Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This seems to have been a comparatively quieter merge window, I assume
  due to holidays etc. The "biggest" change is AMD header cleanups, which
  merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
  with the etnaviv driver wanting to reuse the code, hopefully other drivers
  can go in the same direction.

  Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
  elsewhere.

  Core:
   - Add .last_close and .output_poll_changed helpers to reduce driver footprints
   - Fix plane clipping
   - Improved debug printing support
   - Add panel orientation property
   - Update edid derived properties at edid setting
   - Reduction in fbdev driver footprint
   - Move amdgpu scheduler into core for other drivers to use.

  i915:
   - Selftest and IGT improvements
   - Fast boot prep work on IPS, pipe config
   - HW workarounds for Cannonlake, Geminilake
   - Cannonlake clock and HDMI2.0 fixes
   - GPU cache invalidation and context switch improvements
   - Display planes cleanup
   - New PMU interface for perf queries
   - New firmware support for KBL/SKL
   - Geminilake HW workaround for perforamce
   - Coffeelake stolen memory improvements
   - GPU reset robustness work
   - Cannonlake horizontal plane flipping
   - GVT work

  amdgpu/radeon:
   - RV and Vega header file cleanups (lots of lines gone!)
   - TTM operation context support
   - 48-bit GPUVM support for Vega/RV
   - ECC support for Vega
   - Resizeable BAR support
   - Multi-display sync support
   - Enable swapout for reserved BOs during allocation
   - S3 fixes on Raven
   - GPU reset cleanup and fixes
   - 2+1 level GPU page table

  amdkfd:
   - GFX7/8 SDMA user queues support
   - Hardware scheduling for multiple processes
   - dGPU prep work

  rcar:
   - Added R8A7743/5 support
   - System suspend/resume support

  sun4i:
   - Multi-plane support for YUV formats
   - A83T and LVDS support

  msm:
   - Devfreq support for GPU

  tegra:
   - Prep work for adding Tegra186 support
   - Tegra186 HDMI support
   - HDMI2.0 and zpos support by using generic helpers

  tilcdc:
   - Misc fixes

  omapdrm:
   - Support memory bandwidth limits
   - DSI command mode panel cleanups
   - DMM error handling

  exynos:
   - drop the old IPP subdriver.

  etnaviv:
   - Occlusion query fixes
   - Job handling fixes
   - Prep work for hooking in gpu scheduler

  armada:
   - Move closer to atomic modesetting
   - Allow disabling primary plane if overlay is full screen

  imx:
   - Format modifier support
   - Add tile prefetch to PRE
   - Runtime PM support for PRG

  ast:
   - fix LUT loading"

* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
  drm/ast: Load lut in crtc_commit
  drm: Check for lessee in DROP_MASTER ioctl
  drm: fix gpu scheduler link order
  drm/amd/display: Demote error print to debug print when ATOM impl missing
  dma-buf: fix reservation_object_wait_timeout_rcu once more v2
  drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
  drm/amd/amdgpu: Add Polaris version check
  drm/amdgpu: Reenable manual GPU reset from sysfs
  drm/amdgpu: disable MMHUB power gating on raven
  drm/ttm: Don't unreserve swapped BOs that were previously reserved
  drm/ttm: Don't add swapped BOs to swap-LRU list
  drm/amdgpu: only check for ECC on Vega10
  drm/amd/powerplay: Fix smu_table_entry.handle type
  drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
  drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
  drm/radeon: fill in rb backend map on evergreen/ni.
  drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
  drm/ttm: only free pages rather than update global memory count together
  drm/amdgpu: fix CPU based VM updates
  drm/amdgpu: fix typo in amdgpu_vce_validate_bo
  ...

1 files changed, 90 insertions, 63 deletions

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index d453756ca128..e42d9a4de322 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -207,6 +207,8 @@
 #include "i915_oa_kblgt3.h"
 #include "i915_oa_glk.h"
 #include "i915_oa_cflgt2.h"
+#include "i915_oa_cflgt3.h"
+#include "i915_oa_cnl.h"
 
 /* HW requires this to be a power of two, between 128k and 16M, though driver
  * is currently generally designed assuming the largest 16M size is used such
@@ -1214,9 +1216,9 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	if (i915_modparams.enable_execlists)
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
-	else {
+	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
 		struct intel_ring *ring;
 		int ret;
@@ -1260,7 +1262,7 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	if (i915_modparams.enable_execlists) {
+	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
 	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
@@ -1724,10 +1726,9 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr
 							 GFP_KERNEL);
 	}
 
-	ret = i915_switch_context(req);
 	i915_add_request(req);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -1851,7 +1852,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv,
 	 * be read back from automatically triggered reports, as part of the
 	 * RPT_ID field.
 	 */
-	if (IS_GEN9(dev_priv)) {
+	if (IS_GEN9(dev_priv) || IS_GEN10(dev_priv)) {
 		I915_WRITE(GEN8_OA_DEBUG,
 			   _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
 					      GEN9_OA_DEBUG_INCLUDE_CLK_RATIO));
@@ -1884,6 +1885,16 @@ static void gen8_disable_metric_set(struct drm_i915_private *dev_priv)
 
 }
 
+static void gen10_disable_metric_set(struct drm_i915_private *dev_priv)
+{
+	/* Reset all contexts' slices/subslices configurations. */
+	gen8_configure_all_contexts(dev_priv, NULL, false);
+
+	/* Make sure we disable noa to save power. */
+	I915_WRITE(RPM_CONFIG1,
+		   I915_READ(RPM_CONFIG1) & ~GEN10_GT_NOA_ENABLE);
+}
+
 static void gen7_oa_enable(struct drm_i915_private *dev_priv)
 {
 	/*
@@ -2679,8 +2690,8 @@ err:
 
 static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent)
 {
-	return div_u64(1000000000ULL * (2ULL << exponent),
-		       dev_priv->perf.oa.timestamp_frequency);
+	return div64_u64(1000000000ULL * (2ULL << exponent),
+			 1000ULL * INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz);
 }
 
 /**
@@ -2934,6 +2945,10 @@ void i915_perf_register(struct drm_i915_private *dev_priv)
 	} else if (IS_COFFEELAKE(dev_priv)) {
 		if (IS_CFL_GT2(dev_priv))
 			i915_perf_load_test_config_cflgt2(dev_priv);
+		if (IS_CFL_GT3(dev_priv))
+			i915_perf_load_test_config_cflgt3(dev_priv);
+	} else if (IS_CANNONLAKE(dev_priv)) {
+		i915_perf_load_test_config_cnl(dev_priv);
 	}
 
 	if (dev_priv->perf.oa.test_config.id == 0)
@@ -2991,7 +3006,7 @@ static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(flex_eu_regs); i++) {
-		if (flex_eu_regs[i].reg == addr)
+		if (i915_mmio_reg_offset(flex_eu_regs[i]) == addr)
 			return true;
 	}
 	return false;
@@ -2999,31 +3014,47 @@ static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
 
 static bool gen7_is_valid_b_counter_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
-	return (addr >= OASTARTTRIG1.reg && addr <= OASTARTTRIG8.reg) ||
-		(addr >= OAREPORTTRIG1.reg && addr <= OAREPORTTRIG8.reg) ||
-		(addr >= OACEC0_0.reg && addr <= OACEC7_1.reg);
+	return (addr >= i915_mmio_reg_offset(OASTARTTRIG1) &&
+		addr <= i915_mmio_reg_offset(OASTARTTRIG8)) ||
+		(addr >= i915_mmio_reg_offset(OAREPORTTRIG1) &&
+		 addr <= i915_mmio_reg_offset(OAREPORTTRIG8)) ||
+		(addr >= i915_mmio_reg_offset(OACEC0_0) &&
+		 addr <= i915_mmio_reg_offset(OACEC7_1));
 }
 
 static bool gen7_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
-	return addr == HALF_SLICE_CHICKEN2.reg ||
-		(addr >= MICRO_BP0_0.reg && addr <= NOA_WRITE.reg) ||
-		(addr >= OA_PERFCNT1_LO.reg && addr <= OA_PERFCNT2_HI.reg) ||
-		(addr >= OA_PERFMATRIX_LO.reg && addr <= OA_PERFMATRIX_HI.reg);
+	return addr == i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) ||
+		(addr >= i915_mmio_reg_offset(MICRO_BP0_0) &&
+		 addr <= i915_mmio_reg_offset(NOA_WRITE)) ||
+		(addr >= i915_mmio_reg_offset(OA_PERFCNT1_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFCNT2_HI)) ||
+		(addr >= i915_mmio_reg_offset(OA_PERFMATRIX_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFMATRIX_HI));
 }
 
 static bool gen8_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
 	return gen7_is_valid_mux_addr(dev_priv, addr) ||
-		addr == WAIT_FOR_RC6_EXIT.reg ||
-		(addr >= RPM_CONFIG0.reg && addr <= NOA_CONFIG(8).reg);
+		addr == i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) ||
+		(addr >= i915_mmio_reg_offset(RPM_CONFIG0) &&
+		 addr <= i915_mmio_reg_offset(NOA_CONFIG(8)));
+}
+
+static bool gen10_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+{
+	return gen8_is_valid_mux_addr(dev_priv, addr) ||
+		(addr >= i915_mmio_reg_offset(OA_PERFCNT3_LO) &&
+		 addr <= i915_mmio_reg_offset(OA_PERFCNT4_HI));
 }
 
 static bool hsw_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 {
 	return gen7_is_valid_mux_addr(dev_priv, addr) ||
 		(addr >= 0x25100 && addr <= 0x2FF90) ||
-		addr == 0x9ec0;
+		(addr >= i915_mmio_reg_offset(HSW_MBVID2_NOA0) &&
+		 addr <= i915_mmio_reg_offset(HSW_MBVID2_NOA9)) ||
+		addr == i915_mmio_reg_offset(HSW_MBVID2_MISR0);
 }
 
 static bool chv_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
@@ -3038,14 +3069,14 @@ static uint32_t mask_reg_value(u32 reg, u32 val)
 	 * WaDisableSTUnitPowerOptimization workaround. Make sure the value
 	 * programmed by userspace doesn't change this.
 	 */
-	if (HALF_SLICE_CHICKEN2.reg == reg)
+	if (i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) == reg)
 		val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE);
 
 	/* WAIT_FOR_RC6_EXIT has only one bit fullfilling the function
 	 * indicated by its name and a bunch of selection fields used by OA
 	 * configs.
 	 */
-	if (WAIT_FOR_RC6_EXIT.reg == reg)
+	if (i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) == reg)
 		val = val & ~_MASKED_BIT_ENABLE(HSW_WAIT_FOR_RC6_EXIT_ENABLE);
 
 	return val;
@@ -3392,8 +3423,6 @@ static struct ctl_table dev_root[] = {
  */
 void i915_perf_init(struct drm_i915_private *dev_priv)
 {
-	dev_priv->perf.oa.timestamp_frequency = 0;
-
 	if (IS_HASWELL(dev_priv)) {
 		dev_priv->perf.oa.ops.is_valid_b_counter_reg =
 			gen7_is_valid_b_counter_addr;
@@ -3409,70 +3438,68 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 		dev_priv->perf.oa.ops.oa_hw_tail_read =
 			gen7_oa_hw_tail_read;
 
-		dev_priv->perf.oa.timestamp_frequency = 12500000;
-
 		dev_priv->perf.oa.oa_formats = hsw_oa_formats;
-	} else if (i915_modparams.enable_execlists) {
+	} else if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
 		/* Note: that although we could theoretically also support the
 		 * legacy ringbuffer mode on BDW (and earlier iterations of
 		 * this driver, before upstreaming did this) it didn't seem
 		 * worth the complexity to maintain now that BDW+ enable
 		 * execlist mode by default.
 		 */
-		dev_priv->perf.oa.ops.is_valid_b_counter_reg =
-			gen7_is_valid_b_counter_addr;
-		dev_priv->perf.oa.ops.is_valid_mux_reg =
-			gen8_is_valid_mux_addr;
-		dev_priv->perf.oa.ops.is_valid_flex_reg =
-			gen8_is_valid_flex_addr;
+		dev_priv->perf.oa.oa_formats = gen8_plus_oa_formats;
 
 		dev_priv->perf.oa.ops.init_oa_buffer = gen8_init_oa_buffer;
-		dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set;
-		dev_priv->perf.oa.ops.disable_metric_set = gen8_disable_metric_set;
 		dev_priv->perf.oa.ops.oa_enable = gen8_oa_enable;
 		dev_priv->perf.oa.ops.oa_disable = gen8_oa_disable;
 		dev_priv->perf.oa.ops.read = gen8_oa_read;
 		dev_priv->perf.oa.ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
-		dev_priv->perf.oa.oa_formats = gen8_plus_oa_formats;
-
-		if (IS_GEN8(dev_priv)) {
-			dev_priv->perf.oa.ctx_oactxctrl_offset = 0x120;
-			dev_priv->perf.oa.ctx_flexeu0_offset = 0x2ce;
-
-			dev_priv->perf.oa.timestamp_frequency = 12500000;
+		if (IS_GEN8(dev_priv) || IS_GEN9(dev_priv)) {
+			dev_priv->perf.oa.ops.is_valid_b_counter_reg =
+				gen7_is_valid_b_counter_addr;
+			dev_priv->perf.oa.ops.is_valid_mux_reg =
+				gen8_is_valid_mux_addr;
+			dev_priv->perf.oa.ops.is_valid_flex_reg =
+				gen8_is_valid_flex_addr;
 
-			dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<25);
 			if (IS_CHERRYVIEW(dev_priv)) {
 				dev_priv->perf.oa.ops.is_valid_mux_reg =
 					chv_is_valid_mux_addr;
 			}
-		} else if (IS_GEN9(dev_priv)) {
+
+			dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set;
+			dev_priv->perf.oa.ops.disable_metric_set = gen8_disable_metric_set;
+
+			if (IS_GEN8(dev_priv)) {
+				dev_priv->perf.oa.ctx_oactxctrl_offset = 0x120;
+				dev_priv->perf.oa.ctx_flexeu0_offset = 0x2ce;
+
+				dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<25);
+			} else {
+				dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128;
+				dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de;
+
+				dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
+			}
+		} else if (IS_GEN10(dev_priv)) {
+			dev_priv->perf.oa.ops.is_valid_b_counter_reg =
+				gen7_is_valid_b_counter_addr;
+			dev_priv->perf.oa.ops.is_valid_mux_reg =
+				gen10_is_valid_mux_addr;
+			dev_priv->perf.oa.ops.is_valid_flex_reg =
+				gen8_is_valid_flex_addr;
+
+			dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set;
+			dev_priv->perf.oa.ops.disable_metric_set = gen10_disable_metric_set;
+
 			dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128;
 			dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de;
 
 			dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
-
-			switch (dev_priv->info.platform) {
-			case INTEL_BROXTON:
-			case INTEL_GEMINILAKE:
-				dev_priv->perf.oa.timestamp_frequency = 19200000;
-				break;
-			case INTEL_SKYLAKE:
-			case INTEL_KABYLAKE:
-			case INTEL_COFFEELAKE:
-				dev_priv->perf.oa.timestamp_frequency = 12000000;
-				break;
-			default:
-				/* Leave timestamp_frequency to 0 so we can
-				 * detect unsupported platforms.
-				 */
-				break;
-			}
 		}
 	}
 
-	if (dev_priv->perf.oa.timestamp_frequency) {
+	if (dev_priv->perf.oa.ops.enable_metric_set) {
 		hrtimer_init(&dev_priv->perf.oa.poll_check_timer,
 				CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		dev_priv->perf.oa.poll_check_timer.function = oa_poll_check_timer_cb;
@@ -3482,8 +3509,8 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 		mutex_init(&dev_priv->perf.lock);
 		spin_lock_init(&dev_priv->perf.oa.oa_buffer.ptr_lock);
 
-		oa_sample_rate_hard_limit =
-			dev_priv->perf.oa.timestamp_frequency / 2;
+		oa_sample_rate_hard_limit = 1000 *
+			(INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz / 2);
 		dev_priv->perf.sysctl_header = register_sysctl_table(dev_root);
 
 		mutex_init(&dev_priv->perf.metrics_lock);