summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/binfmt_elf.c2
-rw-r--r--fs/btrfs/ioctl.c5
-rw-r--r--fs/btrfs/send.c4
-rw-r--r--fs/btrfs/transaction.c12
-rw-r--r--fs/cifs/cifs_swn.c6
-rw-r--r--fs/cifs/cifsacl.c9
-rw-r--r--fs/cifs/cifsfs.c1
-rw-r--r--fs/cifs/connect.c31
-rw-r--r--fs/cifs/dfs_cache.c2
-rw-r--r--fs/cifs/fs_context.c4
-rw-r--r--fs/cifs/sess.c11
-rw-r--r--fs/cifs/smb1ops.c4
-rw-r--r--fs/cifs/transport.c5
-rw-r--r--fs/cifs/xattr.c2
-rw-r--r--fs/file_table.c8
-rw-r--r--fs/gfs2/file.c7
-rw-r--r--fs/gfs2/glock.c3
-rw-r--r--fs/io_uring.c32
-rw-r--r--fs/namespace.c30
-rw-r--r--fs/nfs/dir.c4
-rw-r--r--fs/nfs/inode.c9
-rw-r--r--fs/nfs/nfs4proc.c3
-rw-r--r--fs/proc/task_mmu.c40
23 files changed, 165 insertions, 69 deletions
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 605017eb9349..9e11e6f13e83 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1117,7 +1117,7 @@ out_free_interp:
* without MAP_FIXED nor MAP_FIXED_NOREPLACE).
*/
alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum);
- if (alignment > ELF_MIN_ALIGN) {
+ if (interpreter || alignment > ELF_MIN_ALIGN) {
load_bias = ELF_ET_DYN_BASE;
if (current->flags & PF_RANDOMIZE)
load_bias += arch_mmap_rnd();
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 33eda39df685..927771d1853f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1210,6 +1210,10 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
if (em->generation < newer_than)
goto next;
+ /* This em is under writeback, no need to defrag */
+ if (em->generation == (u64)-1)
+ goto next;
+
/*
* Our start offset might be in the middle of an existing extent
* map, so take that into account.
@@ -1629,6 +1633,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
ret = 0;
break;
}
+ cond_resched();
}
if (ra_allocated)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d8ccb62aa7d2..201eb2628aea 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4999,6 +4999,10 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
+ btrfs_err(fs_info,
+ "send: IO error at offset %llu for inode %llu root %llu",
+ page_offset(page), sctx->cur_ino,
+ sctx->send_root->root_key.objectid);
put_page(page);
ret = -EIO;
break;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c43bbc7f623e..c3cfdfd8de9b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1981,16 +1981,24 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{
/*
- * We use writeback_inodes_sb here because if we used
+ * We use try_to_writeback_inodes_sb() here because if we used
* btrfs_start_delalloc_roots we would deadlock with fs freeze.
* Currently are holding the fs freeze lock, if we do an async flush
* we'll do btrfs_join_transaction() and deadlock because we need to
* wait for the fs freeze lock. Using the direct flushing we benefit
* from already being in a transaction and our join_transaction doesn't
* have to re-take the fs freeze lock.
+ *
+ * Note that try_to_writeback_inodes_sb() will only trigger writeback
+ * if it can read lock sb->s_umount. It will always be able to lock it,
+ * except when the filesystem is being unmounted or being frozen, but in
+ * those cases sync_filesystem() is called, which results in calling
+ * writeback_inodes_sb() while holding a write lock on sb->s_umount.
+ * Note that we don't call writeback_inodes_sb() directly, because it
+ * will emit a warning if sb->s_umount is not locked.
*/
if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
- writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
+ try_to_writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
return 0;
}
diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index 463ebe34892b..cdce1609c5c2 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -396,11 +396,11 @@ static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const ch
switch (state) {
case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE:
cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name);
- cifs_reconnect(swnreg->tcon->ses->server, true);
+ cifs_mark_tcp_ses_conns_for_reconnect(swnreg->tcon->ses->server, true);
break;
case CIFS_SWN_RESOURCE_STATE_AVAILABLE:
cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name);
- cifs_reconnect(swnreg->tcon->ses->server, true);
+ cifs_mark_tcp_ses_conns_for_reconnect(swnreg->tcon->ses->server, true);
break;
case CIFS_SWN_RESOURCE_STATE_UNKNOWN:
cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name);
@@ -498,7 +498,7 @@ static int cifs_swn_reconnect(struct cifs_tcon *tcon, struct sockaddr_storage *a
goto unlock;
}
- cifs_reconnect(tcon->ses->server, false);
+ cifs_mark_tcp_ses_conns_for_reconnect(tcon->ses->server, false);
unlock:
mutex_unlock(&tcon->ses->server->srv_mutex);
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index ee3aab3dd4ac..bf861fef2f0c 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -949,6 +949,9 @@ static void populate_new_aces(char *nacl_base,
pnntace = (struct cifs_ace *) (nacl_base + nsize);
nsize += setup_special_mode_ACE(pnntace, nmode);
num_aces++;
+ pnntace = (struct cifs_ace *) (nacl_base + nsize);
+ nsize += setup_authusers_ACE(pnntace);
+ num_aces++;
goto set_size;
}
@@ -1297,7 +1300,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
if (uid_valid(uid)) { /* chown */
uid_t id;
- nowner_sid_ptr = kmalloc(sizeof(struct cifs_sid),
+ nowner_sid_ptr = kzalloc(sizeof(struct cifs_sid),
GFP_KERNEL);
if (!nowner_sid_ptr) {
rc = -ENOMEM;
@@ -1326,7 +1329,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
}
if (gid_valid(gid)) { /* chgrp */
gid_t id;
- ngroup_sid_ptr = kmalloc(sizeof(struct cifs_sid),
+ ngroup_sid_ptr = kzalloc(sizeof(struct cifs_sid),
GFP_KERNEL);
if (!ngroup_sid_ptr) {
rc = -ENOMEM;
@@ -1613,7 +1616,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
nsecdesclen = secdesclen;
if (pnmode && *pnmode != NO_CHANGE_64) { /* chmod */
if (mode_from_sid)
- nsecdesclen += sizeof(struct cifs_ace);
+ nsecdesclen += 2 * sizeof(struct cifs_ace);
else /* cifsacl */
nsecdesclen += 5 * sizeof(struct cifs_ace);
} else { /* chown */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 199edac0cb59..082c21478686 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -919,6 +919,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
out_super:
deactivate_locked_super(sb);
+ return root;
out:
if (cifs_sb) {
kfree(cifs_sb->prepath);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 0b742bd50642..053cb449eb16 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -175,11 +175,6 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
- struct mid_q_entry *mid, *nmid;
- struct list_head retry_list;
-
- server->maxBuf = 0;
- server->max_read = 0;
/*
* before reconnecting the tcp session, mark the smb session (uid) and the tid bad so they
@@ -219,6 +214,16 @@ next_session:
spin_unlock(&ses->chan_lock);
}
spin_unlock(&cifs_tcp_ses_lock);
+}
+
+static void
+cifs_abort_connection(struct TCP_Server_Info *server)
+{
+ struct mid_q_entry *mid, *nmid;
+ struct list_head retry_list;
+
+ server->maxBuf = 0;
+ server->max_read = 0;
/* do not want to be sending data on a socket we are freeing */
cifs_dbg(FYI, "%s: tearing down socket\n", __func__);
@@ -310,6 +315,8 @@ static int __cifs_reconnect(struct TCP_Server_Info *server,
cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session);
+ cifs_abort_connection(server);
+
do {
try_to_freeze();
mutex_lock(&server->srv_mutex);
@@ -434,6 +441,8 @@ reconnect_dfs_server(struct TCP_Server_Info *server,
cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session);
+ cifs_abort_connection(server);
+
do {
try_to_freeze();
mutex_lock(&server->srv_mutex);
@@ -639,6 +648,7 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
if (server->tcpStatus == CifsNeedReconnect) {
spin_unlock(&cifs_tcp_ses_lock);
+ cifs_reconnect(server, false);
return -ECONNABORTED;
}
spin_unlock(&cifs_tcp_ses_lock);
@@ -2340,10 +2350,19 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
if (ses->server->posix_ext_supported) {
tcon->posix_extensions = true;
pr_warn_once("SMB3.11 POSIX Extensions are experimental\n");
- } else {
+ } else if ((ses->server->vals->protocol_id == SMB311_PROT_ID) ||
+ (strcmp(ses->server->vals->version_string,
+ SMB3ANY_VERSION_STRING) == 0) ||
+ (strcmp(ses->server->vals->version_string,
+ SMBDEFAULT_VERSION_STRING) == 0)) {
cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions\n");
rc = -EOPNOTSUPP;
goto out_fail;
+ } else {
+ cifs_dbg(VFS, "Check vers= mount option. SMB3.11 "
+ "disabled but required for POSIX extensions\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
}
}
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index dd9643751671..831f42458bf6 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1355,7 +1355,7 @@ static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cach
}
cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
- cifs_reconnect(tcon->ses->server, true);
+ cifs_mark_tcp_ses_conns_for_reconnect(tcon->ses->server, true);
}
/* Refresh dfs referral of tcon and mark it for reconnect if needed */
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 7ec35f3f0a5f..a92e9eec521f 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -149,7 +149,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_u32("echo_interval", Opt_echo_interval),
fsparam_u32("max_credits", Opt_max_credits),
fsparam_u32("handletimeout", Opt_handletimeout),
- fsparam_u32("snapshot", Opt_snapshot),
+ fsparam_u64("snapshot", Opt_snapshot),
fsparam_u32("max_channels", Opt_max_channels),
/* Mount options which take string value */
@@ -1078,7 +1078,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
ctx->echo_interval = result.uint_32;
break;
case Opt_snapshot:
- ctx->snapshot_time = result.uint_32;
+ ctx->snapshot_time = result.uint_64;
break;
case Opt_max_credits:
if (result.uint_32 < 20 || result.uint_32 > 60000) {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 5723d50340e5..32f478c7a66d 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -127,11 +127,6 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
struct cifs_server_iface *ifaces = NULL;
size_t iface_count;
- if (ses->server->dialect < SMB30_PROT_ID) {
- cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n");
- return 0;
- }
-
spin_lock(&ses->chan_lock);
new_chan_count = old_chan_count = ses->chan_count;
@@ -145,6 +140,12 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
return 0;
}
+ if (ses->server->dialect < SMB30_PROT_ID) {
+ spin_unlock(&ses->chan_lock);
+ cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n");
+ return 0;
+ }
+
if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
ses->chan_max = 1;
spin_unlock(&ses->chan_lock);
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 8272c91e15ef..b2fb7bd11936 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -228,9 +228,7 @@ cifs_get_next_mid(struct TCP_Server_Info *server)
spin_unlock(&GlobalMid_Lock);
if (reconnect) {
- spin_lock(&cifs_tcp_ses_lock);
- server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&cifs_tcp_ses_lock);
+ cifs_mark_tcp_ses_conns_for_reconnect(server, false);
}
return mid;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 8540f7c13eae..a4c3e027cca2 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -430,10 +430,7 @@ unmask:
* be taken as the remainder of this one. We need to kill the
* socket so the server throws away the partial SMB
*/
- spin_lock(&cifs_tcp_ses_lock);
- if (server->tcpStatus != CifsExiting)
- server->tcpStatus = CifsNeedReconnect;
- spin_unlock(&cifs_tcp_ses_lock);
+ cifs_mark_tcp_ses_conns_for_reconnect(server, false);
trace_smb3_partial_send_reconnect(server->CurrentMid,
server->conn_id, server->hostname);
}
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 7d8b72d67c80..9d486fbbfbbd 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -175,11 +175,13 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
switch (handler->flags) {
case XATTR_CIFS_NTSD_FULL:
aclflags = (CIFS_ACL_OWNER |
+ CIFS_ACL_GROUP |
CIFS_ACL_DACL |
CIFS_ACL_SACL);
break;
case XATTR_CIFS_NTSD:
aclflags = (CIFS_ACL_OWNER |
+ CIFS_ACL_GROUP |
CIFS_ACL_DACL);
break;
case XATTR_CIFS_ACL:
diff --git a/fs/file_table.c b/fs/file_table.c
index 4969021fa676..7d2e692b66a9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -27,6 +27,7 @@
#include <linux/task_work.h>
#include <linux/ima.h>
#include <linux/swap.h>
+#include <linux/kmemleak.h>
#include <linux/atomic.h>
@@ -119,8 +120,11 @@ static struct ctl_table fs_stat_sysctls[] = {
static int __init init_fs_stat_sysctls(void)
{
register_sysctl_init("fs", fs_stat_sysctls);
- if (IS_ENABLED(CONFIG_BINFMT_MISC))
- register_sysctl_mount_point("fs/binfmt_misc");
+ if (IS_ENABLED(CONFIG_BINFMT_MISC)) {
+ struct ctl_table_header *hdr;
+ hdr = register_sysctl_mount_point("fs/binfmt_misc");
+ kmemleak_not_leak(hdr);
+ }
return 0;
}
fs_initcall(init_fs_stat_sysctls);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3e718cfc19a7..8c39a8571b1f 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -704,10 +704,11 @@ static int gfs2_release(struct inode *inode, struct file *file)
kfree(file->private_data);
file->private_data = NULL;
- if (gfs2_rs_active(&ip->i_res))
- gfs2_rs_delete(ip, &inode->i_writecount);
- if (file->f_mode & FMODE_WRITE)
+ if (file->f_mode & FMODE_WRITE) {
+ if (gfs2_rs_active(&ip->i_res))
+ gfs2_rs_delete(ip, &inode->i_writecount);
gfs2_qa_put(ip);
+ }
return 0;
}
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index b7ab8430333c..6b23399eaee0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -301,9 +301,6 @@ void gfs2_glock_queue_put(struct gfs2_glock *gl)
void gfs2_glock_put(struct gfs2_glock *gl)
{
- /* last put could call sleepable dlm api */
- might_sleep();
-
if (lockref_put_or_lock(&gl->gl_lockref))
return;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2e04f718319d..4715980e9015 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4567,6 +4567,7 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
} else {
list_add_tail(&buf->list, &(*head)->list);
}
+ cond_resched();
}
return i ? i : -ENOMEM;
@@ -5228,7 +5229,6 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
min_ret = iov_iter_count(&msg.msg_iter);
ret = sock_recvmsg(sock, &msg, flags);
-out_free:
if (ret < min_ret) {
if (ret == -EAGAIN && force_nonblock)
return -EAGAIN;
@@ -5236,9 +5236,9 @@ out_free:
ret = -EINTR;
req_set_fail(req);
} else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
+out_free:
req_set_fail(req);
}
-
__io_req_complete(req, issue_flags, ret, io_put_kbuf(req));
return 0;
}
@@ -7694,7 +7694,7 @@ static int io_run_task_work_sig(void)
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- signed long *timeout)
+ ktime_t timeout)
{
int ret;
@@ -7706,8 +7706,9 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
if (test_bit(0, &ctx->check_cq_overflow))
return 1;
- *timeout = schedule_timeout(*timeout);
- return !*timeout ? -ETIME : 1;
+ if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ return -ETIME;
+ return 1;
}
/*
@@ -7720,7 +7721,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
{
struct io_wait_queue iowq;
struct io_rings *rings = ctx->rings;
- signed long timeout = MAX_SCHEDULE_TIMEOUT;
+ ktime_t timeout = KTIME_MAX;
int ret;
do {
@@ -7736,7 +7737,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
if (get_timespec64(&ts, uts))
return -EFAULT;
- timeout = timespec64_to_jiffies(&ts);
+ timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
}
if (sig) {
@@ -7768,7 +7769,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
}
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
finish_wait(&ctx->cq_wait, &iowq.wq);
cond_resched();
} while (ret > 0);
@@ -7925,7 +7926,15 @@ static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
ret = wait_for_completion_interruptible(&data->done);
if (!ret) {
mutex_lock(&ctx->uring_lock);
- break;
+ if (atomic_read(&data->refs) > 0) {
+ /*
+ * it has been revived by another thread while
+ * we were unlocked
+ */
+ mutex_unlock(&ctx->uring_lock);
+ } else {
+ break;
+ }
}
atomic_inc(&data->refs);
@@ -8933,10 +8942,9 @@ static void io_mem_free(void *ptr)
static void *io_mem_alloc(size_t size)
{
- gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP |
- __GFP_NORETRY | __GFP_ACCOUNT;
+ gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
- return (void *) __get_free_pages(gfp_flags, get_order(size));
+ return (void *) __get_free_pages(gfp, get_order(size));
}
static unsigned long rings_size(unsigned sq_entries, unsigned cq_entries,
diff --git a/fs/namespace.c b/fs/namespace.c
index 40b994a29e90..de6fae84f1a1 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -469,6 +469,24 @@ void mnt_drop_write_file(struct file *file)
}
EXPORT_SYMBOL(mnt_drop_write_file);
+/**
+ * mnt_hold_writers - prevent write access to the given mount
+ * @mnt: mnt to prevent write access to
+ *
+ * Prevents write access to @mnt if there are no active writers for @mnt.
+ * This function needs to be called and return successfully before changing
+ * properties of @mnt that need to remain stable for callers with write access
+ * to @mnt.
+ *
+ * After this functions has been called successfully callers must pair it with
+ * a call to mnt_unhold_writers() in order to stop preventing write access to
+ * @mnt.
+ *
+ * Context: This function expects lock_mount_hash() to be held serializing
+ * setting MNT_WRITE_HOLD.
+ * Return: On success 0 is returned.
+ * On error, -EBUSY is returned.
+ */
static inline int mnt_hold_writers(struct mount *mnt)
{
mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
@@ -500,6 +518,18 @@ static inline int mnt_hold_writers(struct mount *mnt)
return 0;
}
+/**
+ * mnt_unhold_writers - stop preventing write access to the given mount
+ * @mnt: mnt to stop preventing write access to
+ *
+ * Stop preventing write access to @mnt allowing callers to gain write access
+ * to @mnt again.
+ *
+ * This function can only be called after a successful call to
+ * mnt_hold_writers().
+ *
+ * Context: This function expects lock_mount_hash() to be held.
+ */
static inline void mnt_unhold_writers(struct mount *mnt)
{
/*
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7bc7cf6b26f0..75cb1cbe4cde 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2010,14 +2010,14 @@ no_open:
if (!res) {
inode = d_inode(dentry);
if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
- !S_ISDIR(inode->i_mode))
+ !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)))
res = ERR_PTR(-ENOTDIR);
else if (inode && S_ISREG(inode->i_mode))
res = ERR_PTR(-EOPENSTALE);
} else if (!IS_ERR(res)) {
inode = d_inode(res);
if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
- !S_ISDIR(inode->i_mode)) {
+ !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) {
dput(res);
res = ERR_PTR(-ENOTDIR);
} else if (inode && S_ISREG(inode->i_mode)) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index a918c3a834b6..d96baa4450e3 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -853,12 +853,9 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
}
/* Flush out writes to the server in order to update c/mtime. */
- if ((request_mask & (STATX_CTIME|STATX_MTIME)) &&
- S_ISREG(inode->i_mode)) {
- err = filemap_write_and_wait(inode->i_mapping);
- if (err)
- goto out;
- }
+ if ((request_mask & (STATX_CTIME | STATX_MTIME)) &&
+ S_ISREG(inode->i_mode))
+ filemap_write_and_wait(inode->i_mapping);
/*
* We may force a getattr if the user cares about atime.
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f5020828ab65..0e0db6c27619 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1229,8 +1229,7 @@ nfs4_update_changeattr_locked(struct inode *inode,
NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER |
NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
- NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR |
- NFS_INO_REVAL_PAGECACHE;
+ NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR;
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
}
nfsi->attrtimeo_timestamp = jiffies;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 18f8c3acbb85..6e97ed775074 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -440,7 +440,8 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
}
static void smaps_account(struct mem_size_stats *mss, struct page *page,
- bool compound, bool young, bool dirty, bool locked)
+ bool compound, bool young, bool dirty, bool locked,
+ bool migration)
{
int i, nr = compound ? compound_nr(page) : 1;
unsigned long size = nr * PAGE_SIZE;
@@ -467,8 +468,15 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
* page_count(page) == 1 guarantees the page is mapped exactly once.
* If any subpage of the compound page mapped with PTE it would elevate
* page_count().
+ *
+ * The page_mapcount() is called to get a snapshot of the mapcount.
+ * Without holding the page lock this snapshot can be slightly wrong as
+ * we cannot always read the mapcount atomically. It is not safe to
+ * call page_mapcount() even with PTL held if the page is not mapped,
+ * especially for migration entries. Treat regular migration entries
+ * as mapcount == 1.
*/
- if (page_count(page) == 1) {
+ if ((page_count(page) == 1) || migration) {
smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty,
locked, true);
return;
@@ -517,6 +525,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
+ bool migration = false;
if (pte_present(*pte)) {
page = vm_normal_page(vma, addr, *pte);
@@ -536,8 +545,11 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
} else {
mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
}
- } else if (is_pfn_swap_entry(swpent))
+ } else if (is_pfn_swap_entry(swpent)) {
+ if (is_migration_entry(swpent))
+ migration = true;
page = pfn_swap_entry_to_page(swpent);
+ }
} else {
smaps_pte_hole_lookup(addr, walk);
return;
@@ -546,7 +558,8 @@ 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), locked);
+ smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte),
+ locked, migration);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -557,6 +570,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
+ bool migration = false;
if (pmd_present(*pmd)) {
/* FOLL_DUMP will return -EFAULT on huge zero page */
@@ -564,8 +578,10 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
swp_entry_t entry = pmd_to_swp_entry(*pmd);
- if (is_migration_entry(entry))
+ if (is_migration_entry(entry)) {
+ migration = true;
page = pfn_swap_entry_to_page(entry);
+ }
}
if (IS_ERR_OR_NULL(page))
return;
@@ -577,7 +593,9 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
/* pass */;
else
mss->file_thp += HPAGE_PMD_SIZE;
- smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked);
+
+ smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd),
+ locked, migration);
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -1378,6 +1396,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
{
u64 frame = 0, flags = 0;
struct page *page = NULL;
+ bool migration = false;
if (pte_present(pte)) {
if (pm->show_pfn)
@@ -1399,13 +1418,14 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags |= PM_SWAP;
+ migration = is_migration_entry(entry);
if (is_pfn_swap_entry(entry))
page = pfn_swap_entry_to_page(entry);
}
if (page && !PageAnon(page))
flags |= PM_FILE;
- if (page && page_mapcount(page) == 1)
+ if (page && !migration && page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
@@ -1421,8 +1441,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
spinlock_t *ptl;
pte_t *pte, *orig_pte;
int err = 0;
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ bool migration = false;
+
ptl = pmd_trans_huge_lock(pmdp, vma);
if (ptl) {
u64 flags = 0, frame = 0;
@@ -1461,11 +1482,12 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
if (pmd_swp_uffd_wp(pmd))
flags |= PM_UFFD_WP;
VM_BUG_ON(!is_pmd_migration_entry(pmd));
+ migration = is_migration_entry(entry);
page = pfn_swap_entry_to_page(entry);
}
#endif
- if (page && page_mapcount(page) == 1)
+ if (page && !migration && page_mapcount(page) == 1)
flags |= PM_MMAP_EXCLUSIVE;
for (; addr != end; addr += PAGE_SIZE) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-13 05:12:18 +0300