Merge tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a major amount of change, the i915 trees got split into display
  and gt trees to better facilitate higher level review, and there's a
  major refactoring of i915 GEM locking to use more core kernel concepts
  (like ww-mutexes). msm gets per-process pagetables, older AMD SI cards
  get DC support, nouveau got a bump in displayport support with common
  code extraction from i915.

  Outside of drm this contains a couple of patches for hexint
  moduleparams which you've acked, and a virtio common code tree that
  you should also get via it's regular path.

  New driver:
   - Cadence MHDP8546 DisplayPort bridge driver

  core:
   - cross-driver scatterlist cleanups
   - devm_drm conversions
   - remove drm_dev_init
   - devm_drm_dev_alloc conversion

  ttm:
   - lots of refactoring and cleanups

  bridges:
   - chained bridge support in more drivers

  panel:
   - misc new panels

  scheduler:
   - cleanup priority levels

  displayport:
   - refactor i915 code into helpers for nouveau

  i915:
   - split into display and GT trees
   - WW locking refactoring in GEM
   - execbuf2 extension mechanism
   - syncobj timeline support
   - GEN 12 HOBL display powersaving
   - Rocket Lake display additions
   - Disable FBC on Tigerlake
   - Tigerlake Type-C + DP improvements
   - Hotplug interrupt refactoring

  amdgpu:
   - Sienna Cichlid updates
   - Navy Flounder updates
   - DCE6 (SI) support for DC
   - Plane rotation enabled
   - TMZ state info ioctl
   - PCIe DPC recovery support
   - DC interrupt handling refactor
   - OLED panel fixes

  amdkfd:
   - add SMI events for thermal throttling
   - SMI interface events ioctl update
   - process eviction counters

  radeon:
   - move to dma_ for allocations
   - expose sclk via sysfs

  msm:
   - DSI support for sm8150/sm8250
   - per-process GPU pagetable support
   - Displayport support

  mediatek:
   - move HDMI phy driver to PHY
   - convert mtk-dpi to bridge API
   - disable mt2701 tmds

  tegra:
   - bridge support

  exynos:
   - misc cleanups

  vc4:
   - dual display cleanups

  ast:
   - cleanups

  gma500:
   - conversion to GPIOd API

  hisilicon:
   - misc reworks

  ingenic:
   - clock handling and format improvements

  mcde:
   - DSI support

  mgag200:
   - desktop g200 support

  mxsfb:
   - i.MX7 + i.MX8M
   - alpha plane support

  panfrost:
   - devfreq support
   - amlogic SoC support

  ps8640:
   - EDID from eDP retrieval

  tidss:
   - AM65xx YUV workaround

  virtio:
   - virtio-gpu exported resources

  rcar-du:
   - R8A7742, R8A774E1 and R8A77961 support
   - YUV planar format fixes
   - non-visible plane handling
   - VSP device reference count fix
   - Kconfig fix to avoid displaying disabled options in .config"

* tag 'drm-next-2020-10-15' of git://anongit.freedesktop.org/drm/drm: (1494 commits)
  drm/ingenic: Fix bad revert
  drm/amdgpu: Fix invalid number of character '{' in amdgpu_acpi_init
  drm/amdgpu: Remove warning for virtual_display
  drm/amdgpu: kfd_initialized can be static
  drm/amd/pm: setup APU dpm clock table in SMU HW initialization
  drm/amdgpu: prevent spurious warning
  drm/amdgpu/swsmu: fix ARC build errors
  drm/amd/display: Fix OPTC_DATA_FORMAT programming
  drm/amd/display: Don't allow pstate if no support in blank
  drm/panfrost: increase readl_relaxed_poll_timeout values
  MAINTAINERS: Update entry for st7703 driver after the rename
  Revert "gpu/drm: ingenic: Add option to mmap GEM buffers cached"
  drm/amd/display: HDMI remote sink need mode validation for Linux
  drm/amd/display: Change to correct unit on audio rate
  drm/amd/display: Avoid set zero in the requested clk
  drm/amdgpu: align frag_end to covered address space
  drm/amdgpu: fix NULL pointer dereference for Renoir
  drm/vmwgfx: fix regression in thp code due to ttm init refactor.
  drm/amdgpu/swsmu: add interrupt work handler for smu11 parts
  drm/amdgpu/swsmu: add interrupt work function
  ...

1 files changed, 81 insertions, 32 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 321032d3a51a..c241317edee7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -26,12 +26,12 @@
 #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>
 #include <linux/console.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
 #include <drm/drm_probe_helper.h>
@@ -88,9 +88,10 @@
  * - 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;
@@ -146,16 +147,18 @@ int amdgpu_async_gfx_ring = 1;
 int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
-int amdgpu_noretry;
+int amdgpu_noretry = -1;
 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)
@@ -393,12 +396,12 @@ MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
 /**
- * DOC: ppfeaturemask (uint)
+ * DOC: ppfeaturemask (hexint)
  * Override power features enabled. See enum PP_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
  * The default is the current set of stable power features.
  */
 MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
-module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
+module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, hexint, 0444);
 
 /**
  * DOC: forcelongtraining (uint)
@@ -593,8 +596,13 @@ MODULE_PARM_DESC(mes,
 	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
 module_param_named(mes, amdgpu_mes, int, 0444);
 
+/**
+ * DOC: noretry (int)
+ * Disable retry faults in the GPU memory controller.
+ * (0 = retry enabled, 1 = retry disabled, -1 auto (default))
+ */
 MODULE_PARM_DESC(noretry,
-	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
+	"Disable retry faults (0 = retry enabled, 1 = retry disabled, -1 auto (default))");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
 /**
@@ -676,11 +684,14 @@ 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 +726,15 @@ 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 +785,19 @@ 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},
@@ -1065,7 +1098,7 @@ 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;
@@ -1081,6 +1114,16 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+	/* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping,
+	 * however, SME requires an indirect IOMMU mapping because the encryption
+	 * bit is beyond the DMA mask of the chip.
+	 */
+	if (mem_encrypt_active() && ((flags & AMD_ASIC_MASK) == CHIP_RAVEN)) {
+		dev_info(&pdev->dev,
+			 "SME is not compatible with RAVEN\n");
+		return -ENOTSUPP;
+	}
+
 #ifdef CONFIG_DRM_AMDGPU_SI
 	if (!amdgpu_si_support) {
 		switch (flags & AMD_ASIC_MASK) {
@@ -1121,36 +1164,39 @@ 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 = devm_drm_dev_alloc(&pdev->dev, &kms_driver, typeof(*adev), ddev);
+	if (IS_ERR(adev))
+		return PTR_ERR(adev);
+
+	adev->dev  = &pdev->dev;
+	adev->pdev = pdev;
+	ddev = adev_to_drm(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;
+		return ret;
 
-	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);
@@ -1159,8 +1205,6 @@ retry_init:
 
 err_pci:
 	pci_disable_device(pdev);
-err_free:
-	drm_dev_put(dev);
 	return ret;
 }
 
@@ -1177,14 +1221,13 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	amdgpu_driver_unload_kms(dev);
 	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
-	drm_dev_put(dev);
 }
 
 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;
@@ -1217,7 +1260,7 @@ 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;
@@ -1253,7 +1296,7 @@ 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) {
@@ -1287,7 +1330,7 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
 		if (amdgpu_is_atpx_hybrid()) {
 			pci_ignore_hotplug(pdev);
 		} else {
-			pci_save_state(pdev);
+			amdgpu_device_cache_pci_state(pdev);
 			pci_disable_device(pdev);
 			pci_ignore_hotplug(pdev);
 			pci_set_power_state(pdev, PCI_D3cold);
@@ -1304,7 +1347,7 @@ 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)
@@ -1320,7 +1363,7 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 			pci_set_master(pdev);
 		} else {
 			pci_set_power_state(pdev, PCI_D0);
-			pci_restore_state(pdev);
+			amdgpu_device_load_pci_state(pdev);
 			ret = pci_enable_device(pdev);
 			if (ret)
 				return ret;
@@ -1340,7 +1383,7 @@ 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;
 
@@ -1499,6 +1542,13 @@ static struct drm_driver kms_driver = {
 	.patchlevel = KMS_DRIVER_PATCHLEVEL,
 };
 
+static struct pci_error_handlers amdgpu_pci_err_handler = {
+	.error_detected	= amdgpu_pci_error_detected,
+	.mmio_enabled	= amdgpu_pci_mmio_enabled,
+	.slot_reset	= amdgpu_pci_slot_reset,
+	.resume		= amdgpu_pci_resume,
+};
+
 static struct pci_driver amdgpu_kms_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
@@ -1506,10 +1556,9 @@ static struct pci_driver amdgpu_kms_pci_driver = {
 	.remove = amdgpu_pci_remove,
 	.shutdown = amdgpu_pci_shutdown,
 	.driver.pm = &amdgpu_pm_ops,
+	.err_handler = &amdgpu_pci_err_handler,
 };
 
-
-
 static int __init amdgpu_init(void)
 {
 	int r;