From: Shashank Sharma <shashank.sharma@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: Shashank Sharma <shashank.sharma@amd.com>,
Alex Deucher <alexander.deucher@amd.com>,
Christian Koenig <christian.koenig@amd.com>,
Arvind Yadav <arvind.yadav@amd.com>
Subject: [PATCH v11 11/28] drm/amdgpu: enable GFX-V11 userqueue support
Date: Mon, 9 Sep 2024 22:06:02 +0200 [thread overview]
Message-ID: <20240909200614.481-12-shashank.sharma@amd.com> (raw)
In-Reply-To: <20240909200614.481-1-shashank.sharma@amd.com>
This patch enables GFX-v11 IP support in the usermode queue base
code. It typically:
- adds a GFX_v11 specific MQD structure
- sets IP functions to create and destroy MQDs
- sets MQD objects coming from userspace
V10: introduced this spearate patch for GFX V11 enabling (Alex).
V11: Addressed review comments:
- update the comments in GFX mqd structure informing user about using
the INFO IOCTL for object sizes (Alex)
- rename struct drm_amdgpu_userq_mqd_gfx_v11 to
drm_amdgpu_userq_mqd_gfx11 (Marek)
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
Signed-off-by: Arvind Yadav <arvind.yadav@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c | 6 ++++
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 3 ++
.../gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c | 28 +++++++++++++++++++
include/uapi/drm/amdgpu_drm.h | 19 +++++++++++++
4 files changed, 56 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c
index 64a063ec3b27..5cb984c509c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userqueue.c
@@ -188,6 +188,12 @@ amdgpu_userqueue_create(struct drm_file *filp, union drm_amdgpu_userq *args)
uint64_t index;
int qid, r = 0;
+ /* Usermode queues are only supported for GFX IP as of now */
+ if (args->in.ip_type != AMDGPU_HW_IP_GFX) {
+ DRM_ERROR("Usermode queue doesn't support IP type %u\n", args->in.ip_type);
+ return -EINVAL;
+ }
+
if (args->in.flags) {
DRM_ERROR("Usermode queue flags not supported yet\n");
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index d3e8be82a172..e68874fd0ff9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -49,6 +49,7 @@
#include "gfx_v11_0_3.h"
#include "nbio_v4_3.h"
#include "mes_v11_0.h"
+#include "mes_v11_0_userqueue.h"
#define GFX11_NUM_GFX_RINGS 1
#define GFX11_MEC_HPD_SIZE 2048
@@ -1552,6 +1553,7 @@ static int gfx_v11_0_sw_init(void *handle)
adev->gfx.mec.num_mec = 2;
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 4;
+ adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_v11_0_funcs;
break;
case IP_VERSION(11, 0, 1):
case IP_VERSION(11, 0, 4):
@@ -1564,6 +1566,7 @@ static int gfx_v11_0_sw_init(void *handle)
adev->gfx.mec.num_mec = 1;
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 4;
+ adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_v11_0_funcs;
break;
default:
adev->gfx.me.num_me = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
index bc9ce5233a7d..bcfa0d1ef7bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0_userqueue.c
@@ -180,6 +180,34 @@ static int mes_v11_0_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
return r;
}
+ /* Shadow, GDS and CSA objects come directly from userspace */
+ if (mqd_user->ip_type == AMDGPU_HW_IP_GFX) {
+ struct v11_gfx_mqd *mqd = queue->mqd.cpu_ptr;
+ struct drm_amdgpu_userq_mqd_gfx11 *mqd_gfx_v11;
+
+ if (mqd_user->mqd_size != sizeof(*mqd_gfx_v11) || !mqd_user->mqd) {
+ DRM_ERROR("Invalid GFX MQD\n");
+ return -EINVAL;
+ }
+
+ mqd_gfx_v11 = memdup_user(u64_to_user_ptr(mqd_user->mqd), mqd_user->mqd_size);
+ if (IS_ERR(mqd_gfx_v11)) {
+ DRM_ERROR("Failed to read user MQD\n");
+ amdgpu_userqueue_destroy_object(uq_mgr, ctx);
+ return -ENOMEM;
+ }
+
+ mqd->shadow_base_lo = mqd_gfx_v11->shadow_va & 0xFFFFFFFC;
+ mqd->shadow_base_hi = upper_32_bits(mqd_gfx_v11->shadow_va);
+
+ mqd->gds_bkup_base_lo = mqd_gfx_v11->gds_va & 0xFFFFFFFC;
+ mqd->gds_bkup_base_hi = upper_32_bits(mqd_gfx_v11->gds_va);
+
+ mqd->fw_work_area_base_lo = mqd_gfx_v11->csa_va & 0xFFFFFFFC;
+ mqd->fw_work_area_base_hi = upper_32_bits(mqd_gfx_v11->csa_va);
+ kfree(mqd_gfx_v11);
+ }
+
return 0;
}
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index bd8d47a55553..895d64982498 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -409,6 +409,25 @@ union drm_amdgpu_userq {
struct drm_amdgpu_userq_out out;
};
+/* GFX V11 IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_gfx11 {
+ /**
+ * @shadow_va: Virtual address of the GPU memory to hold the shadow buffer.
+ * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+ */
+ __u64 shadow_va;
+ /**
+ * @gds_va: Virtual address of the GPU memory to hold the GDS buffer.
+ * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+ */
+ __u64 gds_va;
+ /**
+ * @csa_va: Virtual address of the GPU memory to hold the CSA buffer.
+ * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+ */
+ __u64 csa_va;
+};
+
/* vm ioctl */
#define AMDGPU_VM_OP_RESERVE_VMID 1
#define AMDGPU_VM_OP_UNRESERVE_VMID 2
--
2.45.1
next prev parent reply other threads:[~2024-09-09 20:07 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-09-09 20:05 [PATCH v11 00/28] AMDGPU usermode queues Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 01/28] drm/amdgpu: UAPI for user queue management Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 02/28] drm/amdgpu: add usermode queue base code Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 03/28] drm/amdgpu: add new IOCTL for usermode queue Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 04/28] drm/amdgpu: add helpers to create userqueue object Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 05/28] drm/amdgpu: create MES-V11 usermode queue for GFX Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 06/28] drm/amdgpu: create context space for usermode queue Shashank Sharma
2024-10-18 17:39 ` Alex Deucher
2024-09-09 20:05 ` [PATCH v11 07/28] drm/amdgpu: map usermode queue into MES Shashank Sharma
2024-09-09 20:05 ` [PATCH v11 08/28] drm/amdgpu: map wptr BO into GART Shashank Sharma
2024-09-16 12:39 ` Christian König
2024-09-09 20:06 ` [PATCH v11 09/28] drm/amdgpu: generate doorbell index for userqueue Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 10/28] drm/amdgpu: cleanup leftover queues Shashank Sharma
2024-09-09 20:06 ` Shashank Sharma [this message]
2024-09-09 20:06 ` [PATCH v11 12/28] drm/amdgpu: enable SDMA usermode queues Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 13/28] drm/amdgpu: enable compute/gfx usermode queue Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 14/28] drm/amdgpu: update userqueue BOs and PDs Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 15/28] drm/amdgpu: add kernel config for gfx-userqueue Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 21/28] drm/amdgpu: add gfx eviction fence helpers Shashank Sharma
2024-09-16 14:14 ` Christian König
2024-09-25 9:08 ` Sharma, Shashank
2024-09-09 20:06 ` [PATCH v11 22/28] drm/amdgpu: add userqueue suspend/resume functions Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 23/28] drm/amdgpu: suspend gfx userqueues Shashank Sharma
2024-09-17 11:58 ` Christian König
2024-09-25 9:13 ` Sharma, Shashank
2024-09-09 20:06 ` [PATCH v11 24/28] drm/amdgpu: resume " Shashank Sharma
2024-09-17 12:30 ` Christian König
2024-09-25 9:15 ` Sharma, Shashank
2024-09-09 20:06 ` [PATCH v11 25/28] drm/amdgpu: Add input fence to sync bo unmap Shashank Sharma
2024-09-09 20:06 ` [PATCH v11 26/28] drm/amdgpu: fix MES GFX mask Shashank Sharma
2024-09-17 12:21 ` Christian König
2024-09-09 20:06 ` [PATCH v11 27/28] Revert "drm/amdgpu/gfx11: only enable CP GFX shadowing on SR-IOV" Shashank Sharma
2024-09-09 20:31 ` Alex Deucher
2024-09-11 9:20 ` Sharma, Shashank
2024-09-09 20:06 ` [PATCH v11 28/28] Revert "drm/amdgpu: don't allow userspace to create a doorbell BO" Shashank Sharma
2024-09-17 12:25 ` Christian König
2024-09-19 16:59 ` [PATCH v11 00/28] AMDGPU usermode queues Alex Deucher
2024-09-25 9:14 ` Sharma, Shashank
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=20240909200614.481-12-shashank.sharma@amd.com \
--to=shashank.sharma@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=arvind.yadav@amd.com \
--cc=christian.koenig@amd.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