aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/extent_io.h2
-rw-r--r--fs/btrfs/file.c13
-rw-r--r--fs/btrfs/inode.c23
-rw-r--r--fs/btrfs/ioctl.c20
-rw-r--r--fs/btrfs/volumes.c65
-rw-r--r--fs/btrfs/zoned.c13
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/connect.c15
-rw-r--r--fs/cifs/netmisc.c2
-rw-r--r--fs/cifs/smb2misc.c10
-rw-r--r--fs/file_table.c1
-rw-r--r--fs/io-wq.h1
-rw-r--r--fs/io_uring.c617
-rw-r--r--fs/nfs/Kconfig4
-rw-r--r--fs/nfs/dir.c19
-rw-r--r--fs/nfs/inode.c1
-rw-r--r--fs/nfs/internal.h10
-rw-r--r--fs/nfs/nfs42xattr.c2
-rw-r--r--fs/nfs/nfs4file.c6
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/nfs/unlink.c1
21 files changed, 318 insertions, 511 deletions
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0399cf8e3c32..151e9da5da2d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -118,7 +118,7 @@ struct btrfs_bio_ctrl {
*/
struct extent_changeset {
/* How many bytes are set/cleared in this operation */
- unsigned int bytes_changed;
+ u64 bytes_changed;
/* Changed ranges */
struct ulist range_changed;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 9f455c96c974..380054c94e4b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2957,8 +2957,9 @@ out:
return ret;
}
-static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len)
{
+ struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_state *cached_state = NULL;
@@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
goto out_only_mutex;
}
+ ret = file_modified(file);
+ if (ret)
+ goto out_only_mutex;
+
lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode)));
lockend = round_down(offset + len,
btrfs_inode_sectorsize(BTRFS_I(inode))) - 1;
@@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode,
return -EOPNOTSUPP;
if (mode & FALLOC_FL_PUNCH_HOLE)
- return btrfs_punch_hole(inode, offset, len);
+ return btrfs_punch_hole(file, offset, len);
/*
* Only trigger disk allocation, don't trigger qgroup reserve
@@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode,
goto out;
}
+ ret = file_modified(file);
+ if (ret)
+ goto out;
+
/*
* TODO: Move these two operations after we have checked
* accurate reserved space, or fallocate can still fail but
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6bfc4343c98d..17d5557f98ec 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
int ret = 0;
if (btrfs_is_free_space_inode(inode)) {
- WARN_ON_ONCE(1);
ret = -EINVAL;
goto out_unlock;
}
@@ -4488,6 +4487,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
dest->root_key.objectid);
return -EPERM;
}
+ if (atomic_read(&dest->nr_swapfiles)) {
+ spin_unlock(&dest->root_item_lock);
+ btrfs_warn(fs_info,
+ "attempt to delete subvolume %llu with active swapfile",
+ root->root_key.objectid);
+ return -EPERM;
+ }
root_flags = btrfs_root_flags(&dest->root_item);
btrfs_set_root_flags(&dest->root_item,
root_flags | BTRFS_ROOT_SUBVOL_DEAD);
@@ -11107,8 +11113,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
* set. We use this counter to prevent snapshots. We must increment it
* before walking the extents because we don't want a concurrent
* snapshot to run after we've already checked the extents.
+ *
+ * It is possible that subvolume is marked for deletion but still not
+ * removed yet. To prevent this race, we check the root status before
+ * activating the swapfile.
*/
+ spin_lock(&root->root_item_lock);
+ if (btrfs_root_dead(root)) {
+ spin_unlock(&root->root_item_lock);
+
+ btrfs_exclop_finish(fs_info);
+ btrfs_warn(fs_info,
+ "cannot activate swapfile because subvolume %llu is being deleted",
+ root->root_key.objectid);
+ return -EPERM;
+ }
atomic_inc(&root->nr_swapfiles);
+ spin_unlock(&root->root_item_lock);
isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 238cee5b5254..f46e71061942 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em)
}
static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
- bool locked)
+ u32 extent_thresh, u64 newer_than, bool locked)
{
struct extent_map *next;
bool ret = false;
@@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
return false;
/*
- * We want to check if the next extent can be merged with the current
- * one, which can be an extent created in a past generation, so we pass
- * a minimum generation of 0 to defrag_lookup_extent().
+ * Here we need to pass @newer_then when checking the next extent, or
+ * we will hit a case we mark current extent for defrag, but the next
+ * one will not be a target.
+ * This will just cause extra IO without really reducing the fragments.
*/
- next = defrag_lookup_extent(inode, em->start + em->len, 0, locked);
+ next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked);
/* No more em or hole */
if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
goto out;
@@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
*/
if (next->len >= get_extent_max_capacity(em))
goto out;
+ /* Skip older extent */
+ if (next->generation < newer_than)
+ goto out;
+ /* Also check extent size */
+ if (next->len >= extent_thresh)
+ goto out;
+
ret = true;
out:
free_extent_map(next);
@@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
goto next;
next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
- locked);
+ extent_thresh, newer_than, locked);
if (!next_mergeable) {
struct defrag_target_range *last;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1be7cb2f955f..2cfbc74a3b4e 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path)
path_put(&path);
}
-static int btrfs_rm_dev_item(struct btrfs_device *device)
+static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans,
+ struct btrfs_device *device)
{
struct btrfs_root *root = device->fs_info->chunk_root;
int ret;
struct btrfs_path *path;
struct btrfs_key key;
- struct btrfs_trans_handle *trans;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans)) {
- btrfs_free_path(path);
- return PTR_ERR(trans);
- }
key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
key.type = BTRFS_DEV_ITEM_KEY;
key.offset = device->devid;
@@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device)
if (ret) {
if (ret > 0)
ret = -ENOENT;
- btrfs_abort_transaction(trans, ret);
- btrfs_end_transaction(trans);
goto out;
}
ret = btrfs_del_item(trans, root, path);
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- btrfs_end_transaction(trans);
- }
-
out:
btrfs_free_path(path);
- if (!ret)
- ret = btrfs_commit_transaction(trans);
return ret;
}
@@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
struct btrfs_dev_lookup_args *args,
struct block_device **bdev, fmode_t *mode)
{
+ struct btrfs_trans_handle *trans;
struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
@@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1);
if (ret)
- goto out;
+ return ret;
device = btrfs_find_device(fs_info->fs_devices, args);
if (!device) {
@@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
else
ret = -ENOENT;
- goto out;
+ return ret;
}
if (btrfs_pinned_by_swapfile(fs_info, device)) {
btrfs_warn_in_rcu(fs_info,
"cannot remove device %s (devid %llu) due to active swapfile",
rcu_str_deref(device->name), device->devid);
- ret = -ETXTBSY;
- goto out;
+ return -ETXTBSY;
}
- if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
- ret = BTRFS_ERROR_DEV_TGT_REPLACE;
- goto out;
- }
+ if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
+ return BTRFS_ERROR_DEV_TGT_REPLACE;
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
- fs_info->fs_devices->rw_devices == 1) {
- ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
- goto out;
- }
+ fs_info->fs_devices->rw_devices == 1)
+ return BTRFS_ERROR_DEV_ONLY_WRITABLE;
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
@@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
if (ret)
goto error_undo;
- /*
- * TODO: the superblock still includes this device in its num_devices
- * counter although write_all_supers() is not locked out. This
- * could give a filesystem state which requires a degraded mount.
- */
- ret = btrfs_rm_dev_item(device);
- if (ret)
+ trans = btrfs_start_transaction(fs_info->chunk_root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
goto error_undo;
+ }
+
+ ret = btrfs_rm_dev_item(trans, device);
+ if (ret) {
+ /* Any error in dev item removal is critical */
+ btrfs_crit(fs_info,
+ "failed to remove device item for devid %llu: %d",
+ device->devid, ret);
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
+ return ret;
+ }
clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
btrfs_scrub_cancel_dev(device);
@@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
free_fs_devices(cur_devices);
}
-out:
+ ret = btrfs_commit_transaction(trans);
+
return ret;
error_undo:
@@ -2240,7 +2231,7 @@ error_undo:
device->fs_devices->rw_devices++;
mutex_unlock(&fs_info->chunk_mutex);
}
- goto out;
+ return ret;
}
void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b7b5fac1c779..1b1b310c3c51 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info,
map = em->map_lookup;
/* We only support single profile for now */
- ASSERT(map->num_stripes == 1);
device = map->stripes[0].dev;
free_extent_map(em);
@@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group)
bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
{
+ struct btrfs_fs_info *fs_info = fs_devices->fs_info;
struct btrfs_device *device;
bool ret = false;
- if (!btrfs_is_zoned(fs_devices->fs_info))
+ if (!btrfs_is_zoned(fs_info))
return true;
- /* Non-single profiles are not supported yet */
- ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0);
-
/* Check if there is a device with active zones left */
- mutex_lock(&fs_devices->device_list_mutex);
- list_for_each_entry(device, &fs_devices->devices, dev_list) {
+ mutex_lock(&fs_info->chunk_mutex);
+ list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
struct btrfs_zoned_device_info *zinfo = device->zone_info;
if (!device->bdev)
@@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags)
break;
}
}
- mutex_unlock(&fs_devices->device_list_mutex);
+ mutex_unlock(&fs_info->chunk_mutex);
return ret;
}
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 15a5c5db038b..c0542bdcd06b 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
#define SMB3_PRODUCT_BUILD 35
-#define CIFS_VERSION "2.35"
+#define CIFS_VERSION "2.36"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index ee3b7c15e884..54155eb4faac 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_
return rc;
}
-static int
-reconnect_dfs_server(struct TCP_Server_Info *server,
- bool mark_smb_session)
+static int reconnect_dfs_server(struct TCP_Server_Info *server)
{
int rc = 0;
const char *refpath = server->current_fullpath + 1;
@@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server,
if (!cifs_tcp_ses_needs_reconnect(server, num_targets))
return 0;
- cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session);
+ /*
+ * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a
+ * different server or share during failover. It could be improved by adding some logic to
+ * only do that in case it connects to a different server or share, though.
+ */
+ cifs_mark_tcp_ses_conns_for_reconnect(server, true);
cifs_abort_connection(server);
@@ -537,7 +540,7 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session)
}
spin_unlock(&cifs_tcp_ses_lock);
- return reconnect_dfs_server(server, mark_smb_session);
+ return reconnect_dfs_server(server);
}
#else
int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session)
@@ -4465,7 +4468,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco
*/
if (rc && server->current_fullpath != server->origin_fullpath) {
server->current_fullpath = server->origin_fullpath;
- cifs_reconnect(tcon->ses->server, true);
+ cifs_signal_cifsd_for_reconnect(server, true);
}
dfs_cache_free_tgts(tl);
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index ebe236b9d9f5..235aa1b395eb 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr)
if (class == ERRSRV && code == ERRbaduid) {
cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n",
code);
- cifs_reconnect(mid->server, false);
+ cifs_signal_cifsd_for_reconnect(mid->server, false);
}
}
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index c653beb735b8..3fe47a88f47d 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
struct smb2_transform_hdr *thdr =
(struct smb2_transform_hdr *)buf;
struct cifs_ses *ses = NULL;
+ struct cifs_ses *iter;
/* decrypt frame now that it is completely read in */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) {
- if (ses->Suid == le64_to_cpu(thdr->SessionId))
+ list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) {
+ if (iter->Suid == le64_to_cpu(thdr->SessionId)) {
+ ses = iter;
break;
+ }
}
spin_unlock(&cifs_tcp_ses_lock);
- if (list_entry_is_head(ses, &srvr->smb_ses_list,
- smb_ses_list)) {
+ if (!ses) {
cifs_dbg(VFS, "no decryption - session id not found\n");
return 1;
}
diff --git a/fs/file_table.c b/fs/file_table.c
index 7d2e692b66a9..ada8fe814db9 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -412,6 +412,7 @@ void __fput_sync(struct file *file)
}
EXPORT_SYMBOL(fput);
+EXPORT_SYMBOL(__fput_sync);
void __init files_init(void)
{
diff --git a/fs/io-wq.h b/fs/io-wq.h
index dbecd27656c7..04d374e65e54 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
struct io_wq_work {
struct io_wq_work_node list;
unsigned flags;
+ int fd;
};
static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index a8413f006417..659f8ecba5b7 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -63,7 +63,6 @@
#include <net/sock.h>
#include <net/af_unix.h>
#include <net/scm.h>
-#include <net/busy_poll.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
@@ -112,8 +111,7 @@
IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
- REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
- REQ_F_ASYNC_DATA)
+ REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
@@ -412,11 +410,6 @@ struct io_ring_ctx {
struct list_head sqd_list;
unsigned long check_cq_overflow;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- /* used to track busy poll napi_id */
- struct list_head napi_list;
- spinlock_t napi_lock; /* napi_list lock */
-#endif
struct {
unsigned cached_cq_tail;
@@ -500,7 +493,6 @@ struct io_uring_task {
const struct io_ring_ctx *last;
struct io_wq *io_wq;
struct percpu_counter inflight;
- atomic_t inflight_tracked;
atomic_t in_idle;
spinlock_t task_lock;
@@ -592,7 +584,8 @@ struct io_rw {
/* NOTE: kiocb has the file as the first member, so don't do it here */
struct kiocb kiocb;
u64 addr;
- u64 len;
+ u32 len;
+ u32 flags;
};
struct io_connect {
@@ -654,10 +647,10 @@ struct io_epoll {
struct io_splice {
struct file *file_out;
- struct file *file_in;
loff_t off_out;
loff_t off_in;
u64 len;
+ int splice_fd_in;
unsigned int flags;
};
@@ -1182,8 +1175,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
struct io_uring_rsrc_update2 *up,
unsigned nr_args);
static void io_clean_op(struct io_kiocb *req);
-static struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed);
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned issue_flags);
+static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+static void io_drop_inflight_file(struct io_kiocb *req);
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags);
static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);
@@ -1313,13 +1309,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
}
static inline void io_req_set_rsrc_node(struct io_kiocb *req,
- struct io_ring_ctx *ctx)
+ struct io_ring_ctx *ctx,
+ unsigned int issue_flags)
{
if (!req->fixed_rsrc_refs) {
req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
- ctx->rsrc_cached_refs--;
- if (unlikely(ctx->rsrc_cached_refs < 0))
- io_rsrc_refs_refill(ctx);
+
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ lockdep_assert_held(&ctx->uring_lock);
+ ctx->rsrc_cached_refs--;
+ if (unlikely(ctx->rsrc_cached_refs < 0))
+ io_rsrc_refs_refill(ctx);
+ } else {
+ percpu_ref_get(req->fixed_rsrc_refs);
+ }
}
}
@@ -1424,29 +1427,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
__must_hold(&req->ctx->timeout_lock)
{
- struct io_kiocb *req;
-
if (task && head->task != task)
return false;
- if (cancel_all)
- return true;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
-}
-
-static bool io_match_linked(struct io_kiocb *head)
-{
- struct io_kiocb *req;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
+ return cancel_all;
}
/*
@@ -1456,24 +1439,9 @@ static bool io_match_linked(struct io_kiocb *head)
static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
{
- bool matched;
-
if (task && head->task != task)
return false;
- if (cancel_all)
- return true;
-
- if (head->flags & REQ_F_LINK_TIMEOUT) {
- struct io_ring_ctx *ctx = head->ctx;
-
- /* protect against races with linked timeouts */
- spin_lock_irq(&ctx->timeout_lock);
- matched = io_match_linked(head);
- spin_unlock_irq(&ctx->timeout_lock);
- } else {
- matched = io_match_linked(head);
- }
- return matched;
+ return cancel_all;
}
static inline bool req_has_async_data(struct io_kiocb *req)
@@ -1595,10 +1563,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_WQ_LIST(&ctx->locked_free_list);
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- INIT_LIST_HEAD(&ctx->napi_list);
- spin_lock_init(&ctx->napi_lock);
-#endif
return ctx;
err:
kfree(ctx->dummy_ubuf);
@@ -1636,14 +1600,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
return req->flags & REQ_F_FIXED_FILE;
}
-static inline void io_req_track_inflight(struct io_kiocb *req)
-{
- if (!(req->flags & REQ_F_INFLIGHT)) {
- req->flags |= REQ_F_INFLIGHT;
- atomic_inc(&current->io_uring->inflight_tracked);
- }
-}
-
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
@@ -1687,14 +1643,6 @@ static void io_prep_async_work(struct io_kiocb *req)
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
-
- switch (req->opcode) {
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!S_ISREG(file_inode(req->splice.file_in)->i_mode))
- req->work.flags |= IO_WQ_WORK_UNBOUND;
- break;
- }
}
static void io_prep_async_link(struct io_kiocb *req)
@@ -1788,12 +1736,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
__must_hold(&ctx->completion_lock)
{
u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+ struct io_kiocb *req, *tmp;
spin_lock_irq(&ctx->timeout_lock);
- while (!list_empty(&ctx->timeout_list)) {
+ list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
u32 events_needed, events_got;
- struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
- struct io_kiocb, timeout.list);
if (io_is_timeout_noseq(req))
break;
@@ -1810,7 +1757,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
if (events_got < events_needed)
break;
- list_del_init(&req->timeout.list);
io_kill_timeout(req, 0);
}
ctx->cq_last_tm_flush = seq;
@@ -2562,6 +2508,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority)
WARN_ON_ONCE(!tctx);
+ io_drop_inflight_file(req);
+
spin_lock_irqsave(&tctx->task_lock, flags);
if (priority)
wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list);
@@ -3186,42 +3134,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req)
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw.kiocb;
- struct file *file = req->file;
unsigned ioprio;
int ret;
- if (!io_req_ffs_set(req))
- req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
-
kiocb->ki_pos = READ_ONCE(sqe->off);
- kiocb->ki_flags = iocb_flags(file);
- ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
- if (unlikely(ret))
- return ret;
-
- /*
- * If the file is marked O_NONBLOCK, still allow retry for it if it
- * supports async. Otherwise it's impossible to use O_NONBLOCK files
- * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
- */
- if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
- req->flags |= REQ_F_NOWAIT;
-
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
- return -EOPNOTSUPP;
-
- kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
- kiocb->ki_complete = io_complete_rw_iopoll;
- req->iopoll_completed = 0;
- } else {
- if (kiocb->ki_flags & IOCB_HIPRI)
- return -EINVAL;
- kiocb->ki_complete = io_complete_rw;
- }
ioprio = READ_ONCE(sqe->ioprio);
if (ioprio) {
@@ -3237,6 +3154,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
+ req->rw.flags = READ_ONCE(sqe->rw_flags);
req->buf_index = READ_ONCE(sqe->buf_index);
return 0;
}
@@ -3367,7 +3285,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter
return 0;
}
-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
+static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
+ unsigned int issue_flags)
{
struct io_mapped_ubuf *imu = req->imu;
u16 index, buf_index = req->buf_index;
@@ -3377,7 +3296,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, issue_flags);
index = array_index_nospec(buf_index, ctx->nr_user_bufs);
imu = READ_ONCE(ctx->user_bufs[index]);
req->imu = imu;
@@ -3539,7 +3458,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
ssize_t ret;
if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- ret = io_import_fixed(req, rw, iter);
+ ret = io_import_fixed(req, rw, iter, issue_flags);
if (ret)
return ERR_PTR(ret);
return NULL;
@@ -3740,13 +3659,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
return 0;
}
-static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(!(req->file->f_mode & FMODE_READ)))
- return -EBADF;
- return io_prep_rw(req, sqe);
-}
-
/*
* This is our waitqueue callback handler, registered through __folio_lock_async()
* when we initially tried to do the IO with the iocb armed our waitqueue.
@@ -3834,6 +3746,49 @@ static bool need_read_all(struct io_kiocb *req)
S_ISBLK(file_inode(req->file)->i_mode);
}
+static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
+{
+ struct kiocb *kiocb = &req->rw.kiocb;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = req->file;
+ int ret;
+
+ if (unlikely(!file || !(file->f_mode & mode)))
+ return -EBADF;
+
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
+
+ kiocb->ki_flags = iocb_flags(file);
+ ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
+ if (unlikely(ret))
+ return ret;
+
+ /*
+ * If the file is marked O_NONBLOCK, still allow retry for it if it
+ * supports async. Otherwise it's impossible to use O_NONBLOCK files
+ * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
+ */
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
+ req->flags |= REQ_F_NOWAIT;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
+ return -EOPNOTSUPP;
+
+ kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ req->iopoll_completed = 0;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI)
+ return -EINVAL;
+ kiocb->ki_complete = io_complete_rw;
+ }
+
+ return 0;
+}
+
static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
@@ -3869,6 +3824,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
+ ret = io_rw_init_file(req, FMODE_READ);
+ if (unlikely(ret))
+ return ret;
req->result = iov_iter_count(&s->iter);
if (force_nonblock) {
@@ -3972,13 +3930,6 @@ out_free:
return 0;
}
-static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
- return -EBADF;
- return io_prep_rw(req, sqe);
-}
-
static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_rw_state __s, *s = &__s;
@@ -3999,6 +3950,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
}
+ ret = io_rw_init_file(req, FMODE_WRITE);
+ if (unlikely(ret))
+ return ret;
req->result = iov_iter_count(&s->iter);
if (force_nonblock) {
@@ -4369,18 +4323,11 @@ static int __io_splice_prep(struct io_kiocb *req,
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- sp->file_in = NULL;
sp->len = READ_ONCE(sqe->len);
sp->flags = READ_ONCE(sqe->splice_flags);
-
if (unlikely(sp->flags & ~valid_flags))
return -EINVAL;
-
- sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in),
- (sp->flags & SPLICE_F_FD_IN_FIXED));
- if (!sp->file_in)
- return -EBADF;
- req->flags |= REQ_F_NEED_CLEANUP;
+ sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
return 0;
}
@@ -4395,20 +4342,29 @@ static int io_tee_prep(struct io_kiocb *req,
static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ struct file *in;
long ret = 0;
if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
+
+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
if (sp->len)
ret = do_tee(in, out, sp->len, flags);
if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
io_req_complete(req, ret);
@@ -4427,15 +4383,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_splice *sp = &req->splice;
- struct file *in = sp->file_in;
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
+ struct file *in;
long ret = 0;
if (issue_flags & IO_URING_F_NONBLOCK)
return -EAGAIN;
+ if (sp->flags & SPLICE_F_FD_IN_FIXED)
+ in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED);
+ else
+ in = io_file_get_normal(req, sp->splice_fd_in);
+ if (!in) {
+ ret = -EBADF;
+ goto done;
+ }
+
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
@@ -4444,8 +4409,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
io_put_file(in);
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
+done:
if (ret != sp->len)
req_set_fail(req);
io_req_complete(req, ret);
@@ -4513,9 +4477,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
- if (!req->file)
- return -EBADF;
-
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index ||
@@ -5757,108 +5718,6 @@ IO_NETOP_FN(send);
IO_NETOP_FN(recv);
#endif /* CONFIG_NET */
-#ifdef CONFIG_NET_RX_BUSY_POLL
-
-#define NAPI_TIMEOUT (60 * SEC_CONVERSION)
-
-struct napi_entry {
- struct list_head list;
- unsigned int napi_id;
- unsigned long timeout;
-};
-
-/*
- * Add busy poll NAPI ID from sk.
- */
-static void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
- unsigned int napi_id;
- struct socket *sock;
- struct sock *sk;
- struct napi_entry *ne;
-
- if (!net_busy_loop_on())
- return;
-
- sock = sock_from_file(file);
- if (!sock)
- return;
-
- sk = sock->sk;
- if (!sk)
- return;
-
- napi_id = READ_ONCE(sk->sk_napi_id);
-
- /* Non-NAPI IDs can be rejected */
- if (napi_id < MIN_NAPI_ID)
- return;
-
- spin_lock(&ctx->napi_lock);
- list_for_each_entry(ne, &ctx->napi_list, list) {
- if (ne->napi_id == napi_id) {
- ne->timeout = jiffies + NAPI_TIMEOUT;
- goto out;
- }
- }
-
- ne = kmalloc(sizeof(*ne), GFP_NOWAIT);
- if (!ne)
- goto out;
-
- ne->napi_id = napi_id;
- ne->timeout = jiffies + NAPI_TIMEOUT;
- list_add_tail(&ne->list, &ctx->napi_list);
-out:
- spin_unlock(&ctx->napi_lock);
-}
-
-static inline void io_check_napi_entry_timeout(struct napi_entry *ne)
-{
- if (time_after(jiffies, ne->timeout)) {
- list_del(&ne->list);
- kfree(ne);
- }
-}
-
-/*
- * Busy poll if globally on and supporting sockets found
- */
-static bool io_napi_busy_loop(struct list_head *napi_list)
-{
- struct napi_entry *ne, *n;
-
- list_for_each_entry_safe(ne, n, napi_list, list) {
- napi_busy_loop(ne->napi_id, NULL, NULL, true,
- BUSY_POLL_BUDGET);
- io_check_napi_entry_timeout(ne);
- }
- return !list_empty(napi_list);
-}
-
-static void io_free_napi_list(struct io_ring_ctx *ctx)
-{
- spin_lock(&ctx->napi_lock);
- while (!list_empty(&ctx->napi_list)) {
- struct napi_entry *ne =
- list_first_entry(&ctx->napi_list, struct napi_entry,
- list);
-
- list_del(&ne->list);
- kfree(ne);
- }
- spin_unlock(&ctx->napi_lock);
-}
-#else
-static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx)
-{
-}
-
-static inline void io_free_napi_list(struct io_ring_ctx *ctx)
-{
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
struct io_poll_table {
struct poll_table_struct pt;
struct io_kiocb *req;
@@ -5972,7 +5831,7 @@ static void io_poll_remove_entries(struct io_kiocb *req)
* either spurious wakeup or multishot CQE is served. 0 when it's done with
* the request, then the mask is stored in req->result.
*/
-static int io_poll_check_events(struct io_kiocb *req)
+static int io_poll_check_events(struct io_kiocb *req, bool locked)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_poll_iocb *poll = io_poll_get_single(req);
@@ -5994,7 +5853,10 @@ static int io_poll_check_events(struct io_kiocb *req)
if (!req->result) {
struct poll_table_struct pt = { ._key = req->cflags };
- req->result = vfs_poll(req->file, &pt) & req->cflags;
+ if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED)))
+ req->result = -EBADF;
+ else
+ req->result = vfs_poll(req->file, &pt) & req->cflags;
}
/* multishot, just fill an CQE and proceed */
@@ -6010,7 +5872,6 @@ static int io_poll_check_events(struct io_kiocb *req)
if (unlikely(!filled))
return -ECANCELED;
io_cqring_ev_posted(ctx);
- io_add_napi(req->file, ctx);
} else if (req->result) {
return 0;
}
@@ -6029,7 +5890,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
struct io_ring_ctx *ctx = req->ctx;
int ret;
- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, *locked);
if (ret > 0)
return;
@@ -6054,7 +5915,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
struct io_ring_ctx *ctx = req->ctx;
int ret;
- ret = io_poll_check_events(req);
+ ret = io_poll_check_events(req, *locked);
if (ret > 0)
return;
@@ -6261,7 +6122,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
__io_poll_execute(req, mask, poll->events);
return 0;
}
- io_add_napi(req->file, req->ctx);
/*
* Release ownership. If someone tried to queue a tw while it was
@@ -6766,6 +6626,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
return -EINVAL;
+ INIT_LIST_HEAD(&req->timeout.list);
data->mode = io_translate_timeout_mode(flags);
hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
@@ -6992,11 +6853,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
case IORING_OP_READ:
- return io_read_prep(req, sqe);
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
case IORING_OP_WRITE:
- return io_write_prep(req, sqe);
+ return io_prep_rw(req, sqe);
case IORING_OP_POLL_ADD:
return io_poll_add_prep(req, sqe);
case IORING_OP_POLL_REMOVE:
@@ -7179,11 +7039,6 @@ static void io_clean_op(struct io_kiocb *req)
kfree(io->free_iov);
break;
}
- case IORING_OP_SPLICE:
- case IORING_OP_TEE:
- if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED))
- io_put_file(req->splice.file_in);
- break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
if (req->open.filename)
@@ -7218,11 +7073,6 @@ static void io_clean_op(struct io_kiocb *req)
kfree(req->apoll);
req->apoll = NULL;
}
- if (req->flags & REQ_F_INFLIGHT) {
- struct io_uring_task *tctx = req->task->io_uring;
-
- atomic_dec(&tctx->inflight_tracked);
- }
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
if (req->flags & REQ_F_ASYNC_DATA) {
@@ -7232,6 +7082,23 @@ static void io_clean_op(struct io_kiocb *req)
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
+static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags)
+{
+ if (req->file || !io_op_defs[req->opcode].needs_file)
+ return true;
+
+ if (req->flags & REQ_F_FIXED_FILE)
+ req->file = io_file_get_fixed(req, req->work.fd, issue_flags);
+ else
+ req->file = io_file_get_normal(req, req->work.fd);
+ if (req->file)
+ return true;
+
+ req_set_fail(req);
+ req->result = -EBADF;
+ return false;
+}
+
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
const struct cred *creds = NULL;
@@ -7242,6 +7109,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (!io_op_defs[req->opcode].audit_skip)
audit_uring_entry(req->opcode);
+ if (unlikely(!io_assign_file(req, issue_flags)))
+ return -EBADF;
switch (req->opcode) {
case IORING_OP_NOP:
@@ -7386,10 +7255,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
static void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ const struct io_op_def *def = &io_op_defs[req->opcode];
unsigned int issue_flags = IO_URING_F_UNLOCKED;
bool needs_poll = false;
struct io_kiocb *timeout;
- int ret = 0;
+ int ret = 0, err = -ECANCELED;
/* one will be dropped by ->io_free_work() after returning to io-wq */
if (!(req->flags & REQ_F_REFCOUNT))
@@ -7401,14 +7271,18 @@ static void io_wq_submit_work(struct io_wq_work *work)
if (timeout)
io_queue_linked_timeout(timeout);
+ if (!io_assign_file(req, issue_flags)) {
+ err = -EBADF;
+ work->flags |= IO_WQ_WORK_CANCEL;
+ }
+
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
if (work->flags & IO_WQ_WORK_CANCEL) {
- io_req_task_queue_fail(req, -ECANCELED);
+ io_req_task_queue_fail(req, err);
return;
}
if (req->flags & REQ_F_FORCE_ASYNC) {
- const struct io_op_def *def = &io_op_defs[req->opcode];
bool opcode_poll = def->pollin || def->pollout;
if (opcode_poll && file_can_poll(req->file)) {
@@ -7465,46 +7339,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file
file_slot->file_ptr = file_ptr;
}
-static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+ unsigned int issue_flags)
{
- struct file *file;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct file *file = NULL;
unsigned long file_ptr;
+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_lock(&ctx->uring_lock);
+
if (unlikely((unsigned int)fd >= ctx->nr_user_files))
- return NULL;
+ goto out;
fd = array_index_nospec(fd, ctx->nr_user_files);
file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
file = (struct file *) (file_ptr & FFS_MASK);
file_ptr &= ~FFS_MASK;
/* mask in overlapping REQ_F and FFS bits */
req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
- io_req_set_rsrc_node(req, ctx);
+ io_req_set_rsrc_node(req, ctx, 0);
+out:
+ if (issue_flags & IO_URING_F_UNLOCKED)
+ mutex_unlock(&ctx->uring_lock);
return file;
}
-static struct file *io_file_get_normal(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd)
+/*
+ * Drop the file for requeue operations. Only used of req->file is the
+ * io_uring descriptor itself.
+ */
+static void io_drop_inflight_file(struct io_kiocb *req)
+{
+ if (unlikely(req->flags & REQ_F_INFLIGHT)) {
+ fput(req->file);
+ req->file = NULL;
+ req->flags &= ~REQ_F_INFLIGHT;
+ }
+}
+
+static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
{
struct file *file = fget(fd);
- trace_io_uring_file_get(ctx, req, req->user_data, fd);
+ trace_io_uring_file_get(req->ctx, req, req->user_data, fd);
/* we don't allow fixed io_uring files */
- if (file && unlikely(file->f_op == &io_uring_fops))
- io_req_track_inflight(req);
+ if (file && file->f_op == &io_uring_fops)
+ req->flags |= REQ_F_INFLIGHT;
return file;
}
-static inline struct file *io_file_get(struct io_ring_ctx *ctx,
- struct io_kiocb *req, int fd, bool fixed)
-{
- if (fixed)
- return io_file_get_fixed(ctx, req, fd);
- else
- return io_file_get_normal(ctx, req, fd);
-}
-
static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
{
struct io_kiocb *prev = req->timeout.prev;
@@ -7744,6 +7628,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
if (io_op_defs[opcode].needs_file) {
struct io_submit_state *state = &ctx->submit_state;
+ req->work.fd = READ_ONCE(sqe->fd);
+
/*
* Plug now if we have more than 2 IO left after this, and the
* target is potentially a read/write to block based storage.
@@ -7753,11 +7639,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
state->need_plug = false;
blk_start_plug_nr_ios(&state->plug, state->submit_nr);
}
-
- req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
- (sqe_flags & IOSQE_FIXED_FILE));
- if (unlikely(!req->file))
- return -EBADF;
}
personality = READ_ONCE(sqe->personality);
@@ -8032,13 +7913,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
!(ctx->flags & IORING_SETUP_R_DISABLED))
ret = io_submit_sqes(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- spin_lock(&ctx->napi_lock);
- if (!list_empty(&ctx->napi_list) &&
- io_napi_busy_loop(&ctx->napi_list))
- ++ret;
- spin_unlock(&ctx->napi_lock);
-#endif
+
if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
wake_up(&ctx->sqo_sq_wait);
if (creds)
@@ -8176,9 +8051,6 @@ struct io_wait_queue {
struct io_ring_ctx *ctx;
unsigned cq_tail;
unsigned nr_timeouts;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- unsigned busy_poll_to;
-#endif
};
static inline bool io_should_wake(struct io_wait_queue *iowq)
@@ -8240,87 +8112,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
return 1;
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
-static void io_adjust_busy_loop_timeout(struct timespec64 *ts,
- struct io_wait_queue *iowq)
-{
- unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
- struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to);
-
- if (timespec64_compare(ts, &pollto) > 0) {
- *ts = timespec64_sub(*ts, pollto);
- iowq->busy_poll_to = busy_poll_to;
- } else {
- u64 to = timespec64_to_ns(ts);
-
- do_div(to, 1000);
- iowq->busy_poll_to = to;
- ts->tv_sec = 0;
- ts->tv_nsec = 0;
- }
-}
-
-static inline bool io_busy_loop_timeout(unsigned long start_time,
- unsigned long bp_usec)
-{
- if (bp_usec) {
- unsigned long end_time = start_time + bp_usec;
- unsigned long now = busy_loop_current_time();
-
- return time_after(now, end_time);
- }
- return true;
-}
-
-static bool io_busy_loop_end(void *p, unsigned long start_time)
-{
- struct io_wait_queue *iowq = p;
-
- return signal_pending(current) ||
- io_should_wake(iowq) ||
- io_busy_loop_timeout(start_time, iowq->busy_poll_to);
-}
-
-static void io_blocking_napi_busy_loop(struct list_head *napi_list,
- struct io_wait_queue *iowq)
-{
- unsigned long start_time =
- list_is_singular(napi_list) ? 0 :
- busy_loop_current_time();
-
- do {
- if (list_is_singular(napi_list)) {
- struct napi_entry *ne =
- list_first_entry(napi_list,
- struct napi_entry, list);
-
- napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq,
- true, BUSY_POLL_BUDGET);
- io_check_napi_entry_timeout(ne);
- break;
- }
- } while (io_napi_busy_loop(napi_list) &&
- !io_busy_loop_end(iowq, start_time));
-}
-
-static void io_putback_napi_list(struct io_ring_ctx *ctx,
- struct list_head *napi_list)
-{
- struct napi_entry *cne, *lne;
-
- spin_lock(&ctx->napi_lock);
- list_for_each_entry(cne, &ctx->napi_list, list)
- list_for_each_entry(lne, napi_list, list)
- if (cne->napi_id == lne->napi_id) {
- list_del(&lne->list);
- kfree(lne);
- break;
- }
- list_splice(napi_list, &ctx->napi_list);
- spin_unlock(&ctx->napi_lock);
-}
-#endif /* CONFIG_NET_RX_BUSY_POLL */
-
/*
* 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.
@@ -8333,9 +8124,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
struct io_rings *rings = ctx->rings;
ktime_t timeout = KTIME_MAX;
int ret;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- LIST_HEAD(local_napi_list);
-#endif
do {
io_cqring_overflow_flush(ctx);
@@ -8358,29 +8146,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
return ret;
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
- iowq.busy_poll_to = 0;
- if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
- spin_lock(&ctx->napi_lock);
- list_splice_init(&ctx->napi_list, &local_napi_list);
- spin_unlock(&ctx->napi_lock);
- }
-#endif
if (uts) {
struct timespec64 ts;
if (get_timespec64(&ts, uts))
return -EFAULT;
-#ifdef CONFIG_NET_RX_BUSY_POLL
- if (!list_empty(&local_napi_list))
- io_adjust_busy_loop_timeout(&ts, &iowq);
-#endif
timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
- else if (!list_empty(&local_napi_list))
- iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
-#endif
init_waitqueue_func_entry(&iowq.wq, io_wake_function);
iowq.wq.private = current;
@@ -8390,12 +8162,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
trace_io_uring_cqring_wait(ctx, min_events);
-#ifdef CONFIG_NET_RX_BUSY_POLL
- if (iowq.busy_poll_to)
- io_blocking_napi_busy_loop(&local_napi_list, &iowq);
- if (!list_empty(&local_napi_list))
- io_putback_napi_list(ctx, &local_napi_list);
-#endif
do {
/* if we can't even flush overflow, don't wait for more */
if (!io_cqring_overflow_flush(ctx)) {
@@ -8864,8 +8630,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
skb_queue_head(&sk->sk_receive_queue, skb);
- for (i = 0; i < nr_files; i++)
- fput(fpl->fp[i]);
+ for (i = 0; i < nr; i++) {
+ struct file *file = io_file_from_index(ctx, i + offset);
+
+ if (file)
+ fput(file);
+ }
} else {
kfree_skb(skb);
free_uid(fpl->user);
@@ -9156,13 +8926,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
struct io_rsrc_node *node, void *rsrc)
{
+ u64 *tag_slot = io_get_tag_slot(data, idx);
struct io_rsrc_put *prsrc;
prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
if (!prsrc)
return -ENOMEM;
- prsrc->tag = *io_get_tag_slot(data, idx);
+ prsrc->tag = *tag_slot;
+ *tag_slot = 0;
prsrc->rsrc = rsrc;
list_add(&prsrc->list, &node->rsrc_list);
return 0;
@@ -9231,7 +9003,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_fixed_file *file_slot;
struct file *file;
- int ret, i;
+ int ret;
io_ring_submit_lock(ctx, needs_lock);
ret = -ENXIO;
@@ -9244,8 +9016,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
if (ret)
goto out;
- i = array_index_nospec(offset, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(&ctx->file_table, i);
+ offset = array_index_nospec(offset, ctx->nr_user_files);
+ file_slot = io_fixed_file_slot(&ctx->file_table, offset);
ret = -EBADF;
if (!file_slot->file_ptr)
goto out;
@@ -9301,8 +9073,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
if (file_slot->file_ptr) {
file = (struct file *)(file_slot->file_ptr & FFS_MASK);
- err = io_queue_rsrc_removal(data, up->offset + done,
- ctx->rsrc_node, file);
+ err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file);
if (err)
break;
file_slot->file_ptr = 0;
@@ -9327,7 +9098,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
err = -EBADF;
break;
}
- *io_get_tag_slot(data, up->offset + done) = tag;
+ *io_get_tag_slot(data, i) = tag;
io_fixed_file_set(file_slot, file);
err = io_sqe_file_register(ctx, file, i);
if (err) {
@@ -9411,7 +9182,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task,
xa_init(&tctx->xa);
init_waitqueue_head(&tctx->wait);
atomic_set(&tctx->in_idle, 0);
- atomic_set(&tctx->inflight_tracked, 0);
task->io_uring = tctx;
spin_lock_init(&tctx->task_lock);
INIT_WQ_LIST(&tctx->task_list);
@@ -9986,7 +9756,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
i = array_index_nospec(offset, ctx->nr_user_bufs);
if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
- err = io_queue_rsrc_removal(ctx->buf_data, offset,
+ err = io_queue_rsrc_removal(ctx->buf_data, i,
ctx->rsrc_node, ctx->user_bufs[i]);
if (unlikely(err)) {
io_buffer_unmap(ctx, &imu);
@@ -10181,7 +9951,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
io_req_caches_free(ctx);
if (ctx->hash_map)
io_wq_put_hash(ctx->hash_map);
- io_free_napi_list(ctx);
kfree(ctx->cancel_hash);
kfree(ctx->dummy_ubuf);
kfree(ctx->io_buffers);
@@ -10604,7 +10373,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
{
if (tracked)
- return atomic_read(&tctx->inflight_tracked);
+ return 0;
return percpu_counter_sum(&tctx->inflight);
}
@@ -11707,7 +11476,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
if (len > cpumask_size())
len = cpumask_size();
- if (copy_from_user(new_mask, arg, len)) {
+ if (in_compat_syscall()) {
+ ret = compat_get_bitmap(cpumask_bits(new_mask),
+ (const compat_ulong_t __user *)arg,
+ len * 8 /* CHAR_BIT */);
+ } else {
+ ret = copy_from_user(new_mask, arg, len);
+ }
+
+ if (ret) {
free_cpumask_var(new_mask);
return -EFAULT;
}
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 47a53b3362b6..14a72224b657 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -4,10 +4,6 @@ config NFS_FS
depends on INET && FILE_LOCKING && MULTIUSER
select LOCKD
select SUNRPC
- select CRYPTO
- select CRYPTO_HASH
- select XXHASH
- select CRYPTO_XXHASH
select NFS_ACL_SUPPORT if NFS_V3_ACL
help
Choose Y here if you want to access files residing on other
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bac4cf1a308e..c6b263b5faf1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -39,7 +39,7 @@
#include <linux/sched.h>
#include <linux/kmemleak.h>
#include <linux/xattr.h>
-#include <linux/xxhash.h>
+#include <linux/hash.h>
#include "delegation.h"
#include "iostat.h"
@@ -350,10 +350,7 @@ out:
* of directory cookies. Content is addressed by the value of the
* cookie index of the first readdir entry in a page.
*
- * The xxhash algorithm is chosen because it is fast, and is supposed
- * to result in a decent flat distribution of hashes.
- *
- * We then select only the first 18 bits to avoid issues with excessive
+ * We select only the first 18 bits to avoid issues with excessive
* memory use for the page cache XArray. 18 bits should allow the caching
* of 262144 pages of sequences of readdir entries. Since each page holds
* 127 readdir entries for a typical 64-bit system, that works out to a
@@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie)
{
if (cookie == 0)
return 0;
- return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK;
+ return hash_64(cookie, 18);
}
static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
@@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = {
};
EXPORT_SYMBOL_GPL(nfs4_dentry_operations);
-static fmode_t flags_to_mode(int flags)
-{
- fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
- if ((flags & O_ACCMODE) != O_WRONLY)
- res |= FMODE_READ;
- if ((flags & O_ACCMODE) != O_RDONLY)
- res |= FMODE_WRITE;
- return res;
-}
-
static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp)
{
return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7eb3b08d702f..b4e46b0ffa2d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp)
nfs_fscache_open_file(inode, filp);
return 0;
}
-EXPORT_SYMBOL_GPL(nfs_open);
/*
* This function is called whenever some part of NFS notices that
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 57b0497105c8..7eefa16ed381 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry)
return true;
}
+static inline fmode_t flags_to_mode(int flags)
+{
+ fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
+ if ((flags & O_ACCMODE) != O_WRONLY)
+ res |= FMODE_READ;
+ if ((flags & O_ACCMODE) != O_RDONLY)
+ res |= FMODE_WRITE;
+ return res;
+}
+
/*
* Note: RFC 1813 doesn't limit the number of auth flavors that
* a server can return, so make something up.
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index ad3405c64b9e..e7b34f7e0614 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void)
nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache",
sizeof(struct nfs4_xattr_cache), 0,
- (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+ (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
nfs4_xattr_cache_init_once);
if (nfs4_xattr_cache_cachep == NULL)
return -ENOMEM;
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index d258933cf8c8..7b861e4f0533 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
struct dentry *parent = NULL;
struct inode *dir;
unsigned openflags = filp->f_flags;
+ fmode_t f_mode;
struct iattr attr;
int err;
@@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp)
if (err)
return err;
+ f_mode = filp->f_mode;
if ((openflags & O_ACCMODE) == 3)
- return nfs_open(inode, filp);
+ f_mode |= flags_to_mode(openflags);
/* We can't create new files here */
openflags &= ~(O_CREAT|O_EXCL);
@@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
parent = dget_parent(dentry);
dir = d_inode(parent);
- ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp);
+ ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp);
err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e3f5b380cefe..16106f805ffa 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
task = rpc_run_task(&task_setup_data);
+ if (IS_ERR(task))
+ return ERR_CAST(task);
status = rpc_wait_for_completion_task(task);
if (status != 0)
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 5fa11e1aca4c..6f325e10056c 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
return ERR_PTR(-ENOMEM);
+ task_setup_data.task = &data->task;
task_setup_data.callback_data = data;
data->cred = get_current_cred();
generated by cgit (git 2.34.1) at 2025-06-01 18:53:49 +0000