Merge tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.15.

  Core:
   - Atomic object lifetime fixes
   - Atomic iterator improvements
   - Sparse/smatch fixes
   - Legacy kms ioctls to be interruptible
   - EDID override improvements
   - fb/gem helper cleanups
   - Simple outreachy patches
   - Documentation improvements
   - Fix dma-buf rcu races
   - DRM mode object leasing for improving VR use cases.
   - vgaarb improvements for non-x86 platforms.

  New driver:
   - tve200: Faraday Technology TVE200 block.

     This "TV Encoder" encodes a ITU-T BT.656 stream and can be found in
     the StorLink SL3516 (later Cortina Systems CS3516) as well as the
     Grain Media GM8180.

  New bridges:
   - SiI9234 support

  New panels:
   - S6E63J0X03, OTM8009A, Seiko 43WVF1G, 7" rpi touch panel, Toshiba
     LT089AC19000, Innolux AT043TN24

  i915:
   - Remove Coffeelake from alpha support
   - Cannonlake workarounds
   - Infoframe refactoring for DisplayPort
   - VBT updates
   - DisplayPort vswing/emph/buffer translation refactoring
   - CCS fixes
   - Restore GPU clock boost on missed vblanks
   - Scatter list updates for userptr allocations
   - Gen9+ transition watermarks
   - Display IPC (Isochronous Priority Control)
   - Private PAT management
   - GVT: improved error handling and pci config sanitizing
   - Execlist refactoring
   - Transparent Huge Page support
   - User defined priorities support
   - HuC/GuC firmware refactoring
   - DP MST fixes
   - eDP power sequencing fixes
   - Use RCU instead of stop_machine
   - PSR state tracking support
   - Eviction fixes
   - BDW DP aux channel timeout fixes
   - LSPCON fixes
   - Cannonlake PLL fixes

  amdgpu:
   - Per VM BO support
   - Powerplay cleanups
   - CI powerplay support
   - PASID mgr for kfd
   - SR-IOV fixes
   - initial GPU reset for vega10
   - Prime mmap support
   - TTM updates
   - Clock query interface for Raven
   - Fence to handle ioctl
   - UVD encode ring support on Polaris
   - Transparent huge page DMA support
   - Compute LRU pipe tweaks
   - BO flag to allow buffers to opt out of implicit sync
   - CTX priority setting API
   - VRAM lost infrastructure plumbing

  qxl:
   - fix flicker since atomic rework

  amdkfd:
   - Further improvements from internal AMD tree
   - Usermode events
   - Drop radeon support

  nouveau:
   - Pascal temperature sensor support
   - Improved BAR2 handling
   - MMU rework to support Pascal MMU

  exynos:
   - Improved HDMI/mixer support
   - HDMI audio interface support

  tegra:
   - Prep work for tegra186
   - Cleanup/fixes

  msm:
   - Preemption support for a5xx
   - Display fixes for 8x96 (snapdragon 820)
   - Async cursor plane fixes
   - FW loading rework
   - GPU debugging improvements

  vc4:
   - Prep for DSI panels
   - fix T-format tiling scanout
   - New madvise ioctl

  Rockchip:
   - LVDS support

  omapdrm:
   - omap4 HDMI CEC support

  etnaviv:
   - GPU performance counters groundwork

  sun4i:
   - refactor driver load + TCON backend
   - HDMI improvements
   - A31 support
   - Misc fixes

  udl:
   - Probe/EDID read fixes.

  tilcdc:
   - Misc fixes.

  pl111:
   - Support more variants

  adv7511:
   - Improve EDID handling.
   - HDMI CEC support

  sii8620:
   - Add remote control support"

* tag 'drm-for-v4.15' of git://people.freedesktop.org/~airlied/linux: (1480 commits)
  drm/rockchip: analogix_dp: Use mutex rather than spinlock
  drm/mode_object: fix documentation for object lookups.
  drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
  drm/i915: Move init_clock_gating() back to where it was
  drm/i915: Prune the reservation shared fence array
  drm/i915: Idle the GPU before shinking everything
  drm/i915: Lock llist_del_first() vs llist_del_all()
  drm/i915: Calculate ironlake intermediate watermarks correctly, v2.
  drm/i915: Disable lazy PPGTT page table optimization for vGPU
  drm/i915/execlists: Remove the priority "optimisation"
  drm/i915: Filter out spurious execlists context-switch interrupts
  drm/amdgpu: use irq-safe lock for kiq->ring_lock
  drm/amdgpu: bypass lru touch for KIQ ring submission
  drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories()
  drm/amdgpu: potential uninitialized variable in amdgpu_vce_ring_parse_cs()
  drm/amd/powerplay: initialize a variable before using it
  drm/amd/powerplay: suppress KASAN out of bounds warning in vega10_populate_all_memory_levels
  drm/amd/amdgpu: fix evicted VRAM bo adjudgement condition
  drm/vblank: Tune drm_crtc_accurate_vblank_count() WARN down to a debug
  drm/rockchip: add CONFIG_OF dependency for lvds
  ...

1 files changed, 101 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index a11e44340b23..c184468e2b2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -23,13 +23,41 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_auth.h>
 #include "amdgpu.h"
+#include "amdgpu_sched.h"
 
-static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
+static int amdgpu_ctx_priority_permit(struct drm_file *filp,
+				      enum amd_sched_priority priority)
+{
+	/* NORMAL and below are accessible by everyone */
+	if (priority <= AMD_SCHED_PRIORITY_NORMAL)
+		return 0;
+
+	if (capable(CAP_SYS_NICE))
+		return 0;
+
+	if (drm_is_current_master(filp))
+		return 0;
+
+	return -EACCES;
+}
+
+static int amdgpu_ctx_init(struct amdgpu_device *adev,
+			   enum amd_sched_priority priority,
+			   struct drm_file *filp,
+			   struct amdgpu_ctx *ctx)
 {
 	unsigned i, j;
 	int r;
 
+	if (priority < 0 || priority >= AMD_SCHED_PRIORITY_MAX)
+		return -EINVAL;
+
+	r = amdgpu_ctx_priority_permit(filp, priority);
+	if (r)
+		return r;
+
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->adev = adev;
 	kref_init(&ctx->refcount);
@@ -39,19 +67,24 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct amdgpu_ctx *ctx)
 	if (!ctx->fences)
 		return -ENOMEM;
 
+	mutex_init(&ctx->lock);
+
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		ctx->rings[i].sequence = 1;
 		ctx->rings[i].fences = &ctx->fences[amdgpu_sched_jobs * i];
 	}
 
 	ctx->reset_counter = atomic_read(&adev->gpu_reset_counter);
+	ctx->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
+	ctx->init_priority = priority;
+	ctx->override_priority = AMD_SCHED_PRIORITY_UNSET;
 
 	/* create context entity for each ring */
 	for (i = 0; i < adev->num_rings; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
 		struct amd_sched_rq *rq;
 
-		rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
+		rq = &ring->sched.sched_rq[priority];
 
 		if (ring == &adev->gfx.kiq.ring)
 			continue;
@@ -96,10 +129,14 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
 				      &ctx->rings[i].entity);
 
 	amdgpu_queue_mgr_fini(adev, &ctx->queue_mgr);
+
+	mutex_destroy(&ctx->lock);
 }
 
 static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 			    struct amdgpu_fpriv *fpriv,
+			    struct drm_file *filp,
+			    enum amd_sched_priority priority,
 			    uint32_t *id)
 {
 	struct amdgpu_ctx_mgr *mgr = &fpriv->ctx_mgr;
@@ -117,8 +154,9 @@ static int amdgpu_ctx_alloc(struct amdgpu_device *adev,
 		kfree(ctx);
 		return r;
 	}
+
 	*id = (uint32_t)r;
-	r = amdgpu_ctx_init(adev, ctx);
+	r = amdgpu_ctx_init(adev, priority, filp, ctx);
 	if (r) {
 		idr_remove(&mgr->ctx_handles, *id);
 		*id = 0;
@@ -193,6 +231,7 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 {
 	int r;
 	uint32_t id;
+	enum amd_sched_priority priority;
 
 	union drm_amdgpu_ctx *args = data;
 	struct amdgpu_device *adev = dev->dev_private;
@@ -200,10 +239,16 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 
 	r = 0;
 	id = args->in.ctx_id;
+	priority = amdgpu_to_sched_priority(args->in.priority);
+
+	/* For backwards compatibility reasons, we need to accept
+	 * ioctls with garbage in the priority field */
+	if (priority == AMD_SCHED_PRIORITY_INVALID)
+		priority = AMD_SCHED_PRIORITY_NORMAL;
 
 	switch (args->in.op) {
 	case AMDGPU_CTX_OP_ALLOC_CTX:
-		r = amdgpu_ctx_alloc(adev, fpriv, &id);
+		r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id);
 		args->out.alloc.ctx_id = id;
 		break;
 	case AMDGPU_CTX_OP_FREE_CTX:
@@ -246,8 +291,8 @@ int amdgpu_ctx_put(struct amdgpu_ctx *ctx)
 	return 0;
 }
 
-uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
-			      struct dma_fence *fence)
+int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
+			      struct dma_fence *fence, uint64_t* handler)
 {
 	struct amdgpu_ctx_ring *cring = & ctx->rings[ring->idx];
 	uint64_t seq = cring->sequence;
@@ -256,12 +301,8 @@ uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
 
 	idx = seq & (amdgpu_sched_jobs - 1);
 	other = cring->fences[idx];
-	if (other) {
-		signed long r;
-		r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
-		if (r < 0)
-			DRM_ERROR("Error (%ld) waiting for fence!\n", r);
-	}
+	if (other)
+		BUG_ON(!dma_fence_is_signaled(other));
 
 	dma_fence_get(fence);
 
@@ -271,8 +312,10 @@ uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
 	spin_unlock(&ctx->ring_lock);
 
 	dma_fence_put(other);
+	if (handler)
+		*handler = seq;
 
-	return seq;
+	return 0;
 }
 
 struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
@@ -303,6 +346,51 @@ struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,
 	return fence;
 }
 
+void amdgpu_ctx_priority_override(struct amdgpu_ctx *ctx,
+				  enum amd_sched_priority priority)
+{
+	int i;
+	struct amdgpu_device *adev = ctx->adev;
+	struct amd_sched_rq *rq;
+	struct amd_sched_entity *entity;
+	struct amdgpu_ring *ring;
+	enum amd_sched_priority ctx_prio;
+
+	ctx->override_priority = priority;
+
+	ctx_prio = (ctx->override_priority == AMD_SCHED_PRIORITY_UNSET) ?
+			ctx->init_priority : ctx->override_priority;
+
+	for (i = 0; i < adev->num_rings; i++) {
+		ring = adev->rings[i];
+		entity = &ctx->rings[i].entity;
+		rq = &ring->sched.sched_rq[ctx_prio];
+
+		if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+			continue;
+
+		amd_sched_entity_set_rq(entity, rq);
+	}
+}
+
+int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id)
+{
+	struct amdgpu_ctx_ring *cring = &ctx->rings[ring_id];
+	unsigned idx = cring->sequence & (amdgpu_sched_jobs - 1);
+	struct dma_fence *other = cring->fences[idx];
+
+	if (other) {
+		signed long r;
+		r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+		if (r < 0) {
+			DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+			return r;
+		}
+	}
+
+	return 0;
+}
+
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
 {
 	mutex_init(&mgr->lock);