summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig1
-rw-r--r--fs/Kconfig.binfmt2
-rw-r--r--fs/afs/callback.c4
-rw-r--r--fs/afs/cmservice.c216
-rw-r--r--fs/afs/flock.c4
-rw-r--r--fs/afs/fsclient.c337
-rw-r--r--fs/afs/internal.h32
-rw-r--r--fs/afs/main.c1
-rw-r--r--fs/afs/rxrpc.c509
-rw-r--r--fs/afs/server.c11
-rw-r--r--fs/afs/vlclient.c16
-rw-r--r--fs/afs/vlocation.c4
-rw-r--r--fs/aio.c7
-rw-r--r--fs/autofs4/expire.c55
-rw-r--r--fs/binfmt_elf.c25
-rw-r--r--fs/block_dev.c5
-rw-r--r--fs/btrfs/backref.c1
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/delayed-ref.c7
-rw-r--r--fs/btrfs/disk-io.c56
-rw-r--r--fs/btrfs/disk-io.h2
-rw-r--r--fs/btrfs/extent-tree.c223
-rw-r--r--fs/btrfs/extent_io.h1
-rw-r--r--fs/btrfs/file.c28
-rw-r--r--fs/btrfs/inode-map.c3
-rw-r--r--fs/btrfs/inode.c37
-rw-r--r--fs/btrfs/ioctl.c14
-rw-r--r--fs/btrfs/qgroup.c62
-rw-r--r--fs/btrfs/qgroup.h36
-rw-r--r--fs/btrfs/relocation.c128
-rw-r--r--fs/btrfs/root-tree.c27
-rw-r--r--fs/btrfs/send.c8
-rw-r--r--fs/btrfs/super.c16
-rw-r--r--fs/btrfs/transaction.c7
-rw-r--r--fs/btrfs/tree-log.c22
-rw-r--r--fs/btrfs/tree-log.h5
-rw-r--r--fs/btrfs/volumes.c27
-rw-r--r--fs/ceph/dir.c2
-rw-r--r--fs/cifs/cifsfs.c29
-rw-r--r--fs/cifs/cifsproto.h2
-rw-r--r--fs/cifs/connect.c31
-rw-r--r--fs/configfs/file.c1
-rw-r--r--fs/crypto/policy.c41
-rw-r--r--fs/debugfs/file.c15
-rw-r--r--fs/debugfs/internal.h4
-rw-r--r--fs/devpts/inode.c74
-rw-r--r--fs/dlm/debug_fs.c62
-rw-r--r--fs/efivarfs/inode.c5
-rw-r--r--fs/efivarfs/super.c13
-rw-r--r--fs/ext2/ialloc.c5
-rw-r--r--fs/ext2/inode.c10
-rw-r--r--fs/ext4/inode.c2
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/super.c18
-rw-r--r--fs/ext4/xattr.c53
-rw-r--r--fs/ext4/xattr.h1
-rw-r--r--fs/f2fs/data.c2
-rw-r--r--fs/f2fs/f2fs.h12
-rw-r--r--fs/f2fs/file.c22
-rw-r--r--fs/f2fs/node.c47
-rw-r--r--fs/f2fs/super.c6
-rw-r--r--fs/fuse/Kconfig1
-rw-r--r--fs/fuse/Makefile2
-rw-r--r--fs/fuse/acl.c99
-rw-r--r--fs/fuse/dev.c1
-rw-r--r--fs/fuse/dir.c288
-rw-r--r--fs/fuse/file.c75
-rw-r--r--fs/fuse/fuse_i.h40
-rw-r--r--fs/fuse/inode.c28
-rw-r--r--fs/fuse/xattr.c211
-rw-r--r--fs/gfs2/aops.c19
-rw-r--r--fs/gfs2/bmap.c6
-rw-r--r--fs/gfs2/dir.c20
-rw-r--r--fs/gfs2/file.c6
-rw-r--r--fs/gfs2/glock.c10
-rw-r--r--fs/gfs2/inode.c4
-rw-r--r--fs/gfs2/inode.h2
-rw-r--r--fs/gfs2/main.c4
-rw-r--r--fs/gfs2/meta_io.c35
-rw-r--r--fs/gfs2/ops_fstype.c8
-rw-r--r--fs/gfs2/quota.c4
-rw-r--r--fs/gfs2/super.c2
-rw-r--r--fs/ioctl.c6
-rw-r--r--fs/jfs/jfs_txnmgr.c3
-rw-r--r--fs/jfs/resize.c10
-rw-r--r--fs/kernfs/file.c28
-rw-r--r--fs/locks.c89
-rw-r--r--fs/nfs/blocklayout/blocklayout.c2
-rw-r--r--fs/nfs/blocklayout/blocklayout.h3
-rw-r--r--fs/nfs/blocklayout/extent_tree.c10
-rw-r--r--fs/nfs/callback.c1
-rw-r--r--fs/nfs/callback_proc.c8
-rw-r--r--fs/nfs/client.c10
-rw-r--r--fs/nfs/file.c5
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c45
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.h2
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c23
-rw-r--r--fs/nfs/internal.h5
-rw-r--r--fs/nfs/nfs42proc.c34
-rw-r--r--fs/nfs/nfs4client.c5
-rw-r--r--fs/nfs/nfs4proc.c110
-rw-r--r--fs/nfs/nfs4session.c53
-rw-r--r--fs/nfs/nfs4session.h7
-rw-r--r--fs/nfs/pnfs.c44
-rw-r--r--fs/nfs/super.c19
-rw-r--r--fs/notify/fanotify/fanotify.c13
-rw-r--r--fs/notify/fanotify/fanotify_user.c36
-rw-r--r--fs/notify/group.c19
-rw-r--r--fs/notify/notification.c23
-rw-r--r--fs/ocfs2/alloc.c56
-rw-r--r--fs/ocfs2/aops.c10
-rw-r--r--fs/ocfs2/cluster/tcp_internal.h5
-rw-r--r--fs/ocfs2/dlm/dlmconvert.c12
-rw-r--r--fs/ocfs2/file.c34
-rw-r--r--fs/ocfs2/suballoc.c14
-rw-r--r--fs/overlayfs/copy_up.c24
-rw-r--r--fs/overlayfs/dir.c68
-rw-r--r--fs/overlayfs/inode.c108
-rw-r--r--fs/overlayfs/overlayfs.h17
-rw-r--r--fs/overlayfs/readdir.c63
-rw-r--r--fs/overlayfs/super.c93
-rw-r--r--fs/proc/base.c9
-rw-r--r--fs/proc/generic.c2
-rw-r--r--fs/proc/kcore.c31
-rw-r--r--fs/proc/proc_net.c13
-rw-r--r--fs/proc/proc_sysctl.c5
-rw-r--r--fs/proc/task_mmu.c2
-rw-r--r--fs/quota/quota.c18
-rw-r--r--fs/ramfs/file-mmu.c9
-rw-r--r--fs/reiserfs/super.c12
-rw-r--r--fs/seq_file.c4
-rw-r--r--fs/sysfs/file.c8
-rw-r--r--fs/sysfs/group.c4
-rw-r--r--fs/ubifs/tnc_commit.c2
-rw-r--r--fs/ubifs/xattr.c5
-rw-r--r--fs/udf/file.c18
136 files changed, 2780 insertions, 1748 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 2bc7ad775842..3ef62bad8f2b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -79,6 +79,7 @@ config EXPORTFS_BLOCK_OPS
config FILE_LOCKING
bool "Enable POSIX file locking API" if EXPERT
default y
+ select PERCPU_RWSEM
help
This option enables standard file locking support, required
for filesystems like NFS and for the flock() system
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index c7efddf6e038..4c09d93d9569 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -89,7 +89,7 @@ config BINFMT_SCRIPT
config BINFMT_FLAT
bool "Kernel support for flat binaries"
- depends on !MMU || M68K
+ depends on !MMU || ARM || M68K
depends on !FRV || BROKEN
help
Support uClinux FLAT format binaries.
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 7ef637d7f3a5..1e9d2f84e5b5 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -461,8 +461,8 @@ static void afs_callback_updater(struct work_struct *work)
*/
int __init afs_callback_update_init(void)
{
- afs_callback_update_worker =
- create_singlethread_workqueue("kafs_callbackd");
+ afs_callback_update_worker = alloc_ordered_workqueue("kafs_callbackd",
+ WQ_MEM_RECLAIM);
return afs_callback_update_worker ? 0 : -ENOMEM;
}
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 4b0eff6da674..2037e7a77a37 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -17,19 +17,12 @@
#include "internal.h"
#include "afs_cm.h"
-#if 0
-struct workqueue_struct *afs_cm_workqueue;
-#endif /* 0 */
-
-static int afs_deliver_cb_init_call_back_state(struct afs_call *,
- struct sk_buff *, bool);
-static int afs_deliver_cb_init_call_back_state3(struct afs_call *,
- struct sk_buff *, bool);
-static int afs_deliver_cb_probe(struct afs_call *, struct sk_buff *, bool);
-static int afs_deliver_cb_callback(struct afs_call *, struct sk_buff *, bool);
-static int afs_deliver_cb_probe_uuid(struct afs_call *, struct sk_buff *, bool);
-static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *,
- struct sk_buff *, bool);
+static int afs_deliver_cb_init_call_back_state(struct afs_call *);
+static int afs_deliver_cb_init_call_back_state3(struct afs_call *);
+static int afs_deliver_cb_probe(struct afs_call *);
+static int afs_deliver_cb_callback(struct afs_call *);
+static int afs_deliver_cb_probe_uuid(struct afs_call *);
+static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *);
static void afs_cm_destructor(struct afs_call *);
/*
@@ -134,7 +127,7 @@ static void afs_cm_destructor(struct afs_call *call)
* received. The step number here must match the final number in
* afs_deliver_cb_callback().
*/
- if (call->unmarshall == 6) {
+ if (call->unmarshall == 5) {
ASSERT(call->server && call->count && call->request);
afs_break_callbacks(call->server, call->count, call->request);
}
@@ -168,32 +161,29 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
/*
* deliver request data to a CB.CallBack call
*/
-static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
- bool last)
+static int afs_deliver_cb_callback(struct afs_call *call)
{
+ struct sockaddr_rxrpc srx;
struct afs_callback *cb;
struct afs_server *server;
- struct in_addr addr;
__be32 *bp;
u32 tmp;
int ret, loop;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+ _enter("{%u}", call->unmarshall);
switch (call->unmarshall) {
case 0:
+ rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx);
call->offset = 0;
call->unmarshall++;
/* extract the FID array and its count in two steps */
case 1:
_debug("extract FID count");
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("FID count: %u", call->count);
@@ -208,13 +198,10 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
case 2:
_debug("extract FID array");
- ret = afs_extract_data(call, skb, last, call->buffer,
- call->count * 3 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ call->count * 3 * 4, true);
+ if (ret < 0)
+ return ret;
_debug("unmarshall FID array");
call->request = kcalloc(call->count,
@@ -238,12 +225,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
/* extract the callback array and its count in two steps */
case 3:
_debug("extract CB count");
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
tmp = ntohl(call->tmp);
_debug("CB count: %u", tmp);
@@ -251,18 +235,13 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
return -EBADMSG;
call->offset = 0;
call->unmarshall++;
- if (tmp == 0)
- goto empty_cb_array;
case 4:
_debug("extract CB array");
- ret = afs_extract_data(call, skb, last, call->request,
- call->count * 3 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ call->count * 3 * 4, false);
+ if (ret < 0)
+ return ret;
_debug("unmarshall CB array");
cb = call->request;
@@ -273,15 +252,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
cb->type = ntohl(*bp++);
}
- empty_cb_array:
call->offset = 0;
call->unmarshall++;
- case 5:
- _debug("trailer");
- if (skb->len != 0)
- return -EBADMSG;
-
/* Record that the message was unmarshalled successfully so
* that the call destructor can know do the callback breaking
* work, even if the final ACK isn't received.
@@ -290,19 +263,15 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
* updated also.
*/
call->unmarshall++;
- case 6:
+ case 5:
break;
}
- if (!last)
- return 0;
-
call->state = AFS_CALL_REPLYING;
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- memcpy(&addr, &ip_hdr(skb)->saddr, 4);
- server = afs_find_server(&addr);
+ server = afs_find_server(&srx);
if (!server)
return -ENOTCONN;
call->server = server;
@@ -329,27 +298,26 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
/*
* deliver request data to a CB.InitCallBackState call
*/
-static int afs_deliver_cb_init_call_back_state(struct afs_call *call,
- struct sk_buff *skb,
- bool last)
+static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
{
+ struct sockaddr_rxrpc srx;
struct afs_server *server;
- struct in_addr addr;
+ int ret;
- _enter(",{%u},%d", skb->len, last);
+ _enter("");
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx);
+
+ ret = afs_extract_data(call, NULL, 0, false);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- memcpy(&addr, &ip_hdr(skb)->saddr, 4);
- server = afs_find_server(&addr);
+ server = afs_find_server(&srx);
if (!server)
return -ENOTCONN;
call->server = server;
@@ -362,25 +330,68 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call,
/*
* deliver request data to a CB.InitCallBackState3 call
*/
-static int afs_deliver_cb_init_call_back_state3(struct afs_call *call,
- struct sk_buff *skb,
- bool last)
+static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
{
+ struct sockaddr_rxrpc srx;
struct afs_server *server;
- struct in_addr addr;
+ struct afs_uuid *r;
+ unsigned loop;
+ __be32 *b;
+ int ret;
- _enter(",{%u},%d", skb->len, last);
+ _enter("");
+
+ rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx);
+
+ _enter("{%u}", call->unmarshall);
- if (!last)
- return 0;
+ switch (call->unmarshall) {
+ case 0:
+ call->offset = 0;
+ call->buffer = kmalloc(11 * sizeof(__be32), GFP_KERNEL);
+ if (!call->buffer)
+ return -ENOMEM;
+ call->unmarshall++;
+
+ case 1:
+ _debug("extract UUID");
+ ret = afs_extract_data(call, call->buffer,
+ 11 * sizeof(__be32), false);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ _debug("unmarshall UUID");
+ call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL);
+ if (!call->request)
+ return -ENOMEM;
+
+ b = call->buffer;
+ r = call->request;
+ r->time_low = ntohl(b[0]);
+ r->time_mid = ntohl(b[1]);
+ r->time_hi_and_version = ntohl(b[2]);
+ r->clock_seq_hi_and_reserved = ntohl(b[3]);
+ r->clock_seq_low = ntohl(b[4]);
+
+ for (loop = 0; loop < 6; loop++)
+ r->node[loop] = ntohl(b[loop + 5]);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ case 2:
+ break;
+ }
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
/* we'll need the file server record as that tells us which set of
* vnodes to operate upon */
- memcpy(&addr, &ip_hdr(skb)->saddr, 4);
- server = afs_find_server(&addr);
+ server = afs_find_server(&srx);
if (!server)
return -ENOTCONN;
call->server = server;
@@ -405,15 +416,15 @@ static void SRXAFSCB_Probe(struct work_struct *work)
/*
* deliver request data to a CB.Probe call
*/
-static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb,
- bool last)
+static int afs_deliver_cb_probe(struct afs_call *call)
{
- _enter(",{%u},%d", skb->len, last);
+ int ret;
+
+ _enter("");
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_extract_data(call, NULL, 0, false);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
@@ -437,7 +448,6 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
_enter("");
-
if (memcmp(r, &afs_uuid, sizeof(afs_uuid)) == 0)
reply.match = htonl(0);
else
@@ -450,20 +460,14 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
/*
* deliver request data to a CB.ProbeUuid call
*/
-static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
- bool last)
+static int afs_deliver_cb_probe_uuid(struct afs_call *call)
{
struct afs_uuid *r;
unsigned loop;
__be32 *b;
int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
switch (call->unmarshall) {
case 0:
@@ -475,8 +479,8 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
case 1:
_debug("extract UUID");
- ret = afs_extract_data(call, skb, last, call->buffer,
- 11 * sizeof(__be32));
+ ret = afs_extract_data(call, call->buffer,
+ 11 * sizeof(__be32), false);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
@@ -503,15 +507,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
call->unmarshall++;
case 2:
- _debug("trailer");
- if (skb->len != 0)
- return -EBADMSG;
break;
}
- if (!last)
- return 0;
-
call->state = AFS_CALL_REPLYING;
INIT_WORK(&call->work, SRXAFSCB_ProbeUuid);
@@ -585,15 +583,15 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
/*
* deliver request data to a CB.TellMeAboutYourself call
*/
-static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call)
{
- _enter(",{%u},%d", skb->len, last);
+ int ret;
+
+ _enter("");
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_extract_data(call, NULL, 0, false);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index d91a9c9cfbd0..3191dff2c156 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -36,8 +36,8 @@ static int afs_init_lock_manager(void)
if (!afs_lock_manager) {
mutex_lock(&afs_lock_manager_mutex);
if (!afs_lock_manager) {
- afs_lock_manager =
- create_singlethread_workqueue("kafs_lockd");
+ afs_lock_manager = alloc_workqueue("kafs_lockd",
+ WQ_MEM_RECLAIM, 0);
if (!afs_lock_manager)
ret = -ENOMEM;
}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index c2e930ec2888..96f4d764d1a6 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -235,20 +235,17 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp,
/*
* deliver reply data to an FS.FetchStatus
*/
-static int afs_deliver_fs_fetch_status(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_fetch_status(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter(",,%u", last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("");
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -309,8 +306,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
/*
* deliver reply data to an FS.FetchData
*/
-static int afs_deliver_fs_fetch_data(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_fetch_data(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
@@ -318,7 +314,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
void *buffer;
int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+ _enter("{%u}", call->unmarshall);
switch (call->unmarshall) {
case 0:
@@ -334,12 +330,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
* client) */
case 1:
_debug("extract data length (MSW)");
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("DATA length MSW: %u", call->count);
@@ -352,12 +345,9 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
/* extract the returned data length */
case 2:
_debug("extract data length");
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("DATA length: %u", call->count);
@@ -371,15 +361,12 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
_debug("extract data");
if (call->count > 0) {
page = call->reply3;
- buffer = kmap_atomic(page);
- ret = afs_extract_data(call, skb, last, buffer,
- call->count);
- kunmap_atomic(buffer);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ buffer = kmap(page);
+ ret = afs_extract_data(call, buffer,
+ call->count, true);
+ kunmap(buffer);
+ if (ret < 0)
+ return ret;
}
call->offset = 0;
@@ -387,13 +374,10 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
/* extract the metadata */
case 4:
- ret = afs_extract_data(call, skb, last, call->buffer,
- (21 + 3 + 6) * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ (21 + 3 + 6) * 4, false);
+ if (ret < 0)
+ return ret;
bp = call->buffer;
xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
@@ -405,21 +389,15 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call,
call->unmarshall++;
case 5:
- _debug("trailer");
- if (skb->len != 0)
- return -EBADMSG;
break;
}
- if (!last)
- return 0;
-
if (call->count < PAGE_SIZE) {
_debug("clear");
page = call->reply3;
- buffer = kmap_atomic(page);
+ buffer = kmap(page);
memset(buffer + call->count, 0, PAGE_SIZE - call->count);
- kunmap_atomic(buffer);
+ kunmap(buffer);
}
_leave(" = 0 [done]");
@@ -532,14 +510,12 @@ int afs_fs_fetch_data(struct afs_server *server,
/*
* deliver reply data to an FS.GiveUpCallBacks
*/
-static int afs_deliver_fs_give_up_callbacks(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_give_up_callbacks(struct afs_call *call)
{
- _enter(",{%u},%d", skb->len, last);
+ _enter("");
- if (skb->len > 0)
- return -EBADMSG; /* shouldn't be any reply data */
- return 0;
+ /* shouldn't be any reply data */
+ return afs_extract_data(call, NULL, 0, false);
}
/*
@@ -617,20 +593,17 @@ int afs_fs_give_up_callbacks(struct afs_server *server,
/*
* deliver reply data to an FS.CreateFile or an FS.MakeDir
*/
-static int afs_deliver_fs_create_vnode(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_create_vnode(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -716,20 +689,17 @@ int afs_fs_create(struct afs_server *server,
/*
* deliver reply data to an FS.RemoveFile or FS.RemoveDir
*/
-static int afs_deliver_fs_remove(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_remove(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -799,20 +769,17 @@ int afs_fs_remove(struct afs_server *server,
/*
* deliver reply data to an FS.Link
*/
-static int afs_deliver_fs_link(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_link(struct afs_call *call)
{
struct afs_vnode *dvnode = call->reply, *vnode = call->reply2;
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -887,20 +854,17 @@ int afs_fs_link(struct afs_server *server,
/*
* deliver reply data to an FS.Symlink
*/
-static int afs_deliver_fs_symlink(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_symlink(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -994,20 +958,17 @@ int afs_fs_symlink(struct afs_server *server,
/*
* deliver reply data to an FS.Rename
*/
-static int afs_deliver_fs_rename(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_rename(struct afs_call *call)
{
struct afs_vnode *orig_dvnode = call->reply, *new_dvnode = call->reply2;
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+ _enter("{%u}", call->unmarshall);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -1100,25 +1061,17 @@ int afs_fs_rename(struct afs_server *server,
/*
* deliver reply data to an FS.StoreData
*/
-static int afs_deliver_fs_store_data(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_store_data(struct afs_call *call)
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter(",,%u", last);
-
- afs_transfer_reply(call, skb);
- if (!last) {
- _leave(" = 0 [more]");
- return 0;
- }
+ _enter("");
- if (call->reply_size != call->reply_max) {
- _leave(" = -EBADMSG [%u != %u]",
- call->reply_size, call->reply_max);
- return -EBADMSG;
- }
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
@@ -1286,26 +1239,18 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
/*
* deliver reply data to an FS.StoreStatus
*/
-static int afs_deliver_fs_store_status(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_store_status(struct afs_call *call)
{
afs_dataversion_t *store_version;
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
- _enter(",,%u", last);
-
- afs_transfer_reply(call, skb);
- if (!last) {
- _leave(" = 0 [more]");
- return 0;
- }
+ _enter("");
- if (call->reply_size != call->reply_max) {
- _leave(" = -EBADMSG [%u != %u]",
- call->reply_size, call->reply_max);
- return -EBADMSG;
- }
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
store_version = NULL;
@@ -1485,14 +1430,13 @@ int afs_fs_setattr(struct afs_server *server, struct key *key,
/*
* deliver reply data to an FS.GetVolumeStatus
*/
-static int afs_deliver_fs_get_volume_status(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_get_volume_status(struct afs_call *call)
{
const __be32 *bp;
char *p;
int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+ _enter("{%u}", call->unmarshall);
switch (call->unmarshall) {
case 0:
@@ -1502,13 +1446,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
/* extract the returned status record */
case 1:
_debug("extract status");
- ret = afs_extract_data(call, skb, last, call->buffer,
- 12 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ 12 * 4, true);
+ if (ret < 0)
+ return ret;
bp = call->buffer;
xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2);
@@ -1517,12 +1458,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
/* extract the volume name length */
case 2:
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("volname length: %u", call->count);
@@ -1535,13 +1473,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
case 3:
_debug("extract volname");
if (call->count > 0) {
- ret = afs_extract_data(call, skb, last, call->reply3,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->reply3,
+ call->count, true);
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
@@ -1559,13 +1494,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
call->count = 4 - (call->count & 3);
case 4:
- ret = afs_extract_data(call, skb, last, call->buffer,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ call->count, true);
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
@@ -1573,12 +1505,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
/* extract the offline message length */
case 5:
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("offline msg length: %u", call->count);
@@ -1591,13 +1520,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
case 6:
_debug("extract offline");
if (call->count > 0) {
- ret = afs_extract_data(call, skb, last, call->reply3,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->reply3,
+ call->count, true);
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
@@ -1615,13 +1541,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
call->count = 4 - (call->count & 3);
case 7:
- ret = afs_extract_data(call, skb, last, call->buffer,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ call->count, true);
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
@@ -1629,12 +1552,9 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
/* extract the message of the day length */
case 8:
- ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, &call->tmp, 4, true);
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("motd length: %u", call->count);
@@ -1647,13 +1567,10 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
case 9:
_debug("extract motd");
if (call->count > 0) {
- ret = afs_extract_data(call, skb, last, call->reply3,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->reply3,
+ call->count, true);
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
@@ -1664,35 +1581,20 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call,
call->unmarshall++;
/* extract the message of the day padding */
- if ((call->count & 3) == 0) {
- call->unmarshall++;
- goto no_motd_padding;
- }
- call->count = 4 - (call->count & 3);
+ call->count = (4 - (call->count & 3)) & 3;
case 10:
- ret = afs_extract_data(call, skb, last, call->buffer,
- call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ ret = afs_extract_data(call, call->buffer,
+ call->count, false);
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
- no_motd_padding:
-
case 11:
- _debug("trailer %d", skb->len);
- if (skb->len != 0)
- return -EBADMSG;
break;
}
- if (!last)
- return 0;
-
_leave(" = 0 [done]");
return 0;
}
@@ -1760,19 +1662,16 @@ int afs_fs_get_volume_status(struct afs_server *server,
/*
* deliver reply data to an FS.SetLock, FS.ExtendLock or FS.ReleaseLock
*/
-static int afs_deliver_fs_xxxx_lock(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_fs_xxxx_lock(struct afs_call *call)
{
const __be32 *bp;
+ int ret;
- _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("{%u}", call->unmarshall);
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 71d5982312f3..5497c8496055 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -13,13 +13,13 @@
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
-#include <linux/skbuff.h>
#include <linux/rxrpc.h>
#include <linux/key.h>
#include <linux/workqueue.h>
#include <linux/sched.h>
#include <linux/fscache.h>
#include <linux/backing-dev.h>
+#include <net/af_rxrpc.h>
#include "afs.h"
#include "afs_vl.h"
@@ -56,7 +56,7 @@ struct afs_mount_params {
*/
struct afs_wait_mode {
/* RxRPC received message notification */
- void (*rx_wakeup)(struct afs_call *call);
+ rxrpc_notify_rx_t notify_rx;
/* synchronous call waiter and call dispatched notification */
int (*wait)(struct afs_call *call);
@@ -75,10 +75,8 @@ struct afs_call {
const struct afs_call_type *type; /* type of call */
const struct afs_wait_mode *wait_mode; /* completion wait mode */
wait_queue_head_t waitq; /* processes awaiting completion */
- void (*async_workfn)(struct afs_call *call); /* asynchronous work function */
struct work_struct async_work; /* asynchronous work processor */
struct work_struct work; /* actual work processor */
- struct sk_buff_head rx_queue; /* received packets */
struct rxrpc_call *rxcall; /* RxRPC call handle */
struct key *key; /* security for this call */
struct afs_server *server; /* server affected by incoming CM call */
@@ -92,6 +90,7 @@ struct afs_call {
void *reply4; /* reply buffer (fourth part) */
pgoff_t first; /* first page in mapping to deal with */
pgoff_t last; /* last page in mapping to deal with */
+ size_t offset; /* offset into received data store */
enum { /* call state */
AFS_CALL_REQUESTING, /* request is being sent for outgoing call */
AFS_CALL_AWAIT_REPLY, /* awaiting reply to outgoing call */
@@ -99,21 +98,18 @@ struct afs_call {
AFS_CALL_AWAIT_REQUEST, /* awaiting request data on incoming call */
AFS_CALL_REPLYING, /* replying to incoming call */
AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */
- AFS_CALL_COMPLETE, /* successfully completed */
- AFS_CALL_BUSY, /* server was busy */
- AFS_CALL_ABORTED, /* call was aborted */
- AFS_CALL_ERROR, /* call failed due to error */
+ AFS_CALL_COMPLETE, /* Completed or failed */
} state;
int error; /* error code */
+ u32 abort_code; /* Remote abort ID or 0 */
unsigned request_size; /* size of request data */
unsigned reply_max; /* maximum size of reply */
- unsigned reply_size; /* current size of reply */
unsigned first_offset; /* offset into mapping[first] */
unsigned last_to; /* amount of mapping[last] */
- unsigned offset; /* offset into received data store */
unsigned char unmarshall; /* unmarshalling phase */
bool incoming; /* T if incoming call */
bool send_pages; /* T if data from mapping should be sent */
+ bool need_attention; /* T if RxRPC poked us */
u16 service_id; /* RxRPC service ID to call */
__be16 port; /* target UDP port */
__be32 operation_ID; /* operation ID for an incoming call */
@@ -128,8 +124,7 @@ struct afs_call_type {
/* deliver request or reply data to an call
* - returning an error will cause the call to be aborted
*/
- int (*deliver)(struct afs_call *call, struct sk_buff *skb,
- bool last);
+ int (*deliver)(struct afs_call *call);
/* map an abort code to an error number */
int (*abort_to_error)(u32 abort_code);
@@ -607,6 +602,8 @@ extern void afs_proc_cell_remove(struct afs_cell *);
/*
* rxrpc.c
*/
+extern struct socket *afs_socket;
+
extern int afs_open_socket(void);
extern void afs_close_socket(void);
extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t,
@@ -614,11 +611,14 @@ extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t,
extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *,
size_t, size_t);
extern void afs_flat_call_destructor(struct afs_call *);
-extern void afs_transfer_reply(struct afs_call *, struct sk_buff *);
extern void afs_send_empty_reply(struct afs_call *);
extern void afs_send_simple_reply(struct afs_call *, const void *, size_t);
-extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *,
- size_t);
+extern int afs_extract_data(struct afs_call *, void *, size_t, bool);
+
+static inline int afs_transfer_reply(struct afs_call *call)
+{
+ return afs_extract_data(call, call->buffer, call->reply_max, false);
+}
/*
* security.c
@@ -642,7 +642,7 @@ do { \
extern struct afs_server *afs_lookup_server(struct afs_cell *,
const struct in_addr *);
-extern struct afs_server *afs_find_server(const struct in_addr *);
+extern struct afs_server *afs_find_server(const struct sockaddr_rxrpc *);
extern void afs_put_server(struct afs_server *);
extern void __exit afs_purge_servers(void);
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 35de0c04729f..0b187ef3b5b7 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -14,6 +14,7 @@
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/sched.h>
+#include <linux/random.h>
#include "internal.h"
MODULE_DESCRIPTION("AFS Client File System");
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 4832de84d52c..59bdaa7527b6 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -16,34 +16,36 @@
#include "internal.h"
#include "afs_cm.h"
-static struct socket *afs_socket; /* my RxRPC socket */
+struct socket *afs_socket; /* my RxRPC socket */
static struct workqueue_struct *afs_async_calls;
+static struct afs_call *afs_spare_incoming_call;
static atomic_t afs_outstanding_calls;
-static atomic_t afs_outstanding_skbs;
-static void afs_wake_up_call_waiter(struct afs_call *);
+static void afs_free_call(struct afs_call *);
+static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
static int afs_wait_for_call_to_complete(struct afs_call *);
-static void afs_wake_up_async_call(struct afs_call *);
+static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
static int afs_dont_wait_for_call_to_complete(struct afs_call *);
-static void afs_process_async_call(struct afs_call *);
-static void afs_rx_interceptor(struct sock *, unsigned long, struct sk_buff *);
-static int afs_deliver_cm_op_id(struct afs_call *, struct sk_buff *, bool);
+static void afs_process_async_call(struct work_struct *);
+static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long);
+static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long);
+static int afs_deliver_cm_op_id(struct afs_call *);
/* synchronous call management */
const struct afs_wait_mode afs_sync_call = {
- .rx_wakeup = afs_wake_up_call_waiter,
+ .notify_rx = afs_wake_up_call_waiter,
.wait = afs_wait_for_call_to_complete,
};
/* asynchronous call management */
const struct afs_wait_mode afs_async_call = {
- .rx_wakeup = afs_wake_up_async_call,
+ .notify_rx = afs_wake_up_async_call,
.wait = afs_dont_wait_for_call_to_complete,
};
/* asynchronous incoming call management */
static const struct afs_wait_mode afs_async_incoming_call = {
- .rx_wakeup = afs_wake_up_async_call,
+ .notify_rx = afs_wake_up_async_call,
};
/* asynchronous incoming call initial processing */
@@ -53,17 +55,9 @@ static const struct afs_call_type afs_RXCMxxxx = {
.abort_to_error = afs_abort_to_error,
};
-static void afs_collect_incoming_call(struct work_struct *);
+static void afs_charge_preallocation(struct work_struct *);
-static struct sk_buff_head afs_incoming_calls;
-static DECLARE_WORK(afs_collect_incoming_call_work, afs_collect_incoming_call);
-
-static void afs_async_workfn(struct work_struct *work)
-{
- struct afs_call *call = container_of(work, struct afs_call, async_work);
-
- call->async_workfn(call);
-}
+static DECLARE_WORK(afs_charge_preallocation_work, afs_charge_preallocation);
static int afs_wait_atomic_t(atomic_t *p)
{
@@ -83,10 +77,8 @@ int afs_open_socket(void)
_enter("");
- skb_queue_head_init(&afs_incoming_calls);
-
ret = -ENOMEM;
- afs_async_calls = create_singlethread_workqueue("kafsd");
+ afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0);
if (!afs_async_calls)
goto error_0;
@@ -110,13 +102,15 @@ int afs_open_socket(void)
if (ret < 0)
goto error_2;
+ rxrpc_kernel_new_call_notification(socket, afs_rx_new_call,
+ afs_rx_discard_new_call);
+
ret = kernel_listen(socket, INT_MAX);
if (ret < 0)
goto error_2;
- rxrpc_kernel_intercept_rx_messages(socket, afs_rx_interceptor);
-
afs_socket = socket;
+ afs_charge_preallocation(NULL);
_leave(" = 0");
return 0;
@@ -136,55 +130,28 @@ void afs_close_socket(void)
{
_enter("");
+ if (afs_spare_incoming_call) {
+ atomic_inc(&afs_outstanding_calls);
+ afs_free_call(afs_spare_incoming_call);
+ afs_spare_incoming_call = NULL;
+ }
+
+ _debug("outstanding %u", atomic_read(&afs_outstanding_calls));
wait_on_atomic_t(&afs_outstanding_calls, afs_wait_atomic_t,
TASK_UNINTERRUPTIBLE);
_debug("no outstanding calls");
+ flush_workqueue(afs_async_calls);
+ kernel_sock_shutdown(afs_socket, SHUT_RDWR);
+ flush_workqueue(afs_async_calls);
sock_release(afs_socket);
_debug("dework");
destroy_workqueue(afs_async_calls);
-
- ASSERTCMP(atomic_read(&afs_outstanding_skbs), ==, 0);
_leave("");
}
/*
- * note that the data in a socket buffer is now delivered and that the buffer
- * should be freed
- */
-static void afs_data_delivered(struct sk_buff *skb)
-{
- if (!skb) {
- _debug("DLVR NULL [%d]", atomic_read(&afs_outstanding_skbs));
- dump_stack();
- } else {
- _debug("DLVR %p{%u} [%d]",
- skb, skb->mark, atomic_read(&afs_outstanding_skbs));
- if (atomic_dec_return(&afs_outstanding_skbs) == -1)
- BUG();
- rxrpc_kernel_data_delivered(skb);
- }
-}
-
-/*
- * free a socket buffer
- */
-static void afs_free_skb(struct sk_buff *skb)
-{
- if (!skb) {
- _debug("FREE NULL [%d]", atomic_read(&afs_outstanding_skbs));
- dump_stack();
- } else {
- _debug("FREE %p{%u} [%d]",
- skb, skb->mark, atomic_read(&afs_outstanding_skbs));
- if (atomic_dec_return(&afs_outstanding_skbs) == -1)
- BUG();
- rxrpc_kernel_free_skb(skb);
- }
-}
-
-/*
* free a call
*/
static void afs_free_call(struct afs_call *call)
@@ -194,7 +161,6 @@ static void afs_free_call(struct afs_call *call)
ASSERTCMP(call->rxcall, ==, NULL);
ASSERT(!work_pending(&call->async_work));
- ASSERT(skb_queue_empty(&call->rx_queue));
ASSERT(call->type->name != NULL);
kfree(call->request);
@@ -210,7 +176,7 @@ static void afs_free_call(struct afs_call *call)
static void afs_end_call_nofree(struct afs_call *call)
{
if (call->rxcall) {
- rxrpc_kernel_end_call(call->rxcall);
+ rxrpc_kernel_end_call(afs_socket, call->rxcall);
call->rxcall = NULL;
}
if (call->type->destructor)
@@ -230,7 +196,7 @@ static void afs_end_call(struct afs_call *call)
* allocate a call with flat request and reply buffers
*/
struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
- size_t request_size, size_t reply_size)
+ size_t request_size, size_t reply_max)
{
struct afs_call *call;
@@ -244,7 +210,7 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
call->type = type;
call->request_size = request_size;
- call->reply_max = reply_size;
+ call->reply_max = reply_max;
if (request_size) {
call->request = kmalloc(request_size, GFP_NOFS);
@@ -252,14 +218,13 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
goto nomem_free;
}
- if (reply_size) {
- call->buffer = kmalloc(reply_size, GFP_NOFS);
+ if (reply_max) {
+ call->buffer = kmalloc(reply_max, GFP_NOFS);
if (!call->buffer)
goto nomem_free;
}
init_waitqueue_head(&call->waitq);
- skb_queue_head_init(&call->rx_queue);
return call;
nomem_free:
@@ -328,8 +293,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
* returns from sending the request */
if (first + loop >= last)
call->state = AFS_CALL_AWAIT_REPLY;
- ret = rxrpc_kernel_send_data(call->rxcall, msg,
- to - offset);
+ ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
+ msg, to - offset);
kunmap(pages[loop]);
if (ret < 0)
break;
@@ -357,7 +322,6 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
struct msghdr msg;
struct kvec iov[1];
int ret;
- struct sk_buff *skb;
_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
@@ -369,8 +333,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
atomic_read(&afs_outstanding_calls));
call->wait_mode = wait_mode;
- call->async_workfn = afs_process_async_call;
- INIT_WORK(&call->async_work, afs_async_workfn);
+ INIT_WORK(&call->async_work, afs_process_async_call);
memset(&srx, 0, sizeof(srx));
srx.srx_family = AF_RXRPC;
@@ -383,7 +346,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
/* create a call */
rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key,
- (unsigned long) call, gfp);
+ (unsigned long) call, gfp,
+ wait_mode->notify_rx);
call->key = NULL;
if (IS_ERR(rxcall)) {
ret = PTR_ERR(rxcall);
@@ -409,7 +373,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
* request */
if (!call->send_pages)
call->state = AFS_CALL_AWAIT_REPLY;
- ret = rxrpc_kernel_send_data(rxcall, &msg, call->request_size);
+ ret = rxrpc_kernel_send_data(afs_socket, rxcall,
+ &msg, call->request_size);
if (ret < 0)
goto error_do_abort;
@@ -424,9 +389,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
return wait_mode->wait(call);
error_do_abort:
- rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT);
- while ((skb = skb_dequeue(&call->rx_queue)))
- afs_free_skb(skb);
+ rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD");
error_kill_call:
afs_end_call(call);
_leave(" = %d", ret);
@@ -434,135 +397,77 @@ error_kill_call:
}
/*
- * Handles intercepted messages that were arriving in the socket's Rx queue.
- *
- * Called from the AF_RXRPC call processor in waitqueue process context. For
- * each call, it is guaranteed this will be called in order of packet to be
- * delivered.
- */
-static void afs_rx_interceptor(struct sock *sk, unsigned long user_call_ID,
- struct sk_buff *skb)
-{
- struct afs_call *call = (struct afs_call *) user_call_ID;
-
- _enter("%p,,%u", call, skb->mark);
-
- _debug("ICPT %p{%u} [%d]",
- skb, skb->mark, atomic_read(&afs_outstanding_skbs));
-
- ASSERTCMP(sk, ==, afs_socket->sk);
- atomic_inc(&afs_outstanding_skbs);
-
- if (!call) {
- /* its an incoming call for our callback service */
- skb_queue_tail(&afs_incoming_calls, skb);
- queue_work(afs_wq, &afs_collect_incoming_call_work);
- } else {
- /* route the messages directly to the appropriate call */
- skb_queue_tail(&call->rx_queue, skb);
- call->wait_mode->rx_wakeup(call);
- }
-
- _leave("");
-}
-
-/*
* deliver messages to a call
*/
static void afs_deliver_to_call(struct afs_call *call)
{
- struct sk_buff *skb;
- bool last;
u32 abort_code;
int ret;
- _enter("");
-
- while ((call->state == AFS_CALL_AWAIT_REPLY ||
- call->state == AFS_CALL_AWAIT_OP_ID ||
- call->state == AFS_CALL_AWAIT_REQUEST ||
- call->state == AFS_CALL_AWAIT_ACK) &&
- (skb = skb_dequeue(&call->rx_queue))) {
- switch (skb->mark) {
- case RXRPC_SKB_MARK_DATA:
- _debug("Rcv DATA");
- last = rxrpc_kernel_is_data_last(skb);
- ret = call->type->deliver(call, skb, last);
- switch (ret) {
- case 0:
- if (last &&
- call->state == AFS_CALL_AWAIT_REPLY)
- call->state = AFS_CALL_COMPLETE;
- break;
- case -ENOTCONN:
- abort_code = RX_CALL_DEAD;
- goto do_abort;
- case -ENOTSUPP:
- abort_code = RX_INVALID_OPERATION;
- goto do_abort;
- default:
- abort_code = RXGEN_CC_UNMARSHAL;
- if (call->state != AFS_CALL_AWAIT_REPLY)
- abort_code = RXGEN_SS_UNMARSHAL;
- do_abort:
- rxrpc_kernel_abort_call(call->rxcall,
- abort_code);
- call->error = ret;
- call->state = AFS_CALL_ERROR;
- break;
+ _enter("%s", call->type->name);
+
+ while (call->state == AFS_CALL_AWAIT_REPLY ||
+ call->state == AFS_CALL_AWAIT_OP_ID ||
+ call->state == AFS_CALL_AWAIT_REQUEST ||
+ call->state == AFS_CALL_AWAIT_ACK
+ ) {
+ if (call->state == AFS_CALL_AWAIT_ACK) {
+ size_t offset = 0;
+ ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
+ NULL, 0, &offset, false,
+ &call->abort_code);
+ if (ret == -EINPROGRESS || ret == -EAGAIN)
+ return;
+ if (ret == 1) {
+ call->state = AFS_CALL_COMPLETE;
+ goto done;
}
- afs_data_delivered(skb);
- skb = NULL;
- continue;
- case RXRPC_SKB_MARK_FINAL_ACK:
- _debug("Rcv ACK");
- call->state = AFS_CALL_COMPLETE;
- break;
- case RXRPC_SKB_MARK_BUSY:
- _debug("Rcv BUSY");
- call->error = -EBUSY;
- call->state = AFS_CALL_BUSY;
- break;
- case RXRPC_SKB_MARK_REMOTE_ABORT:
- abort_code = rxrpc_kernel_get_abort_code(skb);
- call->error = call->type->abort_to_error(abort_code);
- call->state = AFS_CALL_ABORTED;
- _debug("Rcv ABORT %u -> %d", abort_code, call->error);
- break;
- case RXRPC_SKB_MARK_LOCAL_ABORT:
- abort_code = rxrpc_kernel_get_abort_code(skb);
- call->error = call->type->abort_to_error(abort_code);
- call->state = AFS_CALL_ABORTED;
- _debug("Loc ABORT %u -> %d", abort_code, call->error);
- break;
- case RXRPC_SKB_MARK_NET_ERROR:
- call->error = -rxrpc_kernel_get_error_number(skb);
- call->state = AFS_CALL_ERROR;
- _debug("Rcv NET ERROR %d", call->error);
- break;
- case RXRPC_SKB_MARK_LOCAL_ERROR:
- call->error = -rxrpc_kernel_get_error_number(skb);
- call->state = AFS_CALL_ERROR;
- _debug("Rcv LOCAL ERROR %d", call->error);
- break;
- default:
- BUG();
- break;
+ return;
}
- afs_free_skb(skb);
- }
-
- /* make sure the queue is empty if the call is done with (we might have
- * aborted the call early because of an unmarshalling error) */
- if (call->state >= AFS_CALL_COMPLETE) {
- while ((skb = skb_dequeue(&call->rx_queue)))
- afs_free_skb(skb);
- if (call->incoming)
- afs_end_call(call);
+ ret = call->type->deliver(call);
+ switch (ret) {
+ case 0:
+ if (call->state == AFS_CALL_AWAIT_REPLY)
+ call->state = AFS_CALL_COMPLETE;
+ goto done;
+ case -EINPROGRESS:
+ case -EAGAIN:
+ goto out;
+ case -ENOTCONN:
+ abort_code = RX_CALL_DEAD;
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ abort_code, -ret, "KNC");
+ goto do_abort;
+ case -ENOTSUPP:
+ abort_code = RX_INVALID_OPERATION;
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ abort_code, -ret, "KIV");
+ goto do_abort;
+ case -ENODATA:
+ case -EBADMSG:
+ case -EMSGSIZE:
+ default:
+ abort_code = RXGEN_CC_UNMARSHAL;
+ if (call->state != AFS_CALL_AWAIT_REPLY)
+ abort_code = RXGEN_SS_UNMARSHAL;
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ abort_code, EBADMSG, "KUM");
+ goto do_abort;
+ }
}
+done:
+ if (call->state == AFS_CALL_COMPLETE && call->incoming)
+ afs_end_call(call);
+out:
_leave("");
+ return;
+
+do_abort:
+ call->error = ret;
+ call->state = AFS_CALL_COMPLETE;
+ goto done;
}
/*
@@ -570,7 +475,7 @@ static void afs_deliver_to_call(struct afs_call *call)
*/
static int afs_wait_for_call_to_complete(struct afs_call *call)
{
- struct sk_buff *skb;
+ const char *abort_why;
int ret;
DECLARE_WAITQUEUE(myself, current);
@@ -582,15 +487,18 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
set_current_state(TASK_INTERRUPTIBLE);
/* deliver any messages that are in the queue */
- if (!skb_queue_empty(&call->rx_queue)) {
+ if (call->state < AFS_CALL_COMPLETE && call->need_attention) {
+ call->need_attention = false;
__set_current_state(TASK_RUNNING);
afs_deliver_to_call(call);
continue;
}
+ abort_why = "KWC";
ret = call->error;
- if (call->state >= AFS_CALL_COMPLETE)
+ if (call->state == AFS_CALL_COMPLETE)
break;
+ abort_why = "KWI";
ret = -EINTR;
if (signal_pending(current))
break;
@@ -603,9 +511,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
/* kill the call */
if (call->state < AFS_CALL_COMPLETE) {
_debug("call incomplete");
- rxrpc_kernel_abort_call(call->rxcall, RX_CALL_DEAD);
- while ((skb = skb_dequeue(&call->rx_queue)))
- afs_free_skb(skb);
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ RX_CALL_DEAD, -ret, abort_why);
}
_debug("call complete");
@@ -617,17 +524,24 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
/*
* wake up a waiting call
*/
-static void afs_wake_up_call_waiter(struct afs_call *call)
+static void afs_wake_up_call_waiter(struct sock *sk, struct rxrpc_call *rxcall,
+ unsigned long call_user_ID)
{
+ struct afs_call *call = (struct afs_call *)call_user_ID;
+
+ call->need_attention = true;
wake_up(&call->waitq);
}
/*
* wake up an asynchronous call
*/
-static void afs_wake_up_async_call(struct afs_call *call)
+static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
+ unsigned long call_user_ID)
{
- _enter("");
+ struct afs_call *call = (struct afs_call *)call_user_ID;
+
+ call->need_attention = true;
queue_work(afs_async_calls, &call->async_work);
}
@@ -645,8 +559,10 @@ static int afs_dont_wait_for_call_to_complete(struct afs_call *call)
/*
* delete an asynchronous call
*/
-static void afs_delete_async_call(struct afs_call *call)
+static void afs_delete_async_call(struct work_struct *work)
{
+ struct afs_call *call = container_of(work, struct afs_call, async_work);
+
_enter("");
afs_free_call(call);
@@ -656,17 +572,19 @@ static void afs_delete_async_call(struct afs_call *call)
/*
* perform processing on an asynchronous call
- * - on a multiple-thread workqueue this work item may try to run on several
- * CPUs at the same time
*/
-static void afs_process_async_call(struct afs_call *call)
+static void afs_process_async_call(struct work_struct *work)
{
+ struct afs_call *call = container_of(work, struct afs_call, async_work);
+
_enter("");
- if (!skb_queue_empty(&call->rx_queue))
+ if (call->state < AFS_CALL_COMPLETE && call->need_attention) {
+ call->need_attention = false;
afs_deliver_to_call(call);
+ }
- if (call->state >= AFS_CALL_COMPLETE && call->wait_mode) {
+ if (call->state == AFS_CALL_COMPLETE && call->wait_mode) {
if (call->wait_mode->async_complete)
call->wait_mode->async_complete(call->reply,
call->error);
@@ -677,104 +595,93 @@ static void afs_process_async_call(struct afs_call *call)
/* we can't just delete the call because the work item may be
* queued */
- call->async_workfn = afs_delete_async_call;
+ call->async_work.func = afs_delete_async_call;
queue_work(afs_async_calls, &call->async_work);
}
_leave("");
}
-/*
- * empty a socket buffer into a flat reply buffer
- */
-void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb)
+static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID)
{
- size_t len = skb->len;
+ struct afs_call *call = (struct afs_call *)user_call_ID;
- if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, len) < 0)
- BUG();
- call->reply_size += len;
+ call->rxcall = rxcall;
}
/*
- * accept the backlog of incoming calls
+ * Charge the incoming call preallocation.
*/
-static void afs_collect_incoming_call(struct work_struct *work)
+static void afs_charge_preallocation(struct work_struct *work)
{
- struct rxrpc_call *rxcall;
- struct afs_call *call = NULL;
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&afs_incoming_calls))) {
- _debug("new call");
-
- /* don't need the notification */
- afs_free_skb(skb);
+ struct afs_call *call = afs_spare_incoming_call;
+ for (;;) {
if (!call) {
call = kzalloc(sizeof(struct afs_call), GFP_KERNEL);
- if (!call) {
- rxrpc_kernel_reject_call(afs_socket);
- return;
- }
+ if (!call)
+ break;
- call->async_workfn = afs_process_async_call;
- INIT_WORK(&call->async_work, afs_async_workfn);
+ INIT_WORK(&call->async_work, afs_process_async_call);
call->wait_mode = &afs_async_incoming_call;
call->type = &afs_RXCMxxxx;
init_waitqueue_head(&call->waitq);
- skb_queue_head_init(&call->rx_queue);
call->state = AFS_CALL_AWAIT_OP_ID;
-
- _debug("CALL %p{%s} [%d]",
- call, call->type->name,
- atomic_read(&afs_outstanding_calls));
- atomic_inc(&afs_outstanding_calls);
}
- rxcall = rxrpc_kernel_accept_call(afs_socket,
- (unsigned long) call);
- if (!IS_ERR(rxcall)) {
- call->rxcall = rxcall;
- call = NULL;
- }
+ if (rxrpc_kernel_charge_accept(afs_socket,
+ afs_wake_up_async_call,
+ afs_rx_attach,
+ (unsigned long)call,
+ GFP_KERNEL) < 0)
+ break;
+ call = NULL;
}
+ afs_spare_incoming_call = call;
+}
- if (call)
- afs_free_call(call);
+/*
+ * Discard a preallocated call when a socket is shut down.
+ */
+static void afs_rx_discard_new_call(struct rxrpc_call *rxcall,
+ unsigned long user_call_ID)
+{
+ struct afs_call *call = (struct afs_call *)user_call_ID;
+
+ atomic_inc(&afs_outstanding_calls);
+ call->rxcall = NULL;
+ afs_free_call(call);
}
/*
- * grab the operation ID from an incoming cache manager call
+ * Notification of an incoming call.
*/
-static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
- bool last)
+static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall,
+ unsigned long user_call_ID)
{
- size_t len = skb->len;
- void *oibuf = (void *) &call->operation_ID;
+ atomic_inc(&afs_outstanding_calls);
+ queue_work(afs_wq, &afs_charge_preallocation_work);
+}
- _enter("{%u},{%zu},%d", call->offset, len, last);
+/*
+ * Grab the operation ID from an incoming cache manager call. The socket
+ * buffer is discarded on error or if we don't yet have sufficient data.
+ */
+static int afs_deliver_cm_op_id(struct afs_call *call)
+{
+ int ret;
+
+ _enter("{%zu}", call->offset);
ASSERTCMP(call->offset, <, 4);
/* the operation ID forms the first four bytes of the request data */
- len = min_t(size_t, len, 4 - call->offset);
- if (skb_copy_bits(skb, 0, oibuf + call->offset, len) < 0)
- BUG();
- if (!pskb_pull(skb, len))
- BUG();
- call->offset += len;
-
- if (call->offset < 4) {
- if (last) {
- _leave(" = -EBADMSG [op ID short]");
- return -EBADMSG;
- }
- _leave(" = 0 [incomplete]");
- return 0;
- }
+ ret = afs_extract_data(call, &call->operation_ID, 4, true);
+ if (ret < 0)
+ return ret;
call->state = AFS_CALL_AWAIT_REQUEST;
+ call->offset = 0;
/* ask the cache manager to route the call (it'll change the call type
* if successful) */
@@ -783,7 +690,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
/* pass responsibility for the remainer of this message off to the
* cache manager op */
- return call->type->deliver(call, skb, last);
+ return call->type->deliver(call);
}
/*
@@ -803,14 +710,15 @@ void afs_send_empty_reply(struct afs_call *call)
msg.msg_flags = 0;
call->state = AFS_CALL_AWAIT_ACK;
- switch (rxrpc_kernel_send_data(call->rxcall, &msg, 0)) {
+ switch (rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, 0)) {
case 0:
_leave(" [replied]");
return;
case -ENOMEM:
_debug("oom");
- rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT);
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ RX_USER_ABORT, ENOMEM, "KOO");
default:
afs_end_call(call);
_leave(" [error]");
@@ -839,7 +747,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
msg.msg_flags = 0;
call->state = AFS_CALL_AWAIT_ACK;
- n = rxrpc_kernel_send_data(call->rxcall, &msg, len);
+ n = rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, len);
if (n >= 0) {
/* Success */
_leave(" [replied]");
@@ -848,37 +756,50 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
if (n == -ENOMEM) {
_debug("oom");
- rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT);
+ rxrpc_kernel_abort_call(afs_socket, call->rxcall,
+ RX_USER_ABORT, ENOMEM, "KOO");
}
afs_end_call(call);
_leave(" [error]");
}
/*
- * extract a piece of data from the received data socket buffers
+ * Extract a piece of data from the received data socket buffers.
*/
-int afs_extract_data(struct afs_call *call, struct sk_buff *skb,
- bool last, void *buf, size_t count)
+int afs_extract_data(struct afs_call *call, void *buf, size_t count,
+ bool want_more)
{
- size_t len = skb->len;
+ int ret;
- _enter("{%u},{%zu},%d,,%zu", call->offset, len, last, count);
+ _enter("{%s,%zu},,%zu,%d",
+ call->type->name, call->offset, count, want_more);
- ASSERTCMP(call->offset, <, count);
+ ASSERTCMP(call->offset, <=, count);
- len = min_t(size_t, len, count - call->offset);
- if (skb_copy_bits(skb, 0, buf + call->offset, len) < 0 ||
- !pskb_pull(skb, len))
- BUG();
- call->offset += len;
+ ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
+ buf, count, &call->offset,
+ want_more, &call->abort_code);
+ if (ret == 0 || ret == -EAGAIN)
+ return ret;
- if (call->offset < count) {
- if (last) {
- _leave(" = -EBADMSG [%d < %zu]", call->offset, count);
- return -EBADMSG;
+ if (ret == 1) {
+ switch (call->state) {
+ case AFS_CALL_AWAIT_REPLY:
+ call->state = AFS_CALL_COMPLETE;
+ break;
+ case AFS_CALL_AWAIT_REQUEST:
+ call->state = AFS_CALL_REPLYING;
+ break;
+ default:
+ break;
}
- _leave(" = -EAGAIN");
- return -EAGAIN;
+ return 0;
}
- return 0;
+
+ if (ret == -ECONNABORTED)
+ call->error = call->type->abort_to_error(call->abort_code);
+ else
+ call->error = ret;
+ call->state = AFS_CALL_COMPLETE;
+ return ret;
}
diff --git a/fs/afs/server.c b/fs/afs/server.c
index f342acf3547d..d4066ab7dd55 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -178,13 +178,18 @@ server_in_two_cells:
/*
* look up a server by its IP address
*/
-struct afs_server *afs_find_server(const struct in_addr *_addr)
+struct afs_server *afs_find_server(const struct sockaddr_rxrpc *srx)
{
struct afs_server *server = NULL;
struct rb_node *p;
- struct in_addr addr = *_addr;
+ struct in_addr addr = srx->transport.sin.sin_addr;
- _enter("%pI4", &addr.s_addr);
+ _enter("{%d,%pI4}", srx->transport.family, &addr.s_addr);
+
+ if (srx->transport.family != AF_INET) {
+ WARN(true, "AFS does not yes support non-IPv4 addresses\n");
+ return NULL;
+ }
read_lock(&afs_servers_lock);
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 340afd0cd182..94bcd97d22b8 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -58,22 +58,18 @@ static int afs_vl_abort_to_error(u32 abort_code)
/*
* deliver reply data to a VL.GetEntryByXXX call
*/
-static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call,
- struct sk_buff *skb, bool last)
+static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call)
{
struct afs_cache_vlocation *entry;
__be32 *bp;
u32 tmp;
- int loop;
+ int loop, ret;
- _enter(",,%u", last);
-
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
+ _enter("");
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
entry = call->reply;
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 52976785a32c..45a86396fd2d 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -594,8 +594,8 @@ static void afs_vlocation_reaper(struct work_struct *work)
*/
int __init afs_vlocation_update_init(void)
{
- afs_vlocation_update_worker =
- create_singlethread_workqueue("kafs_vlupdated");
+ afs_vlocation_update_worker = alloc_workqueue("kafs_vlupdated",
+ WQ_MEM_RECLAIM, 0);
return afs_vlocation_update_worker ? 0 : -ENOMEM;
}
diff --git a/fs/aio.c b/fs/aio.c
index fb8e45b88cd4..4fe81d1c60f9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -239,7 +239,12 @@ static struct dentry *aio_mount(struct file_system_type *fs_type,
static const struct dentry_operations ops = {
.d_dname = simple_dname,
};
- return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+ struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+ AIO_RING_MAGIC);
+
+ if (!IS_ERR(root))
+ root->d_sb->s_iflags |= SB_I_NOEXEC;
+ return root;
}
/* aio_setup
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index b493909e7492..d8e6d421c27f 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -417,6 +417,7 @@ static struct dentry *should_expire(struct dentry *dentry,
}
return NULL;
}
+
/*
* Find an eligible tree to time-out
* A tree is eligible if :-
@@ -432,6 +433,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
struct dentry *root = sb->s_root;
struct dentry *dentry;
struct dentry *expired;
+ struct dentry *found;
struct autofs_info *ino;
if (!root)
@@ -442,31 +444,46 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
dentry = NULL;
while ((dentry = get_next_positive_subdir(dentry, root))) {
+ int flags = how;
+
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
- if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
- expired = NULL;
- else
- expired = should_expire(dentry, mnt, timeout, how);
- if (!expired) {
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
spin_unlock(&sbi->fs_lock);
continue;
}
+ spin_unlock(&sbi->fs_lock);
+
+ expired = should_expire(dentry, mnt, timeout, flags);
+ if (!expired)
+ continue;
+
+ spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(expired);
ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
- spin_lock(&sbi->fs_lock);
- if (should_expire(expired, mnt, timeout, how)) {
- if (expired != dentry)
- dput(dentry);
- goto found;
- }
+ /* Make sure a reference is not taken on found if
+ * things have changed.
+ */
+ flags &= ~AUTOFS_EXP_LEAVES;
+ found = should_expire(expired, mnt, timeout, how);
+ if (!found || found != expired)
+ /* Something has changed, continue */
+ goto next;
+
+ if (expired != dentry)
+ dput(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ goto found;
+next:
+ spin_lock(&sbi->fs_lock);
ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
+ spin_unlock(&sbi->fs_lock);
if (expired != dentry)
dput(expired);
- spin_unlock(&sbi->fs_lock);
}
return NULL;
@@ -483,6 +500,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
+ int state;
/* Block on any pending expire */
if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
@@ -490,8 +508,19 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
if (rcu_walk)
return -ECHILD;
+retry:
spin_lock(&sbi->fs_lock);
- if (ino->flags & AUTOFS_INF_EXPIRING) {
+ state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+ if (state == AUTOFS_INF_WANT_EXPIRE) {
+ spin_unlock(&sbi->fs_lock);
+ /*
+ * Possibly being selected for expire, wait until
+ * it's selected or not.
+ */
+ schedule_timeout_uninterruptible(HZ/10);
+ goto retry;
+ }
+ if (state & AUTOFS_INF_EXPIRING) {
spin_unlock(&sbi->fs_lock);
pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 7f6aff3f72eb..2472af2798c7 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -853,6 +853,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
current->flags |= PF_RANDOMIZE;
setup_new_exec(bprm);
+ install_exec_creds(bprm);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
@@ -1044,7 +1045,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
goto out;
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
- install_exec_creds(bprm);
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0)
@@ -1624,20 +1624,12 @@ static void do_thread_regset_writeback(struct task_struct *task,
regset->writeback(task, regset, 1);
}
-#ifndef PR_REG_SIZE
-#define PR_REG_SIZE(S) sizeof(S)
-#endif
-
#ifndef PRSTATUS_SIZE
-#define PRSTATUS_SIZE(S) sizeof(S)
-#endif
-
-#ifndef PR_REG_PTR
-#define PR_REG_PTR(S) (&((S)->pr_reg))
+#define PRSTATUS_SIZE(S, R) sizeof(S)
#endif
#ifndef SET_PR_FPVALID
-#define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
+#define SET_PR_FPVALID(S, V, R) ((S)->pr_fpvalid = (V))
#endif
static int fill_thread_core_info(struct elf_thread_core_info *t,
@@ -1645,6 +1637,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
long signr, size_t *total)
{
unsigned int i;
+ unsigned int regset_size = view->regsets[0].n * view->regsets[0].size;
/*
* NT_PRSTATUS is the one special case, because the regset data
@@ -1653,12 +1646,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
* We assume that regset 0 is NT_PRSTATUS.
*/
fill_prstatus(&t->prstatus, t->task, signr);
- (void) view->regsets[0].get(t->task, &view->regsets[0],
- 0, PR_REG_SIZE(t->prstatus.pr_reg),
- PR_REG_PTR(&t->prstatus), NULL);
+ (void) view->regsets[0].get(t->task, &view->regsets[0], 0, regset_size,
+ &t->prstatus.pr_reg, NULL);
fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
- PRSTATUS_SIZE(t->prstatus), &t->prstatus);
+ PRSTATUS_SIZE(t->prstatus, regset_size), &t->prstatus);
*total += notesize(&t->notes[0]);
do_thread_regset_writeback(t->task, &view->regsets[0]);
@@ -1688,7 +1680,8 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
regset->core_note_type,
size, data);
else {
- SET_PR_FPVALID(&t->prstatus, 1);
+ SET_PR_FPVALID(&t->prstatus,
+ 1, regset_size);
fill_note(&t->notes[i], "CORE",
NT_PRFPREG, size, data);
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c3cdde87cc8c..08ae99343d92 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -249,7 +249,8 @@ struct super_block *freeze_bdev(struct block_device *bdev)
* thaw_bdev drops it.
*/
sb = get_super(bdev);
- drop_super(sb);
+ if (sb)
+ drop_super(sb);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return sb;
}
@@ -646,7 +647,7 @@ static struct dentry *bd_mount(struct file_system_type *fs_type,
{
struct dentry *dent;
dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
- if (dent)
+ if (!IS_ERR(dent))
dent->d_sb->s_iflags |= SB_I_CGROUPWB;
return dent;
}
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2b88439c2ee8..455a6b2fd539 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -589,6 +589,7 @@ static void __merge_refs(struct list_head *head, int mode)
list_del(&ref2->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref2);
+ cond_resched();
}
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2fe8f89091a3..33fe03551105 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -427,6 +427,7 @@ struct btrfs_space_info {
struct list_head ro_bgs;
struct list_head priority_tickets;
struct list_head tickets;
+ u64 tickets_id;
struct rw_semaphore groups_sem;
/* for block groups in our same type */
@@ -1028,6 +1029,7 @@ struct btrfs_fs_info {
struct btrfs_workqueue *qgroup_rescan_workers;
struct completion qgroup_rescan_completion;
struct btrfs_work qgroup_rescan_work;
+ bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */
/* filesystem state */
unsigned long fs_state;
@@ -1079,6 +1081,8 @@ struct btrfs_fs_info {
struct list_head pinned_chunks;
int creating_free_space_tree;
+ /* Used to record internally whether fs has been frozen */
+ int fs_frozen;
};
struct btrfs_subvolume_writers {
@@ -2578,7 +2582,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
-int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index d9ddcfc18c91..ac02e041464b 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -541,7 +541,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_qgroup_extent_record *qexisting;
int count_mod = 1;
int must_insert_reserved = 0;
@@ -606,10 +605,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
- qexisting = btrfs_qgroup_insert_dirty_extent(fs_info,
- delayed_refs,
- qrecord);
- if (qexisting)
+ if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info,
+ delayed_refs, qrecord))
kfree(qrecord);
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 59febfb8d04a..54bc8c7c6bcd 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -559,8 +559,29 @@ static noinline int check_leaf(struct btrfs_root *root,
u32 nritems = btrfs_header_nritems(leaf);
int slot;
- if (nritems == 0)
+ if (nritems == 0) {
+ struct btrfs_root *check_root;
+
+ key.objectid = btrfs_header_owner(leaf);
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ check_root = btrfs_get_fs_root(root->fs_info, &key, false);
+ /*
+ * The only reason we also check NULL here is that during
+ * open_ctree() some roots has not yet been set up.
+ */
+ if (!IS_ERR_OR_NULL(check_root)) {
+ /* if leaf is the root, then it's fine */
+ if (leaf->start !=
+ btrfs_root_bytenr(&check_root->root_item)) {
+ CORRUPT("non-root leaf's nritems is 0",
+ leaf, root, 0);
+ return -EIO;
+ }
+ }
return 0;
+ }
/* Check the 0 item */
if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
@@ -612,6 +633,19 @@ static noinline int check_leaf(struct btrfs_root *root,
return 0;
}
+static int check_node(struct btrfs_root *root, struct extent_buffer *node)
+{
+ unsigned long nr = btrfs_header_nritems(node);
+
+ if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) {
+ btrfs_crit(root->fs_info,
+ "corrupt node: block %llu root %llu nritems %lu",
+ node->start, root->objectid, nr);
+ return -EIO;
+ }
+ return 0;
+}
+
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
@@ -682,6 +716,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
ret = -EIO;
}
+ if (found_level > 0 && check_node(root, eb))
+ ret = -EIO;
+
if (!ret)
set_extent_buffer_uptodate(eb);
err:
@@ -1618,8 +1655,8 @@ fail:
return ret;
}
-static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
- u64 root_id)
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id)
{
struct btrfs_root *root;
@@ -2298,6 +2335,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
fs_info->qgroup_ulist = NULL;
+ fs_info->qgroup_rescan_running = false;
mutex_init(&fs_info->qgroup_rescan_lock);
}
@@ -2624,6 +2662,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
+ fs_info->fs_frozen = 0;
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
@@ -3739,8 +3778,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log(NULL, root);
+ if (root->reloc_root) {
+ free_extent_buffer(root->reloc_root->node);
+ free_extent_buffer(root->reloc_root->commit_root);
+ btrfs_put_fs_root(root->reloc_root);
+ root->reloc_root = NULL;
+ }
+ }
if (root->free_ino_pinned)
__btrfs_remove_free_space_cache(root->free_ino_pinned);
@@ -3851,7 +3897,7 @@ void close_ctree(struct btrfs_root *root)
smp_mb();
/* wait for the qgroup rescan worker to stop */
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index b3207a0e09f7..f19a982f5a4f 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
struct btrfs_key *location);
int btrfs_init_fs_root(struct btrfs_root *root);
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 61b494e8e604..665da8f66ff1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -60,21 +60,6 @@ enum {
CHUNK_ALLOC_FORCE = 2,
};
-/*
- * Control how reservations are dealt with.
- *
- * RESERVE_FREE - freeing a reservation.
- * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for
- * ENOSPC accounting
- * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update
- * bytes_may_use as the ENOSPC accounting is done elsewhere
- */
-enum {
- RESERVE_FREE = 0,
- RESERVE_ALLOC = 1,
- RESERVE_ALLOC_NO_ACCOUNT = 2,
-};
-
static int update_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr,
u64 num_bytes, int alloc);
@@ -104,9 +89,10 @@ static int find_next_key(struct btrfs_path *path, int level,
struct btrfs_key *key);
static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
int dump_block_groups);
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve,
- int delalloc);
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc);
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
int btrfs_pin_extent(struct btrfs_root *root,
@@ -3501,7 +3487,6 @@ again:
dcs = BTRFS_DC_SETUP;
else if (ret == -ENOSPC)
set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);
- btrfs_free_reserved_data_space(inode, 0, num_pages);
out_put:
iput(inode);
@@ -4286,13 +4271,10 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
if (ret < 0)
return ret;
- /*
- * Use new btrfs_qgroup_reserve_data to reserve precious data space
- *
- * TODO: Find a good method to avoid reserve data space for NOCOW
- * range, but don't impact performance on quota disable case.
- */
+ /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
ret = btrfs_qgroup_reserve_data(inode, start, len);
+ if (ret)
+ btrfs_free_reserved_data_space_noquota(inode, start, len);
return ret;
}
@@ -4472,6 +4454,15 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
}
}
+/*
+ * If force is CHUNK_ALLOC_FORCE:
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ * If force is NOT CHUNK_ALLOC_FORCE:
+ * - return 0 if it doesn't need to allocate a new chunk,
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ */
static int do_chunk_alloc(struct btrfs_trans_handle *trans,
struct btrfs_root *extent_root, u64 flags, int force)
{
@@ -4882,7 +4873,7 @@ static int flush_space(struct btrfs_root *root,
btrfs_get_alloc_profile(root, 0),
CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans, root);
- if (ret == -ENOSPC)
+ if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
case COMMIT_TRANS:
@@ -4907,11 +4898,6 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
u64 expected;
u64 to_reclaim = 0;
- to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
- if (can_overcommit(root, space_info, to_reclaim,
- BTRFS_RESERVE_FLUSH_ALL))
- return 0;
-
list_for_each_entry(ticket, &space_info->tickets, list)
to_reclaim += ticket->bytes;
list_for_each_entry(ticket, &space_info->priority_tickets, list)
@@ -4919,6 +4905,11 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
if (to_reclaim)
return to_reclaim;
+ to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
+ if (can_overcommit(root, space_info, to_reclaim,
+ BTRFS_RESERVE_FLUSH_ALL))
+ return 0;
+
used = space_info->bytes_used + space_info->bytes_reserved +
space_info->bytes_pinned + space_info->bytes_readonly +
space_info->bytes_may_use;
@@ -4972,12 +4963,12 @@ static void wake_all_tickets(struct list_head *head)
*/
static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
{
- struct reserve_ticket *last_ticket = NULL;
struct btrfs_fs_info *fs_info;
struct btrfs_space_info *space_info;
u64 to_reclaim;
int flush_state;
int commit_cycles = 0;
+ u64 last_tickets_id;
fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
@@ -4990,8 +4981,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
spin_unlock(&space_info->lock);
return;
}
- last_ticket = list_first_entry(&space_info->tickets,
- struct reserve_ticket, list);
+ last_tickets_id = space_info->tickets_id;
spin_unlock(&space_info->lock);
flush_state = FLUSH_DELAYED_ITEMS_NR;
@@ -5011,10 +5001,10 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
space_info);
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
- if (last_ticket == ticket) {
+ if (last_tickets_id == space_info->tickets_id) {
flush_state++;
} else {
- last_ticket = ticket;
+ last_tickets_id = space_info->tickets_id;
flush_state = FLUSH_DELAYED_ITEMS_NR;
if (commit_cycles)
commit_cycles--;
@@ -5390,6 +5380,7 @@ again:
list_del_init(&ticket->list);
num_bytes -= ticket->bytes;
ticket->bytes = 0;
+ space_info->tickets_id++;
wake_up(&ticket->wait);
} else {
ticket->bytes -= num_bytes;
@@ -5432,6 +5423,7 @@ again:
num_bytes -= ticket->bytes;
space_info->bytes_may_use += ticket->bytes;
ticket->bytes = 0;
+ space_info->tickets_id++;
wake_up(&ticket->wait);
} else {
trace_btrfs_space_reservation(fs_info, "space_info",
@@ -6497,19 +6489,15 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
}
/**
- * btrfs_update_reserved_bytes - update the block_group and space info counters
+ * btrfs_add_reserved_bytes - update the block_group and space info counters
* @cache: The cache we are manipulating
+ * @ram_bytes: The number of bytes of file content, and will be same to
+ * @num_bytes except for the compress path.
* @num_bytes: The number of bytes in question
- * @reserve: One of the reservation enums
* @delalloc: The blocks are allocated for the delalloc write
*
- * This is called by the allocator when it reserves space, or by somebody who is
- * freeing space that was never actually used on disk. For example if you
- * reserve some space for a new leaf in transaction A and before transaction A
- * commits you free that leaf, you call this with reserve set to 0 in order to
- * clear the reservation.
- *
- * Metadata reservations should be called with RESERVE_ALLOC so we do the proper
+ * This is called by the allocator when it reserves space. Metadata
+ * reservations should be called with RESERVE_ALLOC so we do the proper
* ENOSPC accounting. For data we handle the reservation through clearing the
* delalloc bits in the io_tree. We have to do this since we could end up
* allocating less disk space for the amount of data we have reserved in the
@@ -6519,44 +6507,63 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
* make the reservation and return -EAGAIN, otherwise this function always
* succeeds.
*/
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve, int delalloc)
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
int ret = 0;
spin_lock(&space_info->lock);
spin_lock(&cache->lock);
- if (reserve != RESERVE_FREE) {
- if (cache->ro) {
- ret = -EAGAIN;
- } else {
- cache->reserved += num_bytes;
- space_info->bytes_reserved += num_bytes;
- if (reserve == RESERVE_ALLOC) {
- trace_btrfs_space_reservation(cache->fs_info,
- "space_info", space_info->flags,
- num_bytes, 0);
- space_info->bytes_may_use -= num_bytes;
- }
-
- if (delalloc)
- cache->delalloc_bytes += num_bytes;
- }
+ if (cache->ro) {
+ ret = -EAGAIN;
} else {
- if (cache->ro)
- space_info->bytes_readonly += num_bytes;
- cache->reserved -= num_bytes;
- space_info->bytes_reserved -= num_bytes;
+ cache->reserved += num_bytes;
+ space_info->bytes_reserved += num_bytes;
+ trace_btrfs_space_reservation(cache->fs_info,
+ "space_info", space_info->flags,
+ ram_bytes, 0);
+ space_info->bytes_may_use -= ram_bytes;
if (delalloc)
- cache->delalloc_bytes -= num_bytes;
+ cache->delalloc_bytes += num_bytes;
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
return ret;
}
+/**
+ * btrfs_free_reserved_bytes - update the block_group and space info counters
+ * @cache: The cache we are manipulating
+ * @num_bytes: The number of bytes in question
+ * @delalloc: The blocks are allocated for the delalloc write
+ *
+ * This is called by somebody who is freeing space that was never actually used
+ * on disk. For example if you reserve some space for a new leaf in transaction
+ * A and before transaction A commits you free that leaf, you call this with
+ * reserve set to 0 in order to clear the reservation.
+ */
+
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc)
+{
+ struct btrfs_space_info *space_info = cache->space_info;
+ int ret = 0;
+
+ spin_lock(&space_info->lock);
+ spin_lock(&cache->lock);
+ if (cache->ro)
+ space_info->bytes_readonly += num_bytes;
+ cache->reserved -= num_bytes;
+ space_info->bytes_reserved -= num_bytes;
+
+ if (delalloc)
+ cache->delalloc_bytes -= num_bytes;
+ spin_unlock(&cache->lock);
+ spin_unlock(&space_info->lock);
+ return ret;
+}
void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
@@ -7191,7 +7198,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
- btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
+ btrfs_free_reserved_bytes(cache, buf->len, 0);
btrfs_put_block_group(cache);
trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
pin = 0;
@@ -7416,9 +7423,9 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache,
* the free space extent currently.
*/
static noinline int find_free_extent(struct btrfs_root *orig_root,
- u64 num_bytes, u64 empty_size,
- u64 hint_byte, struct btrfs_key *ins,
- u64 flags, int delalloc)
+ u64 ram_bytes, u64 num_bytes, u64 empty_size,
+ u64 hint_byte, struct btrfs_key *ins,
+ u64 flags, int delalloc)
{
int ret = 0;
struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -7430,8 +7437,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
struct btrfs_space_info *space_info;
int loop = 0;
int index = __get_raid_index(flags);
- int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ?
- RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
bool failed_cluster_refill = false;
bool failed_alloc = false;
bool use_cluster = true;
@@ -7763,8 +7768,8 @@ checks:
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
- alloc_type, delalloc);
+ ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
+ num_bytes, delalloc);
if (ret == -EAGAIN) {
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
@@ -7936,7 +7941,7 @@ again:
up_read(&info->groups_sem);
}
-int btrfs_reserve_extent(struct btrfs_root *root,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc)
@@ -7948,8 +7953,8 @@ int btrfs_reserve_extent(struct btrfs_root *root,
flags = btrfs_get_alloc_profile(root, is_data);
again:
WARN_ON(num_bytes < root->sectorsize);
- ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
- flags, delalloc);
+ ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
+ hint_byte, ins, flags, delalloc);
if (!ret && !is_data) {
btrfs_dec_block_group_reservations(root->fs_info,
ins->objectid);
@@ -7958,6 +7963,7 @@ again:
num_bytes = min(num_bytes >> 1, ins->offset);
num_bytes = round_down(num_bytes, root->sectorsize);
num_bytes = max(num_bytes, min_alloc_size);
+ ram_bytes = num_bytes;
if (num_bytes == min_alloc_size)
final_tried = true;
goto again;
@@ -7995,7 +8001,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
if (btrfs_test_opt(root->fs_info, DISCARD))
ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
- btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
+ btrfs_free_reserved_bytes(cache, len, delalloc);
trace_btrfs_reserved_extent_free(root, start, len);
}
@@ -8208,6 +8214,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
{
int ret;
struct btrfs_block_group_cache *block_group;
+ struct btrfs_space_info *space_info;
/*
* Mixed block groups will exclude before processing the log so we only
@@ -8223,9 +8230,14 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
if (!block_group)
return -EINVAL;
- ret = btrfs_update_reserved_bytes(block_group, ins->offset,
- RESERVE_ALLOC_NO_ACCOUNT, 0);
- BUG_ON(ret); /* logic error */
+ space_info = block_group->space_info;
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ space_info->bytes_reserved += ins->offset;
+ block_group->reserved += ins->offset;
+ spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
+
ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
0, owner, offset, ins, 1);
btrfs_put_block_group(block_group);
@@ -8368,7 +8380,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
if (IS_ERR(block_rsv))
return ERR_CAST(block_rsv);
- ret = btrfs_reserve_extent(root, blocksize, blocksize,
+ ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize,
empty_size, hint, &ins, 0, 0);
if (ret)
goto out_unuse;
@@ -8521,35 +8533,6 @@ reada:
wc->reada_slot = slot;
}
-/*
- * These may not be seen by the usual inc/dec ref code so we have to
- * add them here.
- */
-static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, u64 bytenr,
- u64 num_bytes)
-{
- struct btrfs_qgroup_extent_record *qrecord;
- struct btrfs_delayed_ref_root *delayed_refs;
-
- qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
- if (!qrecord)
- return -ENOMEM;
-
- qrecord->bytenr = bytenr;
- qrecord->num_bytes = num_bytes;
- qrecord->old_roots = NULL;
-
- delayed_refs = &trans->transaction->delayed_refs;
- spin_lock(&delayed_refs->lock);
- if (btrfs_qgroup_insert_dirty_extent(trans->fs_info,
- delayed_refs, qrecord))
- kfree(qrecord);
- spin_unlock(&delayed_refs->lock);
-
- return 0;
-}
-
static int account_leaf_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *eb)
@@ -8583,7 +8566,8 @@ static int account_leaf_items(struct btrfs_trans_handle *trans,
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
- ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ bytenr, num_bytes, GFP_NOFS);
if (ret)
return ret;
}
@@ -8732,8 +8716,9 @@ walk_down:
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
- ret = record_one_subtree_extent(trans, root, child_bytenr,
- root->nodesize);
+ ret = btrfs_qgroup_insert_dirty_extent(trans,
+ root->fs_info, child_bytenr,
+ root->nodesize, GFP_NOFS);
if (ret)
goto out;
}
@@ -9906,6 +9891,7 @@ static int find_first_block_group(struct btrfs_root *root,
} else {
ret = 0;
}
+ free_extent_map(em);
goto out;
}
path->slots[0]++;
@@ -9942,6 +9928,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
block_group->iref = 0;
block_group->inode = NULL;
spin_unlock(&block_group->lock);
+ ASSERT(block_group->io_ctl.inode == NULL);
iput(inode);
last = block_group->key.objectid + block_group->key.offset;
btrfs_put_block_group(block_group);
@@ -9999,6 +9986,10 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
free_excluded_extents(info->extent_root, block_group);
btrfs_remove_free_space_cache(block_group);
+ ASSERT(list_empty(&block_group->dirty_list));
+ ASSERT(list_empty(&block_group->io_list));
+ ASSERT(list_empty(&block_group->bg_list));
+ ASSERT(atomic_read(&block_group->count) == 1);
btrfs_put_block_group(block_group);
spin_lock(&info->block_group_cache_lock);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index bc2729a7612d..28cd88fccc7e 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -20,6 +20,7 @@
#define EXTENT_DAMAGED (1U << 14)
#define EXTENT_NORESERVE (1U << 15)
#define EXTENT_QGROUP_RESERVED (1U << 16)
+#define EXTENT_CLEAR_DATA_RESV (1U << 17)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 5842423f8f47..fea31a4a6e36 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2070,7 +2070,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
trans->sync = true;
- btrfs_init_log_ctx(&ctx);
+ btrfs_init_log_ctx(&ctx, inode);
ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
@@ -2675,6 +2675,7 @@ static long btrfs_fallocate(struct file *file, int mode,
alloc_start = round_down(offset, blocksize);
alloc_end = round_up(offset + len, blocksize);
+ cur_offset = alloc_start;
/* Make sure we aren't being give some crap mode */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -2767,7 +2768,6 @@ static long btrfs_fallocate(struct file *file, int mode,
/* First, check if we exceed the qgroup limit */
INIT_LIST_HEAD(&reserve_list);
- cur_offset = alloc_start;
while (1) {
em = btrfs_get_extent(inode, NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
@@ -2794,6 +2794,14 @@ static long btrfs_fallocate(struct file *file, int mode,
last_byte - cur_offset);
if (ret < 0)
break;
+ } else {
+ /*
+ * Do not need to reserve unwritten extent for this
+ * range, free reserved data space first, otherwise
+ * it'll result in false ENOSPC error.
+ */
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ last_byte - cur_offset);
}
free_extent_map(em);
cur_offset = last_byte;
@@ -2811,6 +2819,9 @@ static long btrfs_fallocate(struct file *file, int mode,
range->start,
range->len, 1 << inode->i_blkbits,
offset + len, &alloc_hint);
+ else
+ btrfs_free_reserved_data_space(inode, range->start,
+ range->len);
list_del(&range->list);
kfree(range);
}
@@ -2845,18 +2856,11 @@ out_unlock:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
&cached_state, GFP_KERNEL);
out:
- /*
- * As we waited the extent range, the data_rsv_map must be empty
- * in the range, as written data range will be released from it.
- * And for prealloacted extent, it will also be released when
- * its metadata is written.
- * So this is completely used as cleanup.
- */
- btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
inode_unlock(inode);
/* Let go of our reservation. */
- btrfs_free_reserved_data_space(inode, alloc_start,
- alloc_end - alloc_start);
+ if (ret != 0)
+ btrfs_free_reserved_data_space(inode, alloc_start,
+ alloc_end - cur_offset);
return ret;
}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index aa6fabaee72e..359ee861b5a4 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -495,10 +495,9 @@ again:
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_space(inode, 0, prealloc);
+ btrfs_delalloc_release_metadata(inode, prealloc);
goto out_put;
}
- btrfs_free_reserved_data_space(inode, 0, prealloc);
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
out_put:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 08dfc57e2270..e6811c42e41e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -566,6 +566,8 @@ cont:
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
goto free_pages_out;
}
}
@@ -742,7 +744,7 @@ retry:
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
- ret = btrfs_reserve_extent(root,
+ ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
@@ -969,7 +971,8 @@ static noinline int cow_file_range(struct inode *inode,
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
-
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
*nr_written = *nr_written +
(end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
@@ -989,7 +992,7 @@ static noinline int cow_file_range(struct inode *inode,
unsigned long op;
cur_alloc_size = disk_num_bytes;
- ret = btrfs_reserve_extent(root, cur_alloc_size,
+ ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
@@ -1489,8 +1492,10 @@ out_check:
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1,
locked_page, EXTENT_LOCKED |
- EXTENT_DELALLOC, PAGE_UNLOCK |
- PAGE_SET_PRIVATE2);
+ EXTENT_DELALLOC |
+ EXTENT_CLEAR_DATA_RESV,
+ PAGE_UNLOCK | PAGE_SET_PRIVATE2);
+
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
@@ -1807,7 +1812,9 @@ static void btrfs_clear_bit_hook(struct inode *inode,
return;
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE))
+ && do_list && !(state->state & EXTENT_NORESERVE)
+ && (*bits & (EXTENT_DO_ACCOUNTING |
+ EXTENT_CLEAR_DATA_RESV)))
btrfs_free_reserved_data_space_noquota(inode,
state->start, len);
@@ -7251,7 +7258,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
int ret;
alloc_hint = get_extent_allocation_hint(inode, start, len);
- ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
+ ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0,
alloc_hint, &ins, 1, 1);
if (ret)
return ERR_PTR(ret);
@@ -7751,6 +7758,13 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
ret = PTR_ERR(em2);
goto unlock_err;
}
+ /*
+ * For inode marked NODATACOW or extent marked PREALLOC,
+ * use the existing or preallocated extent, so does not
+ * need to adjust btrfs_space_info's bytes_may_use.
+ */
+ btrfs_free_reserved_data_space_noquota(inode,
+ start, len);
goto unlock;
}
}
@@ -7785,7 +7799,6 @@ unlock:
i_size_write(inode, start + len);
adjust_dio_outstanding_extents(inode, dio_data, len);
- btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
dio_data->unsubmitted_oe_range_end = start + len;
@@ -10306,6 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 last_alloc = (u64)-1;
int ret = 0;
bool own_trans = true;
+ u64 end = start + num_bytes - 1;
if (trans)
own_trans = false;
@@ -10327,8 +10341,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
* sized chunks.
*/
cur_bytes = min(cur_bytes, last_alloc);
- ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
- *alloc_hint, &ins, 1, 0);
+ ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
+ min_size, 0, *alloc_hint, &ins, 1, 0);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
@@ -10414,6 +10428,9 @@ next:
if (own_trans)
btrfs_end_transaction(trans, root);
}
+ if (cur_offset < end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ end - cur_offset + 1);
return ret;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 14ed1e9e6bc8..7fd939bfbd99 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1634,6 +1634,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
int namelen;
int ret = 0;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
ret = mnt_want_write_file(file);
if (ret)
goto out;
@@ -1691,6 +1694,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
struct btrfs_ioctl_vol_args *vol_args;
int ret;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
@@ -1714,6 +1720,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
bool readonly = false;
struct btrfs_qgroup_inherit *inherit = NULL;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
@@ -2357,6 +2366,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
int ret;
int err = 0;
+ if (!S_ISDIR(dir->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
@@ -5084,7 +5096,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- return btrfs_qgroup_wait_for_completion(root->fs_info);
+ return btrfs_qgroup_wait_for_completion(root->fs_info, true);
}
static long _btrfs_ioctl_set_received_subvol(struct file *file,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 93ee1c18ef9d..8db2e29fdcf4 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
goto out;
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
@@ -1453,10 +1453,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
return ret;
}
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record)
+int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record)
{
struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node;
struct rb_node *parent_node = NULL;
@@ -1475,12 +1474,42 @@ btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
else if (bytenr > entry->bytenr)
p = &(*p)->rb_right;
else
- return entry;
+ return 1;
}
rb_link_node(&record->node, parent_node, p);
rb_insert_color(&record->node, &delayed_refs->dirty_extent_root);
- return NULL;
+ return 0;
+}
+
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag)
+{
+ struct btrfs_qgroup_extent_record *record;
+ struct btrfs_delayed_ref_root *delayed_refs;
+ int ret;
+
+ if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0)
+ return 0;
+ if (WARN_ON(trans == NULL))
+ return -EINVAL;
+ record = kmalloc(sizeof(*record), gfp_flag);
+ if (!record)
+ return -ENOMEM;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+ record->bytenr = bytenr;
+ record->num_bytes = num_bytes;
+ record->old_roots = NULL;
+
+ spin_lock(&delayed_refs->lock);
+ ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs,
+ record);
+ spin_unlock(&delayed_refs->lock);
+ if (ret > 0)
+ kfree(record);
+ return 0;
}
#define UPDATE_NEW 0
@@ -2303,6 +2332,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
int err = -ENOMEM;
int ret = 0;
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = true;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
+
path = btrfs_alloc_path();
if (!path)
goto out;
@@ -2369,6 +2402,9 @@ out:
}
done:
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = false;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
complete_all(&fs_info->qgroup_rescan_completion);
}
@@ -2487,20 +2523,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
return 0;
}
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible)
{
int running;
int ret = 0;
mutex_lock(&fs_info->qgroup_rescan_lock);
spin_lock(&fs_info->qgroup_lock);
- running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ running = fs_info->qgroup_rescan_running;
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- if (running)
+ if (!running)
+ return 0;
+
+ if (interruptible)
ret = wait_for_completion_interruptible(
&fs_info->qgroup_rescan_completion);
+ else
+ wait_for_completion(&fs_info->qgroup_rescan_completion);
return ret;
}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 710887c06aaf..1bc64c864b62 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible);
int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 src, u64 dst);
int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
@@ -63,10 +64,35 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
struct btrfs_delayed_extent_op;
int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record);
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * No lock version, caller must acquire delayed ref lock and allocate memory.
+ *
+ * Return 0 for success insert
+ * Return >0 for existing record, caller can free @record safely.
+ * Error is not possible
+ */
+int btrfs_qgroup_insert_dirty_extent_nolock(
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record);
+
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * Better encapsulated version.
+ *
+ * Return 0 if the operation is done.
+ * Return <0 for error, like memory allocation failure or invalid parameter
+ * (NULL trans)
+ */
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag);
+
int
btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index b26a5aea41b4..c0c13dc6fe12 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -31,6 +31,7 @@
#include "async-thread.h"
#include "free-space-cache.h"
#include "inode-map.h"
+#include "qgroup.h"
/*
* backref_node, mapping_node and tree_block start with this
@@ -3037,15 +3038,19 @@ int prealloc_file_extent_cluster(struct inode *inode,
u64 num_bytes;
int nr = 0;
int ret = 0;
+ u64 prealloc_start = cluster->start - offset;
+ u64 prealloc_end = cluster->end - offset;
+ u64 cur_offset;
BUG_ON(cluster->start != cluster->boundary[0]);
inode_lock(inode);
- ret = btrfs_check_data_free_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ ret = btrfs_check_data_free_space(inode, prealloc_start,
+ prealloc_end + 1 - prealloc_start);
if (ret)
goto out;
+ cur_offset = prealloc_start;
while (nr < cluster->nr) {
start = cluster->boundary[nr] - offset;
if (nr + 1 < cluster->nr)
@@ -3055,16 +3060,21 @@ int prealloc_file_extent_cluster(struct inode *inode,
lock_extent(&BTRFS_I(inode)->io_tree, start, end);
num_bytes = end + 1 - start;
+ if (cur_offset < start)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ start - cur_offset);
ret = btrfs_prealloc_file_range(inode, 0, start,
num_bytes, num_bytes,
end + 1, &alloc_hint);
+ cur_offset = end + 1;
unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
if (ret)
break;
nr++;
}
- btrfs_free_reserved_data_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ if (cur_offset < prealloc_end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ prealloc_end + 1 - cur_offset);
out:
inode_unlock(inode);
return ret;
@@ -3916,6 +3926,90 @@ int prepare_to_relocate(struct reloc_control *rc)
return 0;
}
+/*
+ * Qgroup fixer for data chunk relocation.
+ * The data relocation is done in the following steps
+ * 1) Copy data extents into data reloc tree
+ * 2) Create tree reloc tree(special snapshot) for related subvolumes
+ * 3) Modify file extents in tree reloc tree
+ * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks
+ *
+ * The problem is, data and tree reloc tree are not accounted to qgroup,
+ * and 4) will only info qgroup to track tree blocks change, not file extents
+ * in the tree blocks.
+ *
+ * The good news is, related data extents are all in data reloc tree, so we
+ * only need to info qgroup to track all file extents in data reloc tree
+ * before commit trans.
+ */
+static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans,
+ struct reloc_control *rc)
+{
+ struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+ struct inode *inode = rc->data_inode;
+ struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret = 0;
+
+ if (!fs_info->quota_enabled)
+ return 0;
+
+ /*
+ * Only for stage where we update data pointers the qgroup fix is
+ * valid.
+ * For MOVING_DATA stage, we will miss the timing of swapping tree
+ * blocks, and won't fix it.
+ */
+ if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found))
+ return 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1);
+ while (1) {
+ struct btrfs_file_extent_item *fi;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ if (key.objectid > btrfs_ino(inode))
+ break;
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ goto next;
+ fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(path->nodes[0], fi) !=
+ BTRFS_FILE_EXTENT_REG)
+ goto next;
+ ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info,
+ btrfs_file_extent_disk_bytenr(path->nodes[0], fi),
+ btrfs_file_extent_disk_num_bytes(path->nodes[0], fi),
+ GFP_NOFS);
+ if (ret < 0)
+ break;
+next:
+ ret = btrfs_next_item(data_reloc_root, path);
+ if (ret < 0)
+ break;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
{
struct rb_root blocks = RB_ROOT;
@@ -4102,10 +4196,18 @@ restart:
/* get rid of pinned extents */
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ ret = qgroup_fix_relocated_data_extents(trans, rc);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ if (!err)
+ err = ret;
+ goto out_free;
+ }
+ btrfs_commit_transaction(trans, rc->extent_root);
out_free:
btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
btrfs_free_path(path);
@@ -4468,10 +4570,16 @@ int btrfs_recover_relocation(struct btrfs_root *root)
unset_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- err = btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ err = qgroup_fix_relocated_data_extents(trans, rc);
+ if (err < 0) {
+ btrfs_abort_transaction(trans, err);
+ goto out_free;
+ }
+ err = btrfs_commit_transaction(trans, rc->extent_root);
out_free:
kfree(rc);
out:
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7fd7e1830cfe..091296062456 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
root_key.objectid = key.offset;
key.offset++;
+ /*
+ * The root might have been inserted already, as before we look
+ * for orphan roots, log replay might have happened, which
+ * triggers a transaction commit and qgroup accounting, which
+ * in turn reads and inserts fs roots while doing backref
+ * walking.
+ */
+ root = btrfs_lookup_fs_root(tree_root->fs_info,
+ root_key.objectid);
+ if (root) {
+ WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ &root->state));
+ if (btrfs_root_refs(&root->root_item) == 0)
+ btrfs_add_dead_root(root);
+ continue;
+ }
+
root = btrfs_read_fs_root(tree_root, &root_key);
err = PTR_ERR_OR_ZERO(root);
if (err && err != -ENOENT) {
@@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
err = btrfs_insert_fs_root(root->fs_info, root);
- /*
- * The root might have been inserted already, as before we look
- * for orphan roots, log replay might have happened, which
- * triggers a transaction commit and qgroup accounting, which
- * in turn reads and inserts fs roots while doing backref
- * walking.
- */
- if (err == -EEXIST)
- err = 0;
if (err) {
+ BUG_ON(err == -EEXIST);
btrfs_free_fs_root(root);
break;
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index efe129fe2678..a87675ffd02b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4268,10 +4268,12 @@ static int process_all_refs(struct send_ctx *sctx,
}
btrfs_release_path(path);
+ /*
+ * We don't actually care about pending_move as we are simply
+ * re-creating this inode and will be rename'ing it into place once we
+ * rename the parent directory.
+ */
ret = process_recorded_refs(sctx, &pending_move);
- /* Only applicable to an incremental send. */
- ASSERT(pending_move == 0);
-
out:
btrfs_free_path(path);
return ret;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 864ce334f696..4071fe2bd098 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2241,6 +2241,13 @@ static int btrfs_freeze(struct super_block *sb)
struct btrfs_trans_handle *trans;
struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+ root->fs_info->fs_frozen = 1;
+ /*
+ * We don't need a barrier here, we'll wait for any transaction that
+ * could be in progress on other threads (and do delayed iputs that
+ * we want to avoid on a frozen filesystem), or do the commit
+ * ourselves.
+ */
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
@@ -2251,6 +2258,14 @@ static int btrfs_freeze(struct super_block *sb)
return btrfs_commit_transaction(trans, root);
}
+static int btrfs_unfreeze(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+
+ root->fs_info->fs_frozen = 0;
+ return 0;
+}
+
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
@@ -2299,6 +2314,7 @@ static const struct super_operations btrfs_super_ops = {
.statfs = btrfs_statfs,
.remount_fs = btrfs_remount,
.freeze_fs = btrfs_freeze,
+ .unfreeze_fs = btrfs_unfreeze,
};
static const struct file_operations btrfs_ctl_fops = {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9cca0a721961..95d41919d034 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2278,8 +2278,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
kmem_cache_free(btrfs_trans_handle_cachep, trans);
+ /*
+ * If fs has been frozen, we can not handle delayed iputs, otherwise
+ * it'll result in deadlock about SB_FREEZE_FS.
+ */
if (current != root->fs_info->transaction_kthread &&
- current != root->fs_info->cleaner_kthread)
+ current != root->fs_info->cleaner_kthread &&
+ !root->fs_info->fs_frozen)
btrfs_run_delayed_iputs(root);
return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fff3f3efa436..ef9c55bc7907 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -27,6 +27,7 @@
#include "backref.h"
#include "hash.h"
#include "compression.h"
+#include "qgroup.h"
/* magic values for the inode_only field in btrfs_log_inode:
*
@@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
ins.type = BTRFS_EXTENT_ITEM_KEY;
offset = key->offset - btrfs_file_extent_offset(eb, item);
+ /*
+ * Manually record dirty extent, as here we did a shallow
+ * file extent item copy and skip normal backref update,
+ * but modifying extent tree all by ourselves.
+ * So need to manually record dirty extent for qgroup,
+ * as the owner of the file extent changed from log tree
+ * (doesn't affect qgroup) to fs/file tree(affects qgroup)
+ */
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ btrfs_file_extent_disk_bytenr(eb, item),
+ btrfs_file_extent_disk_num_bytes(eb, item),
+ GFP_NOFS);
+ if (ret < 0)
+ goto out;
+
if (ins.objectid > 0) {
u64 csum_start;
u64 csum_end;
@@ -2807,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
*/
mutex_unlock(&root->log_mutex);
- btrfs_init_log_ctx(&root_log_ctx);
+ btrfs_init_log_ctx(&root_log_ctx, NULL);
mutex_lock(&log_root_tree->log_mutex);
atomic_inc(&log_root_tree->log_batch);
@@ -2851,6 +2867,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
blk_finish_plug(&plug);
+ list_del_init(&root_log_ctx.list);
mutex_unlock(&log_root_tree->log_mutex);
ret = root_log_ctx.log_ret;
goto out;
@@ -4741,7 +4758,8 @@ again:
if (ret < 0) {
err = ret;
goto out_unlock;
- } else if (ret > 0) {
+ } else if (ret > 0 && ctx &&
+ other_ino != btrfs_ino(ctx->inode)) {
struct btrfs_key inode_key;
struct inode *other_inode;
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index a9f1b75d080d..ab858e31ccbc 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -30,15 +30,18 @@ struct btrfs_log_ctx {
int log_transid;
int io_err;
bool log_new_dentries;
+ struct inode *inode;
struct list_head list;
};
-static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
+static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
+ struct inode *inode)
{
ctx->log_ret = 0;
ctx->log_transid = 0;
ctx->io_err = 0;
ctx->log_new_dentries = false;
+ ctx->inode = inode;
INIT_LIST_HEAD(&ctx->list);
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 51f125508771..035efce603a9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -834,10 +834,6 @@ static void __free_device(struct work_struct *work)
struct btrfs_device *device;
device = container_of(work, struct btrfs_device, rcu_work);
-
- if (device->bdev)
- blkdev_put(device->bdev, device->mode);
-
rcu_string_free(device->name);
kfree(device);
}
@@ -852,6 +848,17 @@ static void free_device(struct rcu_head *head)
schedule_work(&device->rcu_work);
}
+static void btrfs_close_bdev(struct btrfs_device *device)
+{
+ if (device->bdev && device->writeable) {
+ sync_blockdev(device->bdev);
+ invalidate_bdev(device->bdev);
+ }
+
+ if (device->bdev)
+ blkdev_put(device->bdev, device->mode);
+}
+
static void btrfs_close_one_device(struct btrfs_device *device)
{
struct btrfs_fs_devices *fs_devices = device->fs_devices;
@@ -870,10 +877,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
if (device->missing)
fs_devices->missing_devices--;
- if (device->bdev && device->writeable) {
- sync_blockdev(device->bdev);
- invalidate_bdev(device->bdev);
- }
+ btrfs_close_bdev(device);
new_device = btrfs_alloc_device(NULL, &device->devid,
device->uuid);
@@ -1932,6 +1936,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid)
btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device);
}
+ btrfs_close_bdev(device);
+
call_rcu(&device->rcu, free_device);
num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
@@ -2025,6 +2031,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
/* zero out the old super if it is writable */
btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
}
+
+ btrfs_close_bdev(srcdev);
+
call_rcu(&srcdev->rcu, free_device);
/*
@@ -2080,6 +2089,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
* the device_list_mutex lock.
*/
btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+
+ btrfs_close_bdev(tgtdev);
call_rcu(&tgtdev->rcu, free_device);
}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index c64a0b794d49..df4b3e6fa563 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -597,7 +597,7 @@ static bool need_reset_readdir(struct ceph_file_info *fi, loff_t new_pos)
if (is_hash_order(new_pos)) {
/* no need to reset last_name for a forward seek when
* dentries are sotred in hash order */
- } else if (fi->frag |= fpos_frag(new_pos)) {
+ } else if (fi->frag != fpos_frag(new_pos)) {
return true;
}
rinfo = fi->last_readdir ? &fi->last_readdir->r_reply_info : NULL;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 6bbec5e784cd..14ae4b8e1a3c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -609,6 +609,9 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
char *s, *p;
char sep;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+ return dget(sb->s_root);
+
full_path = cifs_build_path_to_root(vol, cifs_sb,
cifs_sb_master_tcon(cifs_sb));
if (full_path == NULL)
@@ -686,26 +689,22 @@ cifs_do_mount(struct file_system_type *fs_type,
cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
if (cifs_sb->mountdata == NULL) {
root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
+ goto out_free;
}
- if (volume_info->prepath) {
- cifs_sb->prepath = kstrdup(volume_info->prepath, GFP_KERNEL);
- if (cifs_sb->prepath == NULL) {
- root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
- }
+ rc = cifs_setup_cifs_sb(volume_info, cifs_sb);
+ if (rc) {
+ root = ERR_PTR(rc);
+ goto out_free;
}
- cifs_setup_cifs_sb(volume_info, cifs_sb);
-
rc = cifs_mount(cifs_sb, volume_info);
if (rc) {
if (!(flags & MS_SILENT))
cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
rc);
root = ERR_PTR(rc);
- goto out_mountdata;
+ goto out_free;
}
mnt_data.vol = volume_info;
@@ -735,11 +734,7 @@ cifs_do_mount(struct file_system_type *fs_type,
sb->s_flags |= MS_ACTIVE;
}
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
- root = dget(sb->s_root);
- else
- root = cifs_get_root(volume_info, sb);
-
+ root = cifs_get_root(volume_info, sb);
if (IS_ERR(root))
goto out_super;
@@ -752,9 +747,9 @@ out:
cifs_cleanup_volume_info(volume_info);
return root;
-out_mountdata:
+out_free:
+ kfree(cifs_sb->prepath);
kfree(cifs_sb->mountdata);
-out_cifs_sb:
kfree(cifs_sb);
out_nls:
unload_nls(volume_info->local_nls);
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 1243bd326591..95dab43646f0 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -184,7 +184,7 @@ extern int cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
unsigned int to_read);
extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
struct page *page, unsigned int to_read);
-extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb);
extern int cifs_match_super(struct super_block *, void *);
extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 7ae03283bd61..2e4f4bad8b1e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2781,6 +2781,24 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
return 1;
}
+static int
+match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
+{
+ struct cifs_sb_info *old = CIFS_SB(sb);
+ struct cifs_sb_info *new = mnt_data->cifs_sb;
+
+ if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
+ if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
+ return 0;
+ /* The prepath should be null terminated strings */
+ if (strcmp(new->prepath, old->prepath))
+ return 0;
+
+ return 1;
+ }
+ return 0;
+}
+
int
cifs_match_super(struct super_block *sb, void *data)
{
@@ -2808,7 +2826,8 @@ cifs_match_super(struct super_block *sb, void *data)
if (!match_server(tcp_srv, volume_info) ||
!match_session(ses, volume_info) ||
- !match_tcon(tcon, volume_info->UNC)) {
+ !match_tcon(tcon, volume_info->UNC) ||
+ !match_prepath(sb, mnt_data)) {
rc = 0;
goto out;
}
@@ -3222,7 +3241,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
}
}
-void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb)
{
INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
@@ -3316,6 +3335,14 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
cifs_dbg(VFS, "mount option dynperm ignored if cifsacl mount option supported\n");
+
+ if (pvolume_info->prepath) {
+ cifs_sb->prepath = kstrdup(pvolume_info->prepath, GFP_KERNEL);
+ if (cifs_sb->prepath == NULL)
+ return -ENOMEM;
+ }
+
+ return 0;
}
static void
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
index c30cf49b69d2..2c6312db8516 100644
--- a/fs/configfs/file.c
+++ b/fs/configfs/file.c
@@ -333,6 +333,7 @@ configfs_write_bin_file(struct file *file, const char __user *buf,
if (bin_attr->cb_max_size &&
*ppos + count > bin_attr->cb_max_size) {
len = -EFBIG;
+ goto out;
}
tbuf = vmalloc(*ppos + count);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 0f9961eede1e..ed115acb5dee 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -11,6 +11,7 @@
#include <linux/random.h>
#include <linux/string.h>
#include <linux/fscrypto.h>
+#include <linux/mount.h>
static int inode_has_encryption_context(struct inode *inode)
{
@@ -92,26 +93,42 @@ static int create_encryption_context_from_policy(struct inode *inode,
return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
}
-int fscrypt_process_policy(struct inode *inode,
+int fscrypt_process_policy(struct file *filp,
const struct fscrypt_policy *policy)
{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
if (policy->version != 0)
return -EINVAL;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
if (!inode_has_encryption_context(inode)) {
- if (!inode->i_sb->s_cop->empty_dir)
- return -EOPNOTSUPP;
- if (!inode->i_sb->s_cop->empty_dir(inode))
- return -ENOTEMPTY;
- return create_encryption_context_from_policy(inode, policy);
+ if (!S_ISDIR(inode->i_mode))
+ ret = -EINVAL;
+ else if (!inode->i_sb->s_cop->empty_dir)
+ ret = -EOPNOTSUPP;
+ else if (!inode->i_sb->s_cop->empty_dir(inode))
+ ret = -ENOTEMPTY;
+ else
+ ret = create_encryption_context_from_policy(inode,
+ policy);
+ } else if (!is_encryption_context_consistent_with_policy(inode,
+ policy)) {
+ printk(KERN_WARNING
+ "%s: Policy inconsistent with encryption context\n",
+ __func__);
+ ret = -EINVAL;
}
- if (is_encryption_context_consistent_with_policy(inode, policy))
- return 0;
-
- printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
- __func__);
- return -EINVAL;
+ mnt_drop_write_file(filp);
+ return ret;
}
EXPORT_SYMBOL(fscrypt_process_policy);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 592059f88e04..354e2ab62031 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -97,9 +97,6 @@ EXPORT_SYMBOL_GPL(debugfs_use_file_finish);
#define F_DENTRY(filp) ((filp)->f_path.dentry)
-#define REAL_FOPS_DEREF(dentry) \
- ((const struct file_operations *)(dentry)->d_fsdata)
-
static int open_proxy_open(struct inode *inode, struct file *filp)
{
const struct dentry *dentry = F_DENTRY(filp);
@@ -112,7 +109,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
goto out;
}
- real_fops = REAL_FOPS_DEREF(dentry);
+ real_fops = debugfs_real_fops(filp);
real_fops = fops_get(real_fops);
if (!real_fops) {
/* Huh? Module did not clean up after itself at exit? */
@@ -143,7 +140,7 @@ static ret_type full_proxy_ ## name(proto) \
{ \
const struct dentry *dentry = F_DENTRY(filp); \
const struct file_operations *real_fops = \
- REAL_FOPS_DEREF(dentry); \
+ debugfs_real_fops(filp); \
int srcu_idx; \
ret_type r; \
\
@@ -176,7 +173,7 @@ static unsigned int full_proxy_poll(struct file *filp,
struct poll_table_struct *wait)
{
const struct dentry *dentry = F_DENTRY(filp);
- const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+ const struct file_operations *real_fops = debugfs_real_fops(filp);
int srcu_idx;
unsigned int r = 0;
@@ -193,7 +190,7 @@ static unsigned int full_proxy_poll(struct file *filp,
static int full_proxy_release(struct inode *inode, struct file *filp)
{
const struct dentry *dentry = F_DENTRY(filp);
- const struct file_operations *real_fops = REAL_FOPS_DEREF(dentry);
+ const struct file_operations *real_fops = debugfs_real_fops(filp);
const struct file_operations *proxy_fops = filp->f_op;
int r = 0;
@@ -209,7 +206,7 @@ static int full_proxy_release(struct inode *inode, struct file *filp)
replace_fops(filp, d_inode(dentry)->i_fop);
kfree((void *)proxy_fops);
fops_put(real_fops);
- return 0;
+ return r;
}
static void __full_proxy_fops_init(struct file_operations *proxy_fops,
@@ -241,7 +238,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
goto out;
}
- real_fops = REAL_FOPS_DEREF(dentry);
+ real_fops = debugfs_real_fops(filp);
real_fops = fops_get(real_fops);
if (!real_fops) {
/* Huh? Module did not cleanup after itself at exit? */
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index bba52634b995..b3e8443a1f47 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -19,8 +19,4 @@ extern const struct file_operations debugfs_noop_file_operations;
extern const struct file_operations debugfs_open_proxy_file_operations;
extern const struct file_operations debugfs_full_proxy_file_operations;
-struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
- struct dentry *parent, void *data,
- const struct file_operations *fops);
-
#endif /* _DEBUGFS_INTERNAL_H_ */
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index d116453b0276..442d1a7e671b 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -272,13 +272,8 @@ static int mknod_ptmx(struct super_block *sb)
struct dentry *root = sb->s_root;
struct pts_fs_info *fsi = DEVPTS_SB(sb);
struct pts_mount_opts *opts = &fsi->mount_opts;
- kuid_t root_uid;
- kgid_t root_gid;
-
- root_uid = make_kuid(current_user_ns(), 0);
- root_gid = make_kgid(current_user_ns(), 0);
- if (!uid_valid(root_uid) || !gid_valid(root_gid))
- return -EINVAL;
+ kuid_t ptmx_uid = current_fsuid();
+ kgid_t ptmx_gid = current_fsgid();
inode_lock(d_inode(root));
@@ -309,8 +304,8 @@ static int mknod_ptmx(struct super_block *sb)
mode = S_IFCHR|opts->ptmxmode;
init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2));
- inode->i_uid = root_uid;
- inode->i_gid = root_gid;
+ inode->i_uid = ptmx_uid;
+ inode->i_gid = ptmx_gid;
d_add(dentry, inode);
@@ -336,7 +331,6 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data)
struct pts_fs_info *fsi = DEVPTS_SB(sb);
struct pts_mount_opts *opts = &fsi->mount_opts;
- sync_filesystem(sb);
err = parse_mount_options(data, PARSE_REMOUNT, opts);
/*
@@ -395,6 +389,7 @@ static int
devpts_fill_super(struct super_block *s, void *data, int silent)
{
struct inode *inode;
+ int error;
s->s_iflags &= ~SB_I_NODEV;
s->s_blocksize = 1024;
@@ -403,10 +398,16 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
s->s_op = &devpts_sops;
s->s_time_gran = 1;
+ error = -ENOMEM;
s->s_fs_info = new_pts_fs_info(s);
if (!s->s_fs_info)
goto fail;
+ error = parse_mount_options(data, PARSE_MOUNT, &DEVPTS_SB(s)->mount_opts);
+ if (error)
+ goto fail;
+
+ error = -ENOMEM;
inode = new_inode(s);
if (!inode)
goto fail;
@@ -418,13 +419,21 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
set_nlink(inode, 2);
s->s_root = d_make_root(inode);
- if (s->s_root)
- return 0;
+ if (!s->s_root) {
+ pr_err("get root dentry failed\n");
+ goto fail;
+ }
- pr_err("get root dentry failed\n");
+ error = mknod_ptmx(s);
+ if (error)
+ goto fail_dput;
+ return 0;
+fail_dput:
+ dput(s->s_root);
+ s->s_root = NULL;
fail:
- return -ENOMEM;
+ return error;
}
/*
@@ -436,43 +445,15 @@ fail:
static struct dentry *devpts_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- int error;
- struct pts_mount_opts opts;
- struct super_block *s;
-
- error = parse_mount_options(data, PARSE_MOUNT, &opts);
- if (error)
- return ERR_PTR(error);
-
- s = sget(fs_type, NULL, set_anon_super, flags, NULL);
- if (IS_ERR(s))
- return ERR_CAST(s);
-
- if (!s->s_root) {
- error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
- if (error)
- goto out_undo_sget;
- s->s_flags |= MS_ACTIVE;
- }
-
- memcpy(&(DEVPTS_SB(s))->mount_opts, &opts, sizeof(opts));
-
- error = mknod_ptmx(s);
- if (error)
- goto out_undo_sget;
-
- return dget(s->s_root);
-
-out_undo_sget:
- deactivate_locked_super(s);
- return ERR_PTR(error);
+ return mount_nodev(fs_type, flags, data, devpts_fill_super);
}
static void devpts_kill_sb(struct super_block *sb)
{
struct pts_fs_info *fsi = DEVPTS_SB(sb);
- ida_destroy(&fsi->allocated_ptys);
+ if (fsi)
+ ida_destroy(&fsi->allocated_ptys);
kfree(fsi);
kill_litter_super(sb);
}
@@ -585,7 +566,8 @@ struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
*/
void *devpts_get_priv(struct dentry *dentry)
{
- WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
+ if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC)
+ return NULL;
return dentry->d_fsdata;
}
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index eea64912c9c0..466f7d60edc2 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -607,20 +607,54 @@ static const struct file_operations format2_fops;
static const struct file_operations format3_fops;
static const struct file_operations format4_fops;
-static int table_open(struct inode *inode, struct file *file)
+static int table_open1(struct inode *inode, struct file *file)
{
struct seq_file *seq;
- int ret = -1;
+ int ret;
- if (file->f_op == &format1_fops)
- ret = seq_open(file, &format1_seq_ops);
- else if (file->f_op == &format2_fops)
- ret = seq_open(file, &format2_seq_ops);
- else if (file->f_op == &format3_fops)
- ret = seq_open(file, &format3_seq_ops);
- else if (file->f_op == &format4_fops)
- ret = seq_open(file, &format4_seq_ops);
+ ret = seq_open(file, &format1_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open2(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format2_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open3(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format3_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open4(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+ ret = seq_open(file, &format4_seq_ops);
if (ret)
return ret;
@@ -631,7 +665,7 @@ static int table_open(struct inode *inode, struct file *file)
static const struct file_operations format1_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open1,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -639,7 +673,7 @@ static const struct file_operations format1_fops = {
static const struct file_operations format2_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open2,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -647,7 +681,7 @@ static const struct file_operations format2_fops = {
static const struct file_operations format3_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open3,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
@@ -655,7 +689,7 @@ static const struct file_operations format3_fops = {
static const struct file_operations format4_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open4,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 1d73fc6dba13..cbb50cadcffc 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -105,7 +105,10 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
inode->i_private = var;
- efivar_entry_add(var, &efivarfs_list);
+ err = efivar_entry_add(var, &efivarfs_list);
+ if (err)
+ goto out;
+
d_instantiate(dentry, inode);
dget(dentry);
out:
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 688ccc16b702..d7a7c53803c1 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -157,12 +157,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
goto fail_inode;
}
+ efivar_entry_size(entry, &size);
+ err = efivar_entry_add(entry, &efivarfs_list);
+ if (err)
+ goto fail_inode;
+
/* copied by the above to local storage in the dentry. */
kfree(name);
- efivar_entry_size(entry, &size);
- efivar_entry_add(entry, &efivarfs_list);
-
inode_lock(inode);
inode->i_private = entry;
i_size_write(inode, size + sizeof(entry->var.Attributes));
@@ -182,7 +184,10 @@ fail:
static int efivarfs_destroy(struct efivar_entry *entry, void *data)
{
- efivar_entry_remove(entry);
+ int err = efivar_entry_remove(entry);
+
+ if (err)
+ return err;
kfree(entry);
return 0;
}
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index efe5fb21c533..04e73a99902b 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -465,6 +465,11 @@ struct inode *ext2_new_inode(struct inode *dir, umode_t mode,
for (i = 0; i < sbi->s_groups_count; i++) {
gdp = ext2_get_group_desc(sb, group, &bh2);
+ if (!gdp) {
+ if (++group == sbi->s_groups_count)
+ group = 0;
+ continue;
+ }
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh) {
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index c7dbb4661119..1e72d425fd3b 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -732,6 +732,16 @@ static int ext2_get_blocks(struct inode *inode,
}
if (IS_DAX(inode)) {
+ int i;
+
+ /*
+ * We must unmap blocks before zeroing so that writeback cannot
+ * overwrite zeros with stale data from block device page cache.
+ */
+ for (i = 0; i < count; i++) {
+ unmap_underlying_metadata(inode->i_sb->s_bdev,
+ le32_to_cpu(chain[depth-1].key) + i);
+ }
/*
* block must be initialised before we put it in the tree
* so that it's not found by another thread before it's
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 3131747199e1..c6ea25a190f8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5466,8 +5466,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 10686fd67fb4..1bb7df5e4536 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -776,7 +776,7 @@ resizefs_out:
(struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
- return fscrypt_process_policy(inode, &policy);
+ return fscrypt_process_policy(filp, &policy);
#else
return -EOPNOTSUPP;
#endif
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1c593aa0218e..3ec8708989ca 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2211,6 +2211,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
+ ext4_fsblk_t sb_block,
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2241,6 +2242,11 @@ static int ext4_check_descriptors(struct super_block *sb,
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
+ if (block_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
@@ -2248,6 +2254,11 @@ static int ext4_check_descriptors(struct super_block *sb,
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
+ if (inode_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
@@ -2255,6 +2266,11 @@ static int ext4_check_descriptors(struct super_block *sb,
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
+ if (inode_table == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "superblock", i);
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -3757,7 +3773,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+ if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 39e9cfb1b371..2eb935ca5d9e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1353,15 +1353,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
size_t min_offs, free;
int total_ino;
void *base, *start, *end;
- int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+ int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+ int isize_diff; /* How much do we need to grow i_extra_isize */
down_write(&EXT4_I(inode)->xattr_sem);
+ /*
+ * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+ */
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
- if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
- up_write(&EXT4_I(inode)->xattr_sem);
- return 0;
- }
+ isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ goto out;
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
@@ -1382,7 +1386,7 @@ retry:
goto cleanup;
free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
- if (free >= new_extra_isize) {
+ if (free >= isize_diff) {
entry = IFIRST(header);
ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
- new_extra_isize, (void *)raw_inode +
@@ -1390,8 +1394,7 @@ retry:
(void *)header, total_ino,
inode->i_sb->s_blocksize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
- error = 0;
- goto cleanup;
+ goto out;
}
/*
@@ -1414,7 +1417,7 @@ retry:
end = bh->b_data + bh->b_size;
min_offs = end - base;
free = ext4_xattr_free_space(first, &min_offs, base, NULL);
- if (free < new_extra_isize) {
+ if (free < isize_diff) {
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
@@ -1428,7 +1431,7 @@ retry:
free = inode->i_sb->s_blocksize;
}
- while (new_extra_isize > 0) {
+ while (isize_diff > 0) {
size_t offs, size, entry_size;
struct ext4_xattr_entry *small_entry = NULL;
struct ext4_xattr_info i = {
@@ -1459,7 +1462,7 @@ retry:
EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
EXT4_XATTR_LEN(last->e_name_len);
if (total_size <= free && total_size < min_total_size) {
- if (total_size < new_extra_isize) {
+ if (total_size < isize_diff) {
small_entry = last;
} else {
entry = last;
@@ -1514,22 +1517,22 @@ retry:
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto cleanup;
+ total_ino -= entry_size;
entry = IFIRST(header);
- if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
- shift_bytes = new_extra_isize;
+ if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+ shift_bytes = isize_diff;
else
- shift_bytes = entry_size + size;
+ shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
/* Adjust the offsets and shift the remaining entries ahead */
- ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
- shift_bytes, (void *)raw_inode +
- EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
- (void *)header, total_ino - entry_size,
- inode->i_sb->s_blocksize);
+ ext4_xattr_shift_entries(entry, -shift_bytes,
+ (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize + shift_bytes,
+ (void *)header, total_ino, inode->i_sb->s_blocksize);
- extra_isize += shift_bytes;
- new_extra_isize -= shift_bytes;
- EXT4_I(inode)->i_extra_isize = extra_isize;
+ isize_diff -= shift_bytes;
+ EXT4_I(inode)->i_extra_isize += shift_bytes;
+ header = IHDR(inode, raw_inode);
i.name = b_entry_name;
i.value = buffer;
@@ -1551,6 +1554,8 @@ retry:
kfree(bs);
}
brelse(bh);
+out:
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return 0;
@@ -1562,6 +1567,10 @@ cleanup:
kfree(is);
kfree(bs);
brelse(bh);
+ /*
+ * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+ * size expansion failed.
+ */
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 69dd3e6566e0..a92e783fa057 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -24,6 +24,7 @@
#define EXT4_XATTR_INDEX_SYSTEM 7
#define EXT4_XATTR_INDEX_RICHACL 8
#define EXT4_XATTR_INDEX_ENCRYPTION 9
+#define EXT4_XATTR_INDEX_HURD 10 /* Reserved for Hurd */
struct ext4_xattr_header {
__le32 h_magic; /* magic number for identification */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d64d2a515cb2..ccb401eebc11 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1699,11 +1699,11 @@ static int f2fs_write_end(struct file *file,
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
- f2fs_put_page(page, 1);
if (pos + copied > i_size_read(inode))
f2fs_i_size_write(inode, pos + copied);
+ f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 675fa79d86f6..14f5fe2b841e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -538,7 +538,7 @@ struct f2fs_nm_info {
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
struct radix_tree_root nat_set_root;/* root of the nat set cache */
- struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
+ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
@@ -787,7 +787,7 @@ struct f2fs_sb_info {
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
- struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */
+ struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
@@ -1074,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
- percpu_down_read(&sbi->cp_rwsem);
+ down_read(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
- percpu_up_read(&sbi->cp_rwsem);
+ up_read(&sbi->cp_rwsem);
}
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- percpu_down_write(&sbi->cp_rwsem);
+ down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
- percpu_up_write(&sbi->cp_rwsem);
+ up_write(&sbi->cp_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0e493f63ea41..28f4f4cbb8d8 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1757,21 +1757,14 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
- int ret;
if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- ret = fscrypt_process_policy(inode, &policy);
- mnt_drop_write_file(filp);
- return ret;
+ return fscrypt_process_policy(filp, &policy);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
@@ -2086,15 +2079,19 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
- if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
- return -EISDIR;
+ if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+ return -EINVAL;
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
inode_lock(src);
- if (src != dst)
- inode_lock(dst);
+ if (src != dst) {
+ if (!inode_trylock(dst)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
@@ -2152,6 +2149,7 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
out_unlock:
if (src != dst)
inode_unlock(dst);
+out:
inode_unlock(src);
return ret;
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b2fa4b615925..f75d197d5beb 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -206,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
struct nat_entry *e;
bool need = false;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
if (!get_nat_flag(e, IS_CHECKPOINTED) &&
!get_nat_flag(e, HAS_FSYNCED_INODE))
need = true;
}
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need;
}
@@ -223,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
struct nat_entry *e;
bool is_cp = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return is_cp;
}
@@ -237,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
struct nat_entry *e;
bool need_update = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need_update;
}
@@ -284,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = grab_nat_entry(nm_i, ni->nid);
@@ -334,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -342,7 +342,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
- percpu_down_write(&nm_i->nat_tree_lock);
+ if (!down_write_trylock(&nm_i->nat_tree_lock))
+ return 0;
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
@@ -351,7 +352,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
@@ -373,13 +374,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
ni->nid = nid;
/* Check nat cache */
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return;
}
@@ -403,11 +404,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
/* cache nat entry */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
cache_nat_entry(sbi, nid, &ne);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
/*
@@ -1788,7 +1789,7 @@ void build_free_nids(struct f2fs_sb_info *sbi)
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1820,7 +1821,7 @@ void build_free_nids(struct f2fs_sb_info *sbi)
remove_free_nid(nm_i, nid);
}
up_read(&curseg->journal_rwsem);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
@@ -2209,7 +2210,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!nm_i->dirty_nat_cnt)
return;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
/*
* if there are no enough space in journal to store dirty nat
@@ -2232,7 +2233,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
@@ -2268,8 +2269,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
- if (percpu_init_rwsem(&nm_i->nat_tree_lock))
- return -ENOMEM;
+ init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -2326,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
@@ -2351,9 +2351,8 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
kmem_cache_free(nat_entry_set_slab, setvec[idx]);
}
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
- percpu_free_rwsem(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
sbi->nm_info = NULL;
kfree(nm_i);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1b86d3f638ef..7f863a645ab1 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -706,8 +706,6 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi)
percpu_counter_destroy(&sbi->nr_pages[i]);
percpu_counter_destroy(&sbi->alloc_valid_block_count);
percpu_counter_destroy(&sbi->total_valid_inode_count);
-
- percpu_free_rwsem(&sbi->cp_rwsem);
}
static void f2fs_put_super(struct super_block *sb)
@@ -1483,9 +1481,6 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
{
int i, err;
- if (percpu_init_rwsem(&sbi->cp_rwsem))
- return -ENOMEM;
-
for (i = 0; i < NR_COUNT_TYPE; i++) {
err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
if (err)
@@ -1686,6 +1681,7 @@ try_onemore:
sbi->write_io[i].bio = NULL;
}
+ init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 1b2f6c2c3aaf..76f09ce7e5b2 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -1,5 +1,6 @@
config FUSE_FS
tristate "FUSE (Filesystem in Userspace) support"
+ select FS_POSIX_ACL
help
With FUSE it is possible to implement a fully functional filesystem
in a userspace program.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index e95eeb445e58..60da84a86dab 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -5,4 +5,4 @@
obj-$(CONFIG_FUSE_FS) += fuse.o
obj-$(CONFIG_CUSE) += cuse.o
-fuse-objs := dev.o dir.o file.o inode.o control.o
+fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o
diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c
new file mode 100644
index 000000000000..ec85765502f1
--- /dev/null
+++ b/fs/fuse/acl.c
@@ -0,0 +1,99 @@
+/*
+ * FUSE: Filesystem in Userspace
+ * Copyright (C) 2016 Canonical Ltd. <seth.forshee@canonical.com>
+ *
+ * This program can be distributed under the terms of the GNU GPL.
+ * See the file COPYING.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+
+struct posix_acl *fuse_get_acl(struct inode *inode, int type)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ int size;
+ const char *name;
+ void *value = NULL;
+ struct posix_acl *acl;
+
+ if (!fc->posix_acl || fc->no_getxattr)
+ return NULL;
+
+ if (type == ACL_TYPE_ACCESS)
+ name = XATTR_NAME_POSIX_ACL_ACCESS;
+ else if (type == ACL_TYPE_DEFAULT)
+ name = XATTR_NAME_POSIX_ACL_DEFAULT;
+ else
+ return ERR_PTR(-EOPNOTSUPP);
+
+ value = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!value)
+ return ERR_PTR(-ENOMEM);
+ size = fuse_getxattr(inode, name, value, PAGE_SIZE);
+ if (size > 0)
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ else if ((size == 0) || (size == -ENODATA) ||
+ (size == -EOPNOTSUPP && fc->no_getxattr))
+ acl = NULL;
+ else if (size == -ERANGE)
+ acl = ERR_PTR(-E2BIG);
+ else
+ acl = ERR_PTR(size);
+
+ kfree(value);
+ return acl;
+}
+
+int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ const char *name;
+ int ret;
+
+ if (!fc->posix_acl || fc->no_setxattr)
+ return -EOPNOTSUPP;
+
+ if (type == ACL_TYPE_ACCESS)
+ name = XATTR_NAME_POSIX_ACL_ACCESS;
+ else if (type == ACL_TYPE_DEFAULT)
+ name = XATTR_NAME_POSIX_ACL_DEFAULT;
+ else
+ return -EINVAL;
+
+ if (acl) {
+ /*
+ * Fuse userspace is responsible for updating access
+ * permissions in the inode, if needed. fuse_setxattr
+ * invalidates the inode attributes, which will force
+ * them to be refreshed the next time they are used,
+ * and it also updates i_ctime.
+ */
+ size_t size = posix_acl_xattr_size(acl->a_count);
+ void *value;
+
+ if (size > PAGE_SIZE)
+ return -E2BIG;
+
+ value = kmalloc(size, GFP_KERNEL);
+ if (!value)
+ return -ENOMEM;
+
+ ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+ if (ret < 0) {
+ kfree(value);
+ return ret;
+ }
+
+ ret = fuse_setxattr(inode, name, value, size, 0);
+ kfree(value);
+ } else {
+ ret = fuse_removexattr(inode, name);
+ }
+ forget_all_cached_acls(inode);
+ fuse_invalidate_attr(inode);
+
+ return ret;
+}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index a94d2ed81ab4..c41bde26c338 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -767,7 +767,6 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
cs->len = err;
cs->offset = off;
cs->pg = page;
- cs->offset = off;
iov_iter_advance(cs->iter, err);
}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index c47b7780ce37..f7c84ab835ca 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -13,6 +13,8 @@
#include <linux/sched.h>
#include <linux/namei.h>
#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx)
{
@@ -37,47 +39,39 @@ static void fuse_advise_use_readdirplus(struct inode *dir)
set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
}
-#if BITS_PER_LONG >= 64
+union fuse_dentry {
+ u64 time;
+ struct rcu_head rcu;
+};
+
static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
{
- entry->d_time = time;
+ ((union fuse_dentry *) entry->d_fsdata)->time = time;
}
static inline u64 fuse_dentry_time(struct dentry *entry)
{
- return entry->d_time;
-}
-#else
-/*
- * On 32 bit archs store the high 32 bits of time in d_fsdata
- */
-static void fuse_dentry_settime(struct dentry *entry, u64 time)
-{
- entry->d_time = time;
- entry->d_fsdata = (void *) (unsigned long) (time >> 32);
-}
-
-static u64 fuse_dentry_time(struct dentry *entry)
-{
- return (u64) entry->d_time +
- ((u64) (unsigned long) entry->d_fsdata << 32);
+ return ((union fuse_dentry *) entry->d_fsdata)->time;
}
-#endif
/*
* FUSE caches dentries and attributes with separate timeout. The
* time in jiffies until the dentry/attributes are valid is stored in
- * dentry->d_time and fuse_inode->i_time respectively.
+ * dentry->d_fsdata and fuse_inode->i_time respectively.
*/
/*
* Calculate the time in jiffies until a dentry/attributes are valid
*/
-static u64 time_to_jiffies(unsigned long sec, unsigned long nsec)
+static u64 time_to_jiffies(u64 sec, u32 nsec)
{
if (sec || nsec) {
- struct timespec ts = {sec, nsec};
- return get_jiffies_64() + timespec_to_jiffies(&ts);
+ struct timespec64 ts = {
+ sec,
+ max_t(u32, nsec, NSEC_PER_SEC - 1)
+ };
+
+ return get_jiffies_64() + timespec64_to_jiffies(&ts);
} else
return 0;
}
@@ -243,6 +237,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
@@ -272,8 +267,23 @@ static int invalid_nodeid(u64 nodeid)
return !nodeid || nodeid == FUSE_ROOT_ID;
}
+static int fuse_dentry_init(struct dentry *dentry)
+{
+ dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL);
+
+ return dentry->d_fsdata ? 0 : -ENOMEM;
+}
+static void fuse_dentry_release(struct dentry *dentry)
+{
+ union fuse_dentry *fd = dentry->d_fsdata;
+
+ kfree_rcu(fd, rcu);
+}
+
const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
+ .d_init = fuse_dentry_init,
+ .d_release = fuse_dentry_release,
};
int fuse_valid_type(int m)
@@ -634,7 +644,7 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry,
return create_new_entry(fc, &args, dir, entry, S_IFLNK);
}
-static inline void fuse_update_ctime(struct inode *inode)
+void fuse_update_ctime(struct inode *inode)
{
if (!IS_NOCMTIME(inode)) {
inode->i_ctime = current_fs_time(inode->i_sb);
@@ -917,6 +927,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
if (time_before64(fi->i_time, get_jiffies_64())) {
r = true;
+ forget_all_cached_acls(inode);
err = fuse_do_getattr(inode, stat, file);
} else {
r = false;
@@ -1017,7 +1028,7 @@ int fuse_allow_current_process(struct fuse_conn *fc)
{
const struct cred *cred;
- if (fc->flags & FUSE_ALLOW_OTHER)
+ if (fc->allow_other)
return 1;
cred = current_cred();
@@ -1064,6 +1075,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask)
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
+ forget_all_cached_acls(inode);
return fuse_do_getattr(inode, NULL, NULL);
}
@@ -1092,7 +1104,7 @@ static int fuse_permission(struct inode *inode, int mask)
/*
* If attributes are needed, refresh them before proceeding
*/
- if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
+ if (fc->default_permissions ||
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
@@ -1105,7 +1117,7 @@ static int fuse_permission(struct inode *inode, int mask)
}
}
- if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
+ if (fc->default_permissions) {
err = generic_permission(inode, mask);
/* If permission is denied, try to refresh file
@@ -1233,6 +1245,7 @@ retry:
fi->nlookup++;
spin_unlock(&fc->lock);
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &o->attr,
entry_attr_timeout(o),
attr_version);
@@ -1605,7 +1618,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
int err;
bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode);
- if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
err = inode_change_ok(inode, attr);
@@ -1702,172 +1715,75 @@ error:
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
{
struct inode *inode = d_inode(entry);
-
- if (!fuse_allow_current_process(get_fuse_conn(inode)))
- return -EACCES;
-
- if (attr->ia_valid & ATTR_FILE)
- return fuse_do_setattr(inode, attr, attr->ia_file);
- else
- return fuse_do_setattr(inode, attr, NULL);
-}
-
-static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
- struct kstat *stat)
-{
- struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
+ struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL;
+ int ret;
- if (!fuse_allow_current_process(fc))
+ if (!fuse_allow_current_process(get_fuse_conn(inode)))
return -EACCES;
- return fuse_update_attributes(inode, stat, NULL, NULL);
-}
-
-static int fuse_setxattr(struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
-{
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_setxattr_in inarg;
- int err;
-
- if (fc->no_setxattr)
- return -EOPNOTSUPP;
+ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) {
+ attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID |
+ ATTR_MODE);
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- inarg.flags = flags;
- args.in.h.opcode = FUSE_SETXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 3;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- args.in.args[1].size = strlen(name) + 1;
- args.in.args[1].value = name;
- args.in.args[2].size = size;
- args.in.args[2].value = value;
- err = fuse_simple_request(fc, &args);
- if (err == -ENOSYS) {
- fc->no_setxattr = 1;
- err = -EOPNOTSUPP;
- }
- if (!err) {
- fuse_invalidate_attr(inode);
- fuse_update_ctime(inode);
+ /*
+ * The only sane way to reliably kill suid/sgid is to do it in
+ * the userspace filesystem
+ *
+ * This should be done on write(), truncate() and chown().
+ */
+ if (!fc->handle_killpriv) {
+ int kill;
+
+ /*
+ * ia_mode calculation may have used stale i_mode.
+ * Refresh and recalculate.
+ */
+ ret = fuse_do_getattr(inode, NULL, file);
+ if (ret)
+ return ret;
+
+ attr->ia_mode = inode->i_mode;
+ kill = should_remove_suid(entry);
+ if (kill & ATTR_KILL_SUID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISUID;
+ }
+ if (kill & ATTR_KILL_SGID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISGID;
+ }
+ }
}
- return err;
-}
-
-static ssize_t fuse_getxattr(struct dentry *entry, struct inode *inode,
- const char *name, void *value, size_t size)
-{
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_getxattr_in inarg;
- struct fuse_getxattr_out outarg;
- ssize_t ret;
+ if (!attr->ia_valid)
+ return 0;
- if (fc->no_getxattr)
- return -EOPNOTSUPP;
+ ret = fuse_do_setattr(inode, attr, file);
+ if (!ret) {
+ /*
+ * If filesystem supports acls it may have updated acl xattrs in
+ * the filesystem, so forget cached acls for the inode.
+ */
+ if (fc->posix_acl)
+ forget_all_cached_acls(inode);
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- args.in.h.opcode = FUSE_GETXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 2;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- args.in.args[1].size = strlen(name) + 1;
- args.in.args[1].value = name;
- /* This is really two different operations rolled into one */
- args.out.numargs = 1;
- if (size) {
- args.out.argvar = 1;
- args.out.args[0].size = size;
- args.out.args[0].value = value;
- } else {
- args.out.args[0].size = sizeof(outarg);
- args.out.args[0].value = &outarg;
- }
- ret = fuse_simple_request(fc, &args);
- if (!ret && !size)
- ret = outarg.size;
- if (ret == -ENOSYS) {
- fc->no_getxattr = 1;
- ret = -EOPNOTSUPP;
+ /* Directory mode changed, may need to revalidate access */
+ if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE))
+ fuse_invalidate_entry_cache(entry);
}
return ret;
}
-static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
+static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
+ struct kstat *stat)
{
struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_getxattr_in inarg;
- struct fuse_getxattr_out outarg;
- ssize_t ret;
if (!fuse_allow_current_process(fc))
return -EACCES;
- if (fc->no_listxattr)
- return -EOPNOTSUPP;
-
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- args.in.h.opcode = FUSE_LISTXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 1;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- /* This is really two different operations rolled into one */
- args.out.numargs = 1;
- if (size) {
- args.out.argvar = 1;
- args.out.args[0].size = size;
- args.out.args[0].value = list;
- } else {
- args.out.args[0].size = sizeof(outarg);
- args.out.args[0].value = &outarg;
- }
- ret = fuse_simple_request(fc, &args);
- if (!ret && !size)
- ret = outarg.size;
- if (ret == -ENOSYS) {
- fc->no_listxattr = 1;
- ret = -EOPNOTSUPP;
- }
- return ret;
-}
-
-static int fuse_removexattr(struct dentry *entry, const char *name)
-{
- struct inode *inode = d_inode(entry);
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- int err;
-
- if (fc->no_removexattr)
- return -EOPNOTSUPP;
-
- args.in.h.opcode = FUSE_REMOVEXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 1;
- args.in.args[0].size = strlen(name) + 1;
- args.in.args[0].value = name;
- err = fuse_simple_request(fc, &args);
- if (err == -ENOSYS) {
- fc->no_removexattr = 1;
- err = -EOPNOTSUPP;
- }
- if (!err) {
- fuse_invalidate_attr(inode);
- fuse_update_ctime(inode);
- }
- return err;
+ return fuse_update_attributes(inode, stat, NULL, NULL);
}
static const struct inode_operations fuse_dir_inode_operations = {
@@ -1884,10 +1800,12 @@ static const struct inode_operations fuse_dir_inode_operations = {
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct file_operations fuse_dir_operations = {
@@ -1905,10 +1823,12 @@ static const struct inode_operations fuse_common_inode_operations = {
.setattr = fuse_setattr,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct inode_operations fuse_symlink_inode_operations = {
@@ -1916,10 +1836,10 @@ static const struct inode_operations fuse_symlink_inode_operations = {
.get_link = fuse_get_link,
.readlink = generic_readlink,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
};
void fuse_init_common(struct inode *inode)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f394aff59c36..b7beb67bf005 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -530,13 +530,13 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
req->out.args[0].size = count;
}
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
{
unsigned i;
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
- if (write)
+ if (should_dirty)
set_page_dirty_lock(page);
put_page(page);
}
@@ -1320,6 +1320,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
loff_t *ppos, int flags)
{
int write = flags & FUSE_DIO_WRITE;
+ bool should_dirty = !write && iter_is_iovec(iter);
int cuse = flags & FUSE_DIO_CUSE;
struct file *file = io->file;
struct inode *inode = file->f_mapping->host;
@@ -1363,7 +1364,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
nres = fuse_send_read(req, io, pos, nbytes, owner);
if (!io->async)
- fuse_release_user_pages(req, !write);
+ fuse_release_user_pages(req, should_dirty);
if (req->out.h.error) {
err = req->out.h.error;
break;
@@ -2325,49 +2326,6 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
return retval;
}
-static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
- unsigned int nr_segs, size_t bytes, bool to_user)
-{
- struct iov_iter ii;
- int page_idx = 0;
-
- if (!bytes)
- return 0;
-
- iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes);
-
- while (iov_iter_count(&ii)) {
- struct page *page = pages[page_idx++];
- size_t todo = min_t(size_t, PAGE_SIZE, iov_iter_count(&ii));
- void *kaddr;
-
- kaddr = kmap(page);
-
- while (todo) {
- char __user *uaddr = ii.iov->iov_base + ii.iov_offset;
- size_t iov_len = ii.iov->iov_len - ii.iov_offset;
- size_t copy = min(todo, iov_len);
- size_t left;
-
- if (!to_user)
- left = copy_from_user(kaddr, uaddr, copy);
- else
- left = copy_to_user(uaddr, kaddr, copy);
-
- if (unlikely(left))
- return -EFAULT;
-
- iov_iter_advance(&ii, copy);
- todo -= copy;
- kaddr += copy;
- }
-
- kunmap(page);
- }
-
- return 0;
-}
-
/*
* CUSE servers compiled on 32bit broke on 64bit kernels because the
* ABI was defined to be 'struct iovec' which is different on 32bit
@@ -2519,8 +2477,9 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
struct iovec *iov_page = NULL;
struct iovec *in_iov = NULL, *out_iov = NULL;
unsigned int in_iovs = 0, out_iovs = 0, num_pages = 0, max_pages;
- size_t in_size, out_size, transferred;
- int err;
+ size_t in_size, out_size, transferred, c;
+ int err, i;
+ struct iov_iter ii;
#if BITS_PER_LONG == 32
inarg.flags |= FUSE_IOCTL_32BIT;
@@ -2602,10 +2561,13 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
req->in.args[1].size = in_size;
req->in.argpages = 1;
- err = fuse_ioctl_copy_user(pages, in_iov, in_iovs, in_size,
- false);
- if (err)
- goto out;
+ err = -EFAULT;
+ iov_iter_init(&ii, WRITE, in_iov, in_iovs, in_size);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) {
+ c = copy_page_from_iter(pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
}
req->out.numargs = 2;
@@ -2671,7 +2633,14 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
if (transferred > inarg.out_size)
goto out;
- err = fuse_ioctl_copy_user(pages, out_iov, out_iovs, transferred, true);
+ err = -EFAULT;
+ iov_iter_init(&ii, READ, out_iov, out_iovs, transferred);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) {
+ c = copy_page_to_iter(pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
+ err = 0;
out:
if (req)
fuse_put_request(fc, req);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index d98d8cc84def..24ada5dc4dae 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -23,6 +23,7 @@
#include <linux/poll.h>
#include <linux/workqueue.h>
#include <linux/kref.h>
+#include <linux/xattr.h>
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
@@ -36,15 +37,6 @@
/** Number of dentries for each connection in the control filesystem */
#define FUSE_CTL_NUM_DENTRIES 5
-/** If the FUSE_DEFAULT_PERMISSIONS flag is given, the filesystem
- module will check permissions based on the file mode. Otherwise no
- permission checking is done in the kernel */
-#define FUSE_DEFAULT_PERMISSIONS (1 << 0)
-
-/** If the FUSE_ALLOW_OTHER flag is given, then not only the user
- doing the mount will be allowed to access the filesystem */
-#define FUSE_ALLOW_OTHER (1 << 1)
-
/** Number of page pointers embedded in fuse_req */
#define FUSE_REQ_INLINE_PAGES 1
@@ -469,9 +461,6 @@ struct fuse_conn {
/** The group id for this mount */
kgid_t group_id;
- /** The fuse mount flags for this mount */
- unsigned flags;
-
/** Maximum read size */
unsigned max_read;
@@ -547,6 +536,9 @@ struct fuse_conn {
/** allow parallel lookups and readdir (default is serialized) */
unsigned parallel_dirops:1;
+ /** handle fs handles killing suid/sgid/cap on write/chown/trunc */
+ unsigned handle_killpriv:1;
+
/*
* The following bitfields are only for optimization purposes
* and hence races in setting them will not cause malfunction
@@ -624,6 +616,15 @@ struct fuse_conn {
/** Is lseek not implemented by fs? */
unsigned no_lseek:1;
+ /** Does the filesystem support posix acls? */
+ unsigned posix_acl:1;
+
+ /** Check permissions based on the file mode or not? */
+ unsigned default_permissions:1;
+
+ /** Allow other than the mounter user to access the filesystem ? */
+ unsigned allow_other:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -902,6 +903,8 @@ int fuse_allow_current_process(struct fuse_conn *fc);
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id);
+void fuse_update_ctime(struct inode *inode);
+
int fuse_update_attributes(struct inode *inode, struct kstat *stat,
struct file *file, bool *refreshed);
@@ -966,4 +969,17 @@ void fuse_set_initialized(struct fuse_conn *fc);
void fuse_unlock_inode(struct inode *inode);
void fuse_lock_inode(struct inode *inode);
+int fuse_setxattr(struct inode *inode, const char *name, const void *value,
+ size_t size, int flags);
+ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
+ size_t size);
+ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);
+int fuse_removexattr(struct inode *inode, const char *name);
+extern const struct xattr_handler *fuse_xattr_handlers[];
+extern const struct xattr_handler *fuse_acl_xattr_handlers[];
+
+struct posix_acl;
+struct posix_acl *fuse_get_acl(struct inode *inode, int type);
+int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 4e05b51120f4..17141099f2e7 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -20,6 +20,7 @@
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/exportfs.h>
+#include <linux/posix_acl.h>
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -66,7 +67,8 @@ struct fuse_mount_data {
unsigned rootmode_present:1;
unsigned user_id_present:1;
unsigned group_id_present:1;
- unsigned flags;
+ unsigned default_permissions:1;
+ unsigned allow_other:1;
unsigned max_read;
unsigned blksize;
};
@@ -192,7 +194,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
* check in may_delete().
*/
fi->orig_i_mode = inode->i_mode;
- if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ if (!fc->default_permissions)
inode->i_mode &= ~S_ISVTX;
fi->orig_ino = attr->ino;
@@ -340,6 +342,7 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
return -ENOENT;
fuse_invalidate_attr(inode);
+ forget_all_cached_acls(inode);
if (offset >= 0) {
pg_start = offset >> PAGE_SHIFT;
if (len <= 0)
@@ -532,11 +535,11 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
break;
case OPT_DEFAULT_PERMISSIONS:
- d->flags |= FUSE_DEFAULT_PERMISSIONS;
+ d->default_permissions = 1;
break;
case OPT_ALLOW_OTHER:
- d->flags |= FUSE_ALLOW_OTHER;
+ d->allow_other = 1;
break;
case OPT_MAX_READ:
@@ -570,9 +573,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",user_id=%u", from_kuid_munged(&init_user_ns, fc->user_id));
seq_printf(m, ",group_id=%u", from_kgid_munged(&init_user_ns, fc->group_id));
- if (fc->flags & FUSE_DEFAULT_PERMISSIONS)
+ if (fc->default_permissions)
seq_puts(m, ",default_permissions");
- if (fc->flags & FUSE_ALLOW_OTHER)
+ if (fc->allow_other)
seq_puts(m, ",allow_other");
if (fc->max_read != ~0)
seq_printf(m, ",max_read=%u", fc->max_read);
@@ -910,8 +913,15 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->writeback_cache = 1;
if (arg->flags & FUSE_PARALLEL_DIROPS)
fc->parallel_dirops = 1;
+ if (arg->flags & FUSE_HANDLE_KILLPRIV)
+ fc->handle_killpriv = 1;
if (arg->time_gran && arg->time_gran <= 1000000000)
fc->sb->s_time_gran = arg->time_gran;
+ if ((arg->flags & FUSE_POSIX_ACL)) {
+ fc->default_permissions = 1;
+ fc->posix_acl = 1;
+ fc->sb->s_xattr = fuse_acl_xattr_handlers;
+ }
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
@@ -941,7 +951,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
- FUSE_PARALLEL_DIROPS;
+ FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
@@ -1071,6 +1081,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
}
sb->s_magic = FUSE_SUPER_MAGIC;
sb->s_op = &fuse_super_operations;
+ sb->s_xattr = fuse_xattr_handlers;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_time_gran = 1;
sb->s_export_op = &fuse_export_operations;
@@ -1109,7 +1120,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
fc->dont_mask = 1;
sb->s_flags |= MS_POSIXACL;
- fc->flags = d.flags;
+ fc->default_permissions = d.default_permissions;
+ fc->allow_other = d.allow_other;
fc->user_id = d.user_id;
fc->group_id = d.group_id;
fc->max_read = max_t(unsigned, 4096, d.max_read);
diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
new file mode 100644
index 000000000000..3caac46b08b0
--- /dev/null
+++ b/fs/fuse/xattr.c
@@ -0,0 +1,211 @@
+/*
+ * FUSE: Filesystem in Userspace
+ * Copyright (C) 2001-2016 Miklos Szeredi <miklos@szeredi.hu>
+ *
+ * This program can be distributed under the terms of the GNU GPL.
+ * See the file COPYING.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/xattr.h>
+#include <linux/posix_acl_xattr.h>
+
+int fuse_setxattr(struct inode *inode, const char *name, const void *value,
+ size_t size, int flags)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ FUSE_ARGS(args);
+ struct fuse_setxattr_in inarg;
+ int err;
+
+ if (fc->no_setxattr)
+ return -EOPNOTSUPP;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.size = size;
+ inarg.flags = flags;
+ args.in.h.opcode = FUSE_SETXATTR;
+ args.in.h.nodeid = get_node_id(inode);
+ args.in.numargs = 3;
+ args.in.args[0].size = sizeof(inarg);
+ args.in.args[0].value = &inarg;
+ args.in.args[1].size = strlen(name) + 1;
+ args.in.args[1].value = name;
+ args.in.args[2].size = size;
+ args.in.args[2].value = value;
+ err = fuse_simple_request(fc, &args);
+ if (err == -ENOSYS) {
+ fc->no_setxattr = 1;
+ err = -EOPNOTSUPP;
+ }
+ if (!err) {
+ fuse_invalidate_attr(inode);
+ fuse_update_ctime(inode);
+ }
+ return err;
+}
+
+ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
+ size_t size)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ FUSE_ARGS(args);
+ struct fuse_getxattr_in inarg;
+ struct fuse_getxattr_out outarg;
+ ssize_t ret;
+
+ if (fc->no_getxattr)
+ return -EOPNOTSUPP;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.size = size;
+ args.in.h.opcode = FUSE_GETXATTR;
+ args.in.h.nodeid = get_node_id(inode);
+ args.in.numargs = 2;
+ args.in.args[0].size = sizeof(inarg);
+ args.in.args[0].value = &inarg;
+ args.in.args[1].size = strlen(name) + 1;
+ args.in.args[1].value = name;
+ /* This is really two different operations rolled into one */
+ args.out.numargs = 1;
+ if (size) {
+ args.out.argvar = 1;
+ args.out.args[0].size = size;
+ args.out.args[0].value = value;
+ } else {
+ args.out.args[0].size = sizeof(outarg);
+ args.out.args[0].value = &outarg;
+ }
+ ret = fuse_simple_request(fc, &args);
+ if (!ret && !size)
+ ret = min_t(ssize_t, outarg.size, XATTR_SIZE_MAX);
+ if (ret == -ENOSYS) {
+ fc->no_getxattr = 1;
+ ret = -EOPNOTSUPP;
+ }
+ return ret;
+}
+
+static int fuse_verify_xattr_list(char *list, size_t size)
+{
+ size_t origsize = size;
+
+ while (size) {
+ size_t thislen = strnlen(list, size);
+
+ if (!thislen || thislen == size)
+ return -EIO;
+
+ size -= thislen + 1;
+ list += thislen + 1;
+ }
+
+ return origsize;
+}
+
+ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
+{
+ struct inode *inode = d_inode(entry);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ FUSE_ARGS(args);
+ struct fuse_getxattr_in inarg;
+ struct fuse_getxattr_out outarg;
+ ssize_t ret;
+
+ if (!fuse_allow_current_process(fc))
+ return -EACCES;
+
+ if (fc->no_listxattr)
+ return -EOPNOTSUPP;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.size = size;
+ args.in.h.opcode = FUSE_LISTXATTR;
+ args.in.h.nodeid = get_node_id(inode);
+ args.in.numargs = 1;
+ args.in.args[0].size = sizeof(inarg);
+ args.in.args[0].value = &inarg;
+ /* This is really two different operations rolled into one */
+ args.out.numargs = 1;
+ if (size) {
+ args.out.argvar = 1;
+ args.out.args[0].size = size;
+ args.out.args[0].value = list;
+ } else {
+ args.out.args[0].size = sizeof(outarg);
+ args.out.args[0].value = &outarg;
+ }
+ ret = fuse_simple_request(fc, &args);
+ if (!ret && !size)
+ ret = min_t(ssize_t, outarg.size, XATTR_LIST_MAX);
+ if (ret > 0 && size)
+ ret = fuse_verify_xattr_list(list, ret);
+ if (ret == -ENOSYS) {
+ fc->no_listxattr = 1;
+ ret = -EOPNOTSUPP;
+ }
+ return ret;
+}
+
+int fuse_removexattr(struct inode *inode, const char *name)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ FUSE_ARGS(args);
+ int err;
+
+ if (fc->no_removexattr)
+ return -EOPNOTSUPP;
+
+ args.in.h.opcode = FUSE_REMOVEXATTR;
+ args.in.h.nodeid = get_node_id(inode);
+ args.in.numargs = 1;
+ args.in.args[0].size = strlen(name) + 1;
+ args.in.args[0].value = name;
+ err = fuse_simple_request(fc, &args);
+ if (err == -ENOSYS) {
+ fc->no_removexattr = 1;
+ err = -EOPNOTSUPP;
+ }
+ if (!err) {
+ fuse_invalidate_attr(inode);
+ fuse_update_ctime(inode);
+ }
+ return err;
+}
+
+static int fuse_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
+{
+ return fuse_getxattr(inode, name, value, size);
+}
+
+static int fuse_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value, size_t size,
+ int flags)
+{
+ if (!value)
+ return fuse_removexattr(inode, name);
+
+ return fuse_setxattr(inode, name, value, size, flags);
+}
+
+static const struct xattr_handler fuse_xattr_handler = {
+ .prefix = "",
+ .get = fuse_xattr_get,
+ .set = fuse_xattr_set,
+};
+
+const struct xattr_handler *fuse_xattr_handlers[] = {
+ &fuse_xattr_handler,
+ NULL
+};
+
+const struct xattr_handler *fuse_acl_xattr_handlers[] = {
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_handler,
+ &fuse_xattr_handler,
+ NULL
+};
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 82df36886938..5a6f52ea2722 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -187,7 +187,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w
ClearPageChecked(page);
if (!page_has_buffers(page)) {
create_empty_buffers(page, inode->i_sb->s_blocksize,
- (1 << BH_Dirty)|(1 << BH_Uptodate));
+ BIT(BH_Dirty)|BIT(BH_Uptodate));
}
gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
}
@@ -1147,6 +1147,16 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
if (!page_has_buffers(page))
return 0;
+ /*
+ * From xfs_vm_releasepage: mm accommodates an old ext3 case where
+ * clean pages might not have had the dirty bit cleared. Thus, it can
+ * send actual dirty pages to ->releasepage() via shrink_active_list().
+ *
+ * As a workaround, we skip pages that contain dirty buffers below.
+ * Once ->releasepage isn't called on dirty pages anymore, we can warn
+ * on dirty buffers like we used to here again.
+ */
+
gfs2_log_lock(sdp);
spin_lock(&sdp->sd_ail_lock);
head = bh = page_buffers(page);
@@ -1156,8 +1166,8 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
bd = bh->b_private;
if (bd && bd->bd_tr)
goto cannot_release;
- if (buffer_pinned(bh) || buffer_dirty(bh))
- goto not_possible;
+ if (buffer_dirty(bh) || WARN_ON(buffer_pinned(bh)))
+ goto cannot_release;
bh = bh->b_this_page;
} while(bh != head);
spin_unlock(&sdp->sd_ail_lock);
@@ -1180,9 +1190,6 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
return try_to_free_buffers(page);
-not_possible: /* Should never happen */
- WARN_ON(buffer_dirty(bh));
- WARN_ON(buffer_pinned(bh));
cannot_release:
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6e2bec1cd289..645721f3ff00 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -82,8 +82,8 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
}
if (!page_has_buffers(page))
- create_empty_buffers(page, 1 << inode->i_blkbits,
- (1 << BH_Uptodate));
+ create_empty_buffers(page, BIT(inode->i_blkbits),
+ BIT(BH_Uptodate));
bh = page_buffers(page);
@@ -690,7 +690,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
BUG_ON(!dblock);
BUG_ON(!new);
- bh.b_size = 1 << (inode->i_blkbits + (create ? 0 : 5));
+ bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5));
ret = gfs2_block_map(inode, lblock, &bh, create);
*extlen = bh.b_size >> inode->i_blkbits;
*dblock = bh.b_blocknr;
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index fcb59b23f1e3..db8fbeb62483 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -351,7 +351,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
if (hc)
return hc;
- hsize = 1 << ip->i_depth;
+ hsize = BIT(ip->i_depth);
hsize *= sizeof(__be64);
if (hsize != i_size_read(&ip->i_inode)) {
gfs2_consist_inode(ip);
@@ -819,8 +819,8 @@ static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode,
if (ip->i_diskflags & GFS2_DIF_EXHASH) {
struct gfs2_leaf *leaf;
- unsigned hsize = 1 << ip->i_depth;
- unsigned index;
+ unsigned int hsize = BIT(ip->i_depth);
+ unsigned int index;
u64 ln;
if (hsize * sizeof(u64) != i_size_read(inode)) {
gfs2_consist_inode(ip);
@@ -932,7 +932,7 @@ static int dir_make_exhash(struct inode *inode)
return -ENOSPC;
bn = bh->b_blocknr;
- gfs2_assert(sdp, dip->i_entries < (1 << 16));
+ gfs2_assert(sdp, dip->i_entries < BIT(16));
leaf->lf_entries = cpu_to_be16(dip->i_entries);
/* Copy dirents */
@@ -1041,7 +1041,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
bn = nbh->b_blocknr;
/* Compute the start and len of leaf pointers in the hash table. */
- len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth));
+ len = BIT(dip->i_depth - be16_to_cpu(oleaf->lf_depth));
half_len = len >> 1;
if (!half_len) {
pr_warn("i_depth %u lf_depth %u index %u\n",
@@ -1163,7 +1163,7 @@ static int dir_double_exhash(struct gfs2_inode *dip)
int x;
int error = 0;
- hsize = 1 << dip->i_depth;
+ hsize = BIT(dip->i_depth);
hsize_bytes = hsize * sizeof(__be64);
hc = gfs2_dir_get_hash_table(dip);
@@ -1539,7 +1539,7 @@ static int dir_e_read(struct inode *inode, struct dir_context *ctx,
int error = 0;
unsigned depth = 0;
- hsize = 1 << dip->i_depth;
+ hsize = BIT(dip->i_depth);
hash = gfs2_dir_offset2hash(ctx->pos);
index = hash >> (32 - dip->i_depth);
@@ -1558,7 +1558,7 @@ static int dir_e_read(struct inode *inode, struct dir_context *ctx,
if (error)
break;
- len = 1 << (dip->i_depth - depth);
+ len = BIT(dip->i_depth - depth);
index = (index & ~(len - 1)) + len;
}
@@ -2113,7 +2113,7 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip)
u64 leaf_no;
int error = 0, last;
- hsize = 1 << dip->i_depth;
+ hsize = BIT(dip->i_depth);
lp = gfs2_dir_get_hash_table(dip);
if (IS_ERR(lp))
@@ -2126,7 +2126,7 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip)
if (error)
goto out;
leaf = (struct gfs2_leaf *)bh->b_data;
- len = 1 << (dip->i_depth - be16_to_cpu(leaf->lf_depth));
+ len = BIT(dip->i_depth - be16_to_cpu(leaf->lf_depth));
next_index = (index & ~(len - 1)) + len;
last = ((next_index >= hsize) ? 1 : 0);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 320e65e61938..360188f162bd 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -395,9 +395,6 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
- /* Update file times before taking page lock */
- file_update_time(vma->vm_file);
-
ret = gfs2_rsqa_alloc(ip);
if (ret)
goto out;
@@ -409,6 +406,9 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
if (ret)
goto out_uninit;
+ /* Update file times before taking page lock */
+ file_update_time(vma->vm_file);
+
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3a90b2b5b9bb..14cbf60167a7 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -69,7 +69,7 @@ static atomic_t lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(lru_lock);
#define GFS2_GL_HASH_SHIFT 15
-#define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT)
+#define GFS2_GL_HASH_SIZE BIT(GFS2_GL_HASH_SHIFT)
static struct rhashtable_params ht_parms = {
.nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4,
@@ -1781,7 +1781,13 @@ int __init gfs2_glock_init(void)
return -ENOMEM;
}
- register_shrinker(&glock_shrinker);
+ ret = register_shrinker(&glock_shrinker);
+ if (ret) {
+ destroy_workqueue(gfs2_delete_workqueue);
+ destroy_workqueue(glock_workqueue);
+ rhashtable_destroy(&gl_hash_table);
+ return ret;
+ }
return 0;
}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index e4da0ecd3285..fb3a810b506f 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -187,6 +187,10 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
}
gfs2_set_iop(inode);
+
+ inode->i_atime.tv_sec = 0;
+ inode->i_atime.tv_nsec = 0;
+
unlock_new_inode(inode);
}
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 7710dfd3af35..aace8ce34a18 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -85,7 +85,7 @@ static inline int gfs2_check_internal_file_size(struct inode *inode,
u64 size = i_size_read(inode);
if (size < minsize || size > maxsize)
goto err;
- if (size & ((1 << inode->i_blkbits) - 1))
+ if (size & (BIT(inode->i_blkbits) - 1))
goto err;
return 0;
err:
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 74fd0139e6c2..67d1fc4668f7 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -145,7 +145,9 @@ static int __init init_gfs2_fs(void)
if (!gfs2_qadata_cachep)
goto fail;
- register_shrinker(&gfs2_qd_shrinker);
+ error = register_shrinker(&gfs2_qd_shrinker);
+ if (error)
+ goto fail;
error = register_filesystem(&gfs2_fs_type);
if (error)
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 950b8be68e41..373639a59782 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -216,23 +216,26 @@ static void gfs2_meta_read_endio(struct bio *bio)
static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
int num)
{
- struct buffer_head *bh = bhs[0];
- struct bio *bio;
- int i;
-
- if (!num)
- return;
-
- bio = bio_alloc(GFP_NOIO, num);
- bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
- for (i = 0; i < num; i++) {
- bh = bhs[i];
- bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+ while (num > 0) {
+ struct buffer_head *bh = *bhs;
+ struct bio *bio;
+
+ bio = bio_alloc(GFP_NOIO, num);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_bdev = bh->b_bdev;
+ while (num > 0) {
+ bh = *bhs;
+ if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) {
+ BUG_ON(bio->bi_iter.bi_size == 0);
+ break;
+ }
+ bhs++;
+ num--;
+ }
+ bio->bi_end_io = gfs2_meta_read_endio;
+ bio_set_op_attrs(bio, op, op_flags);
+ submit_bio(bio);
}
- bio->bi_end_io = gfs2_meta_read_endio;
- bio_set_op_attrs(bio, op, op_flags);
- submit_bio(bio);
}
/**
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index ef1e1822977f..ff72ac6439c8 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -58,7 +58,7 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
gt->gt_quota_scale_num = 1;
gt->gt_quota_scale_den = 1;
gt->gt_new_files_jdata = 0;
- gt->gt_max_readahead = 1 << 18;
+ gt->gt_max_readahead = BIT(18);
gt->gt_complain_secs = 10;
}
@@ -284,7 +284,7 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
GFS2_BASIC_BLOCK_SHIFT;
- sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+ sdp->sd_fsb2bb = BIT(sdp->sd_fsb2bb_shift);
sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_dinode)) / sizeof(u64);
sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
@@ -302,7 +302,7 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
/* Compute maximum reservation required to add a entry to a directory */
- hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+ hash_blocks = DIV_ROUND_UP(sizeof(u64) * BIT(GFS2_DIR_MAX_DEPTH),
sdp->sd_jbsize);
ind_blocks = 0;
@@ -1089,7 +1089,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
sdp->sd_sb.sb_bsize_shift = sb->s_blocksize_bits;
sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
GFS2_BASIC_BLOCK_SHIFT;
- sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+ sdp->sd_fsb2bb = BIT(sdp->sd_fsb2bb_shift);
sdp->sd_tune.gt_logd_secs = sdp->sd_args.ar_commit;
sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 77930ca25303..8af2dfa09236 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -75,7 +75,7 @@
#include "util.h"
#define GFS2_QD_HASH_SHIFT 12
-#define GFS2_QD_HASH_SIZE (1 << GFS2_QD_HASH_SHIFT)
+#define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT)
#define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1)
/* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */
@@ -384,7 +384,7 @@ static int bh_get(struct gfs2_quota_data *qd)
block = qd->qd_slot / sdp->sd_qc_per_block;
offset = qd->qd_slot % sdp->sd_qc_per_block;
- bh_map.b_size = 1 << ip->i_inode.i_blkbits;
+ bh_map.b_size = BIT(ip->i_inode.i_blkbits);
error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
if (error)
goto fail;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 3a7e60bb39f8..e3ee387a6dfe 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -359,7 +359,7 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
u64 size = i_size_read(jd->jd_inode);
- if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30))
+ if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, BIT(30)))
return -EIO;
jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 0f56deb24ce6..c415668c86d4 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -568,7 +568,7 @@ static int ioctl_fsthaw(struct file *filp)
return thaw_super(sb);
}
-static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
{
struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
@@ -582,6 +582,10 @@ static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
}
size = offsetof(struct file_dedupe_range __user, info[count]);
+ if (size > PAGE_SIZE) {
+ ret = -ENOMEM;
+ goto out;
+ }
same = memdup_user(argp, size);
if (IS_ERR(same)) {
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 2e58978d6f45..4d973524c887 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2893,8 +2893,7 @@ restart:
* on anon_list2. Let's check.
*/
if (!list_empty(&TxAnchor.anon_list2)) {
- list_splice(&TxAnchor.anon_list2, &TxAnchor.anon_list);
- INIT_LIST_HEAD(&TxAnchor.anon_list2);
+ list_splice_init(&TxAnchor.anon_list2, &TxAnchor.anon_list);
goto restart;
}
TXN_UNLOCK();
diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 90b3bc21e9b0..bd9b641ada2c 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -379,8 +379,14 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
* cached in meta-data cache, and not written out
* by txCommit();
*/
- filemap_fdatawait(ipbmap->i_mapping);
- filemap_write_and_wait(ipbmap->i_mapping);
+ rc = filemap_fdatawait(ipbmap->i_mapping);
+ if (rc)
+ goto error_out;
+
+ rc = filemap_write_and_wait(ipbmap->i_mapping);
+ if (rc)
+ goto error_out;
+
diWriteSpecial(ipbmap, 0);
newPage = nPages; /* first new page number */
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e1574008adc9..2bcb86e6e6ca 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -840,21 +840,35 @@ repeat:
mutex_lock(&kernfs_mutex);
list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
+ struct kernfs_node *parent;
struct inode *inode;
- struct dentry *dentry;
+ /*
+ * We want fsnotify_modify() on @kn but as the
+ * modifications aren't originating from userland don't
+ * have the matching @file available. Look up the inodes
+ * and generate the events manually.
+ */
inode = ilookup(info->sb, kn->ino);
if (!inode)
continue;
- dentry = d_find_any_alias(inode);
- if (dentry) {
- fsnotify_parent(NULL, dentry, FS_MODIFY);
- fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
- NULL, 0);
- dput(dentry);
+ parent = kernfs_get_parent(kn);
+ if (parent) {
+ struct inode *p_inode;
+
+ p_inode = ilookup(info->sb, parent->ino);
+ if (p_inode) {
+ fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
+ inode, FSNOTIFY_EVENT_INODE, kn->name, 0);
+ iput(p_inode);
+ }
+
+ kernfs_put(parent);
}
+ fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+ kn->name, 0);
iput(inode);
}
diff --git a/fs/locks.c b/fs/locks.c
index ee1b15f6fc13..90ec67108b22 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -127,7 +127,6 @@
#include <linux/pid_namespace.h>
#include <linux/hashtable.h>
#include <linux/percpu.h>
-#include <linux/lglock.h>
#define CREATE_TRACE_POINTS
#include <trace/events/filelock.h>
@@ -158,12 +157,18 @@ int lease_break_time = 45;
/*
* The global file_lock_list is only used for displaying /proc/locks, so we
- * keep a list on each CPU, with each list protected by its own spinlock via
- * the file_lock_lglock. Note that alterations to the list also require that
- * the relevant flc_lock is held.
+ * keep a list on each CPU, with each list protected by its own spinlock.
+ * Global serialization is done using file_rwsem.
+ *
+ * Note that alterations to the list also require that the relevant flc_lock is
+ * held.
*/
-DEFINE_STATIC_LGLOCK(file_lock_lglock);
-static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
+struct file_lock_list_struct {
+ spinlock_t lock;
+ struct hlist_head hlist;
+};
+static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list);
+DEFINE_STATIC_PERCPU_RWSEM(file_rwsem);
/*
* The blocked_hash is used to find POSIX lock loops for deadlock detection.
@@ -587,15 +592,23 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock *fl)
{
- lg_local_lock(&file_lock_lglock);
+ struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);
+
+ percpu_rwsem_assert_held(&file_rwsem);
+
+ spin_lock(&fll->lock);
fl->fl_link_cpu = smp_processor_id();
- hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list));
- lg_local_unlock(&file_lock_lglock);
+ hlist_add_head(&fl->fl_link, &fll->hlist);
+ spin_unlock(&fll->lock);
}
/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock *fl)
{
+ struct file_lock_list_struct *fll;
+
+ percpu_rwsem_assert_held(&file_rwsem);
+
/*
* Avoid taking lock if already unhashed. This is safe since this check
* is done while holding the flc_lock, and new insertions into the list
@@ -603,9 +616,11 @@ static void locks_delete_global_locks(struct file_lock *fl)
*/
if (hlist_unhashed(&fl->fl_link))
return;
- lg_local_lock_cpu(&file_lock_lglock, fl->fl_link_cpu);
+
+ fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu);
+ spin_lock(&fll->lock);
hlist_del_init(&fl->fl_link);
- lg_local_unlock_cpu(&file_lock_lglock, fl->fl_link_cpu);
+ spin_unlock(&fll->lock);
}
static unsigned long
@@ -915,6 +930,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
return -ENOMEM;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
if (request->fl_flags & FL_ACCESS)
goto find_conflict;
@@ -955,6 +971,7 @@ find_conflict:
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
if (new_fl)
locks_free_lock(new_fl);
locks_dispose_list(&dispose);
@@ -991,6 +1008,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
new_fl2 = locks_alloc_lock();
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
@@ -1162,6 +1180,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
/*
* Free any unused locks.
*/
@@ -1436,6 +1455,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
return error;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
@@ -1487,9 +1507,13 @@ restart:
locks_insert_block(fl, new_fl);
trace_break_lease_block(inode, new_fl);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
+
locks_dispose_list(&dispose);
error = wait_event_interruptible_timeout(new_fl->fl_wait,
!new_fl->fl_next, break_time);
+
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
trace_break_lease_unblock(inode, new_fl);
locks_delete_block(new_fl);
@@ -1506,6 +1530,7 @@ restart:
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
locks_free_lock(new_fl);
return error;
@@ -1660,6 +1685,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
return -EINVAL;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
error = check_conflicting_open(dentry, arg, lease->fl_flags);
@@ -1730,6 +1756,7 @@ out_setup:
lease->fl_lmops->lm_setup(lease, priv);
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
if (is_deleg)
inode_unlock(inode);
@@ -1752,6 +1779,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
return error;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file == filp &&
@@ -1764,6 +1792,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
if (victim)
error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
return error;
}
@@ -2574,9 +2603,20 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
struct inode *inode = NULL;
unsigned int fl_pid;
- if (fl->fl_nspid)
- fl_pid = pid_vnr(fl->fl_nspid);
- else
+ if (fl->fl_nspid) {
+ struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
+
+ /* Don't let fl_pid change based on who is reading the file */
+ fl_pid = pid_nr_ns(fl->fl_nspid, proc_pidns);
+
+ /*
+ * If there isn't a fl_pid don't display who is waiting on
+ * the lock if we are called from locks_show, or if we are
+ * called from __show_fd_info - skip lock entirely
+ */
+ if (fl_pid == 0)
+ return;
+ } else
fl_pid = fl->fl_pid;
if (fl->fl_file != NULL)
@@ -2648,9 +2688,13 @@ static int locks_show(struct seq_file *f, void *v)
{
struct locks_iterator *iter = f->private;
struct file_lock *fl, *bfl;
+ struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
fl = hlist_entry(v, struct file_lock, fl_link);
+ if (fl->fl_nspid && !pid_nr_ns(fl->fl_nspid, proc_pidns))
+ return 0;
+
lock_get_status(f, fl, iter->li_pos, "");
list_for_each_entry(bfl, &fl->fl_block, fl_block)
@@ -2703,9 +2747,9 @@ static void *locks_start(struct seq_file *f, loff_t *pos)
struct locks_iterator *iter = f->private;
iter->li_pos = *pos + 1;
- lg_global_lock(&file_lock_lglock);
+ percpu_down_write(&file_rwsem);
spin_lock(&blocked_lock_lock);
- return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos);
+ return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos);
}
static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
@@ -2713,14 +2757,14 @@ static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
struct locks_iterator *iter = f->private;
++iter->li_pos;
- return seq_hlist_next_percpu(v, &file_lock_list, &iter->li_cpu, pos);
+ return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos);
}
static void locks_stop(struct seq_file *f, void *v)
__releases(&blocked_lock_lock)
{
spin_unlock(&blocked_lock_lock);
- lg_global_unlock(&file_lock_lglock);
+ percpu_up_write(&file_rwsem);
}
static const struct seq_operations locks_seq_operations = {
@@ -2761,10 +2805,13 @@ static int __init filelock_init(void)
filelock_cache = kmem_cache_create("file_lock_cache",
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
- lg_lock_init(&file_lock_lglock, "file_lock_lglock");
- for_each_possible_cpu(i)
- INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i));
+ for_each_possible_cpu(i) {
+ struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
+
+ spin_lock_init(&fll->lock);
+ INIT_HLIST_HEAD(&fll->hlist);
+ }
return 0;
}
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index f55a4e756047..217847679f0e 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -346,7 +346,7 @@ static void bl_write_cleanup(struct work_struct *work)
PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
- (end - start) >> SECTOR_SHIFT);
+ (end - start) >> SECTOR_SHIFT, end);
}
pnfs_ld_write_done(hdr);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 18e6fd0b9506..efc007f00742 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -141,6 +141,7 @@ struct pnfs_block_layout {
struct rb_root bl_ext_ro;
spinlock_t bl_ext_lock; /* Protects list manipulation */
bool bl_scsi_layout;
+ u64 bl_lwb;
};
static inline struct pnfs_block_layout *
@@ -182,7 +183,7 @@ int ext_tree_insert(struct pnfs_block_layout *bl,
int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
sector_t end);
int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len);
+ sector_t len, u64 lwb);
bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
struct pnfs_block_extent *ret, bool rw);
int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 992bcb19c11e..c85fbfd2d0d9 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -402,7 +402,7 @@ ext_tree_split(struct rb_root *root, struct pnfs_block_extent *be,
int
ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len)
+ sector_t len, u64 lwb)
{
struct rb_root *root = &bl->bl_ext_rw;
sector_t end = start + len;
@@ -471,6 +471,8 @@ ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
}
}
out:
+ if (bl->bl_lwb < lwb)
+ bl->bl_lwb = lwb;
spin_unlock(&bl->bl_ext_lock);
__ext_put_deviceids(&tmp);
@@ -518,7 +520,7 @@ static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
}
static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
- size_t buffer_size, size_t *count)
+ size_t buffer_size, size_t *count, __u64 *lastbyte)
{
struct pnfs_block_extent *be;
int ret = 0;
@@ -542,6 +544,8 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
p = encode_block_extent(be, p);
be->be_tag = EXTENT_COMMITTING;
}
+ *lastbyte = bl->bl_lwb - 1;
+ bl->bl_lwb = 0;
spin_unlock(&bl->bl_ext_lock);
return ret;
@@ -564,7 +568,7 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
arg->layoutupdate_pages = &arg->layoutupdate_page;
retry:
- ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
+ ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
if (unlikely(ret)) {
ext_tree_free_commitdata(arg, buffer_size);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index a7f2e6e33305..52a28311e2a4 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -275,6 +275,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
err_socks:
svc_rpcb_cleanup(serv, net);
err_bind:
+ nn->cb_users[minorversion]--;
dprintk("NFS: Couldn't create callback socket: err = %d; "
"net = %p\n", ret, net);
return ret;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index c92a75e066a6..f953ef6b2f2e 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -454,11 +454,8 @@ static bool referring_call_exists(struct nfs_client *clp,
((u32 *)&rclist->rcl_sessionid.data)[3],
ref->rc_sequenceid, ref->rc_slotid);
- spin_lock(&tbl->slot_tbl_lock);
- status = (test_bit(ref->rc_slotid, tbl->used_slots) &&
- tbl->slots[ref->rc_slotid].seq_nr ==
- ref->rc_sequenceid);
- spin_unlock(&tbl->slot_tbl_lock);
+ status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
+ ref->rc_sequenceid, HZ >> 1) < 0;
if (status)
goto out;
}
@@ -487,7 +484,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
goto out;
tbl = &clp->cl_session->bc_slot_table;
- slot = tbl->slots + args->csa_slotid;
/* Set up res before grabbing the spinlock */
memcpy(&res->csr_sessionid, &args->csa_sessionid,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 003ebce4bbc4..1e106780a237 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -426,7 +426,7 @@ EXPORT_SYMBOL_GPL(nfs_mark_client_ready);
* Initialise the timeout values for a connection
*/
void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
- unsigned int timeo, unsigned int retrans)
+ int timeo, int retrans)
{
to->to_initval = timeo * HZ / 10;
to->to_retries = retrans;
@@ -434,9 +434,9 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
switch (proto) {
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_TCP_RETRANS;
- if (to->to_initval == 0)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0)
to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
to->to_initval = NFS_MAX_TCP_TIMEOUT;
@@ -449,9 +449,9 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
to->to_exponential = 0;
break;
case XPRT_TRANSPORT_UDP:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_UDP_RETRANS;
- if (!to->to_initval)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0)
to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
to->to_initval = NFS_MAX_UDP_TIMEOUT;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 7d620970f2e1..ca699ddc11c1 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -657,7 +657,10 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
if (result <= 0)
goto out;
- written = generic_write_sync(iocb, result);
+ result = generic_write_sync(iocb, result);
+ if (result < 0)
+ goto out;
+ written = result;
iocb->ki_pos += written;
/* Return error values */
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index e6206eaf2bdf..51b51369704c 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -37,6 +37,7 @@ ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
if (ffl) {
INIT_LIST_HEAD(&ffl->error_list);
INIT_LIST_HEAD(&ffl->mirrors);
+ ffl->last_report_time = ktime_get();
return &ffl->generic_hdr;
} else
return NULL;
@@ -640,19 +641,18 @@ nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
{
static const ktime_t notime = {0};
s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
+ struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
if (ktime_equal(mirror->start_time, notime))
mirror->start_time = now;
- if (ktime_equal(mirror->last_report_time, notime))
- mirror->last_report_time = now;
if (mirror->report_interval != 0)
report_interval = (s64)mirror->report_interval * 1000LL;
else if (layoutstats_timer != 0)
report_interval = (s64)layoutstats_timer * 1000LL;
- if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=
+ if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >=
report_interval) {
- mirror->last_report_time = now;
+ ffl->last_report_time = now;
return true;
}
@@ -806,11 +806,14 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_pnfs_ds *ds;
+ bool fail_return = false;
int idx;
/* mirrors are sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+ if (idx+1 == fls->mirror_array_cnt)
+ fail_return = true;
+ ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
if (ds) {
*best_idx = idx;
return ds;
@@ -859,6 +862,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs4_pnfs_ds *ds;
int ds_idx;
+retry:
/* Use full layout for now */
if (!pgio->pg_lseg)
ff_layout_pg_get_read(pgio, req, false);
@@ -871,10 +875,13 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
@@ -890,12 +897,6 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static void
@@ -909,6 +910,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
int i;
int status;
+retry:
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
@@ -940,10 +942,13 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
@@ -956,12 +961,6 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static unsigned int
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index 1bcdb15d0c41..3ee0c9fcea76 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -84,7 +84,6 @@ struct nfs4_ff_layout_mirror {
struct nfs4_ff_layoutstat read_stat;
struct nfs4_ff_layoutstat write_stat;
ktime_t start_time;
- ktime_t last_report_time;
u32 report_interval;
};
@@ -101,6 +100,7 @@ struct nfs4_flexfile_layout {
struct pnfs_ds_commit_info commit_info;
struct list_head mirrors;
struct list_head error_list; /* nfs4_ff_layout_ds_err */
+ ktime_t last_report_time; /* Layoutstat report times */
};
static inline struct nfs4_flexfile_layout *
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 0aa36be71fce..f7a3f6b05369 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -17,8 +17,8 @@
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
-static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS;
+static unsigned int dataserver_retrans;
void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
@@ -379,7 +379,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
devid = &mirror->mirror_ds->id_node;
if (ff_layout_test_devid_unavailable(devid))
- goto out;
+ goto out_fail;
ds = mirror->mirror_ds->ds;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
@@ -405,15 +405,16 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
mirror->mirror_ds->ds_versions[0].rsize = max_payload;
if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
- } else {
- ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
- mirror, lseg->pls_range.offset,
- lseg->pls_range.length, NFS4ERR_NXIO,
- OP_ILLEGAL, GFP_NOIO);
- if (fail_return || !ff_layout_has_available_ds(lseg))
- pnfs_error_mark_layout_for_return(ino, lseg);
- ds = NULL;
+ goto out;
}
+ ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+ mirror, lseg->pls_range.offset,
+ lseg->pls_range.length, NFS4ERR_NXIO,
+ OP_ILLEGAL, GFP_NOIO);
+out_fail:
+ if (fail_return || !ff_layout_has_available_ds(lseg))
+ pnfs_error_mark_layout_for_return(ino, lseg);
+ ds = NULL;
out:
return ds;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7ce5e023c3c3..74935a19e4bf 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -58,6 +58,9 @@ struct nfs_clone_mount {
*/
#define NFS_UNSPEC_PORT (-1)
+#define NFS_UNSPEC_RETRANS (UINT_MAX)
+#define NFS_UNSPEC_TIMEO (UINT_MAX)
+
/*
* Maximum number of pages that readdir can use for creating
* a vmapped array of pages.
@@ -156,7 +159,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *,
int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
void nfs_server_insert_lists(struct nfs_server *);
void nfs_server_remove_lists(struct nfs_server *);
-void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans);
int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
rpc_authflavor_t);
struct nfs_server *nfs_alloc_server(void);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 6f4752734804..64b43b4ad9dd 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -318,10 +318,22 @@ static void
nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
- struct nfs_server *server = NFS_SERVER(data->args.inode);
+ struct inode *inode = data->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct pnfs_layout_hdr *lo;
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (!pnfs_layout_is_valid(lo)) {
+ spin_unlock(&inode->i_lock);
+ rpc_exit(task, 0);
+ return;
+ }
+ nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid);
+ spin_unlock(&inode->i_lock);
nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
&data->res.seq_res, task);
+
}
static void
@@ -341,11 +353,11 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&data->args.stateid,
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match(&data->args.stateid,
&lo->plh_stateid)) {
LIST_HEAD(head);
@@ -359,11 +371,23 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
} else
spin_unlock(&inode->i_lock);
break;
+ case -NFS4ERR_OLD_STATEID:
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&data->args.stateid,
+ &lo->plh_stateid)) {
+ /* Do we need to delay before resending? */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid,
+ &data->args.stateid))
+ rpc_delay(task, HZ);
+ rpc_restart_call_prepare(task);
+ }
+ spin_unlock(&inode->i_lock);
+ break;
case -ENOTSUPP:
case -EOPNOTSUPP:
NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
- default:
- break;
}
dprintk("%s server returns %d\n", __func__, task->tk_status);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8d7d08d4f95f..cd3b7cfdde16 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -817,6 +817,11 @@ static int nfs4_set_client(struct nfs_server *server,
goto error;
}
+ if (server->nfs_client == clp) {
+ error = -ELOOP;
+ goto error;
+ }
+
/*
* Query for the lease time on clientid setup or renewal
*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1949bbd806eb..a9dec32ba9ba 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -634,15 +634,11 @@ out_sleep:
}
EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
-static int nfs40_sequence_done(struct rpc_task *task,
- struct nfs4_sequence_res *res)
+static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res)
{
struct nfs4_slot *slot = res->sr_slot;
struct nfs4_slot_table *tbl;
- if (slot == NULL)
- goto out;
-
tbl = slot->table;
spin_lock(&tbl->slot_tbl_lock);
if (!nfs41_wake_and_assign_slot(tbl, slot))
@@ -650,7 +646,13 @@ static int nfs40_sequence_done(struct rpc_task *task,
spin_unlock(&tbl->slot_tbl_lock);
res->sr_slot = NULL;
-out:
+}
+
+static int nfs40_sequence_done(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
return 1;
}
@@ -666,6 +668,11 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
tbl = slot->table;
session = tbl->session;
+ /* Bump the slot sequence number */
+ if (slot->seq_done)
+ slot->seq_nr++;
+ slot->seq_done = 0;
+
spin_lock(&tbl->slot_tbl_lock);
/* Be nice to the server: try to ensure that the last transmitted
* value for highest_user_slotid <= target_highest_slotid
@@ -686,9 +693,12 @@ out_unlock:
res->sr_slot = NULL;
if (send_new_highest_used_slotid)
nfs41_notify_server(session->clp);
+ if (waitqueue_active(&tbl->slot_waitq))
+ wake_up_all(&tbl->slot_waitq);
}
-int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+static int nfs41_sequence_process(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
@@ -714,7 +724,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
switch (res->sr_status) {
case 0:
/* Update the slot's sequence and clientid lease timer */
- ++slot->seq_nr;
+ slot->seq_done = 1;
clp = session->clp;
do_renew_lease(clp, res->sr_timestamp);
/* Check sequence flags */
@@ -769,16 +779,16 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
goto retry_nowait;
default:
/* Just update the slot sequence no. */
- ++slot->seq_nr;
+ slot->seq_done = 1;
}
out:
/* The session may be reset by one of the error handlers. */
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
- nfs41_sequence_free_slot(res);
out_noaction:
return ret;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
+ nfs41_sequence_free_slot(res);
task->tk_status = 0;
ret = 0;
}
@@ -789,8 +799,37 @@ out_retry:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return 0;
}
+
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (!nfs41_sequence_process(task, res))
+ return 0;
+ if (res->sr_slot != NULL)
+ nfs41_sequence_free_slot(res);
+ return 1;
+
+}
EXPORT_SYMBOL_GPL(nfs41_sequence_done);
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot == NULL)
+ return 1;
+ if (res->sr_slot->table->session != NULL)
+ return nfs41_sequence_process(task, res);
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL) {
+ if (res->sr_slot->table->session != NULL)
+ nfs41_sequence_free_slot(res);
+ else
+ nfs40_sequence_free_slot(res);
+ }
+}
+
int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
if (res->sr_slot == NULL)
@@ -920,6 +959,17 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
args, res, task);
}
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
+}
+
int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
@@ -1197,6 +1247,7 @@ static void nfs4_opendata_free(struct kref *kref)
struct super_block *sb = p->dentry->d_sb;
nfs_free_seqid(p->o_arg.seqid);
+ nfs4_sequence_free_slot(&p->o_res.seq_res);
if (p->state != NULL)
nfs4_put_open_state(p->state);
nfs4_put_state_owner(p->owner);
@@ -1656,9 +1707,14 @@ err:
static struct nfs4_state *
nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
{
+ struct nfs4_state *ret;
+
if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
- return _nfs4_opendata_reclaim_to_nfs4_state(data);
- return _nfs4_opendata_to_nfs4_state(data);
+ ret =_nfs4_opendata_reclaim_to_nfs4_state(data);
+ else
+ ret = _nfs4_opendata_to_nfs4_state(data);
+ nfs4_sequence_free_slot(&data->o_res.seq_res);
+ return ret;
}
static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
@@ -2056,7 +2112,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
data->rpc_status = task->tk_status;
- if (!nfs4_sequence_done(task, &data->o_res.seq_res))
+ if (!nfs4_sequence_process(task, &data->o_res.seq_res))
return;
if (task->tk_status == 0) {
@@ -7514,12 +7570,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
trace_nfs4_create_session(clp, status);
+ switch (status) {
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_DELAY:
+ case -ETIMEDOUT:
+ case -EACCES:
+ case -EAGAIN:
+ goto out;
+ };
+
+ clp->cl_seqid++;
if (!status) {
/* Verify the session's negotiated channel_attrs values */
status = nfs4_verify_channel_attrs(&args, &res);
/* Increment the clientid slot sequence id */
- if (clp->cl_seqid == res.seqid)
- clp->cl_seqid++;
if (status)
goto out;
nfs4_update_session(session, &res);
@@ -7864,7 +7928,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
struct nfs4_layoutget *lgp = calldata;
dprintk("--> %s\n", __func__);
- nfs41_sequence_done(task, &lgp->res.seq_res);
+ nfs41_sequence_process(task, &lgp->res.seq_res);
dprintk("<-- %s\n", __func__);
}
@@ -8080,6 +8144,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
if (status)
@@ -8106,7 +8171,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
dprintk("--> %s\n", __func__);
- if (!nfs41_sequence_done(task, &lrp->res.seq_res))
+ if (!nfs41_sequence_process(task, &lrp->res.seq_res))
return;
server = NFS_SERVER(lrp->args.inode);
@@ -8118,6 +8183,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
case -NFS4ERR_DELAY:
if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
break;
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
rpc_restart_call_prepare(task);
return;
}
@@ -8132,12 +8198,16 @@ static void nfs4_layoutreturn_release(void *calldata)
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
- be32_to_cpu(lrp->args.stateid.seqid));
- if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
+ if (lrp->res.lrs_present) {
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme,
+ &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+ } else
+ pnfs_mark_layout_stateid_invalid(lo, &freeme);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&lo->plh_inode->i_lock);
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
pnfs_free_lseg_list(&freeme);
pnfs_put_layout_hdr(lrp->args.layout);
nfs_iput_and_deactive(lrp->inode);
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 332d06e64fa9..b62973045a3e 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -28,6 +28,7 @@ static void nfs4_init_slot_table(struct nfs4_slot_table *tbl, const char *queue)
tbl->highest_used_slotid = NFS4_NO_SLOT;
spin_lock_init(&tbl->slot_tbl_lock);
rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue);
+ init_waitqueue_head(&tbl->slot_waitq);
init_completion(&tbl->complete);
}
@@ -172,6 +173,58 @@ struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid)
return ERR_PTR(-E2BIG);
}
+static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid,
+ u32 *seq_nr)
+ __must_hold(&tbl->slot_tbl_lock)
+{
+ struct nfs4_slot *slot;
+
+ slot = nfs4_lookup_slot(tbl, slotid);
+ if (IS_ERR(slot))
+ return PTR_ERR(slot);
+ *seq_nr = slot->seq_nr;
+ return 0;
+}
+
+/*
+ * nfs4_slot_seqid_in_use - test if a slot sequence id is still in use
+ *
+ * Given a slot table, slot id and sequence number, determine if the
+ * RPC call in question is still in flight. This function is mainly
+ * intended for use by the callback channel.
+ */
+static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr)
+{
+ u32 cur_seq;
+ bool ret = false;
+
+ spin_lock(&tbl->slot_tbl_lock);
+ if (nfs4_slot_get_seqid(tbl, slotid, &cur_seq) == 0 &&
+ cur_seq == seq_nr && test_bit(slotid, tbl->used_slots))
+ ret = true;
+ spin_unlock(&tbl->slot_tbl_lock);
+ return ret;
+}
+
+/*
+ * nfs4_slot_wait_on_seqid - wait until a slot sequence id is complete
+ *
+ * Given a slot table, slot id and sequence number, wait until the
+ * corresponding RPC call completes. This function is mainly
+ * intended for use by the callback channel.
+ */
+int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout)
+{
+ if (wait_event_timeout(tbl->slot_waitq,
+ !nfs4_slot_seqid_in_use(tbl, slotid, seq_nr),
+ timeout) == 0)
+ return -ETIMEDOUT;
+ return 0;
+}
+
/*
* nfs4_alloc_slot - efficiently look for a free slot
*
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 5b51298d1d03..f703b755351b 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -21,7 +21,8 @@ struct nfs4_slot {
unsigned long generation;
u32 slot_nr;
u32 seq_nr;
- unsigned int interrupted : 1;
+ unsigned int interrupted : 1,
+ seq_done : 1;
};
/* Sessions */
@@ -36,6 +37,7 @@ struct nfs4_slot_table {
unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
spinlock_t slot_tbl_lock;
struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */
+ wait_queue_head_t slot_waitq; /* Completion wait on slot */
u32 max_slots; /* # slots in table */
u32 max_slotid; /* Max allowed slotid value */
u32 highest_used_slotid; /* sent to server on each SEQ.
@@ -78,6 +80,9 @@ extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout);
extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 70806cae0d36..2c93a85eda51 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -365,7 +365,8 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs)) {
- set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ if (atomic_read(&lo->plh_outstanding) == 0)
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
@@ -768,17 +769,32 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
pnfs_destroy_layouts_byclid(clp, false);
}
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+ lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
+ clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier = 0;
- bool invalid = !pnfs_layout_is_valid(lo);
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
- if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
+
+ if (!pnfs_layout_is_valid(lo)) {
+ nfs4_stateid_copy(&lo->plh_stateid, new);
+ lo->plh_barrier = newseq;
+ pnfs_clear_layoutreturn_info(lo);
+ clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ return;
+ }
+ if (pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
/*
* Because of wraparound, we want to keep the barrier
@@ -790,7 +806,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+ if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
@@ -886,19 +902,14 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
-static void
-pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
-{
- lo->plh_return_iomode = 0;
- lo->plh_return_seq = 0;
- clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-}
-
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
nfs4_stateid *stateid,
enum pnfs_iomode *iomode)
{
+ /* Serialise LAYOUTGET/LAYOUTRETURN */
+ if (atomic_read(&lo->plh_outstanding) != 0)
+ return false;
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
pnfs_get_layout_hdr(lo);
@@ -1555,6 +1566,7 @@ pnfs_update_layout(struct inode *ino,
}
lookup_again:
+ nfs4_client_recover_expired_lease(clp);
first = false;
spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
@@ -1797,16 +1809,11 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
*/
pnfs_mark_layout_stateid_invalid(lo, &free_me);
- nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
- lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+ pnfs_set_layout_stateid(lo, &res->stateid, true);
}
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg, &free_me);
- if (!pnfs_layout_is_valid(lo)) {
- pnfs_clear_layoutreturn_info(lo);
- clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- }
if (res->return_on_close)
@@ -2510,7 +2517,6 @@ pnfs_report_layoutstat(struct inode *inode, gfp_t gfp_flags)
data->args.fh = NFS_FH(inode);
data->args.inode = inode;
- nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid);
status = ld->prepare_layoutstats(&data->args);
if (status)
goto out_free;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 18d446e1a82b..d39601381adf 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -923,6 +923,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data) {
+ data->timeo = NFS_UNSPEC_TIMEO;
+ data->retrans = NFS_UNSPEC_RETRANS;
data->acregmin = NFS_DEF_ACREGMIN;
data->acregmax = NFS_DEF_ACREGMAX;
data->acdirmin = NFS_DEF_ACDIRMIN;
@@ -1189,6 +1191,19 @@ static int nfs_get_option_ul(substring_t args[], unsigned long *option)
return rc;
}
+static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option,
+ unsigned long l_bound, unsigned long u_bound)
+{
+ int ret;
+
+ ret = nfs_get_option_ul(args, option);
+ if (ret != 0)
+ return ret;
+ if (*option < l_bound || *option > u_bound)
+ return -ERANGE;
+ return 0;
+}
+
/*
* Error-check and convert a string of mount options from user space into
* a data structure. The whole mount string is processed; bad options are
@@ -1352,12 +1367,12 @@ static int nfs_parse_mount_options(char *raw,
mnt->bsize = option;
break;
case Opt_timeo:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX))
goto out_invalid_value;
mnt->timeo = option;
break;
case Opt_retrans:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX))
goto out_invalid_value;
mnt->retrans = option;
break;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d2f97ecca6a5..e0e5f7c3c99f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- wait_event(group->fanotify_data.access_waitq, event->response ||
- atomic_read(&group->fanotify_data.bypass_perm));
-
- if (!event->response) { /* bypass_perm set */
- /*
- * Event was canceled because group is being destroyed. Remove
- * it from group's event list because we are responsible for
- * freeing the permission event.
- */
- fsnotify_remove_event(group, &event->fae.fse);
- return 0;
- }
+ wait_event(group->fanotify_data.access_waitq, event->response);
/* userspace responded, convert to something usable */
switch (event->response) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8e8e6bcd1d43..a64313868d3a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_perm_event_info *event, *next;
+ struct fsnotify_event *fsn_event;
/*
- * There may be still new events arriving in the notification queue
- * but since userspace cannot use fanotify fd anymore, no event can
- * enter or leave access_list by now.
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
*/
- spin_lock(&group->fanotify_data.access_lock);
-
- atomic_inc(&group->fanotify_data.bypass_perm);
+ fsnotify_group_stop_queueing(group);
+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->fanotify_data.access_lock);
list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
fae.fse.list) {
pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
spin_unlock(&group->fanotify_data.access_lock);
/*
- * Since bypass_perm is set, newly queued events will not wait for
- * access response. Wake up the already sleeping ones now.
- * synchronize_srcu() in fsnotify_destroy_group() will wait for all
- * processes sleeping in fanotify_handle_event() waiting for access
- * response and thus also for all permission events to be freed.
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
*/
+ mutex_lock(&group->notification_mutex);
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ fsn_event = fsnotify_remove_first_event(group);
+ if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+ fsnotify_destroy_event(group, fsn_event);
+ else
+ FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ }
+ mutex_unlock(&group->notification_mutex);
+
+ /* Response for all permission events it set, wakeup waiters */
wake_up(&group->fanotify_data.access_waitq);
#endif
@@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
spin_lock_init(&group->fanotify_data.access_lock);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
- atomic_set(&group->fanotify_data.bypass_perm, 0);
#endif
switch (flags & FAN_ALL_CLASS_BITS) {
case FAN_CLASS_NOTIF:
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 3e2dd85be5dd..b47f7cfdcaa4 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
}
/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+ mutex_lock(&group->notification_mutex);
+ group->shutdown = true;
+ mutex_unlock(&group->notification_mutex);
+}
+
+/*
* Trying to get rid of a group. Remove all marks, flush all events and release
* the group reference.
* Note that another thread calling fsnotify_clear_marks_by_group() may still
@@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
*/
void fsnotify_destroy_group(struct fsnotify_group *group)
{
+ /*
+ * Stop queueing new events. The code below is careful enough to not
+ * require this but fanotify needs to stop queuing events even before
+ * fsnotify_destroy_group() is called and this makes the other callers
+ * of fsnotify_destroy_group() to see the same behavior.
+ */
+ fsnotify_group_stop_queueing(group);
+
/* clear all inode marks for this group, attach them to destroy_list */
fsnotify_detach_group_marks(group);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index a95d8e037aeb..e455e83ceeeb 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
* Add an event to the group notification queue. The group can later pull this
* event off the queue to deal with. The function returns 0 if the event was
* added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
*/
int fsnotify_add_event(struct fsnotify_group *group,
struct fsnotify_event *event,
@@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group,
mutex_lock(&group->notification_mutex);
+ if (group->shutdown) {
+ mutex_unlock(&group->notification_mutex);
+ return 2;
+ }
+
if (group->q_len >= group->max_events) {
ret = 2;
/* Queue overflow event only if it isn't already queued */
@@ -126,21 +132,6 @@ queue:
}
/*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
- struct fsnotify_event *event)
-{
- mutex_lock(&group->notification_mutex);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- group->q_len--;
- }
- mutex_unlock(&group->notification_mutex);
-}
-
-/*
* Remove and return the first event from the notification list. It is the
* responsibility of the caller to destroy the obtained event
*/
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 7dabbc31060e..f165f867f332 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5922,7 +5922,6 @@ bail:
}
static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
- handle_t *handle,
struct inode *data_alloc_inode,
struct buffer_head *data_alloc_bh)
{
@@ -5935,11 +5934,19 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
struct ocfs2_truncate_log *tl;
struct inode *tl_inode = osb->osb_tl_inode;
struct buffer_head *tl_bh = osb->osb_tl_bh;
+ handle_t *handle;
di = (struct ocfs2_dinode *) tl_bh->b_data;
tl = &di->id2.i_dealloc;
i = le16_to_cpu(tl->tl_used) - 1;
while (i >= 0) {
+ handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail;
+ }
+
/* Caller has given us at least enough credits to
* update the truncate log dinode */
status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
@@ -5974,12 +5981,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
}
}
- status = ocfs2_extend_trans(handle,
- OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
+ ocfs2_commit_trans(osb, handle);
i--;
}
@@ -5994,7 +5996,6 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
{
int status;
unsigned int num_to_flush;
- handle_t *handle;
struct inode *tl_inode = osb->osb_tl_inode;
struct inode *data_alloc_inode = NULL;
struct buffer_head *tl_bh = osb->osb_tl_bh;
@@ -6038,21 +6039,11 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (IS_ERR(handle)) {
- status = PTR_ERR(handle);
- mlog_errno(status);
- goto out_unlock;
- }
-
- status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
+ status = ocfs2_replay_truncate_records(osb, data_alloc_inode,
data_alloc_bh);
if (status < 0)
mlog_errno(status);
- ocfs2_commit_trans(osb, handle);
-
-out_unlock:
brelse(data_alloc_bh);
ocfs2_inode_unlock(data_alloc_inode, 1);
@@ -6413,43 +6404,34 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb,
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto out_unlock;
- }
-
while (head) {
if (head->free_bg)
bg_blkno = head->free_bg;
else
bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
head->free_bit);
+ handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto out_unlock;
+ }
+
trace_ocfs2_free_cached_blocks(
(unsigned long long)head->free_blk, head->free_bit);
ret = ocfs2_free_suballoc_bits(handle, inode, di_bh,
head->free_bit, bg_blkno, 1);
- if (ret) {
+ if (ret)
mlog_errno(ret);
- goto out_journal;
- }
- ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE);
- if (ret) {
- mlog_errno(ret);
- goto out_journal;
- }
+ ocfs2_commit_trans(osb, handle);
tmp = head;
head = head->free_next;
kfree(tmp);
}
-out_journal:
- ocfs2_commit_trans(osb, handle);
-
out_unlock:
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 98d36548153d..bbb4b3e5b4ff 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1842,6 +1842,16 @@ out_commit:
ocfs2_commit_trans(osb, handle);
out:
+ /*
+ * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(),
+ * even in case of error here like ENOSPC and ENOMEM. So, we need
+ * to unlock the target page manually to prevent deadlocks when
+ * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED
+ * to VM code.
+ */
+ if (wc->w_target_locked)
+ unlock_page(mmap_page);
+
ocfs2_free_write_ctxt(inode, wc);
if (data_ac) {
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index 94b18369b1cc..b95e7df5b76a 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -44,9 +44,6 @@
* version here in tcp_internal.h should not need to be bumped for
* filesystem locking changes.
*
- * New in version 12
- * - Negotiate hb timeout when storage is down.
- *
* New in version 11
* - Negotiation of filesystem locking in the dlm join.
*
@@ -78,7 +75,7 @@
* - full 64 bit i_size in the metadata lock lvbs
* - introduction of "rw" lock and pushing meta/data locking down
*/
-#define O2NET_PROTOCOL_VERSION 12ULL
+#define O2NET_PROTOCOL_VERSION 11ULL
struct o2net_handshake {
__be64 protocol_version;
__be64 connector_id;
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index cdeafb4e7ed6..0bb128659d4b 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
struct dlm_lock *lock, int flags, int type)
{
enum dlm_status status;
- u8 old_owner = res->owner;
mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
spin_lock(&res->spinlock);
res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
- lock->convert_pending = 0;
/* if it failed, move it back to granted queue.
* if master returns DLM_NORMAL and then down before sending ast,
* it may have already been moved to granted queue, reset to
@@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
if (status != DLM_NOTQUEUED)
dlm_error(status);
dlm_revert_pending_convert(res, lock);
- } else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
- (old_owner != res->owner)) {
- mlog(0, "res %.*s is in recovering or has been recovered.\n",
- res->lockname.len, res->lockname.name);
+ } else if (!lock->convert_pending) {
+ mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+ "to granted list, retry convert.\n",
+ dlm->name, res->lockname.len, res->lockname.name);
status = DLM_RECOVERING;
}
+
+ lock->convert_pending = 0;
bail:
spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 4e7b0dc22450..0b055bfb8e86 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1506,7 +1506,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
u64 start, u64 len)
{
int ret = 0;
- u64 tmpend, end = start + len;
+ u64 tmpend = 0;
+ u64 end = start + len;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
@@ -1538,18 +1539,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
}
/*
- * We want to get the byte offset of the end of the 1st cluster.
+ * If start is on a cluster boundary and end is somewhere in another
+ * cluster, we have not COWed the cluster starting at start, unless
+ * end is also within the same cluster. So, in this case, we skip this
+ * first call to ocfs2_zero_range_for_truncate() truncate and move on
+ * to the next one.
*/
- tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
- if (tmpend > end)
- tmpend = end;
+ if ((start & (csize - 1)) != 0) {
+ /*
+ * We want to get the byte offset of the end of the 1st
+ * cluster.
+ */
+ tmpend = (u64)osb->s_clustersize +
+ (start & ~(osb->s_clustersize - 1));
+ if (tmpend > end)
+ tmpend = end;
- trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
- (unsigned long long)tmpend);
+ trace_ocfs2_zero_partial_clusters_range1(
+ (unsigned long long)start,
+ (unsigned long long)tmpend);
- ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
- if (ret)
- mlog_errno(ret);
+ ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+ tmpend);
+ if (ret)
+ mlog_errno(ret);
+ }
if (tmpend < end) {
/*
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index ea47120a85ff..6ad3533940ba 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1199,14 +1199,24 @@ retry:
inode_unlock((*ac)->ac_inode);
ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
- if (ret == 1)
+ if (ret == 1) {
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
goto retry;
+ }
if (ret < 0)
mlog_errno(ret);
inode_lock((*ac)->ac_inode);
- ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ inode_unlock((*ac)->ac_inode);
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
+ goto bail;
+ }
}
if (status < 0) {
if (status != -ENOSPC)
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 54e5d6681786..db37a0e02d32 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -80,6 +80,8 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new)
}
for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+ if (ovl_is_private_xattr(name))
+ continue;
retry:
size = vfs_getxattr(old, name, value, value_size);
if (size == -ERANGE)
@@ -103,6 +105,13 @@ retry:
goto retry;
}
+ error = security_inode_copy_up_xattr(name);
+ if (error < 0 && error != -EOPNOTSUPP)
+ break;
+ if (error == 1) {
+ error = 0;
+ continue; /* Discard */
+ }
error = vfs_setxattr(new, name, value, size, 0);
if (error)
break;
@@ -246,6 +255,8 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
struct dentry *upper = NULL;
umode_t mode = stat->mode;
int err;
+ const struct cred *old_creds = NULL;
+ struct cred *new_creds = NULL;
newdentry = ovl_lookup_temp(workdir, dentry);
err = PTR_ERR(newdentry);
@@ -258,10 +269,23 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
if (IS_ERR(upper))
goto out1;
+ err = security_inode_copy_up(dentry, &new_creds);
+ if (err < 0)
+ goto out2;
+
+ if (new_creds)
+ old_creds = override_creds(new_creds);
+
/* Can't properly set mode on creation because of the umask */
stat->mode &= S_IFMT;
err = ovl_create_real(wdir, newdentry, stat, link, NULL, true);
stat->mode = mode;
+
+ if (new_creds) {
+ revert_creds(old_creds);
+ put_cred(new_creds);
+ }
+
if (err)
goto out2;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 12bcd07b9e32..b0ffa1d1677e 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -12,6 +12,8 @@
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/cred.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
#include "overlayfs.h"
void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
@@ -186,6 +188,9 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry;
int err;
+ if (!hardlink && !IS_POSIXACL(udir))
+ stat->mode &= ~current_umask();
+
inode_lock_nested(udir, I_MUTEX_PARENT);
newdentry = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
@@ -335,6 +340,32 @@ out_free:
return ret;
}
+static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
+ const struct posix_acl *acl)
+{
+ void *buffer;
+ size_t size;
+ int err;
+
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl)
+ return 0;
+
+ size = posix_acl_to_xattr(NULL, acl, NULL, 0);
+ buffer = kmalloc(size, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ size = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ err = size;
+ if (err < 0)
+ goto out_free;
+
+ err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE);
+out_free:
+ kfree(buffer);
+ return err;
+}
+
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
@@ -346,10 +377,18 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct dentry *upper;
struct dentry *newdentry;
int err;
+ struct posix_acl *acl, *default_acl;
if (WARN_ON(!workdir))
return -EROFS;
+ if (!hardlink) {
+ err = posix_acl_create(dentry->d_parent->d_inode,
+ &stat->mode, &default_acl, &acl);
+ if (err)
+ return err;
+ }
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
@@ -384,6 +423,17 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
if (err)
goto out_cleanup;
}
+ if (!hardlink) {
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_ACCESS,
+ acl);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_DEFAULT,
+ default_acl);
+ if (err)
+ goto out_cleanup;
+ }
if (!hardlink && S_ISDIR(stat->mode)) {
err = ovl_set_opaque(newdentry);
@@ -410,6 +460,10 @@ out_dput:
out_unlock:
unlock_rename(workdir, upperdir);
out:
+ if (!hardlink) {
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
+ }
return err;
out_cleanup:
@@ -435,6 +489,15 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
if (override_cred) {
override_cred->fsuid = inode->i_uid;
override_cred->fsgid = inode->i_gid;
+ if (!hardlink) {
+ err = security_dentry_create_files_as(dentry,
+ stat->mode, &dentry->d_name, old_cred,
+ override_cred);
+ if (err) {
+ put_cred(override_cred);
+ goto out_revert_creds;
+ }
+ }
put_cred(override_creds(override_cred));
put_cred(override_cred);
@@ -445,6 +508,7 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
err = ovl_create_over_whiteout(dentry, inode, stat,
link, hardlink);
}
+out_revert_creds:
revert_creds(old_cred);
if (!err) {
struct inode *realinode = d_inode(ovl_dentry_upper(dentry));
@@ -950,9 +1014,9 @@ const struct inode_operations ovl_dir_inode_operations = {
.permission = ovl_permission,
.getattr = ovl_dir_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 1b885c156028..c75625c1efa3 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -10,6 +10,7 @@
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/posix_acl.h>
#include "overlayfs.h"
static int ovl_copy_up_truncate(struct dentry *dentry)
@@ -191,32 +192,44 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
return err;
}
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
{
-#define OVL_XATTR_PRE_NAME OVL_XATTR_PREFIX "."
- return strncmp(name, OVL_XATTR_PRE_NAME,
- sizeof(OVL_XATTR_PRE_NAME) - 1) == 0;
+ return strncmp(name, OVL_XATTR_PREFIX,
+ sizeof(OVL_XATTR_PREFIX) - 1) == 0;
}
-int ovl_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
{
int err;
- struct dentry *upperdentry;
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
const struct cred *old_cred;
err = ovl_want_write(dentry);
if (err)
goto out;
+ if (!value && !OVL_TYPE_UPPER(type)) {
+ err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+ if (err < 0)
+ goto out_drop_write;
+ }
+
err = ovl_copy_up(dentry);
if (err)
goto out_drop_write;
- upperdentry = ovl_dentry_upper(dentry);
+ if (!OVL_TYPE_UPPER(type))
+ ovl_path_upper(dentry, &realpath);
+
old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_setxattr(upperdentry, name, value, size, flags);
+ if (value)
+ err = vfs_setxattr(realpath.dentry, name, value, size, flags);
+ else {
+ WARN_ON(flags != XATTR_REPLACE);
+ err = vfs_removexattr(realpath.dentry, name);
+ }
revert_creds(old_cred);
out_drop_write:
@@ -225,16 +238,13 @@ out:
return err;
}
-ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
+int ovl_xattr_get(struct dentry *dentry, const char *name,
+ void *value, size_t size)
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
const struct cred *old_cred;
- if (ovl_is_private_xattr(name))
- return -ENODATA;
-
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_getxattr(realdentry, name, value, size);
revert_creds(old_cred);
@@ -245,7 +255,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
- int off;
+ size_t len;
+ char *s;
const struct cred *old_cred;
old_cred = ovl_override_creds(dentry->d_sb);
@@ -255,73 +266,39 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
return res;
/* filter out private xattrs */
- for (off = 0; off < res;) {
- char *s = list + off;
- size_t slen = strlen(s) + 1;
+ for (s = list, len = res; len;) {
+ size_t slen = strnlen(s, len) + 1;
- BUG_ON(off + slen > res);
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > len))
+ return -EIO;
+ len -= slen;
if (ovl_is_private_xattr(s)) {
res -= slen;
- memmove(s, s + slen, res - off);
+ memmove(s, s + slen, len);
} else {
- off += slen;
+ s += slen;
}
}
return res;
}
-int ovl_removexattr(struct dentry *dentry, const char *name)
-{
- int err;
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
- const struct cred *old_cred;
-
- err = ovl_want_write(dentry);
- if (err)
- goto out;
-
- err = -ENODATA;
- if (ovl_is_private_xattr(name))
- goto out_drop_write;
-
- if (!OVL_TYPE_UPPER(type)) {
- err = vfs_getxattr(realpath.dentry, name, NULL, 0);
- if (err < 0)
- goto out_drop_write;
-
- err = ovl_copy_up(dentry);
- if (err)
- goto out_drop_write;
-
- ovl_path_upper(dentry, &realpath);
- }
-
- old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_removexattr(realpath.dentry, name);
- revert_creds(old_cred);
-out_drop_write:
- ovl_drop_write(dentry);
-out:
- return err;
-}
-
struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
struct inode *realinode = ovl_inode_real(inode, NULL);
const struct cred *old_cred;
struct posix_acl *acl;
- if (!IS_POSIXACL(realinode))
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
return NULL;
if (!realinode->i_op->get_acl)
return NULL;
old_cred = ovl_override_creds(inode->i_sb);
- acl = realinode->i_op->get_acl(realinode, type);
+ acl = get_acl(realinode, type);
revert_creds(old_cred);
return acl;
@@ -391,9 +368,9 @@ static const struct inode_operations ovl_file_inode_operations = {
.permission = ovl_permission,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
@@ -404,9 +381,9 @@ static const struct inode_operations ovl_symlink_inode_operations = {
.readlink = ovl_readlink,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.update_time = ovl_update_time,
};
@@ -415,6 +392,9 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode)
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_flags |= S_NOCMTIME;
+#ifdef CONFIG_FS_POSIX_ACL
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
+#endif
mode &= S_IFMT;
switch (mode) {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index e4f5c9536bfe..5813ccff8cd9 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -24,8 +24,8 @@ enum ovl_path_type {
(OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type))
-#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay"
-#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX ".opaque"
+#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
+#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
#define OVL_ISUPPER_MASK 1UL
@@ -179,20 +179,21 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
void ovl_cache_free(struct list_head *list);
int ovl_check_d_type_supported(struct path *realpath);
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level);
/* inode.c */
int ovl_setattr(struct dentry *dentry, struct iattr *attr);
int ovl_permission(struct inode *inode, int mask);
-int ovl_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags);
-ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size);
+int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags);
+int ovl_xattr_get(struct dentry *dentry, const char *name,
+ void *value, size_t size);
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
-int ovl_removexattr(struct dentry *dentry, const char *name);
struct posix_acl *ovl_get_acl(struct inode *inode, int type);
int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
+bool ovl_is_private_xattr(const char *name);
struct inode *ovl_new_inode(struct super_block *sb, umode_t mode);
struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode);
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index cf37fc76fc9f..f241b4ee3d8a 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -248,7 +248,7 @@ static inline int ovl_dir_read(struct path *realpath,
err = rdd->err;
} while (!err && rdd->count);
- if (!err && rdd->first_maybe_whiteout)
+ if (!err && rdd->first_maybe_whiteout && rdd->dentry)
err = ovl_check_whiteouts(realpath->dentry, rdd);
fput(realfile);
@@ -606,3 +606,64 @@ int ovl_check_d_type_supported(struct path *realpath)
return rdd.d_type_supported;
}
+
+static void ovl_workdir_cleanup_recurse(struct path *path, int level)
+{
+ int err;
+ struct inode *dir = path->dentry->d_inode;
+ LIST_HEAD(list);
+ struct ovl_cache_entry *p;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .dentry = NULL,
+ .list = &list,
+ .root = RB_ROOT,
+ .is_lowest = false,
+ };
+
+ err = ovl_dir_read(path, &rdd);
+ if (err)
+ goto out;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ list_for_each_entry(p, &list, l_node) {
+ struct dentry *dentry;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ dentry = lookup_one_len(p->name, path->dentry, p->len);
+ if (IS_ERR(dentry))
+ continue;
+ if (dentry->d_inode)
+ ovl_workdir_cleanup(dir, path->mnt, dentry, level);
+ dput(dentry);
+ }
+ inode_unlock(dir);
+out:
+ ovl_cache_free(&list);
+}
+
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level)
+{
+ int err;
+
+ if (!d_is_dir(dentry) || level > 1) {
+ ovl_cleanup(dir, dentry);
+ return;
+ }
+
+ err = ovl_do_rmdir(dir, dentry);
+ if (err) {
+ struct path path = { .mnt = mnt, .dentry = dentry };
+
+ inode_unlock(dir);
+ ovl_workdir_cleanup_recurse(&path, level + 1);
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ ovl_cleanup(dir, dentry);
+ }
+}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 4036132842b5..e2a94a26767b 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -814,6 +814,10 @@ retry:
struct kstat stat = {
.mode = S_IFDIR | 0,
};
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = stat.mode,
+ };
if (work->d_inode) {
err = -EEXIST;
@@ -821,7 +825,7 @@ retry:
goto out_dput;
retried = true;
- ovl_cleanup(dir, work);
+ ovl_workdir_cleanup(dir, mnt, work, 0);
dput(work);
goto retry;
}
@@ -829,6 +833,21 @@ retry:
err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
if (err)
goto out_dput;
+
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ /* Clear any inherited mode bits */
+ inode_lock(work->d_inode);
+ err = notify_change(work, &attr, NULL);
+ inode_unlock(work->d_inode);
+ if (err)
+ goto out_dput;
}
out_unlock:
inode_unlock(dir);
@@ -967,10 +986,19 @@ static unsigned int ovl_split_lowerdirs(char *str)
return ctr;
}
-static int ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+static int __maybe_unused
+ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ return ovl_xattr_get(dentry, handler->name, buffer, size);
+}
+
+static int __maybe_unused
+ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *realinode = ovl_inode_real(inode, NULL);
@@ -998,19 +1026,22 @@ static int ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
posix_acl_release(acl);
- return ovl_setxattr(dentry, inode, handler->name, value, size, flags);
+ err = ovl_xattr_set(dentry, handler->name, value, size, flags);
+ if (!err)
+ ovl_copyattr(ovl_inode_real(inode, NULL), inode);
+
+ return err;
out_acl_release:
posix_acl_release(acl);
return err;
}
-static int ovl_other_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+static int ovl_own_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ovl_setxattr(dentry, inode, name, value, size, flags);
+ return -EPERM;
}
static int ovl_own_xattr_set(const struct xattr_handler *handler,
@@ -1021,42 +1052,59 @@ static int ovl_own_xattr_set(const struct xattr_handler *handler,
return -EPERM;
}
-static const struct xattr_handler ovl_posix_acl_access_xattr_handler = {
+static int ovl_other_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ return ovl_xattr_get(dentry, name, buffer, size);
+}
+
+static int ovl_other_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ return ovl_xattr_set(dentry, name, value, size, flags);
+}
+
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_access_xattr_handler = {
.name = XATTR_NAME_POSIX_ACL_ACCESS,
.flags = ACL_TYPE_ACCESS,
+ .get = ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
-static const struct xattr_handler ovl_posix_acl_default_xattr_handler = {
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_default_xattr_handler = {
.name = XATTR_NAME_POSIX_ACL_DEFAULT,
.flags = ACL_TYPE_DEFAULT,
+ .get = ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
static const struct xattr_handler ovl_own_xattr_handler = {
.prefix = OVL_XATTR_PREFIX,
+ .get = ovl_own_xattr_get,
.set = ovl_own_xattr_set,
};
static const struct xattr_handler ovl_other_xattr_handler = {
.prefix = "", /* catch all */
+ .get = ovl_other_xattr_get,
.set = ovl_other_xattr_set,
};
static const struct xattr_handler *ovl_xattr_handlers[] = {
+#ifdef CONFIG_FS_POSIX_ACL
&ovl_posix_acl_access_xattr_handler,
&ovl_posix_acl_default_xattr_handler,
+#endif
&ovl_own_xattr_handler,
&ovl_other_xattr_handler,
NULL
};
-static const struct xattr_handler *ovl_xattr_noacl_handlers[] = {
- &ovl_own_xattr_handler,
- &ovl_other_xattr_handler,
- NULL,
-};
-
static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
struct path upperpath = { NULL, NULL };
@@ -1132,7 +1180,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
err = -EINVAL;
stacklen = ovl_split_lowerdirs(lowertmp);
if (stacklen > OVL_MAX_STACK) {
- pr_err("overlayfs: too many lower directries, limit is %d\n",
+ pr_err("overlayfs: too many lower directories, limit is %d\n",
OVL_MAX_STACK);
goto out_free_lowertmp;
} else if (!ufs->config.upperdir && stacklen == 1) {
@@ -1269,10 +1317,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
sb->s_magic = OVERLAYFS_SUPER_MAGIC;
sb->s_op = &ovl_super_operations;
- if (IS_ENABLED(CONFIG_FS_POSIX_ACL))
- sb->s_xattr = ovl_xattr_handlers;
- else
- sb->s_xattr = ovl_xattr_noacl_handlers;
+ sb->s_xattr = ovl_xattr_handlers;
sb->s_root = root_dentry;
sb->s_fs_info = ufs;
sb->s_flags |= MS_POSIXACL;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 54e270262979..3b792ab3c0dc 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -483,7 +483,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
save_stack_trace_tsk(task, &trace);
for (i = 0; i < trace.nr_entries; i++) {
- seq_printf(m, "[<%pK>] %pS\n",
+ seq_printf(m, "[<%pK>] %pB\n",
(void *)entries[i], (void *)entries[i]);
}
unlock_trace(task);
@@ -1556,18 +1556,13 @@ static const struct file_operations proc_pid_set_comm_operations = {
static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
- struct mm_struct *mm;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
- mm = get_task_mm(task);
+ exe_file = get_task_exe_file(task);
put_task_struct(task);
- if (!mm)
- return -ENOENT;
- exe_file = get_mm_exe_file(mm);
- mmput(mm);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index c633476616e0..bca66d83a765 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -390,6 +390,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
atomic_set(&ent->count, 1);
spin_lock_init(&ent->pde_unload_lock);
INIT_LIST_HEAD(&ent->pde_openers);
+ proc_set_user(ent, (*parent)->uid, (*parent)->gid);
+
out:
return ent;
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index a939f5ed7f89..5c89a07e3d7f 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -430,6 +430,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
static ssize_t
read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
{
+ char *buf = file->private_data;
ssize_t acc = 0;
size_t size, tsz;
size_t elf_buflen;
@@ -500,23 +501,20 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
if (clear_user(buffer, tsz))
return -EFAULT;
} else if (is_vmalloc_or_module_addr((void *)start)) {
- char * elf_buf;
-
- elf_buf = kzalloc(tsz, GFP_KERNEL);
- if (!elf_buf)
- return -ENOMEM;
- vread(elf_buf, (char *)start, tsz);
+ vread(buf, (char *)start, tsz);
/* we have to zero-fill user buffer even if no read */
- if (copy_to_user(buffer, elf_buf, tsz)) {
- kfree(elf_buf);
+ if (copy_to_user(buffer, buf, tsz))
return -EFAULT;
- }
- kfree(elf_buf);
} else {
if (kern_addr_valid(start)) {
unsigned long n;
- n = copy_to_user(buffer, (char *)start, tsz);
+ /*
+ * Using bounce buffer to bypass the
+ * hardened user copy kernel text checks.
+ */
+ memcpy(buf, (char *) start, tsz);
+ n = copy_to_user(buffer, buf, tsz);
/*
* We cannot distinguish between fault on source
* and fault on destination. When this happens
@@ -549,6 +547,11 @@ static int open_kcore(struct inode *inode, struct file *filp)
{
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
+
+ filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
@@ -559,10 +562,16 @@ static int open_kcore(struct inode *inode, struct file *filp)
return 0;
}
+static int release_kcore(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
static const struct file_operations proc_kcore_operations = {
.read = read_kcore,
.open = open_kcore,
+ .release = release_kcore,
.llseek = default_llseek,
};
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index c8bbc68cdb05..7ae6b1da7cab 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -21,6 +21,7 @@
#include <linux/bitops.h>
#include <linux/mount.h>
#include <linux/nsproxy.h>
+#include <linux/uidgid.h>
#include <net/net_namespace.h>
#include <linux/seq_file.h>
@@ -185,6 +186,8 @@ const struct file_operations proc_net_operations = {
static __net_init int proc_net_ns_init(struct net *net)
{
struct proc_dir_entry *netd, *net_statd;
+ kuid_t uid;
+ kgid_t gid;
int err;
err = -ENOMEM;
@@ -199,6 +202,16 @@ static __net_init int proc_net_ns_init(struct net *net)
netd->parent = &proc_root;
memcpy(netd->name, "net", 4);
+ uid = make_kuid(net->user_ns, 0);
+ if (!uid_valid(uid))
+ uid = netd->uid;
+
+ gid = make_kgid(net->user_ns, 0);
+ if (!gid_valid(gid))
+ gid = netd->gid;
+
+ proc_set_user(netd, uid, gid);
+
err = -EEXIST;
net_statd = proc_net_mkdir(net, "stat", netd);
if (!net_statd)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 1b93650dda2f..2ed3d71d4767 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -430,6 +430,7 @@ static int sysctl_perm(struct ctl_table_header *head, struct ctl_table *table, i
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
+ struct ctl_table_root *root = head->root;
struct inode *inode;
struct proc_inode *ei;
@@ -457,6 +458,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
if (is_empty_dir(head))
make_empty_dir_inode(inode);
}
+
+ if (root->set_ownership)
+ root->set_ownership(head, table, &inode->i_uid, &inode->i_gid);
+
out:
return inode;
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 187d84ef9de9..f6fa99eca515 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -581,6 +581,8 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
mss->anonymous_thp += HPAGE_PMD_SIZE;
else if (PageSwapBacked(page))
mss->shmem_thp += HPAGE_PMD_SIZE;
+ else if (is_zone_device_page(page))
+ /* pass */;
else
VM_BUG_ON_PAGE(1, page);
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 35df08ee9c97..2d445425aad7 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -341,6 +341,7 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs)
struct qc_state state;
int ret;
+ memset(&state, 0, sizeof (struct qc_state));
ret = sb->s_qcop->get_state(sb, &state);
if (ret < 0)
return ret;
@@ -365,17 +366,19 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs)
fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit;
fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit;
fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit;
- if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) {
+
+ /* Inodes may be allocated even if inactive; copy out if present */
+ if (state.s_state[USRQUOTA].ino) {
fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino;
fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks;
fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents;
}
- if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) {
+ if (state.s_state[GRPQUOTA].ino) {
fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino;
fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks;
fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents;
}
- if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) {
+ if (state.s_state[PRJQUOTA].ino) {
/*
* Q_XGETQSTAT doesn't have room for both group and project
* quotas. So, allow the project quota values to be copied out
@@ -411,6 +414,7 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs)
struct qc_state state;
int ret;
+ memset(&state, 0, sizeof (struct qc_state));
ret = sb->s_qcop->get_state(sb, &state);
if (ret < 0)
return ret;
@@ -435,17 +439,19 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs)
fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit;
fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit;
fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit;
- if (state.s_state[USRQUOTA].flags & QCI_ACCT_ENABLED) {
+
+ /* Inodes may be allocated even if inactive; copy out if present */
+ if (state.s_state[USRQUOTA].ino) {
fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino;
fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks;
fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents;
}
- if (state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED) {
+ if (state.s_state[GRPQUOTA].ino) {
fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino;
fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks;
fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents;
}
- if (state.s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED) {
+ if (state.s_state[PRJQUOTA].ino) {
fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino;
fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks;
fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents;
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
index 183a212694bf..12af0490322f 100644
--- a/fs/ramfs/file-mmu.c
+++ b/fs/ramfs/file-mmu.c
@@ -27,9 +27,17 @@
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/ramfs.h>
+#include <linux/sched.h>
#include "internal.h"
+static unsigned long ramfs_mmu_get_unmapped_area(struct file *file,
+ unsigned long addr, unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
const struct file_operations ramfs_file_operations = {
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
@@ -38,6 +46,7 @@ const struct file_operations ramfs_file_operations = {
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = generic_file_llseek,
+ .get_unmapped_area = ramfs_mmu_get_unmapped_area,
};
const struct inode_operations ramfs_file_inode_operations = {
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 7a4a85a6821e..74d5ddd26296 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -190,7 +190,15 @@ static int remove_save_link_only(struct super_block *s,
static int reiserfs_quota_on_mount(struct super_block *, int);
#endif
-/* look for uncompleted unlinks and truncates and complete them */
+/*
+ * Look for uncompleted unlinks and truncates and complete them
+ *
+ * Called with superblock write locked. If quotas are enabled, we have to
+ * release/retake lest we call dquot_quota_on_mount(), proceed to
+ * schedule_on_each_cpu() in invalidate_bdev() and deadlock waiting for the per
+ * cpu worklets to complete flush_async_commits() that in turn wait for the
+ * superblock write lock.
+ */
static int finish_unfinished(struct super_block *s)
{
INITIALIZE_PATH(path);
@@ -237,7 +245,9 @@ static int finish_unfinished(struct super_block *s)
quota_enabled[i] = 0;
continue;
}
+ reiserfs_write_unlock(s);
ret = reiserfs_quota_on_mount(s, i);
+ reiserfs_write_lock(s);
if (ret < 0)
reiserfs_warning(s, "reiserfs-2500",
"cannot turn on journaled "
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 19f532e7d35e..6dc4296eed62 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -223,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
size -= n;
buf += n;
copied += n;
- if (!m->count)
+ if (!m->count) {
+ m->from = 0;
m->index++;
+ }
if (!size)
goto Done;
}
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index f35523d4fa3a..b803213d1307 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -114,9 +114,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
* If buf != of->prealloc_buf, we don't know how
* large it is, so cannot safely pass it to ->show
*/
- if (pos || WARN_ON_ONCE(buf != of->prealloc_buf))
+ if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (pos) {
+ if (len <= pos)
+ return 0;
+ len -= pos;
+ memmove(buf, buf + pos, len);
+ }
return min(count, len);
}
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index dc1358b5ec95..ac2de0ed69ad 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -233,8 +233,8 @@ void sysfs_remove_group(struct kobject *kobj,
kn = kernfs_find_and_get(parent, grp->name);
if (!kn) {
WARN(!kn, KERN_WARNING
- "sysfs group %p not found for kobject '%s'\n",
- grp, kobject_name(kobj));
+ "sysfs group '%s' not found for kobject '%s'\n",
+ grp->name, kobject_name(kobj));
return;
}
} else {
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index b45345d701e7..51157da3f76e 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt)
p = c->gap_lebs;
do {
- ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+ ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
written = layout_leb_in_gaps(c, p);
if (written < 0) {
err = written;
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index e237811f09ce..11a004114eba 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -575,7 +575,8 @@ static int ubifs_xattr_get(const struct xattr_handler *handler,
dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
inode->i_ino, dentry, size);
- return __ubifs_getxattr(inode, name, buffer, size);
+ name = xattr_full_name(handler, name);
+ return __ubifs_getxattr(inode, name, buffer, size);
}
static int ubifs_xattr_set(const struct xattr_handler *handler,
@@ -586,6 +587,8 @@ static int ubifs_xattr_set(const struct xattr_handler *handler,
dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
name, inode->i_ino, dentry, size);
+ name = xattr_full_name(handler, name);
+
if (value)
return __ubifs_setxattr(inode, name, value, size, flags);
else
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 632570617327..e855bf8d74b4 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -94,7 +94,7 @@ static int udf_adinicb_write_begin(struct file *file,
return -ENOMEM;
*pagep = page;
- if (!PageUptodate(page) && len != PAGE_SIZE)
+ if (!PageUptodate(page))
__udf_adinicb_readpage(page);
return 0;
}
@@ -105,11 +105,25 @@ static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
return 0;
}
+static int udf_adinicb_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = page->mapping->host;
+ loff_t last_pos = pos + copied;
+ if (last_pos > inode->i_size)
+ i_size_write(inode, last_pos);
+ set_page_dirty(page);
+ unlock_page(page);
+ put_page(page);
+ return copied;
+}
+
const struct address_space_operations udf_adinicb_aops = {
.readpage = udf_adinicb_readpage,
.writepage = udf_adinicb_writepage,
.write_begin = udf_adinicb_write_begin,
- .write_end = simple_write_end,
+ .write_end = udf_adinicb_write_end,
.direct_IO = udf_adinicb_direct_IO,
};