[PATCH][RFC] preempt_count corruption across H_CEDE call with CONFIG_PREEMPT on pseries

[Darren Hart <dvhltc@us.ibm.com>]

While testing CPU offline/online, we hit various preempt_count related
bugs. Various hacks have been employed for several theoretical corner
cases. One situation however is perfectly repeatable on 2.6.33.6 with
CONFIG_PREEMPT=y.

BUG: scheduling while atomic: swapper/0/0x00000065
Modules linked in: autofs4 sunrpc ipv6 dm_mirror dm_region_hash dm_log
dm_mod ehea sg ext4 jbd2 mbcache sd_mod crc_t10dif ibmvscsic
scsi_transport_srp scsi_tgt [last unloaded: scsi_wait_scan]
Call Trace:
[c00000010e9e39f0] [c0000000000144d4] .show_stack+0x74/0x1c0 (unreliable)
[c00000010e9e3aa0] [c00000000007a680] .__schedule_bug+0xa0/0xb0
[c00000010e9e3b30] [c00000000056dea4] .schedule+0x7a4/0xd60
[c00000010e9e3cd0] [c000000000016be8] .cpu_idle+0x1f8/0x220
[c00000010e9e3d80] [c00000000057d858] .start_secondary+0x388/0x3c0
[c00000010e9e3e30] [c000000000008278] .start_secondary_resume+0x10/0x14

With some instrumentation we were able to determine that the
preempt_count() appears to change across the extended_cede_processor()
call.  Specifically across the plpar_hcall_norets(H_CEDE) call. On
PREEMPT_RT we call this with preempt_count=1 and return with
preempt_count=0xffffffff. On mainline with CONFIG_PREEMPT=y, the value
is different (0x65) but is still incorrect.

Also of interest is that this path
cpu_idle()->cpu_die()->pseries_mach_cpu_die() to start_secondary()
enters with a preempt_count=1 if it wasn't corrupted across the hcall.
The early boot path from _start however appears to call
start_secondary() with a preempt_count of 0.

The following patch is most certainly not correct, but it does eliminate
the situation on mainline 100% of the time (there is still a 25%
reproduction rate on PREEMPT_RT). Can someone comment on:

1) How can the preempt_count() get mangled across the H_CEDE hcall?
2) Should we call preempt_enable() in cpu_idle() prior to cpu_die() ?

Hacked-up-by: Darren Hart <dvhltc@us.ibm.com>

Index: linux-2.6.33.6/arch/powerpc/platforms/pseries/hotplug-cpu.c
===================================================================
--- linux-2.6.33.6.orig/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ linux-2.6.33.6/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -138,6 +138,7 @@ static void pseries_mach_cpu_die(void)
 			 * Kernel stack will be reset and start_secondary()
 			 * will be called to continue the online operation.
 			 */
+			preempt_count() = 0;
 			start_secondary_resume();
 		}
 	}


-- 
Darren Hart
IBM Linux Technology Center
Real-Time Linux Team