Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "This is the main drm pull request for v4.2.

  I've one other new driver from freescale on my radar, it's been posted
  and reviewed, I'd just like to get someone to give it a last look, so
  maybe I'll send it or maybe I'll leave it.

  There is no major nouveau changes in here, Ben was working on
  something big, and we agreed it was a bit late, there wasn't anything
  else he considered urgent to merge.

  There might be another msm pull for some bits that are waiting on
  arm-soc, I'll see how we time it.

  This touches some "of" stuff, acks are in place except for the fixes
  to the build in various configs,t hat I just applied.

  Summary:

  New drivers:
      - virtio-gpu:
                KMS only pieces of driver for virtio-gpu in qemu.
                This is just the first part of this driver, enough to run
                unaccelerated userspace on. As qemu merges more we'll start
                adding the 3D features for the virgl 3d work.
      - amdgpu:
                a new driver from AMD to driver their newer GPUs. (VI+)
                It contains a new cleaner userspace API, and is a clean
                break from radeon moving forward, that AMD are going to
                concentrate on. It also contains a set of register headers
                auto generated from AMD internal database.

  core:
      - atomic modesetting API completed, enabled by default now.
      - Add support for mode_id blob to atomic ioctl to complete interface.
      - bunch of Displayport MST fixes
      - lots of misc fixes.

  panel:
      - new simple panels
      - fix some long-standing build issues with bridge drivers

  radeon:
      - VCE1 support
      - add a GPU reset counter for userspace
      - lots of fixes.

  amdkfd:
      - H/W debugger support module
      - static user-mode queues
      - support killing all the waves when a process terminates
      - use standard DECLARE_BITMAP

  i915:
      - Add Broxton support
      - S3, rotation support for Skylake
      - RPS booting tuning
      - CPT modeset sequence fixes
      - ns2501 dither support
      - enable cmd parser on haswell
      - cdclk handling fixes
      - gen8 dynamic pte allocation
      - lots of atomic conversion work

  exynos:
      - Add atomic modesetting support
      - Add iommu support
      - Consolidate drm driver initialization
      - and MIC, DECON and MIPI-DSI support for exynos5433

  omapdrm:
      - atomic modesetting support (fixes lots of things in rewrite)

  tegra:
      - DP aux transaction fixes
      - iommu support fix

  msm:
      - adreno a306 support
      - various dsi bits
      - various 64-bit fixes
      - NV12MT support

  rcar-du:
      - atomic and misc fixes

  sti:
      - fix HDMI timing complaince

  tilcdc:
      - use drm component API to access tda998x driver
      - fix module unloading

  qxl:
      - stability fixes"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (872 commits)
  drm/nouveau: Pause between setting gpu to D3hot and cutting the power
  drm/dp/mst: close deadlock in connector destruction.
  drm: Always enable atomic API
  drm/vgem: Set unique to "vgem"
  of: fix a build error to of_graph_get_endpoint_by_regs function
  drm/dp/mst: take lock around looking up the branch device on hpd irq
  drm/dp/mst: make sure mst_primary mstb is valid in work function
  of: add EXPORT_SYMBOL for of_graph_get_endpoint_by_regs
  ARM: dts: rename the clock of MIPI DSI 'pll_clk' to 'sclk_mipi'
  drm/atomic: Don't set crtc_state->enable manually
  drm/exynos: dsi: do not set TE GPIO direction by input
  drm/exynos: dsi: add support for MIC driver as a bridge
  drm/exynos: dsi: add support for Exynos5433
  drm/exynos: dsi: make use of array for clock access
  drm/exynos: dsi: make use of driver data for static values
  drm/exynos: dsi: add macros for register access
  drm/exynos: dsi: rename pll_clk to sclk_clk
  drm/exynos: mic: add MIC driver
  of: add helper for getting endpoint node of specific identifiers
  drm/exynos: add Exynos5433 decon driver
  ...

1 files changed, 419 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
new file mode 100644
index 000000000000..eb20987ce18d
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -0,0 +1,419 @@
+/*
+ * Copyright 2011 Red Hat Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+/*
+ * Authors:
+ *    Jerome Glisse <glisse@freedesktop.org>
+ */
+/* Algorithm:
+ *
+ * We store the last allocated bo in "hole", we always try to allocate
+ * after the last allocated bo. Principle is that in a linear GPU ring
+ * progression was is after last is the oldest bo we allocated and thus
+ * the first one that should no longer be in use by the GPU.
+ *
+ * If it's not the case we skip over the bo after last to the closest
+ * done bo if such one exist. If none exist and we are not asked to
+ * block we report failure to allocate.
+ *
+ * If we are asked to block we wait on all the oldest fence of all
+ * rings. We just wait for any of those fence to complete.
+ */
+#include <drm/drmP.h>
+#include "amdgpu.h"
+
+static void amdgpu_sa_bo_remove_locked(struct amdgpu_sa_bo *sa_bo);
+static void amdgpu_sa_bo_try_free(struct amdgpu_sa_manager *sa_manager);
+
+int amdgpu_sa_bo_manager_init(struct amdgpu_device *adev,
+			      struct amdgpu_sa_manager *sa_manager,
+			      unsigned size, u32 align, u32 domain)
+{
+	int i, r;
+
+	init_waitqueue_head(&sa_manager->wq);
+	sa_manager->bo = NULL;
+	sa_manager->size = size;
+	sa_manager->domain = domain;
+	sa_manager->align = align;
+	sa_manager->hole = &sa_manager->olist;
+	INIT_LIST_HEAD(&sa_manager->olist);
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		INIT_LIST_HEAD(&sa_manager->flist[i]);
+	}
+
+	r = amdgpu_bo_create(adev, size, align, true,
+			     domain, 0, NULL, &sa_manager->bo);
+	if (r) {
+		dev_err(adev->dev, "(%d) failed to allocate bo for manager\n", r);
+		return r;
+	}
+
+	return r;
+}
+
+void amdgpu_sa_bo_manager_fini(struct amdgpu_device *adev,
+			       struct amdgpu_sa_manager *sa_manager)
+{
+	struct amdgpu_sa_bo *sa_bo, *tmp;
+
+	if (!list_empty(&sa_manager->olist)) {
+		sa_manager->hole = &sa_manager->olist,
+		amdgpu_sa_bo_try_free(sa_manager);
+		if (!list_empty(&sa_manager->olist)) {
+			dev_err(adev->dev, "sa_manager is not empty, clearing anyway\n");
+		}
+	}
+	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->olist, olist) {
+		amdgpu_sa_bo_remove_locked(sa_bo);
+	}
+	amdgpu_bo_unref(&sa_manager->bo);
+	sa_manager->size = 0;
+}
+
+int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
+			       struct amdgpu_sa_manager *sa_manager)
+{
+	int r;
+
+	if (sa_manager->bo == NULL) {
+		dev_err(adev->dev, "no bo for sa manager\n");
+		return -EINVAL;
+	}
+
+	/* map the buffer */
+	r = amdgpu_bo_reserve(sa_manager->bo, false);
+	if (r) {
+		dev_err(adev->dev, "(%d) failed to reserve manager bo\n", r);
+		return r;
+	}
+	r = amdgpu_bo_pin(sa_manager->bo, sa_manager->domain, &sa_manager->gpu_addr);
+	if (r) {
+		amdgpu_bo_unreserve(sa_manager->bo);
+		dev_err(adev->dev, "(%d) failed to pin manager bo\n", r);
+		return r;
+	}
+	r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr);
+	amdgpu_bo_unreserve(sa_manager->bo);
+	return r;
+}
+
+int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev,
+				 struct amdgpu_sa_manager *sa_manager)
+{
+	int r;
+
+	if (sa_manager->bo == NULL) {
+		dev_err(adev->dev, "no bo for sa manager\n");
+		return -EINVAL;
+	}
+
+	r = amdgpu_bo_reserve(sa_manager->bo, false);
+	if (!r) {
+		amdgpu_bo_kunmap(sa_manager->bo);
+		amdgpu_bo_unpin(sa_manager->bo);
+		amdgpu_bo_unreserve(sa_manager->bo);
+	}
+	return r;
+}
+
+static void amdgpu_sa_bo_remove_locked(struct amdgpu_sa_bo *sa_bo)
+{
+	struct amdgpu_sa_manager *sa_manager = sa_bo->manager;
+	if (sa_manager->hole == &sa_bo->olist) {
+		sa_manager->hole = sa_bo->olist.prev;
+	}
+	list_del_init(&sa_bo->olist);
+	list_del_init(&sa_bo->flist);
+	amdgpu_fence_unref(&sa_bo->fence);
+	kfree(sa_bo);
+}
+
+static void amdgpu_sa_bo_try_free(struct amdgpu_sa_manager *sa_manager)
+{
+	struct amdgpu_sa_bo *sa_bo, *tmp;
+
+	if (sa_manager->hole->next == &sa_manager->olist)
+		return;
+
+	sa_bo = list_entry(sa_manager->hole->next, struct amdgpu_sa_bo, olist);
+	list_for_each_entry_safe_from(sa_bo, tmp, &sa_manager->olist, olist) {
+		if (sa_bo->fence == NULL || !amdgpu_fence_signaled(sa_bo->fence)) {
+			return;
+		}
+		amdgpu_sa_bo_remove_locked(sa_bo);
+	}
+}
+
+static inline unsigned amdgpu_sa_bo_hole_soffset(struct amdgpu_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole != &sa_manager->olist) {
+		return list_entry(hole, struct amdgpu_sa_bo, olist)->eoffset;
+	}
+	return 0;
+}
+
+static inline unsigned amdgpu_sa_bo_hole_eoffset(struct amdgpu_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole->next != &sa_manager->olist) {
+		return list_entry(hole->next, struct amdgpu_sa_bo, olist)->soffset;
+	}
+	return sa_manager->size;
+}
+
+static bool amdgpu_sa_bo_try_alloc(struct amdgpu_sa_manager *sa_manager,
+				   struct amdgpu_sa_bo *sa_bo,
+				   unsigned size, unsigned align)
+{
+	unsigned soffset, eoffset, wasted;
+
+	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
+	eoffset = amdgpu_sa_bo_hole_eoffset(sa_manager);
+	wasted = (align - (soffset % align)) % align;
+
+	if ((eoffset - soffset) >= (size + wasted)) {
+		soffset += wasted;
+
+		sa_bo->manager = sa_manager;
+		sa_bo->soffset = soffset;
+		sa_bo->eoffset = soffset + size;
+		list_add(&sa_bo->olist, sa_manager->hole);
+		INIT_LIST_HEAD(&sa_bo->flist);
+		sa_manager->hole = &sa_bo->olist;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * amdgpu_sa_event - Check if we can stop waiting
+ *
+ * @sa_manager: pointer to the sa_manager
+ * @size: number of bytes we want to allocate
+ * @align: alignment we need to match
+ *
+ * Check if either there is a fence we can wait for or
+ * enough free memory to satisfy the allocation directly
+ */
+static bool amdgpu_sa_event(struct amdgpu_sa_manager *sa_manager,
+			    unsigned size, unsigned align)
+{
+	unsigned soffset, eoffset, wasted;
+	int i;
+
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		if (!list_empty(&sa_manager->flist[i])) {
+			return true;
+		}
+	}
+
+	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
+	eoffset = amdgpu_sa_bo_hole_eoffset(sa_manager);
+	wasted = (align - (soffset % align)) % align;
+
+	if ((eoffset - soffset) >= (size + wasted)) {
+		return true;
+	}
+
+	return false;
+}
+
+static bool amdgpu_sa_bo_next_hole(struct amdgpu_sa_manager *sa_manager,
+				   struct amdgpu_fence **fences,
+				   unsigned *tries)
+{
+	struct amdgpu_sa_bo *best_bo = NULL;
+	unsigned i, soffset, best, tmp;
+
+	/* if hole points to the end of the buffer */
+	if (sa_manager->hole->next == &sa_manager->olist) {
+		/* try again with its beginning */
+		sa_manager->hole = &sa_manager->olist;
+		return true;
+	}
+
+	soffset = amdgpu_sa_bo_hole_soffset(sa_manager);
+	/* to handle wrap around we add sa_manager->size */
+	best = sa_manager->size * 2;
+	/* go over all fence list and try to find the closest sa_bo
+	 * of the current last
+	 */
+	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		struct amdgpu_sa_bo *sa_bo;
+
+		if (list_empty(&sa_manager->flist[i])) {
+			continue;
+		}
+
+		sa_bo = list_first_entry(&sa_manager->flist[i],
+					 struct amdgpu_sa_bo, flist);
+
+		if (!amdgpu_fence_signaled(sa_bo->fence)) {
+			fences[i] = sa_bo->fence;
+			continue;
+		}
+
+		/* limit the number of tries each ring gets */
+		if (tries[i] > 2) {
+			continue;
+		}
+
+		tmp = sa_bo->soffset;
+		if (tmp < soffset) {
+			/* wrap around, pretend it's after */
+			tmp += sa_manager->size;
+		}
+		tmp -= soffset;
+		if (tmp < best) {
+			/* this sa bo is the closest one */
+			best = tmp;
+			best_bo = sa_bo;
+		}
+	}
+
+	if (best_bo) {
+		++tries[best_bo->fence->ring->idx];
+		sa_manager->hole = best_bo->olist.prev;
+
+		/* we knew that this one is signaled,
+		   so it's save to remote it */
+		amdgpu_sa_bo_remove_locked(best_bo);
+		return true;
+	}
+	return false;
+}
+
+int amdgpu_sa_bo_new(struct amdgpu_device *adev,
+		     struct amdgpu_sa_manager *sa_manager,
+		     struct amdgpu_sa_bo **sa_bo,
+		     unsigned size, unsigned align)
+{
+	struct amdgpu_fence *fences[AMDGPU_MAX_RINGS];
+	unsigned tries[AMDGPU_MAX_RINGS];
+	int i, r;
+
+	BUG_ON(align > sa_manager->align);
+	BUG_ON(size > sa_manager->size);
+
+	*sa_bo = kmalloc(sizeof(struct amdgpu_sa_bo), GFP_KERNEL);
+	if ((*sa_bo) == NULL) {
+		return -ENOMEM;
+	}
+	(*sa_bo)->manager = sa_manager;
+	(*sa_bo)->fence = NULL;
+	INIT_LIST_HEAD(&(*sa_bo)->olist);
+	INIT_LIST_HEAD(&(*sa_bo)->flist);
+
+	spin_lock(&sa_manager->wq.lock);
+	do {
+		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+			fences[i] = NULL;
+			tries[i] = 0;
+		}
+
+		do {
+			amdgpu_sa_bo_try_free(sa_manager);
+
+			if (amdgpu_sa_bo_try_alloc(sa_manager, *sa_bo,
+						   size, align)) {
+				spin_unlock(&sa_manager->wq.lock);
+				return 0;
+			}
+
+			/* see if we can skip over some allocations */
+		} while (amdgpu_sa_bo_next_hole(sa_manager, fences, tries));
+
+		spin_unlock(&sa_manager->wq.lock);
+		r = amdgpu_fence_wait_any(adev, fences, false);
+		spin_lock(&sa_manager->wq.lock);
+		/* if we have nothing to wait for block */
+		if (r == -ENOENT) {
+			r = wait_event_interruptible_locked(
+				sa_manager->wq,
+				amdgpu_sa_event(sa_manager, size, align)
+			);
+		}
+
+	} while (!r);
+
+	spin_unlock(&sa_manager->wq.lock);
+	kfree(*sa_bo);
+	*sa_bo = NULL;
+	return r;
+}
+
+void amdgpu_sa_bo_free(struct amdgpu_device *adev, struct amdgpu_sa_bo **sa_bo,
+		       struct amdgpu_fence *fence)
+{
+	struct amdgpu_sa_manager *sa_manager;
+
+	if (sa_bo == NULL || *sa_bo == NULL) {
+		return;
+	}
+
+	sa_manager = (*sa_bo)->manager;
+	spin_lock(&sa_manager->wq.lock);
+	if (fence && !amdgpu_fence_signaled(fence)) {
+		(*sa_bo)->fence = amdgpu_fence_ref(fence);
+		list_add_tail(&(*sa_bo)->flist,
+			      &sa_manager->flist[fence->ring->idx]);
+	} else {
+		amdgpu_sa_bo_remove_locked(*sa_bo);
+	}
+	wake_up_all_locked(&sa_manager->wq);
+	spin_unlock(&sa_manager->wq.lock);
+	*sa_bo = NULL;
+}
+
+#if defined(CONFIG_DEBUG_FS)
+void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
+				  struct seq_file *m)
+{
+	struct amdgpu_sa_bo *i;
+
+	spin_lock(&sa_manager->wq.lock);
+	list_for_each_entry(i, &sa_manager->olist, olist) {
+		uint64_t soffset = i->soffset + sa_manager->gpu_addr;
+		uint64_t eoffset = i->eoffset + sa_manager->gpu_addr;
+		if (&i->olist == sa_manager->hole) {
+			seq_printf(m, ">");
+		} else {
+			seq_printf(m, " ");
+		}
+		seq_printf(m, "[0x%010llx 0x%010llx] size %8lld",
+			   soffset, eoffset, eoffset - soffset);
+		if (i->fence) {
+			seq_printf(m, " protected by 0x%016llx on ring %d",
+				   i->fence->seq, i->fence->ring->idx);
+		}
+		seq_printf(m, "\n");
+	}
+	spin_unlock(&sa_manager->wq.lock);
+}
+#endif