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, 179 insertions, 9 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1abfe63c80fe..43b18863a8b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -36,9 +36,7 @@
 #include "v9_structs.h"
 #include "soc15.h"
 #include "soc15d.h"
-#include "mmhub_v1_0.h"
-#include "gfxhub_v1_0.h"
-
+#include "gfx_v9_0.h"
 
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
@@ -552,7 +550,7 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
-	if (adev->in_gpu_reset)
+	if (amdgpu_in_reset(adev))
 		return -EIO;
 
 	acquire_queue(kgd, pipe_id, queue_id);
@@ -690,7 +688,7 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 	return 0;
 }
 
-static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
+void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
@@ -701,9 +699,182 @@ static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
 		return;
 	}
 
-	mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	adev->mmhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
+
+	adev->gfxhub.funcs->setup_vm_pt_regs(adev, vmid, page_table_base);
+}
+
+static void lock_spi_csq_mutexes(struct amdgpu_device *adev)
+{
+	mutex_lock(&adev->srbm_mutex);
+	mutex_lock(&adev->grbm_idx_mutex);
+
+}
+
+static void unlock_spi_csq_mutexes(struct amdgpu_device *adev)
+{
+	mutex_unlock(&adev->grbm_idx_mutex);
+	mutex_unlock(&adev->srbm_mutex);
+}
+
+/**
+ * @get_wave_count: Read device registers to get number of waves in flight for
+ * a particular queue. The method also returns the VMID associated with the
+ * queue.
+ *
+ * @adev: Handle of device whose registers are to be read
+ * @queue_idx: Index of queue in the queue-map bit-field
+ * @wave_cnt: Output parameter updated with number of waves in flight
+ * @vmid: Output parameter updated with VMID of queue whose wave count
+ * is being collected
+ */
+static void get_wave_count(struct amdgpu_device *adev, int queue_idx,
+		int *wave_cnt, int *vmid)
+{
+	int pipe_idx;
+	int queue_slot;
+	unsigned int reg_val;
+
+	/*
+	 * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID
+	 * parameters to read out waves in flight. Get VMID if there are
+	 * non-zero waves in flight.
+	 */
+	*vmid = 0xFF;
+	*wave_cnt = 0;
+	pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe;
+	queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe;
+	soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0);
+	reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) +
+			 queue_slot);
+	*wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK;
+	if (*wave_cnt != 0)
+		*vmid = (RREG32_SOC15(GC, 0, mmCP_HQD_VMID) &
+			 CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT;
+}
+
+/**
+ * @kgd_gfx_v9_get_cu_occupancy: Reads relevant registers associated with each
+ * shader engine and aggregates the number of waves that are in flight for the
+ * process whose pasid is provided as a parameter. The process could have ZERO
+ * or more queues running and submitting waves to compute units.
+ *
+ * @kgd: Handle of device from which to get number of waves in flight
+ * @pasid: Identifies the process for which this query call is invoked
+ * @wave_cnt: Output parameter updated with number of waves in flight that
+ * belong to process with given pasid
+ * @max_waves_per_cu: Output parameter updated with maximum number of waves
+ * possible per Compute Unit
+ *
+ * @note: It's possible that the device has too many queues (oversubscription)
+ * in which case a VMID could be remapped to a different PASID. This could lead
+ * to an iaccurate wave count. Following is a high-level sequence:
+ *    Time T1: vmid = getVmid(); vmid is associated with Pasid P1
+ *    Time T2: passId = getPasId(vmid); vmid is associated with Pasid P2
+ * In the sequence above wave count obtained from time T1 will be incorrectly
+ * lost or added to total wave count.
+ *
+ * The registers that provide the waves in flight are:
+ *
+ *  SPI_CSQ_WF_ACTIVE_STATUS - bit-map of queues per pipe. The bit is ON if a
+ *  queue is slotted, OFF if there is no queue. A process could have ZERO or
+ *  more queues slotted and submitting waves to be run on compute units. Even
+ *  when there is a queue it is possible there could be zero wave fronts, this
+ *  can happen when queue is waiting on top-of-pipe events - e.g. waitRegMem
+ *  command
+ *
+ *  For each bit that is ON from above:
+ *
+ *    Read (SPI_CSQ_WF_ACTIVE_COUNT_0 + queue_idx) register. It provides the
+ *    number of waves that are in flight for the queue at specified index. The
+ *    index ranges from 0 to 7.
+ *
+ *    If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID
+ *    of the wave(s).
+ *
+ *    Determine if VMID from above step maps to pasid provided as parameter. If
+ *    it matches agrregate the wave count. That the VMID will not match pasid is
+ *    a normal condition i.e. a device is expected to support multiple queues
+ *    from multiple proceses.
+ *
+ *  Reading registers referenced above involves programming GRBM appropriately
+ */
+static void kgd_gfx_v9_get_cu_occupancy(struct kgd_dev *kgd, int pasid,
+		int *pasid_wave_cnt, int *max_waves_per_cu)
+{
+	int qidx;
+	int vmid;
+	int se_idx;
+	int sh_idx;
+	int se_cnt;
+	int sh_cnt;
+	int wave_cnt;
+	int queue_map;
+	int pasid_tmp;
+	int max_queue_cnt;
+	int vmid_wave_cnt = 0;
+	struct amdgpu_device *adev;
+	DECLARE_BITMAP(cp_queue_bitmap, KGD_MAX_QUEUES);
+
+	adev = get_amdgpu_device(kgd);
+	lock_spi_csq_mutexes(adev);
+	soc15_grbm_select(adev, 1, 0, 0, 0);
+
+	/*
+	 * Iterate through the shader engines and arrays of the device
+	 * to get number of waves in flight
+	 */
+	bitmap_complement(cp_queue_bitmap, adev->gfx.mec.queue_bitmap,
+			  KGD_MAX_QUEUES);
+	max_queue_cnt = adev->gfx.mec.num_pipe_per_mec *
+			adev->gfx.mec.num_queue_per_pipe;
+	sh_cnt = adev->gfx.config.max_sh_per_se;
+	se_cnt = adev->gfx.config.max_shader_engines;
+	for (se_idx = 0; se_idx < se_cnt; se_idx++) {
+		for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) {
+
+			gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff);
+			queue_map = RREG32(SOC15_REG_OFFSET(GC, 0,
+					   mmSPI_CSQ_WF_ACTIVE_STATUS));
+
+			/*
+			 * Assumption: queue map encodes following schema: four
+			 * pipes per each micro-engine, with each pipe mapping
+			 * eight queues. This schema is true for GFX9 devices
+			 * and must be verified for newer device families
+			 */
+			for (qidx = 0; qidx < max_queue_cnt; qidx++) {
+
+				/* Skip qeueus that are not associated with
+				 * compute functions
+				 */
+				if (!test_bit(qidx, cp_queue_bitmap))
+					continue;
+
+				if (!(queue_map & (1 << qidx)))
+					continue;
+
+				/* Get number of waves in flight and aggregate them */
+				get_wave_count(adev, qidx, &wave_cnt, &vmid);
+				if (wave_cnt != 0) {
+					pasid_tmp =
+					  RREG32(SOC15_REG_OFFSET(OSSSYS, 0,
+						 mmIH_VMID_0_LUT) + vmid);
+					if (pasid_tmp == pasid)
+						vmid_wave_cnt += wave_cnt;
+				}
+			}
+		}
+	}
+
+	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	soc15_grbm_select(adev, 0, 0, 0, 0);
+	unlock_spi_csq_mutexes(adev);
 
-	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	/* Update the output parameters and return */
+	*pasid_wave_cnt = vmid_wave_cnt;
+	*max_waves_per_cu = adev->gfx.cu_info.simd_per_cu *
+				adev->gfx.cu_info.max_waves_per_simd;
 }
 
 const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
@@ -726,6 +897,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.get_hive_id = amdgpu_amdkfd_get_hive_id,
-	.get_unique_id = amdgpu_amdkfd_get_unique_id,
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 };