Merge tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main pull request for 5.4-rc1 merge window. I don't think
  there is anything outstanding so next week should just be fixes, but
  we'll see if I missed anything. I landed some fixes earlier in the
  week but got delayed writing summary and sending it out, due to a mix
  of sick kid and jetlag!

  There are some fixes pending, but I'd rather get the main merge out of
  the way instead of delaying it longer.

  It's also pretty large in commit count and new amd header file size.
  The largest thing is four new amdgpu products (navi12/14, arcturus and
  renoir APU support).

  Otherwise it's pretty much lots of work across the board, i915 has
  started landing tigerlake support, lots of icelake fixes and lots of
  locking reworking for future gpu support, lots of header file rework
  (drmP.h is nearly gone), some old legacy hacks (DRM_WAIT_ON) have been
  put into the places they are needed.

  uapi:
   - content protection type property for HDCP

  core:
   - rework include dependencies
   - lots of drmP.h removals
   - link rate calculation robustness fix
   - make fb helper map only when required
   - add connector->DDC adapter link
   - DRM_WAIT_ON removed
   - drop DRM_AUTH usage from drivers

  dma-buf:
   - reservation object fence helper

  dma-fence:
   - shrink dma_fence struct
   - merge signal functions
   - store timestamps in dma_fence
   - selftests

  ttm:
   - embed drm_get_object struct into ttm_buffer_object
   - release_notify callback

  bridges:
   - sii902x - audio graph card support
   - tc358767 - aux data handling rework
   - ti-snd64dsi86 - debugfs support, DSI mode flags support

  panels:
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191, Boe
     Himax8279d, Sharp LD-D5116Z01B
   - TI nspire, NEC NL8048HL11, LG Philips LB035Q02, Sharp LS037V7DW01,
     Sony ACX565AKM, Toppoly TD028TTEC1 Toppoly TD043MTEA1

  i915:
   - Initial tigerlake platform support
   - Locking simplification work, general all over refactoring.
   - Selftests
   - HDCP debug info improvements
   - DSI properties
   - Icelake display PLL fixes, colorspace fixes, bandwidth fixes, DSI
     suspend/resume
   - GuC fixes
   - Perf fixes
   - ElkhartLake enablement
   - DP MST fixes
   - GVT - command parser enhancements

  amdgpu:
   - add wipe memory on release flag for buffer creation
   - Navi12/14 support (may be marked experimental)
   - Arcturus support
   - Renoir APU support
   - mclk DPM for Navi
   - DC display fixes
   - Raven scatter/gather support
   - RAS support for GFX
   - Navi12 + Arcturus power features
   - GPU reset for Picasso
   - smu11 i2c controller support

  amdkfd:
   - navi12/14 support
   - Arcturus support

  radeon:
   - kexec fix

  nouveau:
   - improved display color management
   - detect lack of GPU power cables

  vmwgfx:
   - evicition priority support
   - remove unused security feature

  msm:
   - msm8998 display support
   - better async commit support for cursor updates

  etnaviv:
   - per-process address space support
   - performance counter fixes
   - softpin support

  mcde:
   - DCS transfers fix

  exynos:
   - drmP.h cleanup

  lima:
   - reduce logging

  kirin:
   - misc clenaups

  komeda:
   - dual-link support
   - DT memory regions

  hisilicon:
   - misc fixes

  imx:
   - IPUv3 image converter fixes
   - 32-bit RGB V4L2 pixel format support

  ingenic:
   - more support for panel related cases

  mgag200:
   - cursor support fix

  panfrost:
   - export GPU features register to userspace
   - gpu heap allocations
   - per-fd address space support

  pl111:
   - CLD pads wiring support removed from DT

  rockchip:
   - rework to use DRM PSR helpers
   - fix bug in VOP_WIN_GET macro
   - DSI DT binding rework

  sun4i:
   - improve support for color encoding and range
   - DDC enabled GPIO

  tinydrm:
   - rework SPI support
   - improve MIPI-DBI support
   - moved to drm/tiny

  vkms:
   - rework CRC tracking

  dw-hdmi:
   - get_eld and i2s improvements

  gm12u320:
   - misc fixes

  meson:
   - global code cleanup
   - vpu feature detect

  omap:
   - alpha/pixel blend mode properties

  rcar-du:
   - misc fixes"

* tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm: (2112 commits)
  drm/nouveau/bar/gm20b: Avoid BAR1 teardown during init
  drm/nouveau: Fix ordering between TTM and GEM release
  drm/nouveau/prime: Extend DMA reservation object lock
  drm/nouveau: Fix fallout from reservation object rework
  drm/nouveau/kms/nv50-: Don't create MSTMs for eDP connectors
  drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap
  drm/i915: to make vgpu ppgtt notificaiton as atomic operation
  drm/i915: Flush the existing fence before GGTT read/write
  drm/i915: Hold irq-off for the entire fake lock period
  drm/i915/gvt: update RING_START reg of vGPU when the context is submitted to i915
  drm/i915/gvt: update vgpu workload head pointer correctly
  drm/mcde: Fix DSI transfers
  drm/msm: Use the correct dma_sync calls harder
  drm/msm: remove unlikely() from WARN_ON() conditions
  drm/msm/dsi: Fix return value check for clk_get_parent
  drm/msm: add atomic traces
  drm/msm/dpu: async commit support
  drm/msm: async commit support
  drm/msm: split power control from prepare/complete_commit
  drm/msm: add kms->flush_commit()
  ...

1 files changed, 255 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
new file mode 100644
index 000000000000..8502e736f721
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -0,0 +1,255 @@
+/*
+ * Copyright 2019 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 "umc_v6_1.h"
+#include "amdgpu_ras.h"
+#include "amdgpu.h"
+
+#include "rsmu/rsmu_0_0_2_offset.h"
+#include "rsmu/rsmu_0_0_2_sh_mask.h"
+#include "umc/umc_6_1_1_offset.h"
+#include "umc/umc_6_1_1_sh_mask.h"
+
+#define smnMCA_UMC0_MCUMC_ADDRT0	0x50f10
+
+/*
+ * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
+ * is the index of 8KB block
+ */
+#define ADDR_OF_8KB_BLOCK(addr)		(((addr) & ~0xffULL) << 5)
+/* channel index is the index of 256B block */
+#define ADDR_OF_256B_BLOCK(channel_index)	((channel_index) << 8)
+/* offset in 256B block */
+#define OFFSET_IN_256B_BLOCK(addr)		((addr) & 0xffULL)
+
+const uint32_t
+	umc_v6_1_channel_idx_tbl[UMC_V6_1_UMC_INSTANCE_NUM][UMC_V6_1_CHANNEL_INSTANCE_NUM] = {
+		{2, 18, 11, 27},	{4, 20, 13, 29},
+		{1, 17, 8, 24},		{7, 23, 14, 30},
+		{10, 26, 3, 19},	{12, 28, 5, 21},
+		{9, 25, 0, 16},		{15, 31, 6, 22}
+};
+
+static void umc_v6_1_enable_umc_index_mode(struct amdgpu_device *adev,
+					   uint32_t umc_instance)
+{
+	uint32_t rsmu_umc_index;
+
+	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
+			mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
+			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_MODE_EN, 1);
+	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
+			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_INSTANCE, umc_instance);
+	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
+			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_WREN, 1 << umc_instance);
+	WREG32_SOC15(RSMU, 0, mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+				rsmu_umc_index);
+}
+
+static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
+{
+	WREG32_FIELD15(RSMU, 0, RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_MODE_EN, 0);
+}
+
+static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
+						   uint32_t umc_reg_offset,
+						   unsigned long *error_count)
+{
+	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
+	uint32_t ecc_err_cnt, ecc_err_cnt_addr;
+	uint64_t mc_umc_status;
+	uint32_t mc_umc_status_addr;
+
+	ecc_err_cnt_sel_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+	ecc_err_cnt_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+	mc_umc_status_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+
+	/* select the lower chip and check the error count */
+	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
+					EccErrCntCsSel, 0);
+	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	*error_count +=
+		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
+		 UMC_V6_1_CE_CNT_INIT);
+	/* clear the lower chip err count */
+	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+
+	/* select the higher chip and check the err counter */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
+					EccErrCntCsSel, 1);
+	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	*error_count +=
+		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
+		 UMC_V6_1_CE_CNT_INIT);
+	/* clear the higher chip err count */
+	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+
+	/* check for SRAM correctable error
+	  MCUMC_STATUS is a 64 bit register */
+	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 6 &&
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
+		*error_count += 1;
+}
+
+static void umc_v6_1_querry_uncorrectable_error_count(struct amdgpu_device *adev,
+						      uint32_t umc_reg_offset,
+						      unsigned long *error_count)
+{
+	uint64_t mc_umc_status;
+	uint32_t mc_umc_status_addr;
+
+	mc_umc_status_addr =
+                SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+
+	/* check the MCUMC_STATUS */
+	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1))
+		*error_count += 1;
+}
+
+static void umc_v6_1_query_error_count(struct amdgpu_device *adev,
+					   struct ras_err_data *err_data, uint32_t umc_reg_offset,
+					   uint32_t channel_index)
+{
+	umc_v6_1_query_correctable_error_count(adev, umc_reg_offset,
+						   &(err_data->ce_count));
+	umc_v6_1_querry_uncorrectable_error_count(adev, umc_reg_offset,
+						  &(err_data->ue_count));
+}
+
+static void umc_v6_1_query_ras_error_count(struct amdgpu_device *adev,
+					   void *ras_error_status)
+{
+	amdgpu_umc_for_each_channel(umc_v6_1_query_error_count);
+}
+
+static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
+					 struct ras_err_data *err_data,
+					 uint32_t umc_reg_offset, uint32_t channel_index)
+{
+	uint32_t lsb, mc_umc_status_addr;
+	uint64_t mc_umc_status, err_addr;
+
+	mc_umc_status_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+
+	/* skip error address process if -ENOMEM */
+	if (!err_data->err_addr) {
+		/* clear umc status */
+		WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+		return;
+	}
+
+	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+
+	/* calculate error address if ue/ce error is detected */
+	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
+	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
+	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) {
+		err_addr = RREG64_PCIE(smnMCA_UMC0_MCUMC_ADDRT0 + umc_reg_offset * 4);
+
+		/* the lowest lsb bits should be ignored */
+		lsb = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, LSB);
+		err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr);
+		err_addr &= ~((0x1ULL << lsb) - 1);
+
+		/* translate umc channel address to soc pa, 3 parts are included */
+		err_data->err_addr[err_data->err_addr_cnt] =
+						ADDR_OF_8KB_BLOCK(err_addr) |
+						ADDR_OF_256B_BLOCK(channel_index) |
+						OFFSET_IN_256B_BLOCK(err_addr);
+
+		err_data->err_addr_cnt++;
+	}
+
+	/* clear umc status */
+	WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+}
+
+static void umc_v6_1_query_ras_error_address(struct amdgpu_device *adev,
+					     void *ras_error_status)
+{
+	amdgpu_umc_for_each_channel(umc_v6_1_query_error_address);
+}
+
+static void umc_v6_1_ras_init_per_channel(struct amdgpu_device *adev,
+					 struct ras_err_data *err_data,
+					 uint32_t umc_reg_offset, uint32_t channel_index)
+{
+	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
+	uint32_t ecc_err_cnt_addr;
+
+	ecc_err_cnt_sel_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+	ecc_err_cnt_addr =
+		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+
+	/* select the lower chip and check the error count */
+	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
+					EccErrCntCsSel, 0);
+	/* set ce error interrupt type to APIC based interrupt */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
+					EccErrInt, 0x1);
+	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	/* set error count to initial value */
+	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+
+	/* select the higher chip and check the err counter */
+	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
+					EccErrCntCsSel, 1);
+	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+}
+
+static void umc_v6_1_ras_init(struct amdgpu_device *adev)
+{
+	void *ras_error_status = NULL;
+
+	amdgpu_umc_for_each_channel(umc_v6_1_ras_init_per_channel);
+}
+
+const struct amdgpu_umc_funcs umc_v6_1_funcs = {
+	.ras_init = umc_v6_1_ras_init,
+	.query_ras_error_count = umc_v6_1_query_ras_error_count,
+	.query_ras_error_address = umc_v6_1_query_ras_error_address,
+	.enable_umc_index_mode = umc_v6_1_enable_umc_index_mode,
+	.disable_umc_index_mode = umc_v6_1_disable_umc_index_mode,
+};