[PATCH AUTOSEL 6.7 83/88] Revert "drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole"

Sasha Levin sashal at kernel.org
Mon Jan 22 14:51:56 UTC 2024


From: Kaibo Ma <ent3rm4n at gmail.com>

[ Upstream commit 0f35b0a7b8fa402adbffa2565047cdcc4c480153 ]

That commit causes NULL pointer dereferences in dmesgs when
running applications using ROCm, including clinfo, blender,
and PyTorch, since v6.6.1. Revert it to fix blender again.

This reverts commit 96c211f1f9ef82183493f4ceed4e347b52849149.

Closes: https://github.com/ROCm/ROCm/issues/2596
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2991
Reviewed-by: Jay Cornwall <jay.cornwall at amd.com>
Signed-off-by: Kaibo Ma <ent3rm4n at gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
 drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c | 26 ++++++++++----------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index 62b205dac63a..6604a3f99c5e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -330,12 +330,6 @@ static void kfd_init_apertures_vi(struct kfd_process_device *pdd, uint8_t id)
 	pdd->gpuvm_limit =
 		pdd->dev->kfd->shared_resources.gpuvm_size - 1;
 
-	/* dGPUs: the reserved space for kernel
-	 * before SVM
-	 */
-	pdd->qpd.cwsr_base = SVM_CWSR_BASE;
-	pdd->qpd.ib_base = SVM_IB_BASE;
-
 	pdd->scratch_base = MAKE_SCRATCH_APP_BASE_VI();
 	pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
 }
@@ -345,18 +339,18 @@ static void kfd_init_apertures_v9(struct kfd_process_device *pdd, uint8_t id)
 	pdd->lds_base = MAKE_LDS_APP_BASE_V9();
 	pdd->lds_limit = MAKE_LDS_APP_LIMIT(pdd->lds_base);
 
-	pdd->gpuvm_base = PAGE_SIZE;
+        /* Raven needs SVM to support graphic handle, etc. Leave the small
+         * reserved space before SVM on Raven as well, even though we don't
+         * have to.
+         * Set gpuvm_base and gpuvm_limit to CANONICAL addresses so that they
+         * are used in Thunk to reserve SVM.
+         */
+        pdd->gpuvm_base = SVM_USER_BASE;
 	pdd->gpuvm_limit =
 		pdd->dev->kfd->shared_resources.gpuvm_size - 1;
 
 	pdd->scratch_base = MAKE_SCRATCH_APP_BASE_V9();
 	pdd->scratch_limit = MAKE_SCRATCH_APP_LIMIT(pdd->scratch_base);
-
-	/*
-	 * Place TBA/TMA on opposite side of VM hole to prevent
-	 * stray faults from triggering SVM on these pages.
-	 */
-	pdd->qpd.cwsr_base = pdd->dev->kfd->shared_resources.gpuvm_size;
 }
 
 int kfd_init_apertures(struct kfd_process *process)
@@ -413,6 +407,12 @@ int kfd_init_apertures(struct kfd_process *process)
 					return -EINVAL;
 				}
 			}
+
+                        /* dGPUs: the reserved space for kernel
+                         * before SVM
+                         */
+                        pdd->qpd.cwsr_base = SVM_CWSR_BASE;
+                        pdd->qpd.ib_base = SVM_IB_BASE;
 		}
 
 		dev_dbg(kfd_device, "node id %u\n", id);
-- 
2.43.0



More information about the amd-gfx mailing list