summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/cell.c1
-rw-r--r--fs/afs/flock.c4
-rw-r--r--fs/afs/inode.c3
-rw-r--r--fs/afs/protocol_yfs.h11
-rw-r--r--fs/afs/rxrpc.c53
-rw-r--r--fs/afs/server_list.c4
-rw-r--r--fs/afs/yfsclient.c2
-rw-r--r--fs/aio.c85
-rw-r--r--fs/autofs/expire.c3
-rw-r--r--fs/autofs/inode.c4
-rw-r--r--fs/binfmt_script.c57
-rw-r--r--fs/block_dev.c28
-rw-r--r--fs/btrfs/ctree.c76
-rw-r--r--fs/btrfs/ctree.h7
-rw-r--r--fs/btrfs/disk-io.c12
-rw-r--r--fs/btrfs/extent-tree.c21
-rw-r--r--fs/btrfs/inode.c5
-rw-r--r--fs/btrfs/ioctl.c49
-rw-r--r--fs/btrfs/super.c3
-rw-r--r--fs/btrfs/transaction.c24
-rw-r--r--fs/btrfs/volumes.c16
-rw-r--r--fs/buffer.c19
-rw-r--r--fs/ceph/addr.c5
-rw-r--r--fs/ceph/caps.c2
-rw-r--r--fs/ceph/quota.c13
-rw-r--r--fs/ceph/snap.c3
-rw-r--r--fs/ceph/super.c4
-rw-r--r--fs/cifs/cifs_debug.c1
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h20
-rw-r--r--fs/cifs/cifssmb.c65
-rw-r--r--fs/cifs/connect.c28
-rw-r--r--fs/cifs/dfs_cache.c1
-rw-r--r--fs/cifs/file.c56
-rw-r--r--fs/cifs/inode.c10
-rw-r--r--fs/cifs/smb2file.c8
-rw-r--r--fs/cifs/smb2inode.c17
-rw-r--r--fs/cifs/smb2misc.c7
-rw-r--r--fs/cifs/smb2ops.c72
-rw-r--r--fs/cifs/smb2pdu.c108
-rw-r--r--fs/cifs/smb2pdu.h19
-rw-r--r--fs/cifs/trace.c10
-rw-r--r--fs/cifs/trace.h10
-rw-r--r--fs/cifs/transport.c113
-rw-r--r--fs/dcache.c38
-rw-r--r--fs/debugfs/inode.c36
-rw-r--r--fs/direct-io.c5
-rw-r--r--fs/dlm/lowcomms.c4
-rw-r--r--fs/drop_caches.c8
-rw-r--r--fs/exec.c2
-rw-r--r--fs/ext4/fsync.c13
-rw-r--r--fs/fs-writeback.c40
-rw-r--r--fs/fuse/dev.c4
-rw-r--r--fs/fuse/file.c2
-rw-r--r--fs/fuse/inode.c2
-rw-r--r--fs/gfs2/glops.c1
-rw-r--r--fs/gfs2/log.c4
-rw-r--r--fs/gfs2/lops.c190
-rw-r--r--fs/gfs2/lops.h4
-rw-r--r--fs/gfs2/ops_fstype.c1
-rw-r--r--fs/gfs2/recovery.c123
-rw-r--r--fs/gfs2/recovery.h2
-rw-r--r--fs/gfs2/rgrp.c2
-rw-r--r--fs/gfs2/super.c1
-rw-r--r--fs/hugetlbfs/inode.c73
-rw-r--r--fs/inode.c7
-rw-r--r--fs/iomap.c37
-rw-r--r--fs/kernfs/mount.c8
-rw-r--r--fs/namespace.c4
-rw-r--r--fs/nfs/nfs4file.c8
-rw-r--r--fs/nfs/nfs4idmap.c31
-rw-r--r--fs/nfs/super.c5
-rw-r--r--fs/nfs/write.c20
-rw-r--r--fs/nfsd/nfsctl.c4
-rw-r--r--fs/nfsd/vfs.c6
-rw-r--r--fs/notify/inotify/inotify_user.c6
-rw-r--r--fs/orangefs/file.c4
-rw-r--r--fs/proc/base.c4
-rw-r--r--fs/proc/generic.c4
-rw-r--r--fs/proc/internal.h1
-rw-r--r--fs/proc/proc_net.c20
-rw-r--r--fs/proc/task_mmu.c22
-rw-r--r--fs/pstore/ram.c12
-rw-r--r--fs/read_write.c6
-rw-r--r--fs/splice.c14
-rw-r--r--fs/sysfs/dir.c3
-rw-r--r--fs/sysfs/file.c6
-rw-r--r--fs/sysfs/group.c3
-rw-r--r--fs/sysfs/symlink.c3
-rw-r--r--fs/xfs/scrub/repair.c11
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_buf.c19
92 files changed, 1218 insertions, 668 deletions
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index cf445dbd5f2e..9de46116c749 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -173,6 +173,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
rcu_assign_pointer(cell->vl_servers, vllist);
cell->dns_expiry = TIME64_MAX;
+ __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags);
} else {
cell->dns_expiry = ktime_get_real_seconds();
}
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 0568fd986821..e432bd27a2e7 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -208,7 +208,7 @@ again:
/* The new front of the queue now owns the state variables. */
next = list_entry(vnode->pending_locks.next,
struct file_lock, fl_u.afs.link);
- vnode->lock_key = afs_file_key(next->fl_file);
+ vnode->lock_key = key_get(afs_file_key(next->fl_file));
vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB;
goto again;
@@ -413,7 +413,7 @@ static void afs_dequeue_lock(struct afs_vnode *vnode, struct file_lock *fl)
/* The new front of the queue now owns the state variables. */
next = list_entry(vnode->pending_locks.next,
struct file_lock, fl_u.afs.link);
- vnode->lock_key = afs_file_key(next->fl_file);
+ vnode->lock_key = key_get(afs_file_key(next->fl_file));
vnode->lock_type = (next->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE;
vnode->lock_state = AFS_VNODE_LOCK_WAITING_FOR_CB;
afs_lock_may_be_available(vnode);
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 6b17d3620414..1a4ce07fb406 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -414,7 +414,6 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
} else {
- vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
vnode->cb_v_break = vnode->volume->cb_v_break;
valid = false;
}
@@ -546,6 +545,8 @@ void afs_evict_inode(struct inode *inode)
#endif
afs_put_permits(rcu_access_pointer(vnode->permit_cache));
+ key_put(vnode->lock_key);
+ vnode->lock_key = NULL;
_leave("");
}
diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h
index 07bc10f076aa..d443e2bfa094 100644
--- a/fs/afs/protocol_yfs.h
+++ b/fs/afs/protocol_yfs.h
@@ -161,3 +161,14 @@ struct yfs_xdr_YFSStoreVolumeStatus {
struct yfs_xdr_u64 max_quota;
struct yfs_xdr_u64 file_quota;
} __packed;
+
+enum yfs_lock_type {
+ yfs_LockNone = -1,
+ yfs_LockRead = 0,
+ yfs_LockWrite = 1,
+ yfs_LockExtend = 2,
+ yfs_LockRelease = 3,
+ yfs_LockMandatoryRead = 0x100,
+ yfs_LockMandatoryWrite = 0x101,
+ yfs_LockMandatoryExtend = 0x102,
+};
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a7b44863d502..2c588f9bbbda 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -23,6 +23,7 @@ struct workqueue_struct *afs_async_calls;
static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
static long afs_wait_for_call_to_complete(struct afs_call *, struct afs_addr_cursor *);
static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
+static void afs_delete_async_call(struct work_struct *);
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);
@@ -203,20 +204,26 @@ void afs_put_call(struct afs_call *call)
}
}
+static struct afs_call *afs_get_call(struct afs_call *call,
+ enum afs_call_trace why)
+{
+ int u = atomic_inc_return(&call->usage);
+
+ trace_afs_call(call, why, u,
+ atomic_read(&call->net->nr_outstanding_calls),
+ __builtin_return_address(0));
+ return call;
+}
+
/*
* Queue the call for actual work.
*/
static void afs_queue_call_work(struct afs_call *call)
{
if (call->type->work) {
- int u = atomic_inc_return(&call->usage);
-
- trace_afs_call(call, afs_call_trace_work, u,
- atomic_read(&call->net->nr_outstanding_calls),
- __builtin_return_address(0));
-
INIT_WORK(&call->work, call->type->work);
+ afs_get_call(call, afs_call_trace_work);
if (!queue_work(afs_wq, &call->work))
afs_put_call(call);
}
@@ -398,6 +405,12 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
}
}
+ /* If the call is going to be asynchronous, we need an extra ref for
+ * the call to hold itself so the caller need not hang on to its ref.
+ */
+ if (call->async)
+ afs_get_call(call, afs_call_trace_get);
+
/* create a call */
rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key,
(unsigned long)call,
@@ -438,15 +451,17 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
goto error_do_abort;
}
- /* at this point, an async call may no longer exist as it may have
- * already completed */
- if (call->async)
+ /* Note that at this point, we may have received the reply or an abort
+ * - and an asynchronous call may already have completed.
+ */
+ if (call->async) {
+ afs_put_call(call);
return -EINPROGRESS;
+ }
return afs_wait_for_call_to_complete(call, ac);
error_do_abort:
- call->state = AFS_CALL_COMPLETE;
if (ret != -ECONNABORTED) {
rxrpc_kernel_abort_call(call->net->socket, rxcall,
RX_USER_ABORT, ret, "KSD");
@@ -463,8 +478,24 @@ error_do_abort:
error_kill_call:
if (call->type->done)
call->type->done(call);
- afs_put_call(call);
+
+ /* We need to dispose of the extra ref we grabbed for an async call.
+ * The call, however, might be queued on afs_async_calls and we need to
+ * make sure we don't get any more notifications that might requeue it.
+ */
+ if (call->rxcall) {
+ rxrpc_kernel_end_call(call->net->socket, call->rxcall);
+ call->rxcall = NULL;
+ }
+ if (call->async) {
+ if (cancel_work_sync(&call->async_work))
+ afs_put_call(call);
+ afs_put_call(call);
+ }
+
ac->error = ret;
+ call->state = AFS_CALL_COMPLETE;
+ afs_put_call(call);
_leave(" = %d", ret);
return ret;
}
diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 95d0761cdb34..155dc14caef9 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -42,9 +42,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
if (vldb->fs_mask[i] & type_mask)
nr_servers++;
- slist = kzalloc(sizeof(struct afs_server_list) +
- sizeof(struct afs_server_entry) * nr_servers,
- GFP_KERNEL);
+ slist = kzalloc(struct_size(slist, servers, nr_servers), GFP_KERNEL);
if (!slist)
goto error;
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 12658c1363ae..5aa57929e8c2 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -803,7 +803,7 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc,
bp = xdr_encode_YFSFid(bp, &vnode->fid);
bp = xdr_encode_string(bp, name, namesz);
bp = xdr_encode_YFSStoreStatus_mode(bp, mode);
- bp = xdr_encode_u32(bp, 0); /* ViceLockType */
+ bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */
yfs_check_req(call, bp);
afs_use_fs_server(call, fc->cbi);
diff --git a/fs/aio.c b/fs/aio.c
index b906ff70c90f..3d9669d011b9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -167,9 +167,13 @@ struct kioctx {
unsigned id;
};
+/*
+ * First field must be the file pointer in all the
+ * iocb unions! See also 'struct kiocb' in <linux/fs.h>
+ */
struct fsync_iocb {
- struct work_struct work;
struct file *file;
+ struct work_struct work;
bool datasync;
};
@@ -183,8 +187,15 @@ struct poll_iocb {
struct work_struct work;
};
+/*
+ * NOTE! Each of the iocb union members has the file pointer
+ * as the first entry in their struct definition. So you can
+ * access the file pointer through any of the sub-structs,
+ * or directly as just 'ki_filp' in this struct.
+ */
struct aio_kiocb {
union {
+ struct file *ki_filp;
struct kiocb rw;
struct fsync_iocb fsync;
struct poll_iocb poll;
@@ -1060,6 +1071,8 @@ static inline void iocb_put(struct aio_kiocb *iocb)
{
if (refcount_read(&iocb->ki_refcnt) == 0 ||
refcount_dec_and_test(&iocb->ki_refcnt)) {
+ if (iocb->ki_filp)
+ fput(iocb->ki_filp);
percpu_ref_put(&iocb->ki_ctx->reqs);
kmem_cache_free(kiocb_cachep, iocb);
}
@@ -1424,7 +1437,6 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
file_end_write(kiocb->ki_filp);
}
- fput(kiocb->ki_filp);
aio_complete(iocb, res, res2);
}
@@ -1432,10 +1444,8 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
{
int ret;
- req->ki_filp = fget(iocb->aio_fildes);
- if (unlikely(!req->ki_filp))
- return -EBADF;
req->ki_complete = aio_complete_rw;
+ req->private = NULL;
req->ki_pos = iocb->aio_offset;
req->ki_flags = iocb_flags(req->ki_filp);
if (iocb->aio_flags & IOCB_FLAG_RESFD)
@@ -1450,7 +1460,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
ret = ioprio_check_cap(iocb->aio_reqprio);
if (ret) {
pr_debug("aio ioprio check cap error: %d\n", ret);
- goto out_fput;
+ return ret;
}
req->ki_ioprio = iocb->aio_reqprio;
@@ -1459,14 +1469,10 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags);
if (unlikely(ret))
- goto out_fput;
+ return ret;
req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */
return 0;
-
-out_fput:
- fput(req->ki_filp);
- return ret;
}
static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec,
@@ -1520,24 +1526,19 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
if (ret)
return ret;
file = req->ki_filp;
-
- ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_READ)))
- goto out_fput;
+ return -EBADF;
ret = -EINVAL;
if (unlikely(!file->f_op->read_iter))
- goto out_fput;
+ return -EINVAL;
ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter);
if (ret)
- goto out_fput;
+ return ret;
ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret)
aio_rw_done(req, call_read_iter(file, req, &iter));
kfree(iovec);
-out_fput:
- if (unlikely(ret))
- fput(file);
return ret;
}
@@ -1554,16 +1555,14 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
return ret;
file = req->ki_filp;
- ret = -EBADF;
if (unlikely(!(file->f_mode & FMODE_WRITE)))
- goto out_fput;
- ret = -EINVAL;
+ return -EBADF;
if (unlikely(!file->f_op->write_iter))
- goto out_fput;
+ return -EINVAL;
ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter);
if (ret)
- goto out_fput;
+ return ret;
ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter));
if (!ret) {
/*
@@ -1581,9 +1580,6 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
aio_rw_done(req, call_write_iter(file, req, &iter));
}
kfree(iovec);
-out_fput:
- if (unlikely(ret))
- fput(file);
return ret;
}
@@ -1593,7 +1589,6 @@ static void aio_fsync_work(struct work_struct *work)
int ret;
ret = vfs_fsync(req->file, req->datasync);
- fput(req->file);
aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
}
@@ -1604,13 +1599,8 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
iocb->aio_rw_flags))
return -EINVAL;
- req->file = fget(iocb->aio_fildes);
- if (unlikely(!req->file))
- return -EBADF;
- if (unlikely(!req->file->f_op->fsync)) {
- fput(req->file);
+ if (unlikely(!req->file->f_op->fsync))
return -EINVAL;
- }
req->datasync = datasync;
INIT_WORK(&req->work, aio_fsync_work);
@@ -1620,10 +1610,7 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
{
- struct file *file = iocb->poll.file;
-
aio_complete(iocb, mangle_poll(mask), 0);
- fput(file);
}
static void aio_poll_complete_work(struct work_struct *work)
@@ -1679,6 +1666,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
__poll_t mask = key_to_poll(key);
+ unsigned long flags;
req->woken = true;
@@ -1687,10 +1675,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
if (!(mask & req->events))
return 0;
- /* try to complete the iocb inline if we can: */
- if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+ /*
+ * Try to complete the iocb inline if we can. Use
+ * irqsave/irqrestore because not all filesystems (e.g. fuse)
+ * call this function with IRQs disabled and because IRQs
+ * have to be disabled before ctx_lock is obtained.
+ */
+ if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
list_del(&iocb->ki_list);
- spin_unlock(&iocb->ki_ctx->ctx_lock);
+ spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
list_del_init(&req->wait.entry);
aio_poll_complete(iocb, mask);
@@ -1742,9 +1735,6 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
INIT_WORK(&req->work, aio_poll_complete_work);
req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
- req->file = fget(iocb->aio_fildes);
- if (unlikely(!req->file))
- return -EBADF;
req->head = NULL;
req->woken = false;
@@ -1787,10 +1777,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
spin_unlock_irq(&ctx->ctx_lock);
out:
- if (unlikely(apt.error)) {
- fput(req->file);
+ if (unlikely(apt.error))
return apt.error;
- }
if (mask)
aio_poll_complete(aiocb, mask);
@@ -1828,6 +1816,11 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
if (unlikely(!req))
goto out_put_reqs_available;
+ req->ki_filp = fget(iocb->aio_fildes);
+ ret = -EBADF;
+ if (unlikely(!req->ki_filp))
+ goto out_put_req;
+
if (iocb->aio_flags & IOCB_FLAG_RESFD) {
/*
* If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c
index d441244b79df..28d9c2b1b3bb 100644
--- a/fs/autofs/expire.c
+++ b/fs/autofs/expire.c
@@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb,
pkt.len = dentry->d_name.len;
memcpy(pkt.name, dentry->d_name.name, pkt.len);
pkt.name[pkt.len] = '\0';
- dput(dentry);
if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
ret = -EFAULT;
@@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb,
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
+ dput(dentry);
+
return ret;
}
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index 0e8ea2d9a2bb..078992eee299 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
}
root_inode = autofs_get_inode(s, S_IFDIR | 0755);
root = d_make_root(root_inode);
- if (!root)
+ if (!root) {
+ ret = -ENOMEM;
goto fail_ino;
+ }
pipe = NULL;
root->d_fsdata = ino;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index d0078cbb718b..e996174cbfc0 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -14,13 +14,30 @@
#include <linux/err.h>
#include <linux/fs.h>
+static inline bool spacetab(char c) { return c == ' ' || c == '\t'; }
+static inline char *next_non_spacetab(char *first, const char *last)
+{
+ for (; first <= last; first++)
+ if (!spacetab(*first))
+ return first;
+ return NULL;
+}
+static inline char *next_terminator(char *first, const char *last)
+{
+ for (; first <= last; first++)
+ if (spacetab(*first) || !*first)
+ return first;
+ return NULL;
+}
+
static int load_script(struct linux_binprm *bprm)
{
const char *i_arg, *i_name;
- char *cp;
+ char *cp, *buf_end;
struct file *file;
int retval;
+ /* Not ours to exec if we don't start with "#!". */
if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
return -ENOEXEC;
@@ -33,23 +50,41 @@ static int load_script(struct linux_binprm *bprm)
if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
return -ENOENT;
- /*
- * This section does the #! interpretation.
- * Sorta complicated, but hopefully it will work. -TYT
- */
-
+ /* Release since we are not mapping a binary into memory. */
allow_write_access(bprm->file);
fput(bprm->file);
bprm->file = NULL;
- for (cp = bprm->buf+2;; cp++) {
- if (cp >= bprm->buf + BINPRM_BUF_SIZE)
+ /*
+ * This section handles parsing the #! line into separate
+ * interpreter path and argument strings. We must be careful
+ * because bprm->buf is not yet guaranteed to be NUL-terminated
+ * (though the buffer will have trailing NUL padding when the
+ * file size was smaller than the buffer size).
+ *
+ * We do not want to exec a truncated interpreter path, so either
+ * we find a newline (which indicates nothing is truncated), or
+ * we find a space/tab/NUL after the interpreter path (which
+ * itself may be preceded by spaces/tabs). Truncating the
+ * arguments is fine: the interpreter can re-read the script to
+ * parse them on its own.
+ */
+ buf_end = bprm->buf + sizeof(bprm->buf) - 1;
+ cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n');
+ if (!cp) {
+ cp = next_non_spacetab(bprm->buf + 2, buf_end);
+ if (!cp)
+ return -ENOEXEC; /* Entire buf is spaces/tabs */
+ /*
+ * If there is no later space/tab/NUL we must assume the
+ * interpreter path is truncated.
+ */
+ if (!next_terminator(cp, buf_end))
return -ENOEXEC;
- if (!*cp || (*cp == '\n'))
- break;
+ cp = buf_end;
}
+ /* NUL-terminate the buffer and any trailing spaces/tabs. */
*cp = '\0';
-
while (cp > bprm->buf) {
cp--;
if ((*cp == ' ') || (*cp == '\t'))
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c546cdce77e6..58a4c1217fa8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev)
}
EXPORT_SYMBOL(invalidate_bdev);
+static void set_init_blocksize(struct block_device *bdev)
+{
+ unsigned bsize = bdev_logical_block_size(bdev);
+ loff_t size = i_size_read(bdev->bd_inode);
+
+ while (bsize < PAGE_SIZE) {
+ if (size & bsize)
+ break;
+ bsize <<= 1;
+ }
+ bdev->bd_block_size = bsize;
+ bdev->bd_inode->i_blkbits = blksize_bits(bsize);
+}
+
int set_blocksize(struct block_device *bdev, int size)
{
/* Size must be a power of two, and between 512 and PAGE_SIZE */
@@ -1431,18 +1445,9 @@ EXPORT_SYMBOL(check_disk_change);
void bd_set_size(struct block_device *bdev, loff_t size)
{
- unsigned bsize = bdev_logical_block_size(bdev);
-
inode_lock(bdev->bd_inode);
i_size_write(bdev->bd_inode, size);
inode_unlock(bdev->bd_inode);
- while (bsize < PAGE_SIZE) {
- if (size & bsize)
- break;
- bsize <<= 1;
- }
- bdev->bd_block_size = bsize;
- bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
EXPORT_SYMBOL(bd_set_size);
@@ -1519,8 +1524,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
}
}
- if (!ret)
+ if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+ set_init_blocksize(bdev);
+ }
/*
* If the device is invalidated, rescan partition
@@ -1555,6 +1562,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
goto out_clear;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+ set_init_blocksize(bdev);
}
if (bdev->bd_bdi == &noop_backing_dev_info)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d92462fe66c8..5a6c39b44c84 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
return 0;
}
+static struct extent_buffer *alloc_tree_block_no_bg_flush(
+ struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 parent_start,
+ const struct btrfs_disk_key *disk_key,
+ int level,
+ u64 hint,
+ u64 empty_size)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct extent_buffer *ret;
+
+ /*
+ * If we are COWing a node/leaf from the extent, chunk, device or free
+ * space trees, make sure that we do not finish block group creation of
+ * pending block groups. We do this to avoid a deadlock.
+ * COWing can result in allocation of a new chunk, and flushing pending
+ * block groups (btrfs_create_pending_block_groups()) can be triggered
+ * when finishing allocation of a new chunk. Creation of a pending block
+ * group modifies the extent, chunk, device and free space trees,
+ * therefore we could deadlock with ourselves since we are holding a
+ * lock on an extent buffer that btrfs_create_pending_block_groups() may
+ * try to COW later.
+ * For similar reasons, we also need to delay flushing pending block
+ * groups when splitting a leaf or node, from one of those trees, since
+ * we are holding a write lock on it and its parent or when inserting a
+ * new root node for one of those trees.
+ */
+ if (root == fs_info->extent_root ||
+ root == fs_info->chunk_root ||
+ root == fs_info->dev_root ||
+ root == fs_info->free_space_root)
+ trans->can_flush_pending_bgs = false;
+
+ ret = btrfs_alloc_tree_block(trans, root, parent_start,
+ root->root_key.objectid, disk_key, level,
+ hint, empty_size);
+ trans->can_flush_pending_bgs = true;
+
+ return ret;
+}
+
/*
* does the dirty work in cow of a single block. The parent block (if
* supplied) is updated to point to the new cow copy. The new buffer is marked
@@ -1015,26 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
parent_start = parent->start;
- /*
- * If we are COWing a node/leaf from the extent, chunk or device trees,
- * make sure that we do not finish block group creation of pending block
- * groups. We do this to avoid a deadlock.
- * COWing can result in allocation of a new chunk, and flushing pending
- * block groups (btrfs_create_pending_block_groups()) can be triggered
- * when finishing allocation of a new chunk. Creation of a pending block
- * group modifies the extent, chunk and device trees, therefore we could
- * deadlock with ourselves since we are holding a lock on an extent
- * buffer that btrfs_create_pending_block_groups() may try to COW later.
- */
- if (root == fs_info->extent_root ||
- root == fs_info->chunk_root ||
- root == fs_info->dev_root)
- trans->can_flush_pending_bgs = false;
-
- cow = btrfs_alloc_tree_block(trans, root, parent_start,
- root->root_key.objectid, &disk_key, level,
- search_start, empty_size);
- trans->can_flush_pending_bgs = true;
+ cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
+ level, search_start, empty_size);
if (IS_ERR(cow))
return PTR_ERR(cow);
@@ -3343,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
else
btrfs_node_key(lower, &lower_key, 0);
- c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &lower_key, level, root->node->start, 0);
+ c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
+ root->node->start, 0);
if (IS_ERR(c))
return PTR_ERR(c);
@@ -3473,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
mid = (c_nritems + 1) / 2;
btrfs_node_key(c, &disk_key, mid);
- split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &disk_key, level, c->start, 0);
+ split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
+ c->start, 0);
if (IS_ERR(split))
return PTR_ERR(split);
@@ -4258,8 +4282,8 @@ again:
else
btrfs_item_key(l, &disk_key, mid);
- right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
- &disk_key, 0, l->start, 0);
+ right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
+ l->start, 0);
if (IS_ERR(right))
return PTR_ERR(right);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0a68cf7032f5..7a2a2621f0d9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -35,6 +35,7 @@
struct btrfs_trans_handle;
struct btrfs_transaction;
struct btrfs_pending_snapshot;
+struct btrfs_delayed_ref_root;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
@@ -786,6 +787,9 @@ enum {
* main phase. The fs_info::balance_ctl is initialized.
*/
BTRFS_FS_BALANCE_RUNNING,
+
+ /* Indicate that the cleaner thread is awake and doing something. */
+ BTRFS_FS_CLEANER_RUNNING,
};
struct btrfs_fs_info {
@@ -2661,6 +2665,9 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
unsigned long count);
int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info,
unsigned long count, u64 transid, int wait);
+void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head);
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8da2f380d3c0..6a2a2a951705 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1682,6 +1682,8 @@ static int cleaner_kthread(void *arg)
while (1) {
again = 0;
+ set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+
/* Make the cleaner go to sleep early. */
if (btrfs_need_cleaner_sleep(fs_info))
goto sleep;
@@ -1728,6 +1730,7 @@ static int cleaner_kthread(void *arg)
*/
btrfs_delete_unused_bgs(fs_info);
sleep:
+ clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
if (kthread_should_park())
kthread_parkme();
if (kthread_should_stop())
@@ -4201,6 +4204,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
spin_lock(&fs_info->ordered_root_lock);
}
spin_unlock(&fs_info->ordered_root_lock);
+
+ /*
+ * We need this here because if we've been flipped read-only we won't
+ * get sync() from the umount, so we need to make sure any ordered
+ * extents that haven't had their dirty pages IO start writeout yet
+ * actually get run and error out properly.
+ */
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
}
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
@@ -4265,6 +4276,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
if (pin_bytes)
btrfs_pin_extent(fs_info, head->bytenr,
head->num_bytes, 1);
+ btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);
btrfs_put_delayed_ref_head(head);
cond_resched();
spin_lock(&delayed_refs->lock);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b15afeae16df..d81035b7ea7d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2456,12 +2456,10 @@ static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans,
return ret ? ret : 1;
}
-static void cleanup_ref_head_accounting(struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head)
+void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head)
{
- struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_delayed_ref_root *delayed_refs =
- &trans->transaction->delayed_refs;
int nr_items = 1; /* Dropping this ref head update. */
if (head->total_ref_mod < 0) {
@@ -2544,7 +2542,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
}
}
- cleanup_ref_head_accounting(trans, head);
+ btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);
trace_run_delayed_ref_head(fs_info, head, 0);
btrfs_delayed_ref_unlock(head);
@@ -4954,6 +4952,15 @@ static void flush_space(struct btrfs_fs_info *fs_info,
ret = 0;
break;
case COMMIT_TRANS:
+ /*
+ * If we have pending delayed iputs then we could free up a
+ * bunch of pinned space, so make sure we run the iputs before
+ * we do our pinned bytes check below.
+ */
+ mutex_lock(&fs_info->cleaner_delayed_iput_mutex);
+ btrfs_run_delayed_iputs(fs_info);
+ mutex_unlock(&fs_info->cleaner_delayed_iput_mutex);
+
ret = may_commit_transaction(fs_info, space_info);
break;
default:
@@ -7188,7 +7195,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
if (head->must_insert_reserved)
ret = 1;
- cleanup_ref_head_accounting(trans, head);
+ btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head);
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref_head(head);
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 43eb4535319d..5c349667c761 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3129,9 +3129,6 @@ out:
/* once for the tree */
btrfs_put_ordered_extent(ordered_extent);
- /* Try to release some metadata so we don't get an OOM but don't wait */
- btrfs_btree_balance_dirty_nodelay(fs_info);
-
return ret;
}
@@ -3254,6 +3251,8 @@ void btrfs_add_delayed_iput(struct inode *inode)
ASSERT(list_empty(&binode->delayed_iput));
list_add_tail(&binode->delayed_iput, &fs_info->delayed_iputs);
spin_unlock(&fs_info->delayed_iput_lock);
+ if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags))
+ wake_up_process(fs_info->cleaner_kthread);
}
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fab9443f6a42..9c8e1734429c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3221,6 +3221,26 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
inode_lock_nested(inode2, I_MUTEX_CHILD);
}
+static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+ unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
+static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ if (inode1 < inode2) {
+ swap(inode1, inode2);
+ swap(loff1, loff2);
+ } else if (inode1 == inode2 && loff2 < loff1) {
+ swap(loff1, loff2);
+ }
+ lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+ lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
struct inode *dst, u64 dst_loff)
{
@@ -3242,11 +3262,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
return -EINVAL;
/*
- * Lock destination range to serialize with concurrent readpages().
+ * Lock destination range to serialize with concurrent readpages() and
+ * source range to serialize with relocation.
*/
- lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+ btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
- unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+ btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
return ret;
}
@@ -3905,17 +3926,33 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
len = ALIGN(src->i_size, bs) - off;
if (destoff > inode->i_size) {
+ const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);
+
ret = btrfs_cont_expand(inode, inode->i_size, destoff);
if (ret)
return ret;
+ /*
+ * We may have truncated the last block if the inode's size is
+ * not sector size aligned, so we need to wait for writeback to
+ * complete before proceeding further, otherwise we can race
+ * with cloning and attempt to increment a reference to an
+ * extent that no longer exists (writeback completed right after
+ * we found the previous extent covering eof and before we
+ * attempted to increment its reference count).
+ */
+ ret = btrfs_wait_ordered_range(inode, wb_start,
+ destoff - wb_start);
+ if (ret)
+ return ret;
}
/*
- * Lock destination range to serialize with concurrent readpages().
+ * Lock destination range to serialize with concurrent readpages() and
+ * source range to serialize with relocation.
*/
- lock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+ btrfs_double_extent_lock(src, off, inode, destoff, len);
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
- unlock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+ btrfs_double_extent_unlock(src, off, inode, destoff, len);
/*
* Truncate page cache pages so that future reads will see the cloned
* data immediately and not the previous data.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index c5586ffd1426..0a3f122dd61f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1621,6 +1621,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
flags | SB_RDONLY, device_name, data);
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
@@ -1630,12 +1631,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
if (error < 0) {
root = ERR_PTR(error);
mntput(mnt_root);
+ kfree(subvol_name);
goto out;
}
}
}
if (IS_ERR(mnt_root)) {
root = ERR_CAST(mnt_root);
+ kfree(subvol_name);
goto out;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 127fa1535f58..4ec2b660d014 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
btrfs_trans_release_chunk_metadata(trans);
- if (lock && should_end_transaction(trans) &&
- READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
- spin_lock(&info->trans_lock);
- if (cur_trans->state == TRANS_STATE_RUNNING)
- cur_trans->state = TRANS_STATE_BLOCKED;
- spin_unlock(&info->trans_lock);
- }
-
if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
if (throttle)
return btrfs_commit_transaction(trans);
@@ -1879,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
kmem_cache_free(btrfs_trans_handle_cachep, trans);
}
+/*
+ * Release reserved delayed ref space of all pending block groups of the
+ * transaction and remove them from the list
+ */
+static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_block_group_cache *block_group, *tmp;
+
+ list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+ btrfs_delayed_refs_rsv_release(fs_info, 1);
+ list_del_init(&block_group->bg_list);
+ }
+}
+
static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{
/*
@@ -2270,6 +2277,7 @@ scrub_continue:
btrfs_scrub_continue(fs_info);
cleanup_transaction:
btrfs_trans_release_metadata(trans);
+ btrfs_cleanup_pending_block_groups(trans);
btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
btrfs_warn(fs_info, "Skipping commit of aborted transaction.");
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2576b1a379c9..15561926ab32 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
else
fs_devices = alloc_fs_devices(disk_super->fsid, NULL);
- fs_devices->fsid_change = fsid_change_in_progress;
-
if (IS_ERR(fs_devices))
return ERR_CAST(fs_devices);
+ fs_devices->fsid_change = fsid_change_in_progress;
+
mutex_lock(&fs_devices->device_list_mutex);
list_add(&fs_devices->fs_list, &fs_uuids);
@@ -7825,6 +7825,18 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
ret = -EUCLEAN;
goto out;
}
+
+ /* It's possible this device is a dummy for seed device */
+ if (dev->disk_total_bytes == 0) {
+ dev = find_device(fs_info->fs_devices->seed, devid, NULL);
+ if (!dev) {
+ btrfs_err(fs_info, "failed to find seed devid %llu",
+ devid);
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+
if (physical_offset + physical_len > dev->disk_total_bytes) {
btrfs_err(fs_info,
"dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu",
diff --git a/fs/buffer.c b/fs/buffer.c
index 52d024bfdbc1..48318fb74938 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
struct buffer_head *head;
struct page *page;
int all_mapped = 1;
+ static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1);
index = block >> (PAGE_SHIFT - bd_inode->i_blkbits);
page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED);
@@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
* file io on the block device and getblk. It gets dealt with
* elsewhere, don't buffer_error if we had some unmapped buffers
*/
- if (all_mapped) {
- printk("__find_get_block_slow() failed. "
- "block=%llu, b_blocknr=%llu\n",
- (unsigned long long)block,
- (unsigned long long)bh->b_blocknr);
- printk("b_state=0x%08lx, b_size=%zu\n",
- bh->b_state, bh->b_size);
- printk("device %pg blocksize: %d\n", bdev,
- 1 << bd_inode->i_blkbits);
+ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE);
+ if (all_mapped && __ratelimit(&last_warned)) {
+ printk("__find_get_block_slow() failed. block=%llu, "
+ "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, "
+ "device %pg blocksize: %d\n",
+ (unsigned long long)block,
+ (unsigned long long)bh->b_blocknr,
+ bh->b_state, bh->b_size, bdev,
+ 1 << bd_inode->i_blkbits);
}
out_unlock:
spin_unlock(&bd_mapping->private_lock);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 5d0c05e288cc..a47c541f8006 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1494,10 +1494,7 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
if (err < 0 || off >= i_size_read(inode)) {
unlock_page(page);
put_page(page);
- if (err == -ENOMEM)
- ret = VM_FAULT_OOM;
- else
- ret = VM_FAULT_SIGBUS;
+ ret = vmf_error(err);
goto out_inline;
}
if (err < PAGE_SIZE)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 94c026bba2c2..bba28a5034ba 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1035,6 +1035,8 @@ static void drop_inode_snap_realm(struct ceph_inode_info *ci)
list_del_init(&ci->i_snap_realm_item);
ci->i_snap_realm_counter++;
ci->i_snap_realm = NULL;
+ if (realm->ino == ci->i_vino.ino)
+ realm->inode = NULL;
spin_unlock(&realm->inodes_with_caps_lock);
ceph_put_snap_realm(ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc,
realm);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 03f4d24db8fe..9455d3aef0c3 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -3,19 +3,6 @@
* quota.c - CephFS quota
*
* Copyright (C) 2017-2018 SUSE
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/statfs.h>
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 041c27ea8de1..f74193da0e09 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -616,7 +616,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
capsnap->size);
spin_lock(&mdsc->snap_flush_lock);
- list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
+ if (list_empty(&ci->i_snap_flush_item))
+ list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
spin_unlock(&mdsc->snap_flush_lock);
return 1; /* caller may want to ceph_flush_snaps */
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4e9a7cc488da..da2cd8e89062 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -530,7 +530,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_putc(m, ',');
pos = m->count;
- ret = ceph_print_client_options(m, fsc->client);
+ ret = ceph_print_client_options(m, fsc->client, false);
if (ret)
return ret;
@@ -640,7 +640,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
opt = NULL; /* fsc->client now owns this */
fsc->client->extra_mon_dispatch = extra_mon_dispatch;
- fsc->client->osdc.abort_on_full = true;
+ ceph_set_opt(fsc->client, ABORT_ON_FULL);
if (!fsopt->mds_namespace) {
ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP,
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 593fb422d0f3..e92a2fee3c57 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -252,6 +252,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
seq_printf(m, ",ACL");
#endif
seq_putc(m, '\n');
+ seq_printf(m, "CIFSMaxBufSize: %d\n", CIFSMaxBufSize);
seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
seq_printf(m, "Servers:");
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 26776eddd85d..7652551a1fc4 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.15"
+#define CIFS_VERSION "2.17"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 01ded7038b19..94dbdbe5be34 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1438,6 +1438,7 @@ struct mid_q_entry {
int mid_state; /* wish this were enum but can not pass to wait_event */
unsigned int mid_flags;
__le16 command; /* smb command code */
+ unsigned int optype; /* operation type */
bool large_buf:1; /* if valid response, is pointer to large buf */
bool multiRsp:1; /* multiple trans2 responses for one request */
bool multiEnd:1; /* both received */
@@ -1574,6 +1575,25 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
kfree(param);
}
+static inline bool is_interrupt_error(int error)
+{
+ switch (error) {
+ case -EINTR:
+ case -ERESTARTSYS:
+ case -ERESTARTNOHAND:
+ case -ERESTARTNOINTR:
+ return true;
+ }
+ return false;
+}
+
+static inline bool is_retryable_error(int error)
+{
+ if (is_interrupt_error(error) || error == -EAGAIN)
+ return true;
+ return false;
+}
+
#define MID_FREE 0
#define MID_REQUEST_ALLOCATED 1
#define MID_REQUEST_SUBMITTED 2
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index b1f49c1c543a..bb54ccf8481c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -128,24 +128,31 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc,
int rc;
struct dfs_cache_tgt_list tl;
struct dfs_cache_tgt_iterator *it = NULL;
- char tree[MAX_TREE_SIZE + 1];
+ char *tree;
const char *tcp_host;
size_t tcp_host_len;
const char *dfs_host;
size_t dfs_host_len;
+ tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL);
+ if (!tree)
+ return -ENOMEM;
+
if (tcon->ipc) {
- snprintf(tree, sizeof(tree), "\\\\%s\\IPC$",
+ snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$",
tcon->ses->server->hostname);
- return CIFSTCon(0, tcon->ses, tree, tcon, nlsc);
+ rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc);
+ goto out;
}
- if (!tcon->dfs_path)
- return CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc);
+ if (!tcon->dfs_path) {
+ rc = CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc);
+ goto out;
+ }
rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl);
if (rc)
- return rc;
+ goto out;
extract_unc_hostname(tcon->ses->server->hostname, &tcp_host,
&tcp_host_len);
@@ -165,7 +172,7 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc,
continue;
}
- snprintf(tree, sizeof(tree), "\\%s", tgt);
+ snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt);
rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc);
if (!rc)
@@ -182,6 +189,8 @@ static int __cifs_reconnect_tcon(const struct nls_table *nlsc,
rc = -ENOENT;
}
dfs_cache_free_tgts(&tl);
+out:
+ kfree(tree);
return rc;
}
#else
@@ -1540,18 +1549,26 @@ cifs_discard_remaining_data(struct TCP_Server_Info *server)
}
static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+__cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid,
+ bool malformed)
{
int length;
- struct cifs_readdata *rdata = mid->callback_data;
length = cifs_discard_remaining_data(server);
- dequeue_mid(mid, rdata->result);
+ dequeue_mid(mid, malformed);
mid->resp_buf = server->smallbuf;
server->smallbuf = NULL;
return length;
}
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+ struct cifs_readdata *rdata = mid->callback_data;
+
+ return __cifs_readv_discard(server, mid, rdata->result);
+}
+
int
cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
{
@@ -1593,12 +1610,23 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
return -1;
}
+ /* set up first two iov for signature check and to get credits */
+ rdata->iov[0].iov_base = buf;
+ rdata->iov[0].iov_len = 4;
+ rdata->iov[1].iov_base = buf + 4;
+ rdata->iov[1].iov_len = server->total_read - 4;
+ cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
+ rdata->iov[0].iov_base, rdata->iov[0].iov_len);
+ cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n",
+ rdata->iov[1].iov_base, rdata->iov[1].iov_len);
+
/* Was the SMB read successful? */
rdata->result = server->ops->map_error(buf, false);
if (rdata->result != 0) {
cifs_dbg(FYI, "%s: server returned error %d\n",
__func__, rdata->result);
- return cifs_readv_discard(server, mid);
+ /* normal error on read response */
+ return __cifs_readv_discard(server, mid, false);
}
/* Is there enough to get to the rest of the READ_RSP header? */
@@ -1642,14 +1670,6 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
server->total_read += length;
}
- /* set up first iov for signature check */
- rdata->iov[0].iov_base = buf;
- rdata->iov[0].iov_len = 4;
- rdata->iov[1].iov_base = buf + 4;
- rdata->iov[1].iov_len = server->total_read - 4;
- cifs_dbg(FYI, "0: iov_base=%p iov_len=%u\n",
- rdata->iov[0].iov_base, server->total_read);
-
/* how much data is in the response? */
#ifdef CONFIG_CIFS_SMB_DIRECT
use_rdma_mr = rdata->mr;
@@ -2114,7 +2134,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
for (j = 0; j < nr_pages; j++) {
unlock_page(wdata2->pages[j]);
- if (rc != 0 && rc != -EAGAIN) {
+ if (rc != 0 && !is_retryable_error(rc)) {
SetPageError(wdata2->pages[j]);
end_page_writeback(wdata2->pages[j]);
put_page(wdata2->pages[j]);
@@ -2123,7 +2143,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
if (rc) {
kref_put(&wdata2->refcount, cifs_writedata_release);
- if (rc == -EAGAIN)
+ if (is_retryable_error(rc))
continue;
break;
}
@@ -2132,7 +2152,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
i += nr_pages;
} while (i < wdata->nr_pages);
- mapping_set_error(inode->i_mapping, rc);
+ if (rc != 0 && !is_retryable_error(rc))
+ mapping_set_error(inode->i_mapping, rc);
kref_put(&wdata->refcount, cifs_writedata_release);
}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f66529679ca2..8463c940e0e5 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -433,9 +433,10 @@ static void reconn_inval_dfs_target(struct TCP_Server_Info *server,
kfree(server->hostname);
server->hostname = extract_hostname(name);
- if (!server->hostname) {
- cifs_dbg(FYI, "%s: failed to extract hostname from target: %d\n",
- __func__, -ENOMEM);
+ if (IS_ERR(server->hostname)) {
+ cifs_dbg(FYI,
+ "%s: failed to extract hostname from target: %ld\n",
+ __func__, PTR_ERR(server->hostname));
}
}
@@ -719,6 +720,21 @@ server_unresponsive(struct TCP_Server_Info *server)
return false;
}
+static inline bool
+zero_credits(struct TCP_Server_Info *server)
+{
+ int val;
+
+ spin_lock(&server->req_lock);
+ val = server->credits + server->echo_credits + server->oplock_credits;
+ if (server->in_flight == 0 && val == 0) {
+ spin_unlock(&server->req_lock);
+ return true;
+ }
+ spin_unlock(&server->req_lock);
+ return false;
+}
+
static int
cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
{
@@ -731,6 +747,12 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
for (total_read = 0; msg_data_left(smb_msg); total_read += length) {
try_to_freeze();
+ /* reconnect if no credits and no requests in flight */
+ if (zero_credits(server)) {
+ cifs_reconnect(server);
+ return -ECONNABORTED;
+ }
+
if (server_unresponsive(server))
return -ECONNABORTED;
if (cifs_rdma_enabled(server) && server->smbd_conn)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index cd63c4a70875..09b7d0d4f6e4 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -776,6 +776,7 @@ static int get_tgt_list(const struct dfs_cache_entry *ce,
it->it_name = kstrndup(t->t_name, strlen(t->t_name),
GFP_KERNEL);
if (!it->it_name) {
+ kfree(it);
rc = -ENOMEM;
goto err_free_it;
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index e3e3a7550205..659ce1b92c44 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -733,7 +733,8 @@ reopen_success:
if (can_flush) {
rc = filemap_write_and_wait(inode->i_mapping);
- mapping_set_error(inode->i_mapping, rc);
+ if (!is_interrupt_error(rc))
+ mapping_set_error(inode->i_mapping, rc);
if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path,
@@ -1132,14 +1133,18 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
/*
* Accessing maxBuf is racy with cifs_reconnect - need to store value
- * and check it for zero before using.
+ * and check it before using.
*/
max_buf = tcon->ses->server->maxBuf;
- if (!max_buf) {
+ if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) {
free_xid(xid);
return -EINVAL;
}
+ BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
+ PAGE_SIZE);
+ max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
+ PAGE_SIZE);
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
@@ -1472,12 +1477,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
/*
* Accessing maxBuf is racy with cifs_reconnect - need to store value
- * and check it for zero before using.
+ * and check it before using.
*/
max_buf = tcon->ses->server->maxBuf;
- if (!max_buf)
+ if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE)))
return -EINVAL;
+ BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) >
+ PAGE_SIZE);
+ max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr),
+ PAGE_SIZE);
max_num = (max_buf - sizeof(struct smb_hdr)) /
sizeof(LOCKING_ANDX_RANGE);
buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
@@ -2110,6 +2119,7 @@ static int cifs_writepages(struct address_space *mapping,
pgoff_t end, index;
struct cifs_writedata *wdata;
int rc = 0;
+ int saved_rc = 0;
unsigned int xid;
/*
@@ -2138,8 +2148,10 @@ retry:
rc = server->ops->wait_mtu_credits(server, cifs_sb->wsize,
&wsize, &credits);
- if (rc)
+ if (rc != 0) {
+ done = true;
break;
+ }
tofind = min((wsize / PAGE_SIZE) - 1, end - index) + 1;
@@ -2147,6 +2159,7 @@ retry:
&found_pages);
if (!wdata) {
rc = -ENOMEM;
+ done = true;
add_credits_and_wake_if(server, credits, 0);
break;
}
@@ -2175,7 +2188,7 @@ retry:
if (rc != 0) {
add_credits_and_wake_if(server, wdata->credits, 0);
for (i = 0; i < nr_pages; ++i) {
- if (rc == -EAGAIN)
+ if (is_retryable_error(rc))
redirty_page_for_writepage(wbc,
wdata->pages[i]);
else
@@ -2183,7 +2196,7 @@ retry:
end_page_writeback(wdata->pages[i]);
put_page(wdata->pages[i]);
}
- if (rc != -EAGAIN)
+ if (!is_retryable_error(rc))
mapping_set_error(mapping, rc);
}
kref_put(&wdata->refcount, cifs_writedata_release);
@@ -2193,6 +2206,15 @@ retry:
continue;
}
+ /* Return immediately if we received a signal during writing */
+ if (is_interrupt_error(rc)) {
+ done = true;
+ break;
+ }
+
+ if (rc != 0 && saved_rc == 0)
+ saved_rc = rc;
+
wbc->nr_to_write -= nr_pages;
if (wbc->nr_to_write <= 0)
done = true;
@@ -2210,6 +2232,9 @@ retry:
goto retry;
}
+ if (saved_rc != 0)
+ rc = saved_rc;
+
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
@@ -2242,8 +2267,8 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
set_page_writeback(page);
retry_write:
rc = cifs_partialpagewrite(page, 0, PAGE_SIZE);
- if (rc == -EAGAIN) {
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (is_retryable_error(rc)) {
+ if (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN)
goto retry_write;
redirty_page_for_writepage(wbc, page);
} else if (rc != 0) {
@@ -2671,6 +2696,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
if (rc) {
+ kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
@@ -2682,6 +2708,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
if (rc) {
for (i = 0; i < nr_pages; i++)
put_page(wdata->pages[i]);
+ kvfree(wdata->pages);
kfree(wdata);
add_credits_and_wake_if(server, credits, 0);
break;
@@ -3361,8 +3388,12 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
}
rc = cifs_read_allocate_pages(rdata, npages);
- if (rc)
- goto error;
+ if (rc) {
+ kvfree(rdata->pages);
+ kfree(rdata);
+ add_credits_and_wake_if(server, credits, 0);
+ break;
+ }
rdata->tailsz = PAGE_SIZE;
}
@@ -3382,7 +3413,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
if (!rdata->cfile->invalidHandle ||
!(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
-error:
if (rc) {
add_credits_and_wake_if(server, rdata->credits, 0);
kref_put(&rdata->refcount,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 13fb59aadebc..478003644916 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2257,6 +2257,11 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
* the flush returns error?
*/
rc = filemap_write_and_wait(inode->i_mapping);
+ if (is_interrupt_error(rc)) {
+ rc = -ERESTARTSYS;
+ goto out;
+ }
+
mapping_set_error(inode->i_mapping, rc);
rc = 0;
@@ -2400,6 +2405,11 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
* the flush returns error?
*/
rc = filemap_write_and_wait(inode->i_mapping);
+ if (is_interrupt_error(rc)) {
+ rc = -ERESTARTSYS;
+ goto cifs_setattr_exit;
+ }
+
mapping_set_error(inode->i_mapping, rc);
rc = 0;
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 4ed10dd086e6..b204e84b87fb 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -122,12 +122,14 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
/*
* Accessing maxBuf is racy with cifs_reconnect - need to store value
- * and check it for zero before using.
+ * and check it before using.
*/
max_buf = tcon->ses->server->maxBuf;
- if (!max_buf)
+ if (max_buf < sizeof(struct smb2_lock_element))
return -EINVAL;
+ BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE);
+ max_buf = min_t(unsigned int, max_buf, PAGE_SIZE);
max_num = max_buf / sizeof(struct smb2_lock_element);
buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
if (!buf)
@@ -264,6 +266,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
return -EINVAL;
}
+ BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE);
+ max_buf = min_t(unsigned int, max_buf, PAGE_SIZE);
max_num = max_buf / sizeof(struct smb2_lock_element);
buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
if (!buf) {
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index f14533da3a93..01a76bccdb8d 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -293,6 +293,8 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
int rc;
struct smb2_file_all_info *smb2_data;
__u32 create_options = 0;
+ struct cifs_fid fid;
+ bool no_cached_open = tcon->nohandlecache;
*adjust_tz = false;
*symlink = false;
@@ -301,6 +303,21 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
GFP_KERNEL);
if (smb2_data == NULL)
return -ENOMEM;
+
+ /* If it is a root and its handle is cached then use it */
+ if (!strlen(full_path) && !no_cached_open) {
+ rc = open_shroot(xid, tcon, &fid);
+ if (rc)
+ goto out;
+ rc = SMB2_query_info(xid, tcon, fid.persistent_fid,
+ fid.volatile_fid, smb2_data);
+ close_shroot(&tcon->crfid);
+ if (rc)
+ goto out;
+ move_smb2_info_to_cifs(data, smb2_data);
+ goto out;
+ }
+
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 6a9c47541c53..7b8b58fb4d3f 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -648,6 +648,13 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
if (rsp->sync_hdr.Command != SMB2_OPLOCK_BREAK)
return false;
+ if (rsp->sync_hdr.CreditRequest) {
+ spin_lock(&server->req_lock);
+ server->credits += le16_to_cpu(rsp->sync_hdr.CreditRequest);
+ spin_unlock(&server->req_lock);
+ wake_up(&server->request_q);
+ }
+
if (rsp->StructureSize !=
smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) {
if (le16_to_cpu(rsp->StructureSize) == 44)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index cf7eb891804f..6f96e2292856 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -34,6 +34,7 @@
#include "cifs_ioctl.h"
#include "smbdirect.h"
+/* Change credits for different ops and return the total number of credits */
static int
change_conf(struct TCP_Server_Info *server)
{
@@ -41,17 +42,15 @@ change_conf(struct TCP_Server_Info *server)
server->oplock_credits = server->echo_credits = 0;
switch (server->credits) {
case 0:
- return -1;
+ return 0;
case 1:
server->echoes = false;
server->oplocks = false;
- cifs_dbg(VFS, "disabling echoes and oplocks\n");
break;
case 2:
server->echoes = true;
server->oplocks = false;
server->echo_credits = 1;
- cifs_dbg(FYI, "disabling oplocks\n");
break;
default:
server->echoes = true;
@@ -64,14 +63,15 @@ change_conf(struct TCP_Server_Info *server)
server->echo_credits = 1;
}
server->credits -= server->echo_credits + server->oplock_credits;
- return 0;
+ return server->credits + server->echo_credits + server->oplock_credits;
}
static void
smb2_add_credits(struct TCP_Server_Info *server, const unsigned int add,
const int optype)
{
- int *val, rc = 0;
+ int *val, rc = -1;
+
spin_lock(&server->req_lock);
val = server->ops->get_credits_field(server, optype);
@@ -101,8 +101,26 @@ smb2_add_credits(struct TCP_Server_Info *server, const unsigned int add,
}
spin_unlock(&server->req_lock);
wake_up(&server->request_q);
- if (rc)
- cifs_reconnect(server);
+
+ if (server->tcpStatus == CifsNeedReconnect)
+ return;
+
+ switch (rc) {
+ case -1:
+ /* change_conf hasn't been executed */
+ break;
+ case 0:
+ cifs_dbg(VFS, "Possible client or server bug - zero credits\n");
+ break;
+ case 1:
+ cifs_dbg(VFS, "disabling echoes and oplocks\n");
+ break;
+ case 2:
+ cifs_dbg(FYI, "disabling oplocks\n");
+ break;
+ default:
+ cifs_dbg(FYI, "add %u credits total=%d\n", add, rc);
+ }
}
static void
@@ -136,7 +154,11 @@ smb2_get_credits(struct mid_q_entry *mid)
{
struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)mid->resp_buf;
- return le16_to_cpu(shdr->CreditRequest);
+ if (mid->mid_state == MID_RESPONSE_RECEIVED
+ || mid->mid_state == MID_RESPONSE_MALFORMED)
+ return le16_to_cpu(shdr->CreditRequest);
+
+ return 0;
}
static int
@@ -165,14 +187,14 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size,
scredits = server->credits;
/* can deadlock with reopen */
- if (scredits == 1) {
+ if (scredits <= 8) {
*num = SMB2_MAX_BUFFER_SIZE;
*credits = 0;
break;
}
- /* leave one credit for a possible reopen */
- scredits--;
+ /* leave some credits for reopen and other ops */
+ scredits -= 8;
*num = min_t(unsigned int, size,
scredits * SMB2_MAX_BUFFER_SIZE);
@@ -844,7 +866,9 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
FILE_READ_EA,
FILE_FULL_EA_INFORMATION,
SMB2_O_INFO_FILE,
- SMB2_MAX_EA_BUF,
+ CIFSMaxBufSize -
+ MAX_SMB2_CREATE_RESPONSE_SIZE -
+ MAX_SMB2_CLOSE_RESPONSE_SIZE,
&rsp_iov, &buftype, cifs_sb);
if (rc) {
/*
@@ -3189,11 +3213,23 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
server->ops->is_status_pending(buf, server, 0))
return -1;
- rdata->result = server->ops->map_error(buf, false);
+ /* set up first two iov to get credits */
+ rdata->iov[0].iov_base = buf;
+ rdata->iov[0].iov_len = 4;
+ rdata->iov[1].iov_base = buf + 4;
+ rdata->iov[1].iov_len =
+ min_t(unsigned int, buf_len, server->vals->read_rsp_size) - 4;
+ cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
+ rdata->iov[0].iov_base, rdata->iov[0].iov_len);
+ cifs_dbg(FYI, "1: iov_base=%p iov_len=%zu\n",
+ rdata->iov[1].iov_base, rdata->iov[1].iov_len);
+
+ rdata->result = server->ops->map_error(buf, true);
if (rdata->result != 0) {
cifs_dbg(FYI, "%s: server returned error %d\n",
__func__, rdata->result);
- dequeue_mid(mid, rdata->result);
+ /* normal error on read response */
+ dequeue_mid(mid, false);
return 0;
}
@@ -3266,14 +3302,6 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
return 0;
}
- /* set up first iov for signature check */
- rdata->iov[0].iov_base = buf;
- rdata->iov[0].iov_len = 4;
- rdata->iov[1].iov_base = buf + 4;
- rdata->iov[1].iov_len = server->vals->read_rsp_size - 4;
- cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
- rdata->iov[0].iov_base, server->vals->read_rsp_size);
-
length = rdata->copy_into_pages(server, rdata, &iter);
kfree(bvec);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index e57f6aa1d638..77b3aaa39b35 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -162,24 +162,31 @@ static int __smb2_reconnect(const struct nls_table *nlsc,
int rc;
struct dfs_cache_tgt_list tl;
struct dfs_cache_tgt_iterator *it = NULL;
- char tree[MAX_TREE_SIZE + 1];
+ char *tree;
const char *tcp_host;
size_t tcp_host_len;
const char *dfs_host;
size_t dfs_host_len;
+ tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL);
+ if (!tree)
+ return -ENOMEM;
+
if (tcon->ipc) {
- snprintf(tree, sizeof(tree), "\\\\%s\\IPC$",
+ snprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$",
tcon->ses->server->hostname);
- return SMB2_tcon(0, tcon->ses, tree, tcon, nlsc);
+ rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc);
+ goto out;
}
- if (!tcon->dfs_path)
- return SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc);
+ if (!tcon->dfs_path) {
+ rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc);
+ goto out;
+ }
rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl);
if (rc)
- return rc;
+ goto out;
extract_unc_hostname(tcon->ses->server->hostname, &tcp_host,
&tcp_host_len);
@@ -199,7 +206,7 @@ static int __smb2_reconnect(const struct nls_table *nlsc,
continue;
}
- snprintf(tree, sizeof(tree), "\\%s", tgt);
+ snprintf(tree, MAX_TREE_SIZE, "\\%s", tgt);
rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc);
if (!rc)
@@ -216,6 +223,8 @@ static int __smb2_reconnect(const struct nls_table *nlsc,
rc = -ENOENT;
}
dfs_cache_free_tgts(&tl);
+out:
+ kfree(tree);
return rc;
}
#else
@@ -2807,6 +2816,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
int resp_buftype = CIFS_NO_BUFFER;
struct cifs_ses *ses = tcon->ses;
int flags = 0;
+ bool allocated = false;
cifs_dbg(FYI, "Query Info\n");
@@ -2846,14 +2856,21 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
"Error %d allocating memory for acl\n",
rc);
*dlen = 0;
+ rc = -ENOMEM;
goto qinf_exit;
}
+ allocated = true;
}
}
rc = smb2_validate_and_copy_iov(le16_to_cpu(rsp->OutputBufferOffset),
le32_to_cpu(rsp->OutputBufferLength),
&rsp_iov, min_len, *data);
+ if (rc && allocated) {
+ kfree(*data);
+ *data = NULL;
+ *dlen = 0;
+ }
qinf_exit:
SMB2_query_info_free(&rqst);
@@ -2907,9 +2924,10 @@ smb2_echo_callback(struct mid_q_entry *mid)
{
struct TCP_Server_Info *server = mid->callback_data;
struct smb2_echo_rsp *rsp = (struct smb2_echo_rsp *)mid->resp_buf;
- unsigned int credits_received = 1;
+ unsigned int credits_received = 0;
- if (mid->mid_state == MID_RESPONSE_RECEIVED)
+ if (mid->mid_state == MID_RESPONSE_RECEIVED
+ || mid->mid_state == MID_RESPONSE_MALFORMED)
credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
DeleteMidQEntry(mid);
@@ -3166,7 +3184,7 @@ smb2_readv_callback(struct mid_q_entry *mid)
struct TCP_Server_Info *server = tcon->ses->server;
struct smb2_sync_hdr *shdr =
(struct smb2_sync_hdr *)rdata->iov[0].iov_base;
- unsigned int credits_received = 1;
+ unsigned int credits_received = 0;
struct smb_rqst rqst = { .rq_iov = rdata->iov,
.rq_nvec = 2,
.rq_pages = rdata->pages,
@@ -3205,6 +3223,9 @@ smb2_readv_callback(struct mid_q_entry *mid)
task_io_account_read(rdata->got_bytes);
cifs_stats_bytes_read(tcon, rdata->got_bytes);
break;
+ case MID_RESPONSE_MALFORMED:
+ credits_received = le16_to_cpu(shdr->CreditRequest);
+ /* fall through */
default:
if (rdata->result != -ENODATA)
rdata->result = -EIO;
@@ -3220,8 +3241,17 @@ smb2_readv_callback(struct mid_q_entry *mid)
rdata->mr = NULL;
}
#endif
- if (rdata->result)
+ if (rdata->result && rdata->result != -ENODATA) {
cifs_stats_fail_inc(tcon, SMB2_READ_HE);
+ trace_smb3_read_err(0 /* xid */,
+ rdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid, rdata->offset,
+ rdata->bytes, rdata->result);
+ } else
+ trace_smb3_read_done(0 /* xid */,
+ rdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid,
+ rdata->offset, rdata->got_bytes);
queue_work(cifsiod_wq, &rdata->work);
DeleteMidQEntry(mid);
@@ -3278,12 +3308,14 @@ smb2_async_readv(struct cifs_readdata *rdata)
if (rdata->credits) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
SMB2_MAX_BUFFER_SIZE));
- shdr->CreditRequest = shdr->CreditCharge;
+ shdr->CreditRequest =
+ cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
spin_lock(&server->req_lock);
server->credits += rdata->credits -
le16_to_cpu(shdr->CreditCharge);
spin_unlock(&server->req_lock);
wake_up(&server->request_q);
+ rdata->credits = le16_to_cpu(shdr->CreditCharge);
flags |= CIFS_HAS_CREDITS;
}
@@ -3294,13 +3326,11 @@ smb2_async_readv(struct cifs_readdata *rdata)
if (rc) {
kref_put(&rdata->refcount, cifs_readdata_release);
cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
- trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid,
- io_parms.tcon->tid, io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length);
- } else
- trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid,
- io_parms.tcon->tid, io_parms.tcon->ses->Suid,
- io_parms.offset, io_parms.length);
+ trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid,
+ io_parms.tcon->tid,
+ io_parms.tcon->ses->Suid,
+ io_parms.offset, io_parms.length, rc);
+ }
cifs_small_buf_release(buf);
return rc;
@@ -3344,10 +3374,11 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
if (rc != -ENODATA) {
cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE);
cifs_dbg(VFS, "Send error in read = %d\n", rc);
+ trace_smb3_read_err(xid, req->PersistentFileId,
+ io_parms->tcon->tid, ses->Suid,
+ io_parms->offset, io_parms->length,
+ rc);
}
- trace_smb3_read_err(rc, xid, req->PersistentFileId,
- io_parms->tcon->tid, ses->Suid,
- io_parms->offset, io_parms->length);
free_rsp_buf(resp_buftype, rsp_iov.iov_base);
return rc == -ENODATA ? 0 : rc;
} else
@@ -3388,7 +3419,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
unsigned int written;
struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
- unsigned int credits_received = 1;
+ unsigned int credits_received = 0;
switch (mid->mid_state) {
case MID_RESPONSE_RECEIVED:
@@ -3416,6 +3447,9 @@ smb2_writev_callback(struct mid_q_entry *mid)
case MID_RETRY_NEEDED:
wdata->result = -EAGAIN;
break;
+ case MID_RESPONSE_MALFORMED:
+ credits_received = le16_to_cpu(rsp->sync_hdr.CreditRequest);
+ /* fall through */
default:
wdata->result = -EIO;
break;
@@ -3433,8 +3467,17 @@ smb2_writev_callback(struct mid_q_entry *mid)
wdata->mr = NULL;
}
#endif
- if (wdata->result)
+ if (wdata->result) {
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
+ trace_smb3_write_err(0 /* no xid */,
+ wdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid, wdata->offset,
+ wdata->bytes, wdata->result);
+ } else
+ trace_smb3_write_done(0 /* no xid */,
+ wdata->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid,
+ wdata->offset, wdata->bytes);
queue_work(cifsiod_wq, &wdata->work);
DeleteMidQEntry(mid);
@@ -3555,12 +3598,14 @@ smb2_async_writev(struct cifs_writedata *wdata,
if (wdata->credits) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
SMB2_MAX_BUFFER_SIZE));
- shdr->CreditRequest = shdr->CreditCharge;
+ shdr->CreditRequest =
+ cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
spin_lock(&server->req_lock);
server->credits += wdata->credits -
le16_to_cpu(shdr->CreditCharge);
spin_unlock(&server->req_lock);
wake_up(&server->request_q);
+ wdata->credits = le16_to_cpu(shdr->CreditCharge);
flags |= CIFS_HAS_CREDITS;
}
@@ -3574,10 +3619,7 @@ smb2_async_writev(struct cifs_writedata *wdata,
wdata->bytes, rc);
kref_put(&wdata->refcount, release);
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
- } else
- trace_smb3_write_done(0 /* no xid */, req->PersistentFileId,
- tcon->tid, tcon->ses->Suid, wdata->offset,
- wdata->bytes);
+ }
async_writev_out:
cifs_small_buf_release(req);
@@ -3803,8 +3845,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) {
srch_inf->endOfSearch = true;
rc = 0;
- }
- cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
+ } else
+ cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
goto qdir_exit;
}
@@ -4399,8 +4441,8 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov);
cifs_small_buf_release(req);
- please_key_low = (__u64 *)req->LeaseKey;
- please_key_high = (__u64 *)(req->LeaseKey+8);
+ please_key_low = (__u64 *)lease_key;
+ please_key_high = (__u64 *)(lease_key+8);
if (rc) {
cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 7a2d0a2255e6..538e2299805f 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -84,8 +84,9 @@
#define NUMBER_OF_SMB2_COMMANDS 0x0013
-/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */
-#define MAX_SMB2_HDR_SIZE 0x00b0
+/* 52 transform hdr + 64 hdr + 88 create rsp */
+#define SMB2_TRANSFORM_HEADER_SIZE 52
+#define MAX_SMB2_HDR_SIZE 204
#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
@@ -648,6 +649,13 @@ struct smb2_create_req {
__u8 Buffer[0];
} __packed;
+/*
+ * Maximum size of a SMB2_CREATE response is 64 (smb2 header) +
+ * 88 (fixed part of create response) + 520 (path) + 150 (contexts) +
+ * 2 bytes of padding.
+ */
+#define MAX_SMB2_CREATE_RESPONSE_SIZE 824
+
struct smb2_create_rsp {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 89 */
@@ -996,6 +1004,11 @@ struct smb2_close_req {
__u64 VolatileFileId; /* opaque endianness */
} __packed;
+/*
+ * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data)
+ */
+#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124
+
struct smb2_close_rsp {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* 60 */
@@ -1398,8 +1411,6 @@ struct smb2_file_link_info { /* encoding of request for level 11 */
char FileName[0]; /* Name to be assigned to new link */
} __packed; /* level 11 Set */
-#define SMB2_MAX_EA_BUF 65536
-
struct smb2_file_full_ea_info { /* encoding of response for level 15 */
__le32 next_entry_offset;
__u8 flags;
diff --git a/fs/cifs/trace.c b/fs/cifs/trace.c
index bd4a546feec1..465483787193 100644
--- a/fs/cifs/trace.c
+++ b/fs/cifs/trace.c
@@ -3,16 +3,6 @@
* Copyright (C) 2018, Microsoft Corporation.
*
* Author(s): Steve French <stfrench@microsoft.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
- * the GNU General Public License for more details.
*/
#define CREATE_TRACE_POINTS
#include "trace.h"
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index fb049809555f..59be48206932 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -3,16 +3,6 @@
* Copyright (C) 2018, Microsoft Corporation.
*
* Author(s): Steve French <stfrench@microsoft.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
- * the GNU General Public License for more details.
*/
#undef TRACE_SYSTEM
#define TRACE_SYSTEM cifs
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 5be7302853b6..53532bd3f50d 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -387,7 +387,7 @@ smbd_done:
if (rc < 0 && rc != -EINTR)
cifs_dbg(VFS, "Error %d sending data on socket to server\n",
rc);
- else
+ else if (rc > 0)
rc = 0;
return rc;
@@ -783,8 +783,25 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
}
static void
-cifs_noop_callback(struct mid_q_entry *mid)
+cifs_compound_callback(struct mid_q_entry *mid)
+{
+ struct TCP_Server_Info *server = mid->server;
+
+ add_credits(server, server->ops->get_credits(mid), mid->optype);
+}
+
+static void
+cifs_compound_last_callback(struct mid_q_entry *mid)
{
+ cifs_compound_callback(mid);
+ cifs_wake_up_task(mid);
+}
+
+static void
+cifs_cancelled_callback(struct mid_q_entry *mid)
+{
+ cifs_compound_callback(mid);
+ DeleteMidQEntry(mid);
}
int
@@ -795,7 +812,8 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
int i, j, rc = 0;
int timeout, optype;
struct mid_q_entry *midQ[MAX_COMPOUND];
- unsigned int credits = 0;
+ bool cancelled_mid[MAX_COMPOUND] = {false};
+ unsigned int credits[MAX_COMPOUND] = {0};
char *buf;
timeout = flags & CIFS_TIMEOUT_MASK;
@@ -813,13 +831,31 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
return -ENOENT;
/*
- * Ensure that we do not send more than 50 overlapping requests
- * to the same server. We may make this configurable later or
- * use ses->maxReq.
+ * Ensure we obtain 1 credit per request in the compound chain.
+ * It can be optimized further by waiting for all the credits
+ * at once but this can wait long enough if we don't have enough
+ * credits due to some heavy operations in progress or the server
+ * not granting us much, so a fallback to the current approach is
+ * needed anyway.
*/
- rc = wait_for_free_request(ses->server, timeout, optype);
- if (rc)
- return rc;
+ for (i = 0; i < num_rqst; i++) {
+ rc = wait_for_free_request(ses->server, timeout, optype);
+ if (rc) {
+ /*
+ * We haven't sent an SMB packet to the server yet but
+ * we already obtained credits for i requests in the
+ * compound chain - need to return those credits back
+ * for future use. Note that we need to call add_credits
+ * multiple times to match the way we obtained credits
+ * in the first place and to account for in flight
+ * requests correctly.
+ */
+ for (j = 0; j < i; j++)
+ add_credits(ses->server, 1, optype);
+ return rc;
+ }
+ credits[i] = 1;
+ }
/*
* Make sure that we sign in the same order that we send on this socket
@@ -835,18 +871,24 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
for (j = 0; j < i; j++)
cifs_delete_mid(midQ[j]);
mutex_unlock(&ses->server->srv_mutex);
+
/* Update # of requests on wire to server */
- add_credits(ses->server, 1, optype);
+ for (j = 0; j < num_rqst; j++)
+ add_credits(ses->server, credits[j], optype);
return PTR_ERR(midQ[i]);
}
midQ[i]->mid_state = MID_REQUEST_SUBMITTED;
+ midQ[i]->optype = optype;
/*
- * We don't invoke the callback compounds unless it is the last
- * request.
+ * Invoke callback for every part of the compound chain
+ * to calculate credits properly. Wake up this thread only when
+ * the last element is received.
*/
if (i < num_rqst - 1)
- midQ[i]->callback = cifs_noop_callback;
+ midQ[i]->callback = cifs_compound_callback;
+ else
+ midQ[i]->callback = cifs_compound_last_callback;
}
cifs_in_send_inc(ses->server);
rc = smb_send_rqst(ses->server, num_rqst, rqst, flags);
@@ -860,8 +902,20 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
mutex_unlock(&ses->server->srv_mutex);
- if (rc < 0)
+ if (rc < 0) {
+ /* Sending failed for some reason - return credits back */
+ for (i = 0; i < num_rqst; i++)
+ add_credits(ses->server, credits[i], optype);
goto out;
+ }
+
+ /*
+ * At this point the request is passed to the network stack - we assume
+ * that any credits taken from the server structure on the client have
+ * been spent and we can't return them back. Once we receive responses
+ * we will collect credits granted by the server in the mid callbacks
+ * and add those credits to the server structure.
+ */
/*
* Compounding is never used during session establish.
@@ -875,36 +929,34 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
for (i = 0; i < num_rqst; i++) {
rc = wait_for_response(ses->server, midQ[i]);
- if (rc != 0) {
+ if (rc != 0)
+ break;
+ }
+ if (rc != 0) {
+ for (; i < num_rqst; i++) {
cifs_dbg(VFS, "Cancelling wait for mid %llu cmd: %d\n",
midQ[i]->mid, le16_to_cpu(midQ[i]->command));
send_cancel(ses->server, &rqst[i], midQ[i]);
spin_lock(&GlobalMid_Lock);
if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) {
midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
- midQ[i]->callback = DeleteMidQEntry;
- spin_unlock(&GlobalMid_Lock);
- add_credits(ses->server, 1, optype);
- return rc;
+ midQ[i]->callback = cifs_cancelled_callback;
+ cancelled_mid[i] = true;
+ credits[i] = 0;
}
spin_unlock(&GlobalMid_Lock);
}
}
- for (i = 0; i < num_rqst; i++)
- if (midQ[i]->resp_buf)
- credits += ses->server->ops->get_credits(midQ[i]);
- if (!credits)
- credits = 1;
-
for (i = 0; i < num_rqst; i++) {
if (rc < 0)
goto out;
rc = cifs_sync_mid_result(midQ[i], ses->server);
if (rc != 0) {
- add_credits(ses->server, credits, optype);
- return rc;
+ /* mark this mid as cancelled to not free it below */
+ cancelled_mid[i] = true;
+ goto out;
}
if (!midQ[i]->resp_buf ||
@@ -951,9 +1003,10 @@ out:
* This is prevented above by using a noop callback that will not
* wake this thread except for the very last PDU.
*/
- for (i = 0; i < num_rqst; i++)
- cifs_delete_mid(midQ[i]);
- add_credits(ses->server, credits, optype);
+ for (i = 0; i < num_rqst; i++) {
+ if (!cancelled_mid[i])
+ cifs_delete_mid(midQ[i]);
+ }
return rc;
}
diff --git a/fs/dcache.c b/fs/dcache.c
index 2593153471cf..aac41adf4743 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -119,6 +119,7 @@ struct dentry_stat_t dentry_stat = {
static DEFINE_PER_CPU(long, nr_dentry);
static DEFINE_PER_CPU(long, nr_dentry_unused);
+static DEFINE_PER_CPU(long, nr_dentry_negative);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
@@ -152,11 +153,22 @@ static long get_nr_dentry_unused(void)
return sum < 0 ? 0 : sum;
}
+static long get_nr_dentry_negative(void)
+{
+ int i;
+ long sum = 0;
+
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_dentry_negative, i);
+ return sum < 0 ? 0 : sum;
+}
+
int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
dentry_stat.nr_dentry = get_nr_dentry();
dentry_stat.nr_unused = get_nr_dentry_unused();
+ dentry_stat.nr_negative = get_nr_dentry_negative();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
@@ -317,6 +329,8 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry)
flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
WRITE_ONCE(dentry->d_flags, flags);
dentry->d_inode = NULL;
+ if (dentry->d_flags & DCACHE_LRU_LIST)
+ this_cpu_inc(nr_dentry_negative);
}
static void dentry_free(struct dentry *dentry)
@@ -371,6 +385,11 @@ static void dentry_unlink_inode(struct dentry * dentry)
* The per-cpu "nr_dentry_unused" counters are updated with
* the DCACHE_LRU_LIST bit.
*
+ * The per-cpu "nr_dentry_negative" counters are only updated
+ * when deleted from or added to the per-superblock LRU list, not
+ * from/to the shrink list. That is to avoid an unneeded dec/inc
+ * pair when moving from LRU to shrink list in select_collect().
+ *
* These helper functions make sure we always follow the
* rules. d_lock must be held by the caller.
*/
@@ -380,6 +399,8 @@ static void d_lru_add(struct dentry *dentry)
D_FLAG_VERIFY(dentry, 0);
dentry->d_flags |= DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_inc(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
@@ -388,6 +409,8 @@ static void d_lru_del(struct dentry *dentry)
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
@@ -418,6 +441,8 @@ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry)
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
list_lru_isolate(lru, &dentry->d_lru);
}
@@ -426,6 +451,8 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry,
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags |= DCACHE_SHRINK_LIST;
+ if (d_is_negative(dentry))
+ this_cpu_dec(nr_dentry_negative);
list_lru_isolate_move(lru, &dentry->d_lru, list);
}
@@ -1188,15 +1215,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
*/
void shrink_dcache_sb(struct super_block *sb)
{
- long freed;
-
do {
LIST_HEAD(dispose);
- freed = list_lru_walk(&sb->s_dentry_lru,
+ list_lru_walk(&sb->s_dentry_lru,
dentry_lru_isolate_shrink, &dispose, 1024);
-
- this_cpu_sub(nr_dentry_unused, freed);
shrink_dentry_list(&dispose);
} while (list_lru_count(&sb->s_dentry_lru) > 0);
}
@@ -1820,6 +1843,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
WARN_ON(d_in_lookup(dentry));
spin_lock(&dentry->d_lock);
+ /*
+ * Decrement negative dentry count if it was in the LRU list.
+ */
+ if (dentry->d_flags & DCACHE_LRU_LIST)
+ this_cpu_dec(nr_dentry_negative);
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
raw_write_seqcount_begin(&dentry->d_seq);
__d_set_inode_and_type(dentry, inode, add_flags);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 13b01351dd1c..29c68c5d44d5 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -324,7 +324,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
inode_unlock(d_inode(dentry->d_parent));
dput(dentry);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
static struct dentry *end_creating(struct dentry *dentry)
@@ -347,7 +347,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
dentry = start_creating(name, parent);
if (IS_ERR(dentry))
- return NULL;
+ return dentry;
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode))
@@ -386,7 +386,8 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %NULL will be returned.
+ * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
@@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %NULL will be returned.
+ * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
@@ -495,7 +497,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %NULL will be returned.
+ * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
@@ -506,7 +509,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
struct inode *inode;
if (IS_ERR(dentry))
- return NULL;
+ return dentry;
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode))
@@ -545,7 +548,7 @@ struct dentry *debugfs_create_automount(const char *name,
struct inode *inode;
if (IS_ERR(dentry))
- return NULL;
+ return dentry;
inode = debugfs_get_inode(dentry->d_sb);
if (unlikely(!inode))
@@ -581,8 +584,8 @@ EXPORT_SYMBOL(debugfs_create_automount);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the symbolic
* link is to be removed (no automatic cleanup happens if your module is
- * unloaded, you are responsible here.) If an error occurs, %NULL will be
- * returned.
+ * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR)
+ * will be returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
* returned.
@@ -594,12 +597,12 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
struct inode *inode;
char *link = kstrdup(target, GFP_KERNEL);
if (!link)
- return NULL;
+ return ERR_PTR(-ENOMEM);
dentry = start_creating(name, parent);
if (IS_ERR(dentry)) {
kfree(link);
- return NULL;
+ return dentry;
}
inode = debugfs_get_inode(dentry->d_sb);
@@ -787,6 +790,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
struct dentry *dentry = NULL, *trap;
struct name_snapshot old_name;
+ if (IS_ERR(old_dir))
+ return old_dir;
+ if (IS_ERR(new_dir))
+ return new_dir;
+ if (IS_ERR_OR_NULL(old_dentry))
+ return old_dentry;
+
trap = lock_rename(new_dir, old_dir);
/* Source or destination directories don't exist? */
if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
@@ -820,7 +830,9 @@ exit:
if (dentry && !IS_ERR(dentry))
dput(dentry);
unlock_rename(new_dir, old_dir);
- return NULL;
+ if (IS_ERR(dentry))
+ return dentry;
+ return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL_GPL(debugfs_rename);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index dbc1a1f080ce..ec2fb6fe6d37 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -679,6 +679,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
unsigned long fs_count; /* Number of filesystem-sized blocks */
int create;
unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor;
+ loff_t i_size;
/*
* If there was a memory error and we've overwritten all the
@@ -708,8 +709,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
*/
create = dio->op == REQ_OP_WRITE;
if (dio->flags & DIO_SKIP_HOLES) {
- if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
- i_blkbits))
+ i_size = i_size_read(dio->inode);
+ if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits)
create = 0;
}
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 76976d6e50f9..c98ad9777ad9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con)
* since O_NONBLOCK argument in connect() function does not work here,
* then, we should restore the default value of this attribute.
*/
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv,
sizeof(tv));
result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
0);
memset(&tv, 0, sizeof(tv));
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv,
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv,
sizeof(tv));
if (result == -EINPROGRESS)
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 82377017130f..d31b6c72b476 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
+ /*
+ * We must skip inodes in unusual state. We may also skip
+ * inodes without pages but we deliberately won't in case
+ * we need to reschedule to avoid softlockups.
+ */
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
- (inode->i_mapping->nrpages == 0)) {
+ (inode->i_mapping->nrpages == 0 && !need_resched())) {
spin_unlock(&inode->i_lock);
continue;
}
@@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_list_lock);
+ cond_resched();
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
diff --git a/fs/exec.c b/fs/exec.c
index fb72d36f7823..bcf383730bea 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -932,7 +932,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
bytes = kernel_read(file, *buf + pos, i_size - pos, &pos);
if (bytes < 0) {
ret = bytes;
- goto out;
+ goto out_free;
}
if (bytes == 0)
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 712f00995390..5508baa11bb6 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
goto out;
}
- ret = file_write_and_wait_range(file, start, end);
- if (ret)
- return ret;
-
if (!journal) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL
- };
-
- ret = ext4_write_inode(inode, &wbc);
+ ret = __generic_file_fsync(file, start, end, datasync);
if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
@@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
goto out;
}
+ ret = file_write_and_wait_range(file, start, end);
+ if (ret)
+ return ret;
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index b40168fcc94a..36855c1f8daf 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -331,11 +331,22 @@ struct inode_switch_wbs_context {
struct work_struct work;
};
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+ down_write(&bdi->wb_switch_rwsem);
+}
+
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+ up_write(&bdi->wb_switch_rwsem);
+}
+
static void inode_switch_wbs_work_fn(struct work_struct *work)
{
struct inode_switch_wbs_context *isw =
container_of(work, struct inode_switch_wbs_context, work);
struct inode *inode = isw->inode;
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
struct address_space *mapping = inode->i_mapping;
struct bdi_writeback *old_wb = inode->i_wb;
struct bdi_writeback *new_wb = isw->new_wb;
@@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
bool switched = false;
/*
+ * If @inode switches cgwb membership while sync_inodes_sb() is
+ * being issued, sync_inodes_sb() might miss it. Synchronize.
+ */
+ down_read(&bdi->wb_switch_rwsem);
+
+ /*
* By the time control reaches here, RCU grace period has passed
* since I_WB_SWITCH assertion and all wb stat update transactions
* between unlocked_inode_to_wb_begin/end() are guaranteed to be
@@ -428,6 +445,8 @@ skip_switch:
spin_unlock(&new_wb->list_lock);
spin_unlock(&old_wb->list_lock);
+ up_read(&bdi->wb_switch_rwsem);
+
if (switched) {
wb_wakeup(new_wb);
wb_put(old_wb);
@@ -468,9 +487,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
if (inode->i_state & I_WB_SWITCH)
return;
+ /*
+ * Avoid starting new switches while sync_inodes_sb() is in
+ * progress. Otherwise, if the down_write protected issue path
+ * blocks heavily, we might end up starting a large number of
+ * switches which will block on the rwsem.
+ */
+ if (!down_read_trylock(&bdi->wb_switch_rwsem))
+ return;
+
isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
if (!isw)
- return;
+ goto out_unlock;
/* find and pin the new wb */
rcu_read_lock();
@@ -504,12 +532,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
* Let's continue after I_WB_SWITCH is guaranteed to be visible.
*/
call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
- return;
+ goto out_unlock;
out_free:
if (isw->new_wb)
wb_put(isw->new_wb);
kfree(isw);
+out_unlock:
+ up_read(&bdi->wb_switch_rwsem);
}
/**
@@ -887,6 +917,9 @@ fs_initcall(cgroup_writeback_init);
#else /* CONFIG_CGROUP_WRITEBACK */
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+
static struct bdi_writeback *
locked_inode_to_wb_and_lock_list(struct inode *inode)
__releases(&inode->i_lock)
@@ -2413,8 +2446,11 @@ void sync_inodes_sb(struct super_block *sb)
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
+ /* protect against inode wb switch, see inode_switch_wbs_work_fn() */
+ bdi_down_write_wb_switch_rwsem(bdi);
bdi_split_work_to_wbs(bdi, &work, false);
wb_wait_for_completion(bdi, &done);
+ bdi_up_write_wb_switch_rwsem(bdi);
wait_sb_inodes(sb);
}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index a5e516a40e7a..809c0f2f9942 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1742,7 +1742,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
req->in.h.nodeid = outarg->nodeid;
req->in.numargs = 2;
req->in.argpages = 1;
- req->page_descs[0].offset = offset;
req->end = fuse_retrieve_end;
index = outarg->offset >> PAGE_SHIFT;
@@ -1757,6 +1756,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
this_num = min_t(unsigned, num, PAGE_SIZE - offset);
req->pages[req->num_pages] = page;
+ req->page_descs[req->num_pages].offset = offset;
req->page_descs[req->num_pages].length = this_num;
req->num_pages++;
@@ -2077,8 +2077,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
ret = fuse_dev_do_write(fud, &cs, len);
+ pipe_lock(pipe);
for (idx = 0; idx < nbuf; idx++)
pipe_buf_release(pipe, &bufs[idx]);
+ pipe_unlock(pipe);
out:
kvfree(bufs);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index ffaffe18352a..a59c16bd90ac 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1782,7 +1782,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
spin_unlock(&fc->lock);
dec_wb_stat(&bdi->wb, WB_WRITEBACK);
- dec_node_page_state(page, NR_WRITEBACK_TEMP);
+ dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP);
wb_writeout_inc(&bdi->wb);
fuse_writepage_free(fc, new_req);
fuse_request_free(new_req);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 76baaa6be393..c2d4099429be 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -628,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
fc->user_ns = get_user_ns(user_ns);
+ fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
}
EXPORT_SYMBOL_GPL(fuse_conn_init);
@@ -1162,7 +1163,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
fc->user_id = d.user_id;
fc->group_id = d.group_id;
fc->max_read = max_t(unsigned, 4096, d.max_read);
- fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
/* Used by get_root_inode() */
sb->s_fs_info = fc;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index f15b4c57c4bd..78510ab91835 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -28,7 +28,6 @@
#include "util.h"
#include "trans.h"
#include "dir.h"
-#include "lops.h"
struct workqueue_struct *gfs2_freeze_wq;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 5bfaf381921a..b8830fda51e8 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
lh->lh_crc = cpu_to_be32(crc);
gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr);
- gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags);
+ gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags);
log_flush_wait(sdp);
}
@@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
gfs2_ordered_write(sdp);
lops_before_commit(sdp, tr);
- gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE);
+ gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0);
if (sdp->sd_log_head != sdp->sd_log_flush_head) {
log_flush_wait(sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 94dcab655bc0..2295042bc625 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -17,9 +17,7 @@
#include <linux/bio.h>
#include <linux/fs.h>
#include <linux/list_sort.h>
-#include <linux/blkdev.h>
-#include "bmap.h"
#include "dir.h"
#include "gfs2.h"
#include "incore.h"
@@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
/**
* gfs2_end_log_write - end of i/o to the log
* @bio: The bio
+ * @error: Status of i/o request
*
* Each bio_vec contains either data from the pagecache or data
* relating to the log itself. Here we iterate over the bio_vec
@@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio)
/**
* gfs2_log_submit_bio - Submit any pending log bio
* @biop: Address of the bio pointer
- * @opf: REQ_OP | op_flags
+ * @op: REQ_OP
+ * @op_flags: req_flag_bits
*
* Submit any pending part-built or full bio to the block device. If
* there is no pending bio, then this is a no-op.
*/
-void gfs2_log_submit_bio(struct bio **biop, int opf)
+void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags)
{
struct bio *bio = *biop;
if (bio) {
struct gfs2_sbd *sdp = bio->bi_private;
atomic_inc(&sdp->sd_log_in_flight);
- bio->bi_opf = opf;
+ bio_set_op_attrs(bio, op, op_flags);
submit_bio(bio);
*biop = NULL;
}
@@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno,
nblk >>= sdp->sd_fsb2bb_shift;
if (blkno == nblk && !flush)
return bio;
- gfs2_log_submit_bio(biop, op);
+ gfs2_log_submit_bio(biop, op, 0);
}
*biop = gfs2_log_alloc_bio(sdp, blkno, end_io);
@@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page)
gfs2_log_bmap(sdp));
}
-/**
- * gfs2_end_log_read - end I/O callback for reads from the log
- * @bio: The bio
- *
- * Simply unlock the pages in the bio. The main thread will wait on them and
- * process them in order as necessary.
- */
-
-static void gfs2_end_log_read(struct bio *bio)
-{
- struct page *page;
- struct bio_vec *bvec;
- int i;
-
- bio_for_each_segment_all(bvec, bio, i) {
- page = bvec->bv_page;
- if (bio->bi_status) {
- int err = blk_status_to_errno(bio->bi_status);
-
- SetPageError(page);
- mapping_set_error(page->mapping, err);
- }
- unlock_page(page);
- }
-
- bio_put(bio);
-}
-
-/**
- * gfs2_jhead_pg_srch - Look for the journal head in a given page.
- * @jd: The journal descriptor
- * @page: The page to look in
- *
- * Returns: 1 if found, 0 otherwise.
- */
-
-static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd,
- struct gfs2_log_header_host *head,
- struct page *page)
-{
- struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
- struct gfs2_log_header_host uninitialized_var(lh);
- void *kaddr = kmap_atomic(page);
- unsigned int offset;
- bool ret = false;
-
- for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) {
- if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) {
- if (lh.lh_sequence > head->lh_sequence)
- *head = lh;
- else {
- ret = true;
- break;
- }
- }
- }
- kunmap_atomic(kaddr);
- return ret;
-}
-
-/**
- * gfs2_jhead_process_page - Search/cleanup a page
- * @jd: The journal descriptor
- * @index: Index of the page to look into
- * @done: If set, perform only cleanup, else search and set if found.
- *
- * Find the page with 'index' in the journal's mapping. Search the page for
- * the journal head if requested (cleanup == false). Release refs on the
- * page so the page cache can reclaim it (put_page() twice). We grabbed a
- * reference on this page two times, first when we did a find_or_create_page()
- * to obtain the page to add it to the bio and second when we do a
- * find_get_page() here to get the page to wait on while I/O on it is being
- * completed.
- * This function is also used to free up a page we might've grabbed but not
- * used. Maybe we added it to a bio, but not submitted it for I/O. Or we
- * submitted the I/O, but we already found the jhead so we only need to drop
- * our references to the page.
- */
-
-static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
- struct gfs2_log_header_host *head,
- bool *done)
-{
- struct page *page;
-
- page = find_get_page(jd->jd_inode->i_mapping, index);
- wait_on_page_locked(page);
-
- if (PageError(page))
- *done = true;
-
- if (!*done)
- *done = gfs2_jhead_pg_srch(jd, head, page);
-
- put_page(page); /* Once for find_get_page */
- put_page(page); /* Once more for find_or_create_page */
-}
-
-/**
- * gfs2_find_jhead - find the head of a log
- * @jd: The journal descriptor
- * @head: The log descriptor for the head of the log is returned here
- *
- * Do a search of a journal by reading it in large chunks using bios and find
- * the valid log entry with the highest sequence number. (i.e. the log head)
- *
- * Returns: 0 on success, errno otherwise
- */
-
-int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
-{
- struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
- struct address_space *mapping = jd->jd_inode->i_mapping;
- struct gfs2_journal_extent *je;
- u32 block, read_idx = 0, submit_idx = 0, index = 0;
- int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
- int blocks_per_page = 1 << shift, sz, ret = 0;
- struct bio *bio = NULL;
- struct page *page;
- bool done = false;
- errseq_t since;
-
- memset(head, 0, sizeof(*head));
- if (list_empty(&jd->extent_list))
- gfs2_map_journal_extents(sdp, jd);
-
- since = filemap_sample_wb_err(mapping);
- list_for_each_entry(je, &jd->extent_list, list) {
- for (block = 0; block < je->blocks; block += blocks_per_page) {
- index = (je->lblock + block) >> shift;
-
- page = find_or_create_page(mapping, index, GFP_NOFS);
- if (!page) {
- ret = -ENOMEM;
- done = true;
- goto out;
- }
-
- if (bio) {
- sz = bio_add_page(bio, page, PAGE_SIZE, 0);
- if (sz == PAGE_SIZE)
- goto page_added;
- submit_idx = index;
- submit_bio(bio);
- bio = NULL;
- }
-
- bio = gfs2_log_alloc_bio(sdp,
- je->dblock + (index << shift),
- gfs2_end_log_read);
- bio->bi_opf = REQ_OP_READ;
- sz = bio_add_page(bio, page, PAGE_SIZE, 0);
- gfs2_assert_warn(sdp, sz == PAGE_SIZE);
-
-page_added:
- if (submit_idx <= read_idx + BIO_MAX_PAGES) {
- /* Keep at least one bio in flight */
- continue;
- }
-
- gfs2_jhead_process_page(jd, read_idx++, head, &done);
- if (done)
- goto out; /* found */
- }
- }
-
-out:
- if (bio)
- submit_bio(bio);
- while (read_idx <= index)
- gfs2_jhead_process_page(jd, read_idx++, head, &done);
-
- if (!ret)
- ret = filemap_check_wb_err(mapping, since);
-
- return ret;
-}
-
static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type,
u32 ld_length, u32 ld_data1)
{
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 331160fc568b..711c4d89c063 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp);
extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page,
unsigned size, unsigned offset, u64 blkno);
extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page);
-extern void gfs2_log_submit_bio(struct bio **biop, int opf);
+extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags);
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
-extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
- struct gfs2_log_header_host *head);
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1179763f6370..b041cb8ae383 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -41,7 +41,6 @@
#include "dir.h"
#include "meta_io.h"
#include "trace_gfs2.h"
-#include "lops.h"
#define DO 0
#define UNDO 1
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 7389e445a7a7..2dac43065382 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk,
}
/**
+ * find_good_lh - find a good log header
+ * @jd: the journal
+ * @blk: the segment to start searching from
+ * @lh: the log header to fill in
+ * @forward: if true search forward in the log, else search backward
+ *
+ * Call get_log_header() to get a log header for a segment, but if the
+ * segment is bad, either scan forward or backward until we find a good one.
+ *
+ * Returns: errno
+ */
+
+static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk,
+ struct gfs2_log_header_host *head)
+{
+ unsigned int orig_blk = *blk;
+ int error;
+
+ for (;;) {
+ error = get_log_header(jd, *blk, head);
+ if (error <= 0)
+ return error;
+
+ if (++*blk == jd->jd_blocks)
+ *blk = 0;
+
+ if (*blk == orig_blk) {
+ gfs2_consist_inode(GFS2_I(jd->jd_inode));
+ return -EIO;
+ }
+ }
+}
+
+/**
+ * jhead_scan - make sure we've found the head of the log
+ * @jd: the journal
+ * @head: this is filled in with the log descriptor of the head
+ *
+ * At this point, seg and lh should be either the head of the log or just
+ * before. Scan forward until we find the head.
+ *
+ * Returns: errno
+ */
+
+static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+ unsigned int blk = head->lh_blkno;
+ struct gfs2_log_header_host lh;
+ int error;
+
+ for (;;) {
+ if (++blk == jd->jd_blocks)
+ blk = 0;
+
+ error = get_log_header(jd, blk, &lh);
+ if (error < 0)
+ return error;
+ if (error == 1)
+ continue;
+
+ if (lh.lh_sequence == head->lh_sequence) {
+ gfs2_consist_inode(GFS2_I(jd->jd_inode));
+ return -EIO;
+ }
+ if (lh.lh_sequence < head->lh_sequence)
+ break;
+
+ *head = lh;
+ }
+
+ return 0;
+}
+
+/**
+ * gfs2_find_jhead - find the head of a log
+ * @jd: the journal
+ * @head: the log descriptor for the head of the log is returned here
+ *
+ * Do a binary search of a journal and find the valid log entry with the
+ * highest sequence number. (i.e. the log head)
+ *
+ * Returns: errno
+ */
+
+int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head)
+{
+ struct gfs2_log_header_host lh_1, lh_m;
+ u32 blk_1, blk_2, blk_m;
+ int error;
+
+ blk_1 = 0;
+ blk_2 = jd->jd_blocks - 1;
+
+ for (;;) {
+ blk_m = (blk_1 + blk_2) / 2;
+
+ error = find_good_lh(jd, &blk_1, &lh_1);
+ if (error)
+ return error;
+
+ error = find_good_lh(jd, &blk_m, &lh_m);
+ if (error)
+ return error;
+
+ if (blk_1 == blk_m || blk_m == blk_2)
+ break;
+
+ if (lh_1.lh_sequence <= lh_m.lh_sequence)
+ blk_1 = blk_m;
+ else
+ blk_2 = blk_m;
+ }
+
+ error = jhead_scan(jd, &lh_1);
+ if (error)
+ return error;
+
+ *head = lh_1;
+
+ return error;
+}
+
+/**
* foreach_descriptor - go through the active part of the log
* @jd: the journal
* @start: the first log header in the active region
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index 99575ab81202..11d81248be85 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where)
extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where);
extern void gfs2_revoke_clean(struct gfs2_jdesc *jd);
+extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
+ struct gfs2_log_header_host *head);
extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait);
extern void gfs2_recover_func(struct work_struct *work);
extern int __get_log_header(struct gfs2_sbd *sdp,
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 831d7cb5a49c..17a8d3b43990 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1780,9 +1780,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
goto next_iter;
}
if (ret == -E2BIG) {
- n += rbm->bii - initial_bii;
rbm->bii = 0;
rbm->offset = 0;
+ n += (rbm->bii - initial_bii);
goto res_covered_end_of_rgrp;
}
return ret;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index d4b11c903971..ca71163ff7cf 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -45,7 +45,6 @@
#include "util.h"
#include "sys.h"
#include "xattr.h"
-#include "lops.h"
#define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a2fcea5f8225..a7fa037b876b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -383,16 +383,17 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end)
* truncation is indicated by end of range being LLONG_MAX
* In this case, we first scan the range and release found pages.
* After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- * maps and global counts.
+ * maps and global counts. Page faults can not race with truncation
+ * in this routine. hugetlb_no_page() prevents page faults in the
+ * truncated range. It checks i_size before allocation, and again after
+ * with the page table lock for the page held. The same lock must be
+ * acquired to unmap a page.
* hole punch is indicated if end is not LLONG_MAX
* In the hole punch case we scan the range and release found pages.
* Only when releasing a page is the associated region/reserv map
* deleted. The region/reserv map for ranges without associated
- * pages are not modified.
- *
- * Callers of this routine must hold the i_mmap_rwsem in write mode to prevent
- * races with page faults.
- *
+ * pages are not modified. Page faults can race with hole punch.
+ * This is indicated if we find a mapped page.
* Note: If the passed end of range value is beyond the end of file, but
* not LLONG_MAX this routine still performs a hole punch operation.
*/
@@ -422,14 +423,32 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
+ u32 hash;
index = page->index;
+ hash = hugetlb_fault_mutex_hash(h, current->mm,
+ &pseudo_vma,
+ mapping, index, 0);
+ mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
/*
- * A mapped page is impossible as callers should unmap
- * all references before calling. And, i_mmap_rwsem
- * prevents the creation of additional mappings.
+ * If page is mapped, it was faulted in after being
+ * unmapped in caller. Unmap (again) now after taking
+ * the fault mutex. The mutex will prevent faults
+ * until we finish removing the page.
+ *
+ * This race can only happen in the hole punch case.
+ * Getting here in a truncate operation is a bug.
*/
- VM_BUG_ON(page_mapped(page));
+ if (unlikely(page_mapped(page))) {
+ BUG_ON(truncate_op);
+
+ i_mmap_lock_write(mapping);
+ hugetlb_vmdelete_list(&mapping->i_mmap,
+ index * pages_per_huge_page(h),
+ (index + 1) * pages_per_huge_page(h));
+ i_mmap_unlock_write(mapping);
+ }
lock_page(page);
/*
@@ -451,6 +470,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
}
unlock_page(page);
+ mutex_unlock(&hugetlb_fault_mutex_table[hash]);
}
huge_pagevec_release(&pvec);
cond_resched();
@@ -462,20 +482,9 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
static void hugetlbfs_evict_inode(struct inode *inode)
{
- struct address_space *mapping = inode->i_mapping;
struct resv_map *resv_map;
- /*
- * The vfs layer guarantees that there are no other users of this
- * inode. Therefore, it would be safe to call remove_inode_hugepages
- * without holding i_mmap_rwsem. We acquire and hold here to be
- * consistent with other callers. Since there will be no contention
- * on the semaphore, overhead is negligible.
- */
- i_mmap_lock_write(mapping);
remove_inode_hugepages(inode, 0, LLONG_MAX);
- i_mmap_unlock_write(mapping);
-
resv_map = (struct resv_map *)inode->i_mapping->private_data;
/* root inode doesn't have the resv_map, so we should check it */
if (resv_map)
@@ -496,8 +505,8 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
i_mmap_lock_write(mapping);
if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
- remove_inode_hugepages(inode, offset, LLONG_MAX);
i_mmap_unlock_write(mapping);
+ remove_inode_hugepages(inode, offset, LLONG_MAX);
return 0;
}
@@ -531,8 +540,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
hugetlb_vmdelete_list(&mapping->i_mmap,
hole_start >> PAGE_SHIFT,
hole_end >> PAGE_SHIFT);
- remove_inode_hugepages(inode, hole_start, hole_end);
i_mmap_unlock_write(mapping);
+ remove_inode_hugepages(inode, hole_start, hole_end);
inode_unlock(inode);
}
@@ -615,11 +624,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
/* addr is the offset within the file (zero based) */
addr = index * hpage_size;
- /*
- * fault mutex taken here, protects against fault path
- * and hole punch. inode_lock previously taken protects
- * against truncation.
- */
+ /* mutex taken here, fault path and hole punch */
hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
index, addr);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -854,6 +859,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
rc = migrate_huge_page_move_mapping(mapping, newpage, page);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
+
+ /*
+ * page_private is subpool pointer in hugetlb pages. Transfer to
+ * new page. PagePrivate is not associated with page_private for
+ * hugetlb pages and can not be set here as only page_huge_active
+ * pages can be migrated.
+ */
+ if (page_private(page)) {
+ set_page_private(newpage, page_private(page));
+ set_page_private(page, 0);
+ }
+
if (mode != MIGRATE_SYNC_NO_COPY)
migrate_page_copy(newpage, page);
else
diff --git a/fs/inode.c b/fs/inode.c
index 0cd47fe0dbe5..73432e64f874 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
return LRU_REMOVED;
}
- /*
- * Recently referenced inodes and inodes with many attached pages
- * get one more pass.
- */
- if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) {
+ /* recently referenced inodes get one more pass */
+ if (inode->i_state & I_REFERENCED) {
inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
return LRU_ROTATE;
diff --git a/fs/iomap.c b/fs/iomap.c
index a3088fae567b..897c60215dd1 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page)
atomic_set(&iop->read_count, 0);
atomic_set(&iop->write_count, 0);
bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+
+ /*
+ * migrate_page_move_mapping() assumes that pages with private data have
+ * their count elevated by 1.
+ */
+ get_page(page);
set_page_private(page, (unsigned long)iop);
SetPagePrivate(page);
return iop;
@@ -132,6 +138,7 @@ iomap_page_release(struct page *page)
WARN_ON_ONCE(atomic_read(&iop->write_count));
ClearPagePrivate(page);
set_page_private(page, 0);
+ put_page(page);
kfree(iop);
}
@@ -569,8 +576,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage,
if (page_has_private(page)) {
ClearPagePrivate(page);
+ get_page(newpage);
set_page_private(newpage, page_private(page));
set_page_private(page, 0);
+ put_page(page);
SetPagePrivate(newpage);
}
@@ -1804,6 +1813,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
loff_t pos = iocb->ki_pos, start = pos;
loff_t end = iocb->ki_pos + count - 1, ret = 0;
unsigned int flags = IOMAP_DIRECT;
+ bool wait_for_completion = is_sync_kiocb(iocb);
struct blk_plug plug;
struct iomap_dio *dio;
@@ -1823,7 +1833,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio->end_io = end_io;
dio->error = 0;
dio->flags = 0;
- dio->wait_for_completion = is_sync_kiocb(iocb);
dio->submit.iter = iter;
dio->submit.waiter = current;
@@ -1878,7 +1887,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
dio_warn_stale_pagecache(iocb->ki_filp);
ret = 0;
- if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
+ if (iov_iter_rw(iter) == WRITE && !wait_for_completion &&
!inode->i_sb->s_dio_done_wq) {
ret = sb_init_dio_done_wq(inode->i_sb);
if (ret < 0)
@@ -1894,7 +1903,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret <= 0) {
/* magic error code to fall back to buffered I/O */
if (ret == -ENOTBLK) {
- dio->wait_for_completion = true;
+ wait_for_completion = true;
ret = 0;
}
break;
@@ -1916,8 +1925,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+ /*
+ * We are about to drop our additional submission reference, which
+ * might be the last reference to the dio. There are three three
+ * different ways we can progress here:
+ *
+ * (a) If this is the last reference we will always complete and free
+ * the dio ourselves.
+ * (b) If this is not the last reference, and we serve an asynchronous
+ * iocb, we must never touch the dio after the decrement, the
+ * I/O completion handler will complete and free it.
+ * (c) If this is not the last reference, but we serve a synchronous
+ * iocb, the I/O completion handler will wake us up on the drop
+ * of the final reference, and we will complete and free it here
+ * after we got woken by the I/O completion handler.
+ */
+ dio->wait_for_completion = wait_for_completion;
if (!atomic_dec_and_test(&dio->ref)) {
- if (!dio->wait_for_completion)
+ if (!wait_for_completion)
return -EIOCBQUEUED;
for (;;) {
@@ -1934,9 +1959,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
__set_current_state(TASK_RUNNING);
}
- ret = iomap_dio_complete(dio);
-
- return ret;
+ return iomap_dio_complete(dio);
out_free_dio:
kfree(dio);
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index fdf527b6d79c..d71c9405874a 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -196,8 +196,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
return dentry;
knparent = find_next_ancestor(kn, NULL);
- if (WARN_ON(!knparent))
+ if (WARN_ON(!knparent)) {
+ dput(dentry);
return ERR_PTR(-EINVAL);
+ }
do {
struct dentry *dtmp;
@@ -206,8 +208,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
if (kn == knparent)
return dentry;
kntmp = find_next_ancestor(kn, knparent);
- if (WARN_ON(!kntmp))
+ if (WARN_ON(!kntmp)) {
+ dput(dentry);
return ERR_PTR(-EINVAL);
+ }
dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
strlen(kntmp->name));
dput(dentry);
diff --git a/fs/namespace.c b/fs/namespace.c
index a677b59efd74..c4e83d94840c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2698,7 +2698,6 @@ static long exact_copy_from_user(void *to, const void __user * from,
if (!access_ok(from, n))
return n;
- current->kernel_uaccess_faults_ok++;
while (n) {
if (__get_user(c, f)) {
memset(t, 0, n);
@@ -2708,7 +2707,6 @@ static long exact_copy_from_user(void *to, const void __user * from,
f++;
n--;
}
- current->kernel_uaccess_faults_ok--;
return n;
}
@@ -2746,7 +2744,7 @@ void *copy_mount_options(const void __user * data)
char *copy_mount_string(const void __user *data)
{
- return data ? strndup_user(data, PAGE_SIZE) : NULL;
+ return data ? strndup_user(data, PATH_MAX) : NULL;
}
/*
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 46d691ba04bc..45b2322e092d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,15 +133,9 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t count, unsigned int flags)
{
- ssize_t ret;
-
if (file_inode(file_in) == file_inode(file_out))
return -EINVAL;
-retry:
- ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
- if (ret == -EAGAIN)
- goto retry;
- return ret;
+ return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
}
static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 3f23b6840547..bf34ddaa2ad7 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -44,6 +44,7 @@
#include <linux/keyctl.h>
#include <linux/key-type.h>
#include <keys/user-type.h>
+#include <keys/request_key_auth-type.h>
#include <linux/module.h>
#include "internal.h"
@@ -59,7 +60,7 @@ static struct key_type key_type_id_resolver_legacy;
struct idmap_legacy_upcalldata {
struct rpc_pipe_msg pipe_msg;
struct idmap_msg idmap_msg;
- struct key_construction *key_cons;
+ struct key *authkey;
struct idmap *idmap;
};
@@ -384,7 +385,7 @@ static const match_table_t nfs_idmap_tokens = {
{ Opt_find_err, NULL }
};
-static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *);
+static int nfs_idmap_legacy_upcall(struct key *, void *);
static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
size_t);
static void idmap_release_pipe(struct inode *);
@@ -549,11 +550,12 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap,
static void
nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
{
- struct key_construction *cons = idmap->idmap_upcall_data->key_cons;
+ struct key *authkey = idmap->idmap_upcall_data->authkey;
kfree(idmap->idmap_upcall_data);
idmap->idmap_upcall_data = NULL;
- complete_request_key(cons, ret);
+ complete_request_key(authkey, ret);
+ key_put(authkey);
}
static void
@@ -563,15 +565,14 @@ nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret)
nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
}
-static int nfs_idmap_legacy_upcall(struct key_construction *cons,
- const char *op,
- void *aux)
+static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux)
{
struct idmap_legacy_upcalldata *data;
+ struct request_key_auth *rka = get_request_key_auth(authkey);
struct rpc_pipe_msg *msg;
struct idmap_msg *im;
struct idmap *idmap = (struct idmap *)aux;
- struct key *key = cons->key;
+ struct key *key = rka->target_key;
int ret = -ENOKEY;
if (!aux)
@@ -586,7 +587,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
msg = &data->pipe_msg;
im = &data->idmap_msg;
data->idmap = idmap;
- data->key_cons = cons;
+ data->authkey = key_get(authkey);
ret = nfs_idmap_prepare_message(key->description, idmap, im, msg);
if (ret < 0)
@@ -604,7 +605,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
out2:
kfree(data);
out1:
- complete_request_key(cons, ret);
+ complete_request_key(authkey, ret);
return ret;
}
@@ -651,9 +652,10 @@ out:
static ssize_t
idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
{
+ struct request_key_auth *rka;
struct rpc_inode *rpci = RPC_I(file_inode(filp));
struct idmap *idmap = (struct idmap *)rpci->private;
- struct key_construction *cons;
+ struct key *authkey;
struct idmap_msg im;
size_t namelen_in;
int ret = -ENOKEY;
@@ -665,7 +667,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
if (idmap->idmap_upcall_data == NULL)
goto out_noupcall;
- cons = idmap->idmap_upcall_data->key_cons;
+ authkey = idmap->idmap_upcall_data->authkey;
+ rka = get_request_key_auth(authkey);
if (mlen != sizeof(im)) {
ret = -ENOSPC;
@@ -690,9 +693,9 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
ret = nfs_idmap_read_and_verify_message(&im,
&idmap->idmap_upcall_data->idmap_msg,
- cons->key, cons->authkey);
+ rka->target_key, authkey);
if (ret >= 0) {
- key_set_timeout(cons->key, nfs_idmap_cache_timeout);
+ key_set_timeout(rka->target_key, nfs_idmap_cache_timeout);
ret = mlen;
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 22ce3c8a2f46..0570391eaa16 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1895,6 +1895,11 @@ static int nfs_parse_devname(const char *dev_name,
size_t len;
char *end;
+ if (unlikely(!dev_name || !*dev_name)) {
+ dfprintk(MOUNT, "NFS: device name not specified\n");
+ return -EINVAL;
+ }
+
/* Is the host name protected with square brakcets? */
if (*dev_name == '[') {
end = strchr(++dev_name, ']');
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5a0bbf917a32..d09c9f878141 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -238,9 +238,9 @@ out:
}
/* A writeback failed: mark the page as bad, and invalidate the page cache */
-static void nfs_set_pageerror(struct page *page)
+static void nfs_set_pageerror(struct address_space *mapping)
{
- nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
+ nfs_zap_mapping(mapping->host, mapping);
}
/*
@@ -621,11 +621,12 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
nfs_set_page_writeback(page);
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
- ret = 0;
+ ret = req->wb_context->error;
/* If there is a fatal error that covers this write, just exit */
- if (nfs_error_is_fatal_on_server(req->wb_context->error))
+ if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
+ ret = 0;
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
@@ -635,9 +636,9 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
nfs_context_set_write_error(req->wb_context, ret);
if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
- }
+ } else
+ ret = -EAGAIN;
nfs_redirty_request(req);
- ret = -EAGAIN;
} else
nfs_add_stats(page_file_mapping(page)->host,
NFSIOS_WRITEPAGES, 1);
@@ -993,7 +994,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
nfs_list_remove_request(req);
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) &&
(hdr->good_bytes < bytes)) {
- nfs_set_pageerror(req->wb_page);
+ nfs_set_pageerror(page_file_mapping(req->wb_page));
nfs_context_set_write_error(req->wb_context, hdr->error);
goto remove_req;
}
@@ -1347,7 +1348,8 @@ int nfs_updatepage(struct file *file, struct page *page,
unsigned int offset, unsigned int count)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
- struct inode *inode = page_file_mapping(page)->host;
+ struct address_space *mapping = page_file_mapping(page);
+ struct inode *inode = mapping->host;
int status = 0;
nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
@@ -1365,7 +1367,7 @@ int nfs_updatepage(struct file *file, struct page *page,
status = nfs_writepage_setup(ctx, page, offset, count);
if (status < 0)
- nfs_set_pageerror(page);
+ nfs_set_pageerror(mapping);
else
__set_page_dirty_nobuffers(page);
out:
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b33f9785b756..72a7681f4046 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1239,8 +1239,8 @@ static __net_init int nfsd_init_net(struct net *net)
retval = nfsd_idmap_init(net);
if (retval)
goto out_idmap_error;
- nn->nfsd4_lease = 45; /* default lease time */
- nn->nfsd4_grace = 45;
+ nn->nfsd4_lease = 90; /* default lease time */
+ nn->nfsd4_grace = 90;
nn->somebody_reclaimed = false;
nn->clverifier_counter = prandom_u32();
nn->clientid_counter = prandom_u32();
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 9824e32b2f23..7dc98e14655d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -557,9 +557,11 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
loff_t cloned;
cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
+ if (cloned < 0)
+ return nfserrno(cloned);
if (count && cloned != count)
- cloned = -EINVAL;
- return nfserrno(cloned < 0 ? cloned : 0);
+ return nfserrno(-EINVAL);
+ return 0;
}
ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 105576daca4a..798f1253141a 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -724,8 +724,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
return -EBADF;
/* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */
- if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE)))
- return -EINVAL;
+ if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE))) {
+ ret = -EINVAL;
+ goto fput_and_out;
+ }
/* verify that this is indeed an inotify instance */
if (unlikely(f.file->f_op != &inotify_fops)) {
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index a5a2fe76568f..b094d3d79354 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -398,8 +398,6 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter
loff_t pos = iocb->ki_pos;
ssize_t rc = 0;
- BUG_ON(iocb->private);
-
gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n");
orangefs_stats.reads++;
@@ -416,8 +414,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
loff_t pos;
ssize_t rc;
- BUG_ON(iocb->private);
-
gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n");
inode_lock(file->f_mapping->host);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 633a63462573..f5ed9512d193 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1086,10 +1086,6 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
task_lock(p);
if (!p->vfork_done && process_shares_mm(p, mm)) {
- pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n",
- task_pid_nr(p), p->comm,
- p->signal->oom_score_adj, oom_adj,
- task_pid_nr(task), task->comm);
p->signal->oom_score_adj = oom_adj;
if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
p->signal->oom_score_adj_min = (short)oom_adj;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ae109429a88..e39bac94dead 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &proc_misc_dentry_ops);
+ d_set_d_op(dentry, de->proc_dops);
return d_splice_alias(inode, dentry);
}
read_unlock(&proc_subdir_lock);
@@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
INIT_LIST_HEAD(&ent->pde_openers);
proc_set_user(ent, (*parent)->uid, (*parent)->gid);
+ ent->proc_dops = &proc_misc_dentry_ops;
+
out:
return ent;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5185d7f6a51e..95b14196f284 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,6 +44,7 @@ struct proc_dir_entry {
struct completion *pde_unload_completion;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
+ const struct dentry_operations *proc_dops;
union {
const struct seq_operations *seq_ops;
int (*single_show)(struct seq_file *, void *);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index d5e0fcb3439e..a7b12435519e 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode)
return maybe_get_net(PDE_NET(PDE(inode)));
}
+static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return 0;
+}
+
+static const struct dentry_operations proc_net_dentry_ops = {
+ .d_revalidate = proc_net_d_revalidate,
+ .d_delete = always_delete_dentry,
+};
+
+static void pde_force_lookup(struct proc_dir_entry *pde)
+{
+ /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
+ pde->proc_dops = &proc_net_dentry_ops;
+}
+
static int seq_open_net(struct inode *inode, struct file *file)
{
unsigned int state_size = PDE(inode)->state_size;
@@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
@@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_seq_fops;
p->seq_ops = ops;
p->state_size = state_size;
@@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
return proc_register(parent, p);
@@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
p = proc_create_reg(name, mode, &parent, data);
if (!p)
return NULL;
+ pde_force_lookup(p);
p->proc_fops = &proc_net_single_fops;
p->single_show = show;
p->write = write;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f0ec9edab2f3..85b0ef890b28 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -423,7 +423,7 @@ struct mem_size_stats {
};
static void smaps_account(struct mem_size_stats *mss, struct page *page,
- bool compound, bool young, bool dirty)
+ bool compound, bool young, bool dirty, bool locked)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
@@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
else
mss->private_clean += size;
mss->pss += (u64)size << PSS_SHIFT;
+ if (locked)
+ mss->pss_locked += (u64)size << PSS_SHIFT;
return;
}
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
+ unsigned long pss = (PAGE_SIZE << PSS_SHIFT);
if (mapcount >= 2) {
if (dirty || PageDirty(page))
mss->shared_dirty += PAGE_SIZE;
else
mss->shared_clean += PAGE_SIZE;
- mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+ mss->pss += pss / mapcount;
+ if (locked)
+ mss->pss_locked += pss / mapcount;
} else {
if (dirty || PageDirty(page))
mss->private_dirty += PAGE_SIZE;
else
mss->private_clean += PAGE_SIZE;
- mss->pss += PAGE_SIZE << PSS_SHIFT;
+ mss->pss += pss;
+ if (locked)
+ mss->pss_locked += pss;
}
}
}
@@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
+ bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
if (pte_present(*pte)) {
@@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
if (!page)
return;
- smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
+ smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
+ bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page;
/* FOLL_DUMP will return -EFAULT on huge zero page */
@@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
/* pass */;
else
VM_BUG_ON_PAGE(1, page);
- smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
+ smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked);
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma,
}
}
#endif
-
/* mmap_sem is held in m_start */
walk_page_vma(vma, &smaps_walk);
- if (vma->vm_flags & VM_LOCKED)
- mss->pss_locked += mss->pss;
}
#define SEQ_PUT_DEC(str, val) \
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 96f7d32cd184..898c8321b343 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -128,7 +128,6 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], int id,
struct pstore_record *record)
{
struct persistent_ram_zone *prz;
- bool update = (record->type == PSTORE_TYPE_DMESG);
/* Give up if we never existed or have hit the end. */
if (!przs)
@@ -139,7 +138,7 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], int id,
return NULL;
/* Update old/shadowed buffer. */
- if (update)
+ if (prz->type == PSTORE_TYPE_DMESG)
persistent_ram_save_old(prz);
if (!persistent_ram_old_size(prz))
@@ -711,18 +710,15 @@ static int ramoops_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct ramoops_platform_data *pdata = dev->platform_data;
+ struct ramoops_platform_data pdata_local;
struct ramoops_context *cxt = &oops_cxt;
size_t dump_mem_sz;
phys_addr_t paddr;
int err = -EINVAL;
if (dev_of_node(dev) && !pdata) {
- pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
- if (!pdata) {
- pr_err("cannot allocate platform data buffer\n");
- err = -ENOMEM;
- goto fail_out;
- }
+ pdata = &pdata_local;
+ memset(pdata, 0, sizeof(*pdata));
err = ramoops_parse_dt(pdev, pdata);
if (err < 0)
diff --git a/fs/read_write.c b/fs/read_write.c
index ff3c5e6f87cf..30df848b7451 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -426,7 +426,7 @@ ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
ssize_t result;
old_fs = get_fs();
- set_fs(get_ds());
+ set_fs(KERNEL_DS);
/* The cast to a user pointer is valid due to the set_fs() */
result = vfs_read(file, (void __user *)buf, count, pos);
set_fs(old_fs);
@@ -499,7 +499,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
return -EINVAL;
old_fs = get_fs();
- set_fs(get_ds());
+ set_fs(KERNEL_DS);
p = (__force const char __user *)buf;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
@@ -521,7 +521,7 @@ ssize_t kernel_write(struct file *file, const void *buf, size_t count,
ssize_t res;
old_fs = get_fs();
- set_fs(get_ds());
+ set_fs(KERNEL_DS);
/* The cast to a user pointer is valid due to the set_fs() */
res = vfs_write(file, (__force const char __user *)buf, count, pos);
set_fs(old_fs);
diff --git a/fs/splice.c b/fs/splice.c
index de2ede048473..6489fb9436e4 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -357,7 +357,7 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
ssize_t res;
old_fs = get_fs();
- set_fs(get_ds());
+ set_fs(KERNEL_DS);
/* The cast to a user pointer is valid due to the set_fs() */
res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
set_fs(old_fs);
@@ -1123,6 +1123,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
if (ipipe == opipe)
return -EINVAL;
+ if ((in->f_flags | out->f_flags) & O_NONBLOCK)
+ flags |= SPLICE_F_NONBLOCK;
+
return splice_pipe_to_pipe(ipipe, opipe, len, flags);
}
@@ -1148,6 +1151,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
if (unlikely(ret < 0))
return ret;
+ if (in->f_flags & O_NONBLOCK)
+ flags |= SPLICE_F_NONBLOCK;
+
file_start_write(out);
ret = do_splice_from(ipipe, out, &offset, len, flags);
file_end_write(out);
@@ -1172,6 +1178,9 @@ static long do_splice(struct file *in, loff_t __user *off_in,
offset = in->f_pos;
}
+ if (out->f_flags & O_NONBLOCK)
+ flags |= SPLICE_F_NONBLOCK;
+
pipe_lock(opipe);
ret = wait_for_space(opipe, flags);
if (!ret)
@@ -1717,6 +1726,9 @@ static long do_tee(struct file *in, struct file *out, size_t len,
* copying the data.
*/
if (ipipe && opipe && ipipe != opipe) {
+ if ((in->f_flags | out->f_flags) & O_NONBLOCK)
+ flags |= SPLICE_F_NONBLOCK;
+
/*
* Keep going, unless we encounter an error. The ipipe/opipe
* ordering doesn't really matter.
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index feeae8081c22..aa85f2874a9f 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -43,7 +43,8 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
kuid_t uid;
kgid_t gid;
- BUG_ON(!kobj);
+ if (WARN_ON(!kobj))
+ return -EINVAL;
if (kobj->parent)
parent = kobj->parent->sd;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index bb71db63c99c..51398457fe00 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -325,7 +325,8 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
kuid_t uid;
kgid_t gid;
- BUG_ON(!kobj || !kobj->sd || !attr);
+ if (WARN_ON(!kobj || !kobj->sd || !attr))
+ return -EINVAL;
kobject_get_ownership(kobj, &uid, &gid);
return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode,
@@ -537,7 +538,8 @@ int sysfs_create_bin_file(struct kobject *kobj,
kuid_t uid;
kgid_t gid;
- BUG_ON(!kobj || !kobj->sd || !attr);
+ if (WARN_ON(!kobj || !kobj->sd || !attr))
+ return -EINVAL;
kobject_get_ownership(kobj, &uid, &gid);
return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true,
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 1eb2d6307663..57038604d4a8 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -112,7 +112,8 @@ static int internal_create_group(struct kobject *kobj, int update,
kgid_t gid;
int error;
- BUG_ON(!kobj || (!update && !kobj->sd));
+ if (WARN_ON(!kobj || (!update && !kobj->sd)))
+ return -EINVAL;
/* Updates may happen before the object has been instantiated */
if (unlikely(update && !kobj->sd))
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 215c225b2ca1..c4deecc80f67 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -23,7 +23,8 @@ static int sysfs_do_create_link_sd(struct kernfs_node *parent,
{
struct kernfs_node *kn, *target = NULL;
- BUG_ON(!name || !parent);
+ if (WARN_ON(!name || !parent))
+ return -EINVAL;
/*
* We don't own @target_kobj and it may be removed at any time.
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 1c8eecfe52b8..6acf1bfa0bfe 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -768,18 +768,23 @@ xrep_findroot_block(
if (!uuid_equal(&btblock->bb_u.s.bb_uuid,
&mp->m_sb.sb_meta_uuid))
goto out;
+ /*
+ * Read verifiers can reference b_ops, so we set the pointer
+ * here. If the verifier fails we'll reset the buffer state
+ * to what it was before we touched the buffer.
+ */
+ bp->b_ops = fab->buf_ops;
fab->buf_ops->verify_read(bp);
if (bp->b_error) {
+ bp->b_ops = NULL;
bp->b_error = 0;
goto out;
}
/*
* Some read verifiers will (re)set b_ops, so we must be
- * careful not to blow away any such assignment.
+ * careful not to change b_ops after running the verifier.
*/
- if (!bp->b_ops)
- bp->b_ops = fab->buf_ops;
}
/*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 338b9d9984e0..d9048bcea49c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -449,6 +449,7 @@ xfs_map_blocks(
}
wpc->imap = imap;
+ xfs_trim_extent_eof(&wpc->imap, ip);
trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
return 0;
allocate_blocks:
@@ -459,6 +460,7 @@ allocate_blocks:
ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF ||
imap.br_startoff + imap.br_blockcount <= cow_fsb);
wpc->imap = imap;
+ xfs_trim_extent_eof(&wpc->imap, ip);
trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
return 0;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index eedc5e0156ff..4f5f2ff3f70f 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -776,10 +776,26 @@ _xfs_buf_read(
}
/*
+ * Set buffer ops on an unchecked buffer and validate it, if possible.
+ *
* If the caller passed in an ops structure and the buffer doesn't have ops
* assigned, set the ops and use them to verify the contents. If the contents
* cannot be verified, we'll clear XBF_DONE. We assume the buffer has no
* recorded errors and is already in XBF_DONE state.
+ *
+ * Under normal operations, every in-core buffer must have buffer ops assigned
+ * to them when the buffer is read in from disk so that we can validate the
+ * metadata.
+ *
+ * However, there are two scenarios where one can encounter in-core buffers
+ * that don't have buffer ops. The first is during log recovery of buffers on
+ * a V4 filesystem, though these buffers are purged at the end of recovery.
+ *
+ * The other is online repair, which tries to match arbitrary metadata blocks
+ * with btree types in order to find the root. If online repair doesn't match
+ * the buffer with /any/ btree type, the buffer remains in memory in DONE state
+ * with no ops, and a subsequent read_buf call from elsewhere will not set the
+ * ops. This function helps us fix this situation.
*/
int
xfs_buf_ensure_ops(
@@ -1536,8 +1552,7 @@ __xfs_buf_submit(
xfs_buf_ioerror(bp, -EIO);
bp->b_flags &= ~XBF_DONE;
xfs_buf_stale(bp);
- if (bp->b_flags & XBF_ASYNC)
- xfs_buf_ioend(bp);
+ xfs_buf_ioend(bp);
return -EIO;
}