Commit 60dc43d1 authored by Thomas Hellström's avatar Thomas Hellström
Browse files

drm/i915: Use struct vma_resource instead of struct vma_snapshot 



There is always a struct vma_resource guaranteed to be alive when we
access a corresponding struct vma_snapshot.

So ditch the latter and instead of allocating vma_snapshots, reference
the already existning vma_resource.

This requires a couple of extra members in struct vma_resource but that's
a small price to pay for the simplification.

v2:
- Fix a missing include and declaration (kernel test robot <lkp@intel.com>)

Signed-off-by: default avatarThomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: default avatarMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220110172219.107131-7-thomas.hellstrom@linux.intel.com
parent 950505ca

drivers/gpu/drm/i915/Makefile

+0 −1
Original line number Diff line number Diff line
@@ -175,7 +175,6 @@ i915-y += \ 
	  i915_ttm_buddy_manager.o \

	  i915_vma.o \

	  i915_vma_resource.o \

	  i915_vma_snapshot.o \

	  intel_wopcm.o



# general-purpose microcontroller (GuC) support

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

+3 −12
Original line number Diff line number Diff line
@@ -29,7 +29,6 @@ 
#include "i915_gem_ioctls.h"

#include "i915_trace.h"

#include "i915_user_extensions.h"

#include "i915_vma_snapshot.h"



struct eb_vma {

	struct i915_vma *vma;
@@ -1941,7 +1940,6 @@ static void eb_capture_stage(struct i915_execbuffer *eb) 
{

	const unsigned int count = eb->buffer_count;

	unsigned int i = count, j;

	struct i915_vma_snapshot *vsnap;



	while (i--) {

		struct eb_vma *ev = &eb->vma[i];
@@ -1951,11 +1949,6 @@ static void eb_capture_stage(struct i915_execbuffer *eb) 
		if (!(flags & EXEC_OBJECT_CAPTURE))

			continue;



		vsnap = i915_vma_snapshot_alloc(GFP_KERNEL);

		if (!vsnap)

			continue;



		i915_vma_snapshot_init(vsnap, vma, "user");

		for_each_batch_create_order(eb, j) {

			struct i915_capture_list *capture;
@@ -1964,10 +1957,9 @@ static void eb_capture_stage(struct i915_execbuffer *eb) 
				continue;



			capture->next = eb->capture_lists[j];

			capture->vma_snapshot = i915_vma_snapshot_get(vsnap);

			capture->vma_res = i915_vma_resource_get(vma->resource);

			eb->capture_lists[j] = capture;

		}

		i915_vma_snapshot_put(vsnap);

	}

}
@@ -3270,9 +3262,8 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence, 
		 * _onstack interface.

		 */

		if (eb->batches[i]->vma)

			i915_vma_snapshot_init_onstack(&eb->requests[i]->batch_snapshot,

						       eb->batches[i]->vma,

						       "batch");

			eb->requests[i]->batch_res =

				i915_vma_resource_get(eb->batches[i]->vma->resource);

		if (eb->batch_pool) {

			GEM_BUG_ON(intel_context_is_parallel(eb->context));

			intel_gt_buffer_pool_mark_active(eb->batch_pool,

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

+3 −6
Original line number Diff line number Diff line
@@ -1708,18 +1708,15 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, 


static void print_request_ring(struct drm_printer *m, struct i915_request *rq)

{

	struct i915_vma_snapshot *vsnap = &rq->batch_snapshot;

	struct i915_vma_resource *vma_res = rq->batch_res;

	void *ring;

	int size;



	if (!i915_vma_snapshot_present(vsnap))

		vsnap = NULL;



	drm_printf(m,

		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",

		   rq->head, rq->postfix, rq->tail,

		   vsnap ? upper_32_bits(vsnap->vma_resource->start) : ~0u,

		   vsnap ? lower_32_bits(vsnap->vma_resource->start) : ~0u);

		   vma_res ? upper_32_bits(vma_res->start) : ~0u,

		   vma_res ? lower_32_bits(vma_res->start) : ~0u);



	size = rq->tail - rq->head;

	if (rq->tail < rq->head)

drivers/gpu/drm/i915/i915_gpu_error.c

+40 −47
Original line number Diff line number Diff line
@@ -48,7 +48,6 @@ 
#include "i915_gpu_error.h"

#include "i915_memcpy.h"

#include "i915_scatterlist.h"

#include "i915_vma_snapshot.h"



#define ALLOW_FAIL (__GFP_KSWAPD_RECLAIM | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)

#define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN)
@@ -1013,8 +1012,10 @@ void __i915_gpu_coredump_free(struct kref *error_ref) 


static struct i915_vma_coredump *

i915_vma_coredump_create(const struct intel_gt *gt,

			 const struct i915_vma_snapshot *vsnap,

			 struct i915_vma_compress *compress)

			 const struct i915_vma_resource *vma_res,

			 struct i915_vma_compress *compress,

			 const char *name)



{

	struct i915_ggtt *ggtt = gt->ggtt;

	const u64 slot = ggtt->error_capture.start;
@@ -1024,7 +1025,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, 


	might_sleep();



	if (!vsnap || !vsnap->pages || !compress)

	if (!vma_res || !vma_res->bi.pages || !compress)

		return NULL;



	dst = kmalloc(sizeof(*dst), ALLOW_FAIL);
@@ -1037,12 +1038,12 @@ i915_vma_coredump_create(const struct intel_gt *gt, 
	}



	INIT_LIST_HEAD(&dst->page_list);

	strcpy(dst->name, vsnap->name);

	strcpy(dst->name, name);

	dst->next = NULL;



	dst->gtt_offset = vsnap->vma_resource->start;

	dst->gtt_size = vsnap->vma_resource->node_size;

	dst->gtt_page_sizes = vsnap->vma_resource->page_sizes_gtt;

	dst->gtt_offset = vma_res->start;

	dst->gtt_size = vma_res->node_size;

	dst->gtt_page_sizes = vma_res->page_sizes_gtt;

	dst->unused = 0;



	ret = -EINVAL;
@@ -1050,7 +1051,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, 
		void __iomem *s;

		dma_addr_t dma;



		for_each_sgt_daddr(dma, iter, vsnap->pages) {

		for_each_sgt_daddr(dma, iter, vma_res->bi.pages) {

			mutex_lock(&ggtt->error_mutex);

			ggtt->vm.insert_page(&ggtt->vm, dma, slot,

					     I915_CACHE_NONE, 0);
@@ -1068,11 +1069,11 @@ i915_vma_coredump_create(const struct intel_gt *gt, 
			if (ret)

				break;

		}

	} else if (vsnap->mr && vsnap->mr->type != INTEL_MEMORY_SYSTEM) {

		struct intel_memory_region *mem = vsnap->mr;

	} else if (vma_res->bi.lmem) {

		struct intel_memory_region *mem = vma_res->mr;

		dma_addr_t dma;



		for_each_sgt_daddr(dma, iter, vsnap->pages) {

		for_each_sgt_daddr(dma, iter, vma_res->bi.pages) {

			void __iomem *s;



			s = io_mapping_map_wc(&mem->iomap,
@@ -1088,7 +1089,7 @@ i915_vma_coredump_create(const struct intel_gt *gt, 
	} else {

		struct page *page;



		for_each_sgt_page(page, iter, vsnap->pages) {

		for_each_sgt_page(page, iter, vma_res->bi.pages) {

			void *s;



			drm_clflush_pages(&page, 1);
@@ -1324,33 +1325,32 @@ static bool record_context(struct i915_gem_context_coredump *e, 


struct intel_engine_capture_vma {

	struct intel_engine_capture_vma *next;

	struct i915_vma_snapshot *vsnap;

	struct i915_vma_resource *vma_res;

	char name[16];

	bool lockdep_cookie;

};



static struct intel_engine_capture_vma *

capture_vma_snapshot(struct intel_engine_capture_vma *next,

		     struct i915_vma_snapshot *vsnap,

		     gfp_t gfp)

		     struct i915_vma_resource *vma_res,

		     gfp_t gfp, const char *name)

{

	struct intel_engine_capture_vma *c;



	if (!i915_vma_snapshot_present(vsnap))

	if (!vma_res)

		return next;



	c = kmalloc(sizeof(*c), gfp);

	if (!c)

		return next;



	if (!i915_vma_snapshot_resource_pin(vsnap, &c->lockdep_cookie)) {

	if (!i915_vma_resource_hold(vma_res, &c->lockdep_cookie)) {

		kfree(c);

		return next;

	}



	strcpy(c->name, vsnap->name);

	c->vsnap = vsnap;

	i915_vma_snapshot_get(vsnap);

	strcpy(c->name, name);

	c->vma_res = i915_vma_resource_get(vma_res);



	c->next = next;

	return c;
@@ -1362,8 +1362,6 @@ capture_vma(struct intel_engine_capture_vma *next, 
	    const char *name,

	    gfp_t gfp)

{

	struct i915_vma_snapshot *vsnap;



	if (!vma)

		return next;
@@ -1372,19 +1370,10 @@ capture_vma(struct intel_engine_capture_vma *next, 
	 * to a struct i915_vma_snapshot at command submission time.

	 * Not here.

	 */

	GEM_WARN_ON(!i915_vma_is_pinned(vma));

	if (!i915_vma_is_pinned(vma))

		return next;



	vsnap = i915_vma_snapshot_alloc(gfp);

	if (!vsnap)

	if (GEM_WARN_ON(!i915_vma_is_pinned(vma)))

		return next;



	i915_vma_snapshot_init(vsnap, vma, name);

	next = capture_vma_snapshot(next, vsnap, gfp);



	/* FIXME: Replace on async unbind. */

	i915_vma_snapshot_put(vsnap);

	next = capture_vma_snapshot(next, vma->resource, gfp, name);



	return next;

}
@@ -1397,7 +1386,8 @@ capture_user(struct intel_engine_capture_vma *capture, 
	struct i915_capture_list *c;



	for (c = rq->capture_list; c; c = c->next)

		capture = capture_vma_snapshot(capture, c->vma_snapshot, gfp);

		capture = capture_vma_snapshot(capture, c->vma_res, gfp,

					       "user");



	return capture;

}
@@ -1415,16 +1405,19 @@ static struct i915_vma_coredump * 
create_vma_coredump(const struct intel_gt *gt, struct i915_vma *vma,

		    const char *name, struct i915_vma_compress *compress)

{

	struct i915_vma_coredump *ret;

	struct i915_vma_snapshot tmp;

	struct i915_vma_coredump *ret = NULL;

	struct i915_vma_resource *vma_res;

	bool lockdep_cookie;



	if (!vma)

		return NULL;



	GEM_WARN_ON(!i915_vma_is_pinned(vma));

	i915_vma_snapshot_init_onstack(&tmp, vma, name);

	ret = i915_vma_coredump_create(gt, &tmp, compress);

	i915_vma_snapshot_put_onstack(&tmp);

	vma_res = vma->resource;



	if (i915_vma_resource_hold(vma_res, &lockdep_cookie)) {

		ret = i915_vma_coredump_create(gt, vma_res, compress, name);

		i915_vma_resource_unhold(vma_res, lockdep_cookie);

	}



	return ret;

}
@@ -1471,7 +1464,7 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee, 
	 * as the simplest method to avoid being overwritten

	 * by userspace.

	 */

	vma = capture_vma_snapshot(vma, &rq->batch_snapshot, gfp);

	vma = capture_vma_snapshot(vma, rq->batch_res, gfp, "batch");

	vma = capture_user(vma, rq, gfp);

	vma = capture_vma(vma, rq->ring->vma, "ring", gfp);

	vma = capture_vma(vma, rq->context->state, "HW context", gfp);
@@ -1492,14 +1485,14 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee, 


	while (capture) {

		struct intel_engine_capture_vma *this = capture;

		struct i915_vma_snapshot *vsnap = this->vsnap;

		struct i915_vma_resource *vma_res = this->vma_res;



		add_vma(ee,

			i915_vma_coredump_create(engine->gt,

						 vsnap, compress));

			i915_vma_coredump_create(engine->gt, vma_res,

						 compress, this->name));



		i915_vma_snapshot_resource_unpin(vsnap, this->lockdep_cookie);

		i915_vma_snapshot_put(vsnap);

		i915_vma_resource_unhold(vma_res, this->lockdep_cookie);

		i915_vma_resource_put(vma_res);



		capture = this->next;

		kfree(this);

drivers/gpu/drm/i915/i915_request.c

+7 −5
Original line number Diff line number Diff line
@@ -115,8 +115,10 @@ static void i915_fence_release(struct dma_fence *fence) 
		   rq->guc_prio != GUC_PRIO_FINI);



	i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));

	if (i915_vma_snapshot_present(&rq->batch_snapshot))

		i915_vma_snapshot_put_onstack(&rq->batch_snapshot);

	if (rq->batch_res) {

		i915_vma_resource_put(rq->batch_res);

		rq->batch_res = NULL;

	}



	/*

	 * The request is put onto a RCU freelist (i.e. the address
@@ -307,7 +309,7 @@ void i915_request_free_capture_list(struct i915_capture_list *capture) 
	while (capture) {

		struct i915_capture_list *next = capture->next;



		i915_vma_snapshot_put(capture->vma_snapshot);

		i915_vma_resource_put(capture->vma_res);

		kfree(capture);

		capture = next;

	}
@@ -853,7 +855,7 @@ static void __i915_request_ctor(void *arg) 
	i915_sw_fence_init(&rq->semaphore, semaphore_notify);



	clear_capture_list(rq);

	rq->batch_snapshot.present = false;

	rq->batch_res = NULL;



	init_llist_head(&rq->execute_cb);

}
@@ -959,7 +961,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) 
	__rq_init_watchdog(rq);

	assert_capture_list_is_null(rq);

	GEM_BUG_ON(!llist_empty(&rq->execute_cb));

	GEM_BUG_ON(i915_vma_snapshot_present(&rq->batch_snapshot));

	GEM_BUG_ON(rq->batch_res);



	/*

	 * Reserve space in the ring buffer for all the commands required to