Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:

   - i915 has seen a lot of refactoring and uAPI cleanups due to a
     change in the upstream direction going forward

     This has all been audited with known userspace, but there may be
     some pitfalls that were missed.

   - i915 now uses common TTM to enable discrete memory on DG1/2 GPUs

   - i915 enables Jasper and Elkhart Lake by default and has preliminary
     XeHP/DG2 support

   - amdgpu adds support for Cyan Skillfish

   - lots of implicit fencing rules documented and fixed up in drivers

   - msm now uses the core scheduler

   - the irq midlayer has been removed for non-legacy drivers

   - the sysfb code now works on more than x86.

  Otherwise the usual smattering of stuff everywhere, panels, bridges,
  refactorings.

  Detailed summary:

  core:
   - extract i915 eDP backlight into core
   - DP aux bus support
   - drm_device.irq_enabled removed
   - port drivers to native irq interfaces
   - export gem shadow plane handling for vgem
   - print proper driver name in framebuffer registration
   - driver fixes for implicit fencing rules
   - ARM fixed rate compression modifier added
   - updated fb damage handling
   - rmfb ioctl logging/docs
   - drop drm_gem_object_put_locked
   - define DRM_FORMAT_MAX_PLANES
   - add gem fb vmap/vunmap helpers
   - add lockdep_assert(once) helpers
   - mark drm irq midlayer as legacy
   - use offset adjusted bo mapping conversion

  vgaarb:
   - cleanups

  fbdev:
   - extend efifb handling to all arches
   - div by 0 fixes for multiple drivers

  udmabuf:
   - add hugepage mapping support

  dma-buf:
   - non-dynamic exporter fixups
   - document implicit fencing rules

  amdgpu:
   - Initial Cyan Skillfish support
   - switch virtual DCE over to vkms based atomic
   - VCN/JPEG power down fixes
   - NAVI PCIE link handling fixes
   - AMD HDMI freesync fixes
   - Yellow Carp + Beige Goby fixes
   - Clockgating/S0ix/SMU/EEPROM fixes
   - embed hw fence in job
   - rework dma-resv handling
   - ensure eviction to system ram

  amdkfd:
   - uapi: SVM address range query added
   - sysfs leak fix
   - GPUVM TLB optimizations
   - vmfault/migration counters

  i915:
   - Enable JSL and EHL by default
   - preliminary XeHP/DG2 support
   - remove all CNL support (never shipped)
   - move to TTM for discrete memory support
   - allow mixed object mmap handling
   - GEM uAPI spring cleaning
       - add I915_MMAP_OBJECT_FIXED
       - reinstate ADL-P mmap ioctls
       - drop a bunch of unused by userspace features
       - disable and remove GPU relocations
   - revert some i915 misfeatures
   - major refactoring of GuC for Gen11+
   - execbuffer object locking separate step
   - reject caching/set-domain on discrete
   - Enable pipe DMC loading on XE-LPD and ADL-P
   - add PSF GV point support
   - Refactor and fix DDI buffer translations
   - Clean up FBC CFB allocation code
   - Finish INTEL_GEN() and friends macro conversions

  nouveau:
   - add eDP backlight support
   - implicit fence fix

  msm:
   - a680/7c3 support
   - drm/scheduler conversion

  panfrost:
   - rework GPU reset

  virtio:
   - fix fencing for planes

  ast:
   - add detect support

  bochs:
   - move to tiny GPU driver

  vc4:
   - use hotplug irqs
   - HDMI codec support

  vmwgfx:
   - use internal vmware device headers

  ingenic:
   - demidlayering irq

  rcar-du:
   - shutdown fixes
   - convert to bridge connector helpers

  zynqmp-dsub:
   - misc fixes

  mgag200:
   - convert PLL handling to atomic

  mediatek:
   - MT8133 AAL support
   - gem mmap object support
   - MT8167 support

  etnaviv:
   - NXP Layerscape LS1028A SoC support
   - GEM mmap cleanups

  tegra:
   - new user API

  exynos:
   - missing unlock fix
   - build warning fix
   - use refcount_t"

* tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits)
  drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box
  drm/amd/display: Remove duplicate dml init
  drm/amd/display: Update bounding box states (v2)
  drm/amd/display: Update number of DCN3 clock states
  drm/amdgpu: disable GFX CGCG in aldebaran
  drm/amdgpu: Clear RAS interrupt status on aldebaran
  drm/amdgpu: Add support for RAS XGMI err query
  drm/amdkfd: Account for SH/SE count when setting up cu masks.
  drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain
  drm/amdgpu: drop redundant cancel_delayed_work_sync call
  drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend
  drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend
  drm/amdkfd: map SVM range with correct access permission
  drm/amdkfd: check access permisson to restore retry fault
  drm/amdgpu: Update RAS XGMI Error Query
  drm/amdgpu: Add driver infrastructure for MCA RAS
  drm/amd/display: Add Logging for HDMI color depth information
  drm/amd/amdgpu: consolidate PSP TA init shared buf functions
  drm/amd/amdgpu: add name field back to ras_common_if
  drm/amdgpu: Fix build with missing pm_suspend_target_state module export
  ...

1 files changed, 145 insertions, 58 deletions

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 0581186ebfb3..0da5b3100ab1 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier:	GPL-2.0
 /* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+
+#include <drm/panfrost_drm.h>
+
 #include <linux/atomic.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
@@ -31,10 +34,13 @@ static int wait_ready(struct panfrost_device *pfdev, u32 as_nr)
 	/* Wait for the MMU status to indicate there is no active command, in
 	 * case one is pending. */
 	ret = readl_relaxed_poll_timeout_atomic(pfdev->iomem + AS_STATUS(as_nr),
-		val, !(val & AS_STATUS_AS_ACTIVE), 10, 1000);
+		val, !(val & AS_STATUS_AS_ACTIVE), 10, 100000);
 
-	if (ret)
+	if (ret) {
+		/* The GPU hung, let's trigger a reset */
+		panfrost_device_schedule_reset(pfdev);
 		dev_err(pfdev->dev, "AS_ACTIVE bit stuck\n");
+	}
 
 	return ret;
 }
@@ -151,6 +157,7 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
+		u32 mask = BIT(as) | BIT(16 + as);
 
 		/*
 		 * AS can be retained by active jobs or a perfcnt context,
@@ -159,6 +166,18 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
 		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
+
+		if (pfdev->as_faulty_mask & mask) {
+			/* Unhandled pagefault on this AS, the MMU was
+			 * disabled. We need to re-enable the MMU after
+			 * clearing+unmasking the AS interrupts.
+			 */
+			mmu_write(pfdev, MMU_INT_CLEAR, mask);
+			mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
+			pfdev->as_faulty_mask &= ~mask;
+			panfrost_mmu_enable(pfdev, mmu);
+		}
+
 		goto out;
 	}
 
@@ -208,6 +227,7 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev)
 	spin_lock(&pfdev->as_lock);
 
 	pfdev->as_alloc_mask = 0;
+	pfdev->as_faulty_mask = 0;
 
 	list_for_each_entry_safe(mmu, mmu_tmp, &pfdev->as_lru_list, list) {
 		mmu->as = -1;
@@ -337,7 +357,7 @@ static void mmu_tlb_inv_context_s1(void *cookie)
 
 static void mmu_tlb_sync_context(void *cookie)
 {
-	//struct panfrost_device *pfdev = cookie;
+	//struct panfrost_mmu *mmu = cookie;
 	// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
 }
 
@@ -352,57 +372,10 @@ static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_walk = mmu_tlb_flush_walk,
 };
 
-int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
-{
-	struct panfrost_mmu *mmu = &priv->mmu;
-	struct panfrost_device *pfdev = priv->pfdev;
-
-	INIT_LIST_HEAD(&mmu->list);
-	mmu->as = -1;
-
-	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= SZ_4K | SZ_2M,
-		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
-		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
-		.coherent_walk	= pfdev->coherent,
-		.tlb		= &mmu_tlb_ops,
-		.iommu_dev	= pfdev->dev,
-	};
-
-	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
-					      priv);
-	if (!mmu->pgtbl_ops)
-		return -EINVAL;
-
-	return 0;
-}
-
-void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
-{
-	struct panfrost_device *pfdev = priv->pfdev;
-	struct panfrost_mmu *mmu = &priv->mmu;
-
-	spin_lock(&pfdev->as_lock);
-	if (mmu->as >= 0) {
-		pm_runtime_get_noresume(pfdev->dev);
-		if (pm_runtime_active(pfdev->dev))
-			panfrost_mmu_disable(pfdev, mmu->as);
-		pm_runtime_put_autosuspend(pfdev->dev);
-
-		clear_bit(mmu->as, &pfdev->as_alloc_mask);
-		clear_bit(mmu->as, &pfdev->as_in_use_mask);
-		list_del(&mmu->list);
-	}
-	spin_unlock(&pfdev->as_lock);
-
-	free_io_pgtable_ops(mmu->pgtbl_ops);
-}
-
 static struct panfrost_gem_mapping *
 addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 {
 	struct panfrost_gem_mapping *mapping = NULL;
-	struct panfrost_file_priv *priv;
 	struct drm_mm_node *node;
 	u64 offset = addr >> PAGE_SHIFT;
 	struct panfrost_mmu *mmu;
@@ -415,11 +388,10 @@ addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 	goto out;
 
 found_mmu:
-	priv = container_of(mmu, struct panfrost_file_priv, mmu);
 
-	spin_lock(&priv->mm_lock);
+	spin_lock(&mmu->mm_lock);
 
-	drm_mm_for_each_node(node, &priv->mm) {
+	drm_mm_for_each_node(node, &mmu->mm) {
 		if (offset >= node->start &&
 		    offset < (node->start + node->size)) {
 			mapping = drm_mm_node_to_panfrost_mapping(node);
@@ -429,7 +401,7 @@ found_mmu:
 		}
 	}
 
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mmu->mm_lock);
 out:
 	spin_unlock(&pfdev->as_lock);
 	return mapping;
@@ -542,6 +514,107 @@ err_bo:
 	return ret;
 }
 
+static void panfrost_mmu_release_ctx(struct kref *kref)
+{
+	struct panfrost_mmu *mmu = container_of(kref, struct panfrost_mmu,
+						refcount);
+	struct panfrost_device *pfdev = mmu->pfdev;
+
+	spin_lock(&pfdev->as_lock);
+	if (mmu->as >= 0) {
+		pm_runtime_get_noresume(pfdev->dev);
+		if (pm_runtime_active(pfdev->dev))
+			panfrost_mmu_disable(pfdev, mmu->as);
+		pm_runtime_put_autosuspend(pfdev->dev);
+
+		clear_bit(mmu->as, &pfdev->as_alloc_mask);
+		clear_bit(mmu->as, &pfdev->as_in_use_mask);
+		list_del(&mmu->list);
+	}
+	spin_unlock(&pfdev->as_lock);
+
+	free_io_pgtable_ops(mmu->pgtbl_ops);
+	drm_mm_takedown(&mmu->mm);
+	kfree(mmu);
+}
+
+void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu)
+{
+	kref_put(&mmu->refcount, panfrost_mmu_release_ctx);
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu)
+{
+	kref_get(&mmu->refcount);
+
+	return mmu;
+}
+
+#define PFN_4G		(SZ_4G >> PAGE_SHIFT)
+#define PFN_4G_MASK	(PFN_4G - 1)
+#define PFN_16M		(SZ_16M >> PAGE_SHIFT)
+
+static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node,
+					 unsigned long color,
+					 u64 *start, u64 *end)
+{
+	/* Executable buffers can't start or end on a 4GB boundary */
+	if (!(color & PANFROST_BO_NOEXEC)) {
+		u64 next_seg;
+
+		if ((*start & PFN_4G_MASK) == 0)
+			(*start)++;
+
+		if ((*end & PFN_4G_MASK) == 0)
+			(*end)--;
+
+		next_seg = ALIGN(*start, PFN_4G);
+		if (next_seg - *start <= PFN_16M)
+			*start = next_seg + 1;
+
+		*end = min(*end, ALIGN(*start, PFN_4G) - 1);
+	}
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev)
+{
+	struct panfrost_mmu *mmu;
+
+	mmu = kzalloc(sizeof(*mmu), GFP_KERNEL);
+	if (!mmu)
+		return ERR_PTR(-ENOMEM);
+
+	mmu->pfdev = pfdev;
+	spin_lock_init(&mmu->mm_lock);
+
+	/* 4G enough for now. can be 48-bit */
+	drm_mm_init(&mmu->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT);
+	mmu->mm.color_adjust = panfrost_drm_mm_color_adjust;
+
+	INIT_LIST_HEAD(&mmu->list);
+	mmu->as = -1;
+
+	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= SZ_4K | SZ_2M,
+		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
+		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
+		.coherent_walk	= pfdev->coherent,
+		.tlb		= &mmu_tlb_ops,
+		.iommu_dev	= pfdev->dev,
+	};
+
+	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
+					      mmu);
+	if (!mmu->pgtbl_ops) {
+		kfree(mmu);
+		return ERR_PTR(-EINVAL);
+	}
+
+	kref_init(&mmu->refcount);
+
+	return mmu;
+}
+
 static const char *access_type_name(struct panfrost_device *pfdev,
 		u32 fault_status)
 {
@@ -605,7 +678,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
 		if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0)
 			ret = panfrost_mmu_map_fault_addr(pfdev, as, addr);
 
-		if (ret)
+		if (ret) {
 			/* terminal fault, print info about the fault */
 			dev_err(pfdev->dev,
 				"Unhandled Page fault in AS%d at VA 0x%016llX\n"
@@ -619,18 +692,32 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
 				"TODO",
 				fault_status,
 				(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
-				exception_type, panfrost_exception_name(pfdev, exception_type),
+				exception_type, panfrost_exception_name(exception_type),
 				access_type, access_type_name(pfdev, fault_status),
 				source_id);
 
+			spin_lock(&pfdev->as_lock);
+			/* Ignore MMU interrupts on this AS until it's been
+			 * re-enabled.
+			 */
+			pfdev->as_faulty_mask |= mask;
+
+			/* Disable the MMU to kill jobs on this AS. */
+			panfrost_mmu_disable(pfdev, as);
+			spin_unlock(&pfdev->as_lock);
+		}
+
 		status &= ~mask;
 
 		/* If we received new MMU interrupts, process them before returning. */
 		if (!status)
-			status = mmu_read(pfdev, MMU_INT_RAWSTAT);
+			status = mmu_read(pfdev, MMU_INT_RAWSTAT) & ~pfdev->as_faulty_mask;
 	}
 
-	mmu_write(pfdev, MMU_INT_MASK, ~0);
+	spin_lock(&pfdev->as_lock);
+	mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
+	spin_unlock(&pfdev->as_lock);
+
 	return IRQ_HANDLED;
 };