From: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Date: Tue, 9 Dec 2025 18:47:09 +0000 (-0500)
Subject: drm/amdkfd: Limit per-process xnack support for GFX12.1
X-Git-Tag: v7.2-rc1~141^2~24^2~100
X-Git-Url: http://git.ipfire.org/gitweb/index.cgi?a=commitdiff_plain;h=05c0109e12e1f0f4a731a26bdd4b8618847bfabe;p=thirdparty%2Fkernel%2Flinux.git

drm/amdkfd: Limit per-process xnack support for GFX12.1

GFX12.1 doesn't support different processes with different xnack
setting. Hence, xnack changes from its default setting needs driver
reload with noretry module parameter.

However, if driver boots-up with xnack on and process sets xnack off,
this condition is supported. In this case, only driver takes xnack off
path whereas hardware / firmware considers xnack is on.

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Philip.Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12_1.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12_1.c
index 9e70a5f8a50b0..5259893713782 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12_1.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v12_1.c
@@ -54,6 +54,7 @@ static int update_qpd_v12_1(struct device_queue_manager *dqm,
 	struct kfd_process_device *pdd;
 	struct amdgpu_device *adev = dqm->dev->adev;
 	struct amdgpu_vmhub *hub = &adev->vmhub[AMDGPU_GFXHUB(0)];
+	bool xnack_enabled;
 
 	pdd = qpd_to_pdd(qpd);
 	qpd->vm_cntx_cntl = hub->vm_cntx_cntl;
@@ -71,16 +72,18 @@ static int update_qpd_v12_1(struct device_queue_manager *dqm,
 		qpd->sh_mem_ape1_base = 0;
 	}
 
-	if (KFD_SUPPORT_XNACK_PER_PROCESS(dqm->dev)) {
-		if (!pdd->process->xnack_enabled) {
-			qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
-			qpd->vm_cntx_cntl &=
+	xnack_enabled = KFD_SUPPORT_XNACK_PER_PROCESS(dqm->dev) ?
+			pdd->process->xnack_enabled :
+			!pdd->dev->kfd->noretry;
+
+	if (!xnack_enabled) {
+		qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
+		qpd->vm_cntx_cntl &=
 			~(1 << GCVM_CONTEXT0_CNTL__RETRY_PERMISSION_OR_INVALID_PAGE_FAULT__SHIFT);
-		} else {
-			qpd->sh_mem_config &= ~(1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT);
-			qpd->vm_cntx_cntl |=
+	} else {
+		qpd->sh_mem_config &= ~(1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT);
+		qpd->vm_cntx_cntl |=
 			(1 << GCVM_CONTEXT0_CNTL__RETRY_PERMISSION_OR_INVALID_PAGE_FAULT__SHIFT);
-		}
 	}
 
 	qpd->sh_mem_bases = compute_sh_mem_bases_64bit(pdd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6e333bfa17d62..39b06544460c5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -215,8 +215,7 @@ enum cache_policy {
 	((KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2)) ||	\
 	 (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 3)) ||	\
 	 (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 4)) ||	\
-	 (KFD_GC_VERSION(dev) == IP_VERSION(9, 5, 0)) ||	\
-	 (KFD_GC_VERSION(dev) == IP_VERSION(12, 1, 0)))
+	 (KFD_GC_VERSION(dev) == IP_VERSION(9, 5, 0)))
 
 struct kfd_node;