amd-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Alex Deucher <alexander.deucher@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: Alex Deucher <alexander.deucher@amd.com>
Subject: [PATCH 03/11] drm/amdgpu/UAPI: add new CS chunk for GFX shadow buffers
Date: Mon, 20 Mar 2023 13:38:02 -0400	[thread overview]
Message-ID: <20230320173810.250835-4-alexander.deucher@amd.com> (raw)
In-Reply-To: <20230320173810.250835-1-alexander.deucher@amd.com>

For GFX11, the UMD needs to allocate some shadow buffers
to be used for preemption.  The UMD allocates the buffers
and passes the GPU virtual address to the kernel since the
kernel will program the packet that specified these
addresses as part of its IB submission frame.

v2: UMD passes shadow init to tell kernel when to initialize
    the shadow

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/uapi/drm/amdgpu_drm.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index b6eb90df5d05..3d9474af6566 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -592,6 +592,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES	0x07
 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT    0x08
 #define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL  0x09
+#define AMDGPU_CHUNK_ID_CP_GFX_SHADOW   0x0a
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -708,6 +709,15 @@ struct drm_amdgpu_cs_chunk_data {
 	};
 };
 
+#define AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW         0x1
+
+struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
+	__u64 shadow_va;
+	__u64 csa_va;
+	__u64 gds_va;
+	__u64 flags;
+};
+
 /*
  *  Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU
  *
-- 
2.39.2


  parent reply	other threads:[~2023-03-20 17:38 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-20 17:37 [PATCH V2 00/11] Enable FW assisted shadowing for GFX11 Alex Deucher
2023-03-20 17:38 ` [PATCH 01/11] drm/amdgpu/gfx11: add FW version check for new CP GFX shadow feature Alex Deucher
2023-03-20 17:38 ` [PATCH 02/11] drm/amdgpu/gfx11: check the CP FW version CP GFX shadow support Alex Deucher
2023-03-21 15:36   ` Christian König
2023-03-20 17:38 ` Alex Deucher [this message]
2023-03-20 17:38 ` [PATCH 04/11] drm/amdgpu: add gfx shadow CS IOCTL support Alex Deucher
2023-03-20 17:38 ` [PATCH 05/11] drm/amdgpu: add gfx11 emit shadow callback Alex Deucher
2023-03-20 17:38 ` [PATCH 06/11] drm/amdgpu: don't require a job for cond_exec and shadow Alex Deucher
2023-03-20 17:38 ` [PATCH 07/11] drm/amdgpu: add UAPI to query GFX shadow sizes Alex Deucher
2023-03-21  0:29   ` Marek Olšák
2023-03-21 19:51     ` Alex Deucher
2023-03-22 14:11       ` Marek Olšák
2023-03-22 14:34         ` Alex Deucher
2023-03-21  0:31   ` Marek Olšák
2023-03-21 19:53     ` Alex Deucher
2023-03-22  8:50       ` Christian König
2023-03-22 14:07       ` Marek Olšák
2023-03-20 17:38 ` [PATCH 08/11] drm/amdgpu: add gfx shadow callback Alex Deucher
2023-03-20 17:38 ` [PATCH 09/11] drm/amdgpu: add get_gfx_shadow_info callback for gfx11 Alex Deucher
2023-03-20 17:38 ` [PATCH 10/11] drm/amdgpu: add support for new GFX shadow size query Alex Deucher
2023-03-20 17:38 ` [PATCH 11/11] drm/amdgpu: bump driver version number for CP GFX shadow Alex Deucher

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=20230320173810.250835-4-alexander.deucher@amd.com \
    --to=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    /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;
as well as URLs for NNTP newsgroup(s).