drm/amd/pm: Disable MMIO access during SMU Mode 1 reset

During Mode 1 reset, the ASIC undergoes a reset cycle and becomes
temporarily inaccessible via PCIe. Any attempt to access MMIO registers
during this window (e.g., from interrupt handlers or other driver threads)
can result in uncompleted PCIe transactions, leading to NMI panics or
system hangs.

To prevent this, set the `no_hw_access` flag to true immediately after
triggering the reset. This signals other driver components to skip
register accesses while the device is offline.

A memory barrier `smp_mb()` is added to ensure the flag update is
globally visible to all cores before the driver enters the sleep/wait
state.

Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7edb503fe4b6d67f47d8bb0dfafb8e699bb0f8a4)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 12201b8..25f49be 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5867,6 +5867,9 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
        if (ret)
                goto mode1_reset_failed;
 
+       /* enable mmio access after mode 1 reset completed */
+       adev->no_hw_access = false;
+
        amdgpu_device_load_pci_state(adev->pdev);
        ret = amdgpu_psp_wait_for_bootloader(adev);
        if (ret)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 6777810..eaeff6a 100644 (file)
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2923,8 +2923,13 @@ static int smu_v13_0_0_mode1_reset(struct smu_context *smu)
                break;
        }
 
-       if (!ret)
+       if (!ret) {
+               /* disable mmio access while doing mode 1 reset*/
+               smu->adev->no_hw_access = true;
+               /* ensure no_hw_access is globally visible before any MMIO */
+               smp_mb();
                msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS);
+       }
 
        return ret;
 }

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 2cea688..33c3cd2 100644 (file)
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -2143,10 +2143,15 @@ static int smu_v14_0_2_mode1_reset(struct smu_context *smu)
 
        ret = smu_cmn_send_debug_smc_msg(smu, DEBUGSMC_MSG_Mode1Reset);
        if (!ret) {
-               if (amdgpu_emu_mode == 1)
+               if (amdgpu_emu_mode == 1) {
                        msleep(50000);
-               else
+               } else {
+                       /* disable mmio access while doing mode 1 reset*/
+                       smu->adev->no_hw_access = true;
+                       /* ensure no_hw_access is globally visible before any MMIO */
+                       smp_mb();
                        msleep(1000);
+               }
        }
 
        return ret;