Merge tag 'amd-drm-fixes-6.3-2023-03-23' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.3-2023-03-23:

amdgpu:
- S4 fix
- Soft reset fixes
- SR-IOV fix
- Remove an out of date comment in the DC code
- ASPM fix
- DCN 3.2 fixes

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230323161939.7751-1-alexander.deucher@amd.com

11 files changed, 72 insertions, 41 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 164141bc8b4a..39018f784f9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1272,6 +1272,7 @@ void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
 int amdgpu_device_pci_reset(struct amdgpu_device *adev);
 bool amdgpu_device_need_post(struct amdgpu_device *adev);
 bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
+bool amdgpu_device_aspm_support_quirk(void);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
@@ -1391,10 +1392,12 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta
 int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
 
 void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps);
+bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev);
 void amdgpu_acpi_detect(void);
 #else
 static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
 static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
+static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; }
 static inline void amdgpu_acpi_detect(void) { }
 static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; }
 static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
@@ -1405,11 +1408,9 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev,
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND)
 bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev);
-bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev);
 bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev);
 #else
 static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; }
-static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; }
 static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; }
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index d4196fcb85a0..60b1857f469e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -971,6 +971,29 @@ static bool amdgpu_atcs_pci_probe_handle(struct pci_dev *pdev)
 	return true;
 }
 
+
+/**
+ * amdgpu_acpi_should_gpu_reset
+ *
+ * @adev: amdgpu_device_pointer
+ *
+ * returns true if should reset GPU, false if not
+ */
+bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
+{
+	if (adev->flags & AMD_IS_APU)
+		return false;
+
+	if (amdgpu_sriov_vf(adev))
+		return false;
+
+#if IS_ENABLED(CONFIG_SUSPEND)
+	return pm_suspend_target_state != PM_SUSPEND_TO_IDLE;
+#else
+	return true;
+#endif
+}
+
 /*
  * amdgpu_acpi_detect - detect ACPI ATIF/ATCS methods
  *
@@ -1043,24 +1066,6 @@ bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_acpi_should_gpu_reset
- *
- * @adev: amdgpu_device_pointer
- *
- * returns true if should reset GPU, false if not
- */
-bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev)
-{
-	if (adev->flags & AMD_IS_APU)
-		return false;
-
-	if (amdgpu_sriov_vf(adev))
-		return false;
-
-	return pm_suspend_target_state != PM_SUSPEND_TO_IDLE;
-}
-
-/**
  * amdgpu_acpi_is_s0ix_active
  *
  * @adev: amdgpu_device_pointer
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index da5b0258a237..3d98fc2ad36b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,6 +80,10 @@
 
 #include <drm/drm_drv.h>
 
+#if IS_ENABLED(CONFIG_X86)
+#include <asm/intel-family.h>
+#endif
+
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -1356,6 +1360,17 @@ bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev)
 	return pcie_aspm_enabled(adev->pdev);
 }
 
+bool amdgpu_device_aspm_support_quirk(void)
+{
+#if IS_ENABLED(CONFIG_X86)
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
+#else
+	return true;
+#endif
+}
+
 /* if we get transitioned to only one device, take VGA back */
 /**
  * amdgpu_device_vga_set_decode - enable/disable vga decode
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index f5ffca24def4..ba5def374368 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2467,7 +2467,10 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	adev->in_s4 = false;
 	if (r)
 		return r;
-	return amdgpu_asic_reset(adev);
+
+	if (amdgpu_acpi_should_gpu_reset(adev))
+		return amdgpu_asic_reset(adev);
+	return 0;
 }
 
 static int amdgpu_pmops_thaw(struct device *dev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index faff4a3f96e6..f52d0ba91a77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -678,6 +678,15 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
 		ptr = &ring->fence_drv.fences[i];
 		old = rcu_dereference_protected(*ptr, 1);
 		if (old && old->ops == &amdgpu_job_fence_ops) {
+			struct amdgpu_job *job;
+
+			/* For non-scheduler bad job, i.e. failed ib test, we need to signal
+			 * it right here or we won't be able to track them in fence_drv
+			 * and they will remain unsignaled during sa_bo free.
+			 */
+			job = container_of(old, struct amdgpu_job, hw_fence);
+			if (!job->base.s_fence && !dma_fence_is_signaled(old))
+				dma_fence_signal(old);
 			RCU_INIT_POINTER(*ptr, NULL);
 			dma_fence_put(old);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 3bf697a80cf2..ecf8ceb53311 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1287,6 +1287,11 @@ static int gfx_v11_0_sw_init(void *handle)
 		break;
 	}
 
+	/* Enable CG flag in one VF mode for enabling RLC safe mode enter/exit */
+	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 3) &&
+		amdgpu_sriov_is_pp_one_vf(adev))
+		adev->cg_flags = AMD_CG_SUPPORT_GFX_CGCG;
+
 	/* EOP Event */
 	r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP,
 			      GFX_11_0_0__SRCID__CP_EOP_INTERRUPT,
@@ -4655,6 +4660,14 @@ static bool gfx_v11_0_check_soft_reset(void *handle)
 	return false;
 }
 
+static int gfx_v11_0_post_soft_reset(void *handle)
+{
+	/**
+	 * GFX soft reset will impact MES, need resume MES when do GFX soft reset
+	 */
+	return amdgpu_mes_resume((struct amdgpu_device *)handle);
+}
+
 static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
 	uint64_t clock;
@@ -6166,6 +6179,7 @@ static const struct amd_ip_funcs gfx_v11_0_ip_funcs = {
 	.wait_for_idle = gfx_v11_0_wait_for_idle,
 	.soft_reset = gfx_v11_0_soft_reset,
 	.check_soft_reset = gfx_v11_0_check_soft_reset,
+	.post_soft_reset = gfx_v11_0_post_soft_reset,
 	.set_clockgating_state = gfx_v11_0_set_clockgating_state,
 	.set_powergating_state = gfx_v11_0_set_powergating_state,
 	.get_clockgating_state = gfx_v11_0_get_clockgating_state,
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 22e25ca285f8..ebe0e2d7dbd1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -578,7 +578,7 @@ static void nv_pcie_gen3_enable(struct amdgpu_device *adev)
 
 static void nv_program_aspm(struct amdgpu_device *adev)
 {
-	if (!amdgpu_device_should_use_aspm(adev))
+	if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_aspm_support_quirk())
 		return;
 
 	if (!(adev->flags & AMD_IS_APU) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 12ef782eb478..ceab8783575c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -81,10 +81,6 @@
 #include "mxgpu_vi.h"
 #include "amdgpu_dm.h"
 
-#if IS_ENABLED(CONFIG_X86)
-#include <asm/intel-family.h>
-#endif
-
 #define ixPCIE_LC_L1_PM_SUBSTATE	0x100100C6
 #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK	0x00000001L
 #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK	0x00000002L
@@ -1138,24 +1134,13 @@ static void vi_enable_aspm(struct amdgpu_device *adev)
 		WREG32_PCIE(ixPCIE_LC_CNTL, data);
 }
 
-static bool aspm_support_quirk_check(void)
-{
-#if IS_ENABLED(CONFIG_X86)
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
-#else
-	return true;
-#endif
-}
-
 static void vi_program_aspm(struct amdgpu_device *adev)
 {
 	u32 data, data1, orig;
 	bool bL1SS = false;
 	bool bClkReqSupport = true;
 
-	if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check())
+	if (!amdgpu_device_should_use_aspm(adev) || !amdgpu_device_aspm_support_quirk())
 		return;
 
 	if (adev->flags & AMD_IS_APU ||
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 32abbafd43fa..a01fd41643fc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7244,7 +7244,6 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	if (!aconnector->mst_root)
 		drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16);
 
-	/* This defaults to the max in the range, but we want 8bpc for non-edp. */
 	aconnector->base.state->max_bpc = 16;
 	aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
index e4472c6be6c3..3fb4bcc34353 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
@@ -271,8 +271,7 @@ static void dccg32_set_dpstreamclk(
 	dccg32_set_dtbclk_p_src(dccg, src, otg_inst);
 
 	/* enabled to select one of the DTBCLKs for pipe */
-	switch (otg_inst)
-	{
+	switch (dp_hpo_inst) {
 	case 0:
 		REG_UPDATE_2(DPSTREAMCLK_CNTL,
 			     DPSTREAMCLK0_EN,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index d024007f0f65..4b7abb4af623 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -2186,6 +2186,7 @@ static bool dcn32_resource_construct(
 	dc->caps.edp_dsc_support = true;
 	dc->caps.extended_aux_timeout_support = true;
 	dc->caps.dmcub_support = true;
+	dc->caps.seamless_odm = true;
 
 	/* Color pipeline capabilities */
 	dc->caps.color.dpp.dcn_arch = 1;