drm/amdgpu: reserve fence slot to update page table

BugLink: https://bugs.launchpad.net/bugs/1927535
commit d42a5b639d15622ece5b9dd12dafd9776efa2593 upstream.

Forgot to reserve a fence slot to use sdma to update page table, cause
below kernel BUG backtrace to handle vm retry fault while application is
exiting.

[  133.048143] kernel BUG at /home/yangp/git/compute_staging/kernel/drivers/dma-buf/dma-resv.c:281!
[  133.048487] Workqueue: events amdgpu_irq_handle_ih1 [amdgpu]
[  133.048506] RIP: 0010:dma_resv_add_shared_fence+0x204/0x280
[  133.048672]  amdgpu_vm_sdma_commit+0x134/0x220 [amdgpu]
[  133.048788]  amdgpu_vm_bo_update_range+0x220/0x250 [amdgpu]
[  133.048905]  amdgpu_vm_handle_fault+0x202/0x370 [amdgpu]
[  133.049031]  gmc_v9_0_process_interrupt+0x1ab/0x310 [amdgpu]
[  133.049165]  ? kgd2kfd_interrupt+0x9a/0x180 [amdgpu]
[  133.049289]  ? amdgpu_irq_dispatch+0xb6/0x240 [amdgpu]
[  133.049408]  amdgpu_irq_dispatch+0xb6/0x240 [amdgpu]
[  133.049534]  amdgpu_ih_process+0x9b/0x1c0 [amdgpu]
[  133.049657]  amdgpu_irq_handle_ih1+0x21/0x60 [amdgpu]
[  133.049669]  process_one_work+0x29f/0x640
[  133.049678]  worker_thread+0x39/0x3f0
[  133.049685]  ? process_one_work+0x640/0x640

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.11.x
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kelsey Skunberg <kelsey.skunberg@canonical.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b24cb44739132c622e9f9b90cc556cef5bdc3924..8090c1e7a3bac853a571dd8afb1d55495f878ded 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3298,7 +3298,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
        struct amdgpu_bo *root;
        uint64_t value, flags;
        struct amdgpu_vm *vm;
-       long r;
+       int r;
 
        spin_lock(&adev->vm_manager.pasid_lock);
        vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
@@ -3347,6 +3347,12 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
                value = 0;
        }
 
+       r = dma_resv_reserve_shared(root->tbo.base.resv, 1);
+       if (r) {
+               pr_debug("failed %d to reserve fence slot\n", r);
+               goto error_unlock;
+       }
+
        r = amdgpu_vm_bo_update_mapping(adev, adev, vm, true, false, NULL, addr,
                                        addr, flags, value, NULL, NULL,
                                        NULL);
@@ -3358,7 +3364,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
 error_unlock:
        amdgpu_bo_unreserve(root);
        if (r < 0)
-               DRM_ERROR("Can't handle page fault (%ld)\n", r);
+               DRM_ERROR("Can't handle page fault (%d)\n", r);
 
 error_unref:
        amdgpu_bo_unref(&root);