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, 32 insertions, 21 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index da11ceba0698..c87263ed20ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
 #include "amdgpu_pm.h"
+#include "amdgpu_cs.h"
 #include "soc15.h"
 #include "soc15d.h"
 #include "vcn_v2_0.h"
@@ -213,11 +214,14 @@ static int vcn_v3_0_sw_init(void *handle)
 				return r;
 		}
 
-		fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
+		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SW_RING_FLAG) |
 					     cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) |
 					     cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB);
 		fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED);
+
+		if (amdgpu_vcnfw_log)
+			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 	}
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -249,7 +253,7 @@ static int vcn_v3_0_sw_fini(void *handle)
 
 			if (adev->vcn.harvest_config & (1 << i))
 				continue;
-			fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
+			fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 			fw_shared->present_flag_0 = 0;
 			fw_shared->sw_ring.is_enabled = false;
 		}
@@ -295,6 +299,7 @@ static int vcn_v3_0_hw_init(void *handle)
 			ring = &adev->vcn.inst[i].ring_dec;
 			if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) {
 				ring->sched.ready = false;
+				ring->no_scheduler = true;
 				dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
 			} else {
 				ring->wptr = 0;
@@ -307,6 +312,7 @@ static int vcn_v3_0_hw_init(void *handle)
 				ring = &adev->vcn.inst[i].ring_enc[j];
 				if (amdgpu_vcn_is_disabled_vcn(adev, VCN_ENCODE_RING, i)) {
 					ring->sched.ready = false;
+					ring->no_scheduler = true;
 					dev_info(adev->dev, "ring %s is disabled by hypervisor\n", ring->name);
 				} else {
 					ring->wptr = 0;
@@ -469,9 +475,9 @@ static void vcn_v3_0_mc_resume(struct amdgpu_device *adev, int inst)
 
 	/* non-cache window */
 	WREG32_SOC15(VCN, inst, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW,
-		lower_32_bits(adev->vcn.inst[inst].fw_shared_gpu_addr));
+		lower_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr));
 	WREG32_SOC15(VCN, inst, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH,
-		upper_32_bits(adev->vcn.inst[inst].fw_shared_gpu_addr));
+		upper_32_bits(adev->vcn.inst[inst].fw_shared.gpu_addr));
 	WREG32_SOC15(VCN, inst, mmUVD_VCPU_NONCACHE_OFFSET0, 0);
 	WREG32_SOC15(VCN, inst, mmUVD_VCPU_NONCACHE_SIZE0,
 		AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)));
@@ -558,10 +564,10 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
 	/* non-cache window */
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 			VCN, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW),
-			lower_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect);
+			lower_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect);
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 			VCN, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH),
-			upper_32_bits(adev->vcn.inst[inst_idx].fw_shared_gpu_addr), 0, indirect);
+			upper_32_bits(adev->vcn.inst[inst_idx].fw_shared.gpu_addr), 0, indirect);
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 			VCN, inst_idx, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
@@ -923,7 +929,7 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst)
 
 static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
-	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr;
+	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
 
@@ -1220,7 +1226,7 @@ static int vcn_v3_0_start(struct amdgpu_device *adev)
 		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
 		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_CNTL, tmp);
 
-		fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
+		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
 		fw_shared->multi_queue.decode_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
 
 		/* programm the RB_BASE for ring buffer */
@@ -1611,7 +1617,7 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
 
 				if (adev->ip_versions[UVD_HWIP][0] != IP_VERSION(3, 0, 33)) {
 					/* Restore */
-					fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr;
+					fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 					fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
 					ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 					ring->wptr = 0;
@@ -1700,7 +1706,7 @@ static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
 		/*whenever update RBC_RB_WPTR, we save the wptr in shared rb.wptr and scratch2 */
-		fw_shared = adev->vcn.inst[ring->me].fw_shared_cpu_addr;
+		fw_shared = adev->vcn.inst[ring->me].fw_shared.cpu_addr;
 		fw_shared->rb.wptr = lower_32_bits(ring->wptr);
 		WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2,
 			lower_32_bits(ring->wptr));
@@ -1780,6 +1786,7 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_DEC,
 	.align_mask = 0x3f,
 	.nop = VCN_DEC_SW_CMD_NO_OP,
+	.secure_submission_supported = true,
 	.vmhub = AMDGPU_MMHUB_0,
 	.get_rptr = vcn_v3_0_dec_ring_get_rptr,
 	.get_wptr = vcn_v3_0_dec_ring_get_wptr,
@@ -1806,21 +1813,23 @@ static const struct amdgpu_ring_funcs vcn_v3_0_dec_sw_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p)
+static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p,
+				struct amdgpu_job *job)
 {
 	struct drm_gpu_scheduler **scheds;
 
 	/* The create msg must be in the first IB submitted */
-	if (atomic_read(&p->entity->fence_seq))
+	if (atomic_read(&job->base.entity->fence_seq))
 		return -EINVAL;
 
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC]
 		[AMDGPU_RING_PRIO_DEFAULT].sched;
-	drm_sched_entity_modify_sched(p->entity, scheds, 1);
+	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
 	return 0;
 }
 
-static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
+static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,
+			    uint64_t addr)
 {
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_bo_va_mapping *map;
@@ -1891,7 +1900,7 @@ static int vcn_v3_0_dec_msg(struct amdgpu_cs_parser *p, uint64_t addr)
 		if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11)
 			continue;
 
-		r = vcn_v3_0_limit_sched(p);
+		r = vcn_v3_0_limit_sched(p, job);
 		if (r)
 			goto out;
 	}
@@ -1902,10 +1911,10 @@ out:
 }
 
 static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
-					   uint32_t ib_idx)
+					   struct amdgpu_job *job,
+					   struct amdgpu_ib *ib)
 {
-	struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched);
-	struct amdgpu_ib *ib = &p->job->ibs[ib_idx];
+	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	uint32_t msg_lo = 0, msg_hi = 0;
 	unsigned i;
 	int r;
@@ -1915,8 +1924,8 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 		return 0;
 
 	for (i = 0; i < ib->length_dw; i += 2) {
-		uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i);
-		uint32_t val = amdgpu_get_ib_value(p, ib_idx, i + 1);
+		uint32_t reg = amdgpu_ib_get_value(ib, i);
+		uint32_t val = amdgpu_ib_get_value(ib, i + 1);
 
 		if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) {
 			msg_lo = val;
@@ -1924,7 +1933,8 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 			msg_hi = val;
 		} else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0) &&
 			   val == 0) {
-			r = vcn_v3_0_dec_msg(p, ((u64)msg_hi) << 32 | msg_lo);
+			r = vcn_v3_0_dec_msg(p, job,
+					     ((u64)msg_hi) << 32 | msg_lo);
 			if (r)
 				return r;
 		}
@@ -1935,6 +1945,7 @@ static int vcn_v3_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 static const struct amdgpu_ring_funcs vcn_v3_0_dec_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_DEC,
 	.align_mask = 0xf,
+	.secure_submission_supported = true,
 	.vmhub = AMDGPU_MMHUB_0,
 	.get_rptr = vcn_v3_0_dec_ring_get_rptr,
 	.get_wptr = vcn_v3_0_dec_ring_get_wptr,