Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 115 insertions, 66 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3b7e7af09ead..e687363900bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -21,6 +21,7 @@
  *
  */
 #include <linux/firmware.h>
+#include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "gmc_v9_0.h"
 #include "amdgpu_atomfirmware.h"
@@ -33,6 +34,7 @@
 #include "vega10_enum.h"
 #include "mmhub/mmhub_1_0_offset.h"
 #include "athub/athub_1_0_offset.h"
+#include "oss/osssys_4_0_offset.h"
 
 #include "soc15.h"
 #include "soc15_common.h"
@@ -262,10 +264,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 
 	if (printk_ratelimit()) {
 		dev_err(adev->dev,
-			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pas_id:%u)\n",
+			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
 			entry->vmid_src ? "mmhub" : "gfxhub",
 			entry->src_id, entry->ring_id, entry->vmid,
-			entry->pas_id);
+			entry->pasid);
 		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
 			addr, entry->client_id);
 		if (!amdgpu_sriov_vf(adev))
@@ -284,8 +286,8 @@ static const struct amdgpu_irq_src_funcs gmc_v9_0_irq_funcs = {
 
 static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->mc.vm_fault.num_types = 1;
-	adev->mc.vm_fault.funcs = &gmc_v9_0_irq_funcs;
+	adev->gmc.vm_fault.num_types = 1;
+	adev->gmc.vm_fault.funcs = &gmc_v9_0_irq_funcs;
 }
 
 static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid)
@@ -315,24 +317,21 @@ static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid)
  */
 
 /**
- * gmc_v9_0_gart_flush_gpu_tlb - gart tlb flush callback
+ * gmc_v9_0_flush_gpu_tlb - gart tlb flush callback
  *
  * @adev: amdgpu_device pointer
  * @vmid: vm instance to flush
  *
  * Flush the TLB for the requested page table.
  */
-static void gmc_v9_0_gart_flush_gpu_tlb(struct amdgpu_device *adev,
+static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev,
 					uint32_t vmid)
 {
 	/* Use register 17 for GART */
 	const unsigned eng = 17;
 	unsigned i, j;
 
-	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev);
-
-	spin_lock(&adev->mc.invalidate_lock);
+	spin_lock(&adev->gmc.invalidate_lock);
 
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
 		struct amdgpu_vmhub *hub = &adev->vmhub[i];
@@ -365,11 +364,52 @@ static void gmc_v9_0_gart_flush_gpu_tlb(struct amdgpu_device *adev,
 		DRM_ERROR("Timeout waiting for VM flush ACK!\n");
 	}
 
-	spin_unlock(&adev->mc.invalidate_lock);
+	spin_unlock(&adev->gmc.invalidate_lock);
+}
+
+static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
+					    unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub];
+	uint32_t req = gmc_v9_0_get_invalidate_req(vmid);
+	uint64_t flags = AMDGPU_PTE_VALID;
+	unsigned eng = ring->vm_inv_eng;
+
+	amdgpu_gmc_get_vm_pde(adev, -1, &pd_addr, &flags);
+	pd_addr |= flags;
+
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
+			      lower_32_bits(pd_addr));
+
+	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
+			      upper_32_bits(pd_addr));
+
+	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
+
+	/* wait for the invalidate to complete */
+	amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng,
+				  1 << vmid, 1 << vmid);
+
+	return pd_addr;
+}
+
+static void gmc_v9_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
+					unsigned pasid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg;
+
+	if (ring->funcs->vmhub == AMDGPU_GFXHUB)
+		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT) + vmid;
+	else
+		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT_MM) + vmid;
+
+	amdgpu_ring_emit_wreg(ring, reg, pasid);
 }
 
 /**
- * gmc_v9_0_gart_set_pte_pde - update the page tables using MMIO
+ * gmc_v9_0_set_pte_pde - update the page tables using MMIO
  *
  * @adev: amdgpu_device pointer
  * @cpu_pt_addr: cpu address of the page table
@@ -379,11 +419,9 @@ static void gmc_v9_0_gart_flush_gpu_tlb(struct amdgpu_device *adev,
  *
  * Update the page tables using the CPU.
  */
-static int gmc_v9_0_gart_set_pte_pde(struct amdgpu_device *adev,
-					void *cpu_pt_addr,
-					uint32_t gpu_page_idx,
-					uint64_t addr,
-					uint64_t flags)
+static int gmc_v9_0_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
+				uint32_t gpu_page_idx, uint64_t addr,
+				uint64_t flags)
 {
 	void __iomem *ptr = (void *)cpu_pt_addr;
 	uint64_t value;
@@ -474,10 +512,10 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 {
 	if (!(*flags & AMDGPU_PDE_PTE))
 		*addr = adev->vm_manager.vram_base_offset + *addr -
-			adev->mc.vram_start;
+			adev->gmc.vram_start;
 	BUG_ON(*addr & 0xFFFF00000000003FULL);
 
-	if (!adev->mc.translate_further)
+	if (!adev->gmc.translate_further)
 		return;
 
 	if (level == AMDGPU_VM_PDB1) {
@@ -493,34 +531,35 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 	}
 }
 
-static const struct amdgpu_gart_funcs gmc_v9_0_gart_funcs = {
-	.flush_gpu_tlb = gmc_v9_0_gart_flush_gpu_tlb,
-	.set_pte_pde = gmc_v9_0_gart_set_pte_pde,
-	.get_invalidate_req = gmc_v9_0_get_invalidate_req,
+static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
+	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
+	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
+	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
+	.set_pte_pde = gmc_v9_0_set_pte_pde,
 	.get_vm_pte_flags = gmc_v9_0_get_vm_pte_flags,
 	.get_vm_pde = gmc_v9_0_get_vm_pde
 };
 
-static void gmc_v9_0_set_gart_funcs(struct amdgpu_device *adev)
+static void gmc_v9_0_set_gmc_funcs(struct amdgpu_device *adev)
 {
-	if (adev->gart.gart_funcs == NULL)
-		adev->gart.gart_funcs = &gmc_v9_0_gart_funcs;
+	if (adev->gmc.gmc_funcs == NULL)
+		adev->gmc.gmc_funcs = &gmc_v9_0_gmc_funcs;
 }
 
 static int gmc_v9_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	gmc_v9_0_set_gart_funcs(adev);
+	gmc_v9_0_set_gmc_funcs(adev);
 	gmc_v9_0_set_irq_funcs(adev);
 
-	adev->mc.shared_aperture_start = 0x2000000000000000ULL;
-	adev->mc.shared_aperture_end =
-		adev->mc.shared_aperture_start + (4ULL << 30) - 1;
-	adev->mc.private_aperture_start =
-		adev->mc.shared_aperture_end + 1;
-	adev->mc.private_aperture_end =
-		adev->mc.private_aperture_start + (4ULL << 30) - 1;
+	adev->gmc.shared_aperture_start = 0x2000000000000000ULL;
+	adev->gmc.shared_aperture_end =
+		adev->gmc.shared_aperture_start + (4ULL << 30) - 1;
+	adev->gmc.private_aperture_start =
+		adev->gmc.shared_aperture_end + 1;
+	adev->gmc.private_aperture_end =
+		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
 
 	return 0;
 }
@@ -646,16 +685,16 @@ static int gmc_v9_0_late_init(void *handle)
 		}
 	}
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 }
 
 static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
-					struct amdgpu_mc *mc)
+					struct amdgpu_gmc *mc)
 {
 	u64 base = 0;
 	if (!amdgpu_sriov_vf(adev))
 		base = mmhub_v1_0_get_fb_location(adev);
-	amdgpu_device_vram_location(adev, &adev->mc, base);
+	amdgpu_device_vram_location(adev, &adev->gmc, base);
 	amdgpu_device_gart_location(adev, mc);
 	/* base offset of vram pages */
 	if (adev->flags & AMD_IS_APU)
@@ -679,8 +718,9 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 	int chansize, numchan;
 	int r;
 
-	adev->mc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
-	if (!adev->mc.vram_width) {
+	if (amdgpu_emu_mode != 1)
+		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
+	if (!adev->gmc.vram_width) {
 		/* hbm memory channel size */
 		if (adev->flags & AMD_IS_APU)
 			chansize = 64;
@@ -720,43 +760,50 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 			numchan = 2;
 			break;
 		}
-		adev->mc.vram_width = numchan * chansize;
+		adev->gmc.vram_width = numchan * chansize;
 	}
 
 	/* size in MB on si */
-	adev->mc.mc_vram_size =
+	adev->gmc.mc_vram_size =
 		adev->nbio_funcs->get_memsize(adev) * 1024ULL * 1024ULL;
-	adev->mc.real_vram_size = adev->mc.mc_vram_size;
+	adev->gmc.real_vram_size = adev->gmc.mc_vram_size;
 
 	if (!(adev->flags & AMD_IS_APU)) {
 		r = amdgpu_device_resize_fb_bar(adev);
 		if (r)
 			return r;
 	}
-	adev->mc.aper_base = pci_resource_start(adev->pdev, 0);
-	adev->mc.aper_size = pci_resource_len(adev->pdev, 0);
+	adev->gmc.aper_base = pci_resource_start(adev->pdev, 0);
+	adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
 
+#ifdef CONFIG_X86_64
+	if (adev->flags & AMD_IS_APU) {
+		adev->gmc.aper_base = gfxhub_v1_0_get_mc_fb_offset(adev);
+		adev->gmc.aper_size = adev->gmc.real_vram_size;
+	}
+#endif
 	/* In case the PCI BAR is larger than the actual amount of vram */
-	adev->mc.visible_vram_size = adev->mc.aper_size;
-	if (adev->mc.visible_vram_size > adev->mc.real_vram_size)
-		adev->mc.visible_vram_size = adev->mc.real_vram_size;
+	adev->gmc.visible_vram_size = adev->gmc.aper_size;
+	if (adev->gmc.visible_vram_size > adev->gmc.real_vram_size)
+		adev->gmc.visible_vram_size = adev->gmc.real_vram_size;
 
 	/* set the gart size */
 	if (amdgpu_gart_size == -1) {
 		switch (adev->asic_type) {
 		case CHIP_VEGA10:  /* all engines support GPUVM */
+		case CHIP_VEGA12:  /* all engines support GPUVM */
 		default:
-			adev->mc.gart_size = 256ULL << 20;
+			adev->gmc.gart_size = 512ULL << 20;
 			break;
 		case CHIP_RAVEN:   /* DCE SG support */
-			adev->mc.gart_size = 1024ULL << 20;
+			adev->gmc.gart_size = 1024ULL << 20;
 			break;
 		}
 	} else {
-		adev->mc.gart_size = (u64)amdgpu_gart_size << 20;
+		adev->gmc.gart_size = (u64)amdgpu_gart_size << 20;
 	}
 
-	gmc_v9_0_vram_gtt_location(adev, &adev->mc);
+	gmc_v9_0_vram_gtt_location(adev, &adev->gmc);
 
 	return 0;
 }
@@ -788,23 +835,22 @@ static int gmc_v9_0_sw_init(void *handle)
 	gfxhub_v1_0_init(adev);
 	mmhub_v1_0_init(adev);
 
-	spin_lock_init(&adev->mc.invalidate_lock);
+	spin_lock_init(&adev->gmc.invalidate_lock);
 
+	adev->gmc.vram_type = amdgpu_atomfirmware_get_vram_type(adev);
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
-		adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
 		if (adev->rev_id == 0x0 || adev->rev_id == 0x1) {
 			amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
 		} else {
 			/* vm_size is 128TB + 512GB for legacy 3-level page support */
 			amdgpu_vm_adjust_size(adev, 128 * 1024 + 512, 9, 2, 48);
-			adev->mc.translate_further =
+			adev->gmc.translate_further =
 				adev->vm_manager.num_level > 1;
 		}
 		break;
 	case CHIP_VEGA10:
-		/* XXX Don't know how to get VRAM type yet. */
-		adev->mc.vram_type = AMDGPU_VRAM_TYPE_HBM;
+	case CHIP_VEGA12:
 		/*
 		 * To fulfill 4-level page support,
 		 * vm size is 256TB (48bit), maximum size of Vega10,
@@ -817,10 +863,10 @@ static int gmc_v9_0_sw_init(void *handle)
 	}
 
 	/* This interrupt is VMC page fault.*/
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VMC, 0,
-				&adev->mc.vm_fault);
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_UTCL2, 0,
-				&adev->mc.vm_fault);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, 0,
+				&adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, 0,
+				&adev->gmc.vm_fault);
 
 	if (r)
 		return r;
@@ -829,13 +875,13 @@ static int gmc_v9_0_sw_init(void *handle)
 	 * This is the max address of the GPU's
 	 * internal address space.
 	 */
-	adev->mc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */
+	adev->gmc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */
 
 	/*
 	 * It needs to reserve 8M stolen memory for vega10
 	 * TODO: Figure out how to avoid that...
 	 */
-	adev->mc.stolen_size = 8 * 1024 * 1024;
+	adev->gmc.stolen_size = 8 * 1024 * 1024;
 
 	/* set DMA mask + need_dma32 flags.
 	 * PCIE - can handle 44-bits.
@@ -855,6 +901,7 @@ static int gmc_v9_0_sw_init(void *handle)
 		pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
 		printk(KERN_WARNING "amdgpu: No coherent DMA available.\n");
 	}
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	r = gmc_v9_0_mc_init(adev);
 	if (r)
@@ -920,6 +967,8 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
 						golden_settings_athub_1_0_0,
 						ARRAY_SIZE(golden_settings_athub_1_0_0));
 		break;
+	case CHIP_VEGA12:
+		break;
 	case CHIP_RAVEN:
 		soc15_program_register_sequence(adev,
 						golden_settings_athub_1_0_0,
@@ -976,7 +1025,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	WREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL, tmp);
 
 	/* After HDP is initialized, flush HDP.*/
-	adev->nbio_funcs->hdp_flush(adev);
+	adev->nbio_funcs->hdp_flush(adev, NULL);
 
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
 		value = false;
@@ -985,10 +1034,10 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 
 	gfxhub_v1_0_set_fault_enable_default(adev, value);
 	mmhub_v1_0_set_fault_enable_default(adev, value);
-	gmc_v9_0_gart_flush_gpu_tlb(adev, 0);
+	gmc_v9_0_flush_gpu_tlb(adev, 0);
 
 	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
-		 (unsigned)(adev->mc.gart_size >> 20),
+		 (unsigned)(adev->gmc.gart_size >> 20),
 		 (unsigned long long)adev->gart.table_addr);
 	adev->gart.ready = true;
 	return 0;
@@ -1039,7 +1088,7 @@ static int gmc_v9_0_hw_fini(void *handle)
 		return 0;
 	}
 
-	amdgpu_irq_put(adev, &adev->mc.vm_fault, 0);
+	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 	gmc_v9_0_gart_disable(adev);
 
 	return 0;