Merge tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of work all over, Intel improving DG2 support, amdkfd CRIU
  support, msm new hw support, and faster fbdev support.

  dma-buf:
   - rename dma-buf-map to iosys-map

  core:
   - move buddy allocator to core
   - add pci/platform init macros
   - improve EDID parser deep color handling
   - EDID timing type 7 support
   - add GPD Win Max quirk
   - add yes/no helpers to string_helpers
   - flatten syncobj chains
   - add nomodeset support to lots of drivers
   - improve fb-helper clipping support
   - add default property value interface

  fbdev:
   - improve fbdev ops speed

  ttm:
   - add a backpointer from ttm bo->ttm resource

  dp:
   - move displayport headers
   - add a dp helper module

  bridge:
   - anx7625 atomic support, HDCP support

  panel:
   - split out panel-lvds and lvds bindings
   - find panels in OF subnodes

  privacy:
   - add chromeos privacy screen support

  fb:
   - hot unplug fw fb on forced removal

  simpledrm:
   - request region instead of marking ioresource busy
   - add panel oreintation property

  udmabuf:
   - fix oops with 0 pages

  amdgpu:
   - power management code cleanup
   - Enable freesync video mode by default
   - RAS code cleanup
   - Improve VRAM access for debug using SDMA
   - SR-IOV rework special register access and fixes
   - profiling power state request ioctl
   - expose IP discovery via sysfs
   - Cyan skillfish updates
   - GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
   - expose benchmark tests via debugfs
   - add module param to disable XGMI for testing
   - GPU reset debugfs register dumping support

  amdkfd:
   - CRIU support
   - SDMA queue fixes

  radeon:
   - UVD suspend fix
   - iMac backlight fix

  i915:
   - minimal parallel submission for execlists
   - DG2-G12 subplatform added
   - DG2 programming workarounds
   - DG2 accelerated migration support
   - flat CCS and CCS engine support for XeHP
   - initial small BAR support
   - drop fake LMEM support
   - ADL-N PCH support
   - bigjoiner updates
   - introduce VMA resources and async unbinding
   - register definitions cleanups
   - multi-FBC refactoring
   - DG1 OPROM over SPI support
   - ADL-N platform enabling
   - opregion mailbox #5 support
   - DP MST ESI improvements
   - drm device based logging
   - async flip optimisation for DG2
   - CPU arch abstraction fixes
   - improve GuC ADS init to work on aarch64
   - tweak TTM LRU priority hint
   - GuC 69.0.3 support
   - remove short term execbuf pins

  nouveau:
   - higher DP/eDP bitrates
   - backlight fixes

  msm:
   - dpu + dp support for sc8180x
   - dp support for sm8350
   - dpu + dsi support for qcm2290
   - 10nm dsi phy tuning support
   - bridge support for dp encoder
   - gpu support for additional 7c3 SKUs

  ingenic:
   - HDMI support for JZ4780
   - aux channel EDID support

  ast:
   - AST2600 support
   - add wide screen support
   - create DP/DVI connectors

  omapdrm:
   - fix implicit dma_buf fencing

  vc4:
   - add CSC + full range support
   - better display firmware handoff

  panfrost:
   - add initial dual-core GPU support

  stm:
   - new revision support
   - fb handover support

  mediatek:
   - transfer display binding document to yaml format.
   - add mt8195 display device binding.
   - allow commands to be sent during video mode.
   - add wait_for_event for crtc disable by cmdq.

  tegra:
   - YUV format support

  rcar-du:
   - LVDS support for M3-W+ (R8A77961)

  exynos:
   - BGR pixel format for FIMD device"

* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
  drm/i915/display: Do not re-enable PSR after it was marked as not reliable
  drm/i915/display: Fix HPD short pulse handling for eDP
  drm/amdgpu: Use drm_mode_copy()
  drm/radeon: Use drm_mode_copy()
  drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
  drm/amdgpu: Remove pointless on stack mode copies
  drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
  drm/amdgpu/dc: fix typos in comments
  drm/amdgpu: fix typos in comments
  drm/amd/pm: fix typos in comments
  drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
  drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
  drm/amdkfd: evict svm bo worker handle error
  drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
  drm/amdgpu: only allow secure submission on rings which support that
  drm/amdgpu: fixed the warnings reported by kernel test robot
  drm/amd/display: 3.2.177
  drm/amd/display: [FW Promotion] Release 0.0.108.0
  drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
  drm/amd/display: Wait for hubp read line for Pollock
  ...

1 files changed, 57 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b3489599e4de..07bef7128fdb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -8,9 +8,13 @@
 #include "gen8_engine_cs.h"
 #include "i915_drv.h"
 #include "i915_perf.h"
+#include "i915_reg.h"
+#include "intel_context.h"
 #include "intel_engine.h"
+#include "intel_engine_regs.h"
 #include "intel_gpu_commands.h"
 #include "intel_gt.h"
+#include "intel_gt_regs.h"
 #include "intel_lrc.h"
 #include "intel_lrc_reg.h"
 #include "intel_ring.h"
@@ -619,7 +623,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 	GEM_BUG_ON(GRAPHICS_VER(engine->i915) >= 12 &&
 		   !intel_engine_has_relative_mmio(engine));
 
-	if (engine->class == RENDER_CLASS) {
+	if (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE) {
 		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
 			return dg2_rcs_offsets;
 		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50))
@@ -1065,6 +1069,10 @@ lrc_pin(struct intel_context *ce,
 
 void lrc_unpin(struct intel_context *ce)
 {
+	if (unlikely(ce->parallel.last_rq)) {
+		i915_request_put(ce->parallel.last_rq);
+		ce->parallel.last_rq = NULL;
+	}
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
 		      ce->engine);
 }
@@ -1160,6 +1168,29 @@ gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs)
 	return cs;
 }
 
+/*
+ * On DG2 during context restore of a preempted context in GPGPU mode,
+ * RCS restore hang is detected. This is extremely timing dependent.
+ * To address this below sw wabb is implemented for DG2 A steppings.
+ */
+static u32 *
+dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs)
+{
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG);
+	*cs++ = 0x21;
+
+	*cs++ = MI_LOAD_REGISTER_REG;
+	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
+	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT1);
+
+	*cs++ = MI_LOAD_REGISTER_REG;
+	*cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base));
+	*cs++ = i915_mmio_reg_offset(GEN12_CULLBIT2);
+
+	return cs;
+}
+
 static u32 *
 gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 {
@@ -1167,6 +1198,11 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 	cs = gen12_emit_cmd_buf_wa(ce, cs);
 	cs = gen12_emit_restore_scratch(ce, cs);
 
+	/* Wa_22011450934:dg2 */
+	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_A0, STEP_B0) ||
+	    IS_DG2_GRAPHICS_STEP(ce->engine->i915, G11, STEP_A0, STEP_B0))
+		cs = dg2_emit_rcs_hang_wabb(ce, cs);
+
 	/* Wa_16013000631:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) ||
 	    IS_DG2_G11(ce->engine->i915))
@@ -1181,6 +1217,14 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
 	cs = gen12_emit_timestamp_wa(ce, cs);
 	cs = gen12_emit_restore_scratch(ce, cs);
 
+	/* Wa_16013000631:dg2 */
+	if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) ||
+	    IS_DG2_G11(ce->engine->i915))
+		if (ce->engine->class == COMPUTE_CLASS)
+			cs = gen8_emit_pipe_control(cs,
+						    PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE,
+						    0);
+
 	return cs;
 }
 
@@ -1583,7 +1627,7 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine)
 	unsigned int i;
 	int err;
 
-	if (engine->class != RENDER_CLASS)
+	if (!(engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
 		return;
 
 	switch (GRAPHICS_VER(engine->i915)) {
@@ -1686,6 +1730,17 @@ static void st_update_runtime_underflow(struct intel_context *ce, s32 dt)
 #endif
 }
 
+static u32 lrc_get_runtime(const struct intel_context *ce)
+{
+	/*
+	 * We can use either ppHWSP[16] which is recorded before the context
+	 * switch (and so excludes the cost of context switches) or use the
+	 * value from the context image itself, which is saved/restored earlier
+	 * and so includes the cost of the save.
+	 */
+	return READ_ONCE(ce->lrc_reg_state[CTX_TIMESTAMP]);
+}
+
 void lrc_update_runtime(struct intel_context *ce)
 {
 	u32 old;