2021-10-10 17:46:16

by Eric Badger

Subject: [PATCH] EDAC/sb_edac: Fix top-of-high-memory value for Broadwell/Haswell

The computation of TOHM is off by one bit. This missed bit results in
too low a value for TOHM, which can cause errors in regular memory to
incorrectly report:

EDAC MC0: 1 CE Error at MMIOH area, on addr 0x000000207fffa680 on any memory

Reported-by: Meeta Saggi <[email protected]>
Signed-off-by: Eric Badger <[email protected]>
---
drivers/edac/sb_edac.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 4c626fc..1522d4a 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -1052,7 +1052,7 @@ static u64 haswell_get_tohm(struct sbridge_pvt *pvt)
pci_read_config_dword(pvt->info.pci_vtd, HASWELL_TOHM_1, &reg);
rc = ((reg << 6) | rc) << 26;

- return rc | 0x1ffffff;
+ return rc | 0x3ffffff;
}

static u64 knl_get_tolm(struct sbridge_pvt *pvt)
--

2021-10-11 16:41:21

by Tony Luck

Subject: Re: [PATCH] EDAC/sb_edac: Fix top-of-high-memory value for Broadwell/Haswell

On Sun, Oct 10, 2021 at 10:06:56AM -0700, Eric Badger wrote:
> The computation of TOHM is off by one bit. This missed bit results in
> too low a value for TOHM, which can cause errors in regular memory to
> incorrectly report:
>
> EDAC MC0: 1 CE Error at MMIOH area, on addr 0x000000207fffa680 on any memory
>
> Reported-by: Meeta Saggi <[email protected]>
> Signed-off-by: Eric Badger <[email protected]>

Applied (with added Fixes: tag and Cc: stable).

Thanks

-Tony