drm/amd/pm: fix amdgpu_irq enabled counter unbalanced on smu v11.0

v1:
- fix amdgpu_irq enabled counter unbalanced issue on smu_v11_0_disable_thermal_alert.

v2:
- re-enable smu thermal alert to make amdgpu irq counter balance for smu v11.0 if in runpm state

[75582.361561] ------------[ cut here ]------------
[75582.361565] WARNING: CPU: 42 PID: 533 at drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c:639 amdgpu_irq_put+0xd8/0xf0 [amdgpu]
...
[75582.362211] Tainted: [E]=UNSIGNED_MODULE
[75582.362214] Hardware name: GIGABYTE MZ01-CE0-00/MZ01-CE0-00, BIOS F14a 08/14/2020
[75582.362218] Workqueue: pm pm_runtime_work
[75582.362225] RIP: 0010:amdgpu_irq_put+0xd8/0xf0 [amdgpu]
[75582.362556] Code: 31 f6 31 ff e9 c9 bf cf c2 44 89 f2 4c 89 e6 4c 89 ef e8 db fc ff ff 5b 41 5c 41 5d 41 5e 5d 31 d2 31 f6 31 ff e9 a8 bf cf c2 <0f> 0b eb c3 b8 fe ff ff ff eb 97 e9 84 e8 8b 00 0f 1f 84 00 00 00
[75582.362560] RSP: 0018:ffffd50d51297b80 EFLAGS: 00010246
[75582.362564] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000
[75582.362568] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[75582.362570] RBP: ffffd50d51297ba0 R08: 0000000000000000 R09: 0000000000000000
[75582.362573] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8e72091d2008
[75582.362576] R13: ffff8e720af80000 R14: 0000000000000000 R15: ffff8e720af80000
[75582.362579] FS:  0000000000000000(0000) GS:ffff8e9158262000(0000) knlGS:0000000000000000
[75582.362582] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[75582.362585] CR2: 000074869d040c14 CR3: 0000001e37a3e000 CR4: 00000000003506f0
[75582.362588] Call Trace:
[75582.362591]  <TASK>
[75582.362597]  smu_v11_0_disable_thermal_alert+0x17/0x30 [amdgpu]
[75582.362983]  smu_smc_hw_cleanup+0x79/0x4f0 [amdgpu]
[75582.363375]  smu_suspend+0x92/0x110 [amdgpu]
[75582.363762]  ? gfx_v10_0_hw_fini+0xd5/0x150 [amdgpu]
[75582.364098]  amdgpu_ip_block_suspend+0x27/0x80 [amdgpu]
[75582.364377]  ? timer_delete_sync+0x10/0x20
[75582.364384]  amdgpu_device_ip_suspend_phase2+0x190/0x450 [amdgpu]
[75582.364665]  amdgpu_device_suspend+0x1ae/0x2f0 [amdgpu]
[75582.364948]  amdgpu_pmops_runtime_suspend+0xf3/0x1f0 [amdgpu]
[75582.365230]  pci_pm_runtime_suspend+0x6d/0x1f0
[75582.365237]  ? __pfx_pci_pm_runtime_suspend+0x10/0x10
[75582.365242]  __rpm_callback+0x4c/0x190
[75582.365246]  ? srso_return_thunk+0x5/0x5f
[75582.365252]  ? srso_return_thunk+0x5/0x5f
[75582.365256]  ? ktime_get_mono_fast_ns+0x43/0xe0
[75582.365263]  rpm_callback+0x6e/0x80
[75582.365267]  rpm_suspend+0x124/0x5f0
[75582.365271]  ? srso_return_thunk+0x5/0x5f
[75582.365275]  ? __schedule+0x439/0x15e0
[75582.365281]  ? srso_return_thunk+0x5/0x5f
[75582.365285]  ? __queue_delayed_work+0xb8/0x180
[75582.365293]  pm_runtime_work+0xc6/0xe0
[75582.365297]  process_one_work+0x1a1/0x3f0
[75582.365303]  worker_thread+0x2ba/0x3d0
[75582.365309]  kthread+0x107/0x220
[75582.365313]  ? __pfx_worker_thread+0x10/0x10
[75582.365318]  ? __pfx_kthread+0x10/0x10
[75582.365323]  ret_from_fork+0xa2/0x120
[75582.365328]  ? __pfx_kthread+0x10/0x10
[75582.365332]  ret_from_fork_asm+0x1a/0x30
[75582.365343]  </TASK>
[75582.365345] ---[ end trace 0000000000000000 ]---
[75582.365350] amdgpu 0000:05:00.0: amdgpu: Fail to disable thermal alert!
[75582.365379] amdgpu 0000:05:00.0: amdgpu: suspend of IP block <smu> failed -22

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 4a2c3ad0c38a01725d416e8befe41de4b9bf7c0f..4b5706be34e4e03d44c202cfddcb1be9624e5d40 100644 (file)
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1669,9 +1669,12 @@ static int smu_smc_hw_setup(struct smu_context *smu)
                if (adev->in_suspend && smu_is_dpm_running(smu)) {
                        dev_info(adev->dev, "dpm has been enabled\n");
                        ret = smu_system_features_control(smu, true);
-                       if (ret)
+                       if (ret) {
                                dev_err(adev->dev, "Failed system features control!\n");
-                       return ret;
+                               return ret;
+                       }
+
+                       return smu_enable_thermal_alert(smu);
                }
                break;
        default:

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index 78e4186d06cc03ac5e282eb74aa80f406ba3833b..b0d6487171d70d368d57a601c7d5f245074cd05e 100644 (file)
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1022,7 +1022,12 @@ int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 
 int smu_v11_0_disable_thermal_alert(struct smu_context *smu)
 {
-       return amdgpu_irq_put(smu->adev, &smu->irq_source, 0);
+       int ret = 0;
+
+       if (smu->smu_table.thermal_controller_type)
+               ret = amdgpu_irq_put(smu->adev, &smu->irq_source, 0);
+
+       return ret;
 }
 
 static uint16_t convert_to_vddc(uint8_t vid)