Commit 89351925 authored by Chris Wilson's avatar Chris Wilson Committed by Joonas Lahtinen
Browse files

drm/i915/gt: Switch to object allocations for page directories 



The GEM object is grossly overweight for the practicality of tracking
large numbers of individual pages, yet it is currently our only
abstraction for tracking DMA allocations. Since those allocations need
to be reserved upfront before an operation, and that we need to break
away from simple system memory, we need to ditch using plain struct page
wrappers.

In the process, we drop the WC mapping as we ended up clflushing
everything anyway due to various issues across a wider range of
platforms. Though in a future step, we need to drop the kmap_atomic
approach which suggests we need to pre-map all the pages and keep them
mapped.

v2: Verify our large scratch page is suitably DMA aligned; and manually
clear the scratch since we are allocating plain struct pages full of
prior content.

Signed-off-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: default avatarMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200729164219.5737-2-chris@chris-wilson.co.uk


Signed-off-by: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: default avatarJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
parent cd0452aa

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

+1 −0
Original line number Diff line number Diff line
@@ -282,6 +282,7 @@ struct drm_i915_gem_object { 
		} userptr;



		unsigned long scratch;

		u64 encode;



		void *gvt_info;

	};

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

+1 −1
Original line number Diff line number Diff line
@@ -393,7 +393,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg) 
	 */



	for (i = 1; i < BIT(ARRAY_SIZE(page_sizes)); i++) {

		unsigned int combination = 0;

		unsigned int combination = SZ_4K; /* Required for ppGTT */



		for (j = 0; j < ARRAY_SIZE(page_sizes); j++) {

			if (i & BIT(j))

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

+1 −1
Original line number Diff line number Diff line
@@ -1748,7 +1748,7 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out) 
	if (!vm)

		return -ENODEV;



	page = vm->scratch[0].base.page;

	page = __px_page(vm->scratch[0]);

	if (!page) {

		pr_err("No scratch page!\n");

		return -EINVAL;

drivers/gpu/drm/i915/gt/gen6_ppgtt.c

+27 −26
Original line number Diff line number Diff line
@@ -16,8 +16,10 @@ static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt, 
				  const unsigned int pde,

				  const struct i915_page_table *pt)

{

	dma_addr_t addr = pt ? px_dma(pt) : px_dma(ppgtt->base.vm.scratch[1]);



	/* Caller needs to make sure the write completes if necessary */

	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,

	iowrite32(GEN6_PDE_ADDR_ENCODE(addr) | GEN6_PDE_VALID,

		  ppgtt->pd_addr + pde);

}
@@ -79,7 +81,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, 
{

	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));

	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;

	const gen6_pte_t scratch_pte = vm->scratch[0].encode;

	const gen6_pte_t scratch_pte = vm->scratch[0]->encode;

	unsigned int pde = first_entry / GEN6_PTES;

	unsigned int pte = first_entry % GEN6_PTES;

	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
@@ -90,8 +92,6 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, 
		const unsigned int count = min(num_entries, GEN6_PTES - pte);

		gen6_pte_t *vaddr;



		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));



		num_entries -= count;



		GEM_BUG_ON(count > atomic_read(&pt->used));
@@ -127,7 +127,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, 
	struct sgt_dma iter = sgt_dma(vma);

	gen6_pte_t *vaddr;



	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);

	GEM_BUG_ON(!pd->entry[act_pt]);



	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));

	do {
@@ -192,16 +192,17 @@ static void gen6_alloc_va_range(struct i915_address_space *vm, 
	gen6_for_each_pde(pt, pd, start, length, pde) {

		const unsigned int count = gen6_pte_count(start, length);



		if (px_base(pt) == px_base(&vm->scratch[1])) {

		if (!pt) {

			spin_unlock(&pd->lock);



			pt = stash->pt[0];

			GEM_BUG_ON(!pt);

			__i915_gem_object_pin_pages(pt->base);

			i915_gem_object_make_unshrinkable(pt->base);



			fill32_px(pt, vm->scratch[0].encode);

			fill32_px(pt, vm->scratch[0]->encode);



			spin_lock(&pd->lock);

			if (pd->entry[pde] == &vm->scratch[1]) {

			if (!pd->entry[pde]) {

				stash->pt[0] = pt->stash;

				atomic_set(&pt->used, 0);

				pd->entry[pde] = pt;
@@ -227,24 +228,27 @@ static void gen6_alloc_va_range(struct i915_address_space *vm, 
static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)

{

	struct i915_address_space * const vm = &ppgtt->base.vm;

	struct i915_page_directory * const pd = ppgtt->base.pd;

	int ret;



	ret = setup_scratch_page(vm, __GFP_HIGHMEM);

	ret = setup_scratch_page(vm);

	if (ret)

		return ret;



	vm->scratch[0].encode =

		vm->pte_encode(px_dma(&vm->scratch[0]),

	vm->scratch[0]->encode =

		vm->pte_encode(px_dma(vm->scratch[0]),

			       I915_CACHE_NONE, PTE_READ_ONLY);



	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {

		cleanup_scratch_page(vm);

		return -ENOMEM;

	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);

	if (IS_ERR(vm->scratch[1]))

		return PTR_ERR(vm->scratch[1]);



	ret = pin_pt_dma(vm, vm->scratch[1]);

	if (ret) {

		i915_gem_object_put(vm->scratch[1]);

		return ret;

	}



	fill32_px(&vm->scratch[1], vm->scratch[0].encode);

	memset_p(pd->entry, &vm->scratch[1], I915_PDES);

	fill32_px(vm->scratch[1], vm->scratch[0]->encode);



	return 0;

}
@@ -252,13 +256,11 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt) 
static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)

{

	struct i915_page_directory * const pd = ppgtt->base.pd;

	struct i915_page_dma * const scratch =

		px_base(&ppgtt->base.vm.scratch[1]);

	struct i915_page_table *pt;

	u32 pde;



	gen6_for_all_pdes(pt, pd, pde)

		if (px_base(pt) != scratch)

		if (pt)

			free_px(&ppgtt->base.vm, pt);

}
@@ -299,7 +301,7 @@ static void pd_vma_bind(struct i915_address_space *vm, 
	struct gen6_ppgtt *ppgtt = vma->private;

	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;



	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);

	ppgtt->pp_dir = ggtt_offset * sizeof(gen6_pte_t) << 10;

	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;



	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
@@ -309,8 +311,6 @@ static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma) 
{

	struct gen6_ppgtt *ppgtt = vma->private;

	struct i915_page_directory * const pd = ppgtt->base.pd;

	struct i915_page_dma * const scratch =

		px_base(&ppgtt->base.vm.scratch[1]);

	struct i915_page_table *pt;

	unsigned int pde;
@@ -319,11 +319,11 @@ static void pd_vma_unbind(struct i915_address_space *vm, struct i915_vma *vma) 


	/* Free all no longer used page tables */

	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {

		if (px_base(pt) == scratch || atomic_read(&pt->used))

		if (!pt || atomic_read(&pt->used))

			continue;



		free_px(&ppgtt->base.vm, pt);

		pd->entry[pde] = scratch;

		pd->entry[pde] = NULL;

	}



	ppgtt->scan_for_unused_pt = false;
@@ -444,6 +444,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) 
	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;

	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;



	ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma;

	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;



	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));

drivers/gpu/drm/i915/gt/gen6_ppgtt.h

+1 −0
Original line number Diff line number Diff line
@@ -14,6 +14,7 @@ struct gen6_ppgtt { 
	struct mutex flush;

	struct i915_vma *vma;

	gen6_pte_t __iomem *pd_addr;

	u32 pp_dir;



	atomic_t pin_count;

	struct mutex pin_mutex;

CRA Git | Maintained and supported by SUSTech CRA and CCSE