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 --- include/drm/drm_ras.h | 88 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 include/drm/drm_ras.h (limited to 'include/drm/drm_ras.h') diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h new file mode 100644 index 000000000..0beede3dd --- /dev/null +++ b/include/drm/drm_ras.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2026 Intel Corporation + */ + +#ifndef __DRM_RAS_H__ +#define __DRM_RAS_H__ + +#include + +#include + +/** + * struct drm_ras_node - A DRM RAS Node + */ +struct drm_ras_node { + /** @id: Unique identifier for the node. Dynamically assigned. */ + u32 id; + /** + * @device_name: Human-readable name of the device. Given by the driver. + */ + const char *device_name; + /** @node_name: Human-readable name of the node. Given by the driver. */ + const char *node_name; + /** @type: Type of the node (enum drm_ras_node_type). */ + enum drm_ras_node_type type; + + /* Error-Counter Related Callback and Variables */ + + /** @error_counter_range: Range of valid Error IDs for this node. */ + struct { + /** @first: First valid Error ID. */ + u32 first; + /** @last: Last valid Error ID. Mandatory entry. */ + u32 last; + } error_counter_range; + + /** + * @query_error_counter: + * + * This callback is used by drm-ras to query a specific error counter. + * Used for input check and to iterate all error counters in a node. + * + * Driver should expect query_error_counter() to be called with + * error_id from `error_counter_range.first` to + * `error_counter_range.last`. + * + * The @query_error_counter is a mandatory callback for + * error_counter_node. + * + * Returns: 0 on success, + * -ENOENT when error_id is not supported as an indication that + * drm_ras should silently skip this entry. Used for + * supporting non-contiguous error ranges. + * Driver is responsible for maintaining the list of + * supported error IDs in the range of first to last. + * Other negative values on errors that should terminate the + * netlink query. + */ + int (*query_error_counter)(struct drm_ras_node *node, u32 error_id, + const char **name, u32 *val); + + /** + * @clear_error_counter: + * + * This callback is used by drm_ras to clear a specific error counter. + * Driver should implement this callback to support clearing error counters + * of a node. + * + * Returns: 0 on success, negative error code on failure. + */ + int (*clear_error_counter)(struct drm_ras_node *node, u32 error_id); + + /** @priv: Driver private data */ + void *priv; +}; + +struct drm_device; + +#if IS_ENABLED(CONFIG_DRM_RAS) +int drm_ras_node_register(struct drm_ras_node *node); +void drm_ras_node_unregister(struct drm_ras_node *node); +#else +static inline int drm_ras_node_register(struct drm_ras_node *node) { return 0; } +static inline void drm_ras_node_unregister(struct drm_ras_node *node) { } +#endif + +#endif -- cgit v1.3.1