drm/amdgpu: disable sdma ecc irq only when sdma RAS is enabled in suspend

Guchun Chen · alexdeucher · commit 8b229ada2669 · 2023-05-11T01:11:51.000-04:00
sdma_v4_0_ip is shared on a few asics, but in sdma_v4_0_hw_fini, driver unconditionally disables ecc_irq which is only enabled on those asics enabling sdma ecc. This will introduce a warning in suspend cycle on those chips with sdma ip v4.0, while without sdma ecc. So this patch correct this. [ 7283.166354] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu] [ 7283.167001] RSP: 0018:ffff9a5fc3967d08 EFLAGS: 00010246 [ 7283.167019] RAX: ffff98d88afd3770 RBX: 0000000000000001 RCX: 0000000000000000 [ 7283.167023] RDX: 0000000000000000 RSI: ffff98d89da30390 RDI: ffff98d89da20000 [ 7283.167025] RBP: ffff98d89da20000 R08: 0000000000036838 R09: 0000000000000006 [ 7283.167028] R10: ffffd5764243c008 R11: 0000000000000000 R12: ffff98d89da30390 [ 7283.167030] R13: ffff98d89da38978 R14: ffffffff999ae15a R15: ffff98d880130105 [ 7283.167032] FS: 0000000000000000(0000) GS:ffff98d996f00000(0000) knlGS:0000000000000000 [ 7283.167036] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7283.167039] CR2: 00000000f7a9d178 CR3: 00000001c42ea000 CR4: 00000000003506e0 [ 7283.167041] Call Trace: [ 7283.167046] <TASK> [ 7283.167048] sdma_v4_0_hw_fini+0x38/0xa0 [amdgpu] [ 7283.167704] amdgpu_device_ip_suspend_phase2+0x101/0x1a0 [amdgpu] [ 7283.168296] amdgpu_device_suspend+0x103/0x180 [amdgpu] [ 7283.168875] amdgpu_pmops_freeze+0x21/0x60 [amdgpu] [ 7283.169464] pci_pm_freeze+0x54/0xc0 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Signed-off-by: Guchun Chen <guchun.chen@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1917,9 +1917,11 @@ static int sdma_v4_0_hw_fini(void *handle)
 		return 0;
 	}
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		amdgpu_irq_put(adev, &adev->sdma.ecc_irq,
-			       AMDGPU_SDMA_IRQ_INSTANCE0 + i);
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
+		for (i = 0; i < adev->sdma.num_instances; i++) {
+			amdgpu_irq_put(adev, &adev->sdma.ecc_irq,
+				       AMDGPU_SDMA_IRQ_INSTANCE0 + i);
+		}
 	}
 
 	sdma_v4_0_ctx_switch_enable(adev, false);

Original file line number	Diff line number	Diff line change
`@@ -1917,9 +1917,11 @@ static int sdma_v4_0_hw_fini(void *handle)`
`1917`	`1917`	`return 0;`
`1918`	`1918`	`}`
`1919`	`1919`
`1920`		`- for (i = 0; i < adev->sdma.num_instances; i++) {`
`1921`		`- amdgpu_irq_put(adev, &adev->sdma.ecc_irq,`
`1922`		`- AMDGPU_SDMA_IRQ_INSTANCE0 + i);`
	`1920`	`+ if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {`
	`1921`	`+ for (i = 0; i < adev->sdma.num_instances; i++) {`
	`1922`	`+ amdgpu_irq_put(adev, &adev->sdma.ecc_irq,`
	`1923`	`+ AMDGPU_SDMA_IRQ_INSTANCE0 + i);`
	`1924`	`+ }`
`1923`	`1925`	`}`
`1924`	`1926`
`1925`	`1927`	`sdma_v4_0_ctx_switch_enable(adev, false);`