From 833526941f5945cf0b22a595bb8f3525b512f654 Mon Sep 17 00:00:00 2001 From: Rob Gardner Date: Tue, 22 Dec 2015 21:16:07 -0700 Subject: [PATCH] sparc64: Perf should save/restore fault info There have been several reports of random processes being killed with a bus error or segfault during userspace stack walking in perf. One of the root causes of this problem is an asynchronous modification to thread_info fault_address and fault_code, which stems from a perf counter interrupt arriving during kernel processing of a "benign" fault, such as a TSB miss. Since perf_callchain_user() invokes copy_from_user() to read user stacks, a fault is not only possible, but probable. Validity checks on the stack address merely cover up the problem and reduce its frequency. The solution here is to save and restore fault_address and fault_code in perf_callchain_user() so that the benign fault handler is not disturbed by a perf interrupt. Signed-off-by: Rob Gardner Signed-off-by: Dave Aldridge Signed-off-by: David S. Miller --- arch/sparc/kernel/perf_event.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b1144d6acffe..6596f66ce112 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1828,6 +1828,8 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + u64 saved_fault_address = current_thread_info()->fault_address; + u8 saved_fault_code = get_thread_fault_code(); mm_segment_t old_fs; perf_callchain_store(entry, regs->tpc); @@ -1850,4 +1852,6 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) pagefault_enable(); set_fs(old_fs); + set_thread_fault_code(saved_fault_code); + current_thread_info()->fault_address = saved_fault_address; } -- 2.20.1