EDAC, {i7core,sb,skx}_edac: Fix uncorrected error counting
The count of errors is picked up from bits 52:38 of the machine check bank status register. But this is the count of *corrected* errors. If an uncorrected error is being logged, the h/w sets this field to 0. Which means that when edac_mc_handle_error() is called, the EDAC core will carefully add zero to the appropriate uncorrected error counts. Signed-off-by: Tony Luck <tony.luck@intel.com> [ Massage commit message. ] Signed-off-by: Borislav Petkov <bp@suse.de> Cc: stable@vger.kernel.org Cc: Aristeu Rozanski <aris@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@kernel.org> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: linux-edac <linux-edac@vger.kernel.org> Link: http://lkml.kernel.org/r/20180928213934.19890-1-tony.luck@intel.com
This commit is contained in:
parent
8537bf1097
commit
432de7fd76
|
@ -1711,6 +1711,7 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci,
|
|||
u32 errnum = find_first_bit(&error, 32);
|
||||
|
||||
if (uncorrected_error) {
|
||||
core_err_cnt = 1;
|
||||
if (ripv)
|
||||
tp_event = HW_EVENT_ERR_FATAL;
|
||||
else
|
||||
|
|
|
@ -2982,6 +2982,7 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci,
|
|||
recoverable = GET_BITFIELD(m->status, 56, 56);
|
||||
|
||||
if (uncorrected_error) {
|
||||
core_err_cnt = 1;
|
||||
if (ripv) {
|
||||
type = "FATAL";
|
||||
tp_event = HW_EVENT_ERR_FATAL;
|
||||
|
|
|
@ -959,6 +959,7 @@ static void skx_mce_output_error(struct mem_ctl_info *mci,
|
|||
recoverable = GET_BITFIELD(m->status, 56, 56);
|
||||
|
||||
if (uncorrected_error) {
|
||||
core_err_cnt = 1;
|
||||
if (ripv) {
|
||||
type = "FATAL";
|
||||
tp_event = HW_EVENT_ERR_FATAL;
|
||||
|
|
Loading…
Reference in New Issue