Commit 334a1683 authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'drm-intel-gt-next-2020-11-12-1' of... 

Merge tag 'drm-intel-gt-next-2020-11-12-1' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Cross-subsystem Changes:
- DMA mapped scatterlist fixes in i915 to unblock merging of
  https://lkml.org/lkml/2020/9/27/70

 (Tvrtko, Tom)

Driver Changes:

- Fix for user reported issue #2381 (Graphical output stops with "switching to inteldrmfb from simple"):
  Mark ininitial fb obj as WT on eLLC machines to avoid rcu lockup during fbdev init (Ville, Chris)
- Fix for Tigerlake (and earlier) to avoid spurious empty CSB events leading to hang (Chris, Bruce)
- Delay execlist processing for Tigerlake to avoid hang (Chris)
- Fix for Tigerlake RCS engine health check through heartbeat (Chris)
- Fix for Tigerlake reserved MOCS entries (Ayaz, Chris)
- Fix Media power gate sequence on Tigerlake (Rodrigo)
- Enable eLLC caching of display buffers for SKL+ (Ville)
- Support parsing of oversize batches on Gen9 (Matt, Chris)
- Exclude low pages (128KiB) of stolen from use to avoid thrashing during reset (Chris)
- Flush engines before Tigerlake breadcrumbs (Chris)

- Use the local HWSP offset during submission (Chris)
- Flush coherency domains on first set-domain-ioctl (Chris, Zbigniew)
- Use the active reference on the vma while capturing to avoid use-after-free (Chris)
- Fix MOCS PTE setting for gen9+ (Ville)
- Avoid NULL dereference on IPS driver callback while unbinding i915 (Chris)
- Avoid NULL dereference from PT/PD stash allocation error (Matt)
- Hold request reference for canceling an active context (Chris)
- Avoid infinite loop on x86-32 when mapping a lot of objects (Chris)
- Disallow WC mappings when processor doesn't support them (Chris)
- Return correct error in i915_gem_object_copy_blt() error path (Dan)
- Return correct error in intel_context_create_request() error path (Maarten)
- Tune down GuC communication enabled/disabled messages to debug (Jani)
- Fix rebased commit "Remove i915_request.lock requirement for execution callbacks" (Chris)
- Cancel outstanding work after disabling heartbeats on an engine (Chris)
- Signal cancelled requests (Chris)
- Retire cancelled requests on unload (Chris)
- Scrub HW state on driver remove (Chris)
- Undo forced context restores after trivial preemptions (Chris)
- Handle PCI unbind in PMU code (Tvrtko)
- Fix CPU hotplug with multiple GPUs in PMU code (Trtkko)
- Correctly set SFC capability for video engines (Venkata)

- Update GuC code to use firmware v49.0.1 (John, Matthew B., Daniele, Oscar, Michel, Rodrigo, Michal)
- Improve GuC warnings on loading failure (John)
- Avoid ownership race in buffer pool by clearing age (Chris)
- Use MMIO to read CSB in case of failure (Chris, Mika)
- Show engine properties in engine state dump to indicate changes (Chris, Joonas)
- Break up error capture compression loops with cond_resched() (Chris)
- Reduce GPU error capture mutex hold time to avoid khungtaskd (Chris)
- Serialise debugfs i915_gem_objects with ctx->mutex (Chris)
- Always test execution status on closing the context and close if not persistent (Chris)
- Avoid mixing integer types during batch copies (Chris, Jared)
- Skip over MI_NOOP when parsing to avoid overhead (Chris)
- Hold onto an explicit ref to i915_vma_work.pinned (Chris)
- Perform all asynchronous waits prior to marking payload start (Chris)
- Pull phys pread/pwrite implementations to the backend (Matt)

- Improve record of hung engines in error state (Tvrtko)
- Allow backends to override pread implementation (Matt)
- Reinforce LRC poisoning checks to confirm context survives execution (Chris)
- Fix memory region max size calculation (Matt)
- Fix order when adding blocks to memory region (Matt)
- Eliminate unused intel_virtual_engine_get_sibling func (Chris)
- Cleanup kasan warning for on-stack (unsigned long) casting (Chris)
- Onion unwind for scratch page allocation failure (Chris)
- Poison stolen pages before use (Chris)
- Selftest improvements (Chris)

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

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201112163407.GA20320@jlahtine-mobl.ger.corp.intel.com
parents 24bdae69 695dc55b

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

+9 −9
Original line number Diff line number Diff line
@@ -202,12 +202,6 @@ retry: 
	if (unlikely(err))

		goto out_request;



	if (w->ce->engine->emit_init_breadcrumb) {

		err = w->ce->engine->emit_init_breadcrumb(rq);

		if (unlikely(err))

			goto out_request;

	}



	/*

	 * w->dma is already exported via (vma|obj)->resv we need only

	 * keep track of the GPU activity within this vma/request, and
@@ -217,7 +211,13 @@ retry: 
	if (err)

		goto out_request;



	err = w->ce->engine->emit_bb_start(rq,

	if (rq->engine->emit_init_breadcrumb) {

		err = rq->engine->emit_init_breadcrumb(rq);

		if (unlikely(err))

			goto out_request;

	}



	err = rq->engine->emit_bb_start(rq,

					batch->node.start, batch->node.size,

					0);

out_request:

drivers/gpu/drm/i915/gem/i915_gem_object.c

+2 −0
Original line number Diff line number Diff line
@@ -82,6 +82,8 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, 
	obj->mm.madv = I915_MADV_WILLNEED;

	INIT_RADIX_TREE(&obj->mm.get_page.radix, GFP_KERNEL | __GFP_NOWARN);

	mutex_init(&obj->mm.get_page.lock);

	INIT_RADIX_TREE(&obj->mm.get_dma_page.radix, GFP_KERNEL | __GFP_NOWARN);

	mutex_init(&obj->mm.get_dma_page.lock);



	if (IS_ENABLED(CONFIG_LOCKDEP) && i915_gem_object_is_shrinkable(obj))

		i915_gem_shrinker_taints_mutex(to_i915(obj->base.dev),

drivers/gpu/drm/i915/gem/i915_gem_object.h

+19 −1
Original line number Diff line number Diff line
@@ -272,8 +272,26 @@ int i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, 
			       unsigned int tiling, unsigned int stride);



struct scatterlist *

__i915_gem_object_get_sg(struct drm_i915_gem_object *obj,

			 struct i915_gem_object_page_iter *iter,

			 unsigned int n,

			 unsigned int *offset);



static inline struct scatterlist *

i915_gem_object_get_sg(struct drm_i915_gem_object *obj,

		       unsigned int n, unsigned int *offset);

		       unsigned int n,

		       unsigned int *offset)

{

	return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset);

}



static inline struct scatterlist *

i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj,

			   unsigned int n,

			   unsigned int *offset)

{

	return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset);

}



struct page *

i915_gem_object_get_page(struct drm_i915_gem_object *obj,

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

+12 −7
Original line number Diff line number Diff line
@@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops { 
	void (*truncate)(struct drm_i915_gem_object *obj);

	void (*writeback)(struct drm_i915_gem_object *obj);



	int (*pread)(struct drm_i915_gem_object *obj,

		     const struct drm_i915_gem_pread *arg);

	int (*pwrite)(struct drm_i915_gem_object *obj,

		      const struct drm_i915_gem_pwrite *arg);
@@ -80,6 +82,14 @@ struct i915_mmap_offset { 
	struct rb_node offset;

};



struct i915_gem_object_page_iter {

	struct scatterlist *sg_pos;

	unsigned int sg_idx; /* in pages, but 32bit eek! */



	struct radix_tree_root radix;

	struct mutex lock; /* protects this cache */

};



struct drm_i915_gem_object {

	struct drm_gem_object base;
@@ -246,13 +256,8 @@ struct drm_i915_gem_object { 


		I915_SELFTEST_DECLARE(unsigned int page_mask);



		struct i915_gem_object_page_iter {

			struct scatterlist *sg_pos;

			unsigned int sg_idx; /* in pages, but 32bit eek! */



			struct radix_tree_root radix;

			struct mutex lock; /* protects this cache */

		} get_page;

		struct i915_gem_object_page_iter get_page;

		struct i915_gem_object_page_iter get_dma_page;



		/**

		 * Element within i915->mm.unbound_list or i915->mm.bound_list,

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

+13 −8
Original line number Diff line number Diff line
@@ -33,6 +33,8 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, 


	obj->mm.get_page.sg_pos = pages->sgl;

	obj->mm.get_page.sg_idx = 0;

	obj->mm.get_dma_page.sg_pos = pages->sgl;

	obj->mm.get_dma_page.sg_idx = 0;



	obj->mm.pages = pages;
@@ -155,6 +157,8 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj) 
	rcu_read_lock();

	radix_tree_for_each_slot(slot, &obj->mm.get_page.radix, &iter, 0)

		radix_tree_delete(&obj->mm.get_page.radix, iter.index);

	radix_tree_for_each_slot(slot, &obj->mm.get_dma_page.radix, &iter, 0)

		radix_tree_delete(&obj->mm.get_dma_page.radix, iter.index);

	rcu_read_unlock();

}
@@ -438,11 +442,12 @@ void __i915_gem_object_release_map(struct drm_i915_gem_object *obj) 
}



struct scatterlist *

i915_gem_object_get_sg(struct drm_i915_gem_object *obj,

__i915_gem_object_get_sg(struct drm_i915_gem_object *obj,

			 struct i915_gem_object_page_iter *iter,

			 unsigned int n,

			 unsigned int *offset)

{

	struct i915_gem_object_page_iter *iter = &obj->mm.get_page;

	const bool dma = iter == &obj->mm.get_dma_page;

	struct scatterlist *sg;

	unsigned int idx, count;
@@ -471,7 +476,7 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, 


	sg = iter->sg_pos;

	idx = iter->sg_idx;

	count = __sg_page_count(sg);

	count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);



	while (idx + count <= n) {

		void *entry;
@@ -499,7 +504,7 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, 


		idx += count;

		sg = ____sg_next(sg);

		count = __sg_page_count(sg);

		count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);

	}



scan:
@@ -517,7 +522,7 @@ scan: 
	while (idx + count <= n) {

		idx += count;

		sg = ____sg_next(sg);

		count = __sg_page_count(sg);

		count = dma ? __sg_dma_page_count(sg) : __sg_page_count(sg);

	}



	*offset = n - idx;
@@ -584,7 +589,7 @@ i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, 
	struct scatterlist *sg;

	unsigned int offset;



	sg = i915_gem_object_get_sg(obj, n, &offset);

	sg = i915_gem_object_get_sg_dma(obj, n, &offset);



	if (len)

		*len = sg_dma_len(sg) - (offset << PAGE_SHIFT);

CRA Git | Maintained and supported by SUSTech CRA and CCSE