Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 411 insertions, 0 deletions

diff --git a/io_uring/napi.c b/io_uring/napi.c
new file mode 100644
index 000000000..bfc771445
--- /dev/null
+++ b/io_uring/napi.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "io_uring.h"
+#include "napi.h"
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+
+/* Timeout for cleanout of stale entries. */
+#define NAPI_TIMEOUT		(60 * SEC_CONVERSION)
+
+struct io_napi_entry {
+	unsigned int		napi_id;
+	struct list_head	list;
+
+	unsigned long		timeout;
+	struct hlist_node	node;
+
+	struct rcu_head		rcu;
+};
+
+static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
+					       unsigned int napi_id)
+{
+	struct io_napi_entry *e;
+
+	hlist_for_each_entry_rcu(e, hash_list, node) {
+		if (e->napi_id != napi_id)
+			continue;
+		return e;
+	}
+
+	return NULL;
+}
+
+static inline ktime_t net_to_ktime(unsigned long t)
+{
+	/* napi approximating usecs, reverse busy_loop_current_time */
+	return ns_to_ktime(t << 10);
+}
+
+int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id,
+		     unsigned int mode)
+{
+	struct hlist_head *hash_list;
+	struct io_napi_entry *e;
+
+	/* Non-NAPI IDs can be rejected. */
+	if (!napi_id_valid(napi_id))
+		return -EINVAL;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+
+	scoped_guard(rcu) {
+		e = io_napi_hash_find(hash_list, napi_id);
+		if (e) {
+			WRITE_ONCE(e->timeout, jiffies + NAPI_TIMEOUT);
+			return -EEXIST;
+		}
+	}
+
+	e = kmalloc(sizeof(*e), GFP_NOWAIT);
+	if (!e)
+		return -ENOMEM;
+
+	e->napi_id = napi_id;
+	e->timeout = jiffies + NAPI_TIMEOUT;
+
+	/*
+	 * guard(spinlock) is not used to manually unlock it before calling
+	 * kfree()
+	 */
+	spin_lock(&ctx->napi_lock);
+	if (unlikely(READ_ONCE(ctx->napi_track_mode) != mode)) {
+		spin_unlock(&ctx->napi_lock);
+		kfree(e);
+		return -EINVAL;
+	}
+	if (unlikely(io_napi_hash_find(hash_list, napi_id))) {
+		spin_unlock(&ctx->napi_lock);
+		kfree(e);
+		return -EEXIST;
+	}
+
+	hlist_add_tail_rcu(&e->node, hash_list);
+	list_add_tail_rcu(&e->list, &ctx->napi_list);
+	spin_unlock(&ctx->napi_lock);
+	return 0;
+}
+
+static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id)
+{
+	struct hlist_head *hash_list;
+	struct io_napi_entry *e;
+
+	/* Non-NAPI IDs can be rejected. */
+	if (!napi_id_valid(napi_id))
+		return -EINVAL;
+
+	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
+	guard(spinlock)(&ctx->napi_lock);
+	e = io_napi_hash_find(hash_list, napi_id);
+	if (!e)
+		return -ENOENT;
+
+	list_del_rcu(&e->list);
+	hash_del_rcu(&e->node);
+	kfree_rcu(e, rcu);
+	return 0;
+}
+
+static void __io_napi_remove_stale(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+
+	guard(spinlock)(&ctx->napi_lock);
+	/*
+	 * list_for_each_entry_safe() is not required as long as:
+	 * 1. list_del_rcu() does not reset the deleted node next pointer
+	 * 2. kfree_rcu() delays the memory freeing until the next quiescent
+	 *    state
+	 */
+	list_for_each_entry(e, &ctx->napi_list, list) {
+		if (time_after(jiffies, READ_ONCE(e->timeout))) {
+			list_del_rcu(&e->list);
+			hash_del_rcu(&e->node);
+			kfree_rcu(e, rcu);
+		}
+	}
+}
+
+static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
+{
+	if (is_stale)
+		__io_napi_remove_stale(ctx);
+}
+
+static inline bool io_napi_busy_loop_timeout(ktime_t start_time,
+					     ktime_t bp)
+{
+	if (bp) {
+		ktime_t end_time = ktime_add(start_time, bp);
+		ktime_t now = net_to_ktime(busy_loop_current_time());
+
+		return ktime_after(now, end_time);
+	}
+
+	return true;
+}
+
+static bool io_napi_busy_loop_should_end(void *data,
+					 unsigned long start_time)
+{
+	struct io_wait_queue *iowq = data;
+
+	if (signal_pending(current))
+		return true;
+	if (io_should_wake(iowq) || io_has_work(iowq->ctx))
+		return true;
+	if (io_napi_busy_loop_timeout(net_to_ktime(start_time),
+				      iowq->napi_busy_poll_dt))
+		return true;
+
+	return false;
+}
+
+/*
+ * never report stale entries
+ */
+static bool static_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+					 bool (*loop_end)(void *, unsigned long),
+					 void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list)
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+	return false;
+}
+
+static bool
+dynamic_tracking_do_busy_loop(struct io_ring_ctx *ctx,
+			      bool (*loop_end)(void *, unsigned long),
+			      void *loop_end_arg)
+{
+	struct io_napi_entry *e;
+	bool is_stale = false;
+
+	list_for_each_entry_rcu(e, &ctx->napi_list, list) {
+		napi_busy_loop_rcu(e->napi_id, loop_end, loop_end_arg,
+				   ctx->napi_prefer_busy_poll, BUSY_POLL_BUDGET);
+
+		if (time_after(jiffies, READ_ONCE(e->timeout)))
+			is_stale = true;
+	}
+
+	return is_stale;
+}
+
+static inline bool
+__io_napi_do_busy_loop(struct io_ring_ctx *ctx,
+		       bool (*loop_end)(void *, unsigned long),
+		       void *loop_end_arg)
+{
+	switch (READ_ONCE(ctx->napi_track_mode)) {
+	case IO_URING_NAPI_TRACKING_STATIC:
+		return static_tracking_do_busy_loop(ctx, loop_end, loop_end_arg);
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+		return dynamic_tracking_do_busy_loop(ctx, loop_end, loop_end_arg);
+	default:
+		return false;
+	}
+}
+
+static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
+				       struct io_wait_queue *iowq)
+{
+	unsigned long start_time = busy_loop_current_time();
+	bool (*loop_end)(void *, unsigned long) = NULL;
+	void *loop_end_arg = NULL;
+	bool is_stale = false;
+
+	/* Singular lists use a different napi loop end check function and are
+	 * only executed once.
+	 */
+	if (list_is_singular(&ctx->napi_list)) {
+		loop_end = io_napi_busy_loop_should_end;
+		loop_end_arg = iowq;
+	}
+
+	scoped_guard(rcu) {
+		do {
+			is_stale = __io_napi_do_busy_loop(ctx, loop_end,
+							  loop_end_arg);
+		} while (!io_napi_busy_loop_should_end(iowq, start_time) &&
+			 !loop_end_arg);
+	}
+
+	io_napi_remove_stale(ctx, is_stale);
+}
+
+/*
+ * io_napi_init() - Init napi settings
+ * @ctx: pointer to io-uring context structure
+ *
+ * Init napi settings in the io-uring context.
+ */
+void io_napi_init(struct io_ring_ctx *ctx)
+{
+	u64 sys_dt = READ_ONCE(sysctl_net_busy_poll) * NSEC_PER_USEC;
+
+	INIT_LIST_HEAD(&ctx->napi_list);
+	spin_lock_init(&ctx->napi_lock);
+	ctx->napi_prefer_busy_poll = false;
+	ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt);
+	ctx->napi_track_mode = IO_URING_NAPI_TRACKING_INACTIVE;
+}
+
+/*
+ * io_napi_free() - Deallocate napi
+ * @ctx: pointer to io-uring context structure
+ *
+ * Free the napi list and the hash table in the io-uring context.
+ */
+void io_napi_free(struct io_ring_ctx *ctx)
+{
+	struct io_napi_entry *e;
+
+	guard(spinlock)(&ctx->napi_lock);
+	list_for_each_entry(e, &ctx->napi_list, list) {
+		hash_del_rcu(&e->node);
+		kfree_rcu(e, rcu);
+	}
+	INIT_LIST_HEAD_RCU(&ctx->napi_list);
+}
+
+static int io_napi_register_napi(struct io_ring_ctx *ctx,
+				 struct io_uring_napi *napi)
+{
+	switch (napi->op_param) {
+	case IO_URING_NAPI_TRACKING_DYNAMIC:
+	case IO_URING_NAPI_TRACKING_STATIC:
+		break;
+	default:
+		return -EINVAL;
+	}
+	WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE);
+	io_napi_free(ctx);
+	/* cap NAPI at 10 msec of spin time */
+	napi->busy_poll_to = min(10000, napi->busy_poll_to);
+	WRITE_ONCE(ctx->napi_busy_poll_dt, napi->busy_poll_to * NSEC_PER_USEC);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi->prefer_busy_poll);
+	WRITE_ONCE(ctx->napi_track_mode, napi->op_param);
+	return 0;
+}
+
+/*
+ * io_napi_register() - Register napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Register napi in the io-uring context.
+ */
+int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ktime_to_us(ctx->napi_busy_poll_dt),
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll,
+		.op_param	  = ctx->napi_track_mode
+	};
+	struct io_uring_napi napi;
+
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		return -EINVAL;
+	if (copy_from_user(&napi, arg, sizeof(napi)))
+		return -EFAULT;
+	if (napi.pad[0] || napi.pad[1] || napi.resv)
+		return -EINVAL;
+
+	if (copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	switch (napi.opcode) {
+	case IO_URING_NAPI_REGISTER_OP:
+		return io_napi_register_napi(ctx, &napi);
+	case IO_URING_NAPI_STATIC_ADD_ID:
+		if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC)
+			return -EINVAL;
+		return __io_napi_add_id(ctx, napi.op_param,
+					IO_URING_NAPI_TRACKING_STATIC);
+	case IO_URING_NAPI_STATIC_DEL_ID:
+		if (curr.op_param != IO_URING_NAPI_TRACKING_STATIC)
+			return -EINVAL;
+		return __io_napi_del_id(ctx, napi.op_param);
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * io_napi_unregister() - Unregister napi with io-uring
+ * @ctx: pointer to io-uring context structure
+ * @arg: pointer to io_uring_napi structure
+ *
+ * Unregister napi. If arg has been specified copy the busy poll timeout and
+ * prefer busy poll setting to the passed in structure.
+ */
+int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+{
+	const struct io_uring_napi curr = {
+		.busy_poll_to 	  = ktime_to_us(ctx->napi_busy_poll_dt),
+		.prefer_busy_poll = ctx->napi_prefer_busy_poll
+	};
+
+	if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+		return -EFAULT;
+
+	WRITE_ONCE(ctx->napi_track_mode, IO_URING_NAPI_TRACKING_INACTIVE);
+	WRITE_ONCE(ctx->napi_busy_poll_dt, 0);
+	WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+	io_napi_free(ctx);
+	return 0;
+}
+
+/*
+ * __io_napi_busy_loop() - execute busy poll loop
+ * @ctx: pointer to io-uring context structure
+ * @iowq: pointer to io wait queue
+ *
+ * Execute the busy poll loop and merge the spliced off list.
+ */
+void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
+{
+	if (ctx->flags & IORING_SETUP_SQPOLL)
+		return;
+
+	iowq->napi_busy_poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);
+	if (iowq->timeout != KTIME_MAX) {
+		ktime_t dt = ktime_sub(iowq->timeout, io_get_time(ctx));
+
+		iowq->napi_busy_poll_dt = min_t(u64, iowq->napi_busy_poll_dt, dt);
+	}
+
+	iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+	io_napi_blocking_busy_loop(ctx, iowq);
+}
+
+/*
+ * io_napi_sqpoll_busy_poll() - busy poll loop for sqpoll
+ * @ctx: pointer to io-uring context structure
+ *
+ * Splice of the napi list and execute the napi busy poll loop.
+ */
+int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+{
+	bool is_stale = false;
+
+	if (!READ_ONCE(ctx->napi_busy_poll_dt))
+		return 0;
+	if (list_empty_careful(&ctx->napi_list))
+		return 0;
+
+	scoped_guard(rcu) {
+		is_stale = __io_napi_do_busy_loop(ctx, NULL, NULL);
+	}
+
+	io_napi_remove_stale(ctx, is_stale);
+	return 1;
+}
+
+#endif