[PATCH 1/2] drm/amdgpu: store noretry parameter per driver instance

[PATCH 1/2] drm/amdgpu: store noretry parameter per driver instance

[Alex Deucher]

This will allow us to have different defaults per asic
in a future patch.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c         |  7 +++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h         |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c         |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c            | 14 ++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h            |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c              |  4 ++--
 drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c           |  2 +-
 drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c           |  2 +-
 drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c           |  2 +-
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c            |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c            |  2 ++
 .../drm/amd/amdkfd/kfd_device_queue_manager_v9.c   |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  2 ++
 16 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 53d5aa2d96bf..3c0e43f548fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -581,6 +581,13 @@ uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd)
 	return adev->rev_id;
 }
 
+int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	return adev->gmc.noretry;
+}
+
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a10507ecb750..bc9f0e42e0a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -181,6 +181,7 @@ uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd);
 uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
+int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
 
 /* Read user wptr from a specified user address space with page fault
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2ff43a3d52fc..70c6593aa634 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1267,6 +1267,8 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 		dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid parameter provided by user\n");
 	}
 
+	amdgpu_gmc_noretry_set(adev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 213ef090bb0e..3572629fef0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -413,6 +413,20 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * amdgpu_noretry_set -- set per asic noretry defaults
+ * @adev: amdgpu_device pointer
+ *
+ * Set a per asic default for the no-retry parameter.
+ *
+ */
+void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
+{
+	struct amdgpu_gmc *gmc = &adev->gmc;
+
+	gmc->noretry = amdgpu_noretry;
+}
+
 void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
 				   bool enable)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index d61bbde4c7d2..aa0c83776ce0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -239,6 +239,7 @@ struct amdgpu_gmc {
 
 	struct amdgpu_xgmi xgmi;
 	struct amdgpu_irq_src	ecc_irq;
+	int noretry;
 };
 
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
@@ -300,6 +301,7 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
 int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
 extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev);
+extern void amdgpu_gmc_noretry_set(struct amdgpu_device *adev);
 
 extern void
 amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index bccaf4f77647..a5aaff15f7ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -177,7 +177,7 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags)
 			break;
 		case CHIP_VEGA10:
 			/* turn runpm on if noretry=0 */
-			if (!amdgpu_noretry)
+			if (!adev->gmc.noretry)
 				adev->runpm = true;
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 4d65cbed31d4..f7958f6603d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2557,14 +2557,14 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
-					    !!amdgpu_noretry);
+					    !!adev->gmc.noretry);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_BASES, 0);
 		} else {
 			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
 					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
 			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
-					    !!amdgpu_noretry);
+					    !!adev->gmc.noretry);
 			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
 			tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE,
 				(adev->gmc.private_aperture_start >> 48));
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 529e46386a50..40b17da6a357 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -245,7 +245,7 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index b882ac59879a..fa279d559b72 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -318,7 +318,7 @@ static void gfxhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index 237a9ff5afa0..6dc7a040ed7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -319,7 +319,7 @@ static void gfxhub_v2_1_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 45a902b1acb7..f84701c562bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -268,7 +268,7 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 2d88278c50bf..4120f9478707 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -374,7 +374,7 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
 				    i * hub->ctx_distance, tmp);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index c2ef8142136e..66748bb01b52 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -330,7 +330,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
 				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
-				    !amdgpu_noretry);
+				    !adev->gmc.noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET +
 				    i * hub->ctx_distance, tmp);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 135001a404bc..903170e59342 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -718,6 +718,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 
 	kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd);
 
+	kfd->noretry = amdgpu_amdkfd_get_noretry(kfd->kgd);
+
 	if (kfd_interrupt_init(kfd)) {
 		dev_err(kfd_device, "Error initializing interrupts\n");
 		goto kfd_interrupt_error;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 309f63a0b34a..eca6331efa94 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -61,7 +61,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (amdgpu_noretry &&
+		if (dqm->dev->noretry &&
 		    !dqm->dev->use_iommu_v2)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 739db04080d0..56f92cfff591 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -317,6 +317,8 @@ struct kfd_dev {
 
 	struct ida doorbell_ida;
 	unsigned int max_doorbell_slices;
+
+	int noretry;
 };
 
 enum kfd_mempool {
-- 
2.25.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 2/2] drm/amdgpu: add an auto setting to the noretry parameter

[Alex Deucher]

This allows us to set different defaults on a per asic basis.  This
way we can enable noretry on dGPUs where it can increase performance
in certain cases and disable it on chips where it can be problematic.

For now the default is 0 for all asics, but we may want to try and
enable it again for newer dGPUs.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |  9 +++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 26 ++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index a4b518211b1f..f3e2fbcfadfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -147,7 +147,7 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
-int amdgpu_noretry;
+int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
 int amdgpu_reset_method = -1; /* auto */
@@ -596,8 +596,13 @@ MODULE_PARM_DESC(mes,
 	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
 module_param_named(mes, amdgpu_mes, int, 0444);
 
+/**
+ * DOC: noretry (int)
+ * Disable retry faults in the GPU memory controller.
+ * (0 = retry enabled, 1 = retry disabled, -1 auto (default))
+ */
 MODULE_PARM_DESC(noretry,
-	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
+	"Disable retry faults (0 = retry enabled, 1 = retry disabled, -1 auto (default))");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 3572629fef0a..36604d751d62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -424,7 +424,31 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
 {
 	struct amdgpu_gmc *gmc = &adev->gmc;
 
-	gmc->noretry = amdgpu_noretry;
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+		/* Raven currently has issues with noretry
+		 * regardless of what we decide for other
+		 * asics, we should leave raven with
+		 * noretry = 0 until we root cause the
+		 * issues.
+		 */
+		if (amdgpu_noretry == -1)
+			gmc->noretry = 0;
+		else
+			gmc->noretry = amdgpu_noretry;
+		break;
+	default:
+		/* default this to 0 for now, but we may want
+		 * to change this in the future for certain
+		 * GPUs as it can increase performance in
+		 * certain cases.
+		 */
+		if (amdgpu_noretry == -1)
+			gmc->noretry = 0;
+		else
+			gmc->noretry = amdgpu_noretry;
+		break;
+	}
 }
 
 void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
-- 
2.25.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 2/2] drm/amdgpu: add an auto setting to the noretry parameter

[Luben Tuikov]

Series is Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>

This is a good change!

Regards,
Luben

On 2020-09-23 10:08, Alex Deucher wrote:
> This allows us to set different defaults on a per asic basis.  This
> way we can enable noretry on dGPUs where it can increase performance
> in certain cases and disable it on chips where it can be problematic.
> 
> For now the default is 0 for all asics, but we may want to try and
> enable it again for newer dGPUs.
> 
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |  9 +++++++--
>  drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 26 ++++++++++++++++++++++++-
>  2 files changed, 32 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index a4b518211b1f..f3e2fbcfadfb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -147,7 +147,7 @@ int amdgpu_async_gfx_ring = 1;
>  int amdgpu_mcbp = 0;
>  int amdgpu_discovery = -1;
>  int amdgpu_mes = 0;
> -int amdgpu_noretry;
> +int amdgpu_noretry = -1;
>  int amdgpu_force_asic_type = -1;
>  int amdgpu_tmz = 0;
>  int amdgpu_reset_method = -1; /* auto */
> @@ -596,8 +596,13 @@ MODULE_PARM_DESC(mes,
>  	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
>  module_param_named(mes, amdgpu_mes, int, 0444);
>  
> +/**
> + * DOC: noretry (int)
> + * Disable retry faults in the GPU memory controller.
> + * (0 = retry enabled, 1 = retry disabled, -1 auto (default))
> + */
>  MODULE_PARM_DESC(noretry,
> -	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
> +	"Disable retry faults (0 = retry enabled, 1 = retry disabled, -1 auto (default))");
>  module_param_named(noretry, amdgpu_noretry, int, 0644);
>  
>  /**
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 3572629fef0a..36604d751d62 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -424,7 +424,31 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
>  {
>  	struct amdgpu_gmc *gmc = &adev->gmc;
>  
> -	gmc->noretry = amdgpu_noretry;
> +	switch (adev->asic_type) {
> +	case CHIP_RAVEN:
> +		/* Raven currently has issues with noretry
> +		 * regardless of what we decide for other
> +		 * asics, we should leave raven with
> +		 * noretry = 0 until we root cause the
> +		 * issues.
> +		 */
> +		if (amdgpu_noretry == -1)
> +			gmc->noretry = 0;
> +		else
> +			gmc->noretry = amdgpu_noretry;
> +		break;
> +	default:
> +		/* default this to 0 for now, but we may want
> +		 * to change this in the future for certain
> +		 * GPUs as it can increase performance in
> +		 * certain cases.
> +		 */
> +		if (amdgpu_noretry == -1)
> +			gmc->noretry = 0;
> +		else
> +			gmc->noretry = amdgpu_noretry;
> +		break;
> +	}
>  }
>  
>  void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
> 

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 1/2] drm/amdgpu: store noretry parameter per driver instance

[Christian König]

Am 23.09.20 um 16:08 schrieb Alex Deucher:
> This will allow us to have different defaults per asic
> in a future patch.
>
> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Looks good to me, Reviewed-by: Christian König 
<christian.koenig@amd.com> for both.

> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c         |  7 +++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h         |  1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c         |  2 ++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c            | 14 ++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h            |  2 ++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c            |  2 +-
>   drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c              |  4 ++--
>   drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c           |  2 +-
>   drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c           |  2 +-
>   drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c           |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c            |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c            |  2 +-
>   drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c            |  2 +-
>   drivers/gpu/drm/amd/amdkfd/kfd_device.c            |  2 ++
>   .../drm/amd/amdkfd/kfd_device_queue_manager_v9.c   |  2 +-
>   drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  2 ++
>   16 files changed, 40 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> index 53d5aa2d96bf..3c0e43f548fb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
> @@ -581,6 +581,13 @@ uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd)
>   	return adev->rev_id;
>   }
>   
> +int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd)
> +{
> +	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
> +
> +	return adev->gmc.noretry;
> +}
> +
>   int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
>   				uint32_t vmid, uint64_t gpu_addr,
>   				uint32_t *ib_cmd, uint32_t ib_len)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> index a10507ecb750..bc9f0e42e0a2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
> @@ -181,6 +181,7 @@ uint64_t amdgpu_amdkfd_get_unique_id(struct kgd_dev *kgd);
>   uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
>   uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
>   uint32_t amdgpu_amdkfd_get_asic_rev_id(struct kgd_dev *kgd);
> +int amdgpu_amdkfd_get_noretry(struct kgd_dev *kgd);
>   uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
>   
>   /* Read user wptr from a specified user address space with page fault
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 2ff43a3d52fc..70c6593aa634 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -1267,6 +1267,8 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
>   		dev_warn(adev->dev, "set kernel compute queue number to 8 due to invalid parameter provided by user\n");
>   	}
>   
> +	amdgpu_gmc_noretry_set(adev);
> +
>   	return 0;
>   }
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> index 213ef090bb0e..3572629fef0a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
> @@ -413,6 +413,20 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
>   	}
>   }
>   
> +/**
> + * amdgpu_noretry_set -- set per asic noretry defaults
> + * @adev: amdgpu_device pointer
> + *
> + * Set a per asic default for the no-retry parameter.
> + *
> + */
> +void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
> +{
> +	struct amdgpu_gmc *gmc = &adev->gmc;
> +
> +	gmc->noretry = amdgpu_noretry;
> +}
> +
>   void amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
>   				   bool enable)
>   {
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> index d61bbde4c7d2..aa0c83776ce0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> @@ -239,6 +239,7 @@ struct amdgpu_gmc {
>   
>   	struct amdgpu_xgmi xgmi;
>   	struct amdgpu_irq_src	ecc_irq;
> +	int noretry;
>   };
>   
>   #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
> @@ -300,6 +301,7 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
>   int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
>   
>   extern void amdgpu_gmc_tmz_set(struct amdgpu_device *adev);
> +extern void amdgpu_gmc_noretry_set(struct amdgpu_device *adev);
>   
>   extern void
>   amdgpu_gmc_set_vm_fault_masks(struct amdgpu_device *adev, int hub_type,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index bccaf4f77647..a5aaff15f7ec 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -177,7 +177,7 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags)
>   			break;
>   		case CHIP_VEGA10:
>   			/* turn runpm on if noretry=0 */
> -			if (!amdgpu_noretry)
> +			if (!adev->gmc.noretry)
>   				adev->runpm = true;
>   			break;
>   		default:
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index 4d65cbed31d4..f7958f6603d7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -2557,14 +2557,14 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
>   			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
>   					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
>   			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
> -					    !!amdgpu_noretry);
> +					    !!adev->gmc.noretry);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_BASES, 0);
>   		} else {
>   			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
>   					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
>   			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
> -					    !!amdgpu_noretry);
> +					    !!adev->gmc.noretry);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
>   			tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE,
>   				(adev->gmc.private_aperture_start >> 48));
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> index 529e46386a50..40b17da6a357 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> @@ -245,7 +245,7 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL,
>   				    i * hub->ctx_distance, tmp);
>   		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> index b882ac59879a..fa279d559b72 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> @@ -318,7 +318,7 @@ static void gfxhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
>   				    i * hub->ctx_distance, tmp);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
> index 237a9ff5afa0..6dc7a040ed7f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
> @@ -319,7 +319,7 @@ static void gfxhub_v2_1_setup_vmid_config(struct amdgpu_device *adev)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL,
>   				    i * hub->ctx_distance, tmp);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> index 45a902b1acb7..f84701c562bf 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> @@ -268,7 +268,7 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL,
>   				    i * hub->ctx_distance, tmp);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> index 2d88278c50bf..4120f9478707 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> @@ -374,7 +374,7 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
>   				    i * hub->ctx_distance, tmp);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> index c2ef8142136e..66748bb01b52 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
> @@ -330,7 +330,7 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
>   				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> -				    !amdgpu_noretry);
> +				    !adev->gmc.noretry);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
>   				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET +
>   				    i * hub->ctx_distance, tmp);
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> index 135001a404bc..903170e59342 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
> @@ -718,6 +718,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
>   
>   	kfd->unique_id = amdgpu_amdkfd_get_unique_id(kfd->kgd);
>   
> +	kfd->noretry = amdgpu_amdkfd_get_noretry(kfd->kgd);
> +
>   	if (kfd_interrupt_init(kfd)) {
>   		dev_err(kfd_device, "Error initializing interrupts\n");
>   		goto kfd_interrupt_error;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> index 309f63a0b34a..eca6331efa94 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> @@ -61,7 +61,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
>   		qpd->sh_mem_config =
>   				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
>   					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
> -		if (amdgpu_noretry &&
> +		if (dqm->dev->noretry &&
>   		    !dqm->dev->use_iommu_v2)
>   			qpd->sh_mem_config |=
>   				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> index 739db04080d0..56f92cfff591 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> @@ -317,6 +317,8 @@ struct kfd_dev {
>   
>   	struct ida doorbell_ida;
>   	unsigned int max_doorbell_slices;
> +
> +	int noretry;
>   };
>   
>   enum kfd_mempool {

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx