[PATCH V3 2/5] drm/amdgpu: Add sysfs interface for sdma reset mask
Jesse.zhang@amd.com
jesse.zhang at amd.com
Thu Oct 24 07:39:30 UTC 2024
From: "Jesse.zhang at amd.com" <Jesse.zhang at amd.com>
Add the sysfs interface for sdma:
sdma_reset_mask
The interface is read-only and show the resets supported by the IP.
For example, full adapter reset (mode1/mode2/BACO/etc),
soft reset, queue reset, and pipe reset.
V2: the sysfs node returns a text string instead of some flags (Christian)
v3: add a generic helper which takes the ring as parameter
and print the strings in the order they are applied (Christian)
check amdgpu_gpu_recovery before creating sysfs file itself,
and initialize supported_reset_types in IP version files (Lijo)
Signed-off-by: Jesse Zhang <Jesse.Zhang at amd.com>
Suggested-by:Alex Deucher <alexander.deucher at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 41 ++++++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h | 3 ++
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 18 +++++++++++
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 23 +++++++++++++
drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 17 ++++++++++
5 files changed, 102 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 183a976ba29d..7edcd989afce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -343,3 +343,44 @@ int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev)
return 0;
}
+
+static ssize_t amdgpu_get_sdma_reset_mask(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct drm_device *ddev = dev_get_drvdata(dev);
+ struct amdgpu_device *adev = drm_to_adev(ddev);
+
+ if (!adev)
+ return -ENODEV;
+
+ return amdgpu_show_reset_mask(buf, adev->sdma.supported_reset);
+}
+
+static DEVICE_ATTR(sdma_reset_mask, 0444,
+ amdgpu_get_sdma_reset_mask, NULL);
+
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+ int r = 0;
+
+ if (!amdgpu_gpu_recovery)
+ return r;
+
+ if (adev->sdma.num_instances) {
+ r = device_create_file(adev->dev, &dev_attr_sdma_reset_mask);
+ if (r)
+ return r;
+ }
+
+ return r;
+}
+
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+ if (!amdgpu_gpu_recovery)
+ return;
+
+ if (adev->sdma.num_instances)
+ device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 087ce0f6fa07..7ce613de7ee0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -116,6 +116,7 @@ struct amdgpu_sdma {
struct ras_common_if *ras_if;
struct amdgpu_sdma_ras *ras;
uint32_t *ip_dump;
+ uint32_t supported_reset;
};
/*
@@ -175,5 +176,7 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, u32 instance,
void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev,
bool duplicate);
int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 6a675daf5620..728643efe203 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1452,6 +1452,19 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
return r;
}
+ switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+ case IP_VERSION(5, 0, 0):
+ case IP_VERSION(5, 0, 2):
+ case IP_VERSION(5, 0, 5):
+ if (adev->sdma.instance[i].fw_version >= 35)
+ adev->sdma.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+ break;
+ default:
+ break;
+ }
+ adev->sdma.supported_reset |=
+ amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+
/* Allocate memory for SDMA IP Dump buffer */
ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
if (ptr)
@@ -1459,6 +1472,10 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
else
DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
+ r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+ if (r)
+ return r;
+
return r;
}
@@ -1470,6 +1487,7 @@ static int sdma_v5_0_sw_fini(struct amdgpu_ip_block *ip_block)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ amdgpu_sdma_sysfs_reset_mask_fini(adev);
amdgpu_sdma_destroy_inst_ctx(adev, false);
kfree(adev->sdma.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index e1413ccaf7e4..38cb5ebe1b7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1357,6 +1357,24 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
return r;
}
+ switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+ case IP_VERSION(5, 2, 0):
+ case IP_VERSION(5, 2, 2):
+ case IP_VERSION(5, 2, 3):
+ case IP_VERSION(5, 2, 4):
+ if (adev->sdma.instance[i].fw_version >= 76)
+ adev->sdma.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+ break;
+ case IP_VERSION(5, 2, 5):
+ if (adev->sdma.instance[i].fw_version >= 34)
+ adev->sdma.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+ break;
+ default:
+ break;
+ }
+ adev->sdma.supported_reset |=
+ amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+
/* Allocate memory for SDMA IP Dump buffer */
ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
if (ptr)
@@ -1364,6 +1382,10 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
else
DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
+ r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+ if (r)
+ return r;
+
return r;
}
@@ -1375,6 +1397,7 @@ static int sdma_v5_2_sw_fini(struct amdgpu_ip_block *ip_block)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ amdgpu_sdma_sysfs_reset_mask_fini(adev);
amdgpu_sdma_destroy_inst_ctx(adev, true);
kfree(adev->sdma.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 4856a093e23f..97c837dbb135 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1351,6 +1351,19 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
return r;
}
+ switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+ case IP_VERSION(6, 0, 0):
+ case IP_VERSION(6, 0, 2):
+ case IP_VERSION(6, 0, 3):
+ if (adev->sdma.instance[i].fw_version >= 21)
+ adev->sdma.supported_reset = AMDGPU_RESET_TYPE_PER_QUEUE;
+ break;
+ default:
+ break;
+ }
+ adev->sdma.supported_reset |=
+ amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+
if (amdgpu_sdma_ras_sw_init(adev)) {
dev_err(adev->dev, "Failed to initialize sdma ras block!\n");
return -EINVAL;
@@ -1366,6 +1379,9 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
#ifdef CONFIG_DRM_AMDGPU_NAVI3X_USERQ
adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_v11_0_funcs;
#endif
+ r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+ if (r)
+ return r;
return r;
}
@@ -1378,6 +1394,7 @@ static int sdma_v6_0_sw_fini(struct amdgpu_ip_block *ip_block)
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+ amdgpu_sdma_sysfs_reset_mask_fini(adev);
amdgpu_sdma_destroy_inst_ctx(adev, true);
kfree(adev->sdma.ip_dump);
--
2.25.1
More information about the amd-gfx
mailing list