Merge drm/drm-next into drm-intel-gt-next

Daniele needs 84d4333c1e28 ("misc/mei: Add NULL check to component match
callback functions") in order to merge the DG2 HuC patches.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

1 files changed, 161 insertions, 86 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b03663f42cc9..16f6a313335e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -38,7 +38,6 @@
 #include <linux/mmu_notifier.h>
 #include <linux/suspend.h>
 #include <linux/cc_platform.h>
-#include <linux/fb.h>
 
 #include "amdgpu.h"
 #include "amdgpu_irq.h"
@@ -81,7 +80,7 @@
  * - 3.24.0 - Add high priority compute support for gfx9
  * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk).
  * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE.
- * - 3.27.0 - Add new chunk to to AMDGPU_CS to enable BO_LIST creation.
+ * - 3.27.0 - Add new chunk to AMDGPU_CS to enable BO_LIST creation.
  * - 3.28.0 - Add AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES
  * - 3.29.0 - Add AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID
  * - 3.30.0 - Add AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE.
@@ -100,10 +99,13 @@
  * - 3.43.0 - Add device hot plug/unplug support
  * - 3.44.0 - DCN3 supports DCC independent block settings: !64B && 128B, 64B && 128B
  * - 3.45.0 - Add context ioctl stable pstate interface
- * * 3.46.0 - To enable hot plug amdgpu tests in libdrm
+ * - 3.46.0 - To enable hot plug amdgpu tests in libdrm
+ * - 3.47.0 - Add AMDGPU_GEM_CREATE_DISCARDABLE and AMDGPU_VM_NOALLOC flags
+ * - 3.48.0 - Add IP discovery version info to HW INFO
+ *   3.49.0 - Add gang submit into CS IOCTL
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	46
+#define KMS_DRIVER_MINOR	49
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit;
@@ -136,7 +138,7 @@ int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
 uint amdgpu_pcie_gen_cap;
 uint amdgpu_pcie_lane_cap;
-uint amdgpu_cg_mask = 0xffffffff;
+u64 amdgpu_cg_mask = 0xffffffffffffffff;
 uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
@@ -167,10 +169,12 @@ int amdgpu_smu_pptable_id = -1;
  */
 uint amdgpu_dc_feature_mask = 2;
 uint amdgpu_dc_debug_mask;
+uint amdgpu_dc_visual_confirm;
 int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp;
 int amdgpu_discovery = -1;
 int amdgpu_mes;
+int amdgpu_mes_kiq;
 int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = -1; /* auto */
@@ -306,7 +310,7 @@ module_param_named(dpm, amdgpu_dpm, int, 0444);
  * to -1 to select the default loading mode for the ASIC, as defined
  * by the driver.  The default is -1 (auto).
  */
-MODULE_PARM_DESC(fw_load_type, "firmware loading type (0 = force direct if supported, -1 = auto)");
+MODULE_PARM_DESC(fw_load_type, "firmware loading type (3 = rlc backdoor autoload if supported, 2 = smu load if supported, 1 = psp load, 0 = force direct if supported, -1 = auto)");
 module_param_named(fw_load_type, amdgpu_fw_load_type, int, 0444);
 
 /**
@@ -454,12 +458,12 @@ MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
 module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
 
 /**
- * DOC: cg_mask (uint)
+ * DOC: cg_mask (ullong)
  * Override Clockgating features enabled on GPU (0 = disable clock gating). See the AMD_CG_SUPPORT flags in
- * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffffffffffff (all enabled).
  */
 MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)");
-module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444);
+module_param_named(cg_mask, amdgpu_cg_mask, ullong, 0444);
 
 /**
  * DOC: pg_mask (uint)
@@ -637,6 +641,15 @@ MODULE_PARM_DESC(mes,
 module_param_named(mes, amdgpu_mes, int, 0444);
 
 /**
+ * DOC: mes_kiq (int)
+ * Enable Micro Engine Scheduler KIQ. This is a new engine pipe for kiq.
+ * (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mes_kiq,
+	"Enable Micro Engine Scheduler KIQ (0 = disabled (default), 1 = enabled)");
+module_param_named(mes_kiq, amdgpu_mes_kiq, int, 0444);
+
+/**
  * DOC: noretry (int)
  * Disable XNACK retry in the SQ by default on GFXv9 hardware. On ASICs that
  * do not support per-process XNACK this also disables retry page faults.
@@ -793,6 +806,16 @@ module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm
 #endif
 
 /**
+ * DOC: pcie_p2p (bool)
+ * Enable PCIe P2P (requires large-BAR). Default value: true (on)
+ */
+#ifdef CONFIG_HSA_AMD_P2P
+bool pcie_p2p = true;
+module_param(pcie_p2p, bool, 0444);
+MODULE_PARM_DESC(pcie_p2p, "Enable PCIe P2P (requires large-BAR). (N = off, Y = on(default))");
+#endif
+
+/**
  * DOC: dcfeaturemask (uint)
  * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
  * The default is the current set of stable display features.
@@ -807,6 +830,9 @@ module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444);
 MODULE_PARM_DESC(dcdebugmask, "all debug options disabled (default))");
 module_param_named(dcdebugmask, amdgpu_dc_debug_mask, uint, 0444);
 
+MODULE_PARM_DESC(visualconfirm, "Visual confirm (0 = off (default), 1 = MPO, 5 = PSR)");
+module_param_named(visualconfirm, amdgpu_dc_visual_confirm, uint, 0444);
+
 /**
  * DOC: abmlevel (uint)
  * Override the default ABM (Adaptive Backlight Management) level used for DC
@@ -1931,6 +1957,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x7422, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+	{0x1002, 0x7424, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 	{0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
 
 	{ PCI_DEVICE(0x1002, PCI_ANY_ID),
@@ -1950,26 +1977,6 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static const struct drm_driver amdgpu_kms_driver;
 
-static bool amdgpu_is_fw_framebuffer(resource_size_t base,
-				     resource_size_t size)
-{
-	bool found = false;
-#if IS_REACHABLE(CONFIG_FB)
-	struct apertures_struct *a;
-
-	a = alloc_apertures(1);
-	if (!a)
-		return false;
-
-	a->ranges[0].base = base;
-	a->ranges[0].size = size;
-
-	found = is_firmware_framebuffer(a);
-	kfree(a);
-#endif
-	return found;
-}
-
 static void amdgpu_get_secondary_funcs(struct amdgpu_device *adev)
 {
 	struct pci_dev *p = NULL;
@@ -2000,8 +2007,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	unsigned long flags = ent->driver_data;
 	int ret, retry = 0, i;
 	bool supports_atomic = false;
-	bool is_fw_fb;
-	resource_size_t base, size;
 
 	/* skip devices which are owned by radeon */
 	for (i = 0; i < ARRAY_SIZE(amdgpu_unsupported_pciidlist); i++) {
@@ -2068,10 +2073,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	}
 #endif
 
-	base = pci_resource_start(pdev, 0);
-	size = pci_resource_len(pdev, 0);
-	is_fw_fb = amdgpu_is_fw_framebuffer(base, size);
-
 	/* Get rid of things like offb */
 	ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
 	if (ret)
@@ -2084,7 +2085,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	adev->dev  = &pdev->dev;
 	adev->pdev = pdev;
 	ddev = adev_to_drm(adev);
-	adev->is_fw_fb = is_fw_fb;
 
 	if (!supports_atomic)
 		ddev->driver_features &= ~DRIVER_ATOMIC;
@@ -2127,7 +2127,7 @@ retry_init:
 	if (ret)
 		DRM_ERROR("Creating debugfs files failed (%d).\n", ret);
 
-	if (adev->runpm) {
+	if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) {
 		/* only need to skip on ATPX */
 		if (amdgpu_device_supports_px(ddev))
 			dev_pm_set_driver_flags(ddev->dev, DPM_FLAG_NO_DIRECT_COMPLETE);
@@ -2182,15 +2182,46 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
-	drm_dev_unplug(dev);
-
-	if (adev->runpm) {
+	if (adev->pm.rpm_mode != AMDGPU_RUNPM_NONE) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
 	}
 
+	if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2)) {
+		bool need_to_reset_gpu = false;
+
+		if (adev->gmc.xgmi.num_physical_nodes > 1) {
+			struct amdgpu_hive_info *hive;
+
+			hive = amdgpu_get_xgmi_hive(adev);
+			if (hive->device_remove_count == 0)
+				need_to_reset_gpu = true;
+			hive->device_remove_count++;
+			amdgpu_put_xgmi_hive(hive);
+		} else {
+			need_to_reset_gpu = true;
+		}
+
+		/* Workaround for ASICs need to reset SMU.
+		 * Called only when the first device is removed.
+		 */
+		if (need_to_reset_gpu) {
+			struct amdgpu_reset_context reset_context;
+
+			adev->shutdown = true;
+			memset(&reset_context, 0, sizeof(reset_context));
+			reset_context.method = AMD_RESET_METHOD_NONE;
+			reset_context.reset_req_dev = adev;
+			set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+			set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags);
+			amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+		}
+	}
+
 	amdgpu_driver_unload_kms(dev);
 
+	drm_dev_unplug(dev);
+
 	/*
 	 * Flush any in flight DMA operations from device.
 	 * Clear the Bus Master Enable bit and then wait on the PCIe Device
@@ -2323,18 +2354,23 @@ static int amdgpu_pmops_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
-	int r;
 
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
 	else
 		adev->in_s3 = true;
-	r = amdgpu_device_suspend(drm_dev, true);
-	if (r)
-		return r;
-	if (!adev->in_s0ix)
-		r = amdgpu_asic_reset(adev);
-	return r;
+	return amdgpu_device_suspend(drm_dev, true);
+}
+
+static int amdgpu_pmops_suspend_noirq(struct device *dev)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+
+	if (amdgpu_acpi_should_gpu_reset(adev))
+		return amdgpu_asic_reset(adev);
+
+	return 0;
 }
 
 static int amdgpu_pmops_resume(struct device *dev)
@@ -2390,6 +2426,71 @@ static int amdgpu_pmops_restore(struct device *dev)
 	return amdgpu_device_resume(drm_dev, true);
 }
 
+static int amdgpu_runtime_idle_check_display(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+
+	if (adev->mode_info.num_crtc) {
+		struct drm_connector *list_connector;
+		struct drm_connector_list_iter iter;
+		int ret = 0;
+
+		/* XXX: Return busy if any displays are connected to avoid
+		 * possible display wakeups after runtime resume due to
+		 * hotplug events in case any displays were connected while
+		 * the GPU was in suspend.  Remove this once that is fixed.
+		 */
+		mutex_lock(&drm_dev->mode_config.mutex);
+		drm_connector_list_iter_begin(drm_dev, &iter);
+		drm_for_each_connector_iter(list_connector, &iter) {
+			if (list_connector->status == connector_status_connected) {
+				ret = -EBUSY;
+				break;
+			}
+		}
+		drm_connector_list_iter_end(&iter);
+		mutex_unlock(&drm_dev->mode_config.mutex);
+
+		if (ret)
+			return ret;
+
+		if (amdgpu_device_has_dc_support(adev)) {
+			struct drm_crtc *crtc;
+
+			drm_for_each_crtc(crtc, drm_dev) {
+				drm_modeset_lock(&crtc->mutex, NULL);
+				if (crtc->state->active)
+					ret = -EBUSY;
+				drm_modeset_unlock(&crtc->mutex);
+				if (ret < 0)
+					break;
+			}
+		} else {
+			mutex_lock(&drm_dev->mode_config.mutex);
+			drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL);
+
+			drm_connector_list_iter_begin(drm_dev, &iter);
+			drm_for_each_connector_iter(list_connector, &iter) {
+				if (list_connector->dpms ==  DRM_MODE_DPMS_ON) {
+					ret = -EBUSY;
+					break;
+				}
+			}
+
+			drm_connector_list_iter_end(&iter);
+
+			drm_modeset_unlock(&drm_dev->mode_config.connection_mutex);
+			mutex_unlock(&drm_dev->mode_config.mutex);
+		}
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int amdgpu_pmops_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -2397,11 +2498,15 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret, i;
 
-	if (!adev->runpm) {
+	if (adev->pm.rpm_mode == AMDGPU_RUNPM_NONE) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
+	ret = amdgpu_runtime_idle_check_display(dev);
+	if (ret)
+		return ret;
+
 	/* wait for all rings to drain before suspending */
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -2462,7 +2567,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret;
 
-	if (!adev->runpm)
+	if (adev->pm.rpm_mode == AMDGPU_RUNPM_NONE)
 		return -EINVAL;
 
 	/* Avoids registers access if device is physically gone */
@@ -2490,8 +2595,11 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 		amdgpu_device_baco_exit(drm_dev);
 	}
 	ret = amdgpu_device_resume(drm_dev, false);
-	if (ret)
+	if (ret) {
+		if (amdgpu_device_supports_px(drm_dev))
+			pci_disable_device(pdev);
 		return ret;
+	}
 
 	if (amdgpu_device_supports_px(drm_dev))
 		drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
@@ -2506,46 +2614,12 @@ static int amdgpu_pmops_runtime_idle(struct device *dev)
 	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
 	int ret = 1;
 
-	if (!adev->runpm) {
+	if (adev->pm.rpm_mode == AMDGPU_RUNPM_NONE) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
-	if (amdgpu_device_has_dc_support(adev)) {
-		struct drm_crtc *crtc;
-
-		drm_for_each_crtc(crtc, drm_dev) {
-			drm_modeset_lock(&crtc->mutex, NULL);
-			if (crtc->state->active)
-				ret = -EBUSY;
-			drm_modeset_unlock(&crtc->mutex);
-			if (ret < 0)
-				break;
-		}
-
-	} else {
-		struct drm_connector *list_connector;
-		struct drm_connector_list_iter iter;
-
-		mutex_lock(&drm_dev->mode_config.mutex);
-		drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL);
-
-		drm_connector_list_iter_begin(drm_dev, &iter);
-		drm_for_each_connector_iter(list_connector, &iter) {
-			if (list_connector->dpms ==  DRM_MODE_DPMS_ON) {
-				ret = -EBUSY;
-				break;
-			}
-		}
-
-		drm_connector_list_iter_end(&iter);
-
-		drm_modeset_unlock(&drm_dev->mode_config.connection_mutex);
-		mutex_unlock(&drm_dev->mode_config.mutex);
-	}
-
-	if (ret == -EBUSY)
-		DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
+	ret = amdgpu_runtime_idle_check_display(dev);
 
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_autosuspend(dev);
@@ -2575,6 +2649,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = {
 	.prepare = amdgpu_pmops_prepare,
 	.complete = amdgpu_pmops_complete,
 	.suspend = amdgpu_pmops_suspend,
+	.suspend_noirq = amdgpu_pmops_suspend_noirq,
 	.resume = amdgpu_pmops_resume,
 	.freeze = amdgpu_pmops_freeze,
 	.thaw = amdgpu_pmops_thaw,