Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Souza, Jose" <jose.souza@intel.com>
To: "intel-xe@lists.freedesktop.org" <intel-xe@lists.freedesktop.org>,
	"Mishra, Pallavi" <pallavi.mishra@intel.com>,
	"Roper, Matthew D" <matthew.d.roper@intel.com>
Subject: Re: [PATCH v2] drm/xe/xe2: Enable Priority Mem Read
Date: Thu, 30 May 2024 17:00:36 +0000	[thread overview]
Message-ID: <ce9f3893305f99323f79f0ee39f179543f11483f.camel@intel.com> (raw)
In-Reply-To: <20240530062509.1529357-1-pallavi.mishra@intel.com>

On Thu, 2024-05-30 at 11:55 +0530, Pallavi Mishra wrote:
> Enable feature to allow memory reads to take a
> priority memory path. This will reduce latency
> on the read path, but may introduce read after
> write (RAW) hazards as read and writes will no
> longer be ordered.
> 
> To avoid RAW hazards, SW can use the MI_MEM_FENCE
> command or any other MI command that generates
> non posted memory writes. This will ensure data
> is coherent in memory prior to execution of
> commands which read data from memory.

This has the potential to cause issues in UMDs, Mesa for example don't have any MI_MEM_FENCE instruction in the code base.

So please before merging this sync with all UMDs or merge it behind a run-time or build time parameter with it disabled by default.

> 
> No pattern identified in KMD that could lead to a
> hazard.
> 
> v2: Modify commit message, enable priority mem
> read feature for media, modify version range,
> modify bspec detail (Matt Roper)
> 
> Bspec: 60298, 60237, 60187, 60188
> 
> Signed-off-by: Pallavi Mishra <pallavi.mishra@intel.com>
> ---
>  drivers/gpu/drm/xe/regs/xe_engine_regs.h |  1 +
>  drivers/gpu/drm/xe/xe_hw_engine.c        | 11 +++++++++++
>  2 files changed, 12 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> index 263ffc7bc2ef..4e8f9a61f0bf 100644
> --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
> @@ -104,6 +104,7 @@
>  #define CSFE_CHICKEN1(base)			XE_REG((base) + 0xd4, XE_REG_OPTION_MASKED)
>  #define   GHWSP_CSB_REPORT_DIS			REG_BIT(15)
>  #define   PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS	REG_BIT(14)
> +#define   CS_PRIORITY_MEM_READ			REG_BIT(7)
>  
>  #define FF_SLICE_CS_CHICKEN1(base)		XE_REG((base) + 0xe0, XE_REG_OPTION_MASKED)
>  #define   FFSC_PERCTX_PREEMPT_CTRL		REG_BIT(14)
> diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
> index 9eef789be897..f03e5cc9063e 100644
> --- a/drivers/gpu/drm/xe/xe_hw_engine.c
> +++ b/drivers/gpu/drm/xe/xe_hw_engine.c
> @@ -424,6 +424,17 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe)
>  					   0xA,
>  					   XE_RTP_ACTION_FLAG(ENGINE_BASE)))
>  		},
> +		/* Enable Priority Mem Read */
> +		{ XE_RTP_NAME("Priority_Mem_Read"),
> +		  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, XE_RTP_END_VERSION_UNDEFINED)),
> +		  XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ,
> +				     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
> +		},
> +		{ XE_RTP_NAME("Priority_Mem_Read_For_Media"),
> +		  XE_RTP_RULES(MEDIA_VERSION_RANGE(1301, XE_RTP_END_VERSION_UNDEFINED)),
> +		  XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0), CS_PRIORITY_MEM_READ,
> +				     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
> +		},
>  		{}
>  	};
>  


  parent reply	other threads:[~2024-05-30 17:01 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-30  6:25 [PATCH v2] drm/xe/xe2: Enable Priority Mem Read Pallavi Mishra
2024-05-30  6:21 ` ✓ CI.Patch_applied: success for drm/xe/xe2: Enable Priority Mem Read (rev2) Patchwork
2024-05-30  6:21 ` ✓ CI.checkpatch: " Patchwork
2024-05-30  6:22 ` ✓ CI.KUnit: " Patchwork
2024-05-30  6:34 ` ✓ CI.Build: " Patchwork
2024-05-30  6:34 ` ✗ CI.Hooks: failure " Patchwork
2024-05-30  6:35 ` ✓ CI.checksparse: success " Patchwork
2024-05-30  6:59 ` ✓ CI.BAT: " Patchwork
2024-05-30  7:51 ` ✗ CI.FULL: failure " Patchwork
2024-05-30 16:49 ` [PATCH v2] drm/xe/xe2: Enable Priority Mem Read Matt Roper
2024-05-30 17:00 ` Souza, Jose [this message]
2024-05-31 21:09   ` Matt Roper
2024-06-03 13:20     ` Souza, Jose
2024-06-10  2:31 ` ✓ CI.Patch_applied: success for drm/xe/xe2: Enable Priority Mem Read (rev3) Patchwork
2024-06-10  2:31 ` ✓ CI.checkpatch: " Patchwork
2024-06-10  2:32 ` ✓ CI.KUnit: " Patchwork
2024-06-10  2:44 ` ✓ CI.Build: " Patchwork
2024-06-10  2:46 ` ✓ CI.Hooks: " Patchwork
2024-06-10  2:47 ` ✓ CI.checksparse: " Patchwork
2024-06-10  3:29 ` ✓ CI.BAT: " Patchwork
2024-06-10  4:45 ` ✗ CI.FULL: failure " Patchwork
2024-07-10 17:31 ` [PATCH v2] drm/xe/xe2: Enable Priority Mem Read Souza, Jose
2024-07-11  3:48   ` Zhang, Carl

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=ce9f3893305f99323f79f0ee39f179543f11483f.camel@intel.com \
    --to=jose.souza@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.d.roper@intel.com \
    --cc=pallavi.mishra@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox