Commit 63cf4cad authored by Thomas Hellström's avatar Thomas Hellström
Browse files

drm/i915: Break out the i915_deps utility 



Since it's starting to be used outside the i915 TTM move code, move it
to a separate set of files.

v2:
- Update the documentation.
v4:
- Rebase.

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/20211221200050.436316-4-thomas.hellstrom@linux.intel.com
parent 33654ef4

drivers/gpu/drm/i915/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -163,6 +163,7 @@ i915-y += \ 
	  i915_active.o \

	  i915_buddy.o \

	  i915_cmd_parser.o \

	  i915_deps.o \

	  i915_gem_evict.o \

	  i915_gem_gtt.o \

	  i915_gem_ww.o \

drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c

+1 −170
Original line number Diff line number Diff line
@@ -5,6 +5,7 @@ 


#include <drm/ttm/ttm_bo_driver.h>



#include "i915_deps.h"

#include "i915_drv.h"

#include "intel_memory_region.h"

#include "intel_region_ttm.h"
@@ -41,176 +42,6 @@ void i915_ttm_migrate_set_failure_modes(bool gpu_migration, 
}

#endif



/**

 * DOC: Set of utilities to dynamically collect dependencies into a

 * structure which is fed into the GT migration code.

 *

 * Once we can do async unbinding, this is also needed to coalesce

 * the migration fence with the unbind fences if these are coalesced

 * post-migration.

 *

 * While collecting the individual dependencies, we store the refcounted

 * struct dma_fence pointers in a realloc-managed pointer array, since

 * that can be easily fed into a dma_fence_array. Other options are

 * available, like for example an xarray for similarity with drm/sched.

 * Can be changed easily if needed.

 *

 * A struct i915_deps need to be initialized using i915_deps_init().

 * If i915_deps_add_dependency() or i915_deps_add_resv() return an

 * error code they will internally call i915_deps_fini(), which frees

 * all internal references and allocations.

 *

 * We might want to break this out into a separate file as a utility.

 */



#define I915_DEPS_MIN_ALLOC_CHUNK 8U



static void i915_deps_reset_fences(struct i915_deps *deps)

{

	if (deps->fences != &deps->single)

		kfree(deps->fences);

	deps->num_deps = 0;

	deps->fences_size = 1;

	deps->fences = &deps->single;

}



static void i915_deps_init(struct i915_deps *deps, gfp_t gfp)

{

	deps->fences = NULL;

	deps->gfp = gfp;

	i915_deps_reset_fences(deps);

}



static void i915_deps_fini(struct i915_deps *deps)

{

	unsigned int i;



	for (i = 0; i < deps->num_deps; ++i)

		dma_fence_put(deps->fences[i]);



	if (deps->fences != &deps->single)

		kfree(deps->fences);

}



static int i915_deps_grow(struct i915_deps *deps, struct dma_fence *fence,

			  const struct ttm_operation_ctx *ctx)

{

	int ret;



	if (deps->num_deps >= deps->fences_size) {

		unsigned int new_size = 2 * deps->fences_size;

		struct dma_fence **new_fences;



		new_size = max(new_size, I915_DEPS_MIN_ALLOC_CHUNK);

		new_fences = kmalloc_array(new_size, sizeof(*new_fences), deps->gfp);

		if (!new_fences)

			goto sync;



		memcpy(new_fences, deps->fences,

		       deps->fences_size * sizeof(*new_fences));

		swap(new_fences, deps->fences);

		if (new_fences != &deps->single)

			kfree(new_fences);

		deps->fences_size = new_size;

	}

	deps->fences[deps->num_deps++] = dma_fence_get(fence);

	return 0;



sync:

	if (ctx->no_wait_gpu && !dma_fence_is_signaled(fence)) {

		ret = -EBUSY;

		goto unref;

	}



	ret = dma_fence_wait(fence, ctx->interruptible);

	if (ret)

		goto unref;



	ret = fence->error;

	if (ret)

		goto unref;



	return 0;



unref:

	i915_deps_fini(deps);

	return ret;

}



static int i915_deps_sync(const struct i915_deps *deps,

			  const struct ttm_operation_ctx *ctx)

{

	struct dma_fence **fences = deps->fences;

	unsigned int i;

	int ret = 0;



	for (i = 0; i < deps->num_deps; ++i, ++fences) {

		if (ctx->no_wait_gpu && !dma_fence_is_signaled(*fences)) {

			ret = -EBUSY;

			break;

		}



		ret = dma_fence_wait(*fences, ctx->interruptible);

		if (!ret)

			ret = (*fences)->error;

		if (ret)

			break;

	}



	return ret;

}



static int i915_deps_add_dependency(struct i915_deps *deps,

				    struct dma_fence *fence,

				    const struct ttm_operation_ctx *ctx)

{

	unsigned int i;

	int ret;



	if (!fence)

		return 0;



	if (dma_fence_is_signaled(fence)) {

		ret = fence->error;

		if (ret)

			i915_deps_fini(deps);

		return ret;

	}



	for (i = 0; i < deps->num_deps; ++i) {

		struct dma_fence *entry = deps->fences[i];



		if (!entry->context || entry->context != fence->context)

			continue;



		if (dma_fence_is_later(fence, entry)) {

			dma_fence_put(entry);

			deps->fences[i] = dma_fence_get(fence);

		}



		return 0;

	}



	return i915_deps_grow(deps, fence, ctx);

}



static int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv,

			      const struct ttm_operation_ctx *ctx)

{

	struct dma_resv_iter iter;

	struct dma_fence *fence;

	int ret;



	dma_resv_assert_held(resv);

	dma_resv_for_each_fence(&iter, resv, true, fence) {

		ret = i915_deps_add_dependency(deps, fence, ctx);

		if (ret)

			return ret;

	}



	return 0;

}



static enum i915_cache_level

i915_ttm_cache_level(struct drm_i915_private *i915, struct ttm_resource *res,

		     struct ttm_tt *ttm)

drivers/gpu/drm/i915/gem/i915_gem_ttm_move.h

+0 −17
Original line number Diff line number Diff line
@@ -18,23 +18,6 @@ struct ttm_tt; 
struct drm_i915_gem_object;

struct i915_refct_sgt;



/**

 * struct i915_deps - Collect dependencies into a single dma-fence

 * @single: Storage for pointer if the collection is a single fence.

 * @fences: Allocated array of fence pointers if more than a single fence;

 * otherwise points to the address of @single.

 * @num_deps: Current number of dependency fences.

 * @fences_size: Size of the @fences array in number of pointers.

 * @gfp: Allocation mode.

 */

struct i915_deps {

	struct dma_fence *single;

	struct dma_fence **fences;

	unsigned int num_deps;

	unsigned int fences_size;

	gfp_t gfp;

};



int i915_ttm_move_notify(struct ttm_buffer_object *bo);



I915_SELFTEST_DECLARE(void i915_ttm_migrate_set_failure_modes(bool gpu_migration,

drivers/gpu/drm/i915/i915_deps.c

0 → 100644
+237 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: MIT

/*

 * Copyright © 2021 Intel Corporation

 */



#include <linux/dma-fence.h>

#include <linux/slab.h>



#include <drm/ttm/ttm_bo_api.h>



#include "i915_deps.h"



/**

 * DOC: Set of utilities to dynamically collect dependencies into a

 * structure which is fed into the GT migration code.

 *

 * Once we can do async unbinding, this is also needed to coalesce

 * the migration fence with the unbind fences if these are coalesced

 * post-migration.

 *

 * While collecting the individual dependencies, we store the refcounted

 * struct dma_fence pointers in a realloc-managed pointer array, since

 * that can be easily fed into a dma_fence_array. Other options are

 * available, like for example an xarray for similarity with drm/sched.

 * Can be changed easily if needed.

 *

 * A struct i915_deps need to be initialized using i915_deps_init().

 * If i915_deps_add_dependency() or i915_deps_add_resv() return an

 * error code they will internally call i915_deps_fini(), which frees

 * all internal references and allocations.

 */



/* Min number of fence pointers in the array when an allocation occurs. */

#define I915_DEPS_MIN_ALLOC_CHUNK 8U



static void i915_deps_reset_fences(struct i915_deps *deps)

{

	if (deps->fences != &deps->single)

		kfree(deps->fences);

	deps->num_deps = 0;

	deps->fences_size = 1;

	deps->fences = &deps->single;

}



/**

 * i915_deps_init - Initialize an i915_deps structure

 * @deps: Pointer to the i915_deps structure to initialize.

 * @gfp: The allocation mode for subsequenst allocations.

 */

void i915_deps_init(struct i915_deps *deps, gfp_t gfp)

{

	deps->fences = NULL;

	deps->gfp = gfp;

	i915_deps_reset_fences(deps);

}



/**

 * i915_deps_fini - Finalize an i915_deps structure

 * @deps: Pointer to the i915_deps structure to finalize.

 *

 * This function drops all fence references taken, conditionally frees and

 * then resets the fences array.

 */

void i915_deps_fini(struct i915_deps *deps)

{

	unsigned int i;



	for (i = 0; i < deps->num_deps; ++i)

		dma_fence_put(deps->fences[i]);



	if (deps->fences != &deps->single)

		kfree(deps->fences);

}



static int i915_deps_grow(struct i915_deps *deps, struct dma_fence *fence,

			  const struct ttm_operation_ctx *ctx)

{

	int ret;



	if (deps->num_deps >= deps->fences_size) {

		unsigned int new_size = 2 * deps->fences_size;

		struct dma_fence **new_fences;



		new_size = max(new_size, I915_DEPS_MIN_ALLOC_CHUNK);

		new_fences = kmalloc_array(new_size, sizeof(*new_fences), deps->gfp);

		if (!new_fences)

			goto sync;



		memcpy(new_fences, deps->fences,

		       deps->fences_size * sizeof(*new_fences));

		swap(new_fences, deps->fences);

		if (new_fences != &deps->single)

			kfree(new_fences);

		deps->fences_size = new_size;

	}

	deps->fences[deps->num_deps++] = dma_fence_get(fence);

	return 0;



sync:

	if (ctx->no_wait_gpu && !dma_fence_is_signaled(fence)) {

		ret = -EBUSY;

		goto unref;

	}



	ret = dma_fence_wait(fence, ctx->interruptible);

	if (ret)

		goto unref;



	ret = fence->error;

	if (ret)

		goto unref;



	return 0;



unref:

	i915_deps_fini(deps);

	return ret;

}



/**

 * i915_deps_sync - Wait for all the fences in the dependency collection

 * @deps: Pointer to the i915_deps structure the fences of which to wait for.

 * @ctx: Pointer to a struct ttm_operation_ctx indicating how the waits

 * should be performed.

 *

 * This function waits for fences in the dependency collection. If it

 * encounters an error during the wait or a fence error, the wait for

 * further fences is aborted and the error returned.

 *

 * Return: Zero if successful, Negative error code on error.

 */

int i915_deps_sync(const struct i915_deps *deps, const struct ttm_operation_ctx *ctx)

{

	struct dma_fence **fences = deps->fences;

	unsigned int i;

	int ret = 0;



	for (i = 0; i < deps->num_deps; ++i, ++fences) {

		if (ctx->no_wait_gpu && !dma_fence_is_signaled(*fences)) {

			ret = -EBUSY;

			break;

		}



		ret = dma_fence_wait(*fences, ctx->interruptible);

		if (!ret)

			ret = (*fences)->error;

		if (ret)

			break;

	}



	return ret;

}



/**

 * i915_deps_add_dependency - Add a fence to the dependency collection

 * @deps: Pointer to the i915_deps structure a fence is to be added to.

 * @fence: The fence to add.

 * @ctx: Pointer to a struct ttm_operation_ctx indicating how waits are to

 * be performed if waiting.

 *

 * Adds a fence to the dependency collection, and takes a reference on it.

 * If the fence context is not zero and there was a later fence from the

 * same fence context already added, then the fence is not added to the

 * dependency collection. If the fence context is not zero and there was

 * an earlier fence already added, then the fence will replace the older

 * fence from the same context and the reference on the earlier fence will

 * be dropped.

 * If there is a failure to allocate memory to accommodate the new fence to

 * be added, the new fence will instead be waited for and an error may

 * be returned; depending on the value of @ctx, or if there was a fence

 * error. If an error was returned, the dependency collection will be

 * finalized and all fence reference dropped.

 *

 * Return: 0 if success. Negative error code on error.

 */

int i915_deps_add_dependency(struct i915_deps *deps,

			     struct dma_fence *fence,

			     const struct ttm_operation_ctx *ctx)

{

	unsigned int i;

	int ret;



	if (!fence)

		return 0;



	if (dma_fence_is_signaled(fence)) {

		ret = fence->error;

		if (ret)

			i915_deps_fini(deps);

		return ret;

	}



	for (i = 0; i < deps->num_deps; ++i) {

		struct dma_fence *entry = deps->fences[i];



		if (!entry->context || entry->context != fence->context)

			continue;



		if (dma_fence_is_later(fence, entry)) {

			dma_fence_put(entry);

			deps->fences[i] = dma_fence_get(fence);

		}



		return 0;

	}



	return i915_deps_grow(deps, fence, ctx);

}



/**

 * i915_deps_add_resv - Add the fences of a reservation object to a dependency

 * collection.

 * @deps: Pointer to the i915_deps structure a fence is to be added to.

 * @resv: The reservation object, then fences of which to add.

 * @ctx: Pointer to a struct ttm_operation_ctx indicating how waits are to

 * be performed if waiting.

 *

 * Calls i915_deps_add_depencency() on the indicated fences of @resv.

 *

 * Return: Zero on success. Negative error code on error.

 */

int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv,

		       const struct ttm_operation_ctx *ctx)

{

	struct dma_resv_iter iter;

	struct dma_fence *fence;



	dma_resv_assert_held(resv);

	dma_resv_for_each_fence(&iter, resv, true, fence) {

		int ret = i915_deps_add_dependency(deps, fence, ctx);



		if (ret)

			return ret;

	}



	return 0;

}

drivers/gpu/drm/i915/i915_deps.h

0 → 100644
+45 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: MIT */

/*

 * Copyright © 2021 Intel Corporation

 */



#ifndef _I915_DEPS_H_

#define _I915_DEPS_H_



#include <linux/types.h>



struct ttm_operation_ctx;

struct dma_fence;

struct dma_resv;



/**

 * struct i915_deps - Collect dependencies into a single dma-fence

 * @single: Storage for pointer if the collection is a single fence.

 * @fences: Allocated array of fence pointers if more than a single fence;

 * otherwise points to the address of @single.

 * @num_deps: Current number of dependency fences.

 * @fences_size: Size of the @fences array in number of pointers.

 * @gfp: Allocation mode.

 */

struct i915_deps {

	struct dma_fence *single;

	struct dma_fence **fences;

	unsigned int num_deps;

	unsigned int fences_size;

	gfp_t gfp;

};



void i915_deps_init(struct i915_deps *deps, gfp_t gfp);



void i915_deps_fini(struct i915_deps *deps);



int i915_deps_add_dependency(struct i915_deps *deps,

			     struct dma_fence *fence,

			     const struct ttm_operation_ctx *ctx);



int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv,

		       const struct ttm_operation_ctx *ctx);



int i915_deps_sync(const struct i915_deps *deps,

		   const struct ttm_operation_ctx *ctx);

#endif