summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/cell.c4
-rw-r--r--fs/afs/dir.c3
-rw-r--r--fs/afs/yfsclient.c2
-rw-r--r--fs/ceph/addr.c5
-rw-r--r--fs/ceph/caps.c5
-rw-r--r--fs/ceph/inode.c7
-rw-r--r--fs/ceph/locks.c3
-rw-r--r--fs/ceph/snap.c4
-rw-r--r--fs/ceph/super.h2
-rw-r--r--fs/ceph/xattr.c19
-rw-r--r--fs/cifs/connect.c2
-rw-r--r--fs/io_uring.c66
-rw-r--r--fs/nfsd/nfscache.c2
-rw-r--r--fs/nfsd/nfsctl.c19
-rw-r--r--fs/read_write.c49
-rw-r--r--fs/userfaultfd.c25
-rw-r--r--fs/xfs/xfs_ioctl32.c56
-rw-r--r--fs/xfs/xfs_iops.c1
-rw-r--r--fs/xfs/xfs_pnfs.c2
-rw-r--r--fs/xfs/xfs_reflink.c63
20 files changed, 191 insertions, 148 deletions
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index a2a87117d262..fd5133e26a38 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -74,6 +74,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
cell = rcu_dereference_raw(net->ws_cell);
if (cell) {
afs_get_cell(cell);
+ ret = 0;
break;
}
ret = -EDESTADDRREQ;
@@ -108,6 +109,9 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
done_seqretry(&net->cells_lock, seq);
+ if (ret != 0 && cell)
+ afs_put_cell(net, cell);
+
return ret == 0 ? cell : ERR_PTR(ret);
}
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 81207dc3c997..139b4e3cc946 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -959,7 +959,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
inode ? AFS_FS_I(inode) : NULL);
} else {
trace_afs_lookup(dvnode, &dentry->d_name,
- inode ? AFS_FS_I(inode) : NULL);
+ IS_ERR_OR_NULL(inode) ? NULL
+ : AFS_FS_I(inode));
}
return d;
}
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 2575503170fc..ca2452806ebf 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -2171,7 +2171,7 @@ int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl
key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode);
size = round_up(acl->size, 4);
- call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus,
+ call = afs_alloc_flat_call(net, &yfs_RXYFSStoreOpaqueACL2,
sizeof(__be32) * 2 +
sizeof(struct yfs_xdr_YFSFid) +
sizeof(__be32) + size,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e078cc55b989..b3c8b886bf64 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -913,8 +913,9 @@ get_more_pages:
if (page_offset(page) >= ceph_wbc.i_size) {
dout("%p page eof %llu\n",
page, ceph_wbc.i_size);
- if (ceph_wbc.size_stable ||
- page_offset(page) >= i_size_read(inode))
+ if ((ceph_wbc.size_stable ||
+ page_offset(page) >= i_size_read(inode)) &&
+ clear_page_dirty_for_io(page))
mapping->a_ops->invalidatepage(page,
0, PAGE_SIZE);
unlock_page(page);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d98dcd976c80..ce0f5658720a 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1301,6 +1301,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
{
struct ceph_inode_info *ci = cap->ci;
struct inode *inode = &ci->vfs_inode;
+ struct ceph_buffer *old_blob = NULL;
struct cap_msg_args arg;
int held, revoking;
int wake = 0;
@@ -1365,7 +1366,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
ci->i_requested_max_size = arg.max_size;
if (flushing & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
arg.xattr_version = ci->i_xattrs.version;
arg.xattr_buf = ci->i_xattrs.blob;
} else {
@@ -1409,6 +1410,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
+
ret = send_cap_msg(&arg);
if (ret < 0) {
dout("error sending cap msg, must requeue %p\n", inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 791f84a13bb8..18500edefc56 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -736,6 +736,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
int issued, new_issued, info_caps;
struct timespec64 mtime, atime, ctime;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_buffer *old_blob = NULL;
struct ceph_string *pool_ns = NULL;
struct ceph_cap *new_cap = NULL;
int err = 0;
@@ -881,7 +882,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) &&
le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = xattr_blob;
if (xattr_blob)
memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1022,8 +1023,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
out:
if (new_cap)
ceph_put_cap(mdsc, new_cap);
- if (xattr_blob)
- ceph_buffer_put(xattr_blob);
+ ceph_buffer_put(old_blob);
+ ceph_buffer_put(xattr_blob);
ceph_put_string(pool_ns);
return err;
}
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ac9b53b89365..5083e238ad15 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -111,8 +111,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode,
req->r_wait_for_completion = ceph_lock_wait_for_completion;
err = ceph_mdsc_do_request(mdsc, inode, req);
-
- if (operation == CEPH_MDS_OP_GETFILELOCK) {
+ if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4c6494eb02b5..ccfcc66aaf44 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -465,6 +465,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
struct inode *inode = &ci->vfs_inode;
struct ceph_cap_snap *capsnap;
struct ceph_snap_context *old_snapc, *new_snapc;
+ struct ceph_buffer *old_blob = NULL;
int used, dirty;
capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
@@ -541,7 +542,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
capsnap->gid = inode->i_gid;
if (dirty & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
capsnap->xattr_blob =
ceph_buffer_get(ci->i_xattrs.blob);
capsnap->xattr_version = ci->i_xattrs.version;
@@ -584,6 +585,7 @@ update_snapc:
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
kfree(capsnap);
ceph_put_snap_context(old_snapc);
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index d2352fd95dbc..6b9f1ee7de85 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -926,7 +926,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,
int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
extern const struct xattr_handler *ceph_xattr_handlers[];
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 37b458a9af3a..939eab7aa219 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -754,12 +754,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,
/*
* If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place. It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
*/
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
{
struct rb_node *p;
struct ceph_inode_xattr *xattr = NULL;
+ struct ceph_buffer *old_blob = NULL;
void *dest;
dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
@@ -790,12 +793,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = NULL;
ci->i_xattrs.dirty = false;
ci->i_xattrs.version++;
}
+
+ return old_blob;
}
static inline int __get_request_mask(struct inode *in) {
@@ -1036,6 +1041,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf = NULL;
+ struct ceph_buffer *old_blob = NULL;
int issued;
int err;
int dirty = 0;
@@ -1109,13 +1115,15 @@ retry:
struct ceph_buffer *blob;
spin_unlock(&ci->i_ceph_lock);
- dout(" preaallocating new blob size=%d\n", required_blob_size);
+ ceph_buffer_put(old_blob); /* Shouldn't be required */
+ dout(" pre-allocating new blob size=%d\n", required_blob_size);
blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
if (!blob)
goto do_sync_unlocked;
spin_lock(&ci->i_ceph_lock);
+ /* prealloc_blob can't be released while holding i_ceph_lock */
if (ci->i_xattrs.prealloc_blob)
- ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+ old_blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = blob;
goto retry;
}
@@ -1131,6 +1139,7 @@ retry:
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
if (lock_snap_rwsem)
up_read(&mdsc->snap_rwsem);
if (dirty)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a15a6e738eb5..1795e80cbdf7 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1113,7 +1113,7 @@ cifs_demultiplex_thread(void *p)
mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
set_freezable();
- allow_signal(SIGKILL);
+ allow_kernel_signal(SIGKILL);
while (server->tcpStatus != CifsExiting) {
if (try_to_freeze())
continue;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 24bbe3cb7ad4..cfb48bd088e1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -679,6 +679,13 @@ static void io_put_req(struct io_kiocb *req)
io_free_req(req);
}
+static unsigned io_cqring_events(struct io_cq_ring *ring)
+{
+ /* See comment at the top of this file */
+ smp_rmb();
+ return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
+}
+
/*
* Find and free completed poll iocbs
*/
@@ -771,7 +778,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
long min)
{
- while (!list_empty(&ctx->poll_list)) {
+ while (!list_empty(&ctx->poll_list) && !need_resched()) {
int ret;
ret = io_do_iopoll(ctx, nr_events, min);
@@ -798,6 +805,12 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
unsigned int nr_events = 0;
io_iopoll_getevents(ctx, &nr_events, 1);
+
+ /*
+ * Ensure we allow local-to-the-cpu processing to take place,
+ * in this case we need to ensure that we reap all events.
+ */
+ cond_resched();
}
mutex_unlock(&ctx->uring_lock);
}
@@ -805,11 +818,42 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
long min)
{
- int ret = 0;
+ int iters, ret = 0;
+ /*
+ * We disallow the app entering submit/complete with polling, but we
+ * still need to lock the ring to prevent racing with polled issue
+ * that got punted to a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
+
+ iters = 0;
do {
int tmin = 0;
+ /*
+ * Don't enter poll loop if we already have events pending.
+ * If we do, we can potentially be spinning for commands that
+ * already triggered a CQE (eg in error).
+ */
+ if (io_cqring_events(ctx->cq_ring))
+ break;
+
+ /*
+ * If a submit got punted to a workqueue, we can have the
+ * application entering polling for a command before it gets
+ * issued. That app will hold the uring_lock for the duration
+ * of the poll right here, so we need to take a breather every
+ * now and then to ensure that the issue has a chance to add
+ * the poll to the issued list. Otherwise we can spin here
+ * forever, while the workqueue is stuck trying to acquire the
+ * very same mutex.
+ */
+ if (!(++iters & 7)) {
+ mutex_unlock(&ctx->uring_lock);
+ mutex_lock(&ctx->uring_lock);
+ }
+
if (*nr_events < min)
tmin = min - *nr_events;
@@ -819,6 +863,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
ret = 0;
} while (min && !*nr_events && !need_resched());
+ mutex_unlock(&ctx->uring_lock);
return ret;
}
@@ -2280,15 +2325,7 @@ static int io_sq_thread(void *data)
unsigned nr_events = 0;
if (ctx->flags & IORING_SETUP_IOPOLL) {
- /*
- * We disallow the app entering submit/complete
- * with polling, but we still need to lock the
- * ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
io_iopoll_check(ctx, &nr_events, 0);
- mutex_unlock(&ctx->uring_lock);
} else {
/*
* Normal IO, just pretend everything completed.
@@ -2433,13 +2470,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
return submit;
}
-static unsigned io_cqring_events(struct io_cq_ring *ring)
-{
- /* See comment at the top of this file */
- smp_rmb();
- return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
-}
-
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
@@ -3190,9 +3220,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
min_complete = min(min_complete, ctx->cq_entries);
if (ctx->flags & IORING_SETUP_IOPOLL) {
- mutex_lock(&ctx->uring_lock);
ret = io_iopoll_check(ctx, &nr_events, min_complete);
- mutex_unlock(&ctx->uring_lock);
} else {
ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 26ad75ae2be0..96352ab7bd81 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -571,7 +571,7 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
*/
static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
{
- struct nfsd_net *nn = v;
+ struct nfsd_net *nn = m->private;
seq_printf(m, "max entries: %u\n", nn->max_drc_entries);
seq_printf(m, "num entries: %u\n",
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 13c548733860..3cf4f6aa48d6 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1171,13 +1171,17 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
return inode;
}
-static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl)
{
struct inode *inode;
inode = nfsd_get_inode(dir->i_sb, mode);
if (!inode)
return -ENOMEM;
+ if (ncl) {
+ inode->i_private = ncl;
+ kref_get(&ncl->cl_ref);
+ }
d_add(dentry, inode);
inc_nlink(dir);
fsnotify_mkdir(dir, dentry);
@@ -1194,17 +1198,14 @@ static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *nc
dentry = d_alloc_name(parent, name);
if (!dentry)
goto out_err;
- ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600);
+ ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl);
if (ret)
goto out_err;
- if (ncl) {
- d_inode(dentry)->i_private = ncl;
- kref_get(&ncl->cl_ref);
- }
out:
inode_unlock(dir);
return dentry;
out_err:
+ dput(dentry);
dentry = ERR_PTR(ret);
goto out;
}
@@ -1214,11 +1215,9 @@ static void clear_ncl(struct inode *inode)
struct nfsdfs_client *ncl = inode->i_private;
inode->i_private = NULL;
- synchronize_rcu();
kref_put(&ncl->cl_ref, ncl->cl_release);
}
-
static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc = inode->i_private;
@@ -1232,9 +1231,9 @@ struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc;
- rcu_read_lock();
+ inode_lock_shared(inode);
nc = __get_nfsdfs_client(inode);
- rcu_read_unlock();
+ inode_unlock_shared(inode);
return nc;
}
/* from __rpc_unlink */
diff --git a/fs/read_write.c b/fs/read_write.c
index 1f5088dec566..5bbf587f5bc1 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1811,10 +1811,7 @@ static int generic_remap_check_len(struct inode *inode_in,
return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
}
-/*
- * Read a page's worth of file data into the page cache. Return the page
- * locked.
- */
+/* Read a page's worth of file data into the page cache. */
static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
{
struct page *page;
@@ -1826,11 +1823,33 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
put_page(page);
return ERR_PTR(-EIO);
}
- lock_page(page);
return page;
}
/*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+ /* Always lock in order of increasing index. */
+ if (page1->index > page2->index)
+ swap(page1, page2);
+
+ lock_page(page1);
+ if (page1 != page2)
+ lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+ unlock_page(page1);
+ if (page1 != page2)
+ unlock_page(page2);
+}
+
+/*
* Compare extents of two files to see if they are the same.
* Caller must have locked both inodes to prevent write races.
*/
@@ -1867,10 +1886,24 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
dest_page = vfs_dedupe_get_page(dest, destoff);
if (IS_ERR(dest_page)) {
error = PTR_ERR(dest_page);
- unlock_page(src_page);
put_page(src_page);
goto out_error;
}
+
+ vfs_lock_two_pages(src_page, dest_page);
+
+ /*
+ * Now that we've locked both pages, make sure they're still
+ * mapped to the file data we're interested in. If not,
+ * someone is invalidating pages on us and we lose.
+ */
+ if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+ src_page->mapping != src->i_mapping ||
+ dest_page->mapping != dest->i_mapping) {
+ same = false;
+ goto unlock;
+ }
+
src_addr = kmap_atomic(src_page);
dest_addr = kmap_atomic(dest_page);
@@ -1882,8 +1915,8 @@ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
kunmap_atomic(dest_addr);
kunmap_atomic(src_addr);
- unlock_page(dest_page);
- unlock_page(src_page);
+unlock:
+ vfs_unlock_two_pages(src_page, dest_page);
put_page(dest_page);
put_page(src_page);
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ccbdbd62f0d8..fe6d804a38dc 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -880,6 +880,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
unsigned long new_flags;
+ bool still_valid;
WRITE_ONCE(ctx->released, true);
@@ -895,8 +896,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
* taking the mmap_sem for writing.
*/
down_write(&mm->mmap_sem);
- if (!mmget_still_valid(mm))
- goto skip_mm;
+ still_valid = mmget_still_valid(mm);
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
@@ -907,19 +907,20 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
continue;
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
- prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
- new_flags, vma->anon_vma,
- vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX);
- if (prev)
- vma = prev;
- else
- prev = vma;
+ if (still_valid) {
+ prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+ new_flags, vma->anon_vma,
+ vma->vm_file, vma->vm_pgoff,
+ vma_policy(vma),
+ NULL_VM_UFFD_CTX);
+ if (prev)
+ vma = prev;
+ else
+ prev = vma;
+ }
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
-skip_mm:
up_write(&mm->mmap_sem);
mmput(mm);
wakeup:
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 7fcf7569743f..7bd7534f5051 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -547,63 +547,12 @@ xfs_file_compat_ioctl(
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- void __user *arg = (void __user *)p;
+ void __user *arg = compat_ptr(p);
int error;
trace_xfs_file_compat_ioctl(ip);
switch (cmd) {
- /* No size or alignment issues on any arch */
- case XFS_IOC_DIOINFO:
- case XFS_IOC_FSGEOMETRY_V4:
- case XFS_IOC_FSGEOMETRY:
- case XFS_IOC_AG_GEOMETRY:
- case XFS_IOC_FSGETXATTR:
- case XFS_IOC_FSSETXATTR:
- case XFS_IOC_FSGETXATTRA:
- case XFS_IOC_FSSETDM:
- case XFS_IOC_GETBMAP:
- case XFS_IOC_GETBMAPA:
- case XFS_IOC_GETBMAPX:
- case XFS_IOC_FSCOUNTS:
- case XFS_IOC_SET_RESBLKS:
- case XFS_IOC_GET_RESBLKS:
- case XFS_IOC_FSGROWFSLOG:
- case XFS_IOC_GOINGDOWN:
- case XFS_IOC_ERROR_INJECTION:
- case XFS_IOC_ERROR_CLEARALL:
- case FS_IOC_GETFSMAP:
- case XFS_IOC_SCRUB_METADATA:
- case XFS_IOC_BULKSTAT:
- case XFS_IOC_INUMBERS:
- return xfs_file_ioctl(filp, cmd, p);
-#if !defined(BROKEN_X86_ALIGNMENT) || defined(CONFIG_X86_X32)
- /*
- * These are handled fine if no alignment issues. To support x32
- * which uses native 64-bit alignment we must emit these cases in
- * addition to the ia-32 compat set below.
- */
- case XFS_IOC_ALLOCSP:
- case XFS_IOC_FREESP:
- case XFS_IOC_RESVSP:
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_ALLOCSP64:
- case XFS_IOC_FREESP64:
- case XFS_IOC_RESVSP64:
- case XFS_IOC_UNRESVSP64:
- case XFS_IOC_FSGEOMETRY_V1:
- case XFS_IOC_FSGROWFSDATA:
- case XFS_IOC_FSGROWFSRT:
- case XFS_IOC_ZERO_RANGE:
-#ifdef CONFIG_X86_X32
- /*
- * x32 special: this gets a different cmd number from the ia-32 compat
- * case below; the associated data will match native 64-bit alignment.
- */
- case XFS_IOC_SWAPEXT:
-#endif
- return xfs_file_ioctl(filp, cmd, p);
-#endif
#if defined(BROKEN_X86_ALIGNMENT)
case XFS_IOC_ALLOCSP_32:
case XFS_IOC_FREESP_32:
@@ -705,6 +654,7 @@ xfs_file_compat_ioctl(
case XFS_IOC_FSSETDM_BY_HANDLE_32:
return xfs_compat_fssetdm_by_handle(filp, arg);
default:
- return -ENOIOCTLCMD;
+ /* try the native version */
+ return xfs_file_ioctl(filp, cmd, (unsigned long)arg);
}
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ff3c1fae5357..fe285d123d69 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -793,6 +793,7 @@ xfs_setattr_nonsize(
out_cancel:
xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 0c954cad7449..a339bd5fa260 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -32,7 +32,7 @@ xfs_break_leased_layouts(
struct xfs_inode *ip = XFS_I(inode);
int error;
- while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+ while ((error = break_layout(inode, false)) == -EWOULDBLOCK) {
xfs_iunlock(ip, *iolock);
*did_unlock = true;
error = break_layout(inode, true);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c4ec7afd1170..edbe37b7f636 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1190,11 +1190,11 @@ xfs_reflink_remap_blocks(
}
/*
- * Grab the exclusive iolock for a data copy from src to dest, making
- * sure to abide vfs locking order (lowest pointer value goes first) and
- * breaking the pnfs layout leases on dest before proceeding. The loop
- * is needed because we cannot call the blocking break_layout() with the
- * src iolock held, and therefore have to back out both locks.
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding. The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
*/
static int
xfs_iolock_two_inodes_and_break_layout(
@@ -1203,33 +1203,44 @@ xfs_iolock_two_inodes_and_break_layout(
{
int error;
-retry:
- if (src < dest) {
- inode_lock_shared(src);
- inode_lock_nested(dest, I_MUTEX_NONDIR2);
- } else {
- /* src >= dest */
- inode_lock(dest);
- }
+ if (src > dest)
+ swap(src, dest);
- error = break_layout(dest, false);
- if (error == -EWOULDBLOCK) {
- inode_unlock(dest);
- if (src < dest)
- inode_unlock_shared(src);
+retry:
+ /* Wait to break both inodes' layouts before we start locking. */
+ error = break_layout(src, true);
+ if (error)
+ return error;
+ if (src != dest) {
error = break_layout(dest, true);
if (error)
return error;
- goto retry;
}
+
+ /* Lock one inode and make sure nobody got in and leased it. */
+ inode_lock(src);
+ error = break_layout(src, false);
if (error) {
+ inode_unlock(src);
+ if (error == -EWOULDBLOCK)
+ goto retry;
+ return error;
+ }
+
+ if (src == dest)
+ return 0;
+
+ /* Lock the other inode and make sure nobody got in and leased it. */
+ inode_lock_nested(dest, I_MUTEX_NONDIR2);
+ error = break_layout(dest, false);
+ if (error) {
+ inode_unlock(src);
inode_unlock(dest);
- if (src < dest)
- inode_unlock_shared(src);
+ if (error == -EWOULDBLOCK)
+ goto retry;
return error;
}
- if (src > dest)
- inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
+
return 0;
}
@@ -1247,10 +1258,10 @@ xfs_reflink_remap_unlock(
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
if (!same_inode)
- xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
+ xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
inode_unlock(inode_out);
if (!same_inode)
- inode_unlock_shared(inode_in);
+ inode_unlock(inode_in);
}
/*
@@ -1325,7 +1336,7 @@ xfs_reflink_remap_prep(
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
- xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
+ xfs_lock_two_inodes(src, XFS_MMAPLOCK_EXCL, dest,
XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-23 08:43:39 +0300