Merge tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is a new Qualcomm accel driver for their QAIC, dma-fence got a
  deadline feature added, lots of refactoring around fbdev emulation,
  and the usual pre-release hw enablements from AMD and Intel and fixes
  everywhere.

  New drivers:
   - add QAIC acceleration driver

  dma-buf:
   - constify kobj_type structs
   - Reject prime DMA-Buf attachment if get_sg_table is missing.

  fbdev:
   - cmdline parser fixes
   - implement fbdev emulation for GEM DMA drivers
   - always use shadow buffer in fbdev emulation helpers

  dma-fence:
   - add deadline hint to fences
   - signal private stub fence

  core:
   - improve DisplayID 2.0 and EDID parsing
   - add gem eviction function + callback
   - prep to convert shmem helper to GEM resv lock
   - move suballocator from radeon/amdgpu to core for Xe
   - HPD polling fixes
   - Documentation improvements
   - Add atomic enable_plane callback
   - use tgid instead of pid for client tracking
   - DP: Add SDP Error Detection Configuration Register
   - Add prime import/export to vram-helper
   - use pci aperture helpers in more drivers

  panel:
   - Radxa 8/10HD support
   - Samsung AMD495QA01 support
   - Elida KD50T048A
   - Sony TD4353
   - Novatek NT36523
   - STARRY 2081101QFH032011-53G
   - B133UAN01.0
   - AUO NE135FBM-N41

  i915:
   - More MTL enabling
   - fix s/r problems with MEI/PXP
   - Implement fb_dirty for PSR,FBC,DRRS fixes
   - Fix eDP+DSI dual panel systems
   - Fix issue #6333: "list_add corruption" and full system lockup from
     performance monitoring
   - Don't use stolen memory or BAR for ring buffers on LLC platforms
   - Make sure DSM size has correct 1MiB granularity on Gen12+
   - Whitelist COMMON_SLICE_CHICKEN3 for UMD access on Gen12+
   - Add engine TLB invalidation for Meteorlake
   - Fix GSC races on driver load/unload on Meteorlake+
   - Make kobj_type structures constant
   - Move fd_install after last use of fence
   - wm/vblank refactoring
   - display code refactoring
   - Create GSC submission targeting HDCP and PXP usages on MTL+
   - Enable HDCP2.x via GSC CS
   - Fix context runtime accounting on sysfs fdinfo for heavy workloads
   - Use i915 instead of dev_priv insied the file_priv structure
   - Replace fake flex-array with flexible-array member

  amdgpu:
   - Make kobj structures const
   - Generalize dmabuf import to work with KFD
   - Add capped/uncapped workload handling for supported APUs
   - Expose additional memory stats via fdinfo
   - Register vga_switcheroo for apple-gmux
   - Initial NBIO7.9, GC 9.4.3, GFXHUB 1.2, MMHUB 1.8 support
   - Initial DC FAM infrastructure
   - Link DC backlight to connector device rather than PCI device
   - Add sysfs nodes for secondary VCN clocks

  amdkfd:
   - Make kobj structures const
   - Support for exporting buffers via dmabuf
   - Multi-VMA page migration fixes
   - initial GC 9.4.3 support

  radeon:
   - iMac fix
   - convert to client based fbdev emulation

  habanalabs:
   - Add opcodes to the CS ioctl to allow user to stall/resume specific
     engines inside Gaudi2.
   - INFO ioctl the amount of device memory that the driver and f/w
     reserve for themselves.
   - INFO ioctl a bit-mask of the available rotator engines
   - INFO ioctl the register's address of the f/w that should be used to
     trigger interrupts
   - INFO ioctl two new opcodes to fetch information on h/w and f/w
     events
   - Enable graceful reset mechanism for compute-reset.
   - Align to the latest firmware specs.
   - Enforce the release order of the compute device and dma-buf.

  msm:
   - UBWC decoder programming rework
   - SM8550, SM8450 bindings update
   - uapi C++ fix
   - a3xx and a4xx devfreq support
   - GPU and GEM updates to avoid allocations which could trigger
     reclaim (shrinker) in fence signaling path
   - dma-fence deadline hint support and wait-boost
   - a640/650 speed bin support

  cirrus:
   - convert to regular atomic helpers
   - add damage clipping

  mediatek:
   - 10-bit overlay support
   - mt8195 support
   - Only trigger DRM HPD events if bridge is attached
   - Change the aux retries times when receiving AUX_DEFER

  rockchip:
   - add 4K support

  vc4:
   - use drm_gem_objects

  virtio:
   - allow KMS support to be disabled
   - add damage clipping

  vmwgfx:
   - buffer object lifetime fixes

  exynos:
   - move MIPI DSI driver to drm bridge for iMX sharing
   - use kernel fbdev emulation

  panfrost:
   - add support for mali MT81xx devices
   - add speed binning support

  lima:
   - add usage stats

  tegra:
   - fbdev client conversion

  vkms:
   - Add primary plane positioning support"

* tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm: (1495 commits)
  drm/i915/dp_mst: Fix active port PLL selection for secondary MST streams
  drm/exynos: Implement fbdev emulation as in-kernel client
  drm/exynos: Initialize fbdev DRM client
  drm/exynos: Remove fb_helper from struct exynos_drm_private
  drm/exynos: Remove struct exynos_drm_fbdev
  drm/exynos: Remove exynos_gem from struct exynos_drm_fbdev
  drm/i915: Fix memory leaks in i915 selftests
  drm/i915: Make intel_get_crtc_new_encoder() less oopsy
  drm/i915/gt: Avoid out-of-bounds access when loading HuC
  drm/amdgpu: add some basic elements for multiple XCD case
  drm/amdgpu: move vmhub out of amdgpu_ring_funcs (v4)
  Revert "drm/amdgpu: enable ras for mp0 v13_0_10 on SRIOV"
  drm/amdgpu: add common ip block for GC 9.4.3
  drm/amd/display: Add logging when DP link training Clock recovery is Successful
  drm/amdgpu: add common early init support for GC 9.4.3
  drm/amdgpu: switch to v9_4_3 gfx_funcs callbacks for GC 9.4.3
  drm/amd/display: Add logging when setting DP sink power state fails
  drm/amdkfd: Add gfx_target_version for GC 9.4.3
  drm/amdkfd: Enable HW_UPDATE_RPTR on GC 9.4.3
  drm/amdgpu: reserve the old gc_11_0_*_mes.bin
  ...

1 files changed, 3 insertions, 357 deletions

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 01e75160a84a..154801f1c468 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -69,8 +69,10 @@ static int fake_get_pages(struct drm_i915_gem_object *obj)
 
 	rem = round_up(obj->base.size, BIT(31)) >> 31;
 	/* restricted by sg_alloc_table */
-	if (overflows_type(rem, unsigned int))
+	if (overflows_type(rem, unsigned int)) {
+		kfree(pages);
 		return -E2BIG;
+	}
 
 	if (sg_alloc_table(pages, rem, GFP)) {
 		kfree(pages);
@@ -1940,361 +1942,6 @@ out_put:
 	return err;
 }
 
-static int context_sync(struct intel_context *ce)
-{
-	struct i915_request *rq;
-	long timeout;
-
-	rq = intel_context_create_request(ce);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
-
-	i915_request_get(rq);
-	i915_request_add(rq);
-
-	timeout = i915_request_wait(rq, 0, HZ / 5);
-	i915_request_put(rq);
-
-	return timeout < 0 ? -EIO : 0;
-}
-
-static struct i915_request *
-submit_batch(struct intel_context *ce, u64 addr)
-{
-	struct i915_request *rq;
-	int err;
-
-	rq = intel_context_create_request(ce);
-	if (IS_ERR(rq))
-		return rq;
-
-	err = 0;
-	if (rq->engine->emit_init_breadcrumb) /* detect a hang */
-		err = rq->engine->emit_init_breadcrumb(rq);
-	if (err == 0)
-		err = rq->engine->emit_bb_start(rq, addr, 0, 0);
-
-	if (err == 0)
-		i915_request_get(rq);
-	i915_request_add(rq);
-
-	return err ? ERR_PTR(err) : rq;
-}
-
-static u32 *spinner(u32 *batch, int i)
-{
-	return batch + i * 64 / sizeof(*batch) + 4;
-}
-
-static void end_spin(u32 *batch, int i)
-{
-	*spinner(batch, i) = MI_BATCH_BUFFER_END;
-	wmb();
-}
-
-static int igt_cs_tlb(void *arg)
-{
-	const unsigned int count = PAGE_SIZE / 64;
-	const unsigned int chunk_size = count * PAGE_SIZE;
-	struct drm_i915_private *i915 = arg;
-	struct drm_i915_gem_object *bbe, *act, *out;
-	struct i915_gem_engines_iter it;
-	struct i915_address_space *vm;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
-	struct i915_vma *vma;
-	I915_RND_STATE(prng);
-	struct file *file;
-	unsigned int i;
-	u32 *result;
-	u32 *batch;
-	int err = 0;
-
-	/*
-	 * Our mission here is to fool the hardware to execute something
-	 * from scratch as it has not seen the batch move (due to missing
-	 * the TLB invalidate).
-	 */
-
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_unlock;
-	}
-
-	vm = i915_gem_context_get_eb_vm(ctx);
-	if (i915_is_ggtt(vm))
-		goto out_vm;
-
-	/* Create two pages; dummy we prefill the TLB, and intended */
-	bbe = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(bbe)) {
-		err = PTR_ERR(bbe);
-		goto out_vm;
-	}
-
-	batch = i915_gem_object_pin_map_unlocked(bbe, I915_MAP_WC);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put_bbe;
-	}
-	memset32(batch, MI_BATCH_BUFFER_END, PAGE_SIZE / sizeof(u32));
-	i915_gem_object_flush_map(bbe);
-	i915_gem_object_unpin_map(bbe);
-
-	act = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(act)) {
-		err = PTR_ERR(act);
-		goto out_put_bbe;
-	}
-
-	/* Track the execution of each request by writing into different slot */
-	batch = i915_gem_object_pin_map_unlocked(act, I915_MAP_WC);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_put_act;
-	}
-	for (i = 0; i < count; i++) {
-		u32 *cs = batch + i * 64 / sizeof(*cs);
-		u64 addr = (vm->total - PAGE_SIZE) + i * sizeof(u32);
-
-		GEM_BUG_ON(GRAPHICS_VER(i915) < 6);
-		cs[0] = MI_STORE_DWORD_IMM_GEN4;
-		if (GRAPHICS_VER(i915) >= 8) {
-			cs[1] = lower_32_bits(addr);
-			cs[2] = upper_32_bits(addr);
-			cs[3] = i;
-			cs[4] = MI_NOOP;
-			cs[5] = MI_BATCH_BUFFER_START_GEN8;
-		} else {
-			cs[1] = 0;
-			cs[2] = lower_32_bits(addr);
-			cs[3] = i;
-			cs[4] = MI_NOOP;
-			cs[5] = MI_BATCH_BUFFER_START;
-		}
-	}
-
-	out = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(out)) {
-		err = PTR_ERR(out);
-		goto out_put_batch;
-	}
-	i915_gem_object_set_cache_coherency(out, I915_CACHING_CACHED);
-
-	vma = i915_vma_instance(out, vm, NULL);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto out_put_out;
-	}
-
-	err = i915_vma_pin(vma, 0, 0,
-			   PIN_USER |
-			   PIN_OFFSET_FIXED |
-			   (vm->total - PAGE_SIZE));
-	if (err)
-		goto out_put_out;
-	GEM_BUG_ON(vma->node.start != vm->total - PAGE_SIZE);
-
-	result = i915_gem_object_pin_map_unlocked(out, I915_MAP_WB);
-	if (IS_ERR(result)) {
-		err = PTR_ERR(result);
-		goto out_put_out;
-	}
-
-	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
-		IGT_TIMEOUT(end_time);
-		unsigned long pass = 0;
-
-		if (!intel_engine_can_store_dword(ce->engine))
-			continue;
-
-		while (!__igt_timeout(end_time, NULL)) {
-			struct i915_vm_pt_stash stash = {};
-			struct i915_request *rq;
-			struct i915_gem_ww_ctx ww;
-			struct i915_vma_resource *vma_res;
-			u64 offset;
-
-			offset = igt_random_offset(&prng,
-						   0, vm->total - PAGE_SIZE,
-						   chunk_size, PAGE_SIZE);
-
-			memset32(result, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
-
-			vma = i915_vma_instance(bbe, vm, NULL);
-			if (IS_ERR(vma)) {
-				err = PTR_ERR(vma);
-				goto end;
-			}
-
-			i915_gem_object_lock(bbe, NULL);
-			err = i915_vma_get_pages(vma);
-			i915_gem_object_unlock(bbe);
-			if (err)
-				goto end;
-
-			vma_res = i915_vma_resource_alloc();
-			if (IS_ERR(vma_res)) {
-				i915_vma_put_pages(vma);
-				err = PTR_ERR(vma_res);
-				goto end;
-			}
-
-			i915_gem_ww_ctx_init(&ww, false);
-retry:
-			err = i915_vm_lock_objects(vm, &ww);
-			if (err)
-				goto end_ww;
-
-			err = i915_vm_alloc_pt_stash(vm, &stash, chunk_size);
-			if (err)
-				goto end_ww;
-
-			err = i915_vm_map_pt_stash(vm, &stash);
-			if (!err)
-				vm->allocate_va_range(vm, &stash, offset, chunk_size);
-			i915_vm_free_pt_stash(vm, &stash);
-end_ww:
-			if (err == -EDEADLK) {
-				err = i915_gem_ww_ctx_backoff(&ww);
-				if (!err)
-					goto retry;
-			}
-			i915_gem_ww_ctx_fini(&ww);
-			if (err) {
-				kfree(vma_res);
-				goto end;
-			}
-
-			i915_vma_resource_init_from_vma(vma_res, vma);
-			/* Prime the TLB with the dummy pages */
-			for (i = 0; i < count; i++) {
-				vma_res->start = offset + i * PAGE_SIZE;
-				vm->insert_entries(vm, vma_res, I915_CACHE_NONE,
-						   0);
-
-				rq = submit_batch(ce, vma_res->start);
-				if (IS_ERR(rq)) {
-					err = PTR_ERR(rq);
-					i915_vma_resource_fini(vma_res);
-					kfree(vma_res);
-					goto end;
-				}
-				i915_request_put(rq);
-			}
-			i915_vma_resource_fini(vma_res);
-			i915_vma_put_pages(vma);
-
-			err = context_sync(ce);
-			if (err) {
-				pr_err("%s: dummy setup timed out\n",
-				       ce->engine->name);
-				kfree(vma_res);
-				goto end;
-			}
-
-			vma = i915_vma_instance(act, vm, NULL);
-			if (IS_ERR(vma)) {
-				kfree(vma_res);
-				err = PTR_ERR(vma);
-				goto end;
-			}
-
-			i915_gem_object_lock(act, NULL);
-			err = i915_vma_get_pages(vma);
-			i915_gem_object_unlock(act);
-			if (err) {
-				kfree(vma_res);
-				goto end;
-			}
-
-			i915_vma_resource_init_from_vma(vma_res, vma);
-			/* Replace the TLB with target batches */
-			for (i = 0; i < count; i++) {
-				struct i915_request *rq;
-				u32 *cs = batch + i * 64 / sizeof(*cs);
-				u64 addr;
-
-				vma_res->start = offset + i * PAGE_SIZE;
-				vm->insert_entries(vm, vma_res, I915_CACHE_NONE, 0);
-
-				addr = vma_res->start + i * 64;
-				cs[4] = MI_NOOP;
-				cs[6] = lower_32_bits(addr);
-				cs[7] = upper_32_bits(addr);
-				wmb();
-
-				rq = submit_batch(ce, addr);
-				if (IS_ERR(rq)) {
-					err = PTR_ERR(rq);
-					i915_vma_resource_fini(vma_res);
-					kfree(vma_res);
-					goto end;
-				}
-
-				/* Wait until the context chain has started */
-				if (i == 0) {
-					while (READ_ONCE(result[i]) &&
-					       !i915_request_completed(rq))
-						cond_resched();
-				} else {
-					end_spin(batch, i - 1);
-				}
-
-				i915_request_put(rq);
-			}
-			end_spin(batch, count - 1);
-
-			i915_vma_resource_fini(vma_res);
-			kfree(vma_res);
-			i915_vma_put_pages(vma);
-
-			err = context_sync(ce);
-			if (err) {
-				pr_err("%s: writes timed out\n",
-				       ce->engine->name);
-				goto end;
-			}
-
-			for (i = 0; i < count; i++) {
-				if (result[i] != i) {
-					pr_err("%s: Write lost on pass %lu, at offset %llx, index %d, found %x, expected %x\n",
-					       ce->engine->name, pass,
-					       offset, i, result[i], i);
-					err = -EINVAL;
-					goto end;
-				}
-			}
-
-			vm->clear_range(vm, offset, chunk_size);
-			pass++;
-		}
-	}
-end:
-	if (igt_flush_test(i915))
-		err = -EIO;
-	i915_gem_context_unlock_engines(ctx);
-	i915_gem_object_unpin_map(out);
-out_put_out:
-	i915_gem_object_put(out);
-out_put_batch:
-	i915_gem_object_unpin_map(act);
-out_put_act:
-	i915_gem_object_put(act);
-out_put_bbe:
-	i915_gem_object_put(bbe);
-out_vm:
-	i915_vm_put(vm);
-out_unlock:
-	fput(file);
-	return err;
-}
-
 int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
@@ -2314,7 +1961,6 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ggtt_fill),
 		SUBTEST(igt_ggtt_page),
 		SUBTEST(igt_ggtt_misaligned_pin),
-		SUBTEST(igt_cs_tlb),
 	};
 
 	GEM_BUG_ON(offset_in_page(to_gt(i915)->ggtt->vm.total));