Merge tag 'drm-for-v4.13' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm, I think I've got one later
  driver pull for mediatek SoC driver, I'm undecided on if it needs to
  go to you yet.

  Otherwise summary below:

  Core drm:
   - Atomic add driver private objects
   - Deprecate preclose hook in modern drivers
   - MST bandwidth tracking
   - Use kvmalloc in more places
   - Add mode_valid hook for crtc/encoder/bridge
   - Reduce sync_file construction time
   - Documentation updates
   - New DRM synchronisation object support

  New drivers:
   - pl111 - pl111 CLCD display controller

  Panel:
   - Innolux P079ZCA panel driver
   - Add NL12880B20-05, NL192108AC18-02D, P320HVN03 panels
   - panel-samsung-s6e3ha2: Add s6e3hf2 panel support

  i915:
   - SKL+ watermark fixes
   - G4x/G33 reset improvements
   - DP AUX backlight improvements
   - Buffer based GuC/host communication
   - New getparam for (sub)slice infomation
   - Cannonlake and Coffeelake initial patches
   - Execbuf optimisations

  radeon/amdgpu:
   - Lots of Vega10 bug fixes
   - Preliminary raven support
   - KIQ support for compute rings
   - MEC queue management rework
   - DCE6 Audio support
   - SR-IOV improvements
   - Better radeon/amdgpu selection support

  nouveau:
   - HDMI stereoscopic support
   - Display code rework for >= GM20x GPUs

  msm:
   - GEM rework for fine-grained locking
   - Per-process pagetable work
   - HDMI fixes for Snapdragon 820.

  vc4:
   - Remove 256MB CMA limit from vc4
   - Add out-fence support
   - Add support for cygnus
   - Get/set tiling ioctls support
   - Add T-format tiling support for scanout

  zte:
   - add VGA support.

  etnaviv:
   - Thermal throttle support for newer GPUs
   - Restore userspace buffer cache performance
   - dma-buf sync fix

  stm:
   - add stm32f429 display support

  exynos:
   - Rework vblank handling
   - Fixup sw-trigger code

  sun4i:
   - V3s display engine support
   - HDMI support for older SoCs
   - Preliminary work on dual-pipeline SoCs.

  rcar-du:
   - VSP work

  imx-drm:
   - Remove counter load enable from PRE
   - Double read/write reduction flag support

  tegra:
   - Documentation for the host1x and drm driver.
   - Lots of staging ioctl fixes due to grate project work.

  omapdrm:
   - dma-buf fence support
   - TILER rotation fixes"

* tag 'drm-for-v4.13' of git://people.freedesktop.org/~airlied/linux: (1270 commits)
  drm: Remove unused drm_file parameter to drm_syncobj_replace_fence()
  drm/amd/powerplay: fix bug fail to remove sysfs when rmmod amdgpu.
  amdgpu: Set cik/si_support to 1 by default if radeon isn't built
  drm/amdgpu/gfx9: fix driver reload with KIQ
  drm/amdgpu/gfx8: fix driver reload with KIQ
  drm/amdgpu: Don't call amd_powerplay_destroy() if we don't have powerplay
  drm/ttm: Fix use-after-free in ttm_bo_clean_mm
  drm/amd/amdgpu: move get memory type function from early init to sw init
  drm/amdgpu/cgs: always set reference clock in mode_info
  drm/amdgpu: fix vblank_time when displays are off
  drm/amd/powerplay: power value format change for Vega10
  drm/amdgpu/gfx9: support the amdgpu.disable_cu option
  drm/amd/powerplay: change PPSMC_MSG_GetCurrPkgPwr for Vega10
  drm/amdgpu: Make amdgpu_cs_parser_init static (v2)
  drm/amdgpu/cs: fix a typo in a comment
  drm/amdgpu: Fix the exported always on CU bitmap
  drm/amdgpu/gfx9: gfx_v9_0_enable_gfx_static_mg_power_gating() can be static
  drm/amdgpu/psp: upper_32_bits/lower_32_bits for address setup
  drm/amd/powerplay/cz: print message if smc message fails
  drm/amdgpu: fix typo in amdgpu_debugfs_test_ib_init
  ...

1 files changed, 63 insertions, 38 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index dba8a5b25e66..5f8ada1d872b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -24,6 +24,7 @@
 #include "amd_shared.h"
 #include <drm/drmP.h>
 #include "amdgpu.h"
+#include "amdgpu_gfx.h"
 #include <linux/module.h>
 
 const struct kfd2kgd_calls *kfd2kgd;
@@ -60,9 +61,9 @@ int amdgpu_amdkfd_init(void)
 	return ret;
 }
 
-bool amdgpu_amdkfd_load_interface(struct amdgpu_device *rdev)
+bool amdgpu_amdkfd_load_interface(struct amdgpu_device *adev)
 {
-	switch (rdev->asic_type) {
+	switch (adev->asic_type) {
 #ifdef CONFIG_DRM_AMDGPU_CIK
 	case CHIP_KAVERI:
 		kfd2kgd = amdgpu_amdkfd_gfx_7_get_functions();
@@ -86,59 +87,83 @@ void amdgpu_amdkfd_fini(void)
 	}
 }
 
-void amdgpu_amdkfd_device_probe(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
 	if (kgd2kfd)
-		rdev->kfd = kgd2kfd->probe((struct kgd_dev *)rdev,
-					rdev->pdev, kfd2kgd);
+		adev->kfd = kgd2kfd->probe((struct kgd_dev *)adev,
+					adev->pdev, kfd2kgd);
 }
 
-void amdgpu_amdkfd_device_init(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 {
-	if (rdev->kfd) {
+	int i;
+	int last_valid_bit;
+	if (adev->kfd) {
 		struct kgd2kfd_shared_resources gpu_resources = {
 			.compute_vmid_bitmap = 0xFF00,
-
-			.first_compute_pipe = 1,
-			.compute_pipe_count = 4 - 1,
+			.num_mec = adev->gfx.mec.num_mec,
+			.num_pipe_per_mec = adev->gfx.mec.num_pipe_per_mec,
+			.num_queue_per_pipe = adev->gfx.mec.num_queue_per_pipe
 		};
 
-		amdgpu_doorbell_get_kfd_info(rdev,
+		/* this is going to have a few of the MSBs set that we need to
+		 * clear */
+		bitmap_complement(gpu_resources.queue_bitmap,
+				  adev->gfx.mec.queue_bitmap,
+				  KGD_MAX_QUEUES);
+
+		/* remove the KIQ bit as well */
+		if (adev->gfx.kiq.ring.ready)
+			clear_bit(amdgpu_gfx_queue_to_bit(adev,
+							  adev->gfx.kiq.ring.me - 1,
+							  adev->gfx.kiq.ring.pipe,
+							  adev->gfx.kiq.ring.queue),
+				  gpu_resources.queue_bitmap);
+
+		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
+		 * nbits is not compile time constant */
+		last_valid_bit = adev->gfx.mec.num_mec
+				* adev->gfx.mec.num_pipe_per_mec
+				* adev->gfx.mec.num_queue_per_pipe;
+		for (i = last_valid_bit; i < KGD_MAX_QUEUES; ++i)
+			clear_bit(i, gpu_resources.queue_bitmap);
+
+		amdgpu_doorbell_get_kfd_info(adev,
 				&gpu_resources.doorbell_physical_address,
 				&gpu_resources.doorbell_aperture_size,
 				&gpu_resources.doorbell_start_offset);
 
-		kgd2kfd->device_init(rdev->kfd, &gpu_resources);
+		kgd2kfd->device_init(adev->kfd, &gpu_resources);
 	}
 }
 
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev)
 {
-	if (rdev->kfd) {
-		kgd2kfd->device_exit(rdev->kfd);
-		rdev->kfd = NULL;
+	if (adev->kfd) {
+		kgd2kfd->device_exit(adev->kfd);
+		adev->kfd = NULL;
 	}
 }
 
-void amdgpu_amdkfd_interrupt(struct amdgpu_device *rdev,
+void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 		const void *ih_ring_entry)
 {
-	if (rdev->kfd)
-		kgd2kfd->interrupt(rdev->kfd, ih_ring_entry);
+	if (adev->kfd)
+		kgd2kfd->interrupt(adev->kfd, ih_ring_entry);
 }
 
-void amdgpu_amdkfd_suspend(struct amdgpu_device *rdev)
+void amdgpu_amdkfd_suspend(struct amdgpu_device *adev)
 {
-	if (rdev->kfd)
-		kgd2kfd->suspend(rdev->kfd);
+	if (adev->kfd)
+		kgd2kfd->suspend(adev->kfd);
 }
 
-int amdgpu_amdkfd_resume(struct amdgpu_device *rdev)
+int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 {
 	int r = 0;
 
-	if (rdev->kfd)
-		r = kgd2kfd->resume(rdev->kfd);
+	if (adev->kfd)
+		r = kgd2kfd->resume(adev->kfd);
 
 	return r;
 }
@@ -147,7 +172,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 	struct kgd_mem **mem = (struct kgd_mem **) mem_obj;
 	int r;
 
@@ -159,10 +184,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	if ((*mem) == NULL)
 		return -ENOMEM;
 
-	r = amdgpu_bo_create(rdev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
+	r = amdgpu_bo_create(adev, size, PAGE_SIZE, true, AMDGPU_GEM_DOMAIN_GTT,
 			     AMDGPU_GEM_CREATE_CPU_GTT_USWC, NULL, NULL, &(*mem)->bo);
 	if (r) {
-		dev_err(rdev->dev,
+		dev_err(adev->dev,
 			"failed to allocate BO for amdkfd (%d)\n", r);
 		return r;
 	}
@@ -170,21 +195,21 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	/* map the buffer */
 	r = amdgpu_bo_reserve((*mem)->bo, true);
 	if (r) {
-		dev_err(rdev->dev, "(%d) failed to reserve bo for amdkfd\n", r);
+		dev_err(adev->dev, "(%d) failed to reserve bo for amdkfd\n", r);
 		goto allocate_mem_reserve_bo_failed;
 	}
 
 	r = amdgpu_bo_pin((*mem)->bo, AMDGPU_GEM_DOMAIN_GTT,
 				&(*mem)->gpu_addr);
 	if (r) {
-		dev_err(rdev->dev, "(%d) failed to pin bo for amdkfd\n", r);
+		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
 		goto allocate_mem_pin_bo_failed;
 	}
 	*gpu_addr = (*mem)->gpu_addr;
 
 	r = amdgpu_bo_kmap((*mem)->bo, &(*mem)->cpu_ptr);
 	if (r) {
-		dev_err(rdev->dev,
+		dev_err(adev->dev,
 			"(%d) failed to map bo to kernel for amdkfd\n", r);
 		goto allocate_mem_kmap_bo_failed;
 	}
@@ -220,27 +245,27 @@ void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj)
 
 uint64_t get_vmem_size(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev =
+	struct amdgpu_device *adev =
 		(struct amdgpu_device *)kgd;
 
 	BUG_ON(kgd == NULL);
 
-	return rdev->mc.real_vram_size;
+	return adev->mc.real_vram_size;
 }
 
 uint64_t get_gpu_clock_counter(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	if (rdev->gfx.funcs->get_gpu_clock_counter)
-		return rdev->gfx.funcs->get_gpu_clock_counter(rdev);
+	if (adev->gfx.funcs->get_gpu_clock_counter)
+		return adev->gfx.funcs->get_gpu_clock_counter(adev);
 	return 0;
 }
 
 uint32_t get_max_engine_clock_in_mhz(struct kgd_dev *kgd)
 {
-	struct amdgpu_device *rdev = (struct amdgpu_device *)kgd;
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
 	/* The sclk is in quantas of 10kHz */
-	return rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
+	return adev->pm.dpm.dyn_state.max_clock_voltage_on_ac.sclk / 100;
 }