drm/amdgpu: Fix kernel panic during driver load failure

Avoid kernel panic if MES init fails during driver load. The KIQ ring is
falsely marked as ready as ASICs that use MES, KIQ is owned by MES.

BUG: kernel NULL pointer dereference, address: 0000000000000000
RIP: 0010:gfx_v12_1_wait_reg_mem+0x5a/0x1f0 [amdgpu]
Call Trace:
 gfx_v12_1_ring_emit_reg_write_reg_wait+0x1f/0x30 [amdgpu]
 amdgpu_gmc_fw_reg_write_reg_wait+0xb2/0x190 [amdgpu]
 amdgpu_gmc_flush_gpu_tlb+0x1cc/0x230 [amdgpu]
 amdgpu_gart_invalidate_tlb+0x81/0xa0 [amdgpu]
 amdgpu_gart_unbind+0x72/0x90 [amdgpu]
 amdgpu_ttm_backend_unbind+0xa4/0xb0 [amdgpu]
 amdgpu_ttm_tt_unpopulate+0x13/0xd0 [amdgpu]
 amdttm_tt_unpopulate+0x29/0x70 [amdttm]
 ttm_bo_put+0x1eb/0x360 [amdttm]
 amdgpu_bo_free_kernel+0xf9/0x1f0 [amdgpu]
 amdgpu_ih_ring_fini+0x5a/0x90 [amdgpu]
 amdgpu_irq_fini_hw+0x58/0x80 [amdgpu]
 amdgpu_device_fini_hw+0x4e0/0x5b0 [amdgpu]
 amdgpu_driver_load_kms+0x60/0xa0 [amdgpu]
 amdgpu_pci_probe+0x28e/0x6d0 [amdgpu]
 pci_device_probe+0x19f/0x220
 really_probe+0x1ed/0x340
 driver_probe_device+0x1e/0x80
 __driver_attach+0xd3/0x1a0
 bus_for_each_dev+0x68/0xa0
 bus_add_driver+0x19f/0x270
 driver_register+0x5d/0xf0
 do_one_initcall+0xac/0x200
 do_init_module+0x1ec/0x280
 __se_sys_finit_module+0x2de/0x310
 do_syscall_64+0x6a/0x250
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4623b958dd6da0f4c3026afdf330626a09ecb0f0)
Cc: stable@vger.kernel.org

2 files changed, 22 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 3f3b1754c038..da668a8d6abd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3519,10 +3519,19 @@ static int gfx_v12_0_cp_resume(struct amdgpu_device *adev)
 		gfx_v12_0_cp_gfx_enable(adev, true);
 	}
 
-	if (adev->enable_mes_kiq && adev->mes.kiq_hw_init)
+	if (adev->enable_mes_kiq && adev->mes.kiq_hw_init) {
 		r = amdgpu_mes_kiq_hw_init(adev, 0);
-	else
+		/*
+		 * With MES, GFX KIQ ring is owned by the MES and is never
+		 * initialized/used directly by the driver, so it must
+		 * not be left flagged as ready. mes_v12_0_hw_init() clears
+		 * but clear here if MES init fails
+		*/
+		if (r)
+			adev->gfx.kiq[0].ring.sched.ready = false;
+	} else {
 		r = gfx_v12_0_kiq_resume(adev);
+	}
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
index 02c9cda186ee..e7e9f11b9754 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_1.c
@@ -2547,10 +2547,19 @@ static int gfx_v12_1_xcc_cp_resume(struct amdgpu_device *adev, uint16_t xcc_mask
 
 		gfx_v12_1_xcc_cp_compute_enable(adev, true, xcc_id);
 
-		if (adev->enable_mes_kiq && adev->mes.kiq_hw_init)
+		if (adev->enable_mes_kiq && adev->mes.kiq_hw_init) {
 			r = amdgpu_mes_kiq_hw_init(adev, xcc_id);
-		else
+			/*
+			 * With MES, GFX KIQ ring is owned by the MES and is never
+			 * initialized/used directly by the driver, so it must
+			 * not be left flagged as ready. mes_v12_0_hw_init() clears
+			 * but clear here if MES init fails
+			 */
+			if (r)
+				adev->gfx.kiq[xcc_id].ring.sched.ready = false;
+		} else {
 			r = gfx_v12_1_xcc_kiq_resume(adev, xcc_id);
+		}
 		if (r)
 			return r;