Merge tag 'amd-drm-next-5.10-2020-09-03' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.10-2020-09-03:

amdgpu:
- RAS fixes
- Sienna Cichlid updates
- Navy Flounder updates
- DCE6 (SI) support in DC
- Enable plane rotation
- Rework pre-OS vram reservation handling during driver init
- Add standard interface to dump GPU metrics table from SMU
- Rework tiling and tmz state handling in atomic commits
- Pstate fixes
- Add voltage and power hwmon interfaces for renoir
- SW CTF fixes
- S/G display fix for Raven
- Print client strings for vmfaults for vega and newer
- Manual fan control fixes
- Display updates
- Reorg power management directory structure
- Misc bug fixes
- Misc code cleanups

amdkfd:
- Topology fixes
- Add SMI events for thermal throttling and GPU resets

radeon:
- switch from pci_* to dma_* for dma allocations
- PLL fix

Scheduler:
- Clean up priority levels

UAPI:
- amdgpu INFO IOCTL query update for TMZ state
  https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6049
- amdkfd SMI event interface updates
  https://github.com/RadeonOpenCompute/rocm_smi_lib/tree/therm_thrott

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200903222921.4152-1-alexander.deucher@amd.com

1 files changed, 57 insertions, 22 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 81a79760ca61..6edde2b9e402 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -26,6 +26,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_managed.h>
 #include "amdgpu_drv.h"
 
 #include <drm/drm_pciids.h>
@@ -88,9 +89,10 @@
  * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  * - 3.39.0 - DMABUF implicit sync does a full pipeline sync
+ * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	39
+#define KMS_DRIVER_MINOR	40
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -150,12 +152,14 @@ int amdgpu_noretry;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = 0;
 int amdgpu_reset_method = -1; /* auto */
+int amdgpu_num_kcq = -1;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
 };
 int amdgpu_ras_enable = -1;
 uint amdgpu_ras_mask = 0xffffffff;
+int amdgpu_bad_page_threshold = -1;
 
 /**
  * DOC: vramlimit (int)
@@ -676,11 +680,14 @@ MODULE_PARM_DESC(debug_largebar,
  * Ignore CRAT table during KFD initialization. By default, KFD uses the ACPI CRAT
  * table to get information about AMD APUs. This option can serve as a workaround on
  * systems with a broken CRAT table.
+ *
+ * Default is auto (according to asic type, iommu_v2, and crat table, to decide
+ * whehter use CRAT)
  */
 int ignore_crat;
 module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
-	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
+	"Ignore CRAT table during KFD initialization (0 = auto (default), 1 = ignore CRAT)");
 
 /**
  * DOC: halt_if_hws_hang (int)
@@ -715,6 +722,15 @@ MODULE_PARM_DESC(queue_preemption_timeout_ms, "queue preemption timeout in ms (1
 bool debug_evictions;
 module_param(debug_evictions, bool, 0644);
 MODULE_PARM_DESC(debug_evictions, "enable eviction debug messages (false = default)");
+
+/**
+ * DOC: no_system_mem_limit(bool)
+ * Disable system memory limit, to support multiple process shared memory
+ */
+bool no_system_mem_limit;
+module_param(no_system_mem_limit, bool, 0644);
+MODULE_PARM_DESC(no_system_mem_limit, "disable system memory limit (false = default)");
+
 #endif
 
 /**
@@ -765,6 +781,19 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
 MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)");
 module_param_named(reset_method, amdgpu_reset_method, int, 0444);
 
+/**
+ * DOC: bad_page_threshold (int)
+ * Bad page threshold is to specify the threshold value of faulty pages
+ * detected by RAS ECC, that may result in GPU entering bad status if total
+ * faulty pages by ECC exceed threshold value and leave it for user's further
+ * check.
+ */
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement)");
+module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
+
+MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
+module_param_named(num_kcq, amdgpu_num_kcq, int, 0444);
+
 static const struct pci_device_id pciidlist[] = {
 #ifdef  CONFIG_DRM_AMDGPU_SI
 	{0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI},
@@ -1057,7 +1086,7 @@ static struct drm_driver kms_driver;
 static int amdgpu_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
-	struct drm_device *dev;
+	struct drm_device *ddev;
 	struct amdgpu_device *adev;
 	unsigned long flags = ent->driver_data;
 	int ret, retry = 0;
@@ -1113,36 +1142,44 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 	if (ret)
 		return ret;
 
-	dev = drm_dev_alloc(&kms_driver, &pdev->dev);
-	if (IS_ERR(dev))
-		return PTR_ERR(dev);
+	adev = kzalloc(sizeof(*adev), GFP_KERNEL);
+	if (!adev)
+		return -ENOMEM;
+
+	adev->dev  = &pdev->dev;
+	adev->pdev = pdev;
+	ddev = adev_to_drm(adev);
+	ret = drm_dev_init(ddev, &kms_driver, &pdev->dev);
+	if (ret)
+		goto err_free;
+
+	drmm_add_final_kfree(ddev, adev);
 
 	if (!supports_atomic)
-		dev->driver_features &= ~DRIVER_ATOMIC;
+		ddev->driver_features &= ~DRIVER_ATOMIC;
 
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto err_free;
 
-	dev->pdev = pdev;
-
-	pci_set_drvdata(pdev, dev);
+	ddev->pdev = pdev;
+	pci_set_drvdata(pdev, ddev);
 
-	ret = amdgpu_driver_load_kms(dev, ent->driver_data);
+	ret = amdgpu_driver_load_kms(adev, ent->driver_data);
 	if (ret)
 		goto err_pci;
 
 retry_init:
-	ret = drm_dev_register(dev, ent->driver_data);
+	ret = drm_dev_register(ddev, ent->driver_data);
 	if (ret == -EAGAIN && ++retry <= 3) {
 		DRM_INFO("retry init %d\n", retry);
 		/* Don't request EX mode too frequently which is attacking */
 		msleep(5000);
 		goto retry_init;
-	} else if (ret)
+	} else if (ret) {
 		goto err_pci;
+	}
 
-	adev = dev->dev_private;
 	ret = amdgpu_debugfs_init(adev);
 	if (ret)
 		DRM_ERROR("Creating debugfs files failed (%d).\n", ret);
@@ -1152,7 +1189,7 @@ retry_init:
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_put(dev);
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -1176,7 +1213,7 @@ static void
 amdgpu_pci_shutdown(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(dev);
 
 	if (amdgpu_ras_intr_triggered())
 		return;
@@ -1209,7 +1246,7 @@ static int amdgpu_pmops_resume(struct device *dev)
 static int amdgpu_pmops_freeze(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
 	adev->in_hibernate = true;
@@ -1245,7 +1282,7 @@ static int amdgpu_pmops_runtime_suspend(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_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret, i;
 
 	if (!adev->runpm) {
@@ -1296,7 +1333,7 @@ static int amdgpu_pmops_runtime_resume(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_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int ret;
 
 	if (!adev->runpm)
@@ -1332,7 +1369,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 static int amdgpu_pmops_runtime_idle(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = drm_dev->dev_private;
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
 	int ret = 1;
 
@@ -1500,8 +1537,6 @@ static struct pci_driver amdgpu_kms_pci_driver = {
 	.driver.pm = &amdgpu_pm_ops,
 };
 
-
-
 static int __init amdgpu_init(void)
 {
 	int r;