Merge tag 'drm-intel-gt-next-2021-01-14' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:
- Deprecate I915_PMU_LAST and optimize state tracking (Tvrtko)

  Avoid relying on last item ABI marker in i915_drm.h, add a
  comment to mark as deprecated.

Cross-subsystem Changes:

Core Changes:

Driver Changes:

- Restore clear residuals security mitigations for Ivybridge and
  Baytrail (Chris)
- Close #1858: Allow sysadmin to choose applied GPU security mitigations
  through i915.mitigations=... similar to CPU (Chris)
- Fix for #2024: GPU hangs on HSW GT1 (Chris)
- Fix for #2707: Driver hang when editing UVs in Blender (Chris, Ville)
- Fix for #2797: False positive GuC loading error message (Chris)
- Fix for #2859: Missing GuC firmware for older Cometlakes (Chris)
- Lessen probability of GPU hang due to DMAR faults [reason 7,
  next page table ptr is invalid] on Tigerlake (Chris)
- Fix REVID macros for TGL to fetch correct stepping (Aditya)
- Limit frequency drop to RPe on parking (Chris, Edward)
- Limit W/A 1406941453 to TGL, RKL and DG1 (Swathi)
- Make W/A 22010271021 permanent on DG1 (Lucas)
- Implement W/A 16011163337 to prevent a HS/DS hang on DG1 (Swathi)
- Only disable preemption on gen8 render engines (Chris)
- Disable arbitration around Braswell's PDP updates (Chris)
- Disable arbitration on no-preempt requests (Chris)
- Check for arbitration after writing start seqno before busywaiting (Chris)
- Retain default context state across shrinking (Venkata, CQ)
- Fix mismatch between misplaced vma check and vma insert for 32-bit
  addressing userspaces (Chris, CQ)
- Propagate error for vmap() failure instead kernel NULL deref (Chris)
- Propagate error from cancelled submit due to context closure
  immediately (Chris)
- Fix RCU race on HWSP tracking per request (Chris)
- Clear CMD parser shadow and GPU reloc batches (Matt A)

- Populate logical context during first pin (Maarten)
- Optimistically prune dma-resv from the shrinker (Chris)
- Fix for virtual engine ownership race (Chris)
- Remove timeslice suppression to restore fairness for virtual engines (Chris)
- Rearrange IVB/HSW workarounds properly between GT and engine (Chris)
- Taint the reset mutex with the shrinker (Chris)
- Replace direct submit with direct call to tasklet (Chris)
- Multiple corrections to virtual engine dequeue and breadcrumbs code (Chris)
- Avoid wakeref from potentially hard IRQ context in PMU (Tvrtko)
- Use raw clock for RC6 time estimation in PMU (Tvrtko)
- Differentiate OOM failures from invalid map types (Chris)
- Fix Gen9 to have 64 MOCS entries similar to Gen11 (Chris)
- Ignore repeated attempts to suspend request flow across reset (Chris)
- Remove livelock from "do_idle_maps" VT-d W/A (Chris)
- Cancel the preemption timeout early in case engine reset fails (Chris)
- Code flow optimization in the scheduling code (Chris)
- Clear the execlists timers upon reset (Chris)
- Drain the breadcrumbs just once (Chris, Matt A)
- Track the overall GT awake/busy time (Chris)
- Tweak submission tasklet flushing to avoid starvation (Chris)
- Track timelines created using the HWSP to restore on resume (Chris)
- Use cmpxchg64 for 32b compatilibity for active tracking (Chris)
- Prefer recycling an idle GGTT fence to avoid GPU wait (Chris)

- Restructure GT code organization for clearer split between GuC
  and execlists (Chris, Daniele, John, Matt A)
- Remove GuC code that will remain unused by new interfaces (Matt B)
- Restructure the CS timestamp clocks code to local to GT (Chris)
- Fix error return paths in perf code (Zhang)
- Replace idr_init() by idr_init_base() in perf (Deepak)
- Fix shmem_pin_map error path (Colin)
- Drop redundant free_work worker for GEM contexts (Chris, Mika)
- Increase readability and understandability of intel_workarounds.c (Lucas)
- Defer enabling the breadcrumb interrupt to after submission (Chris)
- Deal with buddy alloc block sizes beyond 4G (Venkata, Chris)
- Encode fence specific waitqueue behaviour into the wait.flags (Chris)
- Don't cancel the breadcrumb interrupt shadow too early (Chris)
- Cancel submitted requests upon context reset (Chris)
- Use correct locks in GuC code (Tvrtko)
- Prevent use of engine->wa_ctx after error (Chris, Matt R)

- Fix build warning on 32-bit (Arnd)
- Avoid memory leak if platform would have more than 16 W/A (Tvrtko)
- Avoid unnecessary #if CONFIG_PM in PMU code (Chris, Tvrtko)
- Improve debugging output (Chris, Tvrtko, Matt R)
- Make file local variables static (Jani)
- Avoid uint*_t types in i915 (Jani)
- Selftest improvements (Chris, Matt A, Dan)
- Documentation fixes (Chris, Jose)

Signed-off-by: Dave Airlie <airlied@redhat.com>

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
#	drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
#	drivers/gpu/drm/i915/gt/intel_lrc.c
#	drivers/gpu/drm/i915/gvt/mmio_context.h
#	drivers/gpu/drm/i915/i915_drv.h
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210114152232.GA21588@jlahtine-mobl.ger.corp.intel.com

Documentation/gpu/i915.rst

@@ -428,7 +428,7 @@ User Batchbuffer Execution
 Logical Rings, Logical Ring Contexts and Execlists
 --------------------------------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_lrc.c
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_execlists_submission.c
    :doc: Logical Rings, Logical Ring Contexts and Execlists
 
 Global GTT views

drivers/gpu/drm/i915/Makefile

@@ -38,6 +38,7 @@ i915-y += i915_drv.o \
 	  i915_config.o \
 	  i915_irq.o \
 	  i915_getparam.o \
+	  i915_mitigations.o \
 	  i915_params.o \
 	  i915_pci.o \
 	  i915_scatterlist.o \
@@ -58,6 +59,7 @@ i915-y += i915_drv.o \
 
 # core library code
 i915-y += \
+	dma_resv_utils.o \
 	i915_memcpy.o \
 	i915_mm.o \
 	i915_sw_fence.o \
@@ -82,6 +84,7 @@ gt-y += \
 	gt/gen6_engine_cs.o \
 	gt/gen6_ppgtt.o \
 	gt/gen7_renderclear.o \
+	gt/gen8_engine_cs.o \
 	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
@@ -91,6 +94,7 @@ gt-y += \
 	gt/intel_engine_heartbeat.o \
 	gt/intel_engine_pm.o \
 	gt/intel_engine_user.o \
+	gt/intel_execlists_submission.o \
 	gt/intel_ggtt.o \
 	gt/intel_ggtt_fencing.o \
 	gt/intel_gt.o \
@@ -106,6 +110,7 @@ gt-y += \
 	gt/intel_mocs.o \
 	gt/intel_ppgtt.o \
 	gt/intel_rc6.o \
+	gt/intel_region_lmem.o \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
 	gt/intel_ring.o \
@@ -166,7 +171,6 @@ i915-y += \
 	  i915_scheduler.o \
 	  i915_trace_points.o \
 	  i915_vma.o \
-	  intel_region_lmem.o \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support

drivers/gpu/drm/i915/display/intel_overlay.c

@@ -29,6 +29,7 @@
 #include <drm/drm_fourcc.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
 
 #include "i915_drv.h"

drivers/gpu/drm/i915/dma_resv_utils.c

@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/dma-resv.h>
+
+#include "dma_resv_utils.h"
+
+void dma_resv_prune(struct dma_resv *resv)
+{
+	if (dma_resv_trylock(resv)) {
+		if (dma_resv_test_signaled_rcu(resv, true))
+			dma_resv_add_excl_fence(resv, NULL);
+		dma_resv_unlock(resv);
+	}
+}

drivers/gpu/drm/i915/dma_resv_utils.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef DMA_RESV_UTILS_H
+#define DMA_RESV_UTILS_H
+
+struct dma_resv;
+
+void dma_resv_prune(struct dma_resv *resv);
+
+#endif /* DMA_RESV_UTILS_H */

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -72,6 +72,8 @@
 #include "gt/intel_context_param.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_engine_user.h"
+#include "gt/intel_execlists_submission.h" /* virtual_engine */
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
 
 #include "i915_gem_context.h"
@@ -333,13 +335,12 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 	return e;
 }
 
-static void i915_gem_context_free(struct i915_gem_context *ctx)
+void i915_gem_context_release(struct kref *ref)
 {
-	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
+	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
 
-	spin_lock(&ctx->i915->gem.contexts.lock);
-	list_del(&ctx->link);
-	spin_unlock(&ctx->i915->gem.contexts.lock);
+	trace_i915_context_free(ctx);
+	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
 	mutex_destroy(&ctx->engines_mutex);
 	mutex_destroy(&ctx->lut_mutex);
@@ -353,37 +354,6 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	kfree_rcu(ctx, rcu);
 }
 
-static void contexts_free_all(struct llist_node *list)
-{
-	struct i915_gem_context *ctx, *cn;
-
-	llist_for_each_entry_safe(ctx, cn, list, free_link)
-		i915_gem_context_free(ctx);
-}
-
-static void contexts_flush_free(struct i915_gem_contexts *gc)
-{
-	contexts_free_all(llist_del_all(&gc->free_list));
-}
-
-static void contexts_free_worker(struct work_struct *work)
-{
-	struct i915_gem_contexts *gc =
-		container_of(work, typeof(*gc), free_work);
-
-	contexts_flush_free(gc);
-}
-
-void i915_gem_context_release(struct kref *ref)
-{
-	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
-	struct i915_gem_contexts *gc = &ctx->i915->gem.contexts;
-
-	trace_i915_context_free(ctx);
-	if (llist_add(&ctx->free_link, &gc->free_list))
-		schedule_work(&gc->free_work);
-}
-
 static inline struct i915_gem_engines *
 __context_engines_static(const struct i915_gem_context *ctx)
 {
@@ -453,6 +423,9 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	struct intel_engine_cs *engine = NULL;
 	struct i915_request *rq;
 
+	if (intel_context_has_inflight(ce))
+		return intel_context_inflight(ce);
+
 	if (!ce->timeline)
 		return NULL;
 
@@ -632,6 +605,10 @@ static void context_close(struct i915_gem_context *ctx)
 	 */
 	lut_close(ctx);
 
+	spin_lock(&ctx->i915->gem.contexts.lock);
+	list_del(&ctx->link);
+	spin_unlock(&ctx->i915->gem.contexts.lock);
+
 	mutex_unlock(&ctx->mutex);
 
 	/*
@@ -849,9 +826,6 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	    !HAS_EXECLISTS(i915))
 		return ERR_PTR(-EINVAL);
 
-	/* Reap the stale contexts */
-	contexts_flush_free(&i915->gem.contexts);
-
 	ctx = __create_context(i915);
 	if (IS_ERR(ctx))
 		return ctx;
@@ -896,23 +870,11 @@ static void init_contexts(struct i915_gem_contexts *gc)
 {
 	spin_lock_init(&gc->lock);
 	INIT_LIST_HEAD(&gc->list);
-
-	INIT_WORK(&gc->free_work, contexts_free_worker);
-	init_llist_head(&gc->free_list);
 }
 
 void i915_gem_init__contexts(struct drm_i915_private *i915)
 {
 	init_contexts(&i915->gem.contexts);
-	drm_dbg(&i915->drm, "%s context support initialized\n",
-		DRIVER_CAPS(i915)->has_logical_contexts ?
-		"logical" : "fake");
-}
-
-void i915_gem_driver_release__contexts(struct drm_i915_private *i915)
-{
-	flush_work(&i915->gem.contexts.free_work);
-	rcu_barrier(); /* and flush the left over RCU frees */
 }
 
 static int gem_context_register(struct i915_gem_context *ctx,
@@ -988,7 +950,6 @@ err:
 void i915_gem_context_close(struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct drm_i915_private *i915 = file_priv->dev_priv;
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	unsigned long idx;
@@ -1000,8 +961,6 @@ void i915_gem_context_close(struct drm_file *file)
 	xa_for_each(&file_priv->vm_xa, idx, vm)
 		i915_vm_put(vm);
 	xa_destroy(&file_priv->vm_xa);
-
-	contexts_flush_free(&i915->gem.contexts);
 }
 
 int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,

drivers/gpu/drm/i915/gem/i915_gem_context.h

@@ -110,7 +110,6 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 
 /* i915_gem_context.c */
 void i915_gem_init__contexts(struct drm_i915_private *i915);
-void i915_gem_driver_release__contexts(struct drm_i915_private *i915);
 
 int i915_gem_context_open(struct drm_i915_private *i915,
 			  struct drm_file *file);

drivers/gpu/drm/i915/gem/i915_gem_context_types.h

@@ -108,7 +108,6 @@ struct i915_gem_context {
 
 	/** link: place with &drm_i915_private.context_list */
 	struct list_head link;
-	struct llist_node free_link;
 
 	/**
 	 * @ref: reference count

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -15,6 +15,7 @@
 
 #include "gem/i915_gem_ioctls.h"
 #include "gt/intel_context.h"
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_buffer_pool.h"
 #include "gt/intel_gt_pm.h"
@@ -534,8 +535,6 @@ eb_add_vma(struct i915_execbuffer *eb,
 	struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 	struct eb_vma *ev = &eb->vma[i];
 
-	GEM_BUG_ON(i915_vma_is_closed(vma));
-
 	ev->vma = vma;
 	ev->exec = entry;
 	ev->flags = entry->flags;
@@ -1046,7 +1045,7 @@ static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cach
 	GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
 	cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
 
-	__i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
 	intel_gt_chipset_flush(cache->rq->engine->gt);
@@ -1296,6 +1295,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_pool;
 	}
 
+	memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
+
 	batch = i915_vma_instance(pool->obj, vma->vm, NULL);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
@@ -2533,6 +2534,9 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch)
 {
 	int err;
 
+	if (intel_context_nopreempt(eb->context))
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
+
 	err = eb_move_to_gpu(eb);
 	if (err)
 		return err;
@@ -2573,15 +2577,12 @@ static int eb_submit(struct i915_execbuffer *eb, struct i915_vma *batch)
 			return err;
 	}
 
-	if (intel_context_nopreempt(eb->context))
-		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
-
 	return 0;
 }
 
 static int num_vcs_engines(const struct drm_i915_private *i915)
 {
-	return hweight64(VDBOX_MASK(&i915->gt));
+	return hweight_long(VDBOX_MASK(&i915->gt));
 }
 
 /*

drivers/gpu/drm/i915/gem/i915_gem_object_blt.c

@@ -6,6 +6,7 @@
 #include "i915_drv.h"
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_buffer_pool.h"
 #include "gt/intel_ring.h"

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -238,7 +238,7 @@ unlock:
 
 /* The 'mapping' part of i915_gem_object_pin_map() below */
 static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
-		enum i915_map_type type)
+				      enum i915_map_type type)
 {
 	unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
 	struct page *stack[32], **pages = stack, *page;
@@ -281,7 +281,7 @@ static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
 		/* Too big for stack -- allocate temporary array instead */
 		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
 		if (!pages)
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 	}
 
 	i = 0;
@@ -290,11 +290,12 @@ static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
 	vaddr = vmap(pages, n_pages, 0, pgprot);
 	if (pages != stack)
 		kvfree(pages);
-	return vaddr;
+
+	return vaddr ?: ERR_PTR(-ENOMEM);
 }
 
 static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
-		enum i915_map_type type)
+				     enum i915_map_type type)
 {
 	resource_size_t iomap = obj->mm.region->iomap.base -
 		obj->mm.region->region.start;
@@ -305,13 +306,13 @@ static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
 	void *vaddr;
 
 	if (type != I915_MAP_WC)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	if (n_pfn > ARRAY_SIZE(stack)) {
 		/* Too big for stack -- allocate temporary array instead */
 		pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
 		if (!pfns)
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 	}
 
 	i = 0;
@@ -320,7 +321,8 @@ static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj,
 	vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
 	if (pfns != stack)
 		kvfree(pfns);
-	return vaddr;
+
+	return vaddr ?: ERR_PTR(-ENOMEM);
 }
 
 /* get, pin, and map the pages of the object into kernel space */
@@ -349,8 +351,10 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 			GEM_BUG_ON(i915_gem_object_has_pinned_pages(obj));
 
 			err = ____i915_gem_object_get_pages(obj);
-			if (err)
-				goto err_unlock;
+			if (err) {
+				ptr = ERR_PTR(err);
+				goto out_unlock;
+			}
 
 			smp_mb__before_atomic();
 		}
@@ -362,7 +366,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	ptr = page_unpack_bits(obj->mm.mapping, &has_type);
 	if (ptr && has_type != type) {
 		if (pinned) {
-			err = -EBUSY;
+			ptr = ERR_PTR(-EBUSY);
 			goto err_unpin;
 		}
 
@@ -374,15 +378,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	if (!ptr) {
 		if (GEM_WARN_ON(type == I915_MAP_WC &&
 				!static_cpu_has(X86_FEATURE_PAT)))
-			ptr = NULL;
+			ptr = ERR_PTR(-ENODEV);
 		else if (i915_gem_object_has_struct_page(obj))
 			ptr = i915_gem_object_map_page(obj, type);
 		else
 			ptr = i915_gem_object_map_pfn(obj, type);
-		if (!ptr) {
-			err = -ENOMEM;
+		if (IS_ERR(ptr))
 			goto err_unpin;
-		}
 
 		obj->mm.mapping = page_pack_bits(ptr, type);
 	}
@@ -393,8 +395,6 @@ out_unlock:
 
 err_unpin:
 	atomic_dec(&obj->mm.pages_pin_count);
-err_unlock:
-	ptr = ERR_PTR(err);
 	goto out_unlock;
 }
 

drivers/gpu/drm/i915/gem/i915_gem_region.c

@@ -22,6 +22,7 @@ i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
 int
 i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 {
+	const u64 max_segment = i915_sg_segment_size();
 	struct intel_memory_region *mem = obj->mm.region;
 	struct list_head *blocks = &obj->mm.blocks;
 	resource_size_t size = obj->base.size;
@@ -37,7 +38,7 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 	if (!st)
 		return -ENOMEM;
 
-	if (sg_alloc_table(st, size >> ilog2(mem->mm.chunk_size), GFP_KERNEL)) {
+	if (sg_alloc_table(st, size >> PAGE_SHIFT, GFP_KERNEL)) {
 		kfree(st);
 		return -ENOMEM;
 	}
@@ -64,27 +65,30 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 				   i915_buddy_block_size(&mem->mm, block));
 		offset = i915_buddy_block_offset(block);
 
-		GEM_BUG_ON(overflows_type(block_size, sg->length));
+		while (block_size) {
+			u64 len;
 
-		if (offset != prev_end ||
-		    add_overflows_t(typeof(sg->length), sg->length, block_size)) {
-			if (st->nents) {
-				sg_page_sizes |= sg->length;
-				sg = __sg_next(sg);
+			if (offset != prev_end || sg->length >= max_segment) {
+				if (st->nents) {
+					sg_page_sizes |= sg->length;
+					sg = __sg_next(sg);
+				}
+
+				sg_dma_address(sg) = mem->region.start + offset;
+				sg_dma_len(sg) = 0;
+				sg->length = 0;
+				st->nents++;
 			}
 
-			sg_dma_address(sg) = mem->region.start + offset;
-			sg_dma_len(sg) = block_size;
+			len = min(block_size, max_segment - sg->length);
+			sg->length += len;
+			sg_dma_len(sg) += len;
 
-			sg->length = block_size;
+			offset += len;
+			block_size -= len;
 
-			st->nents++;
-		} else {
-			sg->length += block_size;
-			sg_dma_len(sg) += block_size;
+			prev_end = offset;
 		}
-
-		prev_end = offset + block_size;
 	}
 
 	sg_page_sizes |= sg->length;

drivers/gpu/drm/i915/gem/i915_gem_shrinker.c

@@ -15,6 +15,7 @@
 
 #include "gt/intel_gt_requests.h"
 
+#include "dma_resv_utils.h"
 #include "i915_trace.h"
 
 static bool swap_available(void)
@@ -209,6 +210,8 @@ i915_gem_shrink(struct drm_i915_private *i915,
 				mutex_unlock(&obj->mm.lock);
 			}
 
+			dma_resv_prune(obj->base.resv);
+
 			scanned += obj->base.size >> PAGE_SHIFT;
 			i915_gem_object_put(obj);
 

drivers/gpu/drm/i915/gem/i915_gem_stolen.c

@@ -608,11 +608,10 @@ i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 	struct drm_mm_node *stolen = fetch_and_zero(&obj->stolen);
 
 	GEM_BUG_ON(!stolen);
-
-	i915_gem_object_release_memory_region(obj);
-
 	i915_gem_stolen_remove_node(i915, stolen);
 	kfree(stolen);
+
+	i915_gem_object_release_memory_region(obj);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {

drivers/gpu/drm/i915/gem/i915_gem_wait.c

@@ -9,6 +9,7 @@
 
 #include "gt/intel_engine.h"
 
+#include "dma_resv_utils.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
 
@@ -84,11 +85,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv,
 	 * Opportunistically prune the fences iff we know they have *all* been
 	 * signaled.
 	 */
-	if (prune_fences && dma_resv_trylock(resv)) {
-		if (dma_resv_test_signaled_rcu(resv, true))
-			dma_resv_add_excl_fence(resv, NULL);
-		dma_resv_unlock(resv);
-	}
+	if (prune_fences)
+		dma_resv_prune(resv);
 
 	return timeout;
 }

drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c

@@ -27,7 +27,7 @@ static void huge_free_pages(struct drm_i915_gem_object *obj,
 
 static int huge_get_pages(struct drm_i915_gem_object *obj)
 {
-#define GFP (GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY)
+#define GFP (GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL)
 	const unsigned long nreal = obj->scratch / PAGE_SIZE;
 	const unsigned long npages = obj->base.size / PAGE_SIZE;
 	struct scatterlist *sg, *src, *end;

drivers/gpu/drm/i915/gem/selftests/huge_pages.c

@@ -368,6 +368,27 @@ static int igt_check_page_sizes(struct i915_vma *vma)
 		err = -EINVAL;
 	}
 
+	/*
+	 * The dma-api is like a box of chocolates when it comes to the
+	 * alignment of dma addresses, however for LMEM we have total control
+	 * and so can guarantee alignment, likewise when we allocate our blocks
+	 * they should appear in descending order, and if we know that we align
+	 * to the largest page size for the GTT address, we should be able to
+	 * assert that if we see 2M physical pages then we should also get 2M
+	 * GTT pages. If we don't then something might be wrong in our
+	 * construction of the backing pages.
+	 *
+	 * Maintaining alignment is required to utilise huge pages in the ppGGT.
+	 */
+	if (i915_gem_object_is_lmem(obj) &&
+	    IS_ALIGNED(vma->node.start, SZ_2M) &&
+	    vma->page_sizes.sg & SZ_2M &&
+	    vma->page_sizes.gtt < SZ_2M) {
+		pr_err("gtt pages mismatch for LMEM, expected 2M GTT pages, sg(%u), gtt(%u)\n",
+		       vma->page_sizes.sg, vma->page_sizes.gtt);
+		err = -EINVAL;
+	}
+
 	if (obj->mm.page_sizes.gtt) {
 		pr_err("obj->page_sizes.gtt(%u) should never be set\n",
 		       obj->mm.page_sizes.gtt);
@@ -1333,6 +1354,7 @@ static int igt_ppgtt_sanity_check(void *arg)
 		unsigned int flags;
 	} backends[] = {
 		{ igt_create_system, 0,                        },
+		{ igt_create_local,  0,                        },
 		{ igt_create_local,  I915_BO_ALLOC_CONTIGUOUS, },
 	};
 	struct {

drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c

@@ -20,13 +20,11 @@ static int __igt_client_fill(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce = engine->kernel_context;
 	struct drm_i915_gem_object *obj;
-	struct rnd_state prng;
+	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end);
 	u32 *vaddr;
 	int err = 0;
 
-	prandom_seed_state(&prng, i915_selftest.random_seed);
-
 	intel_engine_pm_get(engine);
 	do {
 		const u32 max_block_size = S16_MAX * PAGE_SIZE;

drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c

@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_ring.h"

drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c

@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_gpu_commands.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gem/i915_gem_region.h"