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, 51 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 922ae138ab85..c77cf23032ac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -297,6 +297,9 @@ struct kfd_dev {
 
 	bool pci_atomic_requested;
 
+	/* Use IOMMU v2 flag */
+	bool use_iommu_v2;
+
 	/* SRAM ECC flag */
 	atomic_t sram_ecc_flag;
 
@@ -309,6 +312,13 @@ struct kfd_dev {
 	/* Clients watching SMI events */
 	struct list_head smi_clients;
 	spinlock_t smi_lock;
+
+	uint32_t reset_seq_num;
+
+	struct ida doorbell_ida;
+	unsigned int max_doorbell_slices;
+
+	int noretry;
 };
 
 enum kfd_mempool {
@@ -626,7 +636,7 @@ enum kfd_pdd_bound {
 	PDD_BOUND_SUSPENDED,
 };
 
-#define MAX_SYSFS_FILENAME_LEN 11
+#define MAX_SYSFS_FILENAME_LEN 15
 
 /*
  * SDMA counter runs at 100MHz frequency.
@@ -687,6 +697,39 @@ struct kfd_process_device {
 	uint64_t sdma_past_activity_counter;
 	struct attribute attr_sdma;
 	char sdma_filename[MAX_SYSFS_FILENAME_LEN];
+
+	/* Eviction activity tracking */
+	uint64_t last_evict_timestamp;
+	atomic64_t evict_duration_counter;
+	struct attribute attr_evict;
+
+	struct kobject *kobj_stats;
+	unsigned int doorbell_index;
+
+	/*
+	 * @cu_occupancy: Reports occupancy of Compute Units (CU) of a process
+	 * that is associated with device encoded by "this" struct instance. The
+	 * value reflects CU usage by all of the waves launched by this process
+	 * on this device. A very important property of occupancy parameter is
+	 * that its value is a snapshot of current use.
+	 *
+	 * Following is to be noted regarding how this parameter is reported:
+	 *
+	 *  The number of waves that a CU can launch is limited by couple of
+	 *  parameters. These are encoded by struct amdgpu_cu_info instance
+	 *  that is part of every device definition. For GFX9 devices this
+	 *  translates to 40 waves (simd_per_cu * max_waves_per_simd) when waves
+	 *  do not use scratch memory and 32 waves (max_scratch_slots_per_cu)
+	 *  when they do use scratch memory. This could change for future
+	 *  devices and therefore this example should be considered as a guide.
+	 *
+	 *  All CU's of a device are available for the process. This may not be true
+	 *  under certain conditions - e.g. CU masking.
+	 *
+	 *  Finally number of CU's that are occupied by a process is affected by both
+	 *  number of CU's a device has along with number of other competing processes
+	 */
+	struct attribute attr_cu_occupancy;
 };
 
 #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd)
@@ -724,7 +767,6 @@ struct kfd_process {
 	struct mmu_notifier mmu_notifier;
 
 	u32 pasid;
-	unsigned int doorbell_index;
 
 	/*
 	 * List of kfd_process_device structures,
@@ -857,13 +899,13 @@ u32 read_kernel_doorbell(u32 __iomem *db);
 void write_kernel_doorbell(void __iomem *db, u32 value);
 void write_kernel_doorbell64(void __iomem *db, u64 value);
 unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
-					struct kfd_process *process,
+					struct kfd_process_device *pdd,
 					unsigned int doorbell_id);
-phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
-					struct kfd_process *process);
-int kfd_alloc_process_doorbells(struct kfd_process *process);
-void kfd_free_process_doorbells(struct kfd_process *process);
-
+phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd);
+int kfd_alloc_process_doorbells(struct kfd_dev *kfd,
+				unsigned int *doorbell_index);
+void kfd_free_process_doorbells(struct kfd_dev *kfd,
+				unsigned int doorbell_index);
 /* GTT Sub-Allocator */
 
 int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
@@ -892,6 +934,7 @@ struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
 struct kfd_dev *kfd_device_by_kgd(const struct kgd_dev *kgd);
 int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);
 int kfd_numa_node_to_apic_id(int numa_node_id);
+void kfd_double_confirm_iommu_support(struct kfd_dev *gpu);
 
 /* Interrupts */
 int kfd_interrupt_init(struct kfd_dev *dev);