@@ -26,6 +26,7 @@ config DRM_I915
select SND_HDA_I915 if SND_HDA_CORE
select CEC_CORE if CEC_NOTIFIER
select VMAP_PFN
+ select DRM_TTM
help
Choose this option if you have a system that has "Intel Graphics
Media Accelerator" or "HD Graphics" integrated graphics,
@@ -50,6 +50,7 @@ i915-y += i915_drv.o \
intel_memory_region.o \
intel_pch.o \
intel_pm.o \
+ intel_region_ttm.o \
intel_runtime_pm.o \
intel_sideband.o \
intel_step.o \
@@ -160,7 +161,6 @@ gem-y += \
i915-y += \
$(gem-y) \
i915_active.o \
- i915_buddy.o \
i915_cmd_parser.o \
i915_gem_evict.o \
i915_gem_gtt.o \
@@ -4,16 +4,70 @@
*/
#include "intel_memory_region.h"
+#include "intel_region_ttm.h"
#include "gem/i915_gem_region.h"
#include "gem/i915_gem_lmem.h"
#include "i915_drv.h"
+static void lmem_put_pages(struct drm_i915_gem_object *obj,
+ struct sg_table *pages)
+{
+ intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+ obj->mm.dirty = false;
+ sg_free_table(pages);
+ kfree(pages);
+}
+
+static int lmem_get_pages(struct drm_i915_gem_object *obj)
+{
+ unsigned int flags;
+ struct sg_table *pages;
+
+ flags = I915_ALLOC_MIN_PAGE_SIZE;
+ if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
+ flags |= I915_ALLOC_CONTIGUOUS;
+
+ obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
+ obj->base.size,
+ flags);
+ if (IS_ERR(obj->mm.st_mm_node))
+ return PTR_ERR(obj->mm.st_mm_node);
+
+ /* Range manager is always contigous */
+ if (obj->mm.region->is_range_manager)
+ obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
+ pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+
+ __i915_gem_object_set_pages(obj, pages,
+ i915_sg_dma_page_sizes(pages->sgl));
+
+ if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
+ void __iomem *vaddr =
+ i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
+
+ if (!vaddr) {
+ struct sg_table *pages =
+ __i915_gem_object_unset_pages(obj);
+
+ if (!IS_ERR_OR_NULL(pages))
+ lmem_put_pages(obj, pages);
+ }
+
+ memset_io(vaddr, 0, obj->base.size);
+ io_mapping_unmap(vaddr);
+ }
+
+ return 0;
+}
+
const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
.name = "i915_gem_object_lmem",
.flags = I915_GEM_OBJECT_HAS_IOMEM,
- .get_pages = i915_gem_object_get_pages_buddy,
- .put_pages = i915_gem_object_put_pages_buddy,
+ .get_pages = lmem_get_pages,
+ .put_pages = lmem_put_pages,
.release = i915_gem_object_release_memory_region,
};
@@ -232,10 +232,12 @@ struct drm_i915_gem_object {
* Memory region for this object.
*/
struct intel_memory_region *region;
+
/**
- * List of memory region blocks allocated for this object.
+ * Memory manager node allocated for this object.
*/
- struct list_head blocks;
+ void *st_mm_node;
+
/**
* Element within memory_region->objects or region->purgeable
* if the object is marked as DONTNEED. Access is protected by
@@ -473,7 +473,8 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
might_sleep();
GEM_BUG_ON(n >= obj->base.size >> PAGE_SHIFT);
- GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+ if (!i915_gem_object_has_pinned_pages(obj))
+ assert_object_held(obj);
/* As we iterate forward through the sg, we record each entry in a
* radixtree for quick repeated (backwards) lookups. If we have seen
@@ -8,129 +8,9 @@
#include "i915_drv.h"
#include "i915_trace.h"
-void
-i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
- struct sg_table *pages)
-{
- __intel_memory_region_put_pages_buddy(obj->mm.region, &obj->mm.blocks);
-
- obj->mm.dirty = false;
- sg_free_table(pages);
- kfree(pages);
-}
-
-int
-i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
-{
- const u64 max_segment = i915_sg_segment_size();
- struct intel_memory_region *mem = obj->mm.region;
- struct list_head *blocks = &obj->mm.blocks;
- resource_size_t size = obj->base.size;
- resource_size_t prev_end;
- struct i915_buddy_block *block;
- unsigned int flags;
- struct sg_table *st;
- struct scatterlist *sg;
- unsigned int sg_page_sizes;
- int ret;
-
- st = kmalloc(sizeof(*st), GFP_KERNEL);
- if (!st)
- return -ENOMEM;
-
- if (sg_alloc_table(st, size >> PAGE_SHIFT, GFP_KERNEL)) {
- kfree(st);
- return -ENOMEM;
- }
-
- flags = I915_ALLOC_MIN_PAGE_SIZE;
- if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
- flags |= I915_ALLOC_CONTIGUOUS;
-
- ret = __intel_memory_region_get_pages_buddy(mem, size, flags, blocks);
- if (ret)
- goto err_free_sg;
-
- GEM_BUG_ON(list_empty(blocks));
-
- sg = st->sgl;
- st->nents = 0;
- sg_page_sizes = 0;
- prev_end = (resource_size_t)-1;
-
- list_for_each_entry(block, blocks, link) {
- u64 block_size, offset;
-
- block_size = min_t(u64, size,
- i915_buddy_block_size(&mem->mm, block));
- offset = i915_buddy_block_offset(block);
-
- while (block_size) {
- u64 len;
-
- if (offset != prev_end || sg->length >= max_segment) {
- if (st->nents) {
- sg_page_sizes |= sg->length;
- sg = __sg_next(sg);
- }
-
- sg_dma_address(sg) = mem->region.start + offset;
- sg_dma_len(sg) = 0;
- sg->length = 0;
- st->nents++;
- }
-
- len = min(block_size, max_segment - sg->length);
- sg->length += len;
- sg_dma_len(sg) += len;
-
- offset += len;
- block_size -= len;
-
- prev_end = offset;
- }
- }
-
- sg_page_sizes |= sg->length;
- sg_mark_end(sg);
- i915_sg_trim(st);
-
- /* Intended for kernel internal use only */
- if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
- struct scatterlist *sg;
- unsigned long i;
-
- for_each_sg(st->sgl, sg, st->nents, i) {
- unsigned int length;
- void __iomem *vaddr;
- dma_addr_t daddr;
-
- daddr = sg_dma_address(sg);
- daddr -= mem->region.start;
- length = sg_dma_len(sg);
-
- vaddr = io_mapping_map_wc(&mem->iomap, daddr, length);
- memset64((void __force *)vaddr, 0, length / sizeof(u64));
- io_mapping_unmap(vaddr);
- }
-
- wmb();
- }
-
- __i915_gem_object_set_pages(obj, st, sg_page_sizes);
-
- return 0;
-
-err_free_sg:
- sg_free_table(st);
- kfree(st);
- return ret;
-}
-
void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
struct intel_memory_region *mem)
{
- INIT_LIST_HEAD(&obj->mm.blocks);
obj->mm.region = intel_memory_region_get(mem);
if (obj->base.size <= mem->min_page_size)
@@ -12,10 +12,6 @@ struct intel_memory_region;
struct drm_i915_gem_object;
struct sg_table;
-int i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj);
-void i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
- struct sg_table *pages);
-
void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
struct intel_memory_region *mem);
void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj);
@@ -628,11 +628,13 @@ static const struct intel_memory_region_ops shmem_region_ops = {
.init_object = shmem_object_init,
};
-struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915)
+struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915,
+ u16 type, u16 instance)
{
return intel_memory_region_create(i915, 0,
totalram_pages() << PAGE_SHIFT,
PAGE_SIZE, 0,
+ type, instance,
&shmem_region_ops);
}
@@ -770,7 +770,8 @@ static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = {
};
struct intel_memory_region *
-i915_gem_stolen_lmem_setup(struct drm_i915_private *i915)
+i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
+ u16 instance)
{
struct intel_uncore *uncore = &i915->uncore;
struct pci_dev *pdev = to_pci_dev(i915->drm.dev);
@@ -788,6 +789,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915)
mem = intel_memory_region_create(i915, lmem_base, lmem_size,
I915_GTT_PAGE_SIZE_4K, io_start,
+ type, instance,
&i915_region_stolen_lmem_ops);
if (IS_ERR(mem))
return mem;
@@ -809,14 +811,15 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915)
}
struct intel_memory_region*
-i915_gem_stolen_smem_setup(struct drm_i915_private *i915)
+i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type,
+ u16 instance)
{
struct intel_memory_region *mem;
mem = intel_memory_region_create(i915,
intel_graphics_stolen_res.start,
resource_size(&intel_graphics_stolen_res),
- PAGE_SIZE, 0,
+ PAGE_SIZE, 0, type, instance,
&i915_region_stolen_smem_ops);
if (IS_ERR(mem))
return mem;
@@ -824,7 +827,6 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915)
intel_memory_region_set_name(mem, "stolen-system");
mem->private = true;
-
return mem;
}
@@ -21,8 +21,13 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
u64 end);
void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
struct drm_mm_node *node);
-struct intel_memory_region *i915_gem_stolen_smem_setup(struct drm_i915_private *i915);
-struct intel_memory_region *i915_gem_stolen_lmem_setup(struct drm_i915_private *i915);
+struct intel_memory_region *
+i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type,
+ u16 instance);
+struct intel_memory_region *
+i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
+ u16 instance);
+
struct drm_i915_gem_object *
i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
resource_size_t size);
@@ -68,8 +68,6 @@ int intel_gt_probe_lmem(struct intel_gt *gt)
id = INTEL_REGION_LMEM;
mem->id = id;
- mem->type = INTEL_MEMORY_LOCAL;
- mem->instance = 0;
intel_memory_region_set_name(mem, "local%u", mem->instance);
@@ -5,6 +5,8 @@
#include "i915_drv.h"
#include "intel_memory_region.h"
+#include "intel_region_lmem.h"
+#include "intel_region_ttm.h"
#include "gem/i915_gem_lmem.h"
#include "gem/i915_gem_region.h"
#include "intel_region_lmem.h"
@@ -66,9 +68,9 @@ static void release_fake_lmem_bar(struct intel_memory_region *mem)
static void
region_lmem_release(struct intel_memory_region *mem)
{
- release_fake_lmem_bar(mem);
+ intel_region_ttm_fini(mem);
io_mapping_fini(&mem->iomap);
- intel_memory_region_release_buddy(mem);
+ release_fake_lmem_bar(mem);
}
static int
@@ -83,12 +85,21 @@ region_lmem_init(struct intel_memory_region *mem)
if (!io_mapping_init_wc(&mem->iomap,
mem->io_start,
- resource_size(&mem->region)))
- return -EIO;
+ resource_size(&mem->region))) {
+ ret = -EIO;
+ goto out_no_io;
+ }
- ret = intel_memory_region_init_buddy(mem);
+ ret = intel_region_ttm_init(mem);
if (ret)
- io_mapping_fini(&mem->iomap);
+ goto out_no_buddy;
+
+ return 0;
+
+out_no_buddy:
+ io_mapping_fini(&mem->iomap);
+out_no_io:
+ release_fake_lmem_bar(mem);
return ret;
}
@@ -127,6 +138,8 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt)
mappable_end,
PAGE_SIZE,
io_start,
+ INTEL_MEMORY_LOCAL,
+ 0,
&intel_region_lmem_ops);
if (!IS_ERR(mem)) {
drm_info(&i915->drm, "Intel graphics fake LMEM: %pR\n",
@@ -198,6 +211,8 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt)
lmem_size,
I915_GTT_PAGE_SIZE_4K,
io_start,
+ INTEL_MEMORY_LOCAL,
+ 0,
&intel_region_lmem_ops);
if (IS_ERR(mem))
return mem;
deleted file mode 100644
@@ -1,435 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include <linux/kmemleak.h>
-#include <linux/slab.h>
-
-#include "i915_buddy.h"
-
-#include "i915_gem.h"
-#include "i915_globals.h"
-#include "i915_utils.h"
-
-static struct i915_global_block {
- struct i915_global base;
- struct kmem_cache *slab_blocks;
-} global;
-
-static void i915_global_buddy_shrink(void)
-{
- kmem_cache_shrink(global.slab_blocks);
-}
-
-static void i915_global_buddy_exit(void)
-{
- kmem_cache_destroy(global.slab_blocks);
-}
-
-static struct i915_global_block global = { {
- .shrink = i915_global_buddy_shrink,
- .exit = i915_global_buddy_exit,
-} };
-
-int __init i915_global_buddy_init(void)
-{
- global.slab_blocks = KMEM_CACHE(i915_buddy_block, SLAB_HWCACHE_ALIGN);
- if (!global.slab_blocks)
- return -ENOMEM;
-
- i915_global_register(&global.base);
- return 0;
-}
-
-static struct i915_buddy_block *i915_block_alloc(struct i915_buddy_block *parent,
- unsigned int order,
- u64 offset)
-{
- struct i915_buddy_block *block;
-
- GEM_BUG_ON(order > I915_BUDDY_MAX_ORDER);
-
- block = kmem_cache_zalloc(global.slab_blocks, GFP_KERNEL);
- if (!block)
- return NULL;
-
- block->header = offset;
- block->header |= order;
- block->parent = parent;
-
- GEM_BUG_ON(block->header & I915_BUDDY_HEADER_UNUSED);
- return block;
-}
-
-static void i915_block_free(struct i915_buddy_block *block)
-{
- kmem_cache_free(global.slab_blocks, block);
-}
-
-static void mark_allocated(struct i915_buddy_block *block)
-{
- block->header &= ~I915_BUDDY_HEADER_STATE;
- block->header |= I915_BUDDY_ALLOCATED;
-
- list_del(&block->link);
-}
-
-static void mark_free(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- block->header &= ~I915_BUDDY_HEADER_STATE;
- block->header |= I915_BUDDY_FREE;
-
- list_add(&block->link,
- &mm->free_list[i915_buddy_block_order(block)]);
-}
-
-static void mark_split(struct i915_buddy_block *block)
-{
- block->header &= ~I915_BUDDY_HEADER_STATE;
- block->header |= I915_BUDDY_SPLIT;
-
- list_del(&block->link);
-}
-
-int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size)
-{
- unsigned int i;
- u64 offset;
-
- if (size < chunk_size)
- return -EINVAL;
-
- if (chunk_size < PAGE_SIZE)
- return -EINVAL;
-
- if (!is_power_of_2(chunk_size))
- return -EINVAL;
-
- size = round_down(size, chunk_size);
-
- mm->size = size;
- mm->chunk_size = chunk_size;
- mm->max_order = ilog2(size) - ilog2(chunk_size);
-
- GEM_BUG_ON(mm->max_order > I915_BUDDY_MAX_ORDER);
-
- mm->free_list = kmalloc_array(mm->max_order + 1,
- sizeof(struct list_head),
- GFP_KERNEL);
- if (!mm->free_list)
- return -ENOMEM;
-
- for (i = 0; i <= mm->max_order; ++i)
- INIT_LIST_HEAD(&mm->free_list[i]);
-
- mm->n_roots = hweight64(size);
-
- mm->roots = kmalloc_array(mm->n_roots,
- sizeof(struct i915_buddy_block *),
- GFP_KERNEL);
- if (!mm->roots)
- goto out_free_list;
-
- offset = 0;
- i = 0;
-
- /*
- * Split into power-of-two blocks, in case we are given a size that is
- * not itself a power-of-two.
- */
- do {
- struct i915_buddy_block *root;
- unsigned int order;
- u64 root_size;
-
- root_size = rounddown_pow_of_two(size);
- order = ilog2(root_size) - ilog2(chunk_size);
-
- root = i915_block_alloc(NULL, order, offset);
- if (!root)
- goto out_free_roots;
-
- mark_free(mm, root);
-
- GEM_BUG_ON(i > mm->max_order);
- GEM_BUG_ON(i915_buddy_block_size(mm, root) < chunk_size);
-
- mm->roots[i] = root;
-
- offset += root_size;
- size -= root_size;
- i++;
- } while (size);
-
- return 0;
-
-out_free_roots:
- while (i--)
- i915_block_free(mm->roots[i]);
- kfree(mm->roots);
-out_free_list:
- kfree(mm->free_list);
- return -ENOMEM;
-}
-
-void i915_buddy_fini(struct i915_buddy_mm *mm)
-{
- int i;
-
- for (i = 0; i < mm->n_roots; ++i) {
- GEM_WARN_ON(!i915_buddy_block_is_free(mm->roots[i]));
- i915_block_free(mm->roots[i]);
- }
-
- kfree(mm->roots);
- kfree(mm->free_list);
-}
-
-static int split_block(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- unsigned int block_order = i915_buddy_block_order(block) - 1;
- u64 offset = i915_buddy_block_offset(block);
-
- GEM_BUG_ON(!i915_buddy_block_is_free(block));
- GEM_BUG_ON(!i915_buddy_block_order(block));
-
- block->left = i915_block_alloc(block, block_order, offset);
- if (!block->left)
- return -ENOMEM;
-
- block->right = i915_block_alloc(block, block_order,
- offset + (mm->chunk_size << block_order));
- if (!block->right) {
- i915_block_free(block->left);
- return -ENOMEM;
- }
-
- mark_free(mm, block->left);
- mark_free(mm, block->right);
-
- mark_split(block);
-
- return 0;
-}
-
-static struct i915_buddy_block *
-get_buddy(struct i915_buddy_block *block)
-{
- struct i915_buddy_block *parent;
-
- parent = block->parent;
- if (!parent)
- return NULL;
-
- if (parent->left == block)
- return parent->right;
-
- return parent->left;
-}
-
-static void __i915_buddy_free(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- struct i915_buddy_block *parent;
-
- while ((parent = block->parent)) {
- struct i915_buddy_block *buddy;
-
- buddy = get_buddy(block);
-
- if (!i915_buddy_block_is_free(buddy))
- break;
-
- list_del(&buddy->link);
-
- i915_block_free(block);
- i915_block_free(buddy);
-
- block = parent;
- }
-
- mark_free(mm, block);
-}
-
-void i915_buddy_free(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- GEM_BUG_ON(!i915_buddy_block_is_allocated(block));
- __i915_buddy_free(mm, block);
-}
-
-void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects)
-{
- struct i915_buddy_block *block, *on;
-
- list_for_each_entry_safe(block, on, objects, link) {
- i915_buddy_free(mm, block);
- cond_resched();
- }
- INIT_LIST_HEAD(objects);
-}
-
-/*
- * Allocate power-of-two block. The order value here translates to:
- *
- * 0 = 2^0 * mm->chunk_size
- * 1 = 2^1 * mm->chunk_size
- * 2 = 2^2 * mm->chunk_size
- * ...
- */
-struct i915_buddy_block *
-i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order)
-{
- struct i915_buddy_block *block = NULL;
- unsigned int i;
- int err;
-
- for (i = order; i <= mm->max_order; ++i) {
- block = list_first_entry_or_null(&mm->free_list[i],
- struct i915_buddy_block,
- link);
- if (block)
- break;
- }
-
- if (!block)
- return ERR_PTR(-ENOSPC);
-
- GEM_BUG_ON(!i915_buddy_block_is_free(block));
-
- while (i != order) {
- err = split_block(mm, block);
- if (unlikely(err))
- goto out_free;
-
- /* Go low */
- block = block->left;
- i--;
- }
-
- mark_allocated(block);
- kmemleak_update_trace(block);
- return block;
-
-out_free:
- if (i != order)
- __i915_buddy_free(mm, block);
- return ERR_PTR(err);
-}
-
-static inline bool overlaps(u64 s1, u64 e1, u64 s2, u64 e2)
-{
- return s1 <= e2 && e1 >= s2;
-}
-
-static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
-{
- return s1 <= s2 && e1 >= e2;
-}
-
-/*
- * Allocate range. Note that it's safe to chain together multiple alloc_ranges
- * with the same blocks list.
- *
- * Intended for pre-allocating portions of the address space, for example to
- * reserve a block for the initial framebuffer or similar, hence the expectation
- * here is that i915_buddy_alloc() is still the main vehicle for
- * allocations, so if that's not the case then the drm_mm range allocator is
- * probably a much better fit, and so you should probably go use that instead.
- */
-int i915_buddy_alloc_range(struct i915_buddy_mm *mm,
- struct list_head *blocks,
- u64 start, u64 size)
-{
- struct i915_buddy_block *block;
- struct i915_buddy_block *buddy;
- LIST_HEAD(allocated);
- LIST_HEAD(dfs);
- u64 end;
- int err;
- int i;
-
- if (size < mm->chunk_size)
- return -EINVAL;
-
- if (!IS_ALIGNED(size | start, mm->chunk_size))
- return -EINVAL;
-
- if (range_overflows(start, size, mm->size))
- return -EINVAL;
-
- for (i = 0; i < mm->n_roots; ++i)
- list_add_tail(&mm->roots[i]->tmp_link, &dfs);
-
- end = start + size - 1;
-
- do {
- u64 block_start;
- u64 block_end;
-
- block = list_first_entry_or_null(&dfs,
- struct i915_buddy_block,
- tmp_link);
- if (!block)
- break;
-
- list_del(&block->tmp_link);
-
- block_start = i915_buddy_block_offset(block);
- block_end = block_start + i915_buddy_block_size(mm, block) - 1;
-
- if (!overlaps(start, end, block_start, block_end))
- continue;
-
- if (i915_buddy_block_is_allocated(block)) {
- err = -ENOSPC;
- goto err_free;
- }
-
- if (contains(start, end, block_start, block_end)) {
- if (!i915_buddy_block_is_free(block)) {
- err = -ENOSPC;
- goto err_free;
- }
-
- mark_allocated(block);
- list_add_tail(&block->link, &allocated);
- continue;
- }
-
- if (!i915_buddy_block_is_split(block)) {
- err = split_block(mm, block);
- if (unlikely(err))
- goto err_undo;
- }
-
- list_add(&block->right->tmp_link, &dfs);
- list_add(&block->left->tmp_link, &dfs);
- } while (1);
-
- list_splice_tail(&allocated, blocks);
- return 0;
-
-err_undo:
- /*
- * We really don't want to leave around a bunch of split blocks, since
- * bigger is better, so make sure we merge everything back before we
- * free the allocated blocks.
- */
- buddy = get_buddy(block);
- if (buddy &&
- (i915_buddy_block_is_free(block) &&
- i915_buddy_block_is_free(buddy)))
- __i915_buddy_free(mm, block);
-
-err_free:
- i915_buddy_free_list(mm, &allocated);
- return err;
-}
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/i915_buddy.c"
-#endif
deleted file mode 100644
@@ -1,131 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#ifndef __I915_BUDDY_H__
-#define __I915_BUDDY_H__
-
-#include <linux/bitops.h>
-#include <linux/list.h>
-
-struct i915_buddy_block {
-#define I915_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
-#define I915_BUDDY_HEADER_STATE GENMASK_ULL(11, 10)
-#define I915_BUDDY_ALLOCATED (1 << 10)
-#define I915_BUDDY_FREE (2 << 10)
-#define I915_BUDDY_SPLIT (3 << 10)
-/* Free to be used, if needed in the future */
-#define I915_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6)
-#define I915_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0)
- u64 header;
-
- struct i915_buddy_block *left;
- struct i915_buddy_block *right;
- struct i915_buddy_block *parent;
-
- void *private; /* owned by creator */
-
- /*
- * While the block is allocated by the user through i915_buddy_alloc*,
- * the user has ownership of the link, for example to maintain within
- * a list, if so desired. As soon as the block is freed with
- * i915_buddy_free* ownership is given back to the mm.
- */
- struct list_head link;
- struct list_head tmp_link;
-};
-
-/* Order-zero must be at least PAGE_SIZE */
-#define I915_BUDDY_MAX_ORDER (63 - PAGE_SHIFT)
-
-/*
- * Binary Buddy System.
- *
- * Locking should be handled by the user, a simple mutex around
- * i915_buddy_alloc* and i915_buddy_free* should suffice.
- */
-struct i915_buddy_mm {
- /* Maintain a free list for each order. */
- struct list_head *free_list;
-
- /*
- * Maintain explicit binary tree(s) to track the allocation of the
- * address space. This gives us a simple way of finding a buddy block
- * and performing the potentially recursive merge step when freeing a
- * block. Nodes are either allocated or free, in which case they will
- * also exist on the respective free list.
- */
- struct i915_buddy_block **roots;
-
- /*
- * Anything from here is public, and remains static for the lifetime of
- * the mm. Everything above is considered do-not-touch.
- */
- unsigned int n_roots;
- unsigned int max_order;
-
- /* Must be at least PAGE_SIZE */
- u64 chunk_size;
- u64 size;
-};
-
-static inline u64
-i915_buddy_block_offset(struct i915_buddy_block *block)
-{
- return block->header & I915_BUDDY_HEADER_OFFSET;
-}
-
-static inline unsigned int
-i915_buddy_block_order(struct i915_buddy_block *block)
-{
- return block->header & I915_BUDDY_HEADER_ORDER;
-}
-
-static inline unsigned int
-i915_buddy_block_state(struct i915_buddy_block *block)
-{
- return block->header & I915_BUDDY_HEADER_STATE;
-}
-
-static inline bool
-i915_buddy_block_is_allocated(struct i915_buddy_block *block)
-{
- return i915_buddy_block_state(block) == I915_BUDDY_ALLOCATED;
-}
-
-static inline bool
-i915_buddy_block_is_free(struct i915_buddy_block *block)
-{
- return i915_buddy_block_state(block) == I915_BUDDY_FREE;
-}
-
-static inline bool
-i915_buddy_block_is_split(struct i915_buddy_block *block)
-{
- return i915_buddy_block_state(block) == I915_BUDDY_SPLIT;
-}
-
-static inline u64
-i915_buddy_block_size(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- return mm->chunk_size << i915_buddy_block_order(block);
-}
-
-int i915_buddy_init(struct i915_buddy_mm *mm, u64 size, u64 chunk_size);
-
-void i915_buddy_fini(struct i915_buddy_mm *mm);
-
-struct i915_buddy_block *
-i915_buddy_alloc(struct i915_buddy_mm *mm, unsigned int order);
-
-int i915_buddy_alloc_range(struct i915_buddy_mm *mm,
- struct list_head *blocks,
- u64 start, u64 size);
-
-void i915_buddy_free(struct i915_buddy_mm *mm, struct i915_buddy_block *block);
-
-void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects);
-
-#endif
@@ -84,6 +84,7 @@
#include "intel_gvt.h"
#include "intel_memory_region.h"
#include "intel_pm.h"
+#include "intel_region_ttm.h"
#include "intel_sideband.h"
#include "vlv_suspend.h"
@@ -335,6 +336,10 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
if (ret < 0)
goto err_workqueues;
+ ret = intel_region_ttm_device_init(dev_priv);
+ if (ret)
+ goto err_ttm;
+
intel_wopcm_init_early(&dev_priv->wopcm);
intel_gt_init_early(&dev_priv->gt, dev_priv);
@@ -359,6 +364,8 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
err_gem:
i915_gem_cleanup_early(dev_priv);
intel_gt_driver_late_release(&dev_priv->gt);
+ intel_region_ttm_device_fini(dev_priv);
+err_ttm:
vlv_suspend_cleanup(dev_priv);
err_workqueues:
i915_workqueues_cleanup(dev_priv);
@@ -376,6 +383,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv)
intel_power_domains_cleanup(dev_priv);
i915_gem_cleanup_early(dev_priv);
intel_gt_driver_late_release(&dev_priv->gt);
+ intel_region_ttm_device_fini(dev_priv);
vlv_suspend_cleanup(dev_priv);
i915_workqueues_cleanup(dev_priv);
@@ -60,6 +60,7 @@
#include <drm/drm_atomic.h>
#include <drm/drm_connector.h>
#include <drm/i915_mei_hdcp_interface.h>
+#include <drm/ttm/ttm_device.h>
#include "i915_params.h"
#include "i915_reg.h"
@@ -1166,6 +1167,9 @@ struct drm_i915_private {
/* Mutex to protect the above hdcp component related values. */
struct mutex hdcp_comp_mutex;
+ /* The TTM device structure. */
+ struct ttm_device bdev;
+
I915_SELFTEST_DECLARE(struct i915_selftest_stash selftest;)
/*
@@ -1751,7 +1755,8 @@ void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
void i915_gem_init_early(struct drm_i915_private *dev_priv);
void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
-struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915);
+struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915,
+ u16 type, u16 instance);
static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
{
@@ -1109,6 +1109,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
}
i915_gem_drain_freed_objects(dev_priv);
+
return ret;
}
@@ -87,7 +87,6 @@ static void __i915_globals_cleanup(void)
static __initconst int (* const initfn[])(void) = {
i915_global_active_init,
- i915_global_buddy_init,
i915_global_context_init,
i915_global_gem_context_init,
i915_global_objects_init,
@@ -27,7 +27,6 @@ void i915_globals_exit(void);
/* constructors */
int i915_global_active_init(void);
-int i915_global_buddy_init(void);
int i915_global_context_init(void);
int i915_global_gem_context_init(void);
int i915_global_objects_init(void);
@@ -6,6 +6,10 @@
#include "i915_scatterlist.h"
+#include <drm/drm_mm.h>
+
+#include <linux/slab.h>
+
bool i915_sg_trim(struct sg_table *orig_st)
{
struct sg_table new_st;
@@ -34,6 +38,72 @@ bool i915_sg_trim(struct sg_table *orig_st)
return true;
}
+/**
+ * i915_sg_from_mm_node - Create an sg_table from a struct drm_mm_node
+ * @node: The drm_mm_node.
+ * @region_start: An offset to add to the dma addresses of the sg list.
+ *
+ * Create a struct sg_table, initializing it from a struct drm_mm_node,
+ * taking a maximum segment length into account, splitting into segments
+ * if necessary.
+ *
+ * Return: A pointer to a kmalloced struct sg_table on success, negative
+ * error code cast to an error pointer on failure.
+ */
+struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
+ u64 region_start)
+{
+ const u64 max_segment = SZ_1G; /* Do we have a limit on this? */
+ u64 segment_pages = max_segment >> PAGE_SHIFT;
+ u64 block_size, offset, prev_end;
+ struct sg_table *st;
+ struct scatterlist *sg;
+
+ st = kmalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ return ERR_PTR(-ENOMEM);
+
+ if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages),
+ GFP_KERNEL)) {
+ kfree(st);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ sg = st->sgl;
+ st->nents = 0;
+ prev_end = (resource_size_t)-1;
+ block_size = node->size << PAGE_SHIFT;
+ offset = node->start << PAGE_SHIFT;
+
+ while (block_size) {
+ u64 len;
+
+ if (offset != prev_end || sg->length >= max_segment) {
+ if (st->nents)
+ sg = __sg_next(sg);
+
+ sg_dma_address(sg) = region_start + offset;
+ sg_dma_len(sg) = 0;
+ sg->length = 0;
+ st->nents++;
+ }
+
+ len = min(block_size, max_segment - sg->length);
+ sg->length += len;
+ sg_dma_len(sg) += len;
+
+ offset += len;
+ block_size -= len;
+
+ prev_end = offset;
+ }
+
+ sg_mark_end(sg);
+ i915_sg_trim(st);
+
+ return st;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/scatterlist.c"
#endif
@@ -13,6 +13,8 @@
#include "i915_gem.h"
+struct drm_mm_node;
+
/*
* Optimised SGL iterator for GEM objects
*/
@@ -133,4 +135,37 @@ static inline unsigned int i915_sg_segment_size(void)
bool i915_sg_trim(struct sg_table *orig_st);
+/**
+ * i915_sg_dma_page_sizes - Calculate page sizes from a scatterlist
+ * @sg: The scatterlist from which to calculate page sizes
+ *
+ * Return: a value with bits sets for relevant page sizes.
+ */
+static inline unsigned int i915_sg_dma_page_sizes(struct scatterlist *sg)
+{
+ unsigned int page_sizes;
+
+ page_sizes = 0;
+ while (sg) {
+ GEM_BUG_ON(sg->offset);
+ GEM_BUG_ON(!IS_ALIGNED(sg->dma_length, PAGE_SIZE));
+ page_sizes |= sg->dma_length;
+ sg = __sg_next(sg);
+ }
+
+ /*
+ * Is this necessary to support building large GPU pages from
+ * even larger segments?
+ */
+
+ if (page_sizes > SZ_64K)
+ page_sizes |= SZ_64K;
+ if (page_sizes > SZ_2M)
+ page_sizes |= SZ_2M;
+
+ return page_sizes;
+}
+
+struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
+ u64 region_start);
#endif
@@ -28,6 +28,11 @@ static const struct {
},
};
+struct intel_region_reserve {
+ struct list_head link;
+ void *node;
+};
+
struct intel_memory_region *
intel_memory_region_lookup(struct drm_i915_private *i915,
u16 class, u16 instance)
@@ -58,146 +63,61 @@ intel_memory_region_by_type(struct drm_i915_private *i915,
return NULL;
}
-static u64
-intel_memory_region_free_pages(struct intel_memory_region *mem,
- struct list_head *blocks)
+/**
+ * intel_memory_region_unreserve - Unreserve all previously reserved
+ * ranges
+ * @mem: The region containing the reserved ranges.
+ */
+void intel_memory_region_unreserve(struct intel_memory_region *mem)
{
- struct i915_buddy_block *block, *on;
- u64 size = 0;
+ struct intel_region_reserve *reserve, *next;
- list_for_each_entry_safe(block, on, blocks, link) {
- size += i915_buddy_block_size(&mem->mm, block);
- i915_buddy_free(&mem->mm, block);
- }
- INIT_LIST_HEAD(blocks);
+ if (!mem->priv_ops || !mem->priv_ops->free)
+ return;
- return size;
-}
-
-void
-__intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
- struct list_head *blocks)
-{
mutex_lock(&mem->mm_lock);
- mem->avail += intel_memory_region_free_pages(mem, blocks);
- mutex_unlock(&mem->mm_lock);
-}
-
-void
-__intel_memory_region_put_block_buddy(struct i915_buddy_block *block)
-{
- struct list_head blocks;
-
- INIT_LIST_HEAD(&blocks);
- list_add(&block->link, &blocks);
- __intel_memory_region_put_pages_buddy(block->private, &blocks);
-}
-
-int
-__intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
- resource_size_t size,
- unsigned int flags,
- struct list_head *blocks)
-{
- unsigned int min_order = 0;
- unsigned long n_pages;
-
- GEM_BUG_ON(!IS_ALIGNED(size, mem->mm.chunk_size));
- GEM_BUG_ON(!list_empty(blocks));
-
- if (flags & I915_ALLOC_MIN_PAGE_SIZE) {
- min_order = ilog2(mem->min_page_size) -
- ilog2(mem->mm.chunk_size);
- }
-
- if (flags & I915_ALLOC_CONTIGUOUS) {
- size = roundup_pow_of_two(size);
- min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
+ list_for_each_entry_safe(reserve, next, &mem->reserved, link) {
+ list_del(&reserve->link);
+ mem->priv_ops->free(mem, reserve->node);
+ kfree(reserve);
}
-
- if (size > mem->mm.size)
- return -E2BIG;
-
- n_pages = size >> ilog2(mem->mm.chunk_size);
-
- mutex_lock(&mem->mm_lock);
-
- do {
- struct i915_buddy_block *block;
- unsigned int order;
-
- order = fls(n_pages) - 1;
- GEM_BUG_ON(order > mem->mm.max_order);
- GEM_BUG_ON(order < min_order);
-
- do {
- block = i915_buddy_alloc(&mem->mm, order);
- if (!IS_ERR(block))
- break;
-
- if (order-- == min_order)
- goto err_free_blocks;
- } while (1);
-
- n_pages -= BIT(order);
-
- block->private = mem;
- list_add_tail(&block->link, blocks);
-
- if (!n_pages)
- break;
- } while (1);
-
- mem->avail -= size;
mutex_unlock(&mem->mm_lock);
- return 0;
-
-err_free_blocks:
- intel_memory_region_free_pages(mem, blocks);
- mutex_unlock(&mem->mm_lock);
- return -ENXIO;
}
-struct i915_buddy_block *
-__intel_memory_region_get_block_buddy(struct intel_memory_region *mem,
- resource_size_t size,
- unsigned int flags)
+/**
+ * intel_memory_region_reserve - Reserve a memory range
+ * @mem: The region for which we want to reserve a range.
+ * @offset: Start of the range to reserve.
+ * @size: The size of the range to reserve.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int intel_memory_region_reserve(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size)
{
- struct i915_buddy_block *block;
- LIST_HEAD(blocks);
int ret;
+ struct intel_region_reserve *reserve;
- ret = __intel_memory_region_get_pages_buddy(mem, size, flags, &blocks);
- if (ret)
- return ERR_PTR(ret);
+ if (!mem->priv_ops || !mem->priv_ops->reserve)
+ return -EINVAL;
- block = list_first_entry(&blocks, typeof(*block), link);
- list_del_init(&block->link);
- return block;
-}
+ reserve = kzalloc(sizeof(*reserve), GFP_KERNEL);
+ if (!reserve)
+ return -ENOMEM;
-int intel_memory_region_init_buddy(struct intel_memory_region *mem)
-{
- return i915_buddy_init(&mem->mm, resource_size(&mem->region),
- PAGE_SIZE);
-}
-
-void intel_memory_region_release_buddy(struct intel_memory_region *mem)
-{
- i915_buddy_free_list(&mem->mm, &mem->reserved);
- i915_buddy_fini(&mem->mm);
-}
-
-int intel_memory_region_reserve(struct intel_memory_region *mem,
- u64 offset, u64 size)
-{
- int ret;
+ reserve->node = mem->priv_ops->reserve(mem, offset, size);
+ if (IS_ERR(reserve->node)) {
+ ret = PTR_ERR(reserve->node);
+ kfree(reserve);
+ return ret;
+ }
mutex_lock(&mem->mm_lock);
- ret = i915_buddy_alloc_range(&mem->mm, &mem->reserved, offset, size);
+ list_add_tail(&reserve->link, &mem->reserved);
mutex_unlock(&mem->mm_lock);
- return ret;
+ return 0;
}
struct intel_memory_region *
@@ -206,6 +126,8 @@ intel_memory_region_create(struct drm_i915_private *i915,
resource_size_t size,
resource_size_t min_page_size,
resource_size_t io_start,
+ u16 type,
+ u16 instance,
const struct intel_memory_region_ops *ops)
{
struct intel_memory_region *mem;
@@ -222,6 +144,8 @@ intel_memory_region_create(struct drm_i915_private *i915,
mem->ops = ops;
mem->total = size;
mem->avail = mem->total;
+ mem->type = type;
+ mem->instance = instance;
mutex_init(&mem->objects.lock);
INIT_LIST_HEAD(&mem->objects.list);
@@ -259,6 +183,7 @@ static void __intel_memory_region_destroy(struct kref *kref)
struct intel_memory_region *mem =
container_of(kref, typeof(*mem), kref);
+ intel_memory_region_unreserve(mem);
if (mem->ops->release)
mem->ops->release(mem);
@@ -296,15 +221,15 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
instance = intel_region_map[i].instance;
switch (type) {
case INTEL_MEMORY_SYSTEM:
- mem = i915_gem_shmem_setup(i915);
+ mem = i915_gem_shmem_setup(i915, type, instance);
break;
case INTEL_MEMORY_STOLEN_LOCAL:
- mem = i915_gem_stolen_lmem_setup(i915);
+ mem = i915_gem_stolen_lmem_setup(i915, type, instance);
if (!IS_ERR(mem))
i915->mm.stolen_region = mem;
break;
case INTEL_MEMORY_STOLEN_SYSTEM:
- mem = i915_gem_stolen_smem_setup(i915);
+ mem = i915_gem_stolen_smem_setup(i915, type, instance);
if (!IS_ERR(mem))
i915->mm.stolen_region = mem;
break;
@@ -321,9 +246,6 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
}
mem->id = i;
- mem->type = type;
- mem->instance = instance;
-
i915->mm.regions[i] = mem;
}
@@ -13,8 +13,6 @@
#include <drm/drm_mm.h>
#include <drm/i915_drm.h>
-#include "i915_buddy.h"
-
struct drm_i915_private;
struct drm_i915_gem_object;
struct intel_memory_region;
@@ -25,6 +23,7 @@ enum intel_memory_type {
INTEL_MEMORY_LOCAL = I915_MEMORY_CLASS_DEVICE,
INTEL_MEMORY_STOLEN_SYSTEM,
INTEL_MEMORY_STOLEN_LOCAL,
+ INTEL_MEMORY_MOCK,
};
enum intel_region_id {
@@ -59,10 +58,19 @@ struct intel_memory_region_ops {
unsigned int flags);
};
+struct intel_memory_region_private_ops {
+ void *(*reserve)(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size);
+ void (*free)(struct intel_memory_region *mem,
+ void *node);
+};
+
struct intel_memory_region {
struct drm_i915_private *i915;
const struct intel_memory_region_ops *ops;
+ const struct intel_memory_region_private_ops *priv_ops;
struct io_mapping iomap;
struct resource region;
@@ -70,7 +78,6 @@ struct intel_memory_region {
/* For fake LMEM */
struct drm_mm_node fake_mappable;
- struct i915_buddy_mm mm;
struct mutex mm_lock;
struct kref kref;
@@ -95,36 +102,26 @@ struct intel_memory_region {
struct list_head list;
struct list_head purgeable;
} objects;
+
+ size_t chunk_size;
+ unsigned int max_order;
+ bool is_range_manager;
+
+ void *region_private;
};
struct intel_memory_region *
intel_memory_region_lookup(struct drm_i915_private *i915,
u16 class, u16 instance);
-int intel_memory_region_init_buddy(struct intel_memory_region *mem);
-void intel_memory_region_release_buddy(struct intel_memory_region *mem);
-
-int __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
- resource_size_t size,
- unsigned int flags,
- struct list_head *blocks);
-struct i915_buddy_block *
-__intel_memory_region_get_block_buddy(struct intel_memory_region *mem,
- resource_size_t size,
- unsigned int flags);
-void __intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
- struct list_head *blocks);
-void __intel_memory_region_put_block_buddy(struct i915_buddy_block *block);
-
-int intel_memory_region_reserve(struct intel_memory_region *mem,
- u64 offset, u64 size);
-
struct intel_memory_region *
intel_memory_region_create(struct drm_i915_private *i915,
resource_size_t start,
resource_size_t size,
resource_size_t min_page_size,
resource_size_t io_start,
+ u16 type,
+ u16 instance,
const struct intel_memory_region_ops *ops);
struct intel_memory_region *
@@ -141,4 +138,9 @@ __printf(2, 3) void
intel_memory_region_set_name(struct intel_memory_region *mem,
const char *fmt, ...);
+void intel_memory_region_unreserve(struct intel_memory_region *mem);
+
+int intel_memory_region_reserve(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size);
#endif
new file mode 100644
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_device.h>
+
+#include "i915_drv.h"
+#include "i915_scatterlist.h"
+
+#include "intel_region_ttm.h"
+
+/* A Zero-initialized driver for now. We don't have a TTM backend yet. */
+static struct ttm_device_funcs i915_ttm_bo_driver;
+
+/**
+ * DOC: TTM support structure
+ *
+ * The code in this file deals with setting up memory managers for TTM
+ * LMEM and MOCK regions and converting the output from
+ * the managers to struct sg_table, Basically providing the mapping from
+ * i915 GEM regions to TTM memory types and resource managers.
+ */
+
+/**
+ * intel_region_ttm_device_init - Initialize a TTM device
+ * @dev_priv: Pointer to an i915 device private structure.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int intel_region_ttm_device_init(struct drm_i915_private *dev_priv)
+{
+ struct drm_device *drm = &dev_priv->drm;
+
+ return ttm_device_init(&dev_priv->bdev, &i915_ttm_bo_driver,
+ drm->dev, drm->anon_inode->i_mapping,
+ drm->vma_offset_manager, false, false);
+}
+
+/**
+ * intel_region_ttm_device_fini - Finalize a TTM device
+ * @dev_priv: Pointer to an i915 device private structure.
+ */
+void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv)
+{
+ ttm_device_fini(&dev_priv->bdev);
+}
+
+/*
+ * Map the i915 memory regions to TTM memory types. We use the
+ * driver-private types for now, reserving TTM_PL_VRAM for stolen
+ * memory and TTM_PL_TT for GGTT use if decided to implement this.
+ */
+static int intel_region_to_ttm_type(struct intel_memory_region *mem)
+{
+ int type;
+
+ GEM_BUG_ON(mem->type != INTEL_MEMORY_LOCAL);
+
+ type = mem->instance + TTM_PL_PRIV;
+ GEM_BUG_ON(type >= TTM_NUM_MEM_TYPES);
+
+ return type;
+}
+
+static void *intel_region_ttm_node_reserve(struct intel_memory_region *mem,
+ resource_size_t offset,
+ resource_size_t size)
+{
+ struct ttm_resource_manager *man = mem->region_private;
+ struct ttm_place place = {};
+ struct ttm_resource res = {};
+ struct ttm_buffer_object mock_bo = {};
+ int ret;
+
+ /*
+ * Having to use a mock_bo is unfortunate but stems from some
+ * drivers having private managers that insist to know what the
+ * allocate memory is intended for, using it to send private
+ * data to the manager. Also recently the bo has been used to send
+ * alignment info to the manager. Assume that apart from the latter,
+ * none of the managers we use will ever access the buffer object
+ * members, hoping we can pass the alignment info in the
+ * struct ttm_place in the future.
+ */
+
+ place.fpfn = offset >> PAGE_SHIFT;
+ place.lpfn = place.fpfn + (size >> PAGE_SHIFT);
+ res.num_pages = size >> PAGE_SHIFT;
+ ret = man->func->alloc(man, &mock_bo, &place, &res);
+ if (ret == -ENOSPC)
+ ret = -ENXIO;
+
+ return ret ? ERR_PTR(ret) : res.mm_node;
+}
+
+/**
+ * intel_region_ttm_node_free - Free a node allocated from a resource manager
+ * @mem: The region the node was allocated from.
+ * @node: The opaque node representing an allocation.
+ */
+void intel_region_ttm_node_free(struct intel_memory_region *mem,
+ void *node)
+{
+ struct ttm_resource_manager *man = mem->region_private;
+ struct ttm_resource res = {};
+
+ res.mm_node = node;
+ man->func->free(man, &res);
+}
+
+static const struct intel_memory_region_private_ops priv_ops = {
+ .reserve = intel_region_ttm_node_reserve,
+ .free = intel_region_ttm_node_free,
+};
+
+/**
+ * intel_region_ttm_init - Initialize a memory region for TTM.
+ * @mem: The region to initialize.
+ *
+ * This function initializes a suitable TTM resource manager for the
+ * region, and if it's a LMEM region type, attaches it to the TTM
+ * device. MOCK regions are NOT attached to the TTM device, since we don't
+ * have one for the mock selftests.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int intel_region_ttm_init(struct intel_memory_region *mem)
+{
+ struct ttm_resource_manager *man;
+
+ man = ttm_range_man_init_standalone(resource_size(&mem->region) >>
+ PAGE_SHIFT, false);
+ if (IS_ERR(man))
+ return PTR_ERR(man);
+
+ ttm_resource_manager_set_used(man, true);
+ mem->chunk_size = PAGE_SIZE;
+ mem->max_order =
+ get_order(rounddown_pow_of_two(resource_size(&mem->region)));
+ mem->is_range_manager = true;
+ mem->priv_ops = &priv_ops;
+ mem->region_private = man;
+
+
+ /*
+ * Register only LOCAL memory with the device so that we can
+ * run the mock selftests using the manager.
+ */
+ if (mem->type == INTEL_MEMORY_LOCAL) {
+ ttm_set_driver_manager(&mem->i915->bdev,
+ intel_region_to_ttm_type(mem),
+ man);
+ }
+
+ return 0;
+}
+
+/**
+ * intel_region_ttm_fini - Finalize a TTM region.
+ * @mem: The memory region
+ *
+ * This functions takes down the TTM resource manager associated with the
+ * memory region, and if it was registered with the TTM device,
+ * removes that registration.
+ */
+void intel_region_ttm_fini(struct intel_memory_region *mem)
+{
+ struct ttm_resource_manager *man = mem->region_private;
+
+ if (mem->type == INTEL_MEMORY_LOCAL) {
+ int ret;
+
+ ret = ttm_range_man_fini(&mem->i915->bdev,
+ intel_region_to_ttm_type(mem));
+ GEM_WARN_ON(ret);
+ } else {
+ ttm_resource_manager_set_used(man, false);
+ ttm_range_man_fini_standalone(man);
+ }
+}
+
+/**
+ * intel_region_ttm_node_to_st - Convert an opaque TTM resource manager node
+ * to an sg_table.
+ * @mem: The memory region.
+ * @node: The resource manager node obtained from the TTM resource manager.
+ *
+ * The gem backends typically use sg-tables for operations on the underlying
+ * io_memory. So provide a way for the backends to translate the
+ * nodes they are handed from TTM to sg-tables.
+ *
+ * Return: A malloced sg_table on success, an error pointer on failure.
+ */
+struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
+ void *node)
+{
+ return i915_sg_from_mm_node(node, mem->region.start);
+}
+
+/**
+ * intel_region_ttm_node_alloc - Allocate memory resources from a region
+ * @mem: The memory region,
+ * @size: The requested size in bytes
+ * @flags: Allocation flags
+ *
+ * This functionality is provided only for callers that need to allocate
+ * memory from standalone TTM range managers, without the TTM eviction
+ * functionality. Don't use if you are not completely sure that's the
+ * case. The returned opaque node can be converted to an sg_table using
+ * intel_region_ttm_node_to_st(), and can be freed using
+ * intel_region_ttm_node_free().
+ *
+ * Return: A valid pointer on success, an error pointer on failure.
+ */
+void *intel_region_ttm_node_alloc(struct intel_memory_region *mem,
+ resource_size_t size,
+ unsigned int flags)
+{
+ struct ttm_resource_manager *man = mem->region_private;
+ struct ttm_place place = {};
+ struct ttm_resource res = {};
+ struct ttm_buffer_object mock_bo = {};
+ int ret;
+
+ /*
+ * We ignore the flags for now since we're using the range
+ * manager and contigous and min page size would be fulfilled
+ * by default if size is min page size aligned.
+ */
+ res.num_pages = size >> PAGE_SHIFT;
+
+ if (mem->is_range_manager) {
+ if (size >= SZ_1G)
+ mock_bo.page_alignment = SZ_1G >> PAGE_SHIFT;
+ else if (size >= SZ_2M)
+ mock_bo.page_alignment = SZ_2M >> PAGE_SHIFT;
+ else if (size >= SZ_64K)
+ mock_bo.page_alignment = SZ_64K >> PAGE_SHIFT;
+ }
+
+ ret = man->func->alloc(man, &mock_bo, &place, &res);
+ if (ret == -ENOSPC)
+ ret = -ENXIO;
+ return ret ? ERR_PTR(ret) : res.mm_node;
+}
new file mode 100644
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+#ifndef _INTEL_REGION_TTM_H_
+#define _INTEL_REGION_TTM_H_
+
+#include <linux/types.h>
+
+struct drm_i915_private;
+struct intel_memory_region;
+
+int intel_region_ttm_device_init(struct drm_i915_private *dev_priv);
+
+void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv);
+
+int intel_region_ttm_init(struct intel_memory_region *mem);
+
+void intel_region_ttm_fini(struct intel_memory_region *mem);
+
+struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
+ void *node);
+
+void *intel_region_ttm_node_alloc(struct intel_memory_region *mem,
+ resource_size_t size,
+ unsigned int flags);
+void intel_region_ttm_node_free(struct intel_memory_region *mem,
+ void *node);
+#endif /* _INTEL_REGION_TTM_H_ */
deleted file mode 100644
@@ -1,789 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2019 Intel Corporation
- */
-
-#include <linux/prime_numbers.h>
-
-#include "../i915_selftest.h"
-#include "i915_random.h"
-
-static void __igt_dump_block(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block,
- bool buddy)
-{
- pr_err("block info: header=%llx, state=%u, order=%d, offset=%llx size=%llx root=%s buddy=%s\n",
- block->header,
- i915_buddy_block_state(block),
- i915_buddy_block_order(block),
- i915_buddy_block_offset(block),
- i915_buddy_block_size(mm, block),
- yesno(!block->parent),
- yesno(buddy));
-}
-
-static void igt_dump_block(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- struct i915_buddy_block *buddy;
-
- __igt_dump_block(mm, block, false);
-
- buddy = get_buddy(block);
- if (buddy)
- __igt_dump_block(mm, buddy, true);
-}
-
-static int igt_check_block(struct i915_buddy_mm *mm,
- struct i915_buddy_block *block)
-{
- struct i915_buddy_block *buddy;
- unsigned int block_state;
- u64 block_size;
- u64 offset;
- int err = 0;
-
- block_state = i915_buddy_block_state(block);
-
- if (block_state != I915_BUDDY_ALLOCATED &&
- block_state != I915_BUDDY_FREE &&
- block_state != I915_BUDDY_SPLIT) {
- pr_err("block state mismatch\n");
- err = -EINVAL;
- }
-
- block_size = i915_buddy_block_size(mm, block);
- offset = i915_buddy_block_offset(block);
-
- if (block_size < mm->chunk_size) {
- pr_err("block size smaller than min size\n");
- err = -EINVAL;
- }
-
- if (!is_power_of_2(block_size)) {
- pr_err("block size not power of two\n");
- err = -EINVAL;
- }
-
- if (!IS_ALIGNED(block_size, mm->chunk_size)) {
- pr_err("block size not aligned to min size\n");
- err = -EINVAL;
- }
-
- if (!IS_ALIGNED(offset, mm->chunk_size)) {
- pr_err("block offset not aligned to min size\n");
- err = -EINVAL;
- }
-
- if (!IS_ALIGNED(offset, block_size)) {
- pr_err("block offset not aligned to block size\n");
- err = -EINVAL;
- }
-
- buddy = get_buddy(block);
-
- if (!buddy && block->parent) {
- pr_err("buddy has gone fishing\n");
- err = -EINVAL;
- }
-
- if (buddy) {
- if (i915_buddy_block_offset(buddy) != (offset ^ block_size)) {
- pr_err("buddy has wrong offset\n");
- err = -EINVAL;
- }
-
- if (i915_buddy_block_size(mm, buddy) != block_size) {
- pr_err("buddy size mismatch\n");
- err = -EINVAL;
- }
-
- if (i915_buddy_block_state(buddy) == block_state &&
- block_state == I915_BUDDY_FREE) {
- pr_err("block and its buddy are free\n");
- err = -EINVAL;
- }
- }
-
- return err;
-}
-
-static int igt_check_blocks(struct i915_buddy_mm *mm,
- struct list_head *blocks,
- u64 expected_size,
- bool is_contiguous)
-{
- struct i915_buddy_block *block;
- struct i915_buddy_block *prev;
- u64 total;
- int err = 0;
-
- block = NULL;
- prev = NULL;
- total = 0;
-
- list_for_each_entry(block, blocks, link) {
- err = igt_check_block(mm, block);
-
- if (!i915_buddy_block_is_allocated(block)) {
- pr_err("block not allocated\n"),
- err = -EINVAL;
- }
-
- if (is_contiguous && prev) {
- u64 prev_block_size;
- u64 prev_offset;
- u64 offset;
-
- prev_offset = i915_buddy_block_offset(prev);
- prev_block_size = i915_buddy_block_size(mm, prev);
- offset = i915_buddy_block_offset(block);
-
- if (offset != (prev_offset + prev_block_size)) {
- pr_err("block offset mismatch\n");
- err = -EINVAL;
- }
- }
-
- if (err)
- break;
-
- total += i915_buddy_block_size(mm, block);
- prev = block;
- }
-
- if (!err) {
- if (total != expected_size) {
- pr_err("size mismatch, expected=%llx, found=%llx\n",
- expected_size, total);
- err = -EINVAL;
- }
- return err;
- }
-
- if (prev) {
- pr_err("prev block, dump:\n");
- igt_dump_block(mm, prev);
- }
-
- if (block) {
- pr_err("bad block, dump:\n");
- igt_dump_block(mm, block);
- }
-
- return err;
-}
-
-static int igt_check_mm(struct i915_buddy_mm *mm)
-{
- struct i915_buddy_block *root;
- struct i915_buddy_block *prev;
- unsigned int i;
- u64 total;
- int err = 0;
-
- if (!mm->n_roots) {
- pr_err("n_roots is zero\n");
- return -EINVAL;
- }
-
- if (mm->n_roots != hweight64(mm->size)) {
- pr_err("n_roots mismatch, n_roots=%u, expected=%lu\n",
- mm->n_roots, hweight64(mm->size));
- return -EINVAL;
- }
-
- root = NULL;
- prev = NULL;
- total = 0;
-
- for (i = 0; i < mm->n_roots; ++i) {
- struct i915_buddy_block *block;
- unsigned int order;
-
- root = mm->roots[i];
- if (!root) {
- pr_err("root(%u) is NULL\n", i);
- err = -EINVAL;
- break;
- }
-
- err = igt_check_block(mm, root);
-
- if (!i915_buddy_block_is_free(root)) {
- pr_err("root not free\n");
- err = -EINVAL;
- }
-
- order = i915_buddy_block_order(root);
-
- if (!i) {
- if (order != mm->max_order) {
- pr_err("max order root missing\n");
- err = -EINVAL;
- }
- }
-
- if (prev) {
- u64 prev_block_size;
- u64 prev_offset;
- u64 offset;
-
- prev_offset = i915_buddy_block_offset(prev);
- prev_block_size = i915_buddy_block_size(mm, prev);
- offset = i915_buddy_block_offset(root);
-
- if (offset != (prev_offset + prev_block_size)) {
- pr_err("root offset mismatch\n");
- err = -EINVAL;
- }
- }
-
- block = list_first_entry_or_null(&mm->free_list[order],
- struct i915_buddy_block,
- link);
- if (block != root) {
- pr_err("root mismatch at order=%u\n", order);
- err = -EINVAL;
- }
-
- if (err)
- break;
-
- prev = root;
- total += i915_buddy_block_size(mm, root);
- }
-
- if (!err) {
- if (total != mm->size) {
- pr_err("expected mm size=%llx, found=%llx\n", mm->size,
- total);
- err = -EINVAL;
- }
- return err;
- }
-
- if (prev) {
- pr_err("prev root(%u), dump:\n", i - 1);
- igt_dump_block(mm, prev);
- }
-
- if (root) {
- pr_err("bad root(%u), dump:\n", i);
- igt_dump_block(mm, root);
- }
-
- return err;
-}
-
-static void igt_mm_config(u64 *size, u64 *chunk_size)
-{
- I915_RND_STATE(prng);
- u32 s, ms;
-
- /* Nothing fancy, just try to get an interesting bit pattern */
-
- prandom_seed_state(&prng, i915_selftest.random_seed);
-
- /* Let size be a random number of pages up to 8 GB (2M pages) */
- s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng);
- /* Let the chunk size be a random power of 2 less than size */
- ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng));
- /* Round size down to the chunk size */
- s &= -ms;
-
- /* Convert from pages to bytes */
- *chunk_size = (u64)ms << 12;
- *size = (u64)s << 12;
-}
-
-static int igt_buddy_alloc_smoke(void *arg)
-{
- struct i915_buddy_mm mm;
- IGT_TIMEOUT(end_time);
- I915_RND_STATE(prng);
- u64 chunk_size;
- u64 mm_size;
- int *order;
- int err, i;
-
- igt_mm_config(&mm_size, &chunk_size);
-
- pr_info("buddy_init with size=%llx, chunk_size=%llx\n", mm_size, chunk_size);
-
- err = i915_buddy_init(&mm, mm_size, chunk_size);
- if (err) {
- pr_err("buddy_init failed(%d)\n", err);
- return err;
- }
-
- order = i915_random_order(mm.max_order + 1, &prng);
- if (!order)
- goto out_fini;
-
- for (i = 0; i <= mm.max_order; ++i) {
- struct i915_buddy_block *block;
- int max_order = order[i];
- bool timeout = false;
- LIST_HEAD(blocks);
- int order;
- u64 total;
-
- err = igt_check_mm(&mm);
- if (err) {
- pr_err("pre-mm check failed, abort\n");
- break;
- }
-
- pr_info("filling from max_order=%u\n", max_order);
-
- order = max_order;
- total = 0;
-
- do {
-retry:
- block = i915_buddy_alloc(&mm, order);
- if (IS_ERR(block)) {
- err = PTR_ERR(block);
- if (err == -ENOMEM) {
- pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
- order);
- } else {
- if (order--) {
- err = 0;
- goto retry;
- }
-
- pr_err("buddy_alloc with order=%d failed(%d)\n",
- order, err);
- }
-
- break;
- }
-
- list_add_tail(&block->link, &blocks);
-
- if (i915_buddy_block_order(block) != order) {
- pr_err("buddy_alloc order mismatch\n");
- err = -EINVAL;
- break;
- }
-
- total += i915_buddy_block_size(&mm, block);
-
- if (__igt_timeout(end_time, NULL)) {
- timeout = true;
- break;
- }
- } while (total < mm.size);
-
- if (!err)
- err = igt_check_blocks(&mm, &blocks, total, false);
-
- i915_buddy_free_list(&mm, &blocks);
-
- if (!err) {
- err = igt_check_mm(&mm);
- if (err)
- pr_err("post-mm check failed\n");
- }
-
- if (err || timeout)
- break;
-
- cond_resched();
- }
-
- if (err == -ENOMEM)
- err = 0;
-
- kfree(order);
-out_fini:
- i915_buddy_fini(&mm);
-
- return err;
-}
-
-static int igt_buddy_alloc_pessimistic(void *arg)
-{
- const unsigned int max_order = 16;
- struct i915_buddy_block *block, *bn;
- struct i915_buddy_mm mm;
- unsigned int order;
- LIST_HEAD(blocks);
- int err;
-
- /*
- * Create a pot-sized mm, then allocate one of each possible
- * order within. This should leave the mm with exactly one
- * page left.
- */
-
- err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE);
- if (err) {
- pr_err("buddy_init failed(%d)\n", err);
- return err;
- }
- GEM_BUG_ON(mm.max_order != max_order);
-
- for (order = 0; order < max_order; order++) {
- block = i915_buddy_alloc(&mm, order);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
- order);
- err = PTR_ERR(block);
- goto err;
- }
-
- list_add_tail(&block->link, &blocks);
- }
-
- /* And now the last remaining block available */
- block = i915_buddy_alloc(&mm, 0);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc hit -ENOMEM on final alloc\n");
- err = PTR_ERR(block);
- goto err;
- }
- list_add_tail(&block->link, &blocks);
-
- /* Should be completely full! */
- for (order = max_order; order--; ) {
- block = i915_buddy_alloc(&mm, order);
- if (!IS_ERR(block)) {
- pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!",
- order);
- list_add_tail(&block->link, &blocks);
- err = -EINVAL;
- goto err;
- }
- }
-
- block = list_last_entry(&blocks, typeof(*block), link);
- list_del(&block->link);
- i915_buddy_free(&mm, block);
-
- /* As we free in increasing size, we make available larger blocks */
- order = 1;
- list_for_each_entry_safe(block, bn, &blocks, link) {
- list_del(&block->link);
- i915_buddy_free(&mm, block);
-
- block = i915_buddy_alloc(&mm, order);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
- order);
- err = PTR_ERR(block);
- goto err;
- }
- i915_buddy_free(&mm, block);
- order++;
- }
-
- /* To confirm, now the whole mm should be available */
- block = i915_buddy_alloc(&mm, max_order);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
- max_order);
- err = PTR_ERR(block);
- goto err;
- }
- i915_buddy_free(&mm, block);
-
-err:
- i915_buddy_free_list(&mm, &blocks);
- i915_buddy_fini(&mm);
- return err;
-}
-
-static int igt_buddy_alloc_optimistic(void *arg)
-{
- const int max_order = 16;
- struct i915_buddy_block *block;
- struct i915_buddy_mm mm;
- LIST_HEAD(blocks);
- int order;
- int err;
-
- /*
- * Create a mm with one block of each order available, and
- * try to allocate them all.
- */
-
- err = i915_buddy_init(&mm,
- PAGE_SIZE * ((1 << (max_order + 1)) - 1),
- PAGE_SIZE);
- if (err) {
- pr_err("buddy_init failed(%d)\n", err);
- return err;
- }
- GEM_BUG_ON(mm.max_order != max_order);
-
- for (order = 0; order <= max_order; order++) {
- block = i915_buddy_alloc(&mm, order);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc hit -ENOMEM with order=%d\n",
- order);
- err = PTR_ERR(block);
- goto err;
- }
-
- list_add_tail(&block->link, &blocks);
- }
-
- /* Should be completely full! */
- block = i915_buddy_alloc(&mm, 0);
- if (!IS_ERR(block)) {
- pr_info("buddy_alloc unexpectedly succeeded, it should be full!");
- list_add_tail(&block->link, &blocks);
- err = -EINVAL;
- goto err;
- }
-
-err:
- i915_buddy_free_list(&mm, &blocks);
- i915_buddy_fini(&mm);
- return err;
-}
-
-static int igt_buddy_alloc_pathological(void *arg)
-{
- const int max_order = 16;
- struct i915_buddy_block *block;
- struct i915_buddy_mm mm;
- LIST_HEAD(blocks);
- LIST_HEAD(holes);
- int order, top;
- int err;
-
- /*
- * Create a pot-sized mm, then allocate one of each possible
- * order within. This should leave the mm with exactly one
- * page left. Free the largest block, then whittle down again.
- * Eventually we will have a fully 50% fragmented mm.
- */
-
- err = i915_buddy_init(&mm, PAGE_SIZE << max_order, PAGE_SIZE);
- if (err) {
- pr_err("buddy_init failed(%d)\n", err);
- return err;
- }
- GEM_BUG_ON(mm.max_order != max_order);
-
- for (top = max_order; top; top--) {
- /* Make room by freeing the largest allocated block */
- block = list_first_entry_or_null(&blocks, typeof(*block), link);
- if (block) {
- list_del(&block->link);
- i915_buddy_free(&mm, block);
- }
-
- for (order = top; order--; ) {
- block = i915_buddy_alloc(&mm, order);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc hit -ENOMEM with order=%d, top=%d\n",
- order, top);
- err = PTR_ERR(block);
- goto err;
- }
- list_add_tail(&block->link, &blocks);
- }
-
- /* There should be one final page for this sub-allocation */
- block = i915_buddy_alloc(&mm, 0);
- if (IS_ERR(block)) {
- pr_info("buddy_alloc hit -ENOMEM for hole\n");
- err = PTR_ERR(block);
- goto err;
- }
- list_add_tail(&block->link, &holes);
-
- block = i915_buddy_alloc(&mm, top);
- if (!IS_ERR(block)) {
- pr_info("buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!",
- top, max_order);
- list_add_tail(&block->link, &blocks);
- err = -EINVAL;
- goto err;
- }
- }
-
- i915_buddy_free_list(&mm, &holes);
-
- /* Nothing larger than blocks of chunk_size now available */
- for (order = 1; order <= max_order; order++) {
- block = i915_buddy_alloc(&mm, order);
- if (!IS_ERR(block)) {
- pr_info("buddy_alloc unexpectedly succeeded at order %d, it should be full!",
- order);
- list_add_tail(&block->link, &blocks);
- err = -EINVAL;
- goto err;
- }
- }
-
-err:
- list_splice_tail(&holes, &blocks);
- i915_buddy_free_list(&mm, &blocks);
- i915_buddy_fini(&mm);
- return err;
-}
-
-static int igt_buddy_alloc_range(void *arg)
-{
- struct i915_buddy_mm mm;
- unsigned long page_num;
- LIST_HEAD(blocks);
- u64 chunk_size;
- u64 offset;
- u64 size;
- u64 rem;
- int err;
-
- igt_mm_config(&size, &chunk_size);
-
- pr_info("buddy_init with size=%llx, chunk_size=%llx\n", size, chunk_size);
-
- err = i915_buddy_init(&mm, size, chunk_size);
- if (err) {
- pr_err("buddy_init failed(%d)\n", err);
- return err;
- }
-
- err = igt_check_mm(&mm);
- if (err) {
- pr_err("pre-mm check failed, abort, abort, abort!\n");
- goto err_fini;
- }
-
- rem = mm.size;
- offset = 0;
-
- for_each_prime_number_from(page_num, 1, ULONG_MAX - 1) {
- struct i915_buddy_block *block;
- LIST_HEAD(tmp);
-
- size = min(page_num * mm.chunk_size, rem);
-
- err = i915_buddy_alloc_range(&mm, &tmp, offset, size);
- if (err) {
- if (err == -ENOMEM) {
- pr_info("alloc_range hit -ENOMEM with size=%llx\n",
- size);
- } else {
- pr_err("alloc_range with offset=%llx, size=%llx failed(%d)\n",
- offset, size, err);
- }
-
- break;
- }
-
- block = list_first_entry_or_null(&tmp,
- struct i915_buddy_block,
- link);
- if (!block) {
- pr_err("alloc_range has no blocks\n");
- err = -EINVAL;
- break;
- }
-
- if (i915_buddy_block_offset(block) != offset) {
- pr_err("alloc_range start offset mismatch, found=%llx, expected=%llx\n",
- i915_buddy_block_offset(block), offset);
- err = -EINVAL;
- }
-
- if (!err)
- err = igt_check_blocks(&mm, &tmp, size, true);
-
- list_splice_tail(&tmp, &blocks);
-
- if (err)
- break;
-
- offset += size;
-
- rem -= size;
- if (!rem)
- break;
-
- cond_resched();
- }
-
- if (err == -ENOMEM)
- err = 0;
-
- i915_buddy_free_list(&mm, &blocks);
-
- if (!err) {
- err = igt_check_mm(&mm);
- if (err)
- pr_err("post-mm check failed\n");
- }
-
-err_fini:
- i915_buddy_fini(&mm);
-
- return err;
-}
-
-static int igt_buddy_alloc_limit(void *arg)
-{
- struct i915_buddy_block *block;
- struct i915_buddy_mm mm;
- const u64 size = U64_MAX;
- int err;
-
- err = i915_buddy_init(&mm, size, PAGE_SIZE);
- if (err)
- return err;
-
- if (mm.max_order != I915_BUDDY_MAX_ORDER) {
- pr_err("mm.max_order(%d) != %d\n",
- mm.max_order, I915_BUDDY_MAX_ORDER);
- err = -EINVAL;
- goto out_fini;
- }
-
- block = i915_buddy_alloc(&mm, mm.max_order);
- if (IS_ERR(block)) {
- err = PTR_ERR(block);
- goto out_fini;
- }
-
- if (i915_buddy_block_order(block) != mm.max_order) {
- pr_err("block order(%d) != %d\n",
- i915_buddy_block_order(block), mm.max_order);
- err = -EINVAL;
- goto out_free;
- }
-
- if (i915_buddy_block_size(&mm, block) !=
- BIT_ULL(mm.max_order) * PAGE_SIZE) {
- pr_err("block size(%llu) != %llu\n",
- i915_buddy_block_size(&mm, block),
- BIT_ULL(mm.max_order) * PAGE_SIZE);
- err = -EINVAL;
- goto out_free;
- }
-
-out_free:
- i915_buddy_free(&mm, block);
-out_fini:
- i915_buddy_fini(&mm);
- return err;
-}
-
-int i915_buddy_mock_selftests(void)
-{
- static const struct i915_subtest tests[] = {
- SUBTEST(igt_buddy_alloc_pessimistic),
- SUBTEST(igt_buddy_alloc_optimistic),
- SUBTEST(igt_buddy_alloc_pathological),
- SUBTEST(igt_buddy_alloc_smoke),
- SUBTEST(igt_buddy_alloc_range),
- SUBTEST(igt_buddy_alloc_limit),
- };
-
- return i915_subtests(tests, NULL);
-}
@@ -33,5 +33,4 @@ selftest(evict, i915_gem_evict_mock_selftests)
selftest(gtt, i915_gem_gtt_mock_selftests)
selftest(hugepages, i915_gem_huge_page_mock_selftests)
selftest(contexts, i915_gem_context_mock_selftests)
-selftest(buddy, i915_buddy_mock_selftests)
selftest(memory_region, intel_memory_region_mock_selftests)
@@ -57,9 +57,10 @@ static int igt_mock_fill(void *arg)
LIST_HEAD(objects);
int err = 0;
- page_size = mem->mm.chunk_size;
- max_pages = div64_u64(total, page_size);
+ page_size = mem->chunk_size;
rem = total;
+retry:
+ max_pages = div64_u64(rem, page_size);
for_each_prime_number_from(page_num, 1, max_pages) {
resource_size_t size = page_num * page_size;
@@ -85,6 +86,11 @@ static int igt_mock_fill(void *arg)
err = 0;
if (err == -ENXIO) {
if (page_num * page_size <= rem) {
+ if (mem->is_range_manager && max_pages > 1) {
+ max_pages >>= 1;
+ goto retry;
+ }
+
pr_err("%s failed, space still left in region\n",
__func__);
err = -EINVAL;
@@ -199,12 +205,18 @@ static int igt_mock_reserve(void *arg)
do {
u32 size = i915_prandom_u32_max_state(cur_avail, &prng);
+retry:
size = max_t(u32, round_up(size, PAGE_SIZE), PAGE_SIZE);
obj = igt_object_create(mem, &objects, size, 0);
if (IS_ERR(obj)) {
- if (PTR_ERR(obj) == -ENXIO)
+ if (PTR_ERR(obj) == -ENXIO) {
+ if (mem->is_range_manager &&
+ size > mem->chunk_size) {
+ size >>= 1;
+ goto retry;
+ }
break;
-
+ }
err = PTR_ERR(obj);
goto out_close;
}
@@ -220,7 +232,7 @@ static int igt_mock_reserve(void *arg)
out_close:
kfree(order);
close_objects(mem, &objects);
- i915_buddy_free_list(&mem->mm, &mem->reserved);
+ intel_memory_region_unreserve(mem);
return err;
}
@@ -240,7 +252,7 @@ static int igt_mock_contiguous(void *arg)
total = resource_size(&mem->region);
/* Min size */
- obj = igt_object_create(mem, &objects, mem->mm.chunk_size,
+ obj = igt_object_create(mem, &objects, mem->chunk_size,
I915_BO_ALLOC_CONTIGUOUS);
if (IS_ERR(obj))
return PTR_ERR(obj);
@@ -321,14 +333,16 @@ static int igt_mock_contiguous(void *arg)
min = target;
target = total >> 1;
- /* Make sure we can still allocate all the fragmented space */
- obj = igt_object_create(mem, &objects, target, 0);
- if (IS_ERR(obj)) {
- err = PTR_ERR(obj);
- goto err_close_objects;
- }
+ if (!mem->is_range_manager) {
+ /* Make sure we can still allocate all the fragmented space */
+ obj = igt_object_create(mem, &objects, target, 0);
+ if (IS_ERR(obj)) {
+ err = PTR_ERR(obj);
+ goto err_close_objects;
+ }
- igt_object_release(obj);
+ igt_object_release(obj);
+ }
/*
* Even though we have enough free space, we don't have a big enough
@@ -348,7 +362,7 @@ static int igt_mock_contiguous(void *arg)
}
target >>= 1;
- } while (target >= mem->mm.chunk_size);
+ } while (target >= mem->chunk_size);
err_close_objects:
list_splice_tail(&holes, &objects);
@@ -368,7 +382,7 @@ static int igt_mock_splintered_region(void *arg)
/*
* Sanity check we can still allocate everything even if the
- * mm.max_order != mm.size. i.e our starting address space size is not a
+ * max_order != mm.size. i.e our starting address space size is not a
* power-of-two.
*/
@@ -377,17 +391,10 @@ static int igt_mock_splintered_region(void *arg)
if (IS_ERR(mem))
return PTR_ERR(mem);
- if (mem->mm.size != size) {
- pr_err("%s size mismatch(%llu != %llu)\n",
- __func__, mem->mm.size, size);
- err = -EINVAL;
- goto out_put;
- }
-
expected_order = get_order(rounddown_pow_of_two(size));
- if (mem->mm.max_order != expected_order) {
+ if (mem->max_order != expected_order) {
pr_err("%s order mismatch(%u != %u)\n",
- __func__, mem->mm.max_order, expected_order);
+ __func__, mem->max_order, expected_order);
err = -EINVAL;
goto out_put;
}
@@ -408,12 +415,15 @@ static int igt_mock_splintered_region(void *arg)
* sure that does indeed hold true.
*/
- obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS);
- if (!IS_ERR(obj)) {
- pr_err("%s too large contiguous allocation was not rejected\n",
- __func__);
- err = -EINVAL;
- goto out_close;
+ if (!mem->is_range_manager) {
+ obj = igt_object_create(mem, &objects, size,
+ I915_BO_ALLOC_CONTIGUOUS);
+ if (!IS_ERR(obj)) {
+ pr_err("%s too large contiguous allocation was not rejected\n",
+ __func__);
+ err = -EINVAL;
+ goto out_close;
+ }
}
obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size),
@@ -432,68 +442,6 @@ static int igt_mock_splintered_region(void *arg)
return err;
}
-#ifndef SZ_8G
-#define SZ_8G BIT_ULL(33)
-#endif
-
-static int igt_mock_max_segment(void *arg)
-{
- const unsigned int max_segment = i915_sg_segment_size();
- struct intel_memory_region *mem = arg;
- struct drm_i915_private *i915 = mem->i915;
- struct drm_i915_gem_object *obj;
- struct i915_buddy_block *block;
- struct scatterlist *sg;
- LIST_HEAD(objects);
- u64 size;
- int err = 0;
-
- /*
- * While we may create very large contiguous blocks, we may need
- * to break those down for consumption elsewhere. In particular,
- * dma-mapping with scatterlist elements have an implicit limit of
- * UINT_MAX on each element.
- */
-
- size = SZ_8G;
- mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
- if (IS_ERR(mem))
- return PTR_ERR(mem);
-
- obj = igt_object_create(mem, &objects, size, 0);
- if (IS_ERR(obj)) {
- err = PTR_ERR(obj);
- goto out_put;
- }
-
- size = 0;
- list_for_each_entry(block, &obj->mm.blocks, link) {
- if (i915_buddy_block_size(&mem->mm, block) > size)
- size = i915_buddy_block_size(&mem->mm, block);
- }
- if (size < max_segment) {
- pr_err("%s: Failed to create a huge contiguous block [> %u], largest block %lld\n",
- __func__, max_segment, size);
- err = -EINVAL;
- goto out_close;
- }
-
- for (sg = obj->mm.pages->sgl; sg; sg = sg_next(sg)) {
- if (sg->length > max_segment) {
- pr_err("%s: Created an oversized scatterlist entry, %u > %u\n",
- __func__, sg->length, max_segment);
- err = -EINVAL;
- goto out_close;
- }
- }
-
-out_close:
- close_objects(mem, &objects);
-out_put:
- intel_memory_region_put(mem);
- return err;
-}
-
static int igt_gpu_write_dw(struct intel_context *ce,
struct i915_vma *vma,
u32 dword,
@@ -1098,7 +1046,6 @@ int intel_memory_region_mock_selftests(void)
SUBTEST(igt_mock_fill),
SUBTEST(igt_mock_contiguous),
SUBTEST(igt_mock_splintered_region),
- SUBTEST(igt_mock_max_segment),
};
struct intel_memory_region *mem;
struct drm_i915_private *i915;
@@ -1,17 +1,53 @@
// SPDX-License-Identifier: MIT
/*
- * Copyright © 2019 Intel Corporation
+ * Copyright © 2019-2021 Intel Corporation
*/
+#include <linux/scatterlist.h>
+
#include "gem/i915_gem_region.h"
#include "intel_memory_region.h"
+#include "intel_region_ttm.h"
#include "mock_region.h"
+static void mock_region_put_pages(struct drm_i915_gem_object *obj,
+ struct sg_table *pages)
+{
+ intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+ sg_free_table(pages);
+ kfree(pages);
+}
+
+static int mock_region_get_pages(struct drm_i915_gem_object *obj)
+{
+ unsigned int flags;
+ struct sg_table *pages;
+
+ flags = I915_ALLOC_MIN_PAGE_SIZE;
+ if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
+ flags |= I915_ALLOC_CONTIGUOUS;
+
+ obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
+ obj->base.size,
+ flags);
+ if (IS_ERR(obj->mm.st_mm_node))
+ return PTR_ERR(obj->mm.st_mm_node);
+
+ pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+
+ __i915_gem_object_set_pages(obj, pages,
+ i915_sg_dma_page_sizes(pages->sgl));
+
+ return 0;
+}
+
static const struct drm_i915_gem_object_ops mock_region_obj_ops = {
.name = "mock-region",
- .get_pages = i915_gem_object_get_pages_buddy,
- .put_pages = i915_gem_object_put_pages_buddy,
+ .get_pages = mock_region_get_pages,
+ .put_pages = mock_region_put_pages,
.release = i915_gem_object_release_memory_region,
};
@@ -23,7 +59,7 @@ static int mock_object_init(struct intel_memory_region *mem,
static struct lock_class_key lock_class;
struct drm_i915_private *i915 = mem->i915;
- if (size > mem->mm.size)
+ if (size > resource_size(&mem->region))
return -E2BIG;
drm_gem_private_object_init(&i915->drm, &obj->base, size);
@@ -39,8 +75,8 @@ static int mock_object_init(struct intel_memory_region *mem,
}
static const struct intel_memory_region_ops mock_region_ops = {
- .init = intel_memory_region_init_buddy,
- .release = intel_memory_region_release_buddy,
+ .init = intel_region_ttm_init,
+ .release = intel_region_ttm_fini,
.init_object = mock_object_init,
};
@@ -52,5 +88,6 @@ mock_region_create(struct drm_i915_private *i915,
resource_size_t io_start)
{
return intel_memory_region_create(i915, start, size, min_page_size,
- io_start, &mock_region_ops);
+ io_start, INTEL_MEMORY_MOCK, 0,
+ &mock_region_ops);
}
@@ -125,55 +125,76 @@ static const struct ttm_resource_manager_func ttm_range_manager_func = {
.debug = ttm_range_man_debug
};
-int ttm_range_man_init(struct ttm_device *bdev,
- unsigned type, bool use_tt,
- unsigned long p_size)
+struct ttm_resource_manager *
+ttm_range_man_init_standalone(unsigned long size, bool use_tt)
{
struct ttm_resource_manager *man;
struct ttm_range_manager *rman;
rman = kzalloc(sizeof(*rman), GFP_KERNEL);
if (!rman)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
man = &rman->manager;
man->use_tt = use_tt;
man->func = &ttm_range_manager_func;
- ttm_resource_manager_init(man, p_size);
+ ttm_resource_manager_init(man, size);
- drm_mm_init(&rman->mm, 0, p_size);
+ drm_mm_init(&rman->mm, 0, size);
spin_lock_init(&rman->lock);
- ttm_set_driver_manager(bdev, type, &rman->manager);
+ return man;
+}
+EXPORT_SYMBOL(ttm_range_man_init_standalone);
+
+int ttm_range_man_init(struct ttm_device *bdev,
+ unsigned int type, bool use_tt,
+ unsigned long p_size)
+{
+ struct ttm_resource_manager *man;
+
+ man = ttm_range_man_init_standalone(p_size, use_tt);
+ if (IS_ERR(man))
+ return PTR_ERR(man);
+
ttm_resource_manager_set_used(man, true);
+ ttm_set_driver_manager(bdev, type, man);
+
return 0;
}
EXPORT_SYMBOL(ttm_range_man_init);
+void ttm_range_man_fini_standalone(struct ttm_resource_manager *man)
+{
+ struct ttm_range_manager *rman = to_range_manager(man);
+ struct drm_mm *mm = &rman->mm;
+
+ spin_lock(&rman->lock);
+ drm_mm_clean(mm);
+ drm_mm_takedown(mm);
+ spin_unlock(&rman->lock);
+
+ ttm_resource_manager_cleanup(man);
+ kfree(rman);
+}
+EXPORT_SYMBOL(ttm_range_man_fini_standalone);
+
int ttm_range_man_fini(struct ttm_device *bdev,
unsigned type)
{
struct ttm_resource_manager *man = ttm_manager_type(bdev, type);
- struct ttm_range_manager *rman = to_range_manager(man);
- struct drm_mm *mm = &rman->mm;
int ret;
ttm_resource_manager_set_used(man, false);
-
ret = ttm_resource_manager_evict_all(bdev, man);
if (ret)
return ret;
- spin_lock(&rman->lock);
- drm_mm_clean(mm);
- drm_mm_takedown(mm);
- spin_unlock(&rman->lock);
-
- ttm_resource_manager_cleanup(man);
ttm_set_driver_manager(bdev, type, NULL);
- kfree(rman);
+ ttm_range_man_fini_standalone(man);
+
return 0;
}
EXPORT_SYMBOL(ttm_range_man_fini);
@@ -321,6 +321,20 @@ int ttm_range_man_init(struct ttm_device *bdev,
unsigned type, bool use_tt,
unsigned long p_size);
+/**
+ * ttm_range_man_init_standalone - Initialize a ttm range manager without
+ * device interaction.
+ * @size: Size of the area to be managed in pages.
+ * @use_tt: The memory type requires tt backing.
+ *
+ * This function is intended for selftests. It initializes a range manager
+ * without any device interaction.
+ *
+ * Return: pointer to a range manager on success. Error pointer on failure.
+ */
+struct ttm_resource_manager *
+ttm_range_man_init_standalone(unsigned long size, bool use_tt);
+
/**
* ttm_range_man_fini
*
@@ -332,4 +346,13 @@ int ttm_range_man_init(struct ttm_device *bdev,
int ttm_range_man_fini(struct ttm_device *bdev,
unsigned type);
+/**
+ * ttm_range_man_fini_standalone
+ * @man: The range manager
+ *
+ * Tear down a range manager initialized with
+ * ttm_range_manager_init_standalone().
+ */
+void ttm_range_man_fini_standalone(struct ttm_resource_manager *man);
+
#endif
Temporarily remove the buddy allocator and related selftests and hook up the TTM range manager for i915 regions. In order to support some of the mock region-related selftests, we need to be able to initialize the TTM range-manager standalone without a struct ttm_device. Add two functions to allow that to the TTM api. Finally modify the mock region selftests somewhat to account for a fragmenting manager. Cc: Christian König <christian.koenig@amd.com> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> --- drivers/gpu/drm/i915/Kconfig | 1 + drivers/gpu/drm/i915/Makefile | 2 +- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 58 +- .../gpu/drm/i915/gem/i915_gem_object_types.h | 6 +- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 3 +- drivers/gpu/drm/i915/gem/i915_gem_region.c | 120 --- drivers/gpu/drm/i915/gem/i915_gem_region.h | 4 - drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 4 +- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 10 +- drivers/gpu/drm/i915/gem/i915_gem_stolen.h | 9 +- drivers/gpu/drm/i915/gt/intel_gt.c | 2 - drivers/gpu/drm/i915/gt/intel_region_lmem.c | 27 +- drivers/gpu/drm/i915/i915_buddy.c | 435 ---------- drivers/gpu/drm/i915/i915_buddy.h | 131 --- drivers/gpu/drm/i915/i915_drv.c | 8 + drivers/gpu/drm/i915/i915_drv.h | 7 +- drivers/gpu/drm/i915/i915_gem.c | 1 + drivers/gpu/drm/i915/i915_globals.c | 1 - drivers/gpu/drm/i915/i915_globals.h | 1 - drivers/gpu/drm/i915/i915_scatterlist.c | 70 ++ drivers/gpu/drm/i915/i915_scatterlist.h | 35 + drivers/gpu/drm/i915/intel_memory_region.c | 180 ++-- drivers/gpu/drm/i915/intel_memory_region.h | 44 +- drivers/gpu/drm/i915/intel_region_ttm.c | 246 ++++++ drivers/gpu/drm/i915/intel_region_ttm.h | 29 + drivers/gpu/drm/i915/selftests/i915_buddy.c | 789 ------------------ .../drm/i915/selftests/i915_mock_selftests.h | 1 - .../drm/i915/selftests/intel_memory_region.c | 133 +-- drivers/gpu/drm/i915/selftests/mock_region.c | 51 +- drivers/gpu/drm/ttm/ttm_range_manager.c | 55 +- include/drm/ttm/ttm_bo_driver.h | 23 + 31 files changed, 715 insertions(+), 1771 deletions(-) delete mode 100644 drivers/gpu/drm/i915/i915_buddy.c delete mode 100644 drivers/gpu/drm/i915/i915_buddy.h create mode 100644 drivers/gpu/drm/i915/intel_region_ttm.c create mode 100644 drivers/gpu/drm/i915/intel_region_ttm.h delete mode 100644 drivers/gpu/drm/i915/selftests/i915_buddy.c