From: Le Ma <le.ma@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: alexander.deucher@amd.com, Le Ma <le.ma@amd.com>,
felix.kuehling@amd.com, lijo.lazar@amd.com,
hawking.zhang@amd.com
Subject: [PATCH 1/1] drm/amdgpu: move the drm client creation behind drm device registration
Date: Thu, 25 Jan 2024 14:18:31 +0800 [thread overview]
Message-ID: <20240125061831.28290-1-le.ma@amd.com> (raw)
This patch is to eliminate interrupt warning below:
"[drm] Fence fallback timer expired on ring sdma0.0".
An early vm pt clearing job is sent to SDMA ahead of interrupt enabled,
introduced by patch below:
- drm/amdkfd: Export DMABufs from KFD using GEM handles
And re-locating the drm client creation following after drm_dev_register
looks like a more proper flow.
Change-Id: I0fece177b78345187068f92a823d96b3b7581140
Signed-off-by: Le Ma <le.ma@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 13 +------------
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 11 +++++++++++
3 files changed, 14 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index add315644773..69eb0f5574d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -139,14 +139,13 @@ static void amdgpu_amdkfd_reset_work(struct work_struct *work)
amdgpu_device_gpu_recover(adev, NULL, &reset_context);
}
-static const struct drm_client_funcs kfd_client_funcs = {
+const struct drm_client_funcs kfd_client_funcs = {
.unregister = drm_client_release,
};
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
{
int i;
int last_valid_bit;
- int ret;
amdgpu_amdkfd_gpuvm_init_mem_limits();
@@ -165,12 +164,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
.enable_mes = adev->enable_mes,
};
- ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd", &kfd_client_funcs);
- if (ret) {
- dev_err(adev->dev, "Failed to init DRM client: %d\n", ret);
- return;
- }
-
/* this is going to have a few of the MSBs set that we need to
* clear
*/
@@ -209,10 +202,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev,
&gpu_resources);
- if (adev->kfd.init_complete)
- drm_client_register(&adev->kfd.client);
- else
- drm_client_release(&adev->kfd.client);
amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 00eed8c10cd4..b2c6f2b3c0fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -40,6 +40,8 @@
extern uint64_t amdgpu_amdkfd_total_mem_size;
+extern const struct drm_client_funcs kfd_client_funcs;
+
enum TLB_FLUSH_TYPE {
TLB_FLUSH_LEGACY = 0,
TLB_FLUSH_LIGHTWEIGHT,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0d0aa4b798ac..d0b98343481d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2293,6 +2293,17 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
drm_fbdev_generic_setup(adev_to_drm(adev), 32);
}
+ if (adev->kfd.init_complete) {
+ ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",
+ &kfd_client_funcs);
+ if (ret) {
+ dev_err(adev->dev, "Failed to init DRM client: %d\n",
+ ret);
+ goto err_pci;
+ }
+ drm_client_register(&adev->kfd.client);
+ }
+
ret = amdgpu_debugfs_init(adev);
if (ret)
DRM_ERROR("Creating debugfs files failed (%d).\n", ret);
--
2.38.1
next reply other threads:[~2024-01-25 6:19 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-25 6:18 Le Ma [this message]
2024-01-25 7:04 ` [PATCH 1/1] drm/amdgpu: move the drm client creation behind drm device registration Lazar, Lijo
2024-01-26 15:42 ` Christian König
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=20240125061831.28290-1-le.ma@amd.com \
--to=le.ma@amd.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=hawking.zhang@amd.com \
--cc=lijo.lazar@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