summaryrefslogtreecommitdiffstats
path: root/io_uring
diff options
context:
space:
mode:
Diffstat (limited to 'io_uring')
-rw-r--r--io_uring/filetable.h16
-rw-r--r--io_uring/io-wq.c2
-rw-r--r--io_uring/io_uring.c35
-rw-r--r--io_uring/io_uring.h13
-rw-r--r--io_uring/msg_ring.c3
-rw-r--r--io_uring/net.c4
-rw-r--r--io_uring/rsrc.c7
-rw-r--r--io_uring/rsrc.h4
-rw-r--r--io_uring/rw.c2
9 files changed, 35 insertions, 51 deletions
diff --git a/io_uring/filetable.h b/io_uring/filetable.h
index ff3a712e11bf..351111ff8882 100644
--- a/io_uring/filetable.h
+++ b/io_uring/filetable.h
@@ -5,22 +5,9 @@
#include <linux/file.h>
#include <linux/io_uring_types.h>
-/*
- * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
- * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
- * can't safely always dereference the file when the task has exited and ring
- * cleanup is done. If a file is tracked and part of SCM, then unix gc on
- * process exit may reap it before __io_sqe_files_unregister() is run.
- */
#define FFS_NOWAIT 0x1UL
#define FFS_ISREG 0x2UL
-#if defined(CONFIG_64BIT)
-#define FFS_SCM 0x4UL
-#else
-#define IO_URING_SCM_ALL
-#define FFS_SCM 0x0UL
-#endif
-#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)
+#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG)
bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files);
void io_free_file_tables(struct io_file_table *table);
@@ -38,6 +25,7 @@ unsigned int io_file_get_flags(struct file *file);
static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
{
+ WARN_ON_ONCE(!test_bit(bit, table->bitmap));
__clear_bit(bit, table->bitmap);
table->alloc_hint = bit;
}
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index c6536d4b2da0..6f1d0e5df23a 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1164,10 +1164,10 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
if (!wqe)
goto err;
+ wq->wqes[node] = wqe;
if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL))
goto err;
cpumask_copy(wqe->cpu_mask, cpumask_of_node(node));
- wq->wqes[node] = wqe;
wqe->node = alloc_node;
wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index de08d9902b30..ac8c488e3077 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1173,7 +1173,7 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
}
}
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked)
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked)
{
struct llist_node *node;
struct llist_node fake;
@@ -1192,7 +1192,7 @@ again:
struct io_kiocb *req = container_of(node, struct io_kiocb,
io_task_work.node);
prefetch(container_of(next, struct io_kiocb, io_task_work.node));
- req->io_task_work.func(req, &locked);
+ req->io_task_work.func(req, locked);
ret++;
node = next;
}
@@ -1208,7 +1208,7 @@ again:
goto again;
}
- if (locked)
+ if (*locked)
io_submit_flush_completions(ctx);
trace_io_uring_local_work_run(ctx, ret, loops);
return ret;
@@ -1225,7 +1225,7 @@ int io_run_local_work(struct io_ring_ctx *ctx)
__set_current_state(TASK_RUNNING);
locked = mutex_trylock(&ctx->uring_lock);
- ret = __io_run_local_work(ctx, locked);
+ ret = __io_run_local_work(ctx, &locked);
if (locked)
mutex_unlock(&ctx->uring_lock);
@@ -1446,8 +1446,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
io_task_work_pending(ctx)) {
u32 tail = ctx->cached_cq_tail;
- if (!llist_empty(&ctx->work_llist))
- __io_run_local_work(ctx, true);
+ (void) io_run_local_work_locked(ctx);
if (task_work_pending(current) ||
wq_list_empty(&ctx->iopoll_list)) {
@@ -1587,8 +1586,6 @@ unsigned int io_file_get_flags(struct file *file)
res |= FFS_ISREG;
if (__io_file_supports_nowait(file, mode))
res |= FFS_NOWAIT;
- if (io_file_need_scm(file))
- res |= FFS_SCM;
return res;
}
@@ -1860,7 +1857,6 @@ inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
/* mask in overlapping REQ_F and FFS bits */
req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
io_req_set_rsrc_node(req, ctx, 0);
- WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap));
out:
io_ring_submit_unlock(ctx, issue_flags);
return file;
@@ -2563,18 +2559,14 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx)
static void io_req_caches_free(struct io_ring_ctx *ctx)
{
- struct io_submit_state *state = &ctx->submit_state;
int nr = 0;
mutex_lock(&ctx->uring_lock);
- io_flush_cached_locked_reqs(ctx, state);
+ io_flush_cached_locked_reqs(ctx, &ctx->submit_state);
while (!io_req_cache_empty(ctx)) {
- struct io_wq_work_node *node;
- struct io_kiocb *req;
+ struct io_kiocb *req = io_alloc_req(ctx);
- node = wq_stack_extract(&state->free_list);
- req = container_of(node, struct io_kiocb, comp_list);
kmem_cache_free(req_cachep, req);
nr++;
}
@@ -2811,15 +2803,12 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
io_poll_remove_all(ctx, NULL, true);
mutex_unlock(&ctx->uring_lock);
- /* failed during ring init, it couldn't have issued any requests */
- if (ctx->rings) {
+ /*
+ * If we failed setting up the ctx, we might not have any rings
+ * and therefore did not submit any requests
+ */
+ if (ctx->rings)
io_kill_timeouts(ctx, NULL, true);
- /* if we failed setting up the ctx, we might not have any rings */
- io_iopoll_try_reap_events(ctx);
- /* drop cached put refs after potentially doing completions */
- if (current->io_uring)
- io_uring_drop_tctx_refs(current);
- }
INIT_WORK(&ctx->exit_work, io_ring_exit_work);
/*
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index ef77d2aa3172..e99a79f2df9b 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -27,7 +27,7 @@ enum {
struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow);
bool io_req_cqe_overflow(struct io_kiocb *req);
int io_run_task_work_sig(struct io_ring_ctx *ctx);
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked);
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked);
int io_run_local_work(struct io_ring_ctx *ctx);
void io_req_complete_failed(struct io_kiocb *req, s32 res);
void __io_req_complete(struct io_kiocb *req, unsigned issue_flags);
@@ -277,9 +277,18 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx)
static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
{
+ bool locked;
+ int ret;
+
if (llist_empty(&ctx->work_llist))
return 0;
- return __io_run_local_work(ctx, true);
+
+ locked = true;
+ ret = __io_run_local_work(ctx, &locked);
+ /* shouldn't happen! */
+ if (WARN_ON_ONCE(!locked))
+ mutex_lock(&ctx->uring_lock);
+ return ret;
}
static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 4a7e5d030c78..90d2fc6fd80e 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -95,6 +95,9 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
msg->src_fd = array_index_nospec(msg->src_fd, ctx->nr_user_files);
file_ptr = io_fixed_file_slot(&ctx->file_table, msg->src_fd)->file_ptr;
+ if (!file_ptr)
+ goto out_unlock;
+
src_file = (struct file *) (file_ptr & FFS_MASK);
get_file(src_file);
diff --git a/io_uring/net.c b/io_uring/net.c
index 8c7226b5bf41..15dea91625e2 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1056,6 +1056,8 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
+ if (!test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+ return -EOPNOTSUPP;
msg.msg_name = NULL;
msg.msg_control = NULL;
@@ -1151,6 +1153,8 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
sock = sock_from_file(req->file);
if (unlikely(!sock))
return -ENOTSOCK;
+ if (!test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+ return -EOPNOTSUPP;
if (req_has_async_data(req)) {
kmsg = req->async_data;
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 012fdb04ec23..55d4ab96fb92 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -757,20 +757,17 @@ int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
-#if !defined(IO_URING_SCM_ALL)
int i;
for (i = 0; i < ctx->nr_user_files; i++) {
struct file *file = io_file_from_index(&ctx->file_table, i);
- if (!file)
- continue;
- if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM)
+ /* skip scm accounted files, they'll be freed by ->ring_sock */
+ if (!file || io_file_need_scm(file))
continue;
io_file_bitmap_clear(&ctx->file_table, i);
fput(file);
}
-#endif
#if defined(CONFIG_UNIX)
if (ctx->ring_sock) {
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 9bce15665444..81445a477622 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -82,11 +82,7 @@ int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file);
#if defined(CONFIG_UNIX)
static inline bool io_file_need_scm(struct file *filp)
{
-#if defined(IO_URING_SCM_ALL)
- return true;
-#else
return !!unix_get_socket(filp);
-#endif
}
#else
static inline bool io_file_need_scm(struct file *filp)
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 100de2626e47..bb47cc4da713 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -242,8 +242,6 @@ static void io_req_io_end(struct io_kiocb *req)
{
struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
- WARN_ON(!in_task());
-
if (rw->kiocb.ki_flags & IOCB_WRITE) {
kiocb_end_write(req);
fsnotify_modify(req->file);