aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/disk-io.c1
-rw-r--r--fs/btrfs/inode.c21
-rw-r--r--fs/btrfs/send.c16
-rw-r--r--fs/cifs/cifssmb.c21
-rw-r--r--fs/hostfs/hostfs_kern.c4
-rw-r--r--fs/jffs2/README.Locking5
-rw-r--r--fs/jffs2/build.c75
-rw-r--r--fs/jffs2/file.c39
-rw-r--r--fs/jffs2/gc.c17
-rw-r--r--fs/jffs2/nodelist.h6
-rw-r--r--fs/lockd/host.c7
-rw-r--r--fs/lockd/mon.c36
-rw-r--r--fs/lockd/netns.h1
-rw-r--r--fs/lockd/svc.c1
-rw-r--r--fs/lockd/svc4proc.c2
-rw-r--r--fs/lockd/svcproc.c2
-rw-r--r--fs/locks.c51
-rw-r--r--fs/namei.c4
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/proc/task_mmu.c4
-rw-r--r--fs/proc/task_nommu.c2
-rw-r--r--fs/splice.c13
22 files changed, 224 insertions, 106 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7360f03ddbe1..9612a01198df 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2437,6 +2437,7 @@ int open_ctree(struct super_block *sb,
"unsupported option features (%Lx).\n",
(unsigned long long)features);
err = -EINVAL;
+ brelse(bh);
goto fail_alloc;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ae29b403a7e2..b5d13c4eea00 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7477,15 +7477,28 @@ int btrfs_readpage(struct file *file, struct page *page)
static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
{
struct extent_io_tree *tree;
-
+ struct inode *inode = page->mapping->host;
+ int ret;
if (current->flags & PF_MEMALLOC) {
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
+
+ /*
+ * If we are under memory pressure we will call this directly from the
+ * VM, we need to make sure we have the inode referenced for the ordered
+ * extent. If not just return like we didn't do anything.
+ */
+ if (!igrab(inode)) {
+ redirty_page_for_writepage(wbc, page);
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
tree = &BTRFS_I(page->mapping->host)->io_tree;
- return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+ ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+ btrfs_add_delayed_iput(inode);
+ return ret;
}
static int btrfs_writepages(struct address_space *mapping,
@@ -8474,9 +8487,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
/*
* 2 items for inode item and ref
* 2 items for dir items
+ * 1 item for updating parent inode item
+ * 1 item for the inline extent item
* 1 item for xattr if selinux is on
*/
- trans = btrfs_start_transaction(root, 5);
+ trans = btrfs_start_transaction(root, 7);
if (IS_ERR(trans))
return PTR_ERR(trans);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 414c1b9eb896..3104e0eec816 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1338,7 +1338,21 @@ static int read_symlink(struct send_ctx *sctx,
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
- BUG_ON(ret);
+ if (ret) {
+ /*
+ * An empty symlink inode. Can happen in rare error paths when
+ * creating a symlink (transaction committed before the inode
+ * eviction handler removed the symlink inode items and a crash
+ * happened in between or the subvol was snapshoted in between).
+ * Print an informative message to dmesg/syslog so that the user
+ * can delete the symlink.
+ */
+ btrfs_err(root->fs_info,
+ "Found empty symlink inode %llu at root %llu",
+ ino, root->root_key.objectid);
+ ret = -EIO;
+ goto out;
+ }
ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_file_extent_item);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d17c5d72cd29..4c86850bd627 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1389,11 +1389,10 @@ openRetry:
* current bigbuf.
*/
static int
-cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+discard_remaining_data(struct TCP_Server_Info *server)
{
unsigned int rfclen = get_rfc1002_length(server->smallbuf);
int remaining = rfclen + 4 - server->total_read;
- struct cifs_readdata *rdata = mid->callback_data;
while (remaining > 0) {
int length;
@@ -1407,10 +1406,20 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
remaining -= length;
}
- dequeue_mid(mid, rdata->result);
return 0;
}
+static int
+cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+ int length;
+ struct cifs_readdata *rdata = mid->callback_data;
+
+ length = discard_remaining_data(server);
+ dequeue_mid(mid, rdata->result);
+ return length;
+}
+
int
cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
{
@@ -1439,6 +1448,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
return length;
server->total_read += length;
+ if (server->ops->is_status_pending &&
+ server->ops->is_status_pending(buf, server, 0)) {
+ discard_remaining_data(server);
+ return -1;
+ }
+
/* Was the SMB read successful? */
rdata->result = server->ops->map_error(buf, false);
if (rdata->result != 0) {
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 32f35f187989..b58a9cbb9695 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -720,15 +720,13 @@ static int hostfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
init_special_inode(inode, mode, dev);
err = do_mknod(name, mode, MAJOR(dev), MINOR(dev));
- if (!err)
+ if (err)
goto out_free;
err = read_name(inode, name);
__putname(name);
if (err)
goto out_put;
- if (err)
- goto out_put;
d_instantiate(dentry, inode);
return 0;
diff --git a/fs/jffs2/README.Locking b/fs/jffs2/README.Locking
index 3ea36554107f..8918ac905a3b 100644
--- a/fs/jffs2/README.Locking
+++ b/fs/jffs2/README.Locking
@@ -2,10 +2,6 @@
JFFS2 LOCKING DOCUMENTATION
---------------------------
-At least theoretically, JFFS2 does not require the Big Kernel Lock
-(BKL), which was always helpfully obtained for it by Linux 2.4 VFS
-code. It has its own locking, as described below.
-
This document attempts to describe the existing locking rules for
JFFS2. It is not expected to remain perfectly up to date, but ought to
be fairly close.
@@ -69,6 +65,7 @@ Ordering constraints:
any f->sem held.
2. Never attempt to lock two file mutexes in one thread.
No ordering rules have been made for doing so.
+ 3. Never lock a page cache page with f->sem held.
erase_completion_lock spinlock
diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c
index a3750f902adc..c1f04947d7dc 100644
--- a/fs/jffs2/build.c
+++ b/fs/jffs2/build.c
@@ -49,7 +49,8 @@ next_inode(int *i, struct jffs2_inode_cache *ic, struct jffs2_sb_info *c)
static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
- struct jffs2_inode_cache *ic)
+ struct jffs2_inode_cache *ic,
+ int *dir_hardlinks)
{
struct jffs2_full_dirent *fd;
@@ -68,19 +69,21 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
dbg_fsbuild("child \"%s\" (ino #%u) of dir ino #%u doesn't exist!\n",
fd->name, fd->ino, ic->ino);
jffs2_mark_node_obsolete(c, fd->raw);
+ /* Clear the ic/raw union so it doesn't cause problems later. */
+ fd->ic = NULL;
continue;
}
+ /* From this point, fd->raw is no longer used so we can set fd->ic */
+ fd->ic = child_ic;
+ child_ic->pino_nlink++;
+ /* If we appear (at this stage) to have hard-linked directories,
+ * set a flag to trigger a scan later */
if (fd->type == DT_DIR) {
- if (child_ic->pino_nlink) {
- JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u appears to be a hard link\n",
- fd->name, fd->ino, ic->ino);
- /* TODO: What do we do about it? */
- } else {
- child_ic->pino_nlink = ic->ino;
- }
- } else
- child_ic->pino_nlink++;
+ child_ic->flags |= INO_FLAGS_IS_DIR;
+ if (child_ic->pino_nlink > 1)
+ *dir_hardlinks = 1;
+ }
dbg_fsbuild("increased nlink for child \"%s\" (ino #%u)\n", fd->name, fd->ino);
/* Can't free scan_dents so far. We might need them in pass 2 */
@@ -94,8 +97,7 @@ static void jffs2_build_inode_pass1(struct jffs2_sb_info *c,
*/
static int jffs2_build_filesystem(struct jffs2_sb_info *c)
{
- int ret;
- int i;
+ int ret, i, dir_hardlinks = 0;
struct jffs2_inode_cache *ic;
struct jffs2_full_dirent *fd;
struct jffs2_full_dirent *dead_fds = NULL;
@@ -119,7 +121,7 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
/* Now scan the directory tree, increasing nlink according to every dirent found. */
for_each_inode(i, c, ic) {
if (ic->scan_dents) {
- jffs2_build_inode_pass1(c, ic);
+ jffs2_build_inode_pass1(c, ic, &dir_hardlinks);
cond_resched();
}
}
@@ -155,6 +157,20 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
}
dbg_fsbuild("pass 2a complete\n");
+
+ if (dir_hardlinks) {
+ /* If we detected directory hardlinks earlier, *hopefully*
+ * they are gone now because some of the links were from
+ * dead directories which still had some old dirents lying
+ * around and not yet garbage-collected, but which have
+ * been discarded above. So clear the pino_nlink field
+ * in each directory, so that the final scan below can
+ * print appropriate warnings. */
+ for_each_inode(i, c, ic) {
+ if (ic->flags & INO_FLAGS_IS_DIR)
+ ic->pino_nlink = 0;
+ }
+ }
dbg_fsbuild("freeing temporary data structures\n");
/* Finally, we can scan again and free the dirent structs */
@@ -162,6 +178,33 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c)
while(ic->scan_dents) {
fd = ic->scan_dents;
ic->scan_dents = fd->next;
+ /* We do use the pino_nlink field to count nlink of
+ * directories during fs build, so set it to the
+ * parent ino# now. Now that there's hopefully only
+ * one. */
+ if (fd->type == DT_DIR) {
+ if (!fd->ic) {
+ /* We'll have complained about it and marked the coresponding
+ raw node obsolete already. Just skip it. */
+ continue;
+ }
+
+ /* We *have* to have set this in jffs2_build_inode_pass1() */
+ BUG_ON(!(fd->ic->flags & INO_FLAGS_IS_DIR));
+
+ /* We clear ic->pino_nlink ∀ directories' ic *only* if dir_hardlinks
+ * is set. Otherwise, we know this should never trigger anyway, so
+ * we don't do the check. And ic->pino_nlink still contains the nlink
+ * value (which is 1). */
+ if (dir_hardlinks && fd->ic->pino_nlink) {
+ JFFS2_ERROR("child dir \"%s\" (ino #%u) of dir ino #%u is also hard linked from dir ino #%u\n",
+ fd->name, fd->ino, ic->ino, fd->ic->pino_nlink);
+ /* Should we unlink it from its previous parent? */
+ }
+
+ /* For directories, ic->pino_nlink holds that parent inode # */
+ fd->ic->pino_nlink = ic->ino;
+ }
jffs2_free_full_dirent(fd);
}
ic->scan_dents = NULL;
@@ -240,11 +283,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *c,
/* Reduce nlink of the child. If it's now zero, stick it on the
dead_fds list to be cleaned up later. Else just free the fd */
-
- if (fd->type == DT_DIR)
- child_ic->pino_nlink = 0;
- else
- child_ic->pino_nlink--;
+ child_ic->pino_nlink--;
if (!child_ic->pino_nlink) {
dbg_fsbuild("inode #%u (\"%s\") now has no links; adding to dead_fds list.\n",
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 1506673c087e..60ef3fb707ff 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -138,39 +138,33 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
struct page *pg;
struct inode *inode = mapping->host;
struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
- struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
- struct jffs2_raw_inode ri;
- uint32_t alloc_len = 0;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
uint32_t pageofs = index << PAGE_CACHE_SHIFT;
int ret = 0;
- jffs2_dbg(1, "%s()\n", __func__);
-
- if (pageofs > inode->i_size) {
- ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
- ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
- if (ret)
- return ret;
- }
-
- mutex_lock(&f->sem);
pg = grab_cache_page_write_begin(mapping, index, flags);
- if (!pg) {
- if (alloc_len)
- jffs2_complete_reservation(c);
- mutex_unlock(&f->sem);
+ if (!pg)
return -ENOMEM;
- }
*pagep = pg;
- if (alloc_len) {
+ jffs2_dbg(1, "%s()\n", __func__);
+
+ if (pageofs > inode->i_size) {
/* Make new hole frag from old EOF to new page */
+ struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+ struct jffs2_raw_inode ri;
struct jffs2_full_dnode *fn;
+ uint32_t alloc_len;
jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
(unsigned int)inode->i_size, pageofs);
+ ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+ ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+ if (ret)
+ goto out_page;
+
+ mutex_lock(&f->sem);
memset(&ri, 0, sizeof(ri));
ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -197,6 +191,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
if (IS_ERR(fn)) {
ret = PTR_ERR(fn);
jffs2_complete_reservation(c);
+ mutex_unlock(&f->sem);
goto out_page;
}
ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -211,10 +206,12 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
jffs2_mark_node_obsolete(c, fn->raw);
jffs2_free_full_dnode(fn);
jffs2_complete_reservation(c);
+ mutex_unlock(&f->sem);
goto out_page;
}
jffs2_complete_reservation(c);
inode->i_size = pageofs;
+ mutex_unlock(&f->sem);
}
/*
@@ -223,18 +220,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
* case of a short-copy.
*/
if (!PageUptodate(pg)) {
+ mutex_lock(&f->sem);
ret = jffs2_do_readpage_nolock(inode, pg);
+ mutex_unlock(&f->sem);
if (ret)
goto out_page;
}
- mutex_unlock(&f->sem);
jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
return ret;
out_page:
unlock_page(pg);
page_cache_release(pg);
- mutex_unlock(&f->sem);
return ret;
}
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 5a2dec2b064c..95d5880a63ee 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -1296,14 +1296,17 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
BUG_ON(start > orig_start);
}
- /* First, use readpage() to read the appropriate page into the page cache */
- /* Q: What happens if we actually try to GC the _same_ page for which commit_write()
- * triggered garbage collection in the first place?
- * A: I _think_ it's OK. read_cache_page shouldn't deadlock, we'll write out the
- * page OK. We'll actually write it out again in commit_write, which is a little
- * suboptimal, but at least we're correct.
- */
+ /* The rules state that we must obtain the page lock *before* f->sem, so
+ * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
+ * actually going to *change* so we're safe; we only allow reading.
+ *
+ * It is important to note that jffs2_write_begin() will ensure that its
+ * page is marked Uptodate before allocating space. That means that if we
+ * end up here trying to GC the *same* page that jffs2_write_begin() is
+ * trying to write out, read_cache_page() will not deadlock. */
+ mutex_unlock(&f->sem);
pg_ptr = jffs2_gc_fetch_page(c, f, start, &pg);
+ mutex_lock(&f->sem);
if (IS_ERR(pg_ptr)) {
pr_warn("read_cache_page() returned error: %ld\n",
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index fa35ff79ab35..0637271f3770 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -194,6 +194,7 @@ struct jffs2_inode_cache {
#define INO_STATE_CLEARING 6 /* In clear_inode() */
#define INO_FLAGS_XATTR_CHECKED 0x01 /* has no duplicate xattr_ref */
+#define INO_FLAGS_IS_DIR 0x02 /* is a directory */
#define RAWNODE_CLASS_INODE_CACHE 0
#define RAWNODE_CLASS_XATTR_DATUM 1
@@ -249,7 +250,10 @@ struct jffs2_readinode_info
struct jffs2_full_dirent
{
- struct jffs2_raw_node_ref *raw;
+ union {
+ struct jffs2_raw_node_ref *raw;
+ struct jffs2_inode_cache *ic; /* Just during part of build */
+ };
struct jffs2_full_dirent *next;
uint32_t version;
uint32_t ino; /* == zero for unlink */
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 969d589c848d..b5f3c3ab0d5f 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -116,7 +116,7 @@ static struct nlm_host *nlm_alloc_host(struct nlm_lookup_host_info *ni,
atomic_inc(&nsm->sm_count);
else {
host = NULL;
- nsm = nsm_get_handle(ni->sap, ni->salen,
+ nsm = nsm_get_handle(ni->net, ni->sap, ni->salen,
ni->hostname, ni->hostname_len);
if (unlikely(nsm == NULL)) {
dprintk("lockd: %s failed; no nsm handle\n",
@@ -534,17 +534,18 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
/**
* nlm_host_rebooted - Release all resources held by rebooted host
+ * @net: network namespace
* @info: pointer to decoded results of NLM_SM_NOTIFY call
*
* We were notified that the specified host has rebooted. Release
* all resources held by that peer.
*/
-void nlm_host_rebooted(const struct nlm_reboot *info)
+void nlm_host_rebooted(const struct net *net, const struct nlm_reboot *info)
{
struct nsm_handle *nsm;
struct nlm_host *host;
- nsm = nsm_reboot_lookup(info);
+ nsm = nsm_reboot_lookup(net, info);
if (unlikely(nsm == NULL))
return;
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 6ae664b489af..13fac49aff7f 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -51,7 +51,6 @@ struct nsm_res {
};
static const struct rpc_program nsm_program;
-static LIST_HEAD(nsm_handles);
static DEFINE_SPINLOCK(nsm_lock);
/*
@@ -259,33 +258,35 @@ void nsm_unmonitor(const struct nlm_host *host)
}
}
-static struct nsm_handle *nsm_lookup_hostname(const char *hostname,
- const size_t len)
+static struct nsm_handle *nsm_lookup_hostname(const struct list_head *nsm_handles,
+ const char *hostname, const size_t len)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (strlen(nsm->sm_name) == len &&
memcmp(nsm->sm_name, hostname, len) == 0)
return nsm;
return NULL;
}
-static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
+static struct nsm_handle *nsm_lookup_addr(const struct list_head *nsm_handles,
+ const struct sockaddr *sap)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (rpc_cmp_addr(nsm_addr(nsm), sap))
return nsm;
return NULL;
}
-static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv)
+static struct nsm_handle *nsm_lookup_priv(const struct list_head *nsm_handles,
+ const struct nsm_private *priv)
{
struct nsm_handle *nsm;
- list_for_each_entry(nsm, &nsm_handles, sm_link)
+ list_for_each_entry(nsm, nsm_handles, sm_link)
if (memcmp(nsm->sm_priv.data, priv->data,
sizeof(priv->data)) == 0)
return nsm;
@@ -350,6 +351,7 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
/**
* nsm_get_handle - Find or create a cached nsm_handle
+ * @net: network namespace
* @sap: pointer to socket address of handle to find
* @salen: length of socket address
* @hostname: pointer to C string containing hostname to find
@@ -362,11 +364,13 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
* @hostname cannot be found in the handle cache. Returns NULL if
* an error occurs.
*/
-struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+struct nsm_handle *nsm_get_handle(const struct net *net,
+ const struct sockaddr *sap,
const size_t salen, const char *hostname,
const size_t hostname_len)
{
struct nsm_handle *cached, *new = NULL;
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
if (printk_ratelimit()) {
@@ -381,9 +385,10 @@ retry:
spin_lock(&nsm_lock);
if (nsm_use_hostnames && hostname != NULL)
- cached = nsm_lookup_hostname(hostname, hostname_len);
+ cached = nsm_lookup_hostname(&ln->nsm_handles,
+ hostname, hostname_len);
else
- cached = nsm_lookup_addr(sap);
+ cached = nsm_lookup_addr(&ln->nsm_handles, sap);
if (cached != NULL) {
atomic_inc(&cached->sm_count);
@@ -397,7 +402,7 @@ retry:
}
if (new != NULL) {
- list_add(&new->sm_link, &nsm_handles);
+ list_add(&new->sm_link, &ln->nsm_handles);
spin_unlock(&nsm_lock);
dprintk("lockd: created nsm_handle for %s (%s)\n",
new->sm_name, new->sm_addrbuf);
@@ -414,19 +419,22 @@ retry:
/**
* nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle
+ * @net: network namespace
* @info: pointer to NLMPROC_SM_NOTIFY arguments
*
* Returns a matching nsm_handle if found in the nsm cache. The returned
* nsm_handle's reference count is bumped. Otherwise returns NULL if some
* error occurred.
*/
-struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info)
+struct nsm_handle *nsm_reboot_lookup(const struct net *net,
+ const struct nlm_reboot *info)
{
struct nsm_handle *cached;
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
spin_lock(&nsm_lock);
- cached = nsm_lookup_priv(&info->priv);
+ cached = nsm_lookup_priv(&ln->nsm_handles, &info->priv);
if (unlikely(cached == NULL)) {
spin_unlock(&nsm_lock);
dprintk("lockd: never saw rebooted peer '%.*s' before\n",
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 5010b55628b4..414da99744e9 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -16,6 +16,7 @@ struct lockd_net {
spinlock_t nsm_clnt_lock;
unsigned int nsm_users;
struct rpc_clnt *nsm_clnt;
+ struct list_head nsm_handles;
};
extern int lockd_net_id;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 7a318480ab7a..ce05c60ff06d 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -583,6 +583,7 @@ static int lockd_init_net(struct net *net)
INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
INIT_LIST_HEAD(&ln->grace_list);
spin_lock_init(&ln->nsm_clnt_lock);
+ INIT_LIST_HEAD(&ln->nsm_handles);
return 0;
}
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index b147d1ae71fd..09c576f26c7b 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -421,7 +421,7 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
return rpc_system_err;
}
- nlm_host_rebooted(argp);
+ nlm_host_rebooted(SVC_NET(rqstp), argp);
return rpc_success;
}
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 21171f0c6477..fb26b9f522e7 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -464,7 +464,7 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
return rpc_system_err;
}
- nlm_host_rebooted(argp);
+ nlm_host_rebooted(SVC_NET(rqstp), argp);
return rpc_success;
}
diff --git a/fs/locks.c b/fs/locks.c
index 0274c953b07d..f7b1de7e6735 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1852,7 +1852,6 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
goto out;
}
-again:
error = flock_to_posix_lock(filp, file_lock, &flock);
if (error)
goto out;
@@ -1883,19 +1882,22 @@ again:
* Attempt to detect a close/fcntl race and recover by
* releasing the lock that was just acquired.
*/
- /*
- * we need that spin_lock here - it prevents reordering between
- * update of inode->i_flock and check for it done in close().
- * rcu_read_lock() wouldn't do.
- */
- spin_lock(&current->files->file_lock);
- f = fcheck(fd);
- spin_unlock(&current->files->file_lock);
- if (!error && f != filp && flock.l_type != F_UNLCK) {
- flock.l_type = F_UNLCK;
- goto again;
+ if (!error && file_lock->fl_type != F_UNLCK) {
+ /*
+ * We need that spin_lock here - it prevents reordering between
+ * update of inode->i_flock and check for it done in
+ * close(). rcu_read_lock() wouldn't do.
+ */
+ spin_lock(&current->files->file_lock);
+ f = fcheck(fd);
+ spin_unlock(&current->files->file_lock);
+ if (f != filp) {
+ file_lock->fl_type = F_UNLCK;
+ error = do_lock_file_wait(filp, cmd, file_lock);
+ WARN_ON_ONCE(error);
+ error = -EBADF;
+ }
}
-
out:
locks_free_lock(file_lock);
return error;
@@ -1970,7 +1972,6 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
goto out;
}
-again:
error = flock64_to_posix_lock(filp, file_lock, &flock);
if (error)
goto out;
@@ -2001,14 +2002,22 @@ again:
* Attempt to detect a close/fcntl race and recover by
* releasing the lock that was just acquired.
*/
- spin_lock(&current->files->file_lock);
- f = fcheck(fd);
- spin_unlock(&current->files->file_lock);
- if (!error && f != filp && flock.l_type != F_UNLCK) {
- flock.l_type = F_UNLCK;
- goto again;
+ if (!error && file_lock->fl_type != F_UNLCK) {
+ /*
+ * We need that spin_lock here - it prevents reordering between
+ * update of inode->i_flock and check for it done in
+ * close(). rcu_read_lock() wouldn't do.
+ */
+ spin_lock(&current->files->file_lock);
+ f = fcheck(fd);
+ spin_unlock(&current->files->file_lock);
+ if (f != filp) {
+ file_lock->fl_type = F_UNLCK;
+ error = do_lock_file_wait(filp, cmd, file_lock);
+ WARN_ON_ONCE(error);
+ error = -EBADF;
+ }
}
-
out:
locks_free_lock(file_lock);
return error;
diff --git a/fs/namei.c b/fs/namei.c
index 157c3dbacf6c..c87e15ee9255 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2917,6 +2917,10 @@ opened:
goto exit_fput;
}
out:
+ if (unlikely(error > 0)) {
+ WARN_ON(1);
+ error = -EINVAL;
+ }
if (got_write)
mnt_drop_write(nd->path.mnt);
path_put(&save_parent);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index cfa9163b3bb7..2bdaf57c82d0 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1452,7 +1452,7 @@ restart:
}
spin_unlock(&state->state_lock);
nfs4_put_open_state(state);
- clear_bit(NFS4CLNT_RECLAIM_NOGRACE,
+ clear_bit(NFS_STATE_RECLAIM_NOGRACE,
&state->flags);
spin_lock(&sp->so_lock);
goto restart;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9f285fb9bab3..b86db1236c7c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -170,7 +170,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
+ mm = mm_access(priv->task, PTRACE_MODE_READ_FSCREDS);
if (!mm || IS_ERR(mm))
return mm;
down_read(&mm->mmap_sem);
@@ -1044,7 +1044,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!pm.buffer)
goto out_task;
- mm = mm_access(task, PTRACE_MODE_READ);
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
ret = PTR_ERR(mm);
if (!mm || IS_ERR(mm))
goto out_free;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 56123a6f462e..123c19890b14 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -223,7 +223,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (!priv->task)
return ERR_PTR(-ESRCH);
- mm = mm_access(priv->task, PTRACE_MODE_READ);
+ mm = mm_access(priv->task, PTRACE_MODE_READ_FSCREDS);
if (!mm || IS_ERR(mm)) {
put_task_struct(priv->task);
priv->task = NULL;
diff --git a/fs/splice.c b/fs/splice.c
index f183f1342c01..3b94a6bba29f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -949,6 +949,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
splice_from_pipe_begin(sd);
do {
+ cond_resched();
ret = splice_from_pipe_next(pipe, sd);
if (ret > 0)
ret = splice_from_pipe_feed(pipe, sd, actor);
@@ -1189,7 +1190,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
long ret, bytes;
umode_t i_mode;
size_t len;
- int i, flags;
+ int i, flags, more;
/*
* We require the input being a regular file, as we don't want to
@@ -1232,6 +1233,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
* Don't block on output, we have to drain the direct pipe.
*/
sd->flags &= ~SPLICE_F_NONBLOCK;
+ more = sd->flags & SPLICE_F_MORE;
while (len) {
size_t read_len;
@@ -1245,6 +1247,15 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
sd->total_len = read_len;
/*
+ * If more data is pending, set SPLICE_F_MORE
+ * If this is the last data and SPLICE_F_MORE was not set
+ * initially, clears it.
+ */
+ if (read_len < len)
+ sd->flags |= SPLICE_F_MORE;
+ else if (!more)
+ sd->flags &= ~SPLICE_F_MORE;
+ /*
* NOTE: nonblocking mode only applies to the input. We
* must not do the output in nonblocking mode as then we
* could get stuck data in the internal pipe:
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-26 17:42:53 +0000