aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorAnton Blanchard <anton@samba.org>2010-05-10 12:25:51 -0400
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2010-05-21 03:31:10 -0400
commit0644079410065567e3bb31fcb8e6441f2b7685a9 (patch)
tree86063190ee8b84cb4f892454c0905a760cdcec01 /arch
parent426b6cb478e60352a463a0d1ec75c1c9fab30b13 (diff)
powerpc/kdump: CPUs assume the context of the oopsing CPU
We wrap the crash_shutdown_handles[] calls with longjmp/setjmp, so if any of them fault we can recover. The problem is we add a hook to the debugger fault handler hook which calls longjmp unconditionally. This first part of kdump is run before we marshall the other CPUs, so there is a very good chance some CPU on the box is going to page fault. And when it does it hits the longjmp code and assumes the context of the oopsing CPU. The machine gets very confused when it has 10 CPUs all with the same stack, all thinking they have the same CPU id. I get even more confused trying to debug it. The patch below adds crash_shutdown_cpu and uses it to specify which cpu is in the protected region. Since it can only be -1 or the oopsing CPU, we don't need to use memory barriers since it is only valid on the local CPU - no other CPU will ever see a value that matches it's local CPU id. Eventually we should switch the order and marshall all CPUs before doing the crash_shutdown_handles[] calls, but that is a bigger fix. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/kernel/crash.c6
1 files changed, 5 insertions, 1 deletions
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 341d8af6f33e..7ced58dacb12 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -347,10 +347,12 @@ int crash_shutdown_unregister(crash_shutdown_t handler)
347EXPORT_SYMBOL(crash_shutdown_unregister); 347EXPORT_SYMBOL(crash_shutdown_unregister);
348 348
349static unsigned long crash_shutdown_buf[JMP_BUF_LEN]; 349static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
350static int crash_shutdown_cpu = -1;
350 351
351static int handle_fault(struct pt_regs *regs) 352static int handle_fault(struct pt_regs *regs)
352{ 353{
353 longjmp(crash_shutdown_buf, 1); 354 if (crash_shutdown_cpu == smp_processor_id())
355 longjmp(crash_shutdown_buf, 1);
354 return 0; 356 return 0;
355} 357}
356 358
@@ -391,6 +393,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
391 */ 393 */
392 old_handler = __debugger_fault_handler; 394 old_handler = __debugger_fault_handler;
393 __debugger_fault_handler = handle_fault; 395 __debugger_fault_handler = handle_fault;
396 crash_shutdown_cpu = smp_processor_id();
394 for (i = 0; crash_shutdown_handles[i]; i++) { 397 for (i = 0; crash_shutdown_handles[i]; i++) {
395 if (setjmp(crash_shutdown_buf) == 0) { 398 if (setjmp(crash_shutdown_buf) == 0) {
396 /* 399 /*
@@ -404,6 +407,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
404 asm volatile("sync; isync"); 407 asm volatile("sync; isync");
405 } 408 }
406 } 409 }
410 crash_shutdown_cpu = -1;
407 __debugger_fault_handler = old_handler; 411 __debugger_fault_handler = old_handler;
408 412
409 /* 413 /*