All of lore.kernel.org
 help / color / mirror / Atom feed
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
To: Lucas De Marchi <lucas.demarchi@intel.com>,
	igt-dev@lists.freedesktop.org
Subject: Re: [igt-dev] [PATCH 3/5] i915/gem_mocs_settings: add MOCS table for Tiger Lake
Date: Fri, 26 Jul 2019 17:16:02 -0700	[thread overview]
Message-ID: <e3a07813-05ca-08fb-d893-8b5f9df72460@intel.com> (raw)
In-Reply-To: <20190725203354.6757-3-lucas.demarchi@intel.com>



On 7/25/19 1:33 PM, Lucas De Marchi wrote:
> Some small changes compared to Ice Lake, namely:
> 
>    - Removed entries 0 and 1: they are now reserved and shouldn't be used
>    - Entries 16, 17, 48..61 were previously unused and are now available
> 

Not related to this patch, but entries 16 and 17 are defined in the 
gen11 table because they're required on EHL, so we need to update the 
test to check those as well.

> Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
> ---
>   tests/i915/gem_mocs_settings.c | 38 ++++++++++++++++++++++++++++++++++
>   1 file changed, 38 insertions(+)
> 
> diff --git a/tests/i915/gem_mocs_settings.c b/tests/i915/gem_mocs_settings.c
> index 9f4e1b6d..e3da8515 100644
> --- a/tests/i915/gem_mocs_settings.c
> +++ b/tests/i915/gem_mocs_settings.c
> @@ -78,6 +78,40 @@ struct mocs_table {
>   };
>   
>   /* The first entries in the MOCS tables are defined by uABI */
> +
> +static const struct mocs_entry tigerlake_mocs_table[GEN11_NUM_MOCS_ENTRIES] = {
> +	[2]  = { 0x00000037, 0x0030, 0x1},
> +	[3]  = { 0x00000005, 0x0010, 0x1},
> +	[4]  = { 0x00000005, 0x0030, 0x1},
> +	[5]  = { 0x00000037, 0x0010, 0x1},
> +	[6]  = { 0x00000017, 0x0010, 0x1},
> +	[7]  = { 0x00000017, 0x0030, 0x1},
> +	[8]  = { 0x00000027, 0x0010, 0x1},
> +	[9]  = { 0x00000027, 0x0030, 0x1},
> +	[10] = { 0x00000077, 0x0010, 0x1},
> +	[11] = { 0x00000077, 0x0030, 0x1},
> +	[12] = { 0x00000057, 0x0010, 0x1},
> +	[13] = { 0x00000057, 0x0030, 0x1},
> +	[14] = { 0x00000067, 0x0010, 0x1},
> +	[15] = { 0x00000067, 0x0030, 0x1},
> +	[16] = { 0x00004005, 0x0010, 0x1},
> +	[17] = { 0x00004005, 0x0030, 0x1},
> +	[18] = { 0x00060037, 0x0030, 0x1},
> +	[19] = { 0x00000737, 0x0030, 0x1},
> +	[20] = { 0x00000337, 0x0030, 0x1},
> +	[21] = { 0x00000137, 0x0030, 0x1},
> +	[22] = { 0x000003b7, 0x0030, 0x1},
> +	[23] = { 0x000007b7, 0x0030, 0x1},
> +	[48] = { 0x00000037, 0x0030, 0x1},
> +	[49] = { 0x00000005, 0x0030, 0x1},
> +	[50] = { 0x00000037, 0x0010, 0x1},
> +	[51] = { 0x00000005, 0x0010, 0x1},
> +	[60] = { 0x00000037, 0x0010, 0x1},
> +	[61] = { 0x00004005, 0x0030, 0x1},
> +	[62] = { 0x00000037, 0x0010, 0x1},
> +	[63] = { 0x00000037, 0x0010, 0x1},
> +};
> +

Matches the specs.

>   static const struct mocs_entry icelake_mocs_table[GEN11_NUM_MOCS_ENTRIES] = {
>   	[0]  = { 0x00000005, 0x0010, 0x1},
>   	[1]  = ICELAKE_MOCS_PTE,
> @@ -158,6 +192,10 @@ static bool get_mocs_settings(int fd, struct mocs_table *table, bool dirty)
>   		table->size  = ARRAY_SIZE(icelake_mocs_table);
>   		table->table = icelake_mocs_table;
>   		result = true;
> +	} else if (IS_GEN(devid, 12)) {

This should be IS_TIGERLAKE for consistency, since all the other lists 
are assigned with checks per-platform rather than per-gen. With that:

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>

Daniele

> +		table->size  = ARRAY_SIZE(tigerlake_mocs_table);
> +		table->table = tigerlake_mocs_table;
> +		result = true;
>   	}
>   
>   	return result;
> 
_______________________________________________
igt-dev mailing list
igt-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/igt-dev

  reply	other threads:[~2019-07-27  0:16 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-25 20:33 [igt-dev] [PATCH 1/5] i915/gem_mocs_settings: log the engine and MOCS index Lucas De Marchi
2019-07-25 20:33 ` [igt-dev] [PATCH 2/5] i915/gem_mocs_settings: do not set undefined entries to PTE Lucas De Marchi
2019-07-26 20:49   ` Daniele Ceraolo Spurio
2019-07-26 20:57     ` Chris Wilson
2019-07-25 20:33 ` [igt-dev] [PATCH 3/5] i915/gem_mocs_settings: add MOCS table for Tiger Lake Lucas De Marchi
2019-07-27  0:16   ` Daniele Ceraolo Spurio [this message]
2019-07-25 20:33 ` [igt-dev] [PATCH 4/5] i915/gem_mocs_settings: fix global MOCS on gen 11 Lucas De Marchi
2019-07-29 20:53   ` Kumar Valsan, Prathap
2019-07-25 20:33 ` [igt-dev] [PATCH 5/5] i915/gem_mocs_settings: add support for Tiger Lake Lucas De Marchi
2019-07-27  0:23   ` Daniele Ceraolo Spurio
2019-07-25 21:12 ` [igt-dev] ✓ Fi.CI.BAT: success for series starting with [1/5] i915/gem_mocs_settings: log the engine and MOCS index Patchwork
2019-07-25 21:45 ` [igt-dev] [PATCH 1/5] " Lucas De Marchi
2019-07-26 12:39 ` [igt-dev] ✓ Fi.CI.IGT: success for series starting with [1/5] " Patchwork
2019-07-26 23:26   ` Daniele Ceraolo Spurio
2019-07-26 23:49     ` Lucas De Marchi
2019-07-26 23:54       ` Daniele Ceraolo Spurio
2019-07-27  0:04         ` Lucas De Marchi
2019-07-26 23:23 ` [igt-dev] [PATCH 1/5] " Daniele Ceraolo Spurio
2019-07-26 23:35   ` Lucas De Marchi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e3a07813-05ca-08fb-d893-8b5f9df72460@intel.com \
    --to=daniele.ceraolospurio@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.