*
@@ -1235,17 +1235,6 @@ xfs_find_get_desired_pgoff(
break;
}
- /*
- * At lease we found one page. If this is the first time we
- * step into the loop, and if the first page index offset is
- * greater than the given search offset, a hole was found.
- */
- if (type == HOLE_OFF && lastoff == startoff &&
- lastoff < page_offset(pvec.pages[0])) {
- found = true;
- break;
- }
-
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
loff_t b_offset;
@@ -1257,18 +1246,18 @@ xfs_find_get_desired_pgoff(
* file mapping. However, page->index will not change
* because we have a reference on the page.
*
- * Searching done if the page index is out of range.
- * If the current offset is not reaches the end of
- * the specified search range, there should be a hole
- * between them.
+ * If current page offset is beyond where we've ended,
+ * we've found a hole.
*/
- if (page->index > end) {
- if (type == HOLE_OFF && lastoff < endoff) {
- *offset = lastoff;
- found = true;
- }
+ if (type == HOLE_OFF && lastoff < endoff &&
+ lastoff < page_offset(pvec.pages[i])) {
+ found = true;
+ *offset = lastoff;
goto out;
}
+ /* Searching done if the page index is out of range. */
+ if (page->index > end)
+ goto out;
lock_page(page);
/*
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d7a490f24ead..adbc1f59969a 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -210,14 +210,17 @@ xfs_iget_cache_hit(
error = inode_init_always(mp->m_super, inode);
if (error) {
+ bool wake;
/*
* Re-initializing the inode failed, and we are in deep
* trouble. Try to re-add it to the reclaim list.
*/
rcu_read_lock();
spin_lock(&ip->i_flags_lock);
-
+ wake = !!__xfs_iflags_test(ip, XFS_INEW);
ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+ if (wake)
+ wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
trace_xfs_iget_reclaim_fail(ip);
goto out_error;
@@ -363,6 +366,22 @@ out_destroy:
return error;
}
+static void
+xfs_inew_wait(
+ struct xfs_inode *ip)
+{
+ wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+ DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+ do {
+ prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+ if (!xfs_iflags_test(ip, XFS_INEW))
+ break;
+ schedule();
+ } while (true);
+ finish_wait(wq, &wait.wait);
+}
+
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
@@ -467,9 +486,11 @@ out_error_or_again:
STATIC int
xfs_inode_ag_walk_grab(
- struct xfs_inode *ip)
+ struct xfs_inode *ip,
+ int flags)
{
struct inode *inode = VFS_I(ip);
+ bool newinos = !!(flags & XFS_AGITER_INEW_WAIT);
ASSERT(rcu_read_lock_held());
@@ -487,7 +508,8 @@ xfs_inode_ag_walk_grab(
goto out_unlock_noent;
/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
- if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+ if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+ __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
goto out_unlock_noent;
spin_unlock(&ip->i_flags_lock);
@@ -515,7 +537,8 @@ xfs_inode_ag_walk(
void *args),
int flags,
void *args,
- int tag)
+ int tag,
+ int iter_flags)
{
uint32_t first_index;
int last_error = 0;
@@ -557,7 +580,7 @@ restart:
for (i = 0; i < nr_found; i++) {
struct xfs_inode *ip = batch[i];
- if (done || xfs_inode_ag_walk_grab(ip))
+ if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
batch[i] = NULL;
/*
@@ -585,6 +608,9 @@ restart:
for (i = 0; i < nr_found; i++) {
if (!batch[i])
continue;
+ if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+ xfs_iflags_test(batch[i], XFS_INEW))
+ xfs_inew_wait(batch[i]);
error = execute(batch[i], flags, args);
IRELE(batch[i]);
if (error == -EAGAIN) {
@@ -637,12 +663,13 @@ xfs_eofblocks_worker(
}
int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
- void *args)
+ void *args,
+ int iter_flags)
{
struct xfs_perag *pag;
int error = 0;
@@ -652,7 +679,8 @@ xfs_inode_ag_iterator(
ag = 0;
while ((pag = xfs_perag_get(mp, ag))) {
ag = pag->pag_agno + 1;
- error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+ error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+ iter_flags);
xfs_perag_put(pag);
if (error) {
last_error = error;
@@ -664,6 +692,17 @@ xfs_inode_ag_iterator(
}
int
+xfs_inode_ag_iterator(
+ struct xfs_mount *mp,
+ int (*execute)(struct xfs_inode *ip, int flags,
+ void *args),
+ int flags,
+ void *args)
+{
+ return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
+int
xfs_inode_ag_iterator_tag(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags,
@@ -680,7 +719,8 @@ xfs_inode_ag_iterator_tag(
ag = 0;
while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
ag = pag->pag_agno + 1;
- error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+ error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+ 0);
xfs_perag_put(pag);
if (error) {
last_error = error;
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 62f1f91c32cb..147a79212e63 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -48,6 +48,11 @@ struct xfs_eofblocks {
#define XFS_IGET_UNTRUSTED 0x2
#define XFS_IGET_DONTCACHE 0x4
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT 0x1 /* wait on new inodes */
+
int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
uint flags, uint lock_flags, xfs_inode_t **ipp);
@@ -72,6 +77,9 @@ void xfs_eofblocks_worker(struct work_struct *);
int xfs_inode_ag_iterator(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+ int (*execute)(struct xfs_inode *ip, int flags, void *args),
+ int flags, void *args, int iter_flags);
int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args, int tag);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ca9e11989cbd..ae1a49845744 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -208,7 +208,8 @@ xfs_get_initial_prid(struct xfs_inode *dp)
#define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */
#define XFS_ISTALE (1 << 1) /* inode has been staled */
#define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */
-#define XFS_INEW (1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT 3 /* inode has just been allocated */
+#define XFS_INEW (1 << __XFS_INEW_BIT)
#define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */
#define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */
#define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */
@@ -453,6 +454,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(VFS_I(ip));
+ wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
}
static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d42738deec6d..e4a4f82ea13f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -403,6 +403,7 @@ xfs_attrlist_by_handle(
{
int error = -ENOMEM;
attrlist_cursor_kern_t *cursor;
+ struct xfs_fsop_attrlist_handlereq __user *p = arg;
xfs_fsop_attrlist_handlereq_t al_hreq;
struct dentry *dentry;
char *kbuf;
@@ -435,6 +436,11 @@ xfs_attrlist_by_handle(
if (error)
goto out_kfree;
+ if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
+ error = -EFAULT;
+ goto out_kfree;
+ }
+
if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
error = -EFAULT;
@@ -1379,10 +1385,11 @@ xfs_ioc_getbmap(
unsigned int cmd,
void __user *arg)
{
- struct getbmapx bmx;
+ struct getbmapx bmx = { 0 };
int error;
- if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+ /* struct getbmap is a strict subset of struct getbmapx. */
+ if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
return -EFAULT;
if (bmx.bmv_count < 2)
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 532ab79d38fe..572b64a135b3 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1355,12 +1355,7 @@ xfs_qm_quotacheck(
mp->m_qflags |= flags;
error_return:
- while (!list_empty(&buffer_list)) {
- struct xfs_buf *bp =
- list_first_entry(&buffer_list, struct xfs_buf, b_list);
- list_del_init(&bp->b_list);
- xfs_buf_relse(bp);
- }
+ xfs_buf_delwri_cancel(&buffer_list);
if (error) {
xfs_warn(mp,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3640c6e896af..4d334440bd94 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -764,5 +764,6 @@ xfs_qm_dqrele_all_inodes(
uint flags)
{
ASSERT(mp->m_quotainfo);
- xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+ xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+ XFS_AGITER_INEW_WAIT);
}
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 839b35ca21c6..9beaf192b4bb 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -180,7 +180,8 @@ xfs_xattr_put_listent(
arraytop = context->count + prefix_len + namelen + 1;
if (arraytop > context->firstu) {
context->count = -1; /* insufficient space */
- return 1;
+ context->seen_enough = 1;
+ return 0;
}
offset = (char *)context->alist + context->count;
strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
@@ -222,12 +223,15 @@ list_one_attr(const char *name, const size_t len, void *data,
}
ssize_t
-xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
+xfs_vn_listxattr(
+ struct dentry *dentry,
+ char *data,
+ size_t size)
{
struct xfs_attr_list_context context;
struct attrlist_cursor_kern cursor = { 0 };
- struct inode *inode = d_inode(dentry);
- int error;
+ struct inode *inode = d_inode(dentry);
+ int error;
/*
* First read the regular on-disk attributes.
@@ -245,7 +249,9 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
else
context.put_listent = xfs_xattr_put_listent_sizes;
- xfs_attr_list_int(&context);
+ error = xfs_attr_list_int(&context);
+ if (error)
+ return error;
if (context.count < 0)
return -ERANGE;