* [Intel-gfx] [PATCH v2 1/6] drm/i915/ttm: add ttm_buddy_man
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 2/6] drm/i915/ttm: add i915_sg_from_buddy_resource Matthew Auld
` (5 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
Add back our standalone i915_buddy allocator and integrate it into a
ttm_resource_manager. This will plug into our ttm backend for managing
device local-memory in the next couple of patches.
v2(Thomas):
- Return -ENOSPC from the buddy; ttm expects this in order to
trigger eviction
- Drop the unnecessary inline
- bo->page_alignment is in page units
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/Makefile | 2 +
drivers/gpu/drm/i915/i915_buddy.c | 412 +++++++++
drivers/gpu/drm/i915/i915_buddy.h | 133 +++
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 248 ++++++
drivers/gpu/drm/i915/i915_ttm_buddy_manager.h | 56 ++
drivers/gpu/drm/i915/selftests/i915_buddy.c | 789 ++++++++++++++++++
6 files changed, 1640 insertions(+)
create mode 100644 drivers/gpu/drm/i915/i915_buddy.c
create mode 100644 drivers/gpu/drm/i915/i915_buddy.h
create mode 100644 drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
create mode 100644 drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
create mode 100644 drivers/gpu/drm/i915/selftests/i915_buddy.c
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index f57dfc74d6ce..6c84e96ab26a 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -162,6 +162,7 @@ gem-y += \
i915-y += \
$(gem-y) \
i915_active.o \
+ i915_buddy.o \
i915_cmd_parser.o \
i915_gem_evict.o \
i915_gem_gtt.o \
@@ -171,6 +172,7 @@ i915-y += \
i915_request.o \
i915_scheduler.o \
i915_trace_points.o \
+ i915_ttm_buddy_manager.o \
i915_vma.o \
intel_wopcm.o
diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
new file mode 100644
index 000000000000..29dd7d0310c1
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kmemleak.h>
+
+#include "i915_buddy.h"
+
+#include "i915_gem.h"
+#include "i915_utils.h"
+
+static struct i915_buddy_block *i915_block_alloc(struct i915_buddy_mm *mm,
+ 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(mm->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_mm *mm,
+ struct i915_buddy_block *block)
+{
+ kmem_cache_free(mm->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->slab_blocks = KMEM_CACHE(i915_buddy_block, SLAB_HWCACHE_ALIGN);
+ if (!mm->slab_blocks)
+ return -ENOMEM;
+
+ mm->free_list = kmalloc_array(mm->max_order + 1,
+ sizeof(struct list_head),
+ GFP_KERNEL);
+ if (!mm->free_list)
+ goto out_destroy_slab;
+
+ 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(mm, 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, mm->roots[i]);
+ kfree(mm->roots);
+out_free_list:
+ kfree(mm->free_list);
+out_destroy_slab:
+ kmem_cache_destroy(mm->slab_blocks);
+ 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, mm->roots[i]);
+ }
+
+ kfree(mm->roots);
+ kfree(mm->free_list);
+ kmem_cache_destroy(mm->slab_blocks);
+}
+
+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(mm, block, block_order, offset);
+ if (!block->left)
+ return -ENOMEM;
+
+ block->right = i915_block_alloc(mm, block, block_order,
+ offset + (mm->chunk_size << block_order));
+ if (!block->right) {
+ i915_block_free(mm, 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(mm, block);
+ i915_block_free(mm, 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
diff --git a/drivers/gpu/drm/i915/i915_buddy.h b/drivers/gpu/drm/i915/i915_buddy.h
new file mode 100644
index 000000000000..37f8c42071d1
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_buddy.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_BUDDY_H__
+#define __I915_BUDDY_H__
+
+#include <linux/bitops.h>
+#include <linux/list.h>
+#include <linux/slab.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 {
+ struct kmem_cache *slab_blocks;
+ /* 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
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
new file mode 100644
index 000000000000..fc7ad5c035b8
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/slab.h>
+
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_placement.h>
+
+#include "i915_ttm_buddy_manager.h"
+
+#include "i915_buddy.h"
+#include "i915_gem.h"
+
+struct i915_ttm_buddy_manager {
+ struct ttm_resource_manager manager;
+ struct i915_buddy_mm mm;
+ struct list_head reserved;
+ struct mutex lock;
+};
+
+static struct i915_ttm_buddy_manager *
+to_buddy_manager(struct ttm_resource_manager *man)
+{
+ return container_of(man, struct i915_ttm_buddy_manager, manager);
+}
+
+static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
+ struct ttm_buffer_object *bo,
+ const struct ttm_place *place,
+ struct ttm_resource **res)
+{
+ struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+ struct i915_ttm_buddy_resource *bman_res;
+ struct i915_buddy_mm *mm = &bman->mm;
+ unsigned long n_pages;
+ unsigned int min_order;
+ u64 min_page_size;
+ u64 size;
+ int err;
+
+ GEM_BUG_ON(place->fpfn || place->lpfn);
+
+ bman_res = kzalloc(sizeof(*bman_res), GFP_KERNEL);
+ if (!bman_res)
+ return -ENOMEM;
+
+ ttm_resource_init(bo, place, &bman_res->base);
+ INIT_LIST_HEAD(&bman_res->blocks);
+ bman_res->mm = mm;
+
+ GEM_BUG_ON(!bman_res->base.num_pages);
+ size = bman_res->base.num_pages << PAGE_SHIFT;
+
+ min_page_size = bo->page_alignment << PAGE_SHIFT;
+ GEM_BUG_ON(min_page_size < mm->chunk_size);
+ min_order = ilog2(min_page_size) - ilog2(mm->chunk_size);
+ if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
+ size = roundup_pow_of_two(size);
+ min_order = ilog2(size) - ilog2(mm->chunk_size);
+ }
+
+ if (size > mm->size) {
+ err = -E2BIG;
+ goto err_free_res;
+ }
+
+ n_pages = size >> ilog2(mm->chunk_size);
+
+ do {
+ struct i915_buddy_block *block;
+ unsigned int order;
+
+ order = fls(n_pages) - 1;
+ GEM_BUG_ON(order > mm->max_order);
+ GEM_BUG_ON(order < min_order);
+
+ do {
+ mutex_lock(&bman->lock);
+ block = i915_buddy_alloc(mm, order);
+ mutex_unlock(&bman->lock);
+ if (!IS_ERR(block))
+ break;
+
+ if (order-- == min_order) {
+ err = -ENOSPC;
+ goto err_free_blocks;
+ }
+ } while (1);
+
+ n_pages -= BIT(order);
+
+ list_add_tail(&block->link, &bman_res->blocks);
+
+ if (!n_pages)
+ break;
+ } while (1);
+
+ *res = &bman_res->base;
+ return 0;
+
+err_free_blocks:
+ mutex_lock(&bman->lock);
+ i915_buddy_free_list(mm, &bman_res->blocks);
+ mutex_unlock(&bman->lock);
+err_free_res:
+ kfree(bman_res);
+ return err;
+}
+
+static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man,
+ struct ttm_resource *res)
+{
+ struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
+ struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+
+ mutex_lock(&bman->lock);
+ i915_buddy_free_list(&bman->mm, &bman_res->blocks);
+ mutex_unlock(&bman->lock);
+
+ kfree(bman_res);
+}
+
+static const struct ttm_resource_manager_func i915_ttm_buddy_manager_func = {
+ .alloc = i915_ttm_buddy_man_alloc,
+ .free = i915_ttm_buddy_man_free,
+};
+
+
+/**
+ * i915_ttm_buddy_man_init - Setup buddy allocator based ttm manager
+ * @bdev: The ttm device
+ * @type: Memory type we want to manage
+ * @use_tt: Set use_tt for the manager
+ * @size: The size in bytes to manage
+ * @chunk_size: The minimum page size in bytes for our allocations i.e
+ * order-zero
+ *
+ * Note that the starting address is assumed to be zero here, since this
+ * simplifies keeping the property where allocated blocks having natural
+ * power-of-two alignment. So long as the real starting address is some large
+ * power-of-two, or naturally start from zero, then this should be fine. Also
+ * the &i915_ttm_buddy_man_reserve interface can be used to preserve alignment
+ * if say there is some unusable range from the start of the region. We can
+ * revisit this in the future and make the interface accept an actual starting
+ * offset and let it take care of the rest.
+ *
+ * Note that if the @size is not aligned to the @chunk_size then we perform the
+ * required rounding to get the usable size. The final size in pages can be
+ * taken from &ttm_resource_manager.size.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_init(struct ttm_device *bdev,
+ unsigned int type, bool use_tt,
+ u64 size, u64 chunk_size)
+{
+ struct ttm_resource_manager *man;
+ struct i915_ttm_buddy_manager *bman;
+ int err;
+
+ bman = kzalloc(sizeof(*bman), GFP_KERNEL);
+ if (!bman)
+ return -ENOMEM;
+
+ err = i915_buddy_init(&bman->mm, size, chunk_size);
+ if (err)
+ goto err_free_bman;
+
+ mutex_init(&bman->lock);
+ INIT_LIST_HEAD(&bman->reserved);
+
+ man = &bman->manager;
+ man->use_tt = use_tt;
+ man->func = &i915_ttm_buddy_manager_func;
+ ttm_resource_manager_init(man, bman->mm.size >> PAGE_SHIFT);
+
+ ttm_resource_manager_set_used(man, true);
+ ttm_set_driver_manager(bdev, type, man);
+
+ return 0;
+
+err_free_bman:
+ kfree(bman);
+ return err;
+}
+
+/**
+ * i915_ttm_buddy_man_fini - Destroy the buddy allocator ttm manager
+ * @bdev: The ttm device
+ * @type: Memory type we want to manage
+ *
+ * Note that if we reserved anything with &i915_ttm_buddy_man_reserve, this will
+ * also be freed for us here.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type)
+{
+ struct ttm_resource_manager *man = ttm_manager_type(bdev, type);
+ struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+ struct i915_buddy_mm *mm = &bman->mm;
+ int ret;
+
+ ttm_resource_manager_set_used(man, false);
+
+ ret = ttm_resource_manager_evict_all(bdev, man);
+ if (ret)
+ return ret;
+
+ ttm_set_driver_manager(bdev, type, NULL);
+
+ mutex_lock(&bman->lock);
+ i915_buddy_free_list(mm, &bman->reserved);
+ i915_buddy_fini(mm);
+ mutex_unlock(&bman->lock);
+
+ ttm_resource_manager_cleanup(man);
+ kfree(bman);
+
+ return 0;
+}
+
+/**
+ * i915_ttm_buddy_man_reserve - Reserve address range
+ * @man: The buddy allocator ttm manager
+ * @start: The offset in bytes, where the region start is assumed to be zero
+ * @size: The size in bytes
+ *
+ * Note that the starting address for the region is always assumed to be zero.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man,
+ u64 start, u64 size)
+{
+ struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
+ struct i915_buddy_mm *mm = &bman->mm;
+ int ret;
+
+ mutex_lock(&bman->lock);
+ ret = i915_buddy_alloc_range(mm, &bman->reserved, start, size);
+ mutex_unlock(&bman->lock);
+
+ return ret;
+}
+
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
new file mode 100644
index 000000000000..1d58e90548c9
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_TTM_BUDDY_MANAGER_H__
+#define __I915_TTM_BUDDY_MANAGER_H__
+
+#include <linux/list.h>
+#include <linux/types.h>
+
+#include <drm/ttm/ttm_resource.h>
+
+struct ttm_device;
+struct ttm_resource_manager;
+struct i915_buddy_mm;
+
+/**
+ * struct i915_ttm_buddy_resource
+ *
+ * @base: struct ttm_resource base class we extend
+ * @blocks: the list of struct i915_buddy_block for this resource/allocation
+ * @mm: the struct i915_buddy_mm for this resource
+ *
+ * Extends the struct ttm_resource to manage an address space allocation with
+ * one or more struct i915_buddy_block.
+ */
+struct i915_ttm_buddy_resource {
+ struct ttm_resource base;
+ struct list_head blocks;
+ struct i915_buddy_mm *mm;
+};
+
+/**
+ * to_ttm_buddy_resource
+ *
+ * @res: the resource to upcast
+ *
+ * Upcast the ttm_resource object into a i915_ttm_buddy_resource.
+ */
+static inline struct i915_ttm_buddy_resource *
+to_ttm_buddy_resource(struct ttm_resource *res)
+{
+ return container_of(res, struct i915_ttm_buddy_resource, base);
+}
+
+int i915_ttm_buddy_man_init(struct ttm_device *bdev,
+ unsigned type, bool use_tt,
+ u64 size, u64 chunk_size);
+int i915_ttm_buddy_man_fini(struct ttm_device *bdev,
+ unsigned int type);
+
+int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man,
+ u64 start, u64 size);
+
+#endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c
new file mode 100644
index 000000000000..f0f5c4df8dbc
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c
@@ -0,0 +1,789 @@
+// 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);
+}
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* [Intel-gfx] [PATCH v2 2/6] drm/i915/ttm: add i915_sg_from_buddy_resource
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 1/6] drm/i915/ttm: add ttm_buddy_man Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 3/6] drm/i915/ttm: Calculate the object placement at get_pages time Matthew Auld
` (4 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
We need to be able to build an sg table from our list of buddy blocks,
so that we can later plug this into our ttm backend, and replace our use
of the range manager.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/i915_scatterlist.c | 80 +++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_scatterlist.h | 5 ++
2 files changed, 85 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 69e9e6c3135e..0959fe3efbbb 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -6,6 +6,9 @@
#include "i915_scatterlist.h"
+#include "i915_buddy.h"
+#include "i915_ttm_buddy_manager.h"
+
#include <drm/drm_mm.h>
#include <linux/slab.h>
@@ -104,6 +107,83 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
return st;
}
+/**
+ * i915_sg_from_buddy_resource - Create an sg_table from a struct
+ * i915_buddy_block list
+ * @res: The i915_ttm_buddy_resource.
+ * @region_start: An offset to add to the dma addresses of the sg list.
+ *
+ * Create a struct sg_table, initializing it from struct i915_buddy_block list,
+ * 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_buddy_resource(struct ttm_resource *res,
+ u64 region_start)
+{
+ struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
+ struct i915_buddy_mm *mm = bman_res->mm;
+ const u64 size = res->num_pages << PAGE_SHIFT;
+ const u64 max_segment = UINT_MAX;
+ struct list_head *blocks = &bman_res->blocks;
+ struct i915_buddy_block *block;
+ struct scatterlist *sg;
+ struct sg_table *st;
+ resource_size_t prev_end;
+
+ GEM_BUG_ON(list_empty(blocks));
+
+ st = kmalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ return ERR_PTR(-ENOMEM);
+
+ if (sg_alloc_table(st, size >> PAGE_SHIFT, GFP_KERNEL)) {
+ kfree(st);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ sg = st->sgl;
+ st->nents = 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(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 = __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
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 5acca45ea981..b8bd5925b03f 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -14,6 +14,7 @@
#include "i915_gem.h"
struct drm_mm_node;
+struct ttm_resource;
/*
* Optimised SGL iterator for GEM objects
@@ -145,4 +146,8 @@ bool i915_sg_trim(struct sg_table *orig_st);
struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
u64 region_start);
+
+struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
+ u64 region_start);
+
#endif
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* [Intel-gfx] [PATCH v2 3/6] drm/i915/ttm: Calculate the object placement at get_pages time
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 1/6] drm/i915/ttm: add ttm_buddy_man Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 2/6] drm/i915/ttm: add i915_sg_from_buddy_resource Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 4/6] drm/i915/ttm: pass along the I915_BO_ALLOC_CONTIGUOUS Matthew Auld
` (3 subsequent siblings)
6 siblings, 0 replies; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
From: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Instead of relying on a static placement, calculate at get_pages() time.
This should work for LMEM regions and system for now. For stolen we need
to take preallocated range into account. That well be added later.
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 69 +++++++++++++++++++++----
drivers/gpu/drm/i915/intel_region_ttm.c | 8 ++-
drivers/gpu/drm/i915/intel_region_ttm.h | 2 +
3 files changed, 68 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 9dd6e4f69d53..73d52df8f2be 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -24,6 +24,11 @@
#define I915_TTM_PRIO_NO_PAGES 1
#define I915_TTM_PRIO_HAS_PAGES 2
+/*
+ * Size of struct ttm_place vector in on-stack struct ttm_placement allocs
+ */
+#define I915_TTM_MAX_PLACEMENTS 10
+
/**
* struct i915_ttm_tt - TTM page vector with additional private information
* @ttm: The base TTM page vector.
@@ -56,13 +61,6 @@ static const struct ttm_place lmem0_sys_placement_flags[] = {
}
};
-static struct ttm_placement i915_lmem0_placement = {
- .num_placement = 1,
- .placement = &lmem0_sys_placement_flags[0],
- .num_busy_placement = 1,
- .busy_placement = &lmem0_sys_placement_flags[0],
-};
-
static struct ttm_placement i915_sys_placement = {
.num_placement = 1,
.placement = &lmem0_sys_placement_flags[1],
@@ -72,6 +70,55 @@ static struct ttm_placement i915_sys_placement = {
static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj);
+static enum ttm_caching
+i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
+{
+ /*
+ * Objects only allowed in system get cached cpu-mappings.
+ * Other objects get WC mapping for now. Even if in system.
+ */
+ if (obj->mm.region->type == INTEL_MEMORY_SYSTEM &&
+ obj->mm.n_placements <= 1)
+ return ttm_cached;
+
+ return ttm_write_combined;
+}
+
+static void
+i915_ttm_place_from_region(const struct intel_memory_region *mr,
+ struct ttm_place *place)
+{
+ memset(place, 0, sizeof(*place));
+ place->mem_type = intel_region_to_ttm_type(mr);
+}
+
+static void
+i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
+ struct ttm_place *requested,
+ struct ttm_place *busy,
+ struct ttm_placement *placement)
+{
+ unsigned int i;
+ unsigned int num_allowed = obj->mm.n_placements;
+
+ placement->num_placement = 1;
+ i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
+ obj->mm.region, requested);
+
+ /* Cache this on object? */
+ placement->num_busy_placement = num_allowed;
+ for (i = 0; i < placement->num_busy_placement; ++i)
+ i915_ttm_place_from_region(obj->mm.placements[i], busy + i);
+
+ if (num_allowed == 0) {
+ *busy = *requested;
+ placement->num_busy_placement = 1;
+ }
+
+ placement->placement = requested;
+ placement->busy_placement = busy;
+}
+
static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
uint32_t page_flags)
{
@@ -89,7 +136,8 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
man->use_tt)
page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC;
- ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, ttm_write_combined);
+ ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
+ i915_ttm_select_tt_caching(obj));
if (ret) {
kfree(i915_tt);
return NULL;
@@ -414,10 +462,13 @@ static int i915_ttm_get_pages(struct drm_i915_gem_object *obj)
.no_wait_gpu = false,
};
struct sg_table *st;
+ struct ttm_place requested, busy[I915_TTM_MAX_PLACEMENTS];
+ struct ttm_placement placement;
int ret;
/* Move to the requested placement. */
- ret = ttm_bo_validate(bo, &i915_lmem0_placement, &ctx);
+ i915_ttm_placement_from_obj(obj, &requested, busy, &placement);
+ ret = ttm_bo_validate(bo, &placement, &ctx);
if (ret)
return ret == -ENOSPC ? -ENXIO : ret;
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 27fe0668d094..5a664f6cc93f 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -50,12 +50,16 @@ void intel_region_ttm_device_fini(struct drm_i915_private *dev_priv)
* 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 intel_region_to_ttm_type(const struct intel_memory_region *mem)
{
int type;
GEM_BUG_ON(mem->type != INTEL_MEMORY_LOCAL &&
- mem->type != INTEL_MEMORY_MOCK);
+ mem->type != INTEL_MEMORY_MOCK &&
+ mem->type != INTEL_MEMORY_SYSTEM);
+
+ if (mem->type == INTEL_MEMORY_SYSTEM)
+ return TTM_PL_SYSTEM;
type = mem->instance + TTM_PL_PRIV;
GEM_BUG_ON(type >= TTM_NUM_MEM_TYPES);
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
index e8cf830fda6f..5eedcc397bd5 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.h
+++ b/drivers/gpu/drm/i915/intel_region_ttm.h
@@ -22,6 +22,8 @@ int intel_region_ttm_init(struct intel_memory_region *mem);
void intel_region_ttm_fini(struct intel_memory_region *mem);
+int intel_region_to_ttm_type(const struct intel_memory_region *mem);
+
struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem,
struct ttm_resource *res);
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* [Intel-gfx] [PATCH v2 4/6] drm/i915/ttm: pass along the I915_BO_ALLOC_CONTIGUOUS
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
` (2 preceding siblings ...)
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 3/6] drm/i915/ttm: Calculate the object placement at get_pages time Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 9:48 ` Thomas Hellström
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man Matthew Auld
` (2 subsequent siblings)
6 siblings, 1 reply; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
Currently we just ignore the I915_BO_ALLOC_CONTIGUOUS flag, which is
fine since everything is already contiguous with the ttm range manager.
However in the next patch we want to switch over to the ttm buddy
manager, where allocations are by default not contiguous.
v2(Thomas):
- Forward ALLOC_CONTIG for all regions
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 73d52df8f2be..c612275c36c9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -86,10 +86,14 @@ i915_ttm_select_tt_caching(const struct drm_i915_gem_object *obj)
static void
i915_ttm_place_from_region(const struct intel_memory_region *mr,
- struct ttm_place *place)
+ struct ttm_place *place,
+ unsigned int flags)
{
memset(place, 0, sizeof(*place));
place->mem_type = intel_region_to_ttm_type(mr);
+
+ if (flags & I915_BO_ALLOC_CONTIGUOUS)
+ place->flags = TTM_PL_FLAG_CONTIGUOUS;
}
static void
@@ -100,15 +104,16 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
{
unsigned int i;
unsigned int num_allowed = obj->mm.n_placements;
+ unsigned int flags = obj->flags;
placement->num_placement = 1;
i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
- obj->mm.region, requested);
+ obj->mm.region, requested, flags);
/* Cache this on object? */
placement->num_busy_placement = num_allowed;
for (i = 0; i < placement->num_busy_placement; ++i)
- i915_ttm_place_from_region(obj->mm.placements[i], busy + i);
+ i915_ttm_place_from_region(obj->mm.placements[i], busy + i, flags);
if (num_allowed == 0) {
*busy = *requested;
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
` (3 preceding siblings ...)
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 4/6] drm/i915/ttm: pass along the I915_BO_ALLOC_CONTIGUOUS Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 9:53 ` Thomas Hellström
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 6/6] drm/i915/ttm: restore min_page_size behaviour Matthew Auld
2021-06-08 9:13 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for Add back the buddy allocator (rev2) Patchwork
6 siblings, 1 reply; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
Move back to the buddy allocator for managing device local memory, and
restore the lost mock selftests. Keep around the range manager related
bits, since we likely need this for managing stolen at some point. For
stolen we also don't need to reserve anything so no need to support a
generic reserve interface.
v2(Thomas):
- bo->page_alignment is in page units, not bytes
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 26 +--
drivers/gpu/drm/i915/intel_memory_region.c | 55 +-----
drivers/gpu/drm/i915/intel_memory_region.h | 17 --
drivers/gpu/drm/i915/intel_region_ttm.c | 100 +++--------
.../drm/i915/selftests/intel_memory_region.c | 170 ++++++++++++------
drivers/gpu/drm/i915/selftests/mock_region.c | 15 +-
6 files changed, 168 insertions(+), 215 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index c612275c36c9..5bf1d1945dd6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -181,11 +181,7 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
/* Will do for now. Our pinned objects are still on TTM's LRU lists */
- if (!i915_gem_object_evictable(obj))
- return false;
-
- /* This isn't valid with a buddy allocator */
- return ttm_bo_eviction_valuable(bo, place);
+ return i915_gem_object_evictable(obj);
}
static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
@@ -328,11 +324,15 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
struct ttm_resource_manager *man =
ttm_manager_type(bo->bdev, res->mem_type);
+ struct intel_memory_region *mr = obj->mm.region;
if (man->use_tt)
return i915_ttm_tt_get_st(bo->ttm);
- return intel_region_ttm_node_to_st(obj->mm.region, res->mm_node);
+ if (mr->is_range_manager)
+ return intel_region_ttm_node_to_st(mr, res);
+ else
+ return i915_sg_from_buddy_resource(res, mr->region.start);
}
static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
@@ -657,20 +657,8 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
static struct lock_class_key lock_class;
struct drm_i915_private *i915 = mem->i915;
enum ttm_bo_type bo_type;
- size_t alignment = 0;
int ret;
- /* Adjust alignment to GPU- and CPU huge page sizes. */
-
- if (mem->is_range_manager) {
- if (size >= SZ_1G)
- alignment = SZ_1G >> PAGE_SHIFT;
- else if (size >= SZ_2M)
- alignment = SZ_2M >> PAGE_SHIFT;
- else if (size >= SZ_64K)
- alignment = SZ_64K >> PAGE_SHIFT;
- }
-
drm_gem_private_object_init(&i915->drm, &obj->base, size);
i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags);
i915_gem_object_init_memory_region(obj, mem);
@@ -692,7 +680,7 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
*/
obj->base.vma_node.driver_private = i915_gem_to_ttm(obj);
ret = ttm_bo_init(&i915->bdev, i915_gem_to_ttm(obj), size,
- bo_type, &i915_sys_placement, alignment,
+ bo_type, &i915_sys_placement, 1,
true, NULL, NULL, i915_ttm_bo_destroy);
if (!ret)
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 12fb5423fd5e..df59f884d37c 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -5,6 +5,7 @@
#include "intel_memory_region.h"
#include "i915_drv.h"
+#include "i915_ttm_buddy_manager.h"
static const struct {
u16 class;
@@ -28,11 +29,6 @@ static const struct {
},
};
-struct intel_region_reserve {
- struct list_head link;
- struct ttm_resource *res;
-};
-
struct intel_memory_region *
intel_memory_region_lookup(struct drm_i915_private *i915,
u16 class, u16 instance)
@@ -63,27 +59,6 @@ intel_memory_region_by_type(struct drm_i915_private *i915,
return NULL;
}
-/**
- * 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 intel_region_reserve *reserve, *next;
-
- if (!mem->priv_ops || !mem->priv_ops->free)
- return;
-
- mutex_lock(&mem->mm_lock);
- list_for_each_entry_safe(reserve, next, &mem->reserved, link) {
- list_del(&reserve->link);
- mem->priv_ops->free(mem, reserve->res);
- kfree(reserve);
- }
- mutex_unlock(&mem->mm_lock);
-}
-
/**
* intel_memory_region_reserve - Reserve a memory range
* @mem: The region for which we want to reserve a range.
@@ -96,28 +71,11 @@ int intel_memory_region_reserve(struct intel_memory_region *mem,
resource_size_t offset,
resource_size_t size)
{
- int ret;
- struct intel_region_reserve *reserve;
-
- if (!mem->priv_ops || !mem->priv_ops->reserve)
- return -EINVAL;
-
- reserve = kzalloc(sizeof(*reserve), GFP_KERNEL);
- if (!reserve)
- return -ENOMEM;
+ struct ttm_resource_manager *man = mem->region_private;
- reserve->res = mem->priv_ops->reserve(mem, offset, size);
- if (IS_ERR(reserve->res)) {
- ret = PTR_ERR(reserve->res);
- kfree(reserve);
- return ret;
- }
-
- mutex_lock(&mem->mm_lock);
- list_add_tail(&reserve->link, &mem->reserved);
- mutex_unlock(&mem->mm_lock);
+ GEM_BUG_ON(mem->is_range_manager);
- return 0;
+ return i915_ttm_buddy_man_reserve(man, offset, size);
}
struct intel_memory_region *
@@ -149,9 +107,6 @@ intel_memory_region_create(struct drm_i915_private *i915,
mutex_init(&mem->objects.lock);
INIT_LIST_HEAD(&mem->objects.list);
- INIT_LIST_HEAD(&mem->reserved);
-
- mutex_init(&mem->mm_lock);
if (ops->init) {
err = ops->init(mem);
@@ -182,11 +137,9 @@ 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);
- mutex_destroy(&mem->mm_lock);
mutex_destroy(&mem->objects.lock);
kfree(mem);
}
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index c7e635d62e1a..b04fb22726d9 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -59,19 +59,10 @@ struct intel_memory_region_ops {
unsigned int flags);
};
-struct intel_memory_region_private_ops {
- struct ttm_resource *(*reserve)(struct intel_memory_region *mem,
- resource_size_t offset,
- resource_size_t size);
- void (*free)(struct intel_memory_region *mem,
- struct ttm_resource *res);
-};
-
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;
@@ -79,8 +70,6 @@ struct intel_memory_region {
/* For fake LMEM */
struct drm_mm_node fake_mappable;
- struct mutex mm_lock;
-
struct kref kref;
resource_size_t io_start;
@@ -94,8 +83,6 @@ struct intel_memory_region {
char name[16];
bool private; /* not for userspace */
- struct list_head reserved;
-
dma_addr_t remap_addr;
struct {
@@ -103,8 +90,6 @@ struct intel_memory_region {
struct list_head list;
} objects;
- size_t chunk_size;
- unsigned int max_order;
bool is_range_manager;
void *region_private;
@@ -138,8 +123,6 @@ __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);
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 5a664f6cc93f..23a1336d2335 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -8,6 +8,7 @@
#include "i915_drv.h"
#include "i915_scatterlist.h"
+#include "i915_ttm_buddy_manager.h"
#include "intel_region_ttm.h"
@@ -67,72 +68,17 @@ int intel_region_to_ttm_type(const struct intel_memory_region *mem)
return type;
}
-static struct ttm_resource *
-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_buffer_object mock_bo = {};
- struct ttm_resource *res;
- 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);
- mock_bo.base.size = size;
- ret = man->func->alloc(man, &mock_bo, &place, &res);
- if (ret == -ENOSPC)
- ret = -ENXIO;
-
- return ret ? ERR_PTR(ret) : res;
-}
-
-/**
- * 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,
- struct ttm_resource *res)
-{
- struct ttm_resource_manager *man = mem->region_private;
-
- 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,
-};
-
int intel_region_ttm_init(struct intel_memory_region *mem)
{
struct ttm_device *bdev = &mem->i915->bdev;
int mem_type = intel_region_to_ttm_type(mem);
int ret;
- ret = ttm_range_man_init(bdev, mem_type, false,
- resource_size(&mem->region) >> PAGE_SHIFT);
+ ret = i915_ttm_buddy_man_init(bdev, mem_type, false,
+ resource_size(&mem->region), PAGE_SIZE);
if (ret)
return ret;
- 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 = ttm_manager_type(bdev, mem_type);
return 0;
@@ -150,8 +96,8 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
{
int ret;
- ret = ttm_range_man_fini(&mem->i915->bdev,
- intel_region_to_ttm_type(mem));
+ ret = i915_ttm_buddy_man_fini(&mem->i915->bdev,
+ intel_region_to_ttm_type(mem));
GEM_WARN_ON(ret);
mem->region_private = NULL;
}
@@ -206,25 +152,33 @@ intel_region_ttm_node_alloc(struct intel_memory_region *mem,
struct ttm_resource *res;
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.
- */
mock_bo.base.size = size;
-
- 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;
- }
+ mock_bo.page_alignment = 1;
+ place.flags = flags;
ret = man->func->alloc(man, &mock_bo, &place, &res);
if (ret == -ENOSPC)
ret = -ENXIO;
return ret ? ERR_PTR(ret) : res;
}
+
#endif
+
+/**
+ * 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.
+ */
+void intel_region_ttm_node_free(struct intel_memory_region *mem,
+ struct ttm_resource *res)
+{
+ struct ttm_resource_manager *man = mem->region_private;
+
+ man->func->free(man, res);
+}
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index c85d516b85cd..dc23d699ecb5 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -20,7 +20,9 @@
#include "gem/selftests/mock_context.h"
#include "gt/intel_engine_user.h"
#include "gt/intel_gt.h"
+#include "i915_buddy.h"
#include "i915_memcpy.h"
+#include "i915_ttm_buddy_manager.h"
#include "selftests/igt_flush_test.h"
#include "selftests/i915_random.h"
@@ -57,10 +59,9 @@ static int igt_mock_fill(void *arg)
LIST_HEAD(objects);
int err = 0;
- page_size = mem->chunk_size;
+ page_size = PAGE_SIZE;
+ max_pages = div64_u64(total, page_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;
@@ -86,11 +87,6 @@ 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;
@@ -157,6 +153,7 @@ static bool is_contiguous(struct drm_i915_gem_object *obj)
static int igt_mock_reserve(void *arg)
{
struct intel_memory_region *mem = arg;
+ struct drm_i915_private *i915 = mem->i915;
resource_size_t avail = resource_size(&mem->region);
struct drm_i915_gem_object *obj;
const u32 chunk_size = SZ_32M;
@@ -166,16 +163,18 @@ static int igt_mock_reserve(void *arg)
LIST_HEAD(objects);
int err = 0;
- if (!list_empty(&mem->reserved)) {
- pr_err("%s region reserved list is not empty\n", __func__);
- return -EINVAL;
- }
-
count = avail / chunk_size;
order = i915_random_order(count, &prng);
if (!order)
return 0;
+ mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+ if (IS_ERR(mem)) {
+ pr_err("failed to create memory region\n");
+ err = PTR_ERR(mem);
+ goto out_close;
+ }
+
/* Reserve a bunch of ranges within the region */
for (i = 0; i < count; ++i) {
u64 start = order[i] * chunk_size;
@@ -205,18 +204,12 @@ 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 (mem->is_range_manager &&
- size > mem->chunk_size) {
- size >>= 1;
- goto retry;
- }
+ if (PTR_ERR(obj) == -ENXIO)
break;
- }
+
err = PTR_ERR(obj);
goto out_close;
}
@@ -232,7 +225,7 @@ static int igt_mock_reserve(void *arg)
out_close:
kfree(order);
close_objects(mem, &objects);
- intel_memory_region_unreserve(mem);
+ intel_memory_region_put(mem);
return err;
}
@@ -252,7 +245,7 @@ static int igt_mock_contiguous(void *arg)
total = resource_size(&mem->region);
/* Min size */
- obj = igt_object_create(mem, &objects, mem->chunk_size,
+ obj = igt_object_create(mem, &objects, PAGE_SIZE,
I915_BO_ALLOC_CONTIGUOUS);
if (IS_ERR(obj))
return PTR_ERR(obj);
@@ -333,17 +326,15 @@ static int igt_mock_contiguous(void *arg)
min = target;
target = total >> 1;
- 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);
+ /* 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);
+
/*
* Even though we have enough free space, we don't have a big enough
* contiguous block. Make sure that holds true.
@@ -362,7 +353,7 @@ static int igt_mock_contiguous(void *arg)
}
target >>= 1;
- } while (target >= mem->chunk_size);
+ } while (target >= PAGE_SIZE);
err_close_objects:
list_splice_tail(&holes, &objects);
@@ -374,7 +365,9 @@ static int igt_mock_splintered_region(void *arg)
{
struct intel_memory_region *mem = arg;
struct drm_i915_private *i915 = mem->i915;
+ struct i915_ttm_buddy_resource *res;
struct drm_i915_gem_object *obj;
+ struct i915_buddy_mm *mm;
unsigned int expected_order;
LIST_HEAD(objects);
u64 size;
@@ -382,7 +375,7 @@ static int igt_mock_splintered_region(void *arg)
/*
* Sanity check we can still allocate everything even if the
- * max_order != mm.size. i.e our starting address space size is not a
+ * mm.max_order != mm.size. i.e our starting address space size is not a
* power-of-two.
*/
@@ -391,20 +384,29 @@ static int igt_mock_splintered_region(void *arg)
if (IS_ERR(mem))
return PTR_ERR(mem);
- expected_order = get_order(rounddown_pow_of_two(size));
- if (mem->max_order != expected_order) {
- pr_err("%s order mismatch(%u != %u)\n",
- __func__, mem->max_order, expected_order);
- err = -EINVAL;
- goto out_put;
- }
-
obj = igt_object_create(mem, &objects, size, 0);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto out_close;
}
+ res = to_ttm_buddy_resource(obj->mm.st_mm_node);
+ mm = res->mm;
+ if (mm->size != size) {
+ pr_err("%s size mismatch(%llu != %llu)\n",
+ __func__, mm->size, size);
+ err = -EINVAL;
+ goto out_put;
+ }
+
+ expected_order = get_order(rounddown_pow_of_two(size));
+ if (mm->max_order != expected_order) {
+ pr_err("%s order mismatch(%u != %u)\n",
+ __func__, mm->max_order, expected_order);
+ err = -EINVAL;
+ goto out_put;
+ }
+
close_objects(mem, &objects);
/*
@@ -415,15 +417,12 @@ static int igt_mock_splintered_region(void *arg)
* sure that does indeed hold true.
*/
- 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, 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),
@@ -442,6 +441,74 @@ 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 i915_ttm_buddy_resource *res;
+ struct drm_i915_gem_object *obj;
+ struct i915_buddy_block *block;
+ struct i915_buddy_mm *mm;
+ struct list_head *blocks;
+ 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;
+ }
+
+ res = to_ttm_buddy_resource(obj->mm.st_mm_node);
+ blocks = &res->blocks;
+ mm = res->mm;
+ size = 0;
+ list_for_each_entry(block, blocks, link) {
+ if (i915_buddy_block_size(mm, block) > size)
+ size = i915_buddy_block_size(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,
@@ -1046,6 +1113,7 @@ 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;
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index eafc5a04975c..d3e4e6573cb9 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -3,6 +3,7 @@
* Copyright © 2019-2021 Intel Corporation
*/
+#include <drm/ttm/ttm_placement.h>
#include <linux/scatterlist.h>
#include <drm/ttm/ttm_placement.h>
@@ -25,10 +26,11 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
{
unsigned int flags;
struct sg_table *pages;
+ int err;
flags = I915_ALLOC_MIN_PAGE_SIZE;
if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
- flags |= I915_ALLOC_CONTIGUOUS;
+ flags |= TTM_PL_FLAG_CONTIGUOUS;
obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
obj->base.size,
@@ -36,15 +38,20 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
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);
+ pages = i915_sg_from_buddy_resource(obj->mm.st_mm_node,
+ obj->mm.region->region.start);
if (IS_ERR(pages)) {
- intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
- return PTR_ERR(pages);
+ err = PTR_ERR(pages);
+ goto err_free_mm_node;
}
__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
return 0;
+
+err_free_mm_node:
+ intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+ return err;
}
static const struct drm_i915_gem_object_ops mock_region_obj_ops = {
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man Matthew Auld
@ 2021-06-08 9:53 ` Thomas Hellström
2021-06-08 10:08 ` Matthew Auld
0 siblings, 1 reply; 13+ messages in thread
From: Thomas Hellström @ 2021-06-08 9:53 UTC (permalink / raw)
To: Matthew Auld, intel-gfx; +Cc: dri-devel
On 6/8/21 10:44 AM, Matthew Auld wrote:
> Move back to the buddy allocator for managing device local memory, and
> restore the lost mock selftests. Keep around the range manager related
> bits, since we likely need this for managing stolen at some point. For
> stolen we also don't need to reserve anything so no need to support a
> generic reserve interface.
>
> v2(Thomas):
> - bo->page_alignment is in page units, not bytes
>
> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 26 +--
> drivers/gpu/drm/i915/intel_memory_region.c | 55 +-----
> drivers/gpu/drm/i915/intel_memory_region.h | 17 --
> drivers/gpu/drm/i915/intel_region_ttm.c | 100 +++--------
> .../drm/i915/selftests/intel_memory_region.c | 170 ++++++++++++------
> drivers/gpu/drm/i915/selftests/mock_region.c | 15 +-
> 6 files changed, 168 insertions(+), 215 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> index c612275c36c9..5bf1d1945dd6 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> @@ -181,11 +181,7 @@ static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
> struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
>
> /* Will do for now. Our pinned objects are still on TTM's LRU lists */
> - if (!i915_gem_object_evictable(obj))
> - return false;
> -
> - /* This isn't valid with a buddy allocator */
> - return ttm_bo_eviction_valuable(bo, place);
> + return i915_gem_object_evictable(obj);
> }
>
> static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
> @@ -328,11 +324,15 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
> struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
> struct ttm_resource_manager *man =
> ttm_manager_type(bo->bdev, res->mem_type);
> + struct intel_memory_region *mr = obj->mm.region;
>
> if (man->use_tt)
> return i915_ttm_tt_get_st(bo->ttm);
>
> - return intel_region_ttm_node_to_st(obj->mm.region, res->mm_node);
> + if (mr->is_range_manager)
Did you look at moving this test into intel_region_ttm_node_to_st())
> + return intel_region_ttm_node_to_st(mr, res);
> + else
> + return i915_sg_from_buddy_resource(res, mr->region.start);
> }
Thanks,
Thomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man
2021-06-08 9:53 ` Thomas Hellström
@ 2021-06-08 10:08 ` Matthew Auld
2021-06-08 10:14 ` Thomas Hellström
0 siblings, 1 reply; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 10:08 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx; +Cc: dri-devel
On 08/06/2021 10:53, Thomas Hellström wrote:
>
> On 6/8/21 10:44 AM, Matthew Auld wrote:
>> Move back to the buddy allocator for managing device local memory, and
>> restore the lost mock selftests. Keep around the range manager related
>> bits, since we likely need this for managing stolen at some point. For
>> stolen we also don't need to reserve anything so no need to support a
>> generic reserve interface.
>>
>> v2(Thomas):
>> - bo->page_alignment is in page units, not bytes
>>
>> Signed-off-by: Matthew Auld <matthew.auld@intel.com>
>> Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>> ---
>> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 26 +--
>> drivers/gpu/drm/i915/intel_memory_region.c | 55 +-----
>> drivers/gpu/drm/i915/intel_memory_region.h | 17 --
>> drivers/gpu/drm/i915/intel_region_ttm.c | 100 +++--------
>> .../drm/i915/selftests/intel_memory_region.c | 170 ++++++++++++------
>> drivers/gpu/drm/i915/selftests/mock_region.c | 15 +-
>> 6 files changed, 168 insertions(+), 215 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>> b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>> index c612275c36c9..5bf1d1945dd6 100644
>> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>> @@ -181,11 +181,7 @@ static bool i915_ttm_eviction_valuable(struct
>> ttm_buffer_object *bo,
>> struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
>> /* Will do for now. Our pinned objects are still on TTM's LRU
>> lists */
>> - if (!i915_gem_object_evictable(obj))
>> - return false;
>> -
>> - /* This isn't valid with a buddy allocator */
>> - return ttm_bo_eviction_valuable(bo, place);
>> + return i915_gem_object_evictable(obj);
>> }
>> static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
>> @@ -328,11 +324,15 @@ i915_ttm_resource_get_st(struct
>> drm_i915_gem_object *obj,
>> struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
>> struct ttm_resource_manager *man =
>> ttm_manager_type(bo->bdev, res->mem_type);
>> + struct intel_memory_region *mr = obj->mm.region;
>> if (man->use_tt)
>> return i915_ttm_tt_get_st(bo->ttm);
>> - return intel_region_ttm_node_to_st(obj->mm.region, res->mm_node);
>> + if (mr->is_range_manager)
>
> Did you look at moving this test into intel_region_ttm_node_to_st())
I guess I didn't like the _node since that seems to suggest drm_mm_node
to me.
What about something like:
i915_ttm_resource_to_st(res, mr)
intel_region_ttm_resource_to_st(mr, res)
?
>
>> + return intel_region_ttm_node_to_st(mr, res);
>> + else
>> + return i915_sg_from_buddy_resource(res, mr->region.start);
>> }
>
> Thanks,
>
> Thomas
>
>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man
2021-06-08 10:08 ` Matthew Auld
@ 2021-06-08 10:14 ` Thomas Hellström
0 siblings, 0 replies; 13+ messages in thread
From: Thomas Hellström @ 2021-06-08 10:14 UTC (permalink / raw)
To: Matthew Auld, intel-gfx; +Cc: dri-devel
On Tue, 2021-06-08 at 11:08 +0100, Matthew Auld wrote:
> On 08/06/2021 10:53, Thomas Hellström wrote:
> >
> > On 6/8/21 10:44 AM, Matthew Auld wrote:
> > > Move back to the buddy allocator for managing device local
> > > memory, and
> > > restore the lost mock selftests. Keep around the range manager
> > > related
> > > bits, since we likely need this for managing stolen at some
> > > point. For
> > > stolen we also don't need to reserve anything so no need to
> > > support a
> > > generic reserve interface.
> > >
> > > v2(Thomas):
> > > - bo->page_alignment is in page units, not bytes
> > >
> > > Signed-off-by: Matthew Auld <matthew.auld@intel.com>
> > > Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > > Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > > ---
> > > drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 26 +--
> > > drivers/gpu/drm/i915/intel_memory_region.c | 55 +-----
> > > drivers/gpu/drm/i915/intel_memory_region.h | 17 --
> > > drivers/gpu/drm/i915/intel_region_ttm.c | 100 +++--------
> > > .../drm/i915/selftests/intel_memory_region.c | 170
> > > ++++++++++++------
> > > drivers/gpu/drm/i915/selftests/mock_region.c | 15 +-
> > > 6 files changed, 168 insertions(+), 215 deletions(-)
> > >
> > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > index c612275c36c9..5bf1d1945dd6 100644
> > > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > > @@ -181,11 +181,7 @@ static bool
> > > i915_ttm_eviction_valuable(struct
> > > ttm_buffer_object *bo,
> > > struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
> > > /* Will do for now. Our pinned objects are still on TTM's
> > > LRU
> > > lists */
> > > - if (!i915_gem_object_evictable(obj))
> > > - return false;
> > > -
> > > - /* This isn't valid with a buddy allocator */
> > > - return ttm_bo_eviction_valuable(bo, place);
> > > + return i915_gem_object_evictable(obj);
> > > }
> > > static void i915_ttm_evict_flags(struct ttm_buffer_object *bo,
> > > @@ -328,11 +324,15 @@ i915_ttm_resource_get_st(struct
> > > drm_i915_gem_object *obj,
> > > struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
> > > struct ttm_resource_manager *man =
> > > ttm_manager_type(bo->bdev, res->mem_type);
> > > + struct intel_memory_region *mr = obj->mm.region;
> > > if (man->use_tt)
> > > return i915_ttm_tt_get_st(bo->ttm);
> > > - return intel_region_ttm_node_to_st(obj->mm.region, res-
> > > >mm_node);
> > > + if (mr->is_range_manager)
> >
> > Did you look at moving this test into
> > intel_region_ttm_node_to_st())
>
> I guess I didn't like the _node since that seems to suggest
> drm_mm_node
> to me.
>
> What about something like:
> i915_ttm_resource_to_st(res, mr)
> intel_region_ttm_resource_to_st(mr, res)
intel_region_ttm_resource_to_st() would be nice I think. I think it
would be nice if the region ttm code could hide the manager selection.
/Thomas
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 13+ messages in thread
* [Intel-gfx] [PATCH v2 6/6] drm/i915/ttm: restore min_page_size behaviour
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
` (4 preceding siblings ...)
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 5/6] drm/i915/ttm: switch over to ttm_buddy_man Matthew Auld
@ 2021-06-08 8:44 ` Matthew Auld
2021-06-08 9:49 ` Thomas Hellström
2021-06-08 9:13 ` [Intel-gfx] ✗ Fi.CI.BUILD: failure for Add back the buddy allocator (rev2) Patchwork
6 siblings, 1 reply; 13+ messages in thread
From: Matthew Auld @ 2021-06-08 8:44 UTC (permalink / raw)
To: intel-gfx; +Cc: Thomas Hellström, dri-devel
We now have bo->page_alignment which perfectly describes what we need if
we have min page size restrictions for lmem. We can also drop the flag
here, since this is the default behaviour for all objects.
v2(Thomas):
- bo->page_alignment is in page units
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 4 ++--
drivers/gpu/drm/i915/intel_memory_region.h | 3 +--
drivers/gpu/drm/i915/intel_region_ttm.c | 2 +-
drivers/gpu/drm/i915/selftests/mock_region.c | 2 +-
4 files changed, 5 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 5bf1d1945dd6..3df73c79aa19 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -680,9 +680,9 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
*/
obj->base.vma_node.driver_private = i915_gem_to_ttm(obj);
ret = ttm_bo_init(&i915->bdev, i915_gem_to_ttm(obj), size,
- bo_type, &i915_sys_placement, 1,
+ bo_type, &i915_sys_placement,
+ mem->min_page_size >> PAGE_SHIFT,
true, NULL, NULL, i915_ttm_bo_destroy);
-
if (!ret)
obj->ttm.created = true;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index b04fb22726d9..2be8433d373a 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -40,8 +40,7 @@ enum intel_region_id {
#define REGION_STOLEN_SMEM BIT(INTEL_REGION_STOLEN_SMEM)
#define REGION_STOLEN_LMEM BIT(INTEL_REGION_STOLEN_LMEM)
-#define I915_ALLOC_MIN_PAGE_SIZE BIT(0)
-#define I915_ALLOC_CONTIGUOUS BIT(1)
+#define I915_ALLOC_CONTIGUOUS BIT(0)
#define for_each_memory_region(mr, i915, id) \
for (id = 0; id < ARRAY_SIZE((i915)->mm.regions); id++) \
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 23a1336d2335..ad43ca90a46b 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -153,7 +153,7 @@ intel_region_ttm_node_alloc(struct intel_memory_region *mem,
int ret;
mock_bo.base.size = size;
- mock_bo.page_alignment = 1;
+ mock_bo.page_alignment = mem->min_page_size >> PAGE_SHIFT;
place.flags = flags;
ret = man->func->alloc(man, &mock_bo, &place, &res);
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index d3e4e6573cb9..6ce0f9dacad7 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -28,7 +28,7 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
struct sg_table *pages;
int err;
- flags = I915_ALLOC_MIN_PAGE_SIZE;
+ flags = 0;
if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
flags |= TTM_PL_FLAG_CONTIGUOUS;
--
2.26.3
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 13+ messages in thread* [Intel-gfx] ✗ Fi.CI.BUILD: failure for Add back the buddy allocator (rev2)
2021-06-08 8:44 [Intel-gfx] [PATCH v2 0/6] Add back the buddy allocator Matthew Auld
` (5 preceding siblings ...)
2021-06-08 8:44 ` [Intel-gfx] [PATCH v2 6/6] drm/i915/ttm: restore min_page_size behaviour Matthew Auld
@ 2021-06-08 9:13 ` Patchwork
6 siblings, 0 replies; 13+ messages in thread
From: Patchwork @ 2021-06-08 9:13 UTC (permalink / raw)
To: Matthew Auld; +Cc: intel-gfx
== Series Details ==
Series: Add back the buddy allocator (rev2)
URL : https://patchwork.freedesktop.org/series/91110/
State : failure
== Summary ==
Applying: drm/i915/ttm: add ttm_buddy_man
Applying: drm/i915/ttm: add i915_sg_from_buddy_resource
Applying: drm/i915/ttm: Calculate the object placement at get_pages time
error: sha1 information is lacking or useless (drivers/gpu/drm/i915/gem/i915_gem_ttm.c).
error: could not build fake ancestor
hint: Use 'git am --show-current-patch=diff' to see the failed patch
Patch failed at 0003 drm/i915/ttm: Calculate the object placement at get_pages time
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 13+ messages in thread