Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

1 files changed, 44 insertions, 42 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 2b92cc8a7d1a..41b2c3aaa04a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -616,9 +616,6 @@ static inline u32 get_opcode(u32 cmd, int ring_id)
 {
 	struct decode_info *d_info;
 
-	if (ring_id >= I915_NUM_ENGINES)
-		return INVALID_OP;
-
 	d_info = ring_decode_info[ring_id][CMD_TYPE(cmd)];
 	if (d_info == NULL)
 		return INVALID_OP;
@@ -661,9 +658,6 @@ static inline void print_opcode(u32 cmd, int ring_id)
 	struct decode_info *d_info;
 	int i;
 
-	if (ring_id >= I915_NUM_ENGINES)
-		return;
-
 	d_info = ring_decode_info[ring_id][CMD_TYPE(cmd)];
 	if (d_info == NULL)
 		return;
@@ -1215,7 +1209,7 @@ static int gen8_check_mi_display_flip(struct parser_exec_state *s,
 	if (!info->async_flip)
 		return 0;
 
-	if (IS_SKYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		stride = vgpu_vreg(s->vgpu, info->stride_reg) & GENMASK(9, 0);
 		tile = (vgpu_vreg(s->vgpu, info->ctrl_reg) &
 				GENMASK(12, 10)) >> 10;
@@ -1243,7 +1237,7 @@ static int gen8_update_plane_mmio_from_mi_display_flip(
 
 	set_mask_bits(&vgpu_vreg(vgpu, info->surf_reg), GENMASK(31, 12),
 		      info->surf_val << 12);
-	if (IS_SKYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
 		set_mask_bits(&vgpu_vreg(vgpu, info->stride_reg), GENMASK(9, 0),
 			      info->stride_val);
 		set_mask_bits(&vgpu_vreg(vgpu, info->ctrl_reg), GENMASK(12, 10),
@@ -1267,7 +1261,7 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 
 	if (IS_BROADWELL(dev_priv))
 		return gen8_decode_mi_display_flip(s, info);
-	if (IS_SKYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
 		return skl_decode_mi_display_flip(s, info);
 
 	return -ENODEV;
@@ -1278,7 +1272,9 @@ static int check_mi_display_flip(struct parser_exec_state *s,
 {
 	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
 
-	if (IS_BROADWELL(dev_priv) || IS_SKYLAKE(dev_priv))
+	if (IS_BROADWELL(dev_priv)
+		|| IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv))
 		return gen8_check_mi_display_flip(s, info);
 	return -ENODEV;
 }
@@ -1289,7 +1285,9 @@ static int update_plane_mmio_from_mi_display_flip(
 {
 	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
 
-	if (IS_BROADWELL(dev_priv) || IS_SKYLAKE(dev_priv))
+	if (IS_BROADWELL(dev_priv)
+		|| IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv))
 		return gen8_update_plane_mmio_from_mi_display_flip(s, info);
 	return -ENODEV;
 }
@@ -1557,7 +1555,7 @@ static int copy_gma_to_hva(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm,
 		len += copy_len;
 		gma += copy_len;
 	}
-	return 0;
+	return len;
 }
 
 
@@ -1569,7 +1567,8 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s)
 {
 	struct intel_gvt *gvt = s->vgpu->gvt;
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) {
+	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
+		|| IS_KABYLAKE(gvt->dev_priv)) {
 		/* BDW decides privilege based on address space */
 		if (cmd_val(s, 0) & (1 << 8))
 			return 0;
@@ -1673,7 +1672,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	ret = copy_gma_to_hva(s->vgpu, s->vgpu->gtt.ggtt_mm,
 			      gma, gma + bb_size,
 			      dst);
-	if (ret) {
+	if (ret < 0) {
 		gvt_vgpu_err("fail to copy guest ring buffer\n");
 		goto unmap_src;
 	}
@@ -2478,7 +2477,7 @@ static int cmd_parser_exec(struct parser_exec_state *s)
 
 	t1 = get_cycles();
 
-	memcpy(&s_before_advance_custom, s, sizeof(struct parser_exec_state));
+	s_before_advance_custom = *s;
 
 	if (info->handler) {
 		ret = info->handler(s);
@@ -2604,6 +2603,9 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	unsigned long gma_head, gma_tail, gma_bottom, ring_size, ring_tail;
 	struct parser_exec_state s;
 	int ret = 0;
+	struct intel_vgpu_workload *workload = container_of(wa_ctx,
+				struct intel_vgpu_workload,
+				wa_ctx);
 
 	/* ring base is page aligned */
 	if (WARN_ON(!IS_ALIGNED(wa_ctx->indirect_ctx.guest_gma, GTT_PAGE_SIZE)))
@@ -2618,14 +2620,14 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 
 	s.buf_type = RING_BUFFER_INSTRUCTION;
 	s.buf_addr_type = GTT_BUFFER;
-	s.vgpu = wa_ctx->workload->vgpu;
-	s.ring_id = wa_ctx->workload->ring_id;
+	s.vgpu = workload->vgpu;
+	s.ring_id = workload->ring_id;
 	s.ring_start = wa_ctx->indirect_ctx.guest_gma;
 	s.ring_size = ring_size;
 	s.ring_head = gma_head;
 	s.ring_tail = gma_tail;
 	s.rb_va = wa_ctx->indirect_ctx.shadow_va;
-	s.workload = wa_ctx->workload;
+	s.workload = workload;
 
 	ret = ip_gma_set(&s, gma_head);
 	if (ret)
@@ -2640,11 +2642,8 @@ out:
 static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->shadow_ctx;
-	struct intel_ring *ring = shadow_ctx->engine[ring_id].ring;
 	unsigned long gma_head, gma_tail, gma_top, guest_rb_size;
-	unsigned int copy_len = 0;
+	u32 *cs;
 	int ret;
 
 	guest_rb_size = _RING_CTL_BUF_SIZE(workload->rb_ctl);
@@ -2658,36 +2657,33 @@ static int shadow_workload_ring_buffer(struct intel_vgpu_workload *workload)
 	gma_top = workload->rb_start + guest_rb_size;
 
 	/* allocate shadow ring buffer */
-	ret = intel_ring_begin(workload->req, workload->rb_len / 4);
-	if (ret)
-		return ret;
+	cs = intel_ring_begin(workload->req, workload->rb_len / sizeof(u32));
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
 
 	/* get shadow ring buffer va */
-	workload->shadow_ring_buffer_va = ring->vaddr + ring->tail;
+	workload->shadow_ring_buffer_va = cs;
 
 	/* head > tail --> copy head <-> top */
 	if (gma_head > gma_tail) {
 		ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm,
-				gma_head, gma_top,
-				workload->shadow_ring_buffer_va);
-		if (ret) {
+				      gma_head, gma_top, cs);
+		if (ret < 0) {
 			gvt_vgpu_err("fail to copy guest ring buffer\n");
 			return ret;
 		}
-		copy_len = gma_top - gma_head;
+		cs += ret / sizeof(u32);
 		gma_head = workload->rb_start;
 	}
 
 	/* copy head or start <-> tail */
-	ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm,
-			gma_head, gma_tail,
-			workload->shadow_ring_buffer_va + copy_len);
-	if (ret) {
+	ret = copy_gma_to_hva(vgpu, vgpu->gtt.ggtt_mm, gma_head, gma_tail, cs);
+	if (ret < 0) {
 		gvt_vgpu_err("fail to copy guest ring buffer\n");
 		return ret;
 	}
-	ring->tail += workload->rb_len;
-	intel_ring_advance(ring);
+	cs += ret / sizeof(u32);
+	intel_ring_advance(workload->req, cs);
 	return 0;
 }
 
@@ -2714,12 +2710,15 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
 	int ctx_size = wa_ctx->indirect_ctx.size;
 	unsigned long guest_gma = wa_ctx->indirect_ctx.guest_gma;
-	struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
+	struct intel_vgpu_workload *workload = container_of(wa_ctx,
+					struct intel_vgpu_workload,
+					wa_ctx);
+	struct intel_vgpu *vgpu = workload->vgpu;
 	struct drm_i915_gem_object *obj;
 	int ret = 0;
 	void *map;
 
-	obj = i915_gem_object_create(wa_ctx->workload->vgpu->gvt->dev_priv,
+	obj = i915_gem_object_create(workload->vgpu->gvt->dev_priv,
 				     roundup(ctx_size + CACHELINE_BYTES,
 					     PAGE_SIZE));
 	if (IS_ERR(obj))
@@ -2739,11 +2738,11 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 		goto unmap_src;
 	}
 
-	ret = copy_gma_to_hva(wa_ctx->workload->vgpu,
-				wa_ctx->workload->vgpu->gtt.ggtt_mm,
+	ret = copy_gma_to_hva(workload->vgpu,
+				workload->vgpu->gtt.ggtt_mm,
 				guest_gma, guest_gma + ctx_size,
 				map);
-	if (ret) {
+	if (ret < 0) {
 		gvt_vgpu_err("fail to copy guest indirect ctx\n");
 		goto unmap_src;
 	}
@@ -2778,7 +2777,10 @@ static int combine_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
 	int ret;
-	struct intel_vgpu *vgpu = wa_ctx->workload->vgpu;
+	struct intel_vgpu_workload *workload = container_of(wa_ctx,
+					struct intel_vgpu_workload,
+					wa_ctx);
+	struct intel_vgpu *vgpu = workload->vgpu;
 
 	if (wa_ctx->indirect_ctx.size == 0)
 		return 0;