From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace 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 --- io_uring/kbuf.h | 141 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 io_uring/kbuf.h (limited to 'io_uring/kbuf.h') diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h new file mode 100644 index 000000000..401773e1e --- /dev/null +++ b/io_uring/kbuf.h @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef IOU_KBUF_H +#define IOU_KBUF_H + +#include +#include + +enum { + /* ring mapped provided buffers */ + IOBL_BUF_RING = 1, + /* buffers are consumed incrementally rather than always fully */ + IOBL_INC = 2, +}; + +struct io_buffer_list { + /* + * If the IOBL_BUF_RING flag is set, then buf_ring is used. If not, then + * these are classic provided buffers and ->buf_list is used. + */ + union { + struct list_head buf_list; + struct io_uring_buf_ring *buf_ring; + }; + /* count of classic/legacy buffers in buffer list */ + int nbufs; + + __u16 bgid; + + /* below is for ring provided buffers */ + __u16 head; + __u16 mask; + + __u16 flags; + + /* + * minimum required amount to be left to reuse an incrementally + * consumed buffer. If less than this is left at consumption time, + * buffer is done and head is incremented to the next buffer. + */ + __u32 min_left_sub_one; + + struct io_mapped_region region; +}; + +struct io_buffer { + struct list_head list; + __u64 addr; + __u32 len; + __u16 bid; + __u16 bgid; +}; + +enum { + /* can alloc a bigger vec */ + KBUF_MODE_EXPAND = 1, + /* if bigger vec allocated, free old one */ + KBUF_MODE_FREE = 2, +}; + +struct buf_sel_arg { + struct iovec *iovs; + size_t out_len; + size_t max_len; + unsigned short nr_iovs; + unsigned short mode; + unsigned short buf_group; + unsigned short partial_map; +}; + +struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len, + unsigned buf_group, unsigned int issue_flags); +int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg, + struct io_br_sel *sel, unsigned int issue_flags); +int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg, + struct io_br_sel *sel); +void io_destroy_buffers(struct io_ring_ctx *ctx); + +int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); +int io_manage_buffers_legacy(struct io_kiocb *req, unsigned int issue_flags); + +int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); +int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); +int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg); + +bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); +void io_kbuf_drop_legacy(struct io_kiocb *req); + +unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl, + int len, int nbufs); +bool io_kbuf_commit(struct io_kiocb *req, + struct io_buffer_list *bl, int len, int nr); + +struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx, + unsigned int bgid); + +static inline bool io_kbuf_recycle_ring(struct io_kiocb *req, + struct io_buffer_list *bl) +{ + if (bl) { + req->flags &= ~(REQ_F_BUFFER_RING|REQ_F_BUFFERS_COMMIT); + return true; + } + return false; +} + +static inline bool io_do_buffer_select(struct io_kiocb *req) +{ + if (!(req->flags & REQ_F_BUFFER_SELECT)) + return false; + return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)); +} + +static inline bool io_kbuf_recycle(struct io_kiocb *req, struct io_buffer_list *bl, + unsigned issue_flags) +{ + if (req->flags & REQ_F_BL_NO_RECYCLE) + return false; + if (req->flags & REQ_F_BUFFER_RING) + return io_kbuf_recycle_ring(req, bl); + if (req->flags & REQ_F_BUFFER_SELECTED) + return io_kbuf_recycle_legacy(req, issue_flags); + return false; +} + +static inline unsigned int io_put_kbuf(struct io_kiocb *req, int len, + struct io_buffer_list *bl) +{ + if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) + return 0; + return __io_put_kbufs(req, bl, len, 1); +} + +static inline unsigned int io_put_kbufs(struct io_kiocb *req, int len, + struct io_buffer_list *bl, int nbufs) +{ + if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED))) + return 0; + return __io_put_kbufs(req, bl, len, nbufs); +} +#endif -- cgit v1.3.1