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, 125 insertions, 77 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index ef6e91f9f51c..5850c8e34caa 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -93,6 +93,96 @@ const struct attribute_group *df_v3_6_attr_groups[] = {
 		NULL
 };
 
+static uint64_t df_v3_6_get_fica(struct amdgpu_device *adev,
+				 uint32_t ficaa_val)
+{
+	unsigned long flags, address, data;
+	uint32_t ficadl_val, ficadh_val;
+
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
+	WREG32(data, ficaa_val);
+
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3);
+	ficadl_val = RREG32(data);
+
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataHi3);
+	ficadh_val = RREG32(data);
+
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+
+	return (((ficadh_val & 0xFFFFFFFFFFFFFFFF) << 32) | ficadl_val);
+}
+
+static void df_v3_6_set_fica(struct amdgpu_device *adev, uint32_t ficaa_val,
+			     uint32_t ficadl_val, uint32_t ficadh_val)
+{
+	unsigned long flags, address, data;
+
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
+	WREG32(data, ficaa_val);
+
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3);
+	WREG32(data, ficadl_val);
+
+	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessDataHi3);
+	WREG32(data, ficadh_val);
+
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
+/*
+ * df_v3_6_perfmon_rreg - read perfmon lo and hi
+ *
+ * required to be atomic.  no mmio method provided so subsequent reads for lo
+ * and hi require to preserve df finite state machine
+ */
+static void df_v3_6_perfmon_rreg(struct amdgpu_device *adev,
+			    uint32_t lo_addr, uint32_t *lo_val,
+			    uint32_t hi_addr, uint32_t *hi_val)
+{
+	unsigned long flags, address, data;
+
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, lo_addr);
+	*lo_val = RREG32(data);
+	WREG32(address, hi_addr);
+	*hi_val = RREG32(data);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
+/*
+ * df_v3_6_perfmon_wreg - write to perfmon lo and hi
+ *
+ * required to be atomic.  no mmio method provided so subsequent reads after
+ * data writes cannot occur to preserve data fabrics finite state machine.
+ */
+static void df_v3_6_perfmon_wreg(struct amdgpu_device *adev, uint32_t lo_addr,
+			    uint32_t lo_val, uint32_t hi_addr, uint32_t hi_val)
+{
+	unsigned long flags, address, data;
+
+	address = adev->nbio_funcs->get_pcie_index_offset(adev);
+	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, lo_addr);
+	WREG32(data, lo_val);
+	WREG32(address, hi_addr);
+	WREG32(data, hi_val);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+}
+
 /* get the number of df counters available */
 static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 		struct device_attribute *attr,
@@ -268,6 +358,10 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev,
 					  uint32_t *lo_val,
 					  uint32_t *hi_val)
 {
+
+	uint32_t eventsel, instance, unitmask;
+	uint32_t instance_10, instance_5432, instance_76;
+
 	df_v3_6_pmc_get_addr(adev, config, 1, lo_base_addr, hi_base_addr);
 
 	if ((*lo_base_addr == 0) || (*hi_base_addr == 0)) {
@@ -276,40 +370,33 @@ static int df_v3_6_pmc_get_ctrl_settings(struct amdgpu_device *adev,
 		return -ENXIO;
 	}
 
-	if (lo_val && hi_val) {
-		uint32_t eventsel, instance, unitmask;
-		uint32_t instance_10, instance_5432, instance_76;
+	eventsel = DF_V3_6_GET_EVENT(config) & 0x3f;
+	unitmask = DF_V3_6_GET_UNITMASK(config) & 0xf;
+	instance = DF_V3_6_GET_INSTANCE(config);
 
-		eventsel = DF_V3_6_GET_EVENT(config) & 0x3f;
-		unitmask = DF_V3_6_GET_UNITMASK(config) & 0xf;
-		instance = DF_V3_6_GET_INSTANCE(config);
+	instance_10 = instance & 0x3;
+	instance_5432 = (instance >> 2) & 0xf;
+	instance_76 = (instance >> 6) & 0x3;
 
-		instance_10 = instance & 0x3;
-		instance_5432 = (instance >> 2) & 0xf;
-		instance_76 = (instance >> 6) & 0x3;
+	*lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel | (1 << 22);
+	*hi_val = (instance_76 << 29) | instance_5432;
 
-		*lo_val = (unitmask << 8) | (instance_10 << 6) | eventsel;
-		*hi_val = (instance_76 << 29) | instance_5432;
-	}
+	DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
+		config, *lo_base_addr, *hi_base_addr, *lo_val, *hi_val);
 
 	return 0;
 }
 
-/* assign df performance counters for read */
-static int df_v3_6_pmc_assign_cntr(struct amdgpu_device *adev,
-				   uint64_t config,
-				   int *is_assigned)
+/* add df performance counters for read */
+static int df_v3_6_pmc_add_cntr(struct amdgpu_device *adev,
+				   uint64_t config)
 {
 	int i, target_cntr;
 
-	*is_assigned = 0;
-
 	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
 
-	if (target_cntr >= 0) {
-		*is_assigned = 1;
+	if (target_cntr >= 0)
 		return 0;
-	}
 
 	for (i = 0; i < DF_V3_6_MAX_COUNTERS; i++) {
 		if (adev->df_perfmon_config_assign_mask[i] == 0U) {
@@ -344,45 +431,13 @@ static void df_v3_6_reset_perfmon_cntr(struct amdgpu_device *adev,
 	if ((lo_base_addr == 0) || (hi_base_addr == 0))
 		return;
 
-	WREG32_PCIE(lo_base_addr, 0UL);
-	WREG32_PCIE(hi_base_addr, 0UL);
-}
-
-
-static int df_v3_6_add_perfmon_cntr(struct amdgpu_device *adev,
-				      uint64_t config)
-{
-	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
-	int ret, is_assigned;
-
-	ret = df_v3_6_pmc_assign_cntr(adev, config, &is_assigned);
-
-	if (ret || is_assigned)
-		return ret;
-
-	ret = df_v3_6_pmc_get_ctrl_settings(adev,
-			config,
-			&lo_base_addr,
-			&hi_base_addr,
-			&lo_val,
-			&hi_val);
-
-	if (ret)
-		return ret;
-
-	DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
-			config, lo_base_addr, hi_base_addr, lo_val, hi_val);
-
-	WREG32_PCIE(lo_base_addr, lo_val);
-	WREG32_PCIE(hi_base_addr, hi_val);
-
-	return ret;
+	df_v3_6_perfmon_wreg(adev, lo_base_addr, 0, hi_base_addr, 0);
 }
 
 static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 			     int is_enable)
 {
-	uint32_t lo_base_addr, hi_base_addr, lo_val;
+	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
 	int ret = 0;
 
 	switch (adev->asic_type) {
@@ -391,24 +446,20 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 		df_v3_6_reset_perfmon_cntr(adev, config);
 
 		if (is_enable) {
-			ret = df_v3_6_add_perfmon_cntr(adev, config);
+			ret = df_v3_6_pmc_add_cntr(adev, config);
 		} else {
 			ret = df_v3_6_pmc_get_ctrl_settings(adev,
 					config,
 					&lo_base_addr,
 					&hi_base_addr,
-					NULL,
-					NULL);
+					&lo_val,
+					&hi_val);
 
 			if (ret)
 				return ret;
 
-			lo_val = RREG32_PCIE(lo_base_addr);
-
-			DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x",
-				config, lo_base_addr, hi_base_addr, lo_val);
-
-			WREG32_PCIE(lo_base_addr, lo_val | (1ULL << 22));
+			df_v3_6_perfmon_wreg(adev, lo_base_addr, lo_val,
+					hi_base_addr, hi_val);
 		}
 
 		break;
@@ -422,7 +473,7 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
 			    int is_disable)
 {
-	uint32_t lo_base_addr, hi_base_addr, lo_val;
+	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
 	int ret = 0;
 
 	switch (adev->asic_type) {
@@ -431,18 +482,13 @@ static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
 			config,
 			&lo_base_addr,
 			&hi_base_addr,
-			NULL,
-			NULL);
+			&lo_val,
+			&hi_val);
 
 		if (ret)
 			return ret;
 
-		lo_val = RREG32_PCIE(lo_base_addr);
-
-		DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x",
-				config, lo_base_addr, hi_base_addr, lo_val);
-
-		WREG32_PCIE(lo_base_addr, lo_val & ~(1ULL << 22));
+		df_v3_6_perfmon_wreg(adev, lo_base_addr, 0, hi_base_addr, 0);
 
 		if (is_disable)
 			df_v3_6_pmc_release_cntr(adev, config);
@@ -471,8 +517,8 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 		if ((lo_base_addr == 0) || (hi_base_addr == 0))
 			return;
 
-		lo_val = RREG32_PCIE(lo_base_addr);
-		hi_val = RREG32_PCIE(hi_base_addr);
+		df_v3_6_perfmon_rreg(adev, lo_base_addr, &lo_val,
+				hi_base_addr, &hi_val);
 
 		*count  = ((hi_val | 0ULL) << 32) | (lo_val | 0ULL);
 
@@ -480,7 +526,7 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 			*count = 0;
 
 		DRM_DEBUG_DRIVER("config=%llx addr=%08x:%08x val=%08x:%08x",
-			config, lo_base_addr, hi_base_addr, lo_val, hi_val);
+			 config, lo_base_addr, hi_base_addr, lo_val, hi_val);
 
 		break;
 
@@ -499,5 +545,7 @@ const struct amdgpu_df_funcs df_v3_6_funcs = {
 	.get_clockgating_state = df_v3_6_get_clockgating_state,
 	.pmc_start = df_v3_6_pmc_start,
 	.pmc_stop = df_v3_6_pmc_stop,
-	.pmc_get_count = df_v3_6_pmc_get_count
+	.pmc_get_count = df_v3_6_pmc_get_count,
+	.get_fica = df_v3_6_get_fica,
+	.set_fica = df_v3_6_set_fica
 };