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, 156 insertions, 0 deletions

diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
new file mode 100644
index 000000000..9ef88383b
--- /dev/null
+++ b/io_uring/rsrc.h
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_RSRC_H
+#define IOU_RSRC_H
+
+#include <linux/bvec.h>
+#include <linux/io_uring_types.h>
+#include <linux/lockdep.h>
+#include <linux/uio.h>
+
+#define IO_VEC_CACHE_SOFT_CAP		256
+
+enum {
+	IORING_RSRC_FILE		= 0,
+	IORING_RSRC_BUFFER		= 1,
+};
+
+struct io_rsrc_node {
+	unsigned char			type;
+	int				refs;
+
+	u64 tag;
+	union {
+		unsigned long file_ptr;
+		struct io_mapped_ubuf *buf;
+	};
+};
+
+enum {
+	IO_REGBUF_F_KBUF		= 1,
+};
+
+struct io_mapped_ubuf {
+	u64		ubuf;
+	size_t		len;
+	unsigned int	nr_bvecs;
+	unsigned int    folio_shift;
+	refcount_t	refs;
+	u8		flags;
+	u8		dir;
+	void		(*release)(void *);
+	void		*priv;
+	struct bio_vec	bvec[] __counted_by(nr_bvecs);
+};
+
+struct io_imu_folio_data {
+	/* Head folio can be partially included in the fixed buf */
+	unsigned int	nr_pages_head;
+	/* For non-head/tail folios, has to be fully included */
+	unsigned int	nr_pages_mid;
+	unsigned int	folio_shift;
+	unsigned int	nr_folios;
+	unsigned long	first_folio_page_idx;
+};
+
+bool io_rsrc_cache_init(struct io_ring_ctx *ctx);
+void io_rsrc_cache_free(struct io_ring_ctx *ctx);
+struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type);
+void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node);
+void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data);
+int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
+
+struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
+				      unsigned issue_flags);
+int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+			u64 buf_addr, size_t len, int ddir,
+			unsigned issue_flags);
+int io_import_reg_vec(int ddir, struct iov_iter *iter,
+			struct io_kiocb *req, struct iou_vec *vec,
+			unsigned nr_iovs, unsigned issue_flags);
+int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
+			const struct iovec __user *uvec, size_t uvec_segs);
+
+int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
+int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
+int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
+			    unsigned int nr_args, u64 __user *tags);
+int io_sqe_files_unregister(struct io_ring_ctx *ctx);
+int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
+			  unsigned nr_args, u64 __user *tags);
+
+int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
+			     unsigned nr_args);
+int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
+			    unsigned size, unsigned type);
+int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
+			unsigned int size, unsigned int type);
+int io_validate_user_buf_range(u64 uaddr, u64 ulen);
+
+bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
+			      struct io_imu_folio_data *data);
+
+static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data,
+						       unsigned int index)
+{
+	if (index < data->nr)
+		return data->nodes[array_index_nospec(index, data->nr)];
+	return NULL;
+}
+
+static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	if (!--node->refs)
+		io_free_rsrc_node(ctx, node);
+}
+
+static inline bool io_reset_rsrc_node(struct io_ring_ctx *ctx,
+				      struct io_rsrc_data *data,
+				      unsigned int index)
+{
+	struct io_rsrc_node *node;
+
+	if (index >= data->nr)
+		return false;
+	index = array_index_nospec(index, data->nr);
+	node = data->nodes[index];
+	if (!node)
+		return false;
+	io_put_rsrc_node(ctx, node);
+	data->nodes[index] = NULL;
+	return true;
+}
+
+int io_files_update(struct io_kiocb *req, unsigned int issue_flags);
+int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+int __io_account_mem(struct user_struct *user, unsigned long nr_pages);
+int io_account_mem(struct user_struct *user, struct mm_struct *mm_account,
+		   unsigned long nr_pages);
+void io_unaccount_mem(struct user_struct *user, struct mm_struct *mm_account,
+		      unsigned long nr_pages);
+
+static inline void __io_unaccount_mem(struct user_struct *user,
+				      unsigned long nr_pages)
+{
+	atomic_long_sub(nr_pages, &user->locked_vm);
+}
+
+void io_vec_free(struct iou_vec *iv);
+int io_vec_realloc(struct iou_vec *iv, unsigned nr_entries);
+
+static inline void io_vec_reset_iovec(struct iou_vec *iv,
+				      struct iovec *iovec, unsigned nr)
+{
+	io_vec_free(iv);
+	iv->iovec = iovec;
+	iv->nr = nr;
+}
+
+static inline void io_alloc_cache_vec_kasan(struct iou_vec *iv)
+{
+	if (IS_ENABLED(CONFIG_KASAN))
+		io_vec_free(iv);
+}
+
+#endif