powerpc/eeh: Dump PHB diag-data early
authorGavin Shan <gwshan@linux.vnet.ibm.com>
Sat, 22 Nov 2014 10:58:09 +0000 (21:58 +1100)
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>
Tue, 2 Dec 2014 00:03:26 +0000 (11:03 +1100)
commita450e8f55a57d049ac3afe218f06567e12d6b4f5
tree5d3dbf3db60f86f9cb737bf9cbd41d507720b9a8
parentb1d76a7d57762332cd8e0c020470d43c5ad3948e
powerpc/eeh: Dump PHB diag-data early

On PowerNV platform, PHB diag-data is dumped after stopping device
drivers. In case of recursive EEH errors, the kernel is usually
crashed before dumping PHB diag-data for the second EEH error. It's
hard to locate the root cause of the second EEH error without PHB
diag-data.

The patch adds one more EEH option "eeh=early_log", which helps
dumping PHB diag-data immediately once frozen PE is detected, in
order to get the PHB diag-data for the second EEH error.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
arch/powerpc/include/asm/eeh.h
arch/powerpc/kernel/eeh.c
arch/powerpc/platforms/powernv/eeh-ioda.c