[PATCH] drm/i915/ttm: remove shmem memory region and gem object backend
Adrian Larumbe
adrian.larumbe at collabora.com
Thu Mar 3 03:20:52 UTC 2022
The goal is to completely replace the shmem API for the SMEM memory
region with the TTM backend for GEM objects.
Signed-off-by: Adrian Larumbe <adrian.larumbe at collabora.com>
---
drivers/gpu/drm/i915/display/intel_fbdev.c | 6 +-
drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 2 +-
drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 26 --
drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 4 -
drivers/gpu/drm/i915/gem/i915_gem_object.c | 39 +-
drivers/gpu/drm/i915/gem/i915_gem_object.h | 21 +-
drivers/gpu/drm/i915/gem/i915_gem_phys.c | 2 +-
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 435 ------------------
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 25 +
drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c | 2 +-
.../gpu/drm/i915/gem/selftests/huge_pages.c | 6 +-
.../i915/gem/selftests/i915_gem_client_blt.c | 2 +-
.../drm/i915/gem/selftests/i915_gem_dmabuf.c | 6 +-
.../drm/i915/gem/selftests/i915_gem_object.c | 2 +-
.../drm/i915/gem/selftests/i915_gem_phys.c | 2 +-
drivers/gpu/drm/i915/gt/intel_lrc.c | 4 +-
.../gpu/drm/i915/gt/intel_ring_submission.c | 2 +-
drivers/gpu/drm/i915/gt/shmem_utils.c | 6 -
drivers/gpu/drm/i915/gt/uc/intel_guc.c | 2 +-
drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 9 +-
drivers/gpu/drm/i915/gvt/cmd_parser.c | 4 +-
drivers/gpu/drm/i915/i915_perf.c | 4 +-
drivers/gpu/drm/i915/intel_memory_region.c | 6 +-
drivers/gpu/drm/i915/intel_memory_region.h | 3 -
24 files changed, 97 insertions(+), 523 deletions(-)
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index fd5bc7acf08d..39ea2f80b079 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -171,7 +171,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
if (size * 2 < dev_priv->stolen_usable_size)
obj = i915_gem_object_create_stolen(dev_priv, size);
if (IS_ERR(obj))
- obj = i915_gem_object_create_shmem(dev_priv, size);
+ obj = i915_gem_object_create_smem(dev_priv, size);
}
if (IS_ERR(obj)) {
@@ -298,7 +298,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
* If the object is stolen however, it will be full of whatever
* garbage was left in there.
*/
- if (!i915_gem_object_is_shmem(vma->obj) && !prealloc)
+ if (!i915_gem_object_is_smem(vma->obj) && !prealloc)
memset_io(info->screen_base, 0, info->screen_size);
/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -655,7 +655,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
* full of whatever garbage was left in there.
*/
if (state == FBINFO_STATE_RUNNING &&
- !i915_gem_object_is_shmem(intel_fb_obj(&ifbdev->fb->base)))
+ !i915_gem_object_is_smem(intel_fb_obj(&ifbdev->fb->base)))
memset_io(info->screen_base, 0, info->screen_size);
drm_fb_helper_set_suspend(&ifbdev->helper, state);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index ce91b23385cf..c1c4e5774087 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -18,7 +18,7 @@ struct clflush {
struct drm_i915_gem_object *obj;
};
-static void __do_clflush(struct drm_i915_gem_object *obj)
+static void __do_clflush(const struct drm_i915_gem_object *obj)
{
GEM_BUG_ON(!i915_gem_object_has_pages(obj));
drm_clflush_sg(obj->mm.pages);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 444f8268b9c5..b702876909af 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -104,32 +104,6 @@ __i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915,
size, page_size, flags);
}
-struct drm_i915_gem_object *
-i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
- const void *data, size_t size)
-{
- struct drm_i915_gem_object *obj;
- void *map;
-
- obj = i915_gem_object_create_lmem(i915,
- round_up(size, PAGE_SIZE),
- I915_BO_ALLOC_CONTIGUOUS);
- if (IS_ERR(obj))
- return obj;
-
- map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC);
- if (IS_ERR(map)) {
- i915_gem_object_put(obj);
- return map;
- }
-
- memcpy(map, data, size);
-
- i915_gem_object_unpin_map(obj);
-
- return obj;
-}
-
struct drm_i915_gem_object *
i915_gem_object_create_lmem(struct drm_i915_private *i915,
resource_size_t size,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
index 1b88ea13435c..4ee81fc66302 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -23,10 +23,6 @@ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
-struct drm_i915_gem_object *
-i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
- const void *data, size_t size);
-
struct drm_i915_gem_object *
__i915_gem_object_create_lmem_with_ps(struct drm_i915_private *i915,
resource_size_t size,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 2d593d573ef1..facf849609a0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -405,7 +405,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
queue_delayed_work(i915->wq, &i915->mm.free_work, 0);
}
-void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
+void __i915_gem_object_flush_frontbuffer(const struct drm_i915_gem_object *obj,
enum fb_op_origin origin)
{
struct intel_frontbuffer *front;
@@ -699,7 +699,7 @@ int i915_gem_object_migrate(struct drm_i915_gem_object *obj,
*
* Return: True if the object can be placed in @type. False otherwise.
*/
-bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj,
+bool i915_gem_object_placement_possible(const struct drm_i915_gem_object *obj,
enum intel_memory_type type)
{
unsigned int i;
@@ -813,6 +813,41 @@ int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj,
return 0;
}
+struct drm_i915_gem_object *
+i915_gem_object_create_fw(struct drm_i915_private *dev_priv,
+ const void *data, resource_size_t size)
+{
+ struct drm_i915_gem_object *obj;
+ void *map;
+
+ if (HAS_LMEM(dev_priv))
+ obj = i915_gem_object_create_lmem(dev_priv,
+ round_up(size, PAGE_SIZE),
+ I915_BO_ALLOC_CONTIGUOUS);
+ else
+ obj = i915_gem_object_create_smem(dev_priv,
+ round_up(size, PAGE_SIZE));
+ if (IS_ERR(obj))
+ return obj;
+
+ if (HAS_LMEM(dev_priv))
+ obj->flags |= I915_BO_ALLOC_PM_EARLY;
+ else
+ GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
+
+ map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC);
+ if (IS_ERR(map)) {
+ i915_gem_object_put(obj);
+ return map;
+ }
+
+ memcpy(map, data, size);
+
+ i915_gem_object_unpin_map(obj);
+
+ return obj;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/huge_gem_object.c"
#include "selftests/huge_pages.c"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 02c37fe4a535..04780c08a1a0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -62,18 +62,13 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
void __i915_gem_object_fini(struct drm_i915_gem_object *obj);
struct drm_i915_gem_object *
-i915_gem_object_create_shmem(struct drm_i915_private *i915,
+i915_gem_object_create_smem(struct drm_i915_private *i915,
resource_size_t size);
struct drm_i915_gem_object *
-i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
- const void *data, resource_size_t size);
-struct drm_i915_gem_object *
__i915_gem_object_create_user(struct drm_i915_private *i915, u64 size,
struct intel_memory_region **placements,
unsigned int n_placements);
-extern const struct drm_i915_gem_object_ops i915_gem_shmem_ops;
-
void __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
struct sg_table *pages,
bool needs_clflush);
@@ -423,7 +418,7 @@ i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
int i915_gem_object_pin_pages_unlocked(struct drm_i915_gem_object *obj);
static inline bool
-i915_gem_object_has_pages(struct drm_i915_gem_object *obj)
+i915_gem_object_has_pages(const struct drm_i915_gem_object *obj)
{
return !IS_ERR_OR_NULL(READ_ONCE(obj->mm.pages));
}
@@ -573,13 +568,13 @@ int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
unsigned int flags,
const struct i915_sched_attr *attr);
-void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
+void __i915_gem_object_flush_frontbuffer(const struct drm_i915_gem_object *obj,
enum fb_op_origin origin);
void __i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj,
enum fb_op_origin origin);
static inline void
-i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj,
+i915_gem_object_flush_frontbuffer(const struct drm_i915_gem_object *obj,
enum fb_op_origin origin)
{
if (unlikely(rcu_access_pointer(obj->frontbuffer)))
@@ -596,7 +591,7 @@ i915_gem_object_invalidate_frontbuffer(struct drm_i915_gem_object *obj,
int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, void *dst, int size);
-bool i915_gem_object_is_shmem(const struct drm_i915_gem_object *obj);
+bool i915_gem_object_is_smem(const struct drm_i915_gem_object *obj);
void __i915_gem_free_object_rcu(struct rcu_head *head);
@@ -618,9 +613,13 @@ bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj,
int i915_gem_object_wait_migration(struct drm_i915_gem_object *obj,
unsigned int flags);
-bool i915_gem_object_placement_possible(struct drm_i915_gem_object *obj,
+bool i915_gem_object_placement_possible(const struct drm_i915_gem_object *obj,
enum intel_memory_type type);
+struct drm_i915_gem_object *
+i915_gem_object_create_fw(struct drm_i915_private *dev_priv,
+ const void *data, resource_size_t size);
+
int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
size_t size, struct intel_memory_region *mr,
struct address_space *mapping,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index ca6faffcc496..61e676839727 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -225,7 +225,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
if (align > obj->base.size)
return -EINVAL;
- if (!i915_gem_object_is_shmem(obj))
+ if (!i915_gem_object_is_smem(obj))
return -EINVAL;
if (!i915_gem_object_has_struct_page(obj))
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 4efa821f3cb1..a4c189e84270 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -187,105 +187,6 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st,
return ret;
}
-static int shmem_get_pages(struct drm_i915_gem_object *obj)
-{
- struct drm_i915_private *i915 = to_i915(obj->base.dev);
- struct intel_memory_region *mem = obj->mm.region;
- struct address_space *mapping = obj->base.filp->f_mapping;
- const unsigned long page_count = obj->base.size / PAGE_SIZE;
- unsigned int max_segment = i915_sg_segment_size();
- struct sg_table *st;
- struct sgt_iter sgt_iter;
- struct page *page;
- int ret;
-
- /*
- * Assert that the object is not currently in any GPU domain. As it
- * wasn't in the GTT, there shouldn't be any way it could have been in
- * a GPU cache
- */
- GEM_BUG_ON(obj->read_domains & I915_GEM_GPU_DOMAINS);
- GEM_BUG_ON(obj->write_domain & I915_GEM_GPU_DOMAINS);
-
-rebuild_st:
- st = kmalloc(sizeof(*st), GFP_KERNEL);
- if (!st)
- return -ENOMEM;
-
- ret = shmem_sg_alloc_table(i915, st, obj->base.size, mem, mapping,
- max_segment);
- if (ret)
- goto err_st;
-
- ret = i915_gem_gtt_prepare_pages(obj, st);
- if (ret) {
- /*
- * DMA remapping failed? One possible cause is that
- * it could not reserve enough large entries, asking
- * for PAGE_SIZE chunks instead may be helpful.
- */
- if (max_segment > PAGE_SIZE) {
- for_each_sgt_page(page, sgt_iter, st)
- put_page(page);
- sg_free_table(st);
- kfree(st);
-
- max_segment = PAGE_SIZE;
- goto rebuild_st;
- } else {
- dev_warn(i915->drm.dev,
- "Failed to DMA remap %lu pages\n",
- page_count);
- goto err_pages;
- }
- }
-
- if (i915_gem_object_needs_bit17_swizzle(obj))
- i915_gem_object_do_bit_17_swizzle(obj, st);
-
- if (i915_gem_object_can_bypass_llc(obj))
- obj->cache_dirty = true;
-
- __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl));
-
- return 0;
-
-err_pages:
- shmem_sg_free_table(st, mapping, false, false);
- /*
- * shmemfs first checks if there is enough memory to allocate the page
- * and reports ENOSPC should there be insufficient, along with the usual
- * ENOMEM for a genuine allocation failure.
- *
- * We use ENOSPC in our driver to mean that we have run out of aperture
- * space and so want to translate the error from shmemfs back to our
- * usual understanding of ENOMEM.
- */
-err_st:
- if (ret == -ENOSPC)
- ret = -ENOMEM;
-
- kfree(st);
-
- return ret;
-}
-
-static int
-shmem_truncate(struct drm_i915_gem_object *obj)
-{
- /*
- * Our goal here is to return as much of the memory as
- * is possible back to the system as we are called from OOM.
- * To do this we must instruct the shmfs to drop all of its
- * backing pages, *now*.
- */
- shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
- obj->mm.madv = __I915_MADV_PURGED;
- obj->mm.pages = ERR_PTR(-EFAULT);
-
- return 0;
-}
-
void __shmem_writeback(size_t size, struct address_space *mapping)
{
struct writeback_control wbc = {
@@ -328,27 +229,6 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
}
}
-static void
-shmem_writeback(struct drm_i915_gem_object *obj)
-{
- __shmem_writeback(obj->base.size, obj->base.filp->f_mapping);
-}
-
-static int shmem_shrink(struct drm_i915_gem_object *obj, unsigned int flags)
-{
- switch (obj->mm.madv) {
- case I915_MADV_DONTNEED:
- return i915_gem_object_truncate(obj);
- case __I915_MADV_PURGED:
- return 0;
- }
-
- if (flags & I915_GEM_OBJECT_SHRINK_WRITEBACK)
- shmem_writeback(obj);
-
- return 0;
-}
-
void
__i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
struct sg_table *pages,
@@ -393,318 +273,3 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_
kfree(pages);
obj->mm.dirty = false;
}
-
-static void
-shmem_put_pages(struct drm_i915_gem_object *obj, struct sg_table *pages)
-{
- if (likely(i915_gem_object_has_struct_page(obj)))
- i915_gem_object_put_pages_shmem(obj, pages);
- else
- i915_gem_object_put_pages_phys(obj, pages);
-}
-
-static int
-shmem_pwrite(struct drm_i915_gem_object *obj,
- const struct drm_i915_gem_pwrite *arg)
-{
- struct address_space *mapping = obj->base.filp->f_mapping;
- char __user *user_data = u64_to_user_ptr(arg->data_ptr);
- u64 remain, offset;
- unsigned int pg;
-
- /* Caller already validated user args */
- GEM_BUG_ON(!access_ok(user_data, arg->size));
-
- if (!i915_gem_object_has_struct_page(obj))
- return i915_gem_object_pwrite_phys(obj, arg);
-
- /*
- * Before we instantiate/pin the backing store for our use, we
- * can prepopulate the shmemfs filp efficiently using a write into
- * the pagecache. We avoid the penalty of instantiating all the
- * pages, important if the user is just writing to a few and never
- * uses the object on the GPU, and using a direct write into shmemfs
- * allows it to avoid the cost of retrieving a page (either swapin
- * or clearing-before-use) before it is overwritten.
- */
- if (i915_gem_object_has_pages(obj))
- return -ENODEV;
-
- if (obj->mm.madv != I915_MADV_WILLNEED)
- return -EFAULT;
-
- /*
- * Before the pages are instantiated the object is treated as being
- * in the CPU domain. The pages will be clflushed as required before
- * use, and we can freely write into the pages directly. If userspace
- * races pwrite with any other operation; corruption will ensue -
- * that is userspace's prerogative!
- */
-
- remain = arg->size;
- offset = arg->offset;
- pg = offset_in_page(offset);
-
- do {
- unsigned int len, unwritten;
- struct page *page;
- void *data, *vaddr;
- int err;
- char c;
-
- len = PAGE_SIZE - pg;
- if (len > remain)
- len = remain;
-
- /* Prefault the user page to reduce potential recursion */
- err = __get_user(c, user_data);
- if (err)
- return err;
-
- err = __get_user(c, user_data + len - 1);
- if (err)
- return err;
-
- err = pagecache_write_begin(obj->base.filp, mapping,
- offset, len, 0,
- &page, &data);
- if (err < 0)
- return err;
-
- vaddr = kmap_atomic(page);
- unwritten = __copy_from_user_inatomic(vaddr + pg,
- user_data,
- len);
- kunmap_atomic(vaddr);
-
- err = pagecache_write_end(obj->base.filp, mapping,
- offset, len, len - unwritten,
- page, data);
- if (err < 0)
- return err;
-
- /* We don't handle -EFAULT, leave it to the caller to check */
- if (unwritten)
- return -ENODEV;
-
- remain -= len;
- user_data += len;
- offset += len;
- pg = 0;
- } while (remain);
-
- return 0;
-}
-
-static int
-shmem_pread(struct drm_i915_gem_object *obj,
- const struct drm_i915_gem_pread *arg)
-{
- if (!i915_gem_object_has_struct_page(obj))
- return i915_gem_object_pread_phys(obj, arg);
-
- return -ENODEV;
-}
-
-static void shmem_release(struct drm_i915_gem_object *obj)
-{
- if (i915_gem_object_has_struct_page(obj))
- i915_gem_object_release_memory_region(obj);
-
- fput(obj->base.filp);
-}
-
-const struct drm_i915_gem_object_ops i915_gem_shmem_ops = {
- .name = "i915_gem_object_shmem",
- .flags = I915_GEM_OBJECT_IS_SHRINKABLE,
-
- .get_pages = shmem_get_pages,
- .put_pages = shmem_put_pages,
- .truncate = shmem_truncate,
- .shrink = shmem_shrink,
-
- .pwrite = shmem_pwrite,
- .pread = shmem_pread,
-
- .release = shmem_release,
-};
-
-static int __create_shmem(struct drm_i915_private *i915,
- struct drm_gem_object *obj,
- resource_size_t size)
-{
- unsigned long flags = VM_NORESERVE;
- struct file *filp;
-
- drm_gem_private_object_init(&i915->drm, obj, size);
-
- if (i915->mm.gemfs)
- filp = shmem_file_setup_with_mnt(i915->mm.gemfs, "i915", size,
- flags);
- else
- filp = shmem_file_setup("i915", size, flags);
- if (IS_ERR(filp))
- return PTR_ERR(filp);
-
- obj->filp = filp;
- return 0;
-}
-
-static int shmem_object_init(struct intel_memory_region *mem,
- struct drm_i915_gem_object *obj,
- resource_size_t size,
- resource_size_t page_size,
- unsigned int flags)
-{
- static struct lock_class_key lock_class;
- struct drm_i915_private *i915 = mem->i915;
- struct address_space *mapping;
- unsigned int cache_level;
- gfp_t mask;
- int ret;
-
- ret = __create_shmem(i915, &obj->base, size);
- if (ret)
- return ret;
-
- mask = GFP_HIGHUSER | __GFP_RECLAIMABLE;
- if (IS_I965GM(i915) || IS_I965G(i915)) {
- /* 965gm cannot relocate objects above 4GiB. */
- mask &= ~__GFP_HIGHMEM;
- mask |= __GFP_DMA32;
- }
-
- mapping = obj->base.filp->f_mapping;
- mapping_set_gfp_mask(mapping, mask);
- GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
-
- i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0);
- obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
- obj->write_domain = I915_GEM_DOMAIN_CPU;
- obj->read_domains = I915_GEM_DOMAIN_CPU;
-
- if (HAS_LLC(i915))
- /* On some devices, we can have the GPU use the LLC (the CPU
- * cache) for about a 10% performance improvement
- * compared to uncached. Graphics requests other than
- * display scanout are coherent with the CPU in
- * accessing this cache. This means in this mode we
- * don't need to clflush on the CPU side, and on the
- * GPU side we only need to flush internal caches to
- * get data visible to the CPU.
- *
- * However, we maintain the display planes as UC, and so
- * need to rebind when first used as such.
- */
- cache_level = I915_CACHE_LLC;
- else
- cache_level = I915_CACHE_NONE;
-
- i915_gem_object_set_cache_coherency(obj, cache_level);
-
- i915_gem_object_init_memory_region(obj, mem);
-
- return 0;
-}
-
-struct drm_i915_gem_object *
-i915_gem_object_create_shmem(struct drm_i915_private *i915,
- resource_size_t size)
-{
- return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM],
- size, 0, 0);
-}
-
-/* Allocate a new GEM object and fill it with the supplied data */
-struct drm_i915_gem_object *
-i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
- const void *data, resource_size_t size)
-{
- struct drm_i915_gem_object *obj;
- struct file *file;
- resource_size_t offset;
- int err;
-
- GEM_WARN_ON(IS_DGFX(dev_priv));
- obj = i915_gem_object_create_shmem(dev_priv, round_up(size, PAGE_SIZE));
- if (IS_ERR(obj))
- return obj;
-
- GEM_BUG_ON(obj->write_domain != I915_GEM_DOMAIN_CPU);
-
- file = obj->base.filp;
- offset = 0;
- do {
- unsigned int len = min_t(typeof(size), size, PAGE_SIZE);
- struct page *page;
- void *pgdata, *vaddr;
-
- err = pagecache_write_begin(file, file->f_mapping,
- offset, len, 0,
- &page, &pgdata);
- if (err < 0)
- goto fail;
-
- vaddr = kmap(page);
- memcpy(vaddr, data, len);
- kunmap(page);
-
- err = pagecache_write_end(file, file->f_mapping,
- offset, len, len,
- page, pgdata);
- if (err < 0)
- goto fail;
-
- size -= len;
- data += len;
- offset += len;
- } while (size);
-
- return obj;
-
-fail:
- i915_gem_object_put(obj);
- return ERR_PTR(err);
-}
-
-static int init_shmem(struct intel_memory_region *mem)
-{
- int err;
-
- err = i915_gemfs_init(mem->i915);
- if (err) {
- DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n",
- err);
- }
-
- intel_memory_region_set_name(mem, "system");
-
- return 0; /* Don't error, we can simply fallback to the kernel mnt */
-}
-
-static int release_shmem(struct intel_memory_region *mem)
-{
- i915_gemfs_fini(mem->i915);
- return 0;
-}
-
-static const struct intel_memory_region_ops shmem_region_ops = {
- .init = init_shmem,
- .release = release_shmem,
- .init_object = shmem_object_init,
-};
-
-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);
-}
-
-bool i915_gem_object_is_shmem(const struct drm_i915_gem_object *obj)
-{
- return obj->ops == &i915_gem_shmem_ops;
-}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 8419096d4056..f47fb73afb5c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -1090,6 +1090,31 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
return 0;
}
+struct drm_i915_gem_object *
+i915_gem_object_create_smem(struct drm_i915_private *i915,
+ resource_size_t size)
+{
+ return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM],
+ size, 0, 0);
+}
+
+bool i915_gem_object_is_smem(const struct drm_i915_gem_object *obj)
+{
+ struct intel_memory_region *mr = READ_ONCE(obj->mm.region);
+
+#ifdef CONFIG_LOCKDEP
+ if (i915_gem_object_migratable(obj) &&
+ i915_gem_object_evictable(obj))
+ assert_object_held(obj);
+#endif
+
+ /* Review list of placements to make sure object isn't migratable */
+ if (i915_gem_object_placement_possible(obj, INTEL_MEMORY_LOCAL))
+ return false;
+
+ return mr && (mr->type == INTEL_MEMORY_SYSTEM);
+}
+
static const struct intel_memory_region_ops ttm_system_region_ops = {
.init_object = __i915_gem_ttm_object_init,
.release = intel_region_ttm_fini,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
index 9aad84059d56..5fdbc65d5801 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
@@ -65,7 +65,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
if (obj->flags & I915_BO_ALLOC_PM_VOLATILE)
return 0;
- backup = i915_gem_object_create_shmem(i915, obj->base.size);
+ backup = i915_gem_object_create_smem(i915, obj->base.size);
if (IS_ERR(backup))
return PTR_ERR(backup);
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 0528fe1fc9b3..7184a7974686 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1258,7 +1258,7 @@ igt_create_shmem(struct drm_i915_private *i915, u32 size, u32 flags)
return ERR_PTR(-ENODEV);
}
- return i915_gem_object_create_shmem(i915, size);
+ return i915_gem_object_create_smem(i915, size);
}
static struct drm_i915_gem_object *
@@ -1569,7 +1569,7 @@ static int igt_tmpfs_fallback(void *arg)
i915->mm.gemfs = NULL;
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto out_restore;
@@ -1645,7 +1645,7 @@ static int igt_shrink_thp(void *arg)
* up.
*/
- obj = i915_gem_object_create_shmem(i915, SZ_2M);
+ obj = i915_gem_object_create_smem(i915, SZ_2M);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto out_vm;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index ddd0772fd828..76817ff44f0e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -134,7 +134,7 @@ __create_vma(struct tiled_blits *t, size_t size, bool lmem)
if (lmem)
obj = i915_gem_object_create_lmem(i915, size, 0);
else
- obj = i915_gem_object_create_shmem(i915, size);
+ obj = i915_gem_object_create_smem(i915, size);
if (IS_ERR(obj))
return ERR_CAST(obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index b071a58dd6da..fe0082bc0e11 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -16,7 +16,7 @@ static int igt_dmabuf_export(void *arg)
struct drm_i915_gem_object *obj;
struct dma_buf *dmabuf;
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj))
return PTR_ERR(obj);
@@ -40,7 +40,7 @@ static int igt_dmabuf_import_self(void *arg)
struct dma_buf *dmabuf;
int err;
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj))
return PTR_ERR(obj);
@@ -404,7 +404,7 @@ static int igt_dmabuf_export_vmap(void *arg)
void *ptr;
int err;
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj))
return PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
index fe0a890775e2..ed91a38dcbdf 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object.c
@@ -18,7 +18,7 @@ static int igt_gem_object(void *arg)
/* Basic test to ensure we can create an object */
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
pr_err("i915_gem_object_create failed, err=%d\n", err);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
index d43d8dae0f69..60afa537147b 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
@@ -18,7 +18,7 @@ static int mock_phys_object(void *arg)
* i.e. exercise the i915_gem_object_phys API.
*/
- obj = i915_gem_object_create_shmem(i915, PAGE_SIZE);
+ obj = i915_gem_object_create_smem(i915, PAGE_SIZE);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
pr_err("i915_gem_object_create failed, err=%d\n", err);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 004e1216e654..0a0a003ade3a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -954,7 +954,7 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine)
obj = i915_gem_object_create_lmem(engine->i915, context_size,
I915_BO_ALLOC_PM_VOLATILE);
if (IS_ERR(obj))
- obj = i915_gem_object_create_shmem(engine->i915, context_size);
+ obj = i915_gem_object_create_smem(engine->i915, context_size);
if (IS_ERR(obj))
return ERR_CAST(obj);
@@ -1582,7 +1582,7 @@ static int lrc_create_wa_ctx(struct intel_engine_cs *engine)
struct i915_vma *vma;
int err;
- obj = i915_gem_object_create_shmem(engine->i915, CTX_WA_BB_SIZE);
+ obj = i915_gem_object_create_smem(engine->i915, CTX_WA_BB_SIZE);
if (IS_ERR(obj))
return PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 6d7ec3bf1f32..6ae0a9ce876c 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -527,7 +527,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
struct i915_vma *vma;
int err;
- obj = i915_gem_object_create_shmem(i915, engine->context_size);
+ obj = i915_gem_object_create_smem(i915, engine->context_size);
if (IS_ERR(obj))
return ERR_CAST(obj);
diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c
index 0683b27a3890..6d6eada812de 100644
--- a/drivers/gpu/drm/i915/gt/shmem_utils.c
+++ b/drivers/gpu/drm/i915/gt/shmem_utils.c
@@ -34,12 +34,6 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj)
struct file *file;
void *ptr;
- if (i915_gem_object_is_shmem(obj)) {
- file = obj->base.filp;
- atomic_long_inc(&file->f_count);
- return file;
- }
-
ptr = i915_gem_object_pin_map_unlocked(obj, i915_gem_object_is_lmem(obj) ?
I915_MAP_WC : I915_MAP_WB);
if (IS_ERR(ptr))
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 447a976c9f25..716979786fad 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -698,7 +698,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
I915_BO_ALLOC_CONTIGUOUS |
I915_BO_ALLOC_PM_EARLY);
else
- obj = i915_gem_object_create_shmem(gt->i915, size);
+ obj = i915_gem_object_create_smem(gt->i915, size);
if (IS_ERR(obj))
return ERR_CAST(obj);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 55512db29183..c506a7c258d3 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -402,14 +402,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
if (uc_fw->type == INTEL_UC_FW_TYPE_GUC)
uc_fw->private_data_size = css->private_data_size;
- if (HAS_LMEM(i915)) {
- obj = i915_gem_object_create_lmem_from_data(i915, fw->data, fw->size);
- if (!IS_ERR(obj))
- obj->flags |= I915_BO_ALLOC_PM_EARLY;
- } else {
- obj = i915_gem_object_create_shmem_from_data(i915, fw->data, fw->size);
- }
-
+ obj = i915_gem_object_create_fw(i915, fw->data, fw->size);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto fail;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 2459213b6c87..2bd54a2032f5 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1929,7 +1929,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
if (bb->ppgtt)
start_offset = gma & ~I915_GTT_PAGE_MASK;
- bb->obj = i915_gem_object_create_shmem(s->engine->i915,
+ bb->obj = i915_gem_object_create_smem(s->engine->i915,
round_up(bb_size + start_offset,
PAGE_SIZE));
if (IS_ERR(bb->obj)) {
@@ -3003,7 +3003,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
int ret = 0;
void *map;
- obj = i915_gem_object_create_shmem(workload->engine->i915,
+ obj = i915_gem_object_create_smem(workload->engine->i915,
roundup(ctx_size + CACHELINE_BYTES,
PAGE_SIZE));
if (IS_ERR(obj))
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0a9c3fcc09b1..32811383cedd 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1570,7 +1570,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
BUILD_BUG_ON_NOT_POWER_OF_2(OA_BUFFER_SIZE);
BUILD_BUG_ON(OA_BUFFER_SIZE < SZ_128K || OA_BUFFER_SIZE > SZ_16M);
- bo = i915_gem_object_create_shmem(stream->perf->i915, OA_BUFFER_SIZE);
+ bo = i915_gem_object_create_smem(stream->perf->i915, OA_BUFFER_SIZE);
if (IS_ERR(bo)) {
drm_err(&i915->drm, "Failed to allocate OA buffer\n");
return PTR_ERR(bo);
@@ -1877,7 +1877,7 @@ alloc_oa_config_buffer(struct i915_perf_stream *stream,
config_length += 3; /* MI_BATCH_BUFFER_START */
config_length = ALIGN(sizeof(u32) * config_length, I915_GTT_PAGE_SIZE);
- obj = i915_gem_object_create_shmem(stream->perf->i915, config_length);
+ obj = i915_gem_object_create_smem(stream->perf->i915, config_length);
if (IS_ERR(obj)) {
err = PTR_ERR(obj);
goto err_free;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index c70d7e286a51..a80ffed63211 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -301,12 +301,8 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
instance = intel_region_map[i].instance;
switch (type) {
case INTEL_MEMORY_SYSTEM:
- if (IS_DGFX(i915))
- mem = i915_gem_ttm_system_setup(i915, type,
+ mem = i915_gem_ttm_system_setup(i915, type,
instance);
- else
- mem = i915_gem_shmem_setup(i915, type,
- instance);
break;
case INTEL_MEMORY_STOLEN_LOCAL:
mem = i915_gem_stolen_lmem_setup(i915, type, instance);
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 06464b8865fc..e0f564d8c453 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -124,8 +124,5 @@ void intel_memory_region_debug(struct intel_memory_region *mr,
struct intel_memory_region *
i915_gem_ttm_system_setup(struct drm_i915_private *i915,
u16 type, u16 instance);
-struct intel_memory_region *
-i915_gem_shmem_setup(struct drm_i915_private *i915,
- u16 type, u16 instance);
#endif
--
2.35.1
More information about the Intel-gfx-trybot
mailing list