[PATCH] powerpc/64s: Report SLB multi-hit rather than parity error

Nicholas Piggin npiggin at gmail.com
Thu Jun 14 00:40:36 AEST 2018


On Wed, 13 Jun 2018 23:24:14 +1000
Michael Ellerman <mpe at ellerman.id.au> wrote:

> When we take an SLB multi-hit on bare metal, we see both the multi-hit
> and parity error bits set in DSISR. The user manuals indicates this is
> expected to always happen on Power8, whereas on Power9 it says a
> multi-hit will "usually" also cause a parity error.
> 
> We decide what to do based on the various error tables in mce_power.c,
> and because we process them in order and only report the first, we
> currently always report a parity error but not the multi-hit, eg:
> 
>   Severe Machine check interrupt [Recovered]
>     Initiator: CPU
>     Error type: SLB [Parity]
>       Effective address: c000000ffffd4300
> 
> Although this is correct, it leaves the user wondering why they got a
> parity error. It would be clearer instead if we reported the
> multi-hit because that is more likely to be simply a software bug,
> whereas a true parity error is possibly an indication of a bad core.
> 
> We can do that simply by reordering the error tables so that multi-hit
> appears before parity. That doesn't affect the error recovery at all,
> because we flush the SLB either way.

Yeah this is a good idea. I wonder if there are any other conditions
like this that should be reordered.

I think the i-side should not have to be changed here because it
matches the value not bits, so that shouldn't matter.

A bit of a shame we don't report i/d side, and ideally we'd be able
to report multiple conditions. The reporting APIs really want to be
massaged a bit, but for now this is a good step.

Reviewed-by: Nicholas Piggin <npiggin at gmail.com>


> 
> Signed-off-by: Michael Ellerman <mpe at ellerman.id.au>
> ---
>  arch/powerpc/kernel/mce_power.c | 36 ++++++++++++++++++------------------
>  1 file changed, 18 insertions(+), 18 deletions(-)
> 
> diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
> index 38c5b4764bfe..1e450d0c4f72 100644
> --- a/arch/powerpc/kernel/mce_power.c
> +++ b/arch/powerpc/kernel/mce_power.c
> @@ -140,12 +140,12 @@ static const struct mce_ierror_table mce_p7_ierror_table[] = {
>  { 0x00000000001c0000, 0x0000000000040000, true,
>    MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> +{ 0x00000000001c0000, 0x00000000000c0000, true,
> +  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000001c0000, 0x0000000000080000, true,
>    MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> -{ 0x00000000001c0000, 0x00000000000c0000, true,
> -  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000001c0000, 0x0000000000100000, true,
>    MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> @@ -164,12 +164,12 @@ static const struct mce_ierror_table mce_p8_ierror_table[] = {
>  { 0x00000000081c0000, 0x0000000000040000, true,
>    MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> +{ 0x00000000081c0000, 0x00000000000c0000, true,
> +  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000081c0000, 0x0000000000080000, true,
>    MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> -{ 0x00000000081c0000, 0x00000000000c0000, true,
> -  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000081c0000, 0x0000000000100000, true,
>    MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> @@ -194,12 +194,12 @@ static const struct mce_ierror_table mce_p9_ierror_table[] = {
>  { 0x00000000081c0000, 0x0000000000040000, true,
>    MCE_ERROR_TYPE_UE,  MCE_UE_ERROR_IFETCH,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> +{ 0x00000000081c0000, 0x00000000000c0000, true,
> +  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000081c0000, 0x0000000000080000, true,
>    MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> -{ 0x00000000081c0000, 0x00000000000c0000, true,
> -  MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
>  { 0x00000000081c0000, 0x0000000000100000, true,
>    MCE_ERROR_TYPE_ERAT,MCE_ERAT_ERROR_MULTIHIT,
>    MCE_INITIATOR_CPU,  MCE_SEV_ERROR_SYNC, },
> @@ -257,12 +257,12 @@ static const struct mce_derror_table mce_p7_derror_table[] = {
>  { 0x00000400, true,
>    MCE_ERROR_TYPE_TLB,  MCE_TLB_ERROR_MULTIHIT,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> +{ 0x00000080, true,
> +  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0x00000100, true,
>    MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> -{ 0x00000080, true,
> -  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0x00000040, true,
>    MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_INDETERMINATE, /* BOTH */
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> @@ -290,12 +290,12 @@ static const struct mce_derror_table mce_p8_derror_table[] = {
>  { 0x00000200, true,
>    MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, /* SECONDARY ERAT */
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> +{ 0x00000080, true,
> +  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0x00000100, true,
>    MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> -{ 0x00000080, true,
> -  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0, false, 0, 0, 0, 0 } };
>  
>  static const struct mce_derror_table mce_p9_derror_table[] = {
> @@ -320,12 +320,12 @@ static const struct mce_derror_table mce_p9_derror_table[] = {
>  { 0x00000200, false,
>    MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> +{ 0x00000080, true,
> +  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,	/* Before PARITY */
> +  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0x00000100, true,
>    MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_PARITY,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
> -{ 0x00000080, true,
> -  MCE_ERROR_TYPE_SLB,  MCE_SLB_ERROR_MULTIHIT,
> -  MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },
>  { 0x00000040, true,
>    MCE_ERROR_TYPE_RA,   MCE_RA_ERROR_LOAD,
>    MCE_INITIATOR_CPU,   MCE_SEV_ERROR_SYNC, },



More information about the Linuxppc-dev mailing list