summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-02-15 00:47:02 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-02-15 00:47:02 +0300
commitca60ad6a6bc4aa88c02c6f103dd80df54689ea4d (patch)
tree4006fd61ccb1d26882b50078efdff49b4024154f /fs
parent2019fc96af228b412bdb2e8e0ad4b1fc12046a51 (diff)
parent2ca10259b4189a433c309054496dd6af1415f992 (diff)
downloadlinux-ca60ad6a6bc4aa88c02c6f103dd80df54689ea4d.tar.xz
Merge tag 'io_uring-5.6-2020-02-14' of git://git.kernel.dk/linux-block
Pull io_uring fixes from Jens Axboe: "Here's a set of fixes for io_uring: - Various fixes with cleanups from Pavel, fixing corner cases where we're not correctly dealing with iovec cleanup. - Clarify that statx/openat/openat2 don't accept fixed files - Buffered raw device write EOPTNOTSUPP fix - Ensure async workers grab current->fs - A few task exit fixes with pending requests that grab the file table - send/recvmsg async load fix - io-wq offline node setup fix - CQ overflow flush in poll" * tag 'io_uring-5.6-2020-02-14' of git://git.kernel.dk/linux-block: (21 commits) io_uring: prune request from overflow list on flush io-wq: don't call kXalloc_node() with non-online node io_uring: retain sockaddr_storage across send/recvmsg async punt io_uring: cancel pending async work if task exits io-wq: add io_wq_cancel_pid() to cancel based on a specific pid io-wq: make io_wqe_cancel_work() take a match handler io_uring: fix openat/statx's filename leak io_uring: fix double prep iovec leak io_uring: fix async close() with f_op->flush() io_uring: allow AT_FDCWD for non-file openat/openat2/statx io_uring: grab ->fs as part of async preparation io-wq: add support for inheriting ->fs io_uring: retry raw bdev writes if we hit -EOPNOTSUPP io_uring: add cleanup for openat()/statx() io_uring: fix iovec leaks io_uring: remove unused struct io_async_open io_uring: flush overflowed CQ events in the io_uring_poll() io_uring: statx/openat/openat2 don't support fixed files io_uring: fix deferred req iovec leak io_uring: fix 1-bit bitfields to be unsigned ...
Diffstat (limited to 'fs')
-rw-r--r--fs/io-wq.c92
-rw-r--r--fs/io-wq.h6
-rw-r--r--fs/io_uring.c299
3 files changed, 284 insertions, 113 deletions
diff --git a/fs/io-wq.c b/fs/io-wq.c
index cb60a42b9fdf..0a5ab1a8f69a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,6 +16,7 @@
#include <linux/slab.h>
#include <linux/kthread.h>
#include <linux/rculist_nulls.h>
+#include <linux/fs_struct.h>
#include "io-wq.h"
@@ -59,6 +60,7 @@ struct io_worker {
const struct cred *cur_creds;
const struct cred *saved_creds;
struct files_struct *restore_files;
+ struct fs_struct *restore_fs;
};
#if BITS_PER_LONG == 64
@@ -151,6 +153,9 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
task_unlock(current);
}
+ if (current->fs != worker->restore_fs)
+ current->fs = worker->restore_fs;
+
/*
* If we have an active mm, we need to drop the wq lock before unusing
* it. If we do, return true and let the caller retry the idle loop.
@@ -311,6 +316,7 @@ static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker)
worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
worker->restore_files = current->files;
+ worker->restore_fs = current->fs;
io_wqe_inc_running(wqe, worker);
}
@@ -481,6 +487,8 @@ next:
current->files = work->files;
task_unlock(current);
}
+ if (work->fs && current->fs != work->fs)
+ current->fs = work->fs;
if (work->mm != worker->mm)
io_wq_switch_mm(worker, work);
if (worker->cur_creds != work->creds)
@@ -691,11 +699,16 @@ static int io_wq_manager(void *data)
/* create fixed workers */
refcount_set(&wq->refs, workers_to_create);
for_each_node(node) {
+ if (!node_online(node))
+ continue;
if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
goto err;
workers_to_create--;
}
+ while (workers_to_create--)
+ refcount_dec(&wq->refs);
+
complete(&wq->done);
while (!kthread_should_stop()) {
@@ -703,6 +716,9 @@ static int io_wq_manager(void *data)
struct io_wqe *wqe = wq->wqes[node];
bool fork_worker[2] = { false, false };
+ if (!node_online(node))
+ continue;
+
spin_lock_irq(&wqe->lock);
if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
fork_worker[IO_WQ_ACCT_BOUND] = true;
@@ -821,7 +837,9 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe,
list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
if (io_worker_get(worker)) {
- ret = func(worker, data);
+ /* no task if node is/was offline */
+ if (worker->task)
+ ret = func(worker, data);
io_worker_release(worker);
if (ret)
break;
@@ -929,17 +947,19 @@ enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
return ret;
}
+struct work_match {
+ bool (*fn)(struct io_wq_work *, void *data);
+ void *data;
+};
+
static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
{
- struct io_wq_work *work = data;
+ struct work_match *match = data;
unsigned long flags;
bool ret = false;
- if (worker->cur_work != work)
- return false;
-
spin_lock_irqsave(&worker->lock, flags);
- if (worker->cur_work == work &&
+ if (match->fn(worker->cur_work, match->data) &&
!(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
send_sig(SIGINT, worker->task, 1);
ret = true;
@@ -950,15 +970,13 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
}
static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
- struct io_wq_work *cwork)
+ struct work_match *match)
{
struct io_wq_work_node *node, *prev;
struct io_wq_work *work;
unsigned long flags;
bool found = false;
- cwork->flags |= IO_WQ_WORK_CANCEL;
-
/*
* First check pending list, if we're lucky we can just remove it
* from there. CANCEL_OK means that the work is returned as-new,
@@ -968,7 +986,7 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
wq_list_for_each(node, prev, &wqe->work_list) {
work = container_of(node, struct io_wq_work, list);
- if (work == cwork) {
+ if (match->fn(work, match->data)) {
wq_node_del(&wqe->work_list, node, prev);
found = true;
break;
@@ -989,20 +1007,60 @@ static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
* completion will run normally in this case.
*/
rcu_read_lock();
- found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, cwork);
+ found = io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
rcu_read_unlock();
return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
}
+static bool io_wq_work_match(struct io_wq_work *work, void *data)
+{
+ return work == data;
+}
+
enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
{
+ struct work_match match = {
+ .fn = io_wq_work_match,
+ .data = cwork
+ };
enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
int node;
+ cwork->flags |= IO_WQ_WORK_CANCEL;
+
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
- ret = io_wqe_cancel_work(wqe, cwork);
+ ret = io_wqe_cancel_work(wqe, &match);
+ if (ret != IO_WQ_CANCEL_NOTFOUND)
+ break;
+ }
+
+ return ret;
+}
+
+static bool io_wq_pid_match(struct io_wq_work *work, void *data)
+{
+ pid_t pid = (pid_t) (unsigned long) data;
+
+ if (work)
+ return work->task_pid == pid;
+ return false;
+}
+
+enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
+{
+ struct work_match match = {
+ .fn = io_wq_pid_match,
+ .data = (void *) (unsigned long) pid
+ };
+ enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
+ int node;
+
+ for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
+
+ ret = io_wqe_cancel_work(wqe, &match);
if (ret != IO_WQ_CANCEL_NOTFOUND)
break;
}
@@ -1036,6 +1094,8 @@ void io_wq_flush(struct io_wq *wq)
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
+ if (!node_online(node))
+ continue;
init_completion(&data.done);
INIT_IO_WORK(&data.work, io_wq_flush_func);
data.work.flags |= IO_WQ_WORK_INTERNAL;
@@ -1067,12 +1127,15 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
for_each_node(node) {
struct io_wqe *wqe;
+ int alloc_node = node;
- wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node);
+ if (!node_online(alloc_node))
+ alloc_node = NUMA_NO_NODE;
+ wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
if (!wqe)
goto err;
wq->wqes[node] = wqe;
- wqe->node = node;
+ wqe->node = alloc_node;
wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
if (wq->user) {
@@ -1080,7 +1143,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
task_rlimit(current, RLIMIT_NPROC);
}
atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
- wqe->node = node;
wqe->wq = wq;
spin_lock_init(&wqe->lock);
INIT_WQ_LIST(&wqe->work_list);
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 50b3378febf2..ccc7d84af57d 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -74,17 +74,20 @@ struct io_wq_work {
struct files_struct *files;
struct mm_struct *mm;
const struct cred *creds;
+ struct fs_struct *fs;
unsigned flags;
+ pid_t task_pid;
};
#define INIT_IO_WORK(work, _func) \
do { \
(work)->list.next = NULL; \
(work)->func = _func; \
- (work)->flags = 0; \
(work)->files = NULL; \
(work)->mm = NULL; \
(work)->creds = NULL; \
+ (work)->fs = NULL; \
+ (work)->flags = 0; \
} while (0) \
typedef void (get_work_fn)(struct io_wq_work *);
@@ -107,6 +110,7 @@ void io_wq_flush(struct io_wq *wq);
void io_wq_cancel_all(struct io_wq *wq);
enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
+enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid);
typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 77f22c3da30f..5a826017ebb8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -75,6 +75,7 @@
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
#include <linux/eventpoll.h>
+#include <linux/fs_struct.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -204,11 +205,11 @@ struct io_ring_ctx {
struct {
unsigned int flags;
- int compat: 1;
- int account_mem: 1;
- int cq_overflow_flushed: 1;
- int drain_next: 1;
- int eventfd_async: 1;
+ unsigned int compat: 1;
+ unsigned int account_mem: 1;
+ unsigned int cq_overflow_flushed: 1;
+ unsigned int drain_next: 1;
+ unsigned int eventfd_async: 1;
/*
* Ring buffer of indices into array of io_uring_sqe, which is
@@ -441,6 +442,7 @@ struct io_async_msghdr {
struct iovec *iov;
struct sockaddr __user *uaddr;
struct msghdr msg;
+ struct sockaddr_storage addr;
};
struct io_async_rw {
@@ -450,17 +452,12 @@ struct io_async_rw {
ssize_t size;
};
-struct io_async_open {
- struct filename *filename;
-};
-
struct io_async_ctx {
union {
struct io_async_rw rw;
struct io_async_msghdr msg;
struct io_async_connect connect;
struct io_timeout_data timeout;
- struct io_async_open open;
};
};
@@ -483,6 +480,8 @@ enum {
REQ_F_MUST_PUNT_BIT,
REQ_F_TIMEOUT_NOSEQ_BIT,
REQ_F_COMP_LOCKED_BIT,
+ REQ_F_NEED_CLEANUP_BIT,
+ REQ_F_OVERFLOW_BIT,
};
enum {
@@ -521,6 +520,10 @@ enum {
REQ_F_TIMEOUT_NOSEQ = BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
/* completion under lock */
REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT),
+ /* needs cleanup */
+ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
+ /* in overflow list */
+ REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT),
};
/*
@@ -553,7 +556,6 @@ struct io_kiocb {
* llist_node is only used for poll deferred completions
*/
struct llist_node llist_node;
- bool has_user;
bool in_async;
bool needs_fixed_file;
u8 opcode;
@@ -614,6 +616,8 @@ struct io_op_def {
unsigned not_supported : 1;
/* needs file table */
unsigned file_table : 1;
+ /* needs ->fs */
+ unsigned needs_fs : 1;
};
static const struct io_op_def io_op_defs[] = {
@@ -656,12 +660,14 @@ static const struct io_op_def io_op_defs[] = {
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .needs_fs = 1,
},
[IORING_OP_RECVMSG] = {
.async_ctx = 1,
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .needs_fs = 1,
},
[IORING_OP_TIMEOUT] = {
.async_ctx = 1,
@@ -692,6 +698,7 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
.fd_non_neg = 1,
.file_table = 1,
+ .needs_fs = 1,
},
[IORING_OP_CLOSE] = {
.needs_file = 1,
@@ -705,6 +712,7 @@ static const struct io_op_def io_op_defs[] = {
.needs_mm = 1,
.needs_file = 1,
.fd_non_neg = 1,
+ .needs_fs = 1,
},
[IORING_OP_READ] = {
.needs_mm = 1,
@@ -736,6 +744,7 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
.fd_non_neg = 1,
.file_table = 1,
+ .needs_fs = 1,
},
[IORING_OP_EPOLL_CTL] = {
.unbound_nonreg_file = 1,
@@ -754,6 +763,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
unsigned nr_args);
static int io_grab_files(struct io_kiocb *req);
static void io_ring_file_ref_flush(struct fixed_file_data *data);
+static void io_cleanup_req(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -909,6 +919,18 @@ static inline void io_req_work_grab_env(struct io_kiocb *req,
}
if (!req->work.creds)
req->work.creds = get_current_cred();
+ if (!req->work.fs && def->needs_fs) {
+ spin_lock(&current->fs->lock);
+ if (!current->fs->in_exec) {
+ req->work.fs = current->fs;
+ req->work.fs->users++;
+ } else {
+ req->work.flags |= IO_WQ_WORK_CANCEL;
+ }
+ spin_unlock(&current->fs->lock);
+ }
+ if (!req->work.task_pid)
+ req->work.task_pid = task_pid_vnr(current);
}
static inline void io_req_work_drop_env(struct io_kiocb *req)
@@ -921,6 +943,16 @@ static inline void io_req_work_drop_env(struct io_kiocb *req)
put_cred(req->work.creds);
req->work.creds = NULL;
}
+ if (req->work.fs) {
+ struct fs_struct *fs = req->work.fs;
+
+ spin_lock(&req->work.fs->lock);
+ if (--fs->users)
+ fs = NULL;
+ spin_unlock(&req->work.fs->lock);
+ if (fs)
+ free_fs_struct(fs);
+ }
}
static inline bool io_prep_async_work(struct io_kiocb *req,
@@ -1074,6 +1106,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb,
list);
list_move(&req->list, &list);
+ req->flags &= ~REQ_F_OVERFLOW;
if (cqe) {
WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, req->result);
@@ -1126,6 +1159,7 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
set_bit(0, &ctx->sq_check_overflow);
set_bit(0, &ctx->cq_check_overflow);
}
+ req->flags |= REQ_F_OVERFLOW;
refcount_inc(&req->refs);
req->result = res;
list_add_tail(&req->list, &ctx->cq_overflow_list);
@@ -1241,6 +1275,9 @@ static void __io_free_req(struct io_kiocb *req)
{
__io_req_aux_free(req);
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ io_cleanup_req(req);
+
if (req->flags & REQ_F_INFLIGHT) {
struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
@@ -2056,9 +2093,6 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
return iorw->size;
}
- if (!req->has_user)
- return -EFAULT;
-
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
@@ -2137,6 +2171,8 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
req->io->rw.iov = req->io->rw.fast_iov;
memcpy(req->io->rw.iov, fast_iov,
sizeof(struct iovec) * iter->nr_segs);
+ } else {
+ req->flags |= REQ_F_NEED_CLEANUP;
}
}
@@ -2148,17 +2184,6 @@ static int io_alloc_async_ctx(struct io_kiocb *req)
return req->io == NULL;
}
-static void io_rw_async(struct io_wq_work **workptr)
-{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct iovec *iov = NULL;
-
- if (req->io->rw.iov != req->io->rw.fast_iov)
- iov = req->io->rw.iov;
- io_wq_submit_work(workptr);
- kfree(iov);
-}
-
static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
struct iovec *iovec, struct iovec *fast_iov,
struct iov_iter *iter)
@@ -2171,7 +2196,6 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
io_req_map_rw(req, io_size, iovec, fast_iov, iter);
}
- req->work.func = io_rw_async;
return 0;
}
@@ -2189,7 +2213,8 @@ 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;
- if (!req->io)
+ /* either don't need iovec imported or already have it */
+ if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
return 0;
io = req->io;
@@ -2258,8 +2283,8 @@ copy_iov:
}
}
out_free:
- if (!io_wq_current_is_worker())
- kfree(iovec);
+ kfree(iovec);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
return ret;
}
@@ -2277,7 +2302,8 @@ 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;
- if (!req->io)
+ /* either don't need iovec imported or already have it */
+ if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
return 0;
io = req->io;
@@ -2352,6 +2378,12 @@ static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
ret2 = call_write_iter(req->file, kiocb, &iter);
else
ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter);
+ /*
+ * Raw bdev writes will -EOPNOTSUPP for IOCB_NOWAIT. Just
+ * retry them without IOCB_NOWAIT.
+ */
+ if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
+ ret2 = -EAGAIN;
if (!force_nonblock || ret2 != -EAGAIN) {
kiocb_done(kiocb, ret2, nxt, req->in_async);
} else {
@@ -2364,8 +2396,8 @@ copy_iov:
}
}
out_free:
- if (!io_wq_current_is_worker())
- kfree(iovec);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+ kfree(iovec);
return ret;
}
@@ -2534,6 +2566,10 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (sqe->ioprio || sqe->buf_index)
return -EINVAL;
+ if (sqe->flags & IOSQE_FIXED_FILE)
+ return -EBADF;
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
req->open.dfd = READ_ONCE(sqe->fd);
req->open.how.mode = READ_ONCE(sqe->len);
@@ -2547,6 +2583,7 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return ret;
}
+ req->flags |= REQ_F_NEED_CLEANUP;
return 0;
}
@@ -2559,6 +2596,10 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (sqe->ioprio || sqe->buf_index)
return -EINVAL;
+ if (sqe->flags & IOSQE_FIXED_FILE)
+ return -EBADF;
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
req->open.dfd = READ_ONCE(sqe->fd);
fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -2583,6 +2624,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return ret;
}
+ req->flags |= REQ_F_NEED_CLEANUP;
return 0;
}
@@ -2614,6 +2656,7 @@ static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
}
err:
putname(req->open.filename);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
@@ -2754,6 +2797,10 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (sqe->ioprio || sqe->buf_index)
return -EINVAL;
+ if (sqe->flags & IOSQE_FIXED_FILE)
+ return -EBADF;
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
req->open.dfd = READ_ONCE(sqe->fd);
req->open.mask = READ_ONCE(sqe->len);
@@ -2771,6 +2818,7 @@ static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return ret;
}
+ req->flags |= REQ_F_NEED_CLEANUP;
return 0;
}
@@ -2808,6 +2856,7 @@ retry:
ret = cp_statx(&stat, ctx->buffer);
err:
putname(ctx->filename);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
@@ -2827,7 +2876,7 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
sqe->rw_flags || sqe->buf_index)
return -EINVAL;
if (sqe->flags & IOSQE_FIXED_FILE)
- return -EINVAL;
+ return -EBADF;
req->close.fd = READ_ONCE(sqe->fd);
if (req->file->f_op == &io_uring_fops ||
@@ -2837,24 +2886,25 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return 0;
}
+/* only called when __close_fd_get_file() is done */
+static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt)
+{
+ int ret;
+
+ ret = filp_close(req->close.put_file, req->work.files);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ fput(req->close.put_file);
+ io_put_req_find_next(req, nxt);
+}
+
static void io_close_finish(struct io_wq_work **workptr)
{
struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
struct io_kiocb *nxt = NULL;
- /* Invoked with files, we need to do the close */
- if (req->work.files) {
- int ret;
-
- ret = filp_close(req->close.put_file, req->work.files);
- if (ret < 0)
- req_set_fail_links(req);
- io_cqring_add_event(req, ret);
- }
-
- fput(req->close.put_file);
-
- io_put_req_find_next(req, &nxt);
+ __io_close_finish(req, &nxt);
if (nxt)
io_wq_assign_next(workptr, nxt);
}
@@ -2877,22 +2927,8 @@ static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
* No ->flush(), safely close from here and just punt the
* fput() to async context.
*/
- ret = filp_close(req->close.put_file, current->files);
-
- if (ret < 0)
- req_set_fail_links(req);
- io_cqring_add_event(req, ret);
-
- if (io_wq_current_is_worker()) {
- struct io_wq_work *old_work, *work;
-
- old_work = work = &req->work;
- io_close_finish(&work);
- if (work && work != old_work)
- *nxt = container_of(work, struct io_kiocb, work);
- return 0;
- }
-
+ __io_close_finish(req, nxt);
+ return 0;
eagain:
req->work.func = io_close_finish;
/*
@@ -2960,24 +2996,12 @@ static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt,
return 0;
}
-#if defined(CONFIG_NET)
-static void io_sendrecv_async(struct io_wq_work **workptr)
-{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct iovec *iov = NULL;
-
- if (req->io->rw.iov != req->io->rw.fast_iov)
- iov = req->io->msg.iov;
- io_wq_submit_work(workptr);
- kfree(iov);
-}
-#endif
-
static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_NET)
struct io_sr_msg *sr = &req->sr_msg;
struct io_async_ctx *io = req->io;
+ int ret;
sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -2985,10 +3009,16 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (!io || req->opcode == IORING_OP_SEND)
return 0;
+ /* iovec is already imported */
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
io->msg.iov = io->msg.fast_iov;
- return sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
+ ret = sendmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
&io->msg.iov);
+ if (!ret)
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return ret;
#else
return -EOPNOTSUPP;
#endif
@@ -3008,12 +3038,11 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
sock = sock_from_file(req->file, &ret);
if (sock) {
struct io_async_ctx io;
- struct sockaddr_storage addr;
unsigned flags;
if (req->io) {
kmsg = &req->io->msg;
- kmsg->msg.msg_name = &addr;
+ kmsg->msg.msg_name = &req->io->msg.addr;
/* if iov is set, it's allocated already */
if (!kmsg->iov)
kmsg->iov = kmsg->fast_iov;
@@ -3022,7 +3051,7 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
struct io_sr_msg *sr = &req->sr_msg;
kmsg = &io.msg;
- kmsg->msg.msg_name = &addr;
+ kmsg->msg.msg_name = &io.msg.addr;
io.msg.iov = io.msg.fast_iov;
ret = sendmsg_copy_msghdr(&io.msg.msg, sr->msg,
@@ -3041,18 +3070,22 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
if (force_nonblock && ret == -EAGAIN) {
if (req->io)
return -EAGAIN;
- if (io_alloc_async_ctx(req))
+ if (io_alloc_async_ctx(req)) {
+ if (kmsg && kmsg->iov != kmsg->fast_iov)
+ kfree(kmsg->iov);
return -ENOMEM;
+ }
+ req->flags |= REQ_F_NEED_CLEANUP;
memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
- req->work.func = io_sendrecv_async;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
}
- if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
+ if (kmsg && kmsg->iov != kmsg->fast_iov)
kfree(kmsg->iov);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
io_cqring_add_event(req, ret);
if (ret < 0)
req_set_fail_links(req);
@@ -3120,6 +3153,7 @@ static int io_recvmsg_prep(struct io_kiocb *req,
#if defined(CONFIG_NET)
struct io_sr_msg *sr = &req->sr_msg;
struct io_async_ctx *io = req->io;
+ int ret;
sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -3127,10 +3161,16 @@ static int io_recvmsg_prep(struct io_kiocb *req,
if (!io || req->opcode == IORING_OP_RECV)
return 0;
+ /* iovec is already imported */
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
io->msg.iov = io->msg.fast_iov;
- return recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
+ ret = recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
&io->msg.uaddr, &io->msg.iov);
+ if (!ret)
+ req->flags |= REQ_F_NEED_CLEANUP;
+ return ret;
#else
return -EOPNOTSUPP;
#endif
@@ -3150,12 +3190,11 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
sock = sock_from_file(req->file, &ret);
if (sock) {
struct io_async_ctx io;
- struct sockaddr_storage addr;
unsigned flags;
if (req->io) {
kmsg = &req->io->msg;
- kmsg->msg.msg_name = &addr;
+ kmsg->msg.msg_name = &req->io->msg.addr;
/* if iov is set, it's allocated already */
if (!kmsg->iov)
kmsg->iov = kmsg->fast_iov;
@@ -3164,7 +3203,7 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
struct io_sr_msg *sr = &req->sr_msg;
kmsg = &io.msg;
- kmsg->msg.msg_name = &addr;
+ kmsg->msg.msg_name = &io.msg.addr;
io.msg.iov = io.msg.fast_iov;
ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg,
@@ -3185,18 +3224,22 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
if (force_nonblock && ret == -EAGAIN) {
if (req->io)
return -EAGAIN;
- if (io_alloc_async_ctx(req))
+ if (io_alloc_async_ctx(req)) {
+ if (kmsg && kmsg->iov != kmsg->fast_iov)
+ kfree(kmsg->iov);
return -ENOMEM;
+ }
memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
- req->work.func = io_sendrecv_async;
+ req->flags |= REQ_F_NEED_CLEANUP;
return -EAGAIN;
}
if (ret == -ERESTARTSYS)
ret = -EINTR;
}
- if (!io_wq_current_is_worker() && kmsg && kmsg->iov != kmsg->fast_iov)
+ if (kmsg && kmsg->iov != kmsg->fast_iov)
kfree(kmsg->iov);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
io_cqring_add_event(req, ret);
if (ret < 0)
req_set_fail_links(req);
@@ -4207,6 +4250,35 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return -EIOCBQUEUED;
}
+static void io_cleanup_req(struct io_kiocb *req)
+{
+ struct io_async_ctx *io = req->io;
+
+ switch (req->opcode) {
+ case IORING_OP_READV:
+ case IORING_OP_READ_FIXED:
+ case IORING_OP_READ:
+ case IORING_OP_WRITEV:
+ case IORING_OP_WRITE_FIXED:
+ case IORING_OP_WRITE:
+ if (io->rw.iov != io->rw.fast_iov)
+ kfree(io->rw.iov);
+ break;
+ case IORING_OP_SENDMSG:
+ case IORING_OP_RECVMSG:
+ if (io->msg.iov != io->msg.fast_iov)
+ kfree(io->msg.iov);
+ break;
+ case IORING_OP_OPENAT:
+ case IORING_OP_OPENAT2:
+ case IORING_OP_STATX:
+ putname(req->open.filename);
+ break;
+ }
+
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+}
+
static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct io_kiocb **nxt, bool force_nonblock)
{
@@ -4446,7 +4518,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
}
if (!ret) {
- req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
req->in_async = true;
do {
ret = io_issue_sqe(req, NULL, &nxt, false);
@@ -4479,7 +4550,7 @@ static int io_req_needs_file(struct io_kiocb *req, int fd)
{
if (!io_op_defs[req->opcode].needs_file)
return 0;
- if (fd == -1 && io_op_defs[req->opcode].fd_non_neg)
+ if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
return 0;
return 1;
}
@@ -4950,6 +5021,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
for (i = 0; i < nr; i++) {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
+ int err;
req = io_get_req(ctx, statep);
if (unlikely(!req)) {
@@ -4966,20 +5038,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
submitted++;
if (unlikely(req->opcode >= IORING_OP_LAST)) {
- io_cqring_add_event(req, -EINVAL);
+ err = -EINVAL;
+fail_req:
+ io_cqring_add_event(req, err);
io_double_put_req(req);
break;
}
if (io_op_defs[req->opcode].needs_mm && !*mm) {
mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
- if (!mm_fault) {
- use_mm(ctx->sqo_mm);
- *mm = ctx->sqo_mm;
+ if (unlikely(mm_fault)) {
+ err = -EFAULT;
+ goto fail_req;
}
+ use_mm(ctx->sqo_mm);
+ *mm = ctx->sqo_mm;
}
- req->has_user = *mm != NULL;
req->in_async = async;
req->needs_fixed_file = async;
trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
@@ -6301,7 +6376,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
if (READ_ONCE(ctx->rings->sq.tail) - ctx->cached_sq_head !=
ctx->rings->sq_ring_entries)
mask |= EPOLLOUT | EPOLLWRNORM;
- if (READ_ONCE(ctx->rings->cq.head) != ctx->cached_cq_tail)
+ if (io_cqring_events(ctx, false))
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
@@ -6393,6 +6468,29 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
if (!cancel_req)
break;
+ if (cancel_req->flags & REQ_F_OVERFLOW) {
+ spin_lock_irq(&ctx->completion_lock);
+ list_del(&cancel_req->list);
+ cancel_req->flags &= ~REQ_F_OVERFLOW;
+ if (list_empty(&ctx->cq_overflow_list)) {
+ clear_bit(0, &ctx->sq_check_overflow);
+ clear_bit(0, &ctx->cq_check_overflow);
+ }
+ spin_unlock_irq(&ctx->completion_lock);
+
+ WRITE_ONCE(ctx->rings->cq_overflow,
+ atomic_inc_return(&ctx->cached_cq_overflow));
+
+ /*
+ * Put inflight ref and overflow ref. If that's
+ * all we had, then we're done with this request.
+ */
+ if (refcount_sub_and_test(2, &cancel_req->refs)) {
+ io_put_req(cancel_req);
+ continue;
+ }
+ }
+
io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
io_put_req(cancel_req);
schedule();
@@ -6405,6 +6503,13 @@ static int io_uring_flush(struct file *file, void *data)
struct io_ring_ctx *ctx = file->private_data;
io_uring_cancel_files(ctx, data);
+
+ /*
+ * If the task is going away, cancel work it may have pending
+ */
+ if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
+ io_wq_cancel_pid(ctx->io_wq, task_pid_vnr(current));
+
return 0;
}