Skip to main content

Browse the archive

https://github.com/torvalds/linux
27 March 2024, 02:37:15 UTC
Revision 833526941f5945cf0b22a595bb8f3525b512f654 authored by Rob Gardner on 23 December 2015, 04:16:07 UTC, committed by David S. Miller on 24 December 2015, 17:12:46 UTC 
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 <rob.gardner@oracle.com>
Signed-off-by: Dave Aldridge <david.j.aldridge@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 3f74306
History
Tip revision: 833526941f5945cf0b22a595bb8f3525b512f654 authored by Rob Gardner on 23 December 2015, 04:16:07 UTC
sparc64: Perf should save/restore fault info
Tip revision: 8335269
File Mode Size
Documentation
arch
block
certs
crypto
drivers
firmware
fs
include
init
ipc
kernel
lib
mm
net
samples
scripts
security
sound
tools
usr
virt
.get_maintainer.ignore -rw-r--r-- 31 bytes
.gitignore -rw-r--r-- 1.2 KB
.mailmap -rw-r--r-- 5.4 KB
COPYING -rw-r--r-- 18.3 KB
CREDITS -rw-r--r-- 94.9 KB
Kbuild -rw-r--r-- 2.6 KB
Kconfig -rw-r--r-- 252 bytes
MAINTAINERS -rw-r--r-- 328.7 KB
Makefile -rw-r--r-- 53.5 KB
README -rw-r--r-- 18.2 KB
REPORTING-BUGS -rw-r--r-- 7.3 KB

README

back to top