Merge tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for the 5.1 merge window.

  The big changes I'd highlight are:
   - nouveau has HMM support now, there is finally an in-tree user so we
     can quieten down the rip it out people.
   - i915 now enables fastboot by default on Skylake+
   - Displayport Multistream support has been refactored and should
     hopefully be more reliable.

  Core:
   - header cleanups aiming towards removing drmP.h
   - dma-buf fence seqnos to 64-bits
   - common helper for DP mst hotplug for radeon,i915,amdgpu + new
     refcounting scheme
   - MST i2c improvements
   - drm_syncobj_cb removal
   - ARM FB compression fourcc
   - P010 + P016 fourcc
   - allwinner tiled format modifier
   - i2c over aux I2C_M_STOP support
   - DRM_AUTH handling fixes

  TTM:
   - ref/unref renaming

  New driver:
   - ARM komeda display driver

  scheduler:
   - refactor mirror list handling
   - rework hw fence processing
   - 0 run queue entity fix

  bridge:
   - TI DS90C185 LVDS bridge
   - thc631lvdm83d bridge improvements
   - cadence + allwinner DSI ported to generic phy

  panels:
   - Sitronix ST7701 panel
   - Kingdisplay KD097D04
   - LeMaker BL035-RGB-002
   - PDA 91-00156-A0
   - Innolux EE101IA-01D

  i915:
   - Enable fastboot by default on SKL+/VLV/CHV
   - Export RPCS configuration for ICL media driver
   - Coffelake PCI ID
   - CNL clocks setup fixes
   - ACPI/PMIC support for MIPI/DSI
   - Per-engine WA init for all engines
   - Shrinker locking fixes
   - Kerneldoc updates
   - Lots of ring improvements and reset fixes
   - Coffeelake GVT Support
   - VFIO GVT EDID Region support
   - runtime PM wakeref tracking
   - ILK->IVB primary plane enable delays
   - userptr mutex locking fixes
   - DSI fixes
   - LVDS/TV cleanups
   - HW readout fixes
   - LUT robustness fixes
   - ICL display and watermark fixes
   - gem mmap race fix

  amdgpu:
   - add scheduled dependencies interface
   - DCC on scanout surfaces
   - vega10/20 BACO support
   - Multiple IH rings on soc15
   - XGMI locking fixes
   - DC i2c/aux cleanups
   - runtime SMU debug interface
   - Kexec improvmeents
   - SR-IOV fixes
   - DC freesync + ABM fixes
   - GDS fixes
   - GPUVM fixes
   - vega20 PCIE DPM switching fixes
   - Context priority handling fixes

  radeon:
   - fix missing break in evergreen parser

  nouveau:
   - SVM support via HMM

  msm:
   - QCOM Compressed modifier support

  exynos:
   - s5pv210 rotator support

  imx:
   - zpos property support
   - pending update fixes

  v3d:
   - cache flush improvments

  vc4:
   - reflection support
   - HDMI overscan support

  tegra:
   - CEC refactoring
   - HDMI audio fixes
   - Tegra186 prep work
   - SOR crossbar device tree fixes

  sun4i:
   - implicit fencing support
   - YUV and scalar support improvements
   - A23 support
   - tiling fixes

  atmel-hlcdc:
   - clipping and rotation property fixes

  qxl:
   - BO and PRIME improvements
   - generic fbdev emulation

  dw-hdmi:
   - HDMI 2.0 2160p
   - YUV420 ouput

  rockchip:
   - implicit fencing support
   - reflection proerties

  virtio-gpu:
   - use generic fbdev emulation

  tilcdc:
   - cpufreq vs crtc init fix

  rcar-du:
   - R8A774C0 support
   - D3/E3 RGB output routing fixes and DPAD0 support
   - RA87744 LVDS support

  bochs:
   - atomic and generic fbdev emulation
   - ID mismatch error on bochs load

  meson:
   - remove firmware fbs"

* tag 'drm-next-2019-03-06' of git://anongit.freedesktop.org/drm/drm: (1130 commits)
  drm/amd/display: Use vrr friendly pageflip throttling in DC.
  drm/imx: only send commit done event when all state has been applied
  drm/imx: allow building under COMPILE_TEST
  drm/imx: imx-tve: depend on COMMON_CLK
  drm/imx: ipuv3-plane: add zpos property
  drm/imx: ipuv3-plane: add function to query atomic update status
  gpu: ipu-v3: prg: add function to get channel configure status
  gpu: ipu-v3: pre: add double buffer status readback
  drm/amdgpu: Bump amdgpu version for context priority override.
  drm/amdgpu/powerplay: fix typo in BACO header guards
  drm/amdgpu/powerplay: fix return codes in BACO code
  drm/amdgpu: add missing license on baco files
  drm/bochs: Fix the ID mismatch error
  drm/nouveau/dmem: use dma addresses during migration copies
  drm/nouveau/dmem: use physical vram addresses during migration copies
  drm/nouveau/dmem: extend copy function to allow direct use of physical addresses
  drm/nouveau/svm: new ioctl to migrate process memory to GPU memory
  drm/nouveau/dmem: device memory helpers for SVM
  drm/nouveau/svm: initial support for shared virtual memory
  drm/nouveau: prepare for enabling svm with existing userspace interfaces
  ...

1 files changed, 84 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 485b259127c3..02adcaf6ebea 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -31,7 +31,6 @@
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>
 
-#include <drm/drmP.h>
 #include <drm/drm_syncobj.h>
 #include <drm/i915_drm.h>
 
@@ -754,6 +753,68 @@ static int eb_select_context(struct i915_execbuffer *eb)
 	return 0;
 }
 
+static struct i915_request *__eb_wait_for_ring(struct intel_ring *ring)
+{
+	struct i915_request *rq;
+
+	/*
+	 * Completely unscientific finger-in-the-air estimates for suitable
+	 * maximum user request size (to avoid blocking) and then backoff.
+	 */
+	if (intel_ring_update_space(ring) >= PAGE_SIZE)
+		return NULL;
+
+	/*
+	 * Find a request that after waiting upon, there will be at least half
+	 * the ring available. The hysteresis allows us to compete for the
+	 * shared ring and should mean that we sleep less often prior to
+	 * claiming our resources, but not so long that the ring completely
+	 * drains before we can submit our next request.
+	 */
+	list_for_each_entry(rq, &ring->request_list, ring_link) {
+		if (__intel_ring_space(rq->postfix,
+				       ring->emit, ring->size) > ring->size / 2)
+			break;
+	}
+	if (&rq->ring_link == &ring->request_list)
+		return NULL; /* weird, we will check again later for real */
+
+	return i915_request_get(rq);
+}
+
+static int eb_wait_for_ring(const struct i915_execbuffer *eb)
+{
+	const struct intel_context *ce;
+	struct i915_request *rq;
+	int ret = 0;
+
+	/*
+	 * Apply a light amount of backpressure to prevent excessive hogs
+	 * from blocking waiting for space whilst holding struct_mutex and
+	 * keeping all of their resources pinned.
+	 */
+
+	ce = to_intel_context(eb->ctx, eb->engine);
+	if (!ce->ring) /* first use, assume empty! */
+		return 0;
+
+	rq = __eb_wait_for_ring(ce->ring);
+	if (rq) {
+		mutex_unlock(&eb->i915->drm.struct_mutex);
+
+		if (i915_request_wait(rq,
+				      I915_WAIT_INTERRUPTIBLE,
+				      MAX_SCHEDULE_TIMEOUT) < 0)
+			ret = -EINTR;
+
+		i915_request_put(rq);
+
+		mutex_lock(&eb->i915->drm.struct_mutex);
+	}
+
+	return ret;
+}
+
 static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
 	struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
@@ -1380,7 +1441,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 		 * batchbuffers.
 		 */
 		if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
-		    IS_GEN6(eb->i915)) {
+		    IS_GEN(eb->i915, 6)) {
 			err = i915_vma_bind(target, target->obj->cache_level,
 					    PIN_GLOBAL);
 			if (WARN_ONCE(err,
@@ -1896,7 +1957,7 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	u32 *cs;
 	int i;
 
-	if (!IS_GEN7(rq->i915) || rq->engine->id != RCS) {
+	if (!IS_GEN(rq->i915, 7) || rq->engine->id != RCS) {
 		DRM_DEBUG("sol reset is gen7/rcs only\n");
 		return -EINVAL;
 	}
@@ -1977,6 +2038,18 @@ static int eb_submit(struct i915_execbuffer *eb)
 			return err;
 	}
 
+	/*
+	 * After we completed waiting for other engines (using HW semaphores)
+	 * then we can signal that this request/batch is ready to run. This
+	 * allows us to determine if the batch is still waiting on the GPU
+	 * or actually running by checking the breadcrumb.
+	 */
+	if (eb->engine->emit_init_breadcrumb) {
+		err = eb->engine->emit_init_breadcrumb(eb->request);
+		if (err)
+			return err;
+	}
+
 	err = eb->engine->emit_bb_start(eb->request,
 					eb->batch->node.start +
 					eb->batch_start_offset,
@@ -2203,6 +2276,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct sync_file *out_fence = NULL;
+	intel_wakeref_t wakeref;
 	int out_fence_fd = -1;
 	int err;
 
@@ -2273,12 +2347,16 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	 * wakeref that we hold until the GPU has been idle for at least
 	 * 100ms.
 	 */
-	intel_runtime_pm_get(eb.i915);
+	wakeref = intel_runtime_pm_get(eb.i915);
 
 	err = i915_mutex_lock_interruptible(dev);
 	if (err)
 		goto err_rpm;
 
+	err = eb_wait_for_ring(&eb); /* may temporarily drop struct_mutex */
+	if (unlikely(err))
+		goto err_unlock;
+
 	err = eb_relocate(&eb);
 	if (err) {
 		/*
@@ -2423,9 +2501,10 @@ err_batch_unpin:
 err_vma:
 	if (eb.exec)
 		eb_release_vmas(&eb);
+err_unlock:
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
-	intel_runtime_pm_put(eb.i915);
+	intel_runtime_pm_put(eb.i915, wakeref);
 	i915_gem_context_put(eb.ctx);
 err_destroy:
 	eb_destroy(&eb);