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 --- lib/Kconfig.kcsan | 251 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 251 insertions(+) create mode 100644 lib/Kconfig.kcsan (limited to 'lib/Kconfig.kcsan') diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan new file mode 100644 index 000000000..4ce4b0c01 --- /dev/null +++ b/lib/Kconfig.kcsan @@ -0,0 +1,251 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config HAVE_ARCH_KCSAN + bool + +config HAVE_KCSAN_COMPILER + def_bool (CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-distinguish-volatile=1)) || \ + (CC_IS_GCC && $(cc-option,-fsanitize=thread --param tsan-distinguish-volatile=1)) + help + For the list of compilers that support KCSAN, please see + . + +menuconfig KCSAN + bool "KCSAN: dynamic data race detector" + depends on HAVE_ARCH_KCSAN && HAVE_KCSAN_COMPILER + depends on DEBUG_KERNEL && !KASAN + select CONSTRUCTORS + select STACKTRACE + help + The Kernel Concurrency Sanitizer (KCSAN) is a dynamic + data-race detector that relies on compile-time instrumentation. + KCSAN uses a watchpoint-based sampling approach to detect races. + + While KCSAN's primary purpose is to detect data races, it + also provides assertions to check data access constraints. + These assertions can expose bugs that do not manifest as + data races. + + See for more details. + +if KCSAN + +config CC_HAS_TSAN_COMPOUND_READ_BEFORE_WRITE + def_bool (CC_IS_CLANG && $(cc-option,-fsanitize=thread -mllvm -tsan-compound-read-before-write=1)) || \ + (CC_IS_GCC && $(cc-option,-fsanitize=thread --param tsan-compound-read-before-write=1)) + help + The compiler instruments plain compound read-write operations + differently (++, --, +=, -=, |=, &=, etc.), which allows KCSAN to + distinguish them from other plain accesses. This is currently + supported by Clang 12 or later. + +config KCSAN_VERBOSE + bool "Show verbose reports with more information about system state" + depends on PROVE_LOCKING + help + If enabled, reports show more information about the system state that + may help better analyze and debug races. This includes held locks and + IRQ trace events. + + While this option should generally be benign, we call into more + external functions on report generation; if a race report is + generated from any one of them, system stability may suffer due to + deadlocks or recursion. If in doubt, say N. + +config KCSAN_SELFTEST + bool "Perform short selftests on boot" + default y + help + Run KCSAN selftests on boot. On test failure, causes the kernel to + panic. Recommended to be enabled, ensuring critical functionality + works as intended. + +config KCSAN_KUNIT_TEST + tristate "KCSAN test for integrated runtime behaviour" if !KUNIT_ALL_TESTS + default KUNIT_ALL_TESTS + depends on TRACEPOINTS && KUNIT + select TORTURE_TEST + help + KCSAN test focusing on behaviour of the integrated runtime. Tests + various race scenarios, and verifies the reports generated to + console. Makes use of KUnit for test organization, and the Torture + framework for test thread control. + + Each test case may run at least up to KCSAN_REPORT_ONCE_IN_MS + milliseconds. Test run duration may be optimized by building the + kernel and KCSAN test with KCSAN_REPORT_ONCE_IN_MS set to a lower + than default value. + + Say Y here if you want the test to be built into the kernel and run + during boot; say M if you want the test to build as a module; say N + if you are unsure. + +config KCSAN_EARLY_ENABLE + bool "Early enable during boot" + default y + help + If KCSAN should be enabled globally as soon as possible. KCSAN can + later be enabled/disabled via debugfs. + +config KCSAN_NUM_WATCHPOINTS + int "Number of available watchpoints" + default 64 + help + Total number of available watchpoints. An address range maps into a + specific watchpoint slot as specified in kernel/kcsan/encoding.h. + Although larger number of watchpoints may not be usable due to + limited number of CPUs, a larger value helps to improve performance + due to reducing cache-line contention. The chosen default is a + conservative value; we should almost never observe "no_capacity" + events (see /sys/kernel/debug/kcsan). + +config KCSAN_UDELAY_TASK + int "Delay in microseconds (for tasks)" + default 80 + help + For tasks, the microsecond delay after setting up a watchpoint. + +config KCSAN_UDELAY_INTERRUPT + int "Delay in microseconds (for interrupts)" + default 20 + help + For interrupts, the microsecond delay after setting up a watchpoint. + Interrupts have tighter latency requirements, and their delay should + be lower than for tasks. + +config KCSAN_DELAY_RANDOMIZE + bool "Randomize above delays" + default y + help + If delays should be randomized, where the maximum is KCSAN_UDELAY_*. + If false, the chosen delays are always the KCSAN_UDELAY_* values + as defined above. + +config KCSAN_SKIP_WATCH + int "Skip instructions before setting up watchpoint" + default 4000 + help + The number of per-CPU memory operations to skip, before another + watchpoint is set up, i.e. one in KCSAN_SKIP_WATCH per-CPU + memory operations are used to set up a watchpoint. A smaller value + results in more aggressive race detection, whereas a larger value + improves system performance at the cost of missing some races. + +config KCSAN_SKIP_WATCH_RANDOMIZE + bool "Randomize watchpoint instruction skip count" + default y + help + If instruction skip count should be randomized, where the maximum is + KCSAN_SKIP_WATCH. If false, the chosen value is always + KCSAN_SKIP_WATCH. + +config KCSAN_INTERRUPT_WATCHER + bool "Interruptible watchers" if !KCSAN_STRICT + default KCSAN_STRICT + help + If enabled, a task that set up a watchpoint may be interrupted while + delayed. This option will allow KCSAN to detect races between + interrupted tasks and other threads of execution on the same CPU. + + Currently disabled by default, because not all safe per-CPU access + primitives and patterns may be accounted for, and therefore could + result in false positives. + +config KCSAN_REPORT_ONCE_IN_MS + int "Duration in milliseconds, in which any given race is only reported once" + default 3000 + help + Any given race is only reported once in the defined time window. + Different races may still generate reports within a duration that is + smaller than the duration defined here. This allows rate limiting + reporting to avoid flooding the console with reports. Setting this + to 0 disables rate limiting. + +# The main purpose of the below options is to control reported data races, and +# are not expected to be switched frequently by non-testers or at runtime. +# The defaults are chosen to be conservative, and can miss certain bugs. + +config KCSAN_REPORT_RACE_UNKNOWN_ORIGIN + bool "Report races of unknown origin" + default y + help + If KCSAN should report races where only one access is known, and the + conflicting access is of unknown origin. This type of race is + reported if it was only possible to infer a race due to a data value + change while an access is being delayed on a watchpoint. + +config KCSAN_STRICT + bool "Strict data-race checking" + help + KCSAN will report data races with the strictest possible rules, which + closely aligns with the rules defined by the Linux-kernel memory + consistency model (LKMM). + +config KCSAN_WEAK_MEMORY + bool "Enable weak memory modeling to detect missing memory barriers" + default y + depends on KCSAN_STRICT + help + Enable support for modeling a subset of weak memory, which allows + detecting a subset of data races due to missing memory barriers. + + Depends on KCSAN_STRICT, because the options strengthening certain + plain accesses by default (depending on !KCSAN_STRICT) reduce the + ability to detect any data races invoving reordered accesses, in + particular reordered writes. + + Weak memory modeling relies on additional instrumentation and may + affect performance. + +config KCSAN_REPORT_VALUE_CHANGE_ONLY + bool "Only report races where watcher observed a data value change" + default y + depends on !KCSAN_STRICT + help + If enabled and a conflicting write is observed via a watchpoint, but + the data value of the memory location was observed to remain + unchanged, do not report the data race. + +config KCSAN_ASSUME_PLAIN_WRITES_ATOMIC + bool "Assume that plain aligned writes up to word size are atomic" + default y + depends on !KCSAN_STRICT + help + Assume that plain aligned writes up to word size are atomic by + default, and also not subject to other unsafe compiler optimizations + resulting in data races. This will cause KCSAN to not report data + races due to conflicts where the only plain accesses are aligned + writes up to word size: conflicts between marked reads and plain + aligned writes up to word size will not be reported as data races; + notice that data races between two conflicting plain aligned writes + will also not be reported. + +config KCSAN_IGNORE_ATOMICS + bool "Do not instrument marked atomic accesses" + depends on !KCSAN_STRICT + help + Never instrument marked atomic accesses. This option can be used for + additional filtering. Conflicting marked atomic reads and plain + writes will never be reported as a data race, however, will cause + plain reads and marked writes to result in "unknown origin" reports. + If combined with CONFIG_KCSAN_REPORT_RACE_UNKNOWN_ORIGIN=n, data + races where at least one access is marked atomic will never be + reported. + + Similar to KCSAN_ASSUME_PLAIN_WRITES_ATOMIC, but including unaligned + accesses, conflicting marked atomic reads and plain writes will not + be reported as data races; however, unlike that option, data races + due to two conflicting plain writes will be reported (aligned and + unaligned, if CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n). + +config KCSAN_PERMISSIVE + bool "Enable all additional permissive rules" + depends on KCSAN_REPORT_VALUE_CHANGE_ONLY + help + Enable additional permissive rules to ignore certain classes of data + races (also see kernel/kcsan/permissive.h). None of the permissive + rules imply that such data races are generally safe, but can be used + to further reduce reported data races due to data-racy patterns + common across the kernel. + +endif # KCSAN -- cgit v1.3.1