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
  ...

Author: torvalds

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 @@ static void io_worker_handle_work(struct io_worker *worker)
 			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)
@@ -691,18 +699,26 @@ 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()) {
 		for_each_node(node) {
 			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;
@@ -1067,20 +1127,22 @@ 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) {
 			wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
 					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);

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 *);