Merge tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "The biggest thing in this is the AMD Navi GPU support, this again
  contains a bunch of header files that are large. These are the new AMD
  RX5700 GPUs that just recently became available.

  New drivers:
   - ST-Ericsson MCDE driver
   - Ingenic JZ47xx SoC

  UAPI change:
   - HDR source metadata property

  Core:
   - HDR inforframes and EDID parsing
   - drm hdmi infoframe unpacking
   - remove prime sg_table caching into dma-buf
   - New gem vram helpers to reduce driver code
   - Lots of drmP.h removal
   - reservation fencing fix
   - documentation updates
   - drm_fb_helper_connector removed
   - mode name command handler rewrite

  fbcon:
   - Remove the fbcon notifiers

  ttm:
   - forward progress fixes

  dma-buf:
   - make mmap call optional
   - debugfs refcount fixes
   - dma-fence free with pending signals fix
   - each dma-buf gets an inode

  Panels:
   - Lots of additional panel bindings

  amdgpu:
   - initial navi10 support
   - avoid hw reset
   - HDR metadata support
   - new thermal sensors for vega asics
   - RAS fixes
   - use HMM rather than MMU notifier
   - xgmi topology via kfd
   - SR-IOV fixes
   - driver reload fixes
   - DC use a core bpc attribute
   - Aux fixes for DC
   - Bandwidth calc updates for DC
   - Clock handling refactor
   - kfd VEGAM support

  vmwgfx:
   - Coherent memory support changes

  i915:
   - HDR Support
   - HDMI i2c link
   - Icelake multi-segmented gamma support
   - GuC firmware update
   - Mule Creek Canyon PCH support for EHL
   - EHL platform updtes
   - move i915.alpha_support to i915.force_probe
   - runtime PM refactoring
   - VBT parsing refactoring
   - DSI fixes
   - struct mutex dependency reduction
   - GEM code reorg

  mali-dp:
   - Komeda driver features

  msm:
   - dsi vs EPROBE_DEFER fixes
   - msm8998 snapdragon 835 support
   - a540 gpu support
   - mdp5 and dpu interconnect support

  exynos:
   - drmP.h removal

  tegra:
   - misc fixes

  tda998x:
   - audio support improvements
   - pixel repeated mode support
   - quantisation range handling corrections
   - HDMI vendor info fix

  armada:
   - interlace support fix
   - overlay/video plane register handling refactor
   - add gamma support

  rockchip:
   - RX3328 support

  panfrost:
   - expose perf counters via hidden ioctls

  vkms:
   - enumerate CRC sources list

  ast:
   - rework BO handling

  mgag200:
   - rework BO handling

  dw-hdmi:
   - suspend/resume support

  rcar-du:
   - R8A774A1 Soc Support
   - LVDS dual-link mode support
   - Additional formats
   - Misc fixes

  omapdrm:
   - DSI command mode display support

  stm
   - fb modifier support
   - runtime PM support

  sun4i:
   - use vmap ops

  vc4:
   - binner bo binding rework

  v3d:
   - compute shader support
   - resync/sync fixes
   - job management refactoring

  lima:
   - NULL pointer in irq handler fix
   - scheduler default timeout

  virtio:
   - fence seqno support
   - trace events

  bochs:
   - misc fixes

  tc458767:
   - IRQ/HDP handling

  sii902x:
   - HDMI audio support

  atmel-hlcdc:
   - misc fixes

  meson:
   - zpos support"

* tag 'drm-next-2019-07-16' of git://anongit.freedesktop.org/drm/drm: (1815 commits)
  Revert "Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next"
  Revert "mm: adjust apply_to_pfn_range interface for dropped token."
  mm: adjust apply_to_pfn_range interface for dropped token.
  drm/amdgpu/navi10: add uclk activity sensor
  drm/amdgpu: properly guard the generic discovery code
  drm/amdgpu: add missing documentation on new module parameters
  drm/amdgpu: don't invalidate caches in RELEASE_MEM, only do the writeback
  drm/amd/display: avoid 64-bit division
  drm/amdgpu/psp11: simplify the ucode register logic
  drm/amdgpu: properly guard DC support in navi code
  drm/amd/powerplay: vega20: fix uninitialized variable use
  drm/amd/display: dcn20: include linux/delay.h
  amdgpu: make pmu support optional
  drm/amd/powerplay: Zero initialize current_rpm in vega20_get_fan_speed_percent
  drm/amd/powerplay: Zero initialize freq in smu_v11_0_get_current_clk_freq
  drm/amd/powerplay: Use memset to initialize metrics structs
  drm/amdgpu/mes10.1: Fix header guard
  drm/amd/powerplay: add temperature sensor support for navi10
  drm/amdgpu: fix scheduler timeout calc
  drm/amdgpu: Prepare for hmm_range_register API change (v2)
  ...

1 files changed, 415 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
new file mode 100644
index 000000000000..e049ae6a76fb
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -0,0 +1,415 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_discovery.h"
+#include "soc15_common.h"
+#include "soc15_hw_ip.h"
+#include "nbio/nbio_2_3_offset.h"
+#include "discovery.h"
+
+#define mmRCC_CONFIG_MEMSIZE	0xde3
+#define mmMM_INDEX		0x0
+#define mmMM_INDEX_HI		0x6
+#define mmMM_DATA		0x1
+#define HW_ID_MAX		300
+
+const char *hw_id_names[HW_ID_MAX] = {
+	[MP1_HWID]		= "MP1",
+	[MP2_HWID]		= "MP2",
+	[THM_HWID]		= "THM",
+	[SMUIO_HWID]		= "SMUIO",
+	[FUSE_HWID]		= "FUSE",
+	[CLKA_HWID]		= "CLKA",
+	[PWR_HWID]		= "PWR",
+	[GC_HWID]		= "GC",
+	[UVD_HWID]		= "UVD",
+	[AUDIO_AZ_HWID]		= "AUDIO_AZ",
+	[ACP_HWID]		= "ACP",
+	[DCI_HWID]		= "DCI",
+	[DMU_HWID]		= "DMU",
+	[DCO_HWID]		= "DCO",
+	[DIO_HWID]		= "DIO",
+	[XDMA_HWID]		= "XDMA",
+	[DCEAZ_HWID]		= "DCEAZ",
+	[DAZ_HWID]		= "DAZ",
+	[SDPMUX_HWID]		= "SDPMUX",
+	[NTB_HWID]		= "NTB",
+	[IOHC_HWID]		= "IOHC",
+	[L2IMU_HWID]		= "L2IMU",
+	[VCE_HWID]		= "VCE",
+	[MMHUB_HWID]		= "MMHUB",
+	[ATHUB_HWID]		= "ATHUB",
+	[DBGU_NBIO_HWID]	= "DBGU_NBIO",
+	[DFX_HWID]		= "DFX",
+	[DBGU0_HWID]		= "DBGU0",
+	[DBGU1_HWID]		= "DBGU1",
+	[OSSSYS_HWID]		= "OSSSYS",
+	[HDP_HWID]		= "HDP",
+	[SDMA0_HWID]		= "SDMA0",
+	[SDMA1_HWID]		= "SDMA1",
+	[ISP_HWID]		= "ISP",
+	[DBGU_IO_HWID]		= "DBGU_IO",
+	[DF_HWID]		= "DF",
+	[CLKB_HWID]		= "CLKB",
+	[FCH_HWID]		= "FCH",
+	[DFX_DAP_HWID]		= "DFX_DAP",
+	[L1IMU_PCIE_HWID]	= "L1IMU_PCIE",
+	[L1IMU_NBIF_HWID]	= "L1IMU_NBIF",
+	[L1IMU_IOAGR_HWID]	= "L1IMU_IOAGR",
+	[L1IMU3_HWID]		= "L1IMU3",
+	[L1IMU4_HWID]		= "L1IMU4",
+	[L1IMU5_HWID]		= "L1IMU5",
+	[L1IMU6_HWID]		= "L1IMU6",
+	[L1IMU7_HWID]		= "L1IMU7",
+	[L1IMU8_HWID]		= "L1IMU8",
+	[L1IMU9_HWID]		= "L1IMU9",
+	[L1IMU10_HWID]		= "L1IMU10",
+	[L1IMU11_HWID]		= "L1IMU11",
+	[L1IMU12_HWID]		= "L1IMU12",
+	[L1IMU13_HWID]		= "L1IMU13",
+	[L1IMU14_HWID]		= "L1IMU14",
+	[L1IMU15_HWID]		= "L1IMU15",
+	[WAFLC_HWID]		= "WAFLC",
+	[FCH_USB_PD_HWID]	= "FCH_USB_PD",
+	[PCIE_HWID]		= "PCIE",
+	[PCS_HWID]		= "PCS",
+	[DDCL_HWID]		= "DDCL",
+	[SST_HWID]		= "SST",
+	[IOAGR_HWID]		= "IOAGR",
+	[NBIF_HWID]		= "NBIF",
+	[IOAPIC_HWID]		= "IOAPIC",
+	[SYSTEMHUB_HWID]	= "SYSTEMHUB",
+	[NTBCCP_HWID]		= "NTBCCP",
+	[UMC_HWID]		= "UMC",
+	[SATA_HWID]		= "SATA",
+	[USB_HWID]		= "USB",
+	[CCXSEC_HWID]		= "CCXSEC",
+	[XGMI_HWID]		= "XGMI",
+	[XGBE_HWID]		= "XGBE",
+	[MP0_HWID]		= "MP0",
+};
+
+static int hw_id_map[MAX_HWIP] = {
+	[GC_HWIP]	= GC_HWID,
+	[HDP_HWIP]	= HDP_HWID,
+	[SDMA0_HWIP]	= SDMA0_HWID,
+	[SDMA1_HWIP]	= SDMA1_HWID,
+	[MMHUB_HWIP]	= MMHUB_HWID,
+	[ATHUB_HWIP]	= ATHUB_HWID,
+	[NBIO_HWIP]	= NBIF_HWID,
+	[MP0_HWIP]	= MP0_HWID,
+	[MP1_HWIP]	= MP1_HWID,
+	[UVD_HWIP]	= UVD_HWID,
+	[VCE_HWIP]	= VCE_HWID,
+	[DF_HWIP]	= DF_HWID,
+	[DCE_HWIP]	= DCEAZ_HWID,
+	[OSSSYS_HWIP]	= OSSSYS_HWID,
+	[SMUIO_HWIP]	= SMUIO_HWID,
+	[PWR_HWIP]	= PWR_HWID,
+	[NBIF_HWIP]	= NBIF_HWID,
+	[THM_HWIP]	= THM_HWID,
+	[CLK_HWIP]	= CLKA_HWID,
+};
+
+static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *binary)
+{
+	uint32_t *p = (uint32_t *)binary;
+	uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
+	uint64_t pos = vram_size - BINARY_MAX_SIZE;
+	unsigned long flags;
+
+	while (pos < vram_size) {
+		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
+		WREG32_NO_KIQ(mmMM_INDEX_HI, pos >> 31);
+		*p++ = RREG32_NO_KIQ(mmMM_DATA);
+		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+		pos += 4;
+	}
+
+	return 0;
+}
+
+static uint16_t amdgpu_discovery_calculate_checksum(uint8_t *data, uint32_t size)
+{
+	uint16_t checksum = 0;
+	int i;
+
+	for (i = 0; i < size; i++)
+		checksum += data[i];
+
+	return checksum;
+}
+
+static inline bool amdgpu_discovery_verify_checksum(uint8_t *data, uint32_t size,
+						    uint16_t expected)
+{
+	return !!(amdgpu_discovery_calculate_checksum(data, size) == expected);
+}
+
+int amdgpu_discovery_init(struct amdgpu_device *adev)
+{
+	struct table_info *info;
+	struct binary_header *bhdr;
+	struct ip_discovery_header *ihdr;
+	struct gpu_info_header *ghdr;
+	uint16_t offset;
+	uint16_t size;
+	uint16_t checksum;
+	int r;
+
+	adev->discovery = kzalloc(BINARY_MAX_SIZE, GFP_KERNEL);
+	if (!adev->discovery)
+		return -ENOMEM;
+
+	r = amdgpu_discovery_read_binary(adev, adev->discovery);
+	if (r) {
+		DRM_ERROR("failed to read ip discovery binary\n");
+		goto out;
+	}
+
+	bhdr = (struct binary_header *)adev->discovery;
+
+	if (le32_to_cpu(bhdr->binary_signature) != BINARY_SIGNATURE) {
+		DRM_ERROR("invalid ip discovery binary signature\n");
+		r = -EINVAL;
+		goto out;
+	}
+
+	offset = offsetof(struct binary_header, binary_checksum) +
+		sizeof(bhdr->binary_checksum);
+	size = bhdr->binary_size - offset;
+	checksum = bhdr->binary_checksum;
+
+	if (!amdgpu_discovery_verify_checksum(adev->discovery + offset,
+					      size, checksum)) {
+		DRM_ERROR("invalid ip discovery binary checksum\n");
+		r = -EINVAL;
+		goto out;
+	}
+
+	info = &bhdr->table_list[IP_DISCOVERY];
+	offset = le16_to_cpu(info->offset);
+	checksum = le16_to_cpu(info->checksum);
+	ihdr = (struct ip_discovery_header *)(adev->discovery + offset);
+
+	if (le32_to_cpu(ihdr->signature) != DISCOVERY_TABLE_SIGNATURE) {
+		DRM_ERROR("invalid ip discovery data table signature\n");
+		r = -EINVAL;
+		goto out;
+	}
+
+	if (!amdgpu_discovery_verify_checksum(adev->discovery + offset,
+					      ihdr->size, checksum)) {
+		DRM_ERROR("invalid ip discovery data table checksum\n");
+		r = -EINVAL;
+		goto out;
+	}
+
+	info = &bhdr->table_list[GC];
+	offset = le16_to_cpu(info->offset);
+	checksum = le16_to_cpu(info->checksum);
+	ghdr = (struct gpu_info_header *)(adev->discovery + offset);
+
+	if (!amdgpu_discovery_verify_checksum(adev->discovery + offset,
+				              ghdr->size, checksum)) {
+		DRM_ERROR("invalid gc data table checksum\n");
+		r = -EINVAL;
+		goto out;
+	}
+
+	return 0;
+
+out:
+	kfree(adev->discovery);
+	adev->discovery = NULL;
+
+	return r;
+}
+
+void amdgpu_discovery_fini(struct amdgpu_device *adev)
+{
+	kfree(adev->discovery);
+	adev->discovery = NULL;
+}
+
+int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
+{
+	struct binary_header *bhdr;
+	struct ip_discovery_header *ihdr;
+	struct die_header *dhdr;
+	struct ip *ip;
+	uint16_t die_offset;
+	uint16_t ip_offset;
+	uint16_t num_dies;
+	uint16_t num_ips;
+	uint8_t num_base_address;
+	int hw_ip;
+	int i, j, k;
+
+	if (!adev->discovery) {
+		DRM_ERROR("ip discovery uninitialized\n");
+		return -EINVAL;
+	}
+
+	bhdr = (struct binary_header *)adev->discovery;
+	ihdr = (struct ip_discovery_header *)(adev->discovery +
+			le16_to_cpu(bhdr->table_list[IP_DISCOVERY].offset));
+	num_dies = le16_to_cpu(ihdr->num_dies);
+
+	DRM_DEBUG("number of dies: %d\n", num_dies);
+
+	for (i = 0; i < num_dies; i++) {
+		die_offset = le16_to_cpu(ihdr->die_info[i].die_offset);
+		dhdr = (struct die_header *)(adev->discovery + die_offset);
+		num_ips = le16_to_cpu(dhdr->num_ips);
+		ip_offset = die_offset + sizeof(*dhdr);
+
+		if (le16_to_cpu(dhdr->die_id) != i) {
+			DRM_ERROR("invalid die id %d, expected %d\n",
+					le16_to_cpu(dhdr->die_id), i);
+			return -EINVAL;
+		}
+
+		DRM_DEBUG("number of hardware IPs on die%d: %d\n",
+				le16_to_cpu(dhdr->die_id), num_ips);
+
+		for (j = 0; j < num_ips; j++) {
+			ip = (struct ip *)(adev->discovery + ip_offset);
+			num_base_address = ip->num_base_address;
+
+			DRM_DEBUG("%s(%d) #%d v%d.%d.%d:\n",
+				  hw_id_names[le16_to_cpu(ip->hw_id)],
+				  le16_to_cpu(ip->hw_id),
+				  ip->number_instance,
+				  ip->major, ip->minor,
+				  ip->revision);
+
+			for (k = 0; k < num_base_address; k++) {
+				/*
+				 * convert the endianness of base addresses in place,
+				 * so that we don't need to convert them when accessing adev->reg_offset.
+				 */
+				ip->base_address[k] = le32_to_cpu(ip->base_address[k]);
+				DRM_DEBUG("\t0x%08x\n", ip->base_address[k]);
+			}
+
+			for (hw_ip = 0; hw_ip < MAX_HWIP; hw_ip++) {
+				if (hw_id_map[hw_ip] == le16_to_cpu(ip->hw_id)) {
+					DRM_INFO("set register base offset for %s\n",
+							hw_id_names[le16_to_cpu(ip->hw_id)]);
+					adev->reg_offset[hw_ip][ip->number_instance] =
+						ip->base_address;
+				}
+
+			}
+
+			ip_offset += sizeof(*ip) + 4 * (ip->num_base_address - 1);
+		}
+	}
+
+	return 0;
+}
+
+int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
+				    int *major, int *minor)
+{
+	struct binary_header *bhdr;
+	struct ip_discovery_header *ihdr;
+	struct die_header *dhdr;
+	struct ip *ip;
+	uint16_t die_offset;
+	uint16_t ip_offset;
+	uint16_t num_dies;
+	uint16_t num_ips;
+	int i, j;
+
+	if (!adev->discovery) {
+		DRM_ERROR("ip discovery uninitialized\n");
+		return -EINVAL;
+	}
+
+	bhdr = (struct binary_header *)adev->discovery;
+	ihdr = (struct ip_discovery_header *)(adev->discovery +
+			le16_to_cpu(bhdr->table_list[IP_DISCOVERY].offset));
+	num_dies = le16_to_cpu(ihdr->num_dies);
+
+	for (i = 0; i < num_dies; i++) {
+		die_offset = le16_to_cpu(ihdr->die_info[i].die_offset);
+		dhdr = (struct die_header *)(adev->discovery + die_offset);
+		num_ips = le16_to_cpu(dhdr->num_ips);
+		ip_offset = die_offset + sizeof(*dhdr);
+
+		for (j = 0; j < num_ips; j++) {
+			ip = (struct ip *)(adev->discovery + ip_offset);
+
+			if (le16_to_cpu(ip->hw_id) == hw_id) {
+				if (major)
+					*major = ip->major;
+				if (minor)
+					*minor = ip->minor;
+				return 0;
+			}
+			ip_offset += sizeof(*ip) + 4 * (ip->num_base_address - 1);
+		}
+	}
+
+	return -EINVAL;
+}
+
+int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev)
+{
+	struct binary_header *bhdr;
+	struct gc_info_v1_0 *gc_info;
+
+	if (!adev->discovery) {
+		DRM_ERROR("ip discovery uninitialized\n");
+		return -EINVAL;
+	}
+
+	bhdr = (struct binary_header *)adev->discovery;
+	gc_info = (struct gc_info_v1_0 *)(adev->discovery +
+			le16_to_cpu(bhdr->table_list[GC].offset));
+
+	adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se);
+	adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) +
+					      le32_to_cpu(gc_info->gc_num_wgp1_per_sa));
+	adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se);
+	adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se);
+	adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c);
+	adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs);
+	adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds);
+	adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth);
+	adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth);
+	adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer);
+	adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size);
+	adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd);
+	adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu);
+	adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size);
+	adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) /
+					 le32_to_cpu(gc_info->gc_num_sa_per_se);
+	adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc);
+
+	return 0;
+}