Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-12 Thread David Gibson
On Thu, Jan 09, 2020 at 06:46:19PM +1100, Alexey Kardashevskiy wrote: > > > On 08/01/2020 12:06, David Gibson wrote: > > On Tue, Jan 07, 2020 at 03:21:42PM +0100, Cédric Le Goater wrote: > >> On 1/7/20 5:48 AM, David Gibson wrote: > >>> The table of RMA limits based on the LPCR[RMLS] field is sli

Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-08 Thread Alexey Kardashevskiy
On 08/01/2020 12:06, David Gibson wrote: > On Tue, Jan 07, 2020 at 03:21:42PM +0100, Cédric Le Goater wrote: >> On 1/7/20 5:48 AM, David Gibson wrote: >>> The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. >>> We're missing the RMLS == 0 => 256 GiB RMA option, which is avai

Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-08 Thread Cédric Le Goater
On 1/8/20 2:06 AM, David Gibson wrote: > On Tue, Jan 07, 2020 at 03:21:42PM +0100, Cédric Le Goater wrote: >> On 1/7/20 5:48 AM, David Gibson wrote: >>> The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. >>> We're missing the RMLS == 0 => 256 GiB RMA option, which is available

Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-08 Thread Cédric Le Goater
On 1/7/20 5:48 AM, David Gibson wrote: > The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. > We're missing the RMLS == 0 => 256 GiB RMA option, which is available on > POWER8, so add that. > > The comment that goes with the table is much more wrong. We *don't* filter > inva

Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-07 Thread David Gibson
On Tue, Jan 07, 2020 at 03:21:42PM +0100, Cédric Le Goater wrote: > On 1/7/20 5:48 AM, David Gibson wrote: > > The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. > > We're missing the RMLS == 0 => 256 GiB RMA option, which is available on > > POWER8, so add that. > > Where is

Re: [PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-07 Thread Cédric Le Goater
On 1/7/20 5:48 AM, David Gibson wrote: > The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. > We're missing the RMLS == 0 => 256 GiB RMA option, which is available on > POWER8, so add that. Where is this defined ? C. > > The comment that goes with the table is much more

[PATCH v2 09/10] target/ppc: Correct RMLS table

2020-01-06 Thread David Gibson
The table of RMA limits based on the LPCR[RMLS] field is slightly wrong. We're missing the RMLS == 0 => 256 GiB RMA option, which is available on POWER8, so add that. The comment that goes with the table is much more wrong. We *don't* filter invalid RMLS values when writing the LPCR, and there's