This is a note to let you know that I've just added the patch titled
drm/amdkfd: reserve the BO before validating it
to the 6.6-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-amdkfd-reserve-the-bo-before-validating-it.patch
and it can be found in the queue-6.6 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit beb01aaca1374f1f375b329d81e33c937ccf8e77
Author: Lang Yu <Lang.Yu@xxxxxxx>
Date: Thu Jan 11 12:27:07 2024 +0800
drm/amdkfd: reserve the BO before validating it
[ Upstream commit 0c93bd49576677ae1a18817d5ec000ef031d5187 ]
Fix a warning.
v2: Avoid unmapping attachment repeatedly when ERESTARTSYS.
v3: Lock the BO before accessing ttm->sg to avoid race conditions.(Felix)
[ 41.708711] WARNING: CPU: 0 PID: 1463 at drivers/gpu/drm/ttm/ttm_bo.c:846 ttm_bo_validate+0x146/0x1b0 [ttm]
[ 41.708989] Call Trace:
[ 41.708992] <TASK>
[ 41.708996] ? show_regs+0x6c/0x80
[ 41.709000] ? ttm_bo_validate+0x146/0x1b0 [ttm]
[ 41.709008] ? __warn+0x93/0x190
[ 41.709014] ? ttm_bo_validate+0x146/0x1b0 [ttm]
[ 41.709024] ? report_bug+0x1f9/0x210
[ 41.709035] ? handle_bug+0x46/0x80
[ 41.709041] ? exc_invalid_op+0x1d/0x80
[ 41.709048] ? asm_exc_invalid_op+0x1f/0x30
[ 41.709057] ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu]
[ 41.709185] ? ttm_bo_validate+0x146/0x1b0 [ttm]
[ 41.709197] ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu]
[ 41.709337] ? srso_alias_return_thunk+0x5/0x7f
[ 41.709346] kfd_mem_dmaunmap_attachment+0x9e/0x1e0 [amdgpu]
[ 41.709467] amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x56/0x80 [amdgpu]
[ 41.709586] kfd_ioctl_unmap_memory_from_gpu+0x1b7/0x300 [amdgpu]
[ 41.709710] kfd_ioctl+0x1ec/0x650 [amdgpu]
[ 41.709822] ? __pfx_kfd_ioctl_unmap_memory_from_gpu+0x10/0x10 [amdgpu]
[ 41.709945] ? srso_alias_return_thunk+0x5/0x7f
[ 41.709949] ? tomoyo_file_ioctl+0x20/0x30
[ 41.709959] __x64_sys_ioctl+0x9c/0xd0
[ 41.709967] do_syscall_64+0x3f/0x90
[ 41.709973] entry_SYSCALL_64_after_hwframe+0x6e/0xd8
Fixes: 101b8104307e ("drm/amdkfd: Move dma unmapping after TLB flush")
Signed-off-by: Lang Yu <Lang.Yu@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 5e4fb33b97351..db5b1c6beba75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -303,7 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev,
struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv);
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_sync_memory(
struct amdgpu_device *adev, struct kgd_mem *mem, bool intr);
int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index c2d1d57a6c668..9d72bb0a0eaec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2038,21 +2038,35 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
return ret;
}
-void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
+int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv)
{
struct kfd_mem_attachment *entry;
struct amdgpu_vm *vm;
+ int ret;
vm = drm_priv_to_vm(drm_priv);
mutex_lock(&mem->lock);
+ ret = amdgpu_bo_reserve(mem->bo, true);
+ if (ret)
+ goto out;
+
list_for_each_entry(entry, &mem->attachments, list) {
- if (entry->bo_va->base.vm == vm)
- kfd_mem_dmaunmap_attachment(mem, entry);
+ if (entry->bo_va->base.vm != vm)
+ continue;
+ if (entry->bo_va->base.bo->tbo.ttm &&
+ !entry->bo_va->base.bo->tbo.ttm->sg)
+ continue;
+
+ kfd_mem_dmaunmap_attachment(mem, entry);
}
+ amdgpu_bo_unreserve(mem->bo);
+out:
mutex_unlock(&mem->lock);
+
+ return ret;
}
int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 045280c2b607c..9d10530283705 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1442,7 +1442,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
/* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */
- amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+ err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv);
+ if (err)
+ goto sync_memory_failed;
}
mutex_unlock(&p->mutex);
