#include <linux/sizes.h>
#include <linux/hugetlb.h>
#include <linux/highmem.h>
+#include <linux/namei.h>
+#include <linux/fsnotify.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
struct file **files;
};
+enum {
+ FFD_F_ATOMIC,
+};
+
+struct fixed_file_data {
+ struct fixed_file_table *table;
+ struct io_ring_ctx *ctx;
+
+ struct percpu_ref refs;
+ struct llist_head put_llist;
+ unsigned long state;
+ struct work_struct ref_work;
+ struct completion done;
+};
+
struct io_ring_ctx {
struct {
struct percpu_ref refs;
unsigned sq_thread_idle;
unsigned cached_sq_dropped;
atomic_t cached_cq_overflow;
- struct io_uring_sqe *sq_sqes;
+ unsigned long sq_check_overflow;
struct list_head defer_list;
struct list_head timeout_list;
struct list_head cq_overflow_list;
wait_queue_head_t inflight_wait;
+ struct io_uring_sqe *sq_sqes;
} ____cacheline_aligned_in_smp;
struct io_rings *rings;
* readers must ensure that ->refs is alive as long as the file* is
* used. Only updated through io_uring_register(2).
*/
- struct fixed_file_table *file_table;
+ struct fixed_file_data *file_data;
unsigned nr_user_files;
/* if used, fixed mapped user buffers */
unsigned cq_entries;
unsigned cq_mask;
atomic_t cq_timeouts;
+ unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
struct eventfd_ctx *cq_ev_fd;
struct {
spinlock_t completion_lock;
- bool poll_multi_file;
+ struct llist_head poll_llist;
+
/*
* ->poll_list is protected by the ctx->uring_lock for
* io_uring instances that don't use IORING_SETUP_SQPOLL.
struct list_head poll_list;
struct hlist_head *cancel_hash;
unsigned cancel_hash_bits;
+ bool poll_multi_file;
spinlock_t inflight_lock;
struct list_head inflight_list;
struct wait_queue_entry wait;
};
+struct io_close {
+ struct file *file;
+ struct file *put_file;
+ int fd;
+};
+
struct io_timeout_data {
struct io_kiocb *req;
struct hrtimer timer;
loff_t len;
loff_t off;
int flags;
+ int mode;
};
struct io_cancel {
int msg_flags;
};
+struct io_open {
+ struct file *file;
+ int dfd;
+ union {
+ umode_t mode;
+ unsigned mask;
+ };
+ const char __user *fname;
+ struct filename *filename;
+ struct statx __user *buffer;
+ int flags;
+};
+
+struct io_files_update {
+ struct file *file;
+ u64 arg;
+ u32 nr_args;
+ u32 offset;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
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;
};
};
struct io_timeout timeout;
struct io_connect connect;
struct io_sr_msg sr_msg;
+ struct io_open open;
+ struct io_close close;
+ struct io_files_update files_update;
};
struct io_async_ctx *io;
- struct file *ring_file;
+ union {
+ /*
+ * ring_file is only used in the submission path, and
+ * llist_node is only used for poll deferred completions
+ */
+ struct file *ring_file;
+ struct llist_node llist_node;
+ };
int ring_fd;
bool has_user;
bool in_async;
#define REQ_F_INFLIGHT 16384 /* on inflight list */
#define REQ_F_COMP_LOCKED 32768 /* completion under lock */
#define REQ_F_HARDLINK 65536 /* doesn't sever on completion < 0 */
+#define REQ_F_FORCE_ASYNC 131072 /* IOSQE_ASYNC */
u64 user_data;
u32 result;
u32 sequence;
unsigned int ios_left;
};
+struct io_op_def {
+ /* needs req->io allocated for deferral/async */
+ unsigned async_ctx : 1;
+ /* needs current->mm setup, does mm access */
+ unsigned needs_mm : 1;
+ /* needs req->file assigned */
+ unsigned needs_file : 1;
+ /* needs req->file assigned IFF fd is >= 0 */
+ unsigned fd_non_neg : 1;
+ /* hash wq insertion if file is a regular file */
+ unsigned hash_reg_file : 1;
+ /* unbound wq insertion if file is a non-regular file */
+ unsigned unbound_nonreg_file : 1;
+};
+
+static const struct io_op_def io_op_defs[] = {
+ {
+ /* IORING_OP_NOP */
+ },
+ {
+ /* IORING_OP_READV */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_WRITEV */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_FSYNC */
+ .needs_file = 1,
+ },
+ {
+ /* IORING_OP_READ_FIXED */
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_WRITE_FIXED */
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_POLL_ADD */
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_POLL_REMOVE */
+ },
+ {
+ /* IORING_OP_SYNC_FILE_RANGE */
+ .needs_file = 1,
+ },
+ {
+ /* IORING_OP_SENDMSG */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_RECVMSG */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_TIMEOUT */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ },
+ {
+ /* IORING_OP_TIMEOUT_REMOVE */
+ },
+ {
+ /* IORING_OP_ACCEPT */
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_ASYNC_CANCEL */
+ },
+ {
+ /* IORING_OP_LINK_TIMEOUT */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ },
+ {
+ /* IORING_OP_CONNECT */
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_FALLOCATE */
+ .needs_file = 1,
+ },
+ {
+ /* IORING_OP_OPENAT */
+ .needs_file = 1,
+ .fd_non_neg = 1,
+ },
+ {
+ /* IORING_OP_CLOSE */
+ .needs_file = 1,
+ },
+ {
+ /* IORING_OP_FILES_UPDATE */
+ .needs_mm = 1,
+ },
+ {
+ /* IORING_OP_STATX */
+ .needs_mm = 1,
+ .needs_file = 1,
+ .fd_non_neg = 1,
+ },
+ {
+ /* IORING_OP_READ */
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ {
+ /* IORING_OP_WRITE */
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+};
+
static void io_wq_submit_work(struct io_wq_work **workptr);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
-static void __io_free_req(struct io_kiocb *req);
static void io_put_req(struct io_kiocb *req);
-static void io_double_put_req(struct io_kiocb *req);
static void __io_double_put_req(struct io_kiocb *req);
static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+ struct io_uring_files_update *ip,
+ unsigned nr_args);
static struct kmem_cache *req_cachep;
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
+ init_llist_head(&ctx->poll_llist);
INIT_LIST_HEAD(&ctx->poll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
}
}
-static inline bool io_req_needs_user(struct io_kiocb *req)
-{
- return !(req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED);
-}
-
static inline bool io_prep_async_work(struct io_kiocb *req,
struct io_kiocb **link)
{
+ const struct io_op_def *def = &io_op_defs[req->opcode];
bool do_hashed = false;
- switch (req->opcode) {
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- /* only regular files should be hashed for writes */
- if (req->flags & REQ_F_ISREG)
+ if (req->flags & REQ_F_ISREG) {
+ if (def->hash_reg_file)
do_hashed = true;
- /* fall-through */
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_SENDMSG:
- case IORING_OP_RECVMSG:
- case IORING_OP_ACCEPT:
- case IORING_OP_POLL_ADD:
- case IORING_OP_CONNECT:
- /*
- * We know REQ_F_ISREG is not set on some of these
- * opcodes, but this enables us to keep the check in
- * just one place.
- */
- if (!(req->flags & REQ_F_ISREG))
+ } else {
+ if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
- break;
}
- if (io_req_needs_user(req))
+ if (def->needs_mm)
req->work.flags |= IO_WQ_WORK_NEEDS_USER;
*link = io_prep_linked_timeout(req);
}
io_commit_cqring(ctx);
+ if (cqe) {
+ clear_bit(0, &ctx->sq_check_overflow);
+ clear_bit(0, &ctx->cq_check_overflow);
+ }
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
} else {
+ if (list_empty(&ctx->cq_overflow_list)) {
+ set_bit(0, &ctx->sq_check_overflow);
+ set_bit(0, &ctx->cq_check_overflow);
+ }
refcount_inc(&req->refs);
req->result = res;
list_add_tail(&req->list, &ctx->cq_overflow_list);
if (*nr) {
kmem_cache_free_bulk(req_cachep, *nr, reqs);
percpu_ref_put_many(&ctx->refs, *nr);
+ percpu_ref_put_many(&ctx->file_data->refs, *nr);
*nr = 0;
}
}
if (req->io)
kfree(req->io);
- if (req->file && !(req->flags & REQ_F_FIXED_FILE))
- fput(req->file);
+ if (req->file) {
+ if (req->flags & REQ_F_FIXED_FILE)
+ percpu_ref_put(&ctx->file_data->refs);
+ else
+ fput(req->file);
+ }
if (req->flags & REQ_F_INFLIGHT) {
unsigned long flags;
{
struct io_rings *rings = ctx->rings;
- /*
- * noflush == true is from the waitqueue handler, just ensure we wake
- * up the task, and the next invocation will flush the entries. We
- * cannot safely to it from here.
- */
- if (noflush && !list_empty(&ctx->cq_overflow_list))
- return -1U;
+ if (test_bit(0, &ctx->cq_check_overflow)) {
+ /*
+ * noflush == true is from the waitqueue handler, just ensure
+ * we wake up the task, and the next invocation will flush the
+ * entries. We cannot safely to it from here.
+ */
+ if (noflush && !list_empty(&ctx->cq_overflow_list))
+ return -1U;
- io_cqring_overflow_flush(ctx, false);
+ io_cqring_overflow_flush(ctx, false);
+ }
/* See comment at the top of this file */
smp_rmb();
- return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
+ return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
}
static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
}
+static inline bool io_req_multi_free(struct io_kiocb *req)
+{
+ /*
+ * If we're not using fixed files, we have to pair the completion part
+ * with the file put. Use regular completions for those, only batch
+ * free for fixed file and non-linked commands.
+ */
+ if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) == REQ_F_FIXED_FILE)
+ && !io_is_fallback_req(req) && !req->io)
+ return true;
+
+ return false;
+}
+
/*
* Find and free completed poll iocbs
*/
(*nr_events)++;
if (refcount_dec_and_test(&req->refs)) {
- /* If we're not using fixed files, we have to pair the
- * completion part with the file put. Use regular
- * completions for those, only batch free for fixed
- * file and non-linked commands.
- */
- if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
- REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
- !req->io) {
+ if (io_req_multi_free(req)) {
reqs[to_free++] = req;
if (to_free == ARRAY_SIZE(reqs))
io_free_req_many(ctx, reqs, &to_free);
if (req->rw.kiocb.private)
return -EINVAL;
+ if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
+ ssize_t ret;
+ ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
+ *iovec = NULL;
+ return ret;
+ }
+
if (req->io) {
struct io_async_rw *iorw = &req->io->rw;
static int io_alloc_async_ctx(struct io_kiocb *req)
{
+ if (!io_op_defs[req->opcode].async_ctx)
+ return 0;
req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
return req->io == NULL;
}
return 0;
}
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct io_kiocb *nxt = NULL;
+ int ret;
+
+ ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
+ req->sync.len);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, &nxt);
+ if (nxt)
+ io_wq_assign_next(workptr, nxt);
+}
+
+static int io_fallocate_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)
+ return -EINVAL;
+
+ req->sync.off = READ_ONCE(sqe->off);
+ req->sync.len = READ_ONCE(sqe->addr);
+ req->sync.mode = READ_ONCE(sqe->len);
+ return 0;
+}
+
+static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_wq_work *work, *old_work;
+
+ /* fallocate always requiring blocking context */
+ if (force_nonblock) {
+ io_put_req(req);
+ req->work.func = io_fallocate_finish;
+ return -EAGAIN;
+ }
+
+ work = old_work = &req->work;
+ io_fallocate_finish(&work);
+ if (work && work != old_work)
+ *nxt = container_of(work, struct io_kiocb, work);
+
+ return 0;
+}
+
+static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ int ret;
+
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->open.dfd = READ_ONCE(sqe->fd);
+ req->open.mode = READ_ONCE(sqe->len);
+ req->open.fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ req->open.flags = READ_ONCE(sqe->open_flags);
+
+ req->open.filename = getname(req->open.fname);
+ if (IS_ERR(req->open.filename)) {
+ ret = PTR_ERR(req->open.filename);
+ req->open.filename = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct open_flags op;
+ struct open_how how;
+ struct file *file;
+ int ret;
+
+ if (force_nonblock) {
+ req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
+ return -EAGAIN;
+ }
+
+ how = build_open_how(req->open.flags, req->open.mode);
+ ret = build_open_flags(&how, &op);
+ if (ret)
+ goto err;
+
+ ret = get_unused_fd_flags(how.flags);
+ if (ret < 0)
+ goto err;
+
+ file = do_filp_open(req->open.dfd, req->open.filename, &op);
+ if (IS_ERR(file)) {
+ put_unused_fd(ret);
+ ret = PTR_ERR(file);
+ } else {
+ fsnotify_open(file);
+ fd_install(ret, file);
+ }
+err:
+ putname(req->open.filename);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ unsigned lookup_flags;
+ int ret;
+
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->open.dfd = READ_ONCE(sqe->fd);
+ req->open.mask = READ_ONCE(sqe->len);
+ req->open.fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ req->open.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+ req->open.flags = READ_ONCE(sqe->statx_flags);
+
+ if (vfs_stat_set_lookup_flags(&lookup_flags, req->open.flags))
+ return -EINVAL;
+
+ req->open.filename = getname_flags(req->open.fname, lookup_flags, NULL);
+ if (IS_ERR(req->open.filename)) {
+ ret = PTR_ERR(req->open.filename);
+ req->open.filename = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_open *ctx = &req->open;
+ unsigned lookup_flags;
+ struct path path;
+ struct kstat stat;
+ int ret;
+
+ if (force_nonblock)
+ return -EAGAIN;
+
+ if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->flags))
+ return -EINVAL;
+
+retry:
+ /* filename_lookup() drops it, keep a reference */
+ ctx->filename->refcnt++;
+
+ ret = filename_lookup(ctx->dfd, ctx->filename, lookup_flags, &path,
+ NULL);
+ if (ret)
+ goto err;
+
+ ret = vfs_getattr(&path, &stat, ctx->mask, ctx->flags);
+ path_put(&path);
+ if (retry_estale(ret, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
+ if (!ret)
+ ret = cp_statx(&stat, ctx->buffer);
+err:
+ putname(ctx->filename);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ /*
+ * If we queue this for async, it must not be cancellable. That would
+ * leave the 'file' in an undeterminate state.
+ */
+ req->work.flags |= IO_WQ_WORK_NO_CANCEL;
+
+ if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
+ sqe->rw_flags || sqe->buf_index)
+ return -EINVAL;
+ if (sqe->flags & IOSQE_FIXED_FILE)
+ return -EINVAL;
+
+ req->close.fd = READ_ONCE(sqe->fd);
+ if (req->file->f_op == &io_uring_fops ||
+ req->close.fd == req->ring_fd)
+ return -EBADF;
+
+ return 0;
+}
+
+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);
+
+ /* we bypassed the re-issue, drop the submission reference */
+ io_put_req(req);
+ io_put_req_find_next(req, &nxt);
+ if (nxt)
+ io_wq_assign_next(workptr, nxt);
+}
+
+static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ int ret;
+
+ req->close.put_file = NULL;
+ ret = __close_fd_get_file(req->close.fd, &req->close.put_file);
+ if (ret < 0)
+ return ret;
+
+ /* if the file has a flush method, be safe and punt to async */
+ if (req->close.put_file->f_op->flush && !io_wq_current_is_worker()) {
+ req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
+ goto eagain;
+ }
+
+ /*
+ * 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;
+ }
+
+eagain:
+ req->work.func = io_close_finish;
+ return -EAGAIN;
+}
+
static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
io_wq_assign_next(workptr, nxt);
}
-static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
- void *key)
+static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes)
{
- struct io_poll_iocb *poll = wait->private;
- struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
- struct io_ring_ctx *ctx = req->ctx;
- __poll_t mask = key_to_poll(key);
- unsigned long flags;
+ void *reqs[IO_IOPOLL_BATCH];
+ struct io_kiocb *req, *tmp;
+ int to_free = 0;
- /* for instances that support it check for an event match first: */
- if (mask && !(mask & poll->events))
- return 0;
+ spin_lock_irq(&ctx->completion_lock);
+ llist_for_each_entry_safe(req, tmp, nodes, llist_node) {
+ hash_del(&req->hash_node);
+ io_poll_complete(req, req->result, 0);
- list_del_init(&poll->wait.entry);
+ if (refcount_dec_and_test(&req->refs)) {
+ if (io_req_multi_free(req)) {
+ reqs[to_free++] = req;
+ if (to_free == ARRAY_SIZE(reqs))
+ io_free_req_many(ctx, reqs, &to_free);
+ } else {
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_free_req(req);
+ }
+ }
+ }
+ spin_unlock_irq(&ctx->completion_lock);
+
+ io_cqring_ev_posted(ctx);
+ io_free_req_many(ctx, reqs, &to_free);
+}
+
+static void io_poll_flush(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct llist_node *nodes;
+
+ nodes = llist_del_all(&req->ctx->poll_llist);
+ if (nodes)
+ __io_poll_flush(req->ctx, nodes);
+}
+
+static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct io_poll_iocb *poll = wait->private;
+ struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
+ struct io_ring_ctx *ctx = req->ctx;
+ __poll_t mask = key_to_poll(key);
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & poll->events))
+ return 0;
+
+ list_del_init(&poll->wait.entry);
/*
* Run completion inline if we can. We're using trylock here because
* If we have a link timeout we're going to need the completion_lock
* for finalizing the request, mark us as having grabbed that already.
*/
- if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
- hash_del(&req->hash_node);
- io_poll_complete(req, mask, 0);
- req->flags |= REQ_F_COMP_LOCKED;
- io_put_req(req);
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ if (mask) {
+ unsigned long flags;
- io_cqring_ev_posted(ctx);
- } else {
- io_queue_async_work(req);
+ if (llist_empty(&ctx->poll_llist) &&
+ spin_trylock_irqsave(&ctx->completion_lock, flags)) {
+ hash_del(&req->hash_node);
+ io_poll_complete(req, mask, 0);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req(req);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+ io_cqring_ev_posted(ctx);
+ req = NULL;
+ } else {
+ req->result = mask;
+ req->llist_node.next = NULL;
+ /* if the list wasn't empty, we're done */
+ if (!llist_add(&req->llist_node, &ctx->poll_llist))
+ req = NULL;
+ else
+ req->work.func = io_poll_flush;
+ }
}
+ if (req)
+ io_queue_async_work(req);
return 1;
}
return 0;
}
+static int io_files_update_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ if (sqe->flags || sqe->ioprio || sqe->rw_flags)
+ return -EINVAL;
+
+ req->files_update.offset = READ_ONCE(sqe->off);
+ req->files_update.nr_args = READ_ONCE(sqe->len);
+ if (!req->files_update.nr_args)
+ return -EINVAL;
+ req->files_update.arg = READ_ONCE(sqe->addr);
+ return 0;
+}
+
+static int io_files_update(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_uring_files_update up;
+ int ret;
+
+ if (force_nonblock) {
+ req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
+ return -EAGAIN;
+ }
+
+ up.offset = req->files_update.offset;
+ up.fds = req->files_update.arg;
+
+ mutex_lock(&ctx->uring_lock);
+ ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args);
+ mutex_unlock(&ctx->uring_lock);
+
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req(req);
+ return 0;
+}
+
static int io_req_defer_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
break;
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
+ case IORING_OP_READ:
ret = io_read_prep(req, sqe, true);
break;
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
+ case IORING_OP_WRITE:
ret = io_write_prep(req, sqe, true);
break;
case IORING_OP_POLL_ADD:
case IORING_OP_ACCEPT:
ret = io_accept_prep(req, sqe);
break;
+ case IORING_OP_FALLOCATE:
+ ret = io_fallocate_prep(req, sqe);
+ break;
+ case IORING_OP_OPENAT:
+ ret = io_openat_prep(req, sqe);
+ break;
+ case IORING_OP_CLOSE:
+ ret = io_close_prep(req, sqe);
+ break;
+ case IORING_OP_FILES_UPDATE:
+ ret = io_files_update_prep(req, sqe);
+ break;
+ case IORING_OP_STATX:
+ ret = io_statx_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
break;
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
+ case IORING_OP_READ:
if (sqe) {
ret = io_read_prep(req, sqe, force_nonblock);
if (ret < 0)
break;
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
+ case IORING_OP_WRITE:
if (sqe) {
ret = io_write_prep(req, sqe, force_nonblock);
if (ret < 0)
}
ret = io_async_cancel(req, nxt);
break;
+ case IORING_OP_FALLOCATE:
+ if (sqe) {
+ ret = io_fallocate_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_fallocate(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_OPENAT:
+ if (sqe) {
+ ret = io_openat_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_openat(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_CLOSE:
+ if (sqe) {
+ ret = io_close_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_close(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_FILES_UPDATE:
+ if (sqe) {
+ ret = io_files_update_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_files_update(req, force_nonblock);
+ break;
+ case IORING_OP_STATX:
+ if (sqe) {
+ ret = io_statx_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_statx(req, nxt, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
struct io_kiocb *nxt = NULL;
int ret = 0;
- if (work->flags & IO_WQ_WORK_CANCEL)
+ /* if NO_CANCEL is set, we must still run the work */
+ if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) ==
+ IO_WQ_WORK_CANCEL) {
ret = -ECANCELED;
+ }
if (!ret) {
req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
io_wq_assign_next(workptr, nxt);
}
-static bool io_req_op_valid(int op)
+static int io_req_needs_file(struct io_kiocb *req, int fd)
{
- return op >= IORING_OP_NOP && op < IORING_OP_LAST;
-}
-
-static int io_req_needs_file(struct io_kiocb *req)
-{
- switch (req->opcode) {
- case IORING_OP_NOP:
- case IORING_OP_POLL_REMOVE:
- case IORING_OP_TIMEOUT:
- case IORING_OP_TIMEOUT_REMOVE:
- case IORING_OP_ASYNC_CANCEL:
- case IORING_OP_LINK_TIMEOUT:
+ if (!io_op_defs[req->opcode].needs_file)
return 0;
- default:
- if (io_req_op_valid(req->opcode))
- return 1;
- return -EINVAL;
- }
+ if (fd == -1 && io_op_defs[req->opcode].fd_non_neg)
+ return 0;
+ return 1;
}
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
{
struct fixed_file_table *table;
- table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT];
- return table->files[index & IORING_FILE_TABLE_MASK];
+ table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT];
+ return table->files[index & IORING_FILE_TABLE_MASK];;
}
static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
{
struct io_ring_ctx *ctx = req->ctx;
unsigned flags;
- int fd, ret;
+ int fd;
flags = READ_ONCE(sqe->flags);
fd = READ_ONCE(sqe->fd);
if (flags & IOSQE_IO_DRAIN)
req->flags |= REQ_F_IO_DRAIN;
- ret = io_req_needs_file(req);
- if (ret <= 0)
- return ret;
+ if (!io_req_needs_file(req, fd))
+ return 0;
if (flags & IOSQE_FIXED_FILE) {
- if (unlikely(!ctx->file_table ||
+ if (unlikely(!ctx->file_data ||
(unsigned) fd >= ctx->nr_user_files))
return -EBADF;
fd = array_index_nospec(fd, ctx->nr_user_files);
if (!req->file)
return -EBADF;
req->flags |= REQ_F_FIXED_FILE;
+ percpu_ref_get(&ctx->file_data->refs);
} else {
if (req->needs_fixed_file)
return -EBADF;
int ret = -EBADF;
struct io_ring_ctx *ctx = req->ctx;
+ if (!req->ring_file)
+ return -EBADF;
+
rcu_read_lock();
spin_lock_irq(&ctx->inflight_lock);
/*
req_set_fail_links(req);
io_double_put_req(req);
}
- } else
+ } else if ((req->flags & REQ_F_FORCE_ASYNC) &&
+ !io_wq_current_is_worker()) {
+ /*
+ * Never try inline submit of IOSQE_ASYNC is set, go straight
+ * to async execution.
+ */
+ req->work.flags |= IO_WQ_WORK_CONCURRENT;
+ io_queue_async_work(req);
+ } else {
__io_queue_sqe(req, sqe);
+ }
}
static inline void io_queue_link_head(struct io_kiocb *req)
}
#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \
- IOSQE_IO_HARDLINK)
+ IOSQE_IO_HARDLINK | IOSQE_ASYNC)
static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct io_submit_state *state, struct io_kiocb **link)
{
struct io_ring_ctx *ctx = req->ctx;
+ unsigned int sqe_flags;
int ret;
+ sqe_flags = READ_ONCE(sqe->flags);
+
/* enforce forwards compatibility on users */
- if (unlikely(sqe->flags & ~SQE_VALID_FLAGS)) {
+ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
ret = -EINVAL;
goto err_req;
}
+ if (sqe_flags & IOSQE_ASYNC)
+ req->flags |= REQ_F_FORCE_ASYNC;
ret = io_req_set_file(state, req, sqe);
if (unlikely(ret)) {
* conditions are true (normal request), then just queue it.
*/
if (*link) {
- struct io_kiocb *prev = *link;
+ struct io_kiocb *head = *link;
- if (sqe->flags & IOSQE_IO_DRAIN)
- (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
+ if (sqe_flags & IOSQE_IO_DRAIN)
+ head->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
- if (sqe->flags & IOSQE_IO_HARDLINK)
+ if (sqe_flags & IOSQE_IO_HARDLINK)
req->flags |= REQ_F_HARDLINK;
if (io_alloc_async_ctx(req)) {
ret = io_req_defer_prep(req, sqe);
if (ret) {
/* fail even hard links since we don't submit */
- prev->flags |= REQ_F_FAIL_LINK;
+ head->flags |= REQ_F_FAIL_LINK;
goto err_req;
}
- trace_io_uring_link(ctx, req, prev);
- list_add_tail(&req->link_list, &prev->link_list);
- } else if (sqe->flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
+ trace_io_uring_link(ctx, req, head);
+ list_add_tail(&req->link_list, &head->link_list);
+
+ /* last request of a link, enqueue the link */
+ if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) {
+ io_queue_link_head(head);
+ *link = NULL;
+ }
+ } else if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
req->flags |= REQ_F_LINK;
- if (sqe->flags & IOSQE_IO_HARDLINK)
+ if (sqe_flags & IOSQE_IO_HARDLINK)
req->flags |= REQ_F_HARDLINK;
INIT_LIST_HEAD(&req->link_list);
bool mm_fault = false;
/* if we have a backlog and couldn't flush it all, return BUSY */
- if (!list_empty(&ctx->cq_overflow_list) &&
- !io_cqring_overflow_flush(ctx, false))
- return -EBUSY;
+ if (test_bit(0, &ctx->sq_check_overflow)) {
+ if (!list_empty(&ctx->cq_overflow_list) &&
+ !io_cqring_overflow_flush(ctx, false))
+ return -EBUSY;
+ }
if (nr > IO_PLUG_THRESHOLD) {
io_submit_state_start(&state, nr);
for (i = 0; i < nr; i++) {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
- unsigned int sqe_flags;
req = io_get_req(ctx, statep);
if (unlikely(!req)) {
break;
}
- if (io_req_needs_user(req) && !*mm) {
+ /* will complete beyond this point, count as submitted */
+ submitted++;
+
+ if (unlikely(req->opcode >= IORING_OP_LAST)) {
+ io_cqring_add_event(req, -EINVAL);
+ 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);
}
}
- submitted++;
- sqe_flags = sqe->flags;
-
req->ring_file = ring_file;
req->ring_fd = ring_fd;
req->has_user = *mm != NULL;
trace_io_uring_submit_sqe(ctx, req->user_data, true, async);
if (!io_submit_sqe(req, sqe, statep, &link))
break;
- /*
- * If previous wasn't linked and we have a linked command,
- * that's the end of the chain. Submit the previous link.
- */
- if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) && link) {
- io_queue_link_head(link);
- link = NULL;
- }
}
if (link)
#endif
}
+static void io_file_ref_kill(struct percpu_ref *ref)
+{
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+ complete(&data->done);
+}
+
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
+ struct fixed_file_data *data = ctx->file_data;
unsigned nr_tables, i;
- if (!ctx->file_table)
+ if (!data)
return -ENXIO;
+ /* protect against inflight atomic switch, which drops the ref */
+ flush_work(&data->ref_work);
+ percpu_ref_get(&data->refs);
+ percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill);
+ wait_for_completion(&data->done);
+ percpu_ref_put(&data->refs);
+ percpu_ref_exit(&data->refs);
+
__io_sqe_files_unregister(ctx);
nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
for (i = 0; i < nr_tables; i++)
- kfree(ctx->file_table[i].files);
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ kfree(data->table[i].files);
+ kfree(data->table);
+ kfree(data);
+ ctx->file_data = NULL;
ctx->nr_user_files = 0;
return 0;
}
}
#if defined(CONFIG_UNIX)
-static void io_destruct_skb(struct sk_buff *skb)
-{
- struct io_ring_ctx *ctx = skb->sk->sk_user_data;
-
- if (ctx->io_wq)
- io_wq_flush(ctx->io_wq);
-
- unix_destruct_scm(skb);
-}
-
/*
* Ensure the UNIX gc is aware of our file set, so we are certain that
* the io_uring can be safely unregistered on process exit, even if we have
fpl->max = SCM_MAX_FD;
fpl->count = nr_files;
UNIXCB(skb).fp = fpl;
- skb->destructor = io_destruct_skb;
+ skb->destructor = unix_destruct_scm;
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
skb_queue_head(&sk->sk_receive_queue, skb);
int i;
for (i = 0; i < nr_tables; i++) {
- struct fixed_file_table *table = &ctx->file_table[i];
+ struct fixed_file_table *table = &ctx->file_data->table[i];
unsigned this_files;
this_files = min(nr_files, IORING_MAX_FILES_TABLE);
return 0;
for (i = 0; i < nr_tables; i++) {
- struct fixed_file_table *table = &ctx->file_table[i];
+ struct fixed_file_table *table = &ctx->file_data->table[i];
kfree(table->files);
}
return 1;
}
+static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file)
+{
+#if defined(CONFIG_UNIX)
+ struct sock *sock = ctx->ring_sock->sk;
+ struct sk_buff_head list, *head = &sock->sk_receive_queue;
+ struct sk_buff *skb;
+ int i;
+
+ __skb_queue_head_init(&list);
+
+ /*
+ * Find the skb that holds this file in its SCM_RIGHTS. When found,
+ * remove this entry and rearrange the file array.
+ */
+ skb = skb_dequeue(head);
+ while (skb) {
+ struct scm_fp_list *fp;
+
+ fp = UNIXCB(skb).fp;
+ for (i = 0; i < fp->count; i++) {
+ int left;
+
+ if (fp->fp[i] != file)
+ continue;
+
+ unix_notinflight(fp->user, fp->fp[i]);
+ left = fp->count - 1 - i;
+ if (left) {
+ memmove(&fp->fp[i], &fp->fp[i + 1],
+ left * sizeof(struct file *));
+ }
+ fp->count--;
+ if (!fp->count) {
+ kfree_skb(skb);
+ skb = NULL;
+ } else {
+ __skb_queue_tail(&list, skb);
+ }
+ fput(file);
+ file = NULL;
+ break;
+ }
+
+ if (!file)
+ break;
+
+ __skb_queue_tail(&list, skb);
+
+ skb = skb_dequeue(head);
+ }
+
+ if (skb_peek(&list)) {
+ spin_lock_irq(&head->lock);
+ while ((skb = __skb_dequeue(&list)) != NULL)
+ __skb_queue_tail(head, skb);
+ spin_unlock_irq(&head->lock);
+ }
+#else
+ fput(file);
+#endif
+}
+
+struct io_file_put {
+ struct llist_node llist;
+ struct file *file;
+ struct completion *done;
+};
+
+static void io_ring_file_ref_switch(struct work_struct *work)
+{
+ struct io_file_put *pfile, *tmp;
+ struct fixed_file_data *data;
+ struct llist_node *node;
+
+ data = container_of(work, struct fixed_file_data, ref_work);
+
+ while ((node = llist_del_all(&data->put_llist)) != NULL) {
+ llist_for_each_entry_safe(pfile, tmp, node, llist) {
+ io_ring_file_put(data->ctx, pfile->file);
+ if (pfile->done)
+ complete(pfile->done);
+ else
+ kfree(pfile);
+ }
+ }
+
+ percpu_ref_get(&data->refs);
+ percpu_ref_switch_to_percpu(&data->refs);
+}
+
+static void io_file_data_ref_zero(struct percpu_ref *ref)
+{
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+
+ /* we can't safely switch from inside this context, punt to wq */
+ queue_work(system_wq, &data->ref_work);
+}
+
static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args)
{
__s32 __user *fds = (__s32 __user *) arg;
unsigned nr_tables;
+ struct file *file;
int fd, ret = 0;
unsigned i;
- if (ctx->file_table)
+ if (ctx->file_data)
return -EBUSY;
if (!nr_args)
return -EINVAL;
if (nr_args > IORING_MAX_FIXED_FILES)
return -EMFILE;
+ ctx->file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL);
+ if (!ctx->file_data)
+ return -ENOMEM;
+ ctx->file_data->ctx = ctx;
+ init_completion(&ctx->file_data->done);
+
nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
- ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table),
+ ctx->file_data->table = kcalloc(nr_tables,
+ sizeof(struct fixed_file_table),
GFP_KERNEL);
- if (!ctx->file_table)
+ if (!ctx->file_data->table) {
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
return -ENOMEM;
+ }
+
+ if (percpu_ref_init(&ctx->file_data->refs, io_file_data_ref_zero,
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
+ return -ENOMEM;
+ }
+ ctx->file_data->put_llist.first = NULL;
+ INIT_WORK(&ctx->file_data->ref_work, io_ring_file_ref_switch);
if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) {
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ percpu_ref_exit(&ctx->file_data->refs);
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
return -ENOMEM;
}
continue;
}
- table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
index = i & IORING_FILE_TABLE_MASK;
- table->files[index] = fget(fd);
+ file = fget(fd);
ret = -EBADF;
- if (!table->files[index])
+ if (!file)
break;
+
/*
* Don't allow io_uring instances to be registered. If UNIX
* isn't enabled, then this causes a reference cycle and this
* handle it just fine, but there's still no point in allowing
* a ring fd as it doesn't support regular read/write anyway.
*/
- if (table->files[index]->f_op == &io_uring_fops) {
- fput(table->files[index]);
+ if (file->f_op == &io_uring_fops) {
+ fput(file);
break;
}
ret = 0;
+ table->files[index] = file;
}
if (ret) {
for (i = 0; i < ctx->nr_user_files; i++) {
- struct file *file;
-
file = io_file_from_index(ctx, i);
if (file)
fput(file);
}
for (i = 0; i < nr_tables; i++)
- kfree(ctx->file_table[i].files);
+ kfree(ctx->file_data->table[i].files);
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
ctx->nr_user_files = 0;
return ret;
}
return ret;
}
-static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index)
-{
-#if defined(CONFIG_UNIX)
- struct file *file = io_file_from_index(ctx, index);
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff_head list, *head = &sock->sk_receive_queue;
- struct sk_buff *skb;
- int i;
-
- __skb_queue_head_init(&list);
-
- /*
- * Find the skb that holds this file in its SCM_RIGHTS. When found,
- * remove this entry and rearrange the file array.
- */
- skb = skb_dequeue(head);
- while (skb) {
- struct scm_fp_list *fp;
-
- fp = UNIXCB(skb).fp;
- for (i = 0; i < fp->count; i++) {
- int left;
-
- if (fp->fp[i] != file)
- continue;
-
- unix_notinflight(fp->user, fp->fp[i]);
- left = fp->count - 1 - i;
- if (left) {
- memmove(&fp->fp[i], &fp->fp[i + 1],
- left * sizeof(struct file *));
- }
- fp->count--;
- if (!fp->count) {
- kfree_skb(skb);
- skb = NULL;
- } else {
- __skb_queue_tail(&list, skb);
- }
- fput(file);
- file = NULL;
- break;
- }
-
- if (!file)
- break;
-
- __skb_queue_tail(&list, skb);
-
- skb = skb_dequeue(head);
- }
-
- if (skb_peek(&list)) {
- spin_lock_irq(&head->lock);
- while ((skb = __skb_dequeue(&list)) != NULL)
- __skb_queue_tail(head, skb);
- spin_unlock_irq(&head->lock);
- }
-#else
- fput(io_file_from_index(ctx, index));
-#endif
-}
-
static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
int index)
{
#endif
}
-static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
+static void io_atomic_switch(struct percpu_ref *ref)
{
- struct io_uring_files_update up;
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+ clear_bit(FFD_F_ATOMIC, &data->state);
+}
+
+static bool io_queue_file_removal(struct fixed_file_data *data,
+ struct file *file)
+{
+ struct io_file_put *pfile, pfile_stack;
+ DECLARE_COMPLETION_ONSTACK(done);
+
+ /*
+ * If we fail allocating the struct we need for doing async reomval
+ * of this file, just punt to sync and wait for it.
+ */
+ pfile = kzalloc(sizeof(*pfile), GFP_KERNEL);
+ if (!pfile) {
+ pfile = &pfile_stack;
+ pfile->done = &done;
+ }
+
+ pfile->file = file;
+ llist_add(&pfile->llist, &data->put_llist);
+
+ if (pfile == &pfile_stack) {
+ if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+ percpu_ref_put(&data->refs);
+ percpu_ref_switch_to_atomic(&data->refs,
+ io_atomic_switch);
+ }
+ wait_for_completion(&done);
+ flush_work(&data->ref_work);
+ return false;
+ }
+
+ return true;
+}
+
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+ struct io_uring_files_update *up,
+ unsigned nr_args)
+{
+ struct fixed_file_data *data = ctx->file_data;
+ bool ref_switch = false;
+ struct file *file;
__s32 __user *fds;
int fd, i, err;
__u32 done;
- if (!ctx->file_table)
- return -ENXIO;
- if (!nr_args)
- return -EINVAL;
- if (copy_from_user(&up, arg, sizeof(up)))
- return -EFAULT;
- if (check_add_overflow(up.offset, nr_args, &done))
+ if (check_add_overflow(up->offset, nr_args, &done))
return -EOVERFLOW;
if (done > ctx->nr_user_files)
return -EINVAL;
done = 0;
- fds = (__s32 __user *) up.fds;
+ fds = u64_to_user_ptr(up->fds);
while (nr_args) {
struct fixed_file_table *table;
unsigned index;
err = -EFAULT;
break;
}
- i = array_index_nospec(up.offset, ctx->nr_user_files);
- table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ i = array_index_nospec(up->offset, ctx->nr_user_files);
+ table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
index = i & IORING_FILE_TABLE_MASK;
if (table->files[index]) {
- io_sqe_file_unregister(ctx, i);
+ file = io_file_from_index(ctx, index);
table->files[index] = NULL;
+ if (io_queue_file_removal(data, file))
+ ref_switch = true;
}
if (fd != -1) {
- struct file *file;
-
file = fget(fd);
if (!file) {
err = -EBADF;
}
nr_args--;
done++;
- up.offset++;
+ up->offset++;
+ }
+
+ if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+ percpu_ref_put(&data->refs);
+ percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
}
return done ? done : err;
}
+static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ struct io_uring_files_update up;
+
+ if (!ctx->file_data)
+ return -ENXIO;
+ if (!nr_args)
+ return -EINVAL;
+ if (copy_from_user(&up, arg, sizeof(up)))
+ return -EFAULT;
+ if (up.resv)
+ return -EINVAL;
+
+ return __io_sqe_files_update(ctx, &up, nr_args);
+}
static void io_put_work(struct io_wq_work *work)
{
#if defined(CONFIG_UNIX)
ctx->ring_sock->file = file;
- ctx->ring_sock->sk->sk_user_data = ctx;
#endif
fd_install(ret, file);
return ret;
if (percpu_ref_is_dying(&ctx->refs))
return -ENXIO;
- percpu_ref_kill(&ctx->refs);
+ if (opcode != IORING_UNREGISTER_FILES &&
+ opcode != IORING_REGISTER_FILES_UPDATE) {
+ percpu_ref_kill(&ctx->refs);
- /*
- * Drop uring mutex before waiting for references to exit. If another
- * thread is currently inside io_uring_enter() it might need to grab
- * the uring_lock to make progress. If we hold it here across the drain
- * wait, then we can deadlock. It's safe to drop the mutex here, since
- * no new references will come in after we've killed the percpu ref.
- */
- mutex_unlock(&ctx->uring_lock);
- wait_for_completion(&ctx->completions[0]);
- mutex_lock(&ctx->uring_lock);
+ /*
+ * Drop uring mutex before waiting for references to exit. If
+ * another thread is currently inside io_uring_enter() it might
+ * need to grab the uring_lock to make progress. If we hold it
+ * here across the drain wait, then we can deadlock. It's safe
+ * to drop the mutex here, since no new references will come in
+ * after we've killed the percpu ref.
+ */
+ mutex_unlock(&ctx->uring_lock);
+ wait_for_completion(&ctx->completions[0]);
+ mutex_lock(&ctx->uring_lock);
+ }
switch (opcode) {
case IORING_REGISTER_BUFFERS:
break;
}
- /* bring the ctx back to life */
- reinit_completion(&ctx->completions[0]);
- percpu_ref_reinit(&ctx->refs);
+
+ if (opcode != IORING_UNREGISTER_FILES &&
+ opcode != IORING_REGISTER_FILES_UPDATE) {
+ /* bring the ctx back to life */
+ reinit_completion(&ctx->completions[0]);
+ percpu_ref_reinit(&ctx->refs);
+ }
return ret;
}
static int __init io_uring_init(void)
{
+ BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
return 0;
};
OSDN Git Service
