aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@woody.linux-foundation.org>2007-09-19 14:37:14 -0400
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-09-19 14:37:14 -0400
commitdbe3ed1c078c193be34326728d494c5c4bc115e2 (patch)
tree9624273ee199b70db0c8adc0ea38a8b2e0984544
parent4f01a757e75f2a3cab2bab89c4176498963946b9 (diff)
x86-64: page faults from user mode are always user faults
Randy Dunlap noticed an interesting "crashme" behaviour on his dual Prescott Xeon setup, where he gets page faults with the error code having a zero "user" bit, but the register state points back to user mode. This may be a CPU microcode buglet triggered by some strange instruction pattern that crashme generates, and loading a microcode update seems to possibly have fixed it. Regardless, we really should trust the register state more than the error code, since it's really the register state that determines whether we can actually send a signal, or whether we're in kernel mode and need to oops/kill the process in the case of a page fault. Cc: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--arch/x86_64/mm/fault.c7
1 files changed, 7 insertions, 0 deletions
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 327c9f2fa626..54816adb8e93 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -374,6 +374,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
374 if (unlikely(in_atomic() || !mm)) 374 if (unlikely(in_atomic() || !mm))
375 goto bad_area_nosemaphore; 375 goto bad_area_nosemaphore;
376 376
377 /*
378 * User-mode registers count as a user access even for any
379 * potential system fault or CPU buglet.
380 */
381 if (user_mode_vm(regs))
382 error_code |= PF_USER;
383
377 again: 384 again:
378 /* When running in the kernel we expect faults to occur only to 385 /* When running in the kernel we expect faults to occur only to
379 * addresses in user space. All other faults represent errors in the 386 * addresses in user space. All other faults represent errors in the