* [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
@ 2021-10-27 10:52 ` Thomas Hellström
2021-10-27 18:03 ` Matthew Auld
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 2/3] drm/i915: Update error capture code to avoid using the current vma state Thomas Hellström
` (4 subsequent siblings)
5 siblings, 1 reply; 15+ messages in thread
From: Thomas Hellström @ 2021-10-27 10:52 UTC (permalink / raw)
To: intel-gfx, dri-devel
Cc: maarten.lankhorst, matthew.auld, Thomas Hellström
As we start to introduce asynchronous failsafe object migration,
where we update the object state and then submit asynchronous
commands we need to record what memory resources are actually used
by various part of the command stream. Initially for three purposes:
1) Error capture.
2) Asynchronous migration error recovery.
3) Asynchronous vma bind.
At the time where these happens, the object state may have been updated
to be several migrations ahead and object sg-tables discarded.
In order to make it possible to keep sg-tables with memory resource
information for these operations, introduce refcounted sg-tables that
aren't freed until the last user is done with them.
The alternative would be to reference information sitting on the
corresponding ttm_resources which typically have the same lifetime as
these refcountes sg_tables, but that leads to other awkward constructs:
Due to the design direction chosen for ttm resource managers that would
lead to diamond-style inheritance, the LMEM resources may sometimes be
prematurely freed, and finally the subclassed struct ttm_resource would
have to bleed into the asynchronous vma bind code.
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
.../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++-------
drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
9 files changed, 262 insertions(+), 119 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index a5479ac7a4ad..c5ab364d4311 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
size_t size, struct intel_memory_region *mr,
struct address_space *mapping,
unsigned int max_segment);
-void shmem_free_st(struct sg_table *st, struct address_space *mapping,
- bool dirty, bool backup);
+void shmem_free_st_table(struct sg_table *st, struct address_space *mapping,
+ bool dirty, bool backup);
void __shmem_writeback(size_t size, struct address_space *mapping);
#ifdef CONFIG_MMU_NOTIFIER
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index a4b69a43b898..604ed5ad77f5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -544,6 +544,7 @@ struct drm_i915_gem_object {
*/
struct list_head region_link;
+ struct i915_refct_sgt *rsgt;
struct sg_table *pages;
void *mapping;
@@ -597,7 +598,7 @@ struct drm_i915_gem_object {
} mm;
struct {
- struct sg_table *cached_io_st;
+ struct i915_refct_sgt *cached_io_rsgt;
struct i915_gem_object_page_iter get_io_page;
struct drm_i915_gem_object *backup;
bool created:1;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 01f332d8dbde..67c6bee695c7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec *pvec)
cond_resched();
}
-void shmem_free_st(struct sg_table *st, struct address_space *mapping,
- bool dirty, bool backup)
+void shmem_free_st_table(struct sg_table *st, struct address_space *mapping,
+ bool dirty, bool backup)
{
struct sgt_iter sgt_iter;
struct pagevec pvec;
@@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct address_space *mapping,
check_release_pagevec(&pvec);
sg_free_table(st);
- kfree(st);
}
struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
@@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
err_sg:
sg_mark_end(sg);
if (sg != st->sgl) {
- shmem_free_st(st, mapping, false, false);
+ shmem_free_st_table(st, mapping, false, false);
+ kfree(st);
} else {
mapping_clear_unevictable(mapping);
sg_free_table(st);
@@ -254,7 +254,8 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
return 0;
err_pages:
- shmem_free_st(st, mapping, false, false);
+ shmem_free_st_table(st, mapping, false, false);
+ kfree(st);
/*
* shmemfs first checks if there is enough memory to allocate the page
* and reports ENOSPC should there be insufficient, along with the usual
@@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_
if (i915_gem_object_needs_bit17_swizzle(obj))
i915_gem_object_save_bit_17_swizzle(obj, pages);
- shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
- obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED);
+ shmem_free_st_table(pages, file_inode(obj->base.filp)->i_mapping,
+ obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED);
+ kfree(pages);
obj->mm.dirty = false;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 4fd2edb20dd9..6826e3859e18 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -34,7 +34,7 @@
* struct i915_ttm_tt - TTM page vector with additional private information
* @ttm: The base TTM page vector.
* @dev: The struct device used for dma mapping and unmapping.
- * @cached_st: The cached scatter-gather table.
+ * @cached_rsgt: The cached scatter-gather table.
* @is_shmem: Set if using shmem.
* @filp: The shmem file, if using shmem backend.
*
@@ -47,7 +47,7 @@
struct i915_ttm_tt {
struct ttm_tt ttm;
struct device *dev;
- struct sg_table *cached_st;
+ struct i915_refct_sgt cached_rsgt;
bool is_shmem;
struct file *filp;
@@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
if (IS_ERR(st))
return PTR_ERR(st);
- err = dma_map_sg_attrs(i915_tt->dev,
- st->sgl, st->nents,
- DMA_BIDIRECTIONAL,
- DMA_ATTR_SKIP_CPU_SYNC);
- if (err <= 0) {
- err = -EINVAL;
+ err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ if (err)
goto err_free_st;
- }
i = 0;
for_each_sgt_page(page, sgt_iter, st)
@@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
- i915_tt->cached_st = st;
+ i915_tt->cached_rsgt.table = *st;
+ kfree(st);
+
return 0;
err_free_st:
- shmem_free_st(st, filp->f_mapping, false, false);
+ shmem_free_st_table(st, filp->f_mapping, false, false);
+ kfree(st);
+
return err;
}
@@ -249,16 +249,29 @@ static void i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
+ struct sg_table *st = &i915_tt->cached_rsgt.table;
- dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
- i915_tt->cached_st->nents,
- DMA_BIDIRECTIONAL);
+ if (st->sgl)
+ shmem_free_st_table(st,
+ file_inode(i915_tt->filp)->i_mapping,
+ backup, backup);
+}
- shmem_free_st(fetch_and_zero(&i915_tt->cached_st),
- file_inode(i915_tt->filp)->i_mapping,
- backup, backup);
+static void i915_ttm_tt_release(struct kref *ref)
+{
+ struct i915_ttm_tt *i915_tt =
+ container_of(ref, typeof(*i915_tt), cached_rsgt.kref);
+ struct sg_table *st = &i915_tt->cached_rsgt.table;
+
+ GEM_WARN_ON(st->sgl);
+
+ kfree(i915_tt);
}
+static const struct i915_refct_sgt_ops tt_rsgt_ops = {
+ .release = i915_ttm_tt_release
+};
+
static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
uint32_t page_flags)
{
@@ -287,6 +300,9 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
if (ret)
goto err_free;
+ i915_refct_sgt_init_ops(&i915_tt->cached_rsgt, bo->base.size,
+ &tt_rsgt_ops);
+
i915_tt->dev = obj->base.dev->dev;
return &i915_tt->ttm;
@@ -311,17 +327,15 @@ static int i915_ttm_tt_populate(struct ttm_device *bdev,
static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
+ struct sg_table *st = &i915_tt->cached_rsgt.table;
+
+ if (st->sgl)
+ dma_unmap_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
if (i915_tt->is_shmem) {
i915_ttm_tt_shmem_unpopulate(ttm);
} else {
- if (i915_tt->cached_st) {
- dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st,
- DMA_BIDIRECTIONAL, 0);
- sg_free_table(i915_tt->cached_st);
- kfree(i915_tt->cached_st);
- i915_tt->cached_st = NULL;
- }
+ sg_free_table(st);
ttm_pool_free(&bdev->pool, ttm);
}
}
@@ -334,7 +348,7 @@ static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
fput(i915_tt->filp);
ttm_tt_fini(ttm);
- kfree(i915_tt);
+ i915_refct_sgt_put(&i915_tt->cached_rsgt);
}
static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
@@ -376,12 +390,12 @@ static int i915_ttm_move_notify(struct ttm_buffer_object *bo)
return 0;
}
-static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
+static void i915_ttm_free_cached_io_rsgt(struct drm_i915_gem_object *obj)
{
struct radix_tree_iter iter;
void __rcu **slot;
- if (!obj->ttm.cached_io_st)
+ if (!obj->ttm.cached_io_rsgt)
return;
rcu_read_lock();
@@ -389,9 +403,8 @@ static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index);
rcu_read_unlock();
- sg_free_table(obj->ttm.cached_io_st);
- kfree(obj->ttm.cached_io_st);
- obj->ttm.cached_io_st = NULL;
+ i915_refct_sgt_put(obj->ttm.cached_io_rsgt);
+ obj->ttm.cached_io_rsgt = NULL;
}
static void
@@ -477,7 +490,7 @@ static int i915_ttm_purge(struct drm_i915_gem_object *obj)
obj->write_domain = 0;
obj->read_domains = 0;
i915_ttm_adjust_gem_after_move(obj);
- i915_ttm_free_cached_io_st(obj);
+ i915_ttm_free_cached_io_rsgt(obj);
obj->mm.madv = __I915_MADV_PURGED;
return 0;
}
@@ -532,7 +545,7 @@ static void i915_ttm_swap_notify(struct ttm_buffer_object *bo)
int ret = i915_ttm_move_notify(bo);
GEM_WARN_ON(ret);
- GEM_WARN_ON(obj->ttm.cached_io_st);
+ GEM_WARN_ON(obj->ttm.cached_io_rsgt);
if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
i915_ttm_purge(obj);
}
@@ -543,7 +556,7 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
if (likely(obj)) {
__i915_gem_object_pages_fini(obj);
- i915_ttm_free_cached_io_st(obj);
+ i915_ttm_free_cached_io_rsgt(obj);
}
}
@@ -563,40 +576,35 @@ i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type)
ttm_mem_type - I915_PL_LMEM0);
}
-static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
+static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm)
{
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
struct sg_table *st;
int ret;
- if (i915_tt->cached_st)
- return i915_tt->cached_st;
-
- st = kzalloc(sizeof(*st), GFP_KERNEL);
- if (!st)
- return ERR_PTR(-ENOMEM);
+ if (i915_tt->cached_rsgt.table.sgl)
+ return i915_refct_sgt_get(&i915_tt->cached_rsgt);
+ st = &i915_tt->cached_rsgt.table;
ret = sg_alloc_table_from_pages_segment(st,
ttm->pages, ttm->num_pages,
0, (unsigned long)ttm->num_pages << PAGE_SHIFT,
i915_sg_segment_size(), GFP_KERNEL);
if (ret) {
- kfree(st);
+ st->sgl = NULL;
return ERR_PTR(ret);
}
ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
if (ret) {
sg_free_table(st);
- kfree(st);
return ERR_PTR(ret);
}
- i915_tt->cached_st = st;
- return st;
+ return i915_refct_sgt_get(&i915_tt->cached_rsgt);
}
-static struct sg_table *
+static struct i915_refct_sgt *
i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
struct ttm_resource *res)
{
@@ -610,7 +618,21 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
* the resulting st. Might make sense for GGTT.
*/
GEM_WARN_ON(!cpu_maps_iomem(res));
- return intel_region_ttm_resource_to_st(obj->mm.region, res);
+ if (bo->resource == res) {
+ if (!obj->ttm.cached_io_rsgt) {
+ struct i915_refct_sgt *rsgt;
+
+ rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
+ res);
+ if (IS_ERR(rsgt))
+ return rsgt;
+
+ obj->ttm.cached_io_rsgt = rsgt;
+ }
+ return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
+ }
+
+ return intel_region_ttm_resource_to_rsgt(obj->mm.region, res);
}
static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
@@ -621,10 +643,7 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
{
struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
bdev);
- struct ttm_resource_manager *src_man =
- ttm_manager_type(bo->bdev, bo->resource->mem_type);
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
- struct sg_table *src_st;
struct i915_request *rq;
struct ttm_tt *src_ttm = bo->ttm;
enum i915_cache_level src_level, dst_level;
@@ -650,17 +669,22 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
}
intel_engine_pm_put(i915->gt.migrate.context->engine);
} else {
- src_st = src_man->use_tt ? i915_ttm_tt_get_st(src_ttm) :
- obj->ttm.cached_io_st;
+ struct i915_refct_sgt *src_rsgt =
+ i915_ttm_resource_get_st(obj, bo->resource);
+
+ if (IS_ERR(src_rsgt))
+ return PTR_ERR(src_rsgt);
src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm);
intel_engine_pm_get(i915->gt.migrate.context->engine);
ret = intel_context_migrate_copy(i915->gt.migrate.context,
- NULL, src_st->sgl, src_level,
+ NULL, src_rsgt->table.sgl,
+ src_level,
gpu_binds_iomem(bo->resource),
dst_st->sgl, dst_level,
gpu_binds_iomem(dst_mem),
&rq);
+ i915_refct_sgt_put(src_rsgt);
if (!ret && rq) {
i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
i915_request_put(rq);
@@ -674,13 +698,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
struct ttm_resource *dst_mem,
struct ttm_tt *dst_ttm,
- struct sg_table *dst_st,
+ struct i915_refct_sgt *dst_rsgt,
bool allow_accel)
{
int ret = -EINVAL;
if (allow_accel)
- ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, dst_st);
+ ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm,
+ &dst_rsgt->table);
if (ret) {
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
struct intel_memory_region *dst_reg, *src_reg;
@@ -697,12 +722,13 @@ static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
dst_iter = !cpu_maps_iomem(dst_mem) ?
ttm_kmap_iter_tt_init(&_dst_iter.tt, dst_ttm) :
ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
- dst_st, dst_reg->region.start);
+ &dst_rsgt->table,
+ dst_reg->region.start);
src_iter = !cpu_maps_iomem(bo->resource) ?
ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
- obj->ttm.cached_io_st,
+ &obj->ttm.cached_io_rsgt->table,
src_reg->region.start);
ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter);
@@ -718,7 +744,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
struct ttm_resource_manager *dst_man =
ttm_manager_type(bo->bdev, dst_mem->mem_type);
struct ttm_tt *ttm = bo->ttm;
- struct sg_table *dst_st;
+ struct i915_refct_sgt *dst_rsgt;
bool clear;
int ret;
@@ -744,22 +770,24 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
return ret;
}
- dst_st = i915_ttm_resource_get_st(obj, dst_mem);
- if (IS_ERR(dst_st))
- return PTR_ERR(dst_st);
+ dst_rsgt = i915_ttm_resource_get_st(obj, dst_mem);
+ if (IS_ERR(dst_rsgt))
+ return PTR_ERR(dst_rsgt);
clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm));
if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)))
- __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_st, true);
+ __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_rsgt, true);
ttm_bo_move_sync_cleanup(bo, dst_mem);
i915_ttm_adjust_domains_after_move(obj);
- i915_ttm_free_cached_io_st(obj);
+ i915_ttm_free_cached_io_rsgt(obj);
if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) {
- obj->ttm.cached_io_st = dst_st;
- obj->ttm.get_io_page.sg_pos = dst_st->sgl;
+ obj->ttm.cached_io_rsgt = dst_rsgt;
+ obj->ttm.get_io_page.sg_pos = dst_rsgt->table.sgl;
obj->ttm.get_io_page.sg_idx = 0;
+ } else {
+ i915_refct_sgt_put(dst_rsgt);
}
i915_ttm_adjust_lru(obj);
@@ -825,7 +853,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
.interruptible = true,
.no_wait_gpu = false,
};
- struct sg_table *st;
int real_num_busy;
int ret;
@@ -862,12 +889,16 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
}
if (!i915_gem_object_has_pages(obj)) {
- /* Object either has a page vector or is an iomem object */
- st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st;
- if (IS_ERR(st))
- return PTR_ERR(st);
+ struct i915_refct_sgt *rsgt =
+ i915_ttm_resource_get_st(obj, bo->resource);
+
+ if (IS_ERR(rsgt))
+ return PTR_ERR(rsgt);
- __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl));
+ GEM_BUG_ON(obj->mm.rsgt);
+ obj->mm.rsgt = rsgt;
+ __i915_gem_object_set_pages(obj, &rsgt->table,
+ i915_sg_dma_sizes(rsgt->table.sgl));
}
i915_ttm_adjust_lru(obj);
@@ -941,6 +972,13 @@ static void i915_ttm_put_pages(struct drm_i915_gem_object *obj,
* If the object is not destroyed next, The TTM eviction logic
* and shrinkers will move it out if needed.
*/
+
+ if (obj->mm.rsgt) {
+ i915_refct_sgt_put(obj->mm.rsgt);
+ obj->mm.rsgt = NULL;
+ }
+
+ i915_ttm_adjust_lru(obj);
}
static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
@@ -1278,7 +1316,7 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
struct ttm_operation_ctx ctx = {
.interruptible = intr,
};
- struct sg_table *dst_st;
+ struct i915_refct_sgt *dst_rsgt;
int ret;
assert_object_held(dst);
@@ -1293,11 +1331,11 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
if (ret)
return ret;
- dst_st = gpu_binds_iomem(dst_bo->resource) ?
- dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo->ttm);
-
+ dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource);
__i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo->ttm,
- dst_st, allow_accel);
+ dst_rsgt, allow_accel);
+
+ i915_refct_sgt_put(dst_rsgt);
return 0;
}
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 4a6712dca838..8a510ee5d1ad 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -41,8 +41,32 @@ bool i915_sg_trim(struct sg_table *orig_st)
return true;
}
+static void i915_refct_sgt_release(struct kref *ref)
+{
+ struct i915_refct_sgt *rsgt =
+ container_of(ref, typeof(*rsgt), kref);
+
+ sg_free_table(&rsgt->table);
+ kfree(rsgt);
+}
+
+static const struct i915_refct_sgt_ops rsgt_ops = {
+ .release = i915_refct_sgt_release
+};
+
+/**
+ * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with default ops
+ * @rsgt: The struct i915_refct_sgt to initialize.
+ * size: The size of the underlying memory buffer.
+ */
+void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
+{
+ i915_refct_sgt_init_ops(rsgt, size, &rsgt_ops);
+}
+
/**
- * i915_sg_from_mm_node - Create an sg_table from a struct drm_mm_node
+ * i915_rsgt_from_mm_node - Create a refcounted sg_table from a struct
+ * drm_mm_node
* @node: The drm_mm_node.
* @region_start: An offset to add to the dma addresses of the sg list.
*
@@ -50,25 +74,28 @@ bool i915_sg_trim(struct sg_table *orig_st)
* taking a maximum segment length into account, splitting into segments
* if necessary.
*
- * Return: A pointer to a kmalloced struct sg_table on success, negative
+ * Return: A pointer to a kmalloced struct i915_refct_sgt on success, negative
* error code cast to an error pointer on failure.
*/
-struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
- u64 region_start)
+struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
+ u64 region_start)
{
const u64 max_segment = SZ_1G; /* Do we have a limit on this? */
u64 segment_pages = max_segment >> PAGE_SHIFT;
u64 block_size, offset, prev_end;
+ struct i915_refct_sgt *rsgt;
struct sg_table *st;
struct scatterlist *sg;
- st = kmalloc(sizeof(*st), GFP_KERNEL);
- if (!st)
+ rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
+ if (!rsgt)
return ERR_PTR(-ENOMEM);
+ i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
+ st = &rsgt->table;
if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages),
GFP_KERNEL)) {
- kfree(st);
+ i915_refct_sgt_put(rsgt);
return ERR_PTR(-ENOMEM);
}
@@ -104,11 +131,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
sg_mark_end(sg);
i915_sg_trim(st);
- return st;
+ return rsgt;
}
/**
- * i915_sg_from_buddy_resource - Create an sg_table from a struct
+ * i915_rsgt_from_buddy_resource - Create a refcounted sg_table from a struct
* i915_buddy_block list
* @res: The struct i915_ttm_buddy_resource.
* @region_start: An offset to add to the dma addresses of the sg list.
@@ -117,11 +144,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
* taking a maximum segment length into account, splitting into segments
* if necessary.
*
- * Return: A pointer to a kmalloced struct sg_table on success, negative
+ * Return: A pointer to a kmalloced struct i915_refct_sgts 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_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
+ u64 region_start)
{
struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
const u64 size = res->num_pages << PAGE_SHIFT;
@@ -129,18 +156,21 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
struct i915_buddy_mm *mm = bman_res->mm;
struct list_head *blocks = &bman_res->blocks;
struct i915_buddy_block *block;
+ struct i915_refct_sgt *rsgt;
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)
+ rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
+ if (!rsgt)
return ERR_PTR(-ENOMEM);
+ i915_refct_sgt_init(rsgt, size);
+ st = &rsgt->table;
if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) {
- kfree(st);
+ i915_refct_sgt_put(rsgt);
return ERR_PTR(-ENOMEM);
}
@@ -181,7 +211,7 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
sg_mark_end(sg);
i915_sg_trim(st);
- return st;
+ return rsgt;
}
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index b8bd5925b03f..321fd4a9f777 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -144,10 +144,78 @@ static inline unsigned int i915_sg_segment_size(void)
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 i915_refct_sgt_ops - Operations structure for struct i915_refct_sgt
+ */
+struct i915_refct_sgt_ops {
+ /**
+ * release() - Free the memory of the struct i915_refct_sgt
+ * @ref: struct kref that is embedded in the struct i915_refct_sgt
+ */
+ void (*release)(struct kref *ref);
+};
+
+/**
+ * struct i915_refct_sgt - A refcounted scatter-gather table
+ * @kref: struct kref for refcounting
+ * @table: struct sg_table holding the scatter-gather table itself. Note that
+ * @table->sgl = NULL can be used to determine whether a scatter-gather table
+ * is present or not.
+ * @size: The size in bytes of the underlying memory buffer
+ * @ops: The operations structure.
+ */
+struct i915_refct_sgt {
+ struct kref kref;
+ struct sg_table table;
+ size_t size;
+ const struct i915_refct_sgt_ops *ops;
+};
+
+/**
+ * i915_refct_sgt_put - Put a refcounted sg-table
+ * @rsgt the struct i915_refct_sgt to put.
+ */
+static inline void i915_refct_sgt_put(struct i915_refct_sgt *rsgt)
+{
+ if (rsgt)
+ kref_put(&rsgt->kref, rsgt->ops->release);
+}
+
+/**
+ * i915_refct_sgt_get - Get a refcounted sg-table
+ * @rsgt the struct i915_refct_sgt to get.
+ */
+static inline struct i915_refct_sgt *
+i915_refct_sgt_get(struct i915_refct_sgt *rsgt)
+{
+ kref_get(&rsgt->kref);
+ return rsgt;
+}
+
+/**
+ * i915_refct_sgt_init_ops - Initialize a refcounted sg-list with a custom
+ * operations structure
+ * @rsgt The struct i915_refct_sgt to initialize.
+ * @size: Size in bytes of the underlying memory buffer.
+ * @ops: A customized operations structure in case the refcounted sg-list
+ * is embedded into another structure.
+ */
+static inline void i915_refct_sgt_init_ops(struct i915_refct_sgt *rsgt,
+ size_t size,
+ const struct i915_refct_sgt_ops *ops)
+{
+ kref_init(&rsgt->kref);
+ rsgt->table.sgl = NULL;
+ rsgt->size = size;
+ rsgt->ops = ops;
+}
+
+void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size);
+
+struct i915_refct_sgt *i915_rsgt_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);
+struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
+ u64 region_start);
#endif
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
index 98c7339bf8ba..2e901a27e259 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.c
+++ b/drivers/gpu/drm/i915/intel_region_ttm.c
@@ -115,8 +115,8 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
}
/**
- * intel_region_ttm_resource_to_st - Convert an opaque TTM resource manager resource
- * to an sg_table.
+ * intel_region_ttm_resource_to_rsgt -
+ * Convert an opaque TTM resource manager resource to a refcounted sg_table.
* @mem: The memory region.
* @res: The resource manager resource obtained from the TTM resource manager.
*
@@ -126,17 +126,18 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
*
* Return: A malloced sg_table on success, an error pointer on failure.
*/
-struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
- struct ttm_resource *res)
+struct i915_refct_sgt *
+intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
+ struct ttm_resource *res)
{
if (mem->is_range_manager) {
struct ttm_range_mgr_node *range_node =
to_ttm_range_mgr_node(res);
- return i915_sg_from_mm_node(&range_node->mm_nodes[0],
- mem->region.start);
+ return i915_rsgt_from_mm_node(&range_node->mm_nodes[0],
+ mem->region.start);
} else {
- return i915_sg_from_buddy_resource(res, mem->region.start);
+ return i915_rsgt_from_buddy_resource(res, mem->region.start);
}
}
diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
index 6f44075920f2..7bbe2b46b504 100644
--- a/drivers/gpu/drm/i915/intel_region_ttm.h
+++ b/drivers/gpu/drm/i915/intel_region_ttm.h
@@ -22,8 +22,9 @@ int intel_region_ttm_init(struct intel_memory_region *mem);
void intel_region_ttm_fini(struct intel_memory_region *mem);
-struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
- struct ttm_resource *res);
+struct i915_refct_sgt *
+intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
+ struct ttm_resource *res);
void intel_region_ttm_resource_free(struct intel_memory_region *mem,
struct ttm_resource *res);
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 75793008c4ef..7ec5037eaa58 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -15,9 +15,9 @@
static void mock_region_put_pages(struct drm_i915_gem_object *obj,
struct sg_table *pages)
{
+ i915_refct_sgt_put(obj->mm.rsgt);
+ obj->mm.rsgt = NULL;
intel_region_ttm_resource_free(obj->mm.region, obj->mm.res);
- sg_free_table(pages);
- kfree(pages);
}
static int mock_region_get_pages(struct drm_i915_gem_object *obj)
@@ -36,12 +36,14 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
if (IS_ERR(obj->mm.res))
return PTR_ERR(obj->mm.res);
- pages = intel_region_ttm_resource_to_st(obj->mm.region, obj->mm.res);
- if (IS_ERR(pages)) {
- err = PTR_ERR(pages);
+ obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
+ obj->mm.res);
+ if (IS_ERR(obj->mm.rsgt)) {
+ err = PTR_ERR(obj->mm.rsgt);
goto err_free_resource;
}
+ pages = &obj->mm.rsgt->table;
__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
return 0;
--
2.31.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables Thomas Hellström
@ 2021-10-27 18:03 ` Matthew Auld
2021-10-28 7:04 ` Thomas Hellström
0 siblings, 1 reply; 15+ messages in thread
From: Matthew Auld @ 2021-10-27 18:03 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On 27/10/2021 11:52, Thomas Hellström wrote:
> As we start to introduce asynchronous failsafe object migration,
> where we update the object state and then submit asynchronous
> commands we need to record what memory resources are actually used
> by various part of the command stream. Initially for three purposes:
>
> 1) Error capture.
> 2) Asynchronous migration error recovery.
> 3) Asynchronous vma bind.
>
> At the time where these happens, the object state may have been updated
> to be several migrations ahead and object sg-tables discarded.
>
> In order to make it possible to keep sg-tables with memory resource
> information for these operations, introduce refcounted sg-tables that
> aren't freed until the last user is done with them.
>
> The alternative would be to reference information sitting on the
> corresponding ttm_resources which typically have the same lifetime as
> these refcountes sg_tables, but that leads to other awkward constructs:
> Due to the design direction chosen for ttm resource managers that would
> lead to diamond-style inheritance, the LMEM resources may sometimes be
> prematurely freed, and finally the subclassed struct ttm_resource would
> have to bleed into the asynchronous vma bind code.
>
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
> drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
> .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
> drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++-------
> drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
> drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
> drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
> drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
> drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
> 9 files changed, 262 insertions(+), 119 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
> index a5479ac7a4ad..c5ab364d4311 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
> @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
> size_t size, struct intel_memory_region *mr,
> struct address_space *mapping,
> unsigned int max_segment);
> -void shmem_free_st(struct sg_table *st, struct address_space *mapping,
> - bool dirty, bool backup);
> +void shmem_free_st_table(struct sg_table *st, struct address_space *mapping,
> + bool dirty, bool backup);
s/st_table/sg_table/?
I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
> void __shmem_writeback(size_t size, struct address_space *mapping);
>
> #ifdef CONFIG_MMU_NOTIFIER
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> index a4b69a43b898..604ed5ad77f5 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
> */
> struct list_head region_link;
>
> + struct i915_refct_sgt *rsgt;
> struct sg_table *pages;
> void *mapping;
>
> @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
> } mm;
>
> struct {
> - struct sg_table *cached_io_st;
> + struct i915_refct_sgt *cached_io_rsgt;
> struct i915_gem_object_page_iter get_io_page;
> struct drm_i915_gem_object *backup;
> bool created:1;
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> index 01f332d8dbde..67c6bee695c7 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec *pvec)
> cond_resched();
> }
>
> -void shmem_free_st(struct sg_table *st, struct address_space *mapping,
> - bool dirty, bool backup)
> +void shmem_free_st_table(struct sg_table *st, struct address_space *mapping,
> + bool dirty, bool backup)
> {
> struct sgt_iter sgt_iter;
> struct pagevec pvec;
> @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct address_space *mapping,
> check_release_pagevec(&pvec);
>
> sg_free_table(st);
> - kfree(st);
> }
>
> struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
> @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
> err_sg:
> sg_mark_end(sg);
> if (sg != st->sgl) {
> - shmem_free_st(st, mapping, false, false);
> + shmem_free_st_table(st, mapping, false, false);
> + kfree(st);
> } else {
> mapping_clear_unevictable(mapping);
> sg_free_table(st);
> @@ -254,7 +254,8 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
> return 0;
>
> err_pages:
> - shmem_free_st(st, mapping, false, false);
> + shmem_free_st_table(st, mapping, false, false);
> + kfree(st);
> /*
> * shmemfs first checks if there is enough memory to allocate the page
> * and reports ENOSPC should there be insufficient, along with the usual
> @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct drm_i915_gem_object *obj, struct sg_
> if (i915_gem_object_needs_bit17_swizzle(obj))
> i915_gem_object_save_bit_17_swizzle(obj, pages);
>
> - shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
> - obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED);
> + shmem_free_st_table(pages, file_inode(obj->base.filp)->i_mapping,
> + obj->mm.dirty, obj->mm.madv == I915_MADV_WILLNEED);
> + kfree(pages);
> obj->mm.dirty = false;
> }
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> index 4fd2edb20dd9..6826e3859e18 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> @@ -34,7 +34,7 @@
> * struct i915_ttm_tt - TTM page vector with additional private information
> * @ttm: The base TTM page vector.
> * @dev: The struct device used for dma mapping and unmapping.
> - * @cached_st: The cached scatter-gather table.
> + * @cached_rsgt: The cached scatter-gather table.
> * @is_shmem: Set if using shmem.
> * @filp: The shmem file, if using shmem backend.
> *
> @@ -47,7 +47,7 @@
> struct i915_ttm_tt {
> struct ttm_tt ttm;
> struct device *dev;
> - struct sg_table *cached_st;
> + struct i915_refct_sgt cached_rsgt;
>
> bool is_shmem;
> struct file *filp;
> @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
> if (IS_ERR(st))
> return PTR_ERR(st);
>
> - err = dma_map_sg_attrs(i915_tt->dev,
> - st->sgl, st->nents,
> - DMA_BIDIRECTIONAL,
> - DMA_ATTR_SKIP_CPU_SYNC);
> - if (err <= 0) {
> - err = -EINVAL;
> + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
> + DMA_ATTR_SKIP_CPU_SYNC);
> + if (err)
> goto err_free_st;
> - }
>
> i = 0;
> for_each_sgt_page(page, sgt_iter, st)
> @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
> if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
> ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
>
> - i915_tt->cached_st = st;
> + i915_tt->cached_rsgt.table = *st;
> + kfree(st);
Will it work if the above just operates on the rsgt.table?
> +
> return 0;
>
> err_free_st:
> - shmem_free_st(st, filp->f_mapping, false, false);
> + shmem_free_st_table(st, filp->f_mapping, false, false);
> + kfree(st);
> +
> return err;
> }
>
> @@ -249,16 +249,29 @@ static void i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
> {
> struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
> bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>
> - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
> - i915_tt->cached_st->nents,
> - DMA_BIDIRECTIONAL);
> + if (st->sgl)
Can we ever hit this? I would have presumed not? Below also.
> + shmem_free_st_table(st,
> + file_inode(i915_tt->filp)->i_mapping,
> + backup, backup);
> +}
>
> - shmem_free_st(fetch_and_zero(&i915_tt->cached_st),
> - file_inode(i915_tt->filp)->i_mapping,
> - backup, backup);
> +static void i915_ttm_tt_release(struct kref *ref)
> +{
> + struct i915_ttm_tt *i915_tt =
> + container_of(ref, typeof(*i915_tt), cached_rsgt.kref);
> + struct sg_table *st = &i915_tt->cached_rsgt.table;
> +
> + GEM_WARN_ON(st->sgl);
> +
> + kfree(i915_tt);
> }
>
> +static const struct i915_refct_sgt_ops tt_rsgt_ops = {
> + .release = i915_ttm_tt_release
> +};
> +
> static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
> uint32_t page_flags)
> {
> @@ -287,6 +300,9 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
> if (ret)
> goto err_free;
>
> + i915_refct_sgt_init_ops(&i915_tt->cached_rsgt, bo->base.size,
> + &tt_rsgt_ops);
> +
> i915_tt->dev = obj->base.dev->dev;
>
> return &i915_tt->ttm;
> @@ -311,17 +327,15 @@ static int i915_ttm_tt_populate(struct ttm_device *bdev,
> static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm)
> {
> struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
> + struct sg_table *st = &i915_tt->cached_rsgt.table;
> +
> + if (st->sgl)
> + dma_unmap_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
>
> if (i915_tt->is_shmem) {
> i915_ttm_tt_shmem_unpopulate(ttm);
> } else {
> - if (i915_tt->cached_st) {
> - dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st,
> - DMA_BIDIRECTIONAL, 0);
> - sg_free_table(i915_tt->cached_st);
> - kfree(i915_tt->cached_st);
> - i915_tt->cached_st = NULL;
> - }
> + sg_free_table(st);
> ttm_pool_free(&bdev->pool, ttm);
> }
> }
> @@ -334,7 +348,7 @@ static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
> fput(i915_tt->filp);
>
> ttm_tt_fini(ttm);
> - kfree(i915_tt);
> + i915_refct_sgt_put(&i915_tt->cached_rsgt);
> }
>
> static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo,
> @@ -376,12 +390,12 @@ static int i915_ttm_move_notify(struct ttm_buffer_object *bo)
> return 0;
> }
>
> -static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
> +static void i915_ttm_free_cached_io_rsgt(struct drm_i915_gem_object *obj)
> {
> struct radix_tree_iter iter;
> void __rcu **slot;
>
> - if (!obj->ttm.cached_io_st)
> + if (!obj->ttm.cached_io_rsgt)
> return;
>
> rcu_read_lock();
> @@ -389,9 +403,8 @@ static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
> radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index);
> rcu_read_unlock();
>
> - sg_free_table(obj->ttm.cached_io_st);
> - kfree(obj->ttm.cached_io_st);
> - obj->ttm.cached_io_st = NULL;
> + i915_refct_sgt_put(obj->ttm.cached_io_rsgt);
> + obj->ttm.cached_io_rsgt = NULL;
> }
>
> static void
> @@ -477,7 +490,7 @@ static int i915_ttm_purge(struct drm_i915_gem_object *obj)
> obj->write_domain = 0;
> obj->read_domains = 0;
> i915_ttm_adjust_gem_after_move(obj);
> - i915_ttm_free_cached_io_st(obj);
> + i915_ttm_free_cached_io_rsgt(obj);
> obj->mm.madv = __I915_MADV_PURGED;
> return 0;
> }
> @@ -532,7 +545,7 @@ static void i915_ttm_swap_notify(struct ttm_buffer_object *bo)
> int ret = i915_ttm_move_notify(bo);
>
> GEM_WARN_ON(ret);
> - GEM_WARN_ON(obj->ttm.cached_io_st);
> + GEM_WARN_ON(obj->ttm.cached_io_rsgt);
> if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
> i915_ttm_purge(obj);
> }
> @@ -543,7 +556,7 @@ static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo)
>
> if (likely(obj)) {
> __i915_gem_object_pages_fini(obj);
> - i915_ttm_free_cached_io_st(obj);
> + i915_ttm_free_cached_io_rsgt(obj);
> }
> }
>
> @@ -563,40 +576,35 @@ i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type)
> ttm_mem_type - I915_PL_LMEM0);
> }
>
> -static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
> +static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm)
> {
> struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
> struct sg_table *st;
> int ret;
>
> - if (i915_tt->cached_st)
> - return i915_tt->cached_st;
> -
> - st = kzalloc(sizeof(*st), GFP_KERNEL);
> - if (!st)
> - return ERR_PTR(-ENOMEM);
> + if (i915_tt->cached_rsgt.table.sgl)
> + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
>
> + st = &i915_tt->cached_rsgt.table;
> ret = sg_alloc_table_from_pages_segment(st,
> ttm->pages, ttm->num_pages,
> 0, (unsigned long)ttm->num_pages << PAGE_SHIFT,
> i915_sg_segment_size(), GFP_KERNEL);
> if (ret) {
> - kfree(st);
> + st->sgl = NULL;
> return ERR_PTR(ret);
> }
>
> ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0);
> if (ret) {
> sg_free_table(st);
> - kfree(st);
> return ERR_PTR(ret);
> }
>
> - i915_tt->cached_st = st;
> - return st;
> + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
> }
>
> -static struct sg_table *
> +static struct i915_refct_sgt *
> i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
> struct ttm_resource *res)
> {
> @@ -610,7 +618,21 @@ i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
> * the resulting st. Might make sense for GGTT.
> */
> GEM_WARN_ON(!cpu_maps_iomem(res));
> - return intel_region_ttm_resource_to_st(obj->mm.region, res);
> + if (bo->resource == res) {
> + if (!obj->ttm.cached_io_rsgt) {
> + struct i915_refct_sgt *rsgt;
> +
> + rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
> + res);
> + if (IS_ERR(rsgt))
> + return rsgt;
> +
> + obj->ttm.cached_io_rsgt = rsgt;
> + }
> + return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
> + }
> +
> + return intel_region_ttm_resource_to_rsgt(obj->mm.region, res);
> }
>
> static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
> @@ -621,10 +643,7 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
> {
> struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
> bdev);
> - struct ttm_resource_manager *src_man =
> - ttm_manager_type(bo->bdev, bo->resource->mem_type);
> struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
> - struct sg_table *src_st;
> struct i915_request *rq;
> struct ttm_tt *src_ttm = bo->ttm;
> enum i915_cache_level src_level, dst_level;
> @@ -650,17 +669,22 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
> }
> intel_engine_pm_put(i915->gt.migrate.context->engine);
> } else {
> - src_st = src_man->use_tt ? i915_ttm_tt_get_st(src_ttm) :
> - obj->ttm.cached_io_st;
> + struct i915_refct_sgt *src_rsgt =
> + i915_ttm_resource_get_st(obj, bo->resource);
> +
> + if (IS_ERR(src_rsgt))
> + return PTR_ERR(src_rsgt);
>
> src_level = i915_ttm_cache_level(i915, bo->resource, src_ttm);
> intel_engine_pm_get(i915->gt.migrate.context->engine);
> ret = intel_context_migrate_copy(i915->gt.migrate.context,
> - NULL, src_st->sgl, src_level,
> + NULL, src_rsgt->table.sgl,
> + src_level,
> gpu_binds_iomem(bo->resource),
> dst_st->sgl, dst_level,
> gpu_binds_iomem(dst_mem),
> &rq);
> + i915_refct_sgt_put(src_rsgt);
> if (!ret && rq) {
> i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
> i915_request_put(rq);
> @@ -674,13 +698,14 @@ static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
> static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
> struct ttm_resource *dst_mem,
> struct ttm_tt *dst_ttm,
> - struct sg_table *dst_st,
> + struct i915_refct_sgt *dst_rsgt,
> bool allow_accel)
> {
> int ret = -EINVAL;
>
> if (allow_accel)
> - ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm, dst_st);
> + ret = i915_ttm_accel_move(bo, clear, dst_mem, dst_ttm,
> + &dst_rsgt->table);
> if (ret) {
> struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
> struct intel_memory_region *dst_reg, *src_reg;
> @@ -697,12 +722,13 @@ static void __i915_ttm_move(struct ttm_buffer_object *bo, bool clear,
> dst_iter = !cpu_maps_iomem(dst_mem) ?
> ttm_kmap_iter_tt_init(&_dst_iter.tt, dst_ttm) :
> ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap,
> - dst_st, dst_reg->region.start);
> + &dst_rsgt->table,
> + dst_reg->region.start);
>
> src_iter = !cpu_maps_iomem(bo->resource) ?
> ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) :
> ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap,
> - obj->ttm.cached_io_st,
> + &obj->ttm.cached_io_rsgt->table,
> src_reg->region.start);
>
> ttm_move_memcpy(clear, dst_mem->num_pages, dst_iter, src_iter);
> @@ -718,7 +744,7 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
> struct ttm_resource_manager *dst_man =
> ttm_manager_type(bo->bdev, dst_mem->mem_type);
> struct ttm_tt *ttm = bo->ttm;
> - struct sg_table *dst_st;
> + struct i915_refct_sgt *dst_rsgt;
> bool clear;
> int ret;
>
> @@ -744,22 +770,24 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
> return ret;
> }
>
> - dst_st = i915_ttm_resource_get_st(obj, dst_mem);
> - if (IS_ERR(dst_st))
> - return PTR_ERR(dst_st);
> + dst_rsgt = i915_ttm_resource_get_st(obj, dst_mem);
> + if (IS_ERR(dst_rsgt))
> + return PTR_ERR(dst_rsgt);
>
> clear = !cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm));
> if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)))
> - __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_st, true);
> + __i915_ttm_move(bo, clear, dst_mem, bo->ttm, dst_rsgt, true);
>
> ttm_bo_move_sync_cleanup(bo, dst_mem);
> i915_ttm_adjust_domains_after_move(obj);
> - i915_ttm_free_cached_io_st(obj);
> + i915_ttm_free_cached_io_rsgt(obj);
>
> if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) {
> - obj->ttm.cached_io_st = dst_st;
> - obj->ttm.get_io_page.sg_pos = dst_st->sgl;
> + obj->ttm.cached_io_rsgt = dst_rsgt;
> + obj->ttm.get_io_page.sg_pos = dst_rsgt->table.sgl;
> obj->ttm.get_io_page.sg_idx = 0;
> + } else {
> + i915_refct_sgt_put(dst_rsgt);
> }
>
> i915_ttm_adjust_lru(obj);
> @@ -825,7 +853,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
> .interruptible = true,
> .no_wait_gpu = false,
> };
> - struct sg_table *st;
> int real_num_busy;
> int ret;
>
> @@ -862,12 +889,16 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
> }
>
> if (!i915_gem_object_has_pages(obj)) {
> - /* Object either has a page vector or is an iomem object */
> - st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st;
> - if (IS_ERR(st))
> - return PTR_ERR(st);
> + struct i915_refct_sgt *rsgt =
> + i915_ttm_resource_get_st(obj, bo->resource);
> +
> + if (IS_ERR(rsgt))
> + return PTR_ERR(rsgt);
>
> - __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl));
> + GEM_BUG_ON(obj->mm.rsgt);
> + obj->mm.rsgt = rsgt;
> + __i915_gem_object_set_pages(obj, &rsgt->table,
> + i915_sg_dma_sizes(rsgt->table.sgl));
> }
>
> i915_ttm_adjust_lru(obj);
> @@ -941,6 +972,13 @@ static void i915_ttm_put_pages(struct drm_i915_gem_object *obj,
> * If the object is not destroyed next, The TTM eviction logic
> * and shrinkers will move it out if needed.
> */
> +
> + if (obj->mm.rsgt) {
> + i915_refct_sgt_put(obj->mm.rsgt);
> + obj->mm.rsgt = NULL;
> + }
i915_refct_sgt_put(fetch_and_zero(&obj->mm.rsgt)) ?
> +
> + i915_ttm_adjust_lru(obj);
Unrelated change, or do I need to look closer?
> }
>
> static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
> @@ -1278,7 +1316,7 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
> struct ttm_operation_ctx ctx = {
> .interruptible = intr,
> };
> - struct sg_table *dst_st;
> + struct i915_refct_sgt *dst_rsgt;
> int ret;
>
> assert_object_held(dst);
> @@ -1293,11 +1331,11 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
> if (ret)
> return ret;
>
> - dst_st = gpu_binds_iomem(dst_bo->resource) ?
> - dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo->ttm);
> -
> + dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource);
> __i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo->ttm,
> - dst_st, allow_accel);
> + dst_rsgt, allow_accel);
> +
> + i915_refct_sgt_put(dst_rsgt);
>
> return 0;
> }
> diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
> index 4a6712dca838..8a510ee5d1ad 100644
> --- a/drivers/gpu/drm/i915/i915_scatterlist.c
> +++ b/drivers/gpu/drm/i915/i915_scatterlist.c
> @@ -41,8 +41,32 @@ bool i915_sg_trim(struct sg_table *orig_st)
> return true;
> }
>
> +static void i915_refct_sgt_release(struct kref *ref)
> +{
> + struct i915_refct_sgt *rsgt =
> + container_of(ref, typeof(*rsgt), kref);
> +
> + sg_free_table(&rsgt->table);
> + kfree(rsgt);
> +}
> +
> +static const struct i915_refct_sgt_ops rsgt_ops = {
> + .release = i915_refct_sgt_release
> +};
> +
> +/**
> + * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with default ops
> + * @rsgt: The struct i915_refct_sgt to initialize.
> + * size: The size of the underlying memory buffer.
> + */
> +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
> +{
> + i915_refct_sgt_init_ops(rsgt, size, &rsgt_ops);
> +}
> +
> /**
> - * i915_sg_from_mm_node - Create an sg_table from a struct drm_mm_node
> + * i915_rsgt_from_mm_node - Create a refcounted sg_table from a struct
> + * drm_mm_node
> * @node: The drm_mm_node.
> * @region_start: An offset to add to the dma addresses of the sg list.
> *
> @@ -50,25 +74,28 @@ bool i915_sg_trim(struct sg_table *orig_st)
> * taking a maximum segment length into account, splitting into segments
> * if necessary.
> *
> - * Return: A pointer to a kmalloced struct sg_table on success, negative
> + * Return: A pointer to a kmalloced struct i915_refct_sgt on success, negative
> * error code cast to an error pointer on failure.
> */
> -struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
> - u64 region_start)
> +struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct drm_mm_node *node,
> + u64 region_start)
> {
> const u64 max_segment = SZ_1G; /* Do we have a limit on this? */
> u64 segment_pages = max_segment >> PAGE_SHIFT;
> u64 block_size, offset, prev_end;
> + struct i915_refct_sgt *rsgt;
> struct sg_table *st;
> struct scatterlist *sg;
>
> - st = kmalloc(sizeof(*st), GFP_KERNEL);
> - if (!st)
> + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
> + if (!rsgt)
> return ERR_PTR(-ENOMEM);
>
> + i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
> + st = &rsgt->table;
> if (sg_alloc_table(st, DIV_ROUND_UP(node->size, segment_pages),
> GFP_KERNEL)) {
> - kfree(st);
> + i915_refct_sgt_put(rsgt);
> return ERR_PTR(-ENOMEM);
> }
>
> @@ -104,11 +131,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
> sg_mark_end(sg);
> i915_sg_trim(st);
>
> - return st;
> + return rsgt;
> }
>
> /**
> - * i915_sg_from_buddy_resource - Create an sg_table from a struct
> + * i915_rsgt_from_buddy_resource - Create a refcounted sg_table from a struct
> * i915_buddy_block list
> * @res: The struct i915_ttm_buddy_resource.
> * @region_start: An offset to add to the dma addresses of the sg list.
> @@ -117,11 +144,11 @@ struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node *node,
> * taking a maximum segment length into account, splitting into segments
> * if necessary.
> *
> - * Return: A pointer to a kmalloced struct sg_table on success, negative
> + * Return: A pointer to a kmalloced struct i915_refct_sgts 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_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
> + u64 region_start)
> {
> struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
> const u64 size = res->num_pages << PAGE_SHIFT;
> @@ -129,18 +156,21 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
> struct i915_buddy_mm *mm = bman_res->mm;
> struct list_head *blocks = &bman_res->blocks;
> struct i915_buddy_block *block;
> + struct i915_refct_sgt *rsgt;
> 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)
> + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
> + if (!rsgt)
> return ERR_PTR(-ENOMEM);
>
> + i915_refct_sgt_init(rsgt, size);
> + st = &rsgt->table;
> if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) {
> - kfree(st);
> + i915_refct_sgt_put(rsgt);
> return ERR_PTR(-ENOMEM);
> }
>
> @@ -181,7 +211,7 @@ struct sg_table *i915_sg_from_buddy_resource(struct ttm_resource *res,
> sg_mark_end(sg);
> i915_sg_trim(st);
>
> - return st;
> + return rsgt;
> }
>
> #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
> diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
> index b8bd5925b03f..321fd4a9f777 100644
> --- a/drivers/gpu/drm/i915/i915_scatterlist.h
> +++ b/drivers/gpu/drm/i915/i915_scatterlist.h
> @@ -144,10 +144,78 @@ static inline unsigned int i915_sg_segment_size(void)
>
> 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 i915_refct_sgt_ops - Operations structure for struct i915_refct_sgt
> + */
> +struct i915_refct_sgt_ops {
> + /**
> + * release() - Free the memory of the struct i915_refct_sgt
> + * @ref: struct kref that is embedded in the struct i915_refct_sgt
> + */
> + void (*release)(struct kref *ref);
> +};
> +
> +/**
> + * struct i915_refct_sgt - A refcounted scatter-gather table
> + * @kref: struct kref for refcounting
> + * @table: struct sg_table holding the scatter-gather table itself. Note that
> + * @table->sgl = NULL can be used to determine whether a scatter-gather table
> + * is present or not.
> + * @size: The size in bytes of the underlying memory buffer
> + * @ops: The operations structure.
> + */
> +struct i915_refct_sgt {
> + struct kref kref;
> + struct sg_table table;
> + size_t size;
> + const struct i915_refct_sgt_ops *ops;
> +};
> +
> +/**
> + * i915_refct_sgt_put - Put a refcounted sg-table
> + * @rsgt the struct i915_refct_sgt to put.
> + */
> +static inline void i915_refct_sgt_put(struct i915_refct_sgt *rsgt)
> +{
> + if (rsgt)
> + kref_put(&rsgt->kref, rsgt->ops->release);
> +}
> +
> +/**
> + * i915_refct_sgt_get - Get a refcounted sg-table
> + * @rsgt the struct i915_refct_sgt to get.
> + */
> +static inline struct i915_refct_sgt *
> +i915_refct_sgt_get(struct i915_refct_sgt *rsgt)
> +{
> + kref_get(&rsgt->kref);
> + return rsgt;
> +}
> +
> +/**
> + * i915_refct_sgt_init_ops - Initialize a refcounted sg-list with a custom
> + * operations structure
> + * @rsgt The struct i915_refct_sgt to initialize.
> + * @size: Size in bytes of the underlying memory buffer.
> + * @ops: A customized operations structure in case the refcounted sg-list
> + * is embedded into another structure.
> + */
> +static inline void i915_refct_sgt_init_ops(struct i915_refct_sgt *rsgt,
> + size_t size,
> + const struct i915_refct_sgt_ops *ops)
> +{
> + kref_init(&rsgt->kref);
> + rsgt->table.sgl = NULL;
> + rsgt->size = size;
> + rsgt->ops = ops;
> +}
Could maybe make this __i915_refct_sgt_init(), since it inits more than
just the ops?
> +
> +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size);
> +
> +struct i915_refct_sgt *i915_rsgt_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);
> +struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
> + u64 region_start);
>
> #endif
> diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c
> index 98c7339bf8ba..2e901a27e259 100644
> --- a/drivers/gpu/drm/i915/intel_region_ttm.c
> +++ b/drivers/gpu/drm/i915/intel_region_ttm.c
> @@ -115,8 +115,8 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
> }
>
> /**
> - * intel_region_ttm_resource_to_st - Convert an opaque TTM resource manager resource
> - * to an sg_table.
> + * intel_region_ttm_resource_to_rsgt -
> + * Convert an opaque TTM resource manager resource to a refcounted sg_table.
> * @mem: The memory region.
> * @res: The resource manager resource obtained from the TTM resource manager.
> *
> @@ -126,17 +126,18 @@ void intel_region_ttm_fini(struct intel_memory_region *mem)
> *
> * Return: A malloced sg_table on success, an error pointer on failure.
> */
> -struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
> - struct ttm_resource *res)
> +struct i915_refct_sgt *
> +intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
> + struct ttm_resource *res)
> {
> if (mem->is_range_manager) {
> struct ttm_range_mgr_node *range_node =
> to_ttm_range_mgr_node(res);
>
> - return i915_sg_from_mm_node(&range_node->mm_nodes[0],
> - mem->region.start);
> + return i915_rsgt_from_mm_node(&range_node->mm_nodes[0],
> + mem->region.start);
> } else {
> - return i915_sg_from_buddy_resource(res, mem->region.start);
> + return i915_rsgt_from_buddy_resource(res, mem->region.start);
> }
> }
>
> diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h
> index 6f44075920f2..7bbe2b46b504 100644
> --- a/drivers/gpu/drm/i915/intel_region_ttm.h
> +++ b/drivers/gpu/drm/i915/intel_region_ttm.h
> @@ -22,8 +22,9 @@ int intel_region_ttm_init(struct intel_memory_region *mem);
>
> void intel_region_ttm_fini(struct intel_memory_region *mem);
>
> -struct sg_table *intel_region_ttm_resource_to_st(struct intel_memory_region *mem,
> - struct ttm_resource *res);
> +struct i915_refct_sgt *
> +intel_region_ttm_resource_to_rsgt(struct intel_memory_region *mem,
> + struct ttm_resource *res);
>
> void intel_region_ttm_resource_free(struct intel_memory_region *mem,
> struct ttm_resource *res);
> diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
> index 75793008c4ef..7ec5037eaa58 100644
> --- a/drivers/gpu/drm/i915/selftests/mock_region.c
> +++ b/drivers/gpu/drm/i915/selftests/mock_region.c
> @@ -15,9 +15,9 @@
> static void mock_region_put_pages(struct drm_i915_gem_object *obj,
> struct sg_table *pages)
> {
> + i915_refct_sgt_put(obj->mm.rsgt);
> + obj->mm.rsgt = NULL;
> intel_region_ttm_resource_free(obj->mm.region, obj->mm.res);
> - sg_free_table(pages);
> - kfree(pages);
> }
>
> static int mock_region_get_pages(struct drm_i915_gem_object *obj)
> @@ -36,12 +36,14 @@ static int mock_region_get_pages(struct drm_i915_gem_object *obj)
> if (IS_ERR(obj->mm.res))
> return PTR_ERR(obj->mm.res);
>
> - pages = intel_region_ttm_resource_to_st(obj->mm.region, obj->mm.res);
> - if (IS_ERR(pages)) {
> - err = PTR_ERR(pages);
> + obj->mm.rsgt = intel_region_ttm_resource_to_rsgt(obj->mm.region,
> + obj->mm.res);
> + if (IS_ERR(obj->mm.rsgt)) {
> + err = PTR_ERR(obj->mm.rsgt);
> goto err_free_resource;
> }
>
> + pages = &obj->mm.rsgt->table;
> __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
>
> return 0;
>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-27 18:03 ` Matthew Auld
@ 2021-10-28 7:04 ` Thomas Hellström
2021-10-28 8:47 ` Matthew Auld
0 siblings, 1 reply; 15+ messages in thread
From: Thomas Hellström @ 2021-10-28 7:04 UTC (permalink / raw)
To: Matthew Auld, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On Wed, 2021-10-27 at 19:03 +0100, Matthew Auld wrote:
> On 27/10/2021 11:52, Thomas Hellström wrote:
> > As we start to introduce asynchronous failsafe object migration,
> > where we update the object state and then submit asynchronous
> > commands we need to record what memory resources are actually used
> > by various part of the command stream. Initially for three
> > purposes:
> >
> > 1) Error capture.
> > 2) Asynchronous migration error recovery.
> > 3) Asynchronous vma bind.
> >
> > At the time where these happens, the object state may have been
> > updated
> > to be several migrations ahead and object sg-tables discarded.
> >
> > In order to make it possible to keep sg-tables with memory resource
> > information for these operations, introduce refcounted sg-tables
> > that
> > aren't freed until the last user is done with them.
> >
> > The alternative would be to reference information sitting on the
> > corresponding ttm_resources which typically have the same lifetime
> > as
> > these refcountes sg_tables, but that leads to other awkward
> > constructs:
> > Due to the design direction chosen for ttm resource managers that
> > would
> > lead to diamond-style inheritance, the LMEM resources may sometimes
> > be
> > prematurely freed, and finally the subclassed struct ttm_resource
> > would
> > have to bleed into the asynchronous vma bind code.
> >
> > Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> > ---
> > drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
> > .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
> > drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
> > drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++--
> > -----
> > drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
> > drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
> > drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
> > drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
> > drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
> > 9 files changed, 262 insertions(+), 119 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h
> > b/drivers/gpu/drm/i915/gem/i915_gem_object.h
> > index a5479ac7a4ad..c5ab364d4311 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
> > @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct
> > drm_i915_private *i915,
> > size_t size, struct
> > intel_memory_region *mr,
> > struct address_space *mapping,
> > unsigned int max_segment);
> > -void shmem_free_st(struct sg_table *st, struct address_space
> > *mapping,
> > - bool dirty, bool backup);
> > +void shmem_free_st_table(struct sg_table *st, struct address_space
> > *mapping,
> > + bool dirty, bool backup);
>
> s/st_table/sg_table/?
>
> I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
Yes the naming is indeed a bit unfortunate here. To be consistent with
the core's sg_free_table(), I changed to
shmem_sg_free_table() / shmem_sg_alloc_table.
>
>
> > void __shmem_writeback(size_t size, struct address_space
> > *mapping);
> >
> > #ifdef CONFIG_MMU_NOTIFIER
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> > b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> > index a4b69a43b898..604ed5ad77f5 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
> > @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
> > */
> > struct list_head region_link;
> >
> > + struct i915_refct_sgt *rsgt;
> > struct sg_table *pages;
> > void *mapping;
> >
> > @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
> > } mm;
> >
> > struct {
> > - struct sg_table *cached_io_st;
> > + struct i915_refct_sgt *cached_io_rsgt;
> > struct i915_gem_object_page_iter get_io_page;
> > struct drm_i915_gem_object *backup;
> > bool created:1;
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > index 01f332d8dbde..67c6bee695c7 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec
> > *pvec)
> > cond_resched();
> > }
> >
> > -void shmem_free_st(struct sg_table *st, struct address_space
> > *mapping,
> > - bool dirty, bool backup)
> > +void shmem_free_st_table(struct sg_table *st, struct address_space
> > *mapping,
> > + bool dirty, bool backup)
> > {
> > struct sgt_iter sgt_iter;
> > struct pagevec pvec;
> > @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct
> > address_space *mapping,
> > check_release_pagevec(&pvec);
> >
> > sg_free_table(st);
> > - kfree(st);
> > }
> >
> > struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
> > @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct
> > drm_i915_private *i915,
> > err_sg:
> > sg_mark_end(sg);
> > if (sg != st->sgl) {
> > - shmem_free_st(st, mapping, false, false);
> > + shmem_free_st_table(st, mapping, false, false);
> > + kfree(st);
> > } else {
> > mapping_clear_unevictable(mapping);
> > sg_free_table(st);
> > @@ -254,7 +254,8 @@ static int shmem_get_pages(struct
> > drm_i915_gem_object *obj)
> > return 0;
> >
> > err_pages:
> > - shmem_free_st(st, mapping, false, false);
> > + shmem_free_st_table(st, mapping, false, false);
> > + kfree(st);
> > /*
> > * shmemfs first checks if there is enough memory to
> > allocate the page
> > * and reports ENOSPC should there be insufficient, along
> > with the usual
> > @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct
> > drm_i915_gem_object *obj, struct sg_
> > if (i915_gem_object_needs_bit17_swizzle(obj))
> > i915_gem_object_save_bit_17_swizzle(obj, pages);
> >
> > - shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
> > - obj->mm.dirty, obj->mm.madv ==
> > I915_MADV_WILLNEED);
> > + shmem_free_st_table(pages, file_inode(obj->base.filp)-
> > >i_mapping,
> > + obj->mm.dirty, obj->mm.madv ==
> > I915_MADV_WILLNEED);
> > + kfree(pages);
> > obj->mm.dirty = false;
> > }
> >
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > index 4fd2edb20dd9..6826e3859e18 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
> > @@ -34,7 +34,7 @@
> > * struct i915_ttm_tt - TTM page vector with additional private
> > information
> > * @ttm: The base TTM page vector.
> > * @dev: The struct device used for dma mapping and unmapping.
> > - * @cached_st: The cached scatter-gather table.
> > + * @cached_rsgt: The cached scatter-gather table.
> > * @is_shmem: Set if using shmem.
> > * @filp: The shmem file, if using shmem backend.
> > *
> > @@ -47,7 +47,7 @@
> > struct i915_ttm_tt {
> > struct ttm_tt ttm;
> > struct device *dev;
> > - struct sg_table *cached_st;
> > + struct i915_refct_sgt cached_rsgt;
> >
> > bool is_shmem;
> > struct file *filp;
> > @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct
> > ttm_device *bdev,
> > if (IS_ERR(st))
> > return PTR_ERR(st);
> >
> > - err = dma_map_sg_attrs(i915_tt->dev,
> > - st->sgl, st->nents,
> > - DMA_BIDIRECTIONAL,
> > - DMA_ATTR_SKIP_CPU_SYNC);
> > - if (err <= 0) {
> > - err = -EINVAL;
> > + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
> > + DMA_ATTR_SKIP_CPU_SYNC);
> > + if (err)
> > goto err_free_st;
> > - }
> >
> > i = 0;
> > for_each_sgt_page(page, sgt_iter, st)
> > @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct
> > ttm_device *bdev,
> > if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
> > ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
> >
> > - i915_tt->cached_st = st;
> > + i915_tt->cached_rsgt.table = *st;
> > + kfree(st);
>
> Will it work if the above just operates on the rsgt.table?
I'll change the shmem utility here to not allocate the struct sg_table
and then we can operate on it directly.
>
> > +
> > return 0;
> >
> > err_free_st:
> > - shmem_free_st(st, filp->f_mapping, false, false);
> > + shmem_free_st_table(st, filp->f_mapping, false, false);
> > + kfree(st);
> > +
> > return err;
> > }
> >
> > @@ -249,16 +249,29 @@ static void
> > i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
> > {
> > struct i915_ttm_tt *i915_tt = container_of(ttm,
> > typeof(*i915_tt), ttm);
> > bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
> > + struct sg_table *st = &i915_tt->cached_rsgt.table;
> >
> > - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
> > - i915_tt->cached_st->nents,
> > - DMA_BIDIRECTIONAL);
> > + if (st->sgl)
>
> Can we ever hit this? I would have presumed not? Below also.
Yes, here's where we typically free the scatterlist.
>
> > + shmem_free_st_table(st,
> > + file_inode(i915_tt->filp)-
> > >i_mapping,
> > + backup, backup);
> > +}
> >
> > - shmem_free_st(fetch_and_zero(&i915_tt->cached_st),
> > - file_inode(i915_tt->filp)->i_mapping,
> > - backup, backup);
> > +static void i915_ttm_tt_release(struct kref *ref)
> > +{
> > + struct i915_ttm_tt *i915_tt =
> > + container_of(ref, typeof(*i915_tt),
> > cached_rsgt.kref);
> > + struct sg_table *st = &i915_tt->cached_rsgt.table;
> > +
> > + GEM_WARN_ON(st->sgl);
> > +
> > + kfree(i915_tt);
> > }
> >
> > +static const struct i915_refct_sgt_ops tt_rsgt_ops = {
> > + .release = i915_ttm_tt_release
> > +};
> > +
> > static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object
> > *bo,
> > uint32_t page_flags)
> > {
> > @@ -287,6 +300,9 @@ static struct ttm_tt *i915_ttm_tt_create(struct
> > ttm_buffer_object *bo,
> > if (ret)
> > goto err_free;
> >
> > + i915_refct_sgt_init_ops(&i915_tt->cached_rsgt, bo-
> > >base.size,
> > + &tt_rsgt_ops);
> > +
> > i915_tt->dev = obj->base.dev->dev;
> >
> > return &i915_tt->ttm;
> > @@ -311,17 +327,15 @@ static int i915_ttm_tt_populate(struct
> > ttm_device *bdev,
> > static void i915_ttm_tt_unpopulate(struct ttm_device *bdev,
> > struct ttm_tt *ttm)
> > {
> > struct i915_ttm_tt *i915_tt = container_of(ttm,
> > typeof(*i915_tt), ttm);
> > + struct sg_table *st = &i915_tt->cached_rsgt.table;
> > +
> > + if (st->sgl)
> > + dma_unmap_sgtable(i915_tt->dev, st,
> > DMA_BIDIRECTIONAL, 0);
> >
> > if (i915_tt->is_shmem) {
> > i915_ttm_tt_shmem_unpopulate(ttm);
> > } else {
> > - if (i915_tt->cached_st) {
> > - dma_unmap_sgtable(i915_tt->dev, i915_tt-
> > >cached_st,
> > - DMA_BIDIRECTIONAL, 0);
> > - sg_free_table(i915_tt->cached_st);
> > - kfree(i915_tt->cached_st);
> > - i915_tt->cached_st = NULL;
> > - }
> > + sg_free_table(st);
> > ttm_pool_free(&bdev->pool, ttm);
> > }
> > }
> > @@ -334,7 +348,7 @@ static void i915_ttm_tt_destroy(struct
> > ttm_device *bdev, struct ttm_tt *ttm)
> > fput(i915_tt->filp);
> >
> > ttm_tt_fini(ttm);
> > - kfree(i915_tt);
> > + i915_refct_sgt_put(&i915_tt->cached_rsgt);
> > }
> >
> > static bool i915_ttm_eviction_valuable(struct ttm_buffer_object
> > *bo,
> > @@ -376,12 +390,12 @@ static int i915_ttm_move_notify(struct
> > ttm_buffer_object *bo)
> > return 0;
> > }
> >
> > -static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object
> > *obj)
> > +static void i915_ttm_free_cached_io_rsgt(struct
> > drm_i915_gem_object *obj)
> > {
> > struct radix_tree_iter iter;
> > void __rcu **slot;
> >
> > - if (!obj->ttm.cached_io_st)
> > + if (!obj->ttm.cached_io_rsgt)
> > return;
> >
> > rcu_read_lock();
> > @@ -389,9 +403,8 @@ static void i915_ttm_free_cached_io_st(struct
> > drm_i915_gem_object *obj)
> > radix_tree_delete(&obj->ttm.get_io_page.radix,
> > iter.index);
> > rcu_read_unlock();
> >
> > - sg_free_table(obj->ttm.cached_io_st);
> > - kfree(obj->ttm.cached_io_st);
> > - obj->ttm.cached_io_st = NULL;
> > + i915_refct_sgt_put(obj->ttm.cached_io_rsgt);
> > + obj->ttm.cached_io_rsgt = NULL;
> > }
> >
> > static void
> > @@ -477,7 +490,7 @@ static int i915_ttm_purge(struct
> > drm_i915_gem_object *obj)
> > obj->write_domain = 0;
> > obj->read_domains = 0;
> > i915_ttm_adjust_gem_after_move(obj);
> > - i915_ttm_free_cached_io_st(obj);
> > + i915_ttm_free_cached_io_rsgt(obj);
> > obj->mm.madv = __I915_MADV_PURGED;
> > return 0;
> > }
> > @@ -532,7 +545,7 @@ static void i915_ttm_swap_notify(struct
> > ttm_buffer_object *bo)
> > int ret = i915_ttm_move_notify(bo);
> >
> > GEM_WARN_ON(ret);
> > - GEM_WARN_ON(obj->ttm.cached_io_st);
> > + GEM_WARN_ON(obj->ttm.cached_io_rsgt);
> > if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
> > i915_ttm_purge(obj);
> > }
> > @@ -543,7 +556,7 @@ static void i915_ttm_delete_mem_notify(struct
> > ttm_buffer_object *bo)
> >
> > if (likely(obj)) {
> > __i915_gem_object_pages_fini(obj);
> > - i915_ttm_free_cached_io_st(obj);
> > + i915_ttm_free_cached_io_rsgt(obj);
> > }
> > }
> >
> > @@ -563,40 +576,35 @@ i915_ttm_region(struct ttm_device *bdev, int
> > ttm_mem_type)
> > ttm_mem_type -
> > I915_PL_LMEM0);
> > }
> >
> > -static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
> > +static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt
> > *ttm)
> > {
> > struct i915_ttm_tt *i915_tt = container_of(ttm,
> > typeof(*i915_tt), ttm);
> > struct sg_table *st;
> > int ret;
> >
> > - if (i915_tt->cached_st)
> > - return i915_tt->cached_st;
> > -
> > - st = kzalloc(sizeof(*st), GFP_KERNEL);
> > - if (!st)
> > - return ERR_PTR(-ENOMEM);
> > + if (i915_tt->cached_rsgt.table.sgl)
> > + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
> >
> > + st = &i915_tt->cached_rsgt.table;
> > ret = sg_alloc_table_from_pages_segment(st,
> > ttm->pages, ttm->num_pages,
> > 0, (unsigned long)ttm->num_pages <<
> > PAGE_SHIFT,
> > i915_sg_segment_size(), GFP_KERNEL);
> > if (ret) {
> > - kfree(st);
> > + st->sgl = NULL;
> > return ERR_PTR(ret);
> > }
> >
> > ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
> > 0);
> > if (ret) {
> > sg_free_table(st);
> > - kfree(st);
> > return ERR_PTR(ret);
> > }
> >
> > - i915_tt->cached_st = st;
> > - return st;
> > + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
> > }
> >
> > -static struct sg_table *
> > +static struct i915_refct_sgt *
> > i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
> > struct ttm_resource *res)
> > {
> > @@ -610,7 +618,21 @@ i915_ttm_resource_get_st(struct
> > drm_i915_gem_object *obj,
> > * the resulting st. Might make sense for GGTT.
> > */
> > GEM_WARN_ON(!cpu_maps_iomem(res));
> > - return intel_region_ttm_resource_to_st(obj->mm.region,
> > res);
> > + if (bo->resource == res) {
> > + if (!obj->ttm.cached_io_rsgt) {
> > + struct i915_refct_sgt *rsgt;
> > +
> > + rsgt =
> > intel_region_ttm_resource_to_rsgt(obj->mm.region,
> > +
> > res);
> > + if (IS_ERR(rsgt))
> > + return rsgt;
> > +
> > + obj->ttm.cached_io_rsgt = rsgt;
> > + }
> > + return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
> > + }
> > +
> > + return intel_region_ttm_resource_to_rsgt(obj->mm.region,
> > res);
> > }
> >
> > static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
> > @@ -621,10 +643,7 @@ static int i915_ttm_accel_move(struct
> > ttm_buffer_object *bo,
> > {
> > struct drm_i915_private *i915 = container_of(bo->bdev,
> > typeof(*i915),
> > bdev);
> > - struct ttm_resource_manager *src_man =
> > - ttm_manager_type(bo->bdev, bo->resource->mem_type);
> > struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
> > - struct sg_table *src_st;
> > struct i915_request *rq;
> > struct ttm_tt *src_ttm = bo->ttm;
> > enum i915_cache_level src_level, dst_level;
> > @@ -650,17 +669,22 @@ static int i915_ttm_accel_move(struct
> > ttm_buffer_object *bo,
> > }
> > intel_engine_pm_put(i915->gt.migrate.context-
> > >engine);
> > } else {
> > - src_st = src_man->use_tt ?
> > i915_ttm_tt_get_st(src_ttm) :
> > - obj->ttm.cached_io_st;
> > + struct i915_refct_sgt *src_rsgt =
> > + i915_ttm_resource_get_st(obj, bo-
> > >resource);
> > +
> > + if (IS_ERR(src_rsgt))
> > + return PTR_ERR(src_rsgt);
> >
> > src_level = i915_ttm_cache_level(i915, bo-
> > >resource, src_ttm);
> > intel_engine_pm_get(i915->gt.migrate.context-
> > >engine);
> > ret = intel_context_migrate_copy(i915-
> > >gt.migrate.context,
> > - NULL, src_st->sgl,
> > src_level,
> > + NULL, src_rsgt-
> > >table.sgl,
> > + src_level,
> >
> > gpu_binds_iomem(bo->resource),
> > dst_st->sgl,
> > dst_level,
> >
> > gpu_binds_iomem(dst_mem),
> > &rq);
> > + i915_refct_sgt_put(src_rsgt);
> > if (!ret && rq) {
> > i915_request_wait(rq, 0,
> > MAX_SCHEDULE_TIMEOUT);
> > i915_request_put(rq);
> > @@ -674,13 +698,14 @@ static int i915_ttm_accel_move(struct
> > ttm_buffer_object *bo,
> > static void __i915_ttm_move(struct ttm_buffer_object *bo, bool
> > clear,
> > struct ttm_resource *dst_mem,
> > struct ttm_tt *dst_ttm,
> > - struct sg_table *dst_st,
> > + struct i915_refct_sgt *dst_rsgt,
> > bool allow_accel)
> > {
> > int ret = -EINVAL;
> >
> > if (allow_accel)
> > - ret = i915_ttm_accel_move(bo, clear, dst_mem,
> > dst_ttm, dst_st);
> > + ret = i915_ttm_accel_move(bo, clear, dst_mem,
> > dst_ttm,
> > + &dst_rsgt->table);
> > if (ret) {
> > struct drm_i915_gem_object *obj =
> > i915_ttm_to_gem(bo);
> > struct intel_memory_region *dst_reg, *src_reg;
> > @@ -697,12 +722,13 @@ static void __i915_ttm_move(struct
> > ttm_buffer_object *bo, bool clear,
> > dst_iter = !cpu_maps_iomem(dst_mem) ?
> > ttm_kmap_iter_tt_init(&_dst_iter.tt,
> > dst_ttm) :
> > ttm_kmap_iter_iomap_init(&_dst_iter.io,
> > &dst_reg->iomap,
> > - dst_st, dst_reg-
> > >region.start);
> > + &dst_rsgt->table,
> > + dst_reg-
> > >region.start);
> >
> > src_iter = !cpu_maps_iomem(bo->resource) ?
> > ttm_kmap_iter_tt_init(&_src_iter.tt, bo-
> > >ttm) :
> > ttm_kmap_iter_iomap_init(&_src_iter.io,
> > &src_reg->iomap,
> > - obj-
> > >ttm.cached_io_st,
> > + &obj-
> > >ttm.cached_io_rsgt->table,
> > src_reg-
> > >region.start);
> >
> > ttm_move_memcpy(clear, dst_mem->num_pages,
> > dst_iter, src_iter);
> > @@ -718,7 +744,7 @@ static int i915_ttm_move(struct
> > ttm_buffer_object *bo, bool evict,
> > struct ttm_resource_manager *dst_man =
> > ttm_manager_type(bo->bdev, dst_mem->mem_type);
> > struct ttm_tt *ttm = bo->ttm;
> > - struct sg_table *dst_st;
> > + struct i915_refct_sgt *dst_rsgt;
> > bool clear;
> > int ret;
> >
> > @@ -744,22 +770,24 @@ static int i915_ttm_move(struct
> > ttm_buffer_object *bo, bool evict,
> > return ret;
> > }
> >
> > - dst_st = i915_ttm_resource_get_st(obj, dst_mem);
> > - if (IS_ERR(dst_st))
> > - return PTR_ERR(dst_st);
> > + dst_rsgt = i915_ttm_resource_get_st(obj, dst_mem);
> > + if (IS_ERR(dst_rsgt))
> > + return PTR_ERR(dst_rsgt);
> >
> > clear = !cpu_maps_iomem(bo->resource) && (!ttm ||
> > !ttm_tt_is_populated(ttm));
> > if (!(clear && ttm && !(ttm->page_flags &
> > TTM_TT_FLAG_ZERO_ALLOC)))
> > - __i915_ttm_move(bo, clear, dst_mem, bo->ttm,
> > dst_st, true);
> > + __i915_ttm_move(bo, clear, dst_mem, bo->ttm,
> > dst_rsgt, true);
> >
> > ttm_bo_move_sync_cleanup(bo, dst_mem);
> > i915_ttm_adjust_domains_after_move(obj);
> > - i915_ttm_free_cached_io_st(obj);
> > + i915_ttm_free_cached_io_rsgt(obj);
> >
> > if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) {
> > - obj->ttm.cached_io_st = dst_st;
> > - obj->ttm.get_io_page.sg_pos = dst_st->sgl;
> > + obj->ttm.cached_io_rsgt = dst_rsgt;
> > + obj->ttm.get_io_page.sg_pos = dst_rsgt->table.sgl;
> > obj->ttm.get_io_page.sg_idx = 0;
> > + } else {
> > + i915_refct_sgt_put(dst_rsgt);
> > }
> >
> > i915_ttm_adjust_lru(obj);
> > @@ -825,7 +853,6 @@ static int __i915_ttm_get_pages(struct
> > drm_i915_gem_object *obj,
> > .interruptible = true,
> > .no_wait_gpu = false,
> > };
> > - struct sg_table *st;
> > int real_num_busy;
> > int ret;
> >
> > @@ -862,12 +889,16 @@ static int __i915_ttm_get_pages(struct
> > drm_i915_gem_object *obj,
> > }
> >
> > if (!i915_gem_object_has_pages(obj)) {
> > - /* Object either has a page vector or is an iomem
> > object */
> > - st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj-
> > >ttm.cached_io_st;
> > - if (IS_ERR(st))
> > - return PTR_ERR(st);
> > + struct i915_refct_sgt *rsgt =
> > + i915_ttm_resource_get_st(obj, bo-
> > >resource);
> > +
> > + if (IS_ERR(rsgt))
> > + return PTR_ERR(rsgt);
> >
> > - __i915_gem_object_set_pages(obj, st,
> > i915_sg_dma_sizes(st->sgl));
> > + GEM_BUG_ON(obj->mm.rsgt);
> > + obj->mm.rsgt = rsgt;
> > + __i915_gem_object_set_pages(obj, &rsgt->table,
> > + i915_sg_dma_sizes(rsgt-
> > >table.sgl));
> > }
> >
> > i915_ttm_adjust_lru(obj);
> > @@ -941,6 +972,13 @@ static void i915_ttm_put_pages(struct
> > drm_i915_gem_object *obj,
> > * If the object is not destroyed next, The TTM eviction
> > logic
> > * and shrinkers will move it out if needed.
> > */
> > +
> > + if (obj->mm.rsgt) {
> > + i915_refct_sgt_put(obj->mm.rsgt);
> > + obj->mm.rsgt = NULL;
> > + }
>
> i915_refct_sgt_put(fetch_and_zero(&obj->mm.rsgt)) ?
>
> > +
> > + i915_ttm_adjust_lru(obj);
>
> Unrelated change, or do I need to look closer?
No that's unrelated. Probably a rebase mistake. Will remove.
>
> > }
> >
> > static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
> > @@ -1278,7 +1316,7 @@ int i915_gem_obj_copy_ttm(struct
> > drm_i915_gem_object *dst,
> > struct ttm_operation_ctx ctx = {
> > .interruptible = intr,
> > };
> > - struct sg_table *dst_st;
> > + struct i915_refct_sgt *dst_rsgt;
> > int ret;
> >
> > assert_object_held(dst);
> > @@ -1293,11 +1331,11 @@ int i915_gem_obj_copy_ttm(struct
> > drm_i915_gem_object *dst,
> > if (ret)
> > return ret;
> >
> > - dst_st = gpu_binds_iomem(dst_bo->resource) ?
> > - dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo-
> > >ttm);
> > -
> > + dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource);
> > __i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo-
> > >ttm,
> > - dst_st, allow_accel);
> > + dst_rsgt, allow_accel);
> > +
> > + i915_refct_sgt_put(dst_rsgt);
> >
> > return 0;
> > }
> > diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c
> > b/drivers/gpu/drm/i915/i915_scatterlist.c
> > index 4a6712dca838..8a510ee5d1ad 100644
> > --- a/drivers/gpu/drm/i915/i915_scatterlist.c
> > +++ b/drivers/gpu/drm/i915/i915_scatterlist.c
> > @@ -41,8 +41,32 @@ bool i915_sg_trim(struct sg_table *orig_st)
> > return true;
> > }
> >
> > +static void i915_refct_sgt_release(struct kref *ref)
> > +{
> > + struct i915_refct_sgt *rsgt =
> > + container_of(ref, typeof(*rsgt), kref);
> > +
> > + sg_free_table(&rsgt->table);
> > + kfree(rsgt);
> > +}
> > +
> > +static const struct i915_refct_sgt_ops rsgt_ops = {
> > + .release = i915_refct_sgt_release
> > +};
> > +
> > +/**
> > + * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with
> > default ops
> > + * @rsgt: The struct i915_refct_sgt to initialize.
> > + * size: The size of the underlying memory buffer.
> > + */
> > +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
> > +{
> > + i915_refct_sgt_init_ops(rsgt, size, &rsgt_ops);
> > +}
> > +
> > /**
> > - * i915_sg_from_mm_node - Create an sg_table from a struct
> > drm_mm_node
> > + * i915_rsgt_from_mm_node - Create a refcounted sg_table from a
> > struct
> > + * drm_mm_node
> > * @node: The drm_mm_node.
> > * @region_start: An offset to add to the dma addresses of the sg
> > list.
> > *
> > @@ -50,25 +74,28 @@ bool i915_sg_trim(struct sg_table *orig_st)
> > * taking a maximum segment length into account, splitting into
> > segments
> > * if necessary.
> > *
> > - * Return: A pointer to a kmalloced struct sg_table on success,
> > negative
> > + * Return: A pointer to a kmalloced struct i915_refct_sgt on
> > success, negative
> > * error code cast to an error pointer on failure.
> > */
> > -struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node
> > *node,
> > - u64 region_start)
> > +struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct
> > drm_mm_node *node,
> > + u64 region_start)
> > {
> > const u64 max_segment = SZ_1G; /* Do we have a limit on
> > this? */
> > u64 segment_pages = max_segment >> PAGE_SHIFT;
> > u64 block_size, offset, prev_end;
> > + struct i915_refct_sgt *rsgt;
> > struct sg_table *st;
> > struct scatterlist *sg;
> >
> > - st = kmalloc(sizeof(*st), GFP_KERNEL);
> > - if (!st)
> > + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
> > + if (!rsgt)
> > return ERR_PTR(-ENOMEM);
> >
> > + i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
> > + st = &rsgt->table;
> > if (sg_alloc_table(st, DIV_ROUND_UP(node->size,
> > segment_pages),
> > GFP_KERNEL)) {
> > - kfree(st);
> > + i915_refct_sgt_put(rsgt);
> > return ERR_PTR(-ENOMEM);
> > }
> >
> > @@ -104,11 +131,11 @@ struct sg_table *i915_sg_from_mm_node(const
> > struct drm_mm_node *node,
> > sg_mark_end(sg);
> > i915_sg_trim(st);
> >
> > - return st;
> > + return rsgt;
> > }
> >
> > /**
> > - * i915_sg_from_buddy_resource - Create an sg_table from a struct
> > + * i915_rsgt_from_buddy_resource - Create a refcounted sg_table
> > from a struct
> > * i915_buddy_block list
> > * @res: The struct i915_ttm_buddy_resource.
> > * @region_start: An offset to add to the dma addresses of the sg
> > list.
> > @@ -117,11 +144,11 @@ struct sg_table *i915_sg_from_mm_node(const
> > struct drm_mm_node *node,
> > * taking a maximum segment length into account, splitting into
> > segments
> > * if necessary.
> > *
> > - * Return: A pointer to a kmalloced struct sg_table on success,
> > negative
> > + * Return: A pointer to a kmalloced struct i915_refct_sgts 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_refct_sgt *i915_rsgt_from_buddy_resource(struct
> > ttm_resource *res,
> > + u64
> > region_start)
> > {
> > struct i915_ttm_buddy_resource *bman_res =
> > to_ttm_buddy_resource(res);
> > const u64 size = res->num_pages << PAGE_SHIFT;
> > @@ -129,18 +156,21 @@ struct sg_table
> > *i915_sg_from_buddy_resource(struct ttm_resource *res,
> > struct i915_buddy_mm *mm = bman_res->mm;
> > struct list_head *blocks = &bman_res->blocks;
> > struct i915_buddy_block *block;
> > + struct i915_refct_sgt *rsgt;
> > 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)
> > + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
> > + if (!rsgt)
> > return ERR_PTR(-ENOMEM);
> >
> > + i915_refct_sgt_init(rsgt, size);
> > + st = &rsgt->table;
> > if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) {
> > - kfree(st);
> > + i915_refct_sgt_put(rsgt);
> > return ERR_PTR(-ENOMEM);
> > }
> >
> > @@ -181,7 +211,7 @@ struct sg_table
> > *i915_sg_from_buddy_resource(struct ttm_resource *res,
> > sg_mark_end(sg);
> > i915_sg_trim(st);
> >
> > - return st;
> > + return rsgt;
> > }
> >
> > #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
> > diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h
> > b/drivers/gpu/drm/i915/i915_scatterlist.h
> > index b8bd5925b03f..321fd4a9f777 100644
> > --- a/drivers/gpu/drm/i915/i915_scatterlist.h
> > +++ b/drivers/gpu/drm/i915/i915_scatterlist.h
> > @@ -144,10 +144,78 @@ static inline unsigned int
> > i915_sg_segment_size(void)
> >
> > 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 i915_refct_sgt_ops - Operations structure for struct
> > i915_refct_sgt
> > + */
> > +struct i915_refct_sgt_ops {
> > + /**
> > + * release() - Free the memory of the struct i915_refct_sgt
> > + * @ref: struct kref that is embedded in the struct
> > i915_refct_sgt
> > + */
> > + void (*release)(struct kref *ref);
> > +};
> > +
> > +/**
> > + * struct i915_refct_sgt - A refcounted scatter-gather table
> > + * @kref: struct kref for refcounting
> > + * @table: struct sg_table holding the scatter-gather table
> > itself. Note that
> > + * @table->sgl = NULL can be used to determine whether a scatter-
> > gather table
> > + * is present or not.
> > + * @size: The size in bytes of the underlying memory buffer
> > + * @ops: The operations structure.
> > + */
> > +struct i915_refct_sgt {
> > + struct kref kref;
> > + struct sg_table table;
> > + size_t size;
> > + const struct i915_refct_sgt_ops *ops;
> > +};
> > +
> > +/**
> > + * i915_refct_sgt_put - Put a refcounted sg-table
> > + * @rsgt the struct i915_refct_sgt to put.
> > + */
> > +static inline void i915_refct_sgt_put(struct i915_refct_sgt *rsgt)
> > +{
> > + if (rsgt)
> > + kref_put(&rsgt->kref, rsgt->ops->release);
> > +}
> > +
> > +/**
> > + * i915_refct_sgt_get - Get a refcounted sg-table
> > + * @rsgt the struct i915_refct_sgt to get.
> > + */
> > +static inline struct i915_refct_sgt *
> > +i915_refct_sgt_get(struct i915_refct_sgt *rsgt)
> > +{
> > + kref_get(&rsgt->kref);
> > + return rsgt;
> > +}
> > +
> > +/**
> > + * i915_refct_sgt_init_ops - Initialize a refcounted sg-list with
> > a custom
> > + * operations structure
> > + * @rsgt The struct i915_refct_sgt to initialize.
> > + * @size: Size in bytes of the underlying memory buffer.
> > + * @ops: A customized operations structure in case the refcounted
> > sg-list
> > + * is embedded into another structure.
> > + */
> > +static inline void i915_refct_sgt_init_ops(struct i915_refct_sgt
> > *rsgt,
> > + size_t size,
> > + const struct
> > i915_refct_sgt_ops *ops)
> > +{
> > + kref_init(&rsgt->kref);
> > + rsgt->table.sgl = NULL;
> > + rsgt->size = size;
> > + rsgt->ops = ops;
> > +}
>
> Could maybe make this __i915_refct_sgt_init(), since it inits more
> than
> just the ops?
>
>
Will change.
Thanks,
Thomas
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-28 7:04 ` Thomas Hellström
@ 2021-10-28 8:47 ` Matthew Auld
2021-10-28 9:35 ` Thomas Hellström
0 siblings, 1 reply; 15+ messages in thread
From: Matthew Auld @ 2021-10-28 8:47 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On 28/10/2021 08:04, Thomas Hellström wrote:
> On Wed, 2021-10-27 at 19:03 +0100, Matthew Auld wrote:
>> On 27/10/2021 11:52, Thomas Hellström wrote:
>>> As we start to introduce asynchronous failsafe object migration,
>>> where we update the object state and then submit asynchronous
>>> commands we need to record what memory resources are actually used
>>> by various part of the command stream. Initially for three
>>> purposes:
>>>
>>> 1) Error capture.
>>> 2) Asynchronous migration error recovery.
>>> 3) Asynchronous vma bind.
>>>
>>> At the time where these happens, the object state may have been
>>> updated
>>> to be several migrations ahead and object sg-tables discarded.
>>>
>>> In order to make it possible to keep sg-tables with memory resource
>>> information for these operations, introduce refcounted sg-tables
>>> that
>>> aren't freed until the last user is done with them.
>>>
>>> The alternative would be to reference information sitting on the
>>> corresponding ttm_resources which typically have the same lifetime
>>> as
>>> these refcountes sg_tables, but that leads to other awkward
>>> constructs:
>>> Due to the design direction chosen for ttm resource managers that
>>> would
>>> lead to diamond-style inheritance, the LMEM resources may sometimes
>>> be
>>> prematurely freed, and finally the subclassed struct ttm_resource
>>> would
>>> have to bleed into the asynchronous vma bind code.
>>>
>>> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>> ---
>>> drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
>>> .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
>>> drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
>>> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++--
>>> -----
>>> drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
>>> drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
>>> drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
>>> drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
>>> drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
>>> 9 files changed, 262 insertions(+), 119 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>> b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>> index a5479ac7a4ad..c5ab364d4311 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>> @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct
>>> drm_i915_private *i915,
>>> size_t size, struct
>>> intel_memory_region *mr,
>>> struct address_space *mapping,
>>> unsigned int max_segment);
>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>> *mapping,
>>> - bool dirty, bool backup);
>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>> *mapping,
>>> + bool dirty, bool backup);
>>
>> s/st_table/sg_table/?
>>
>> I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
>
> Yes the naming is indeed a bit unfortunate here. To be consistent with
> the core's sg_free_table(), I changed to
> shmem_sg_free_table() / shmem_sg_alloc_table.
>
>>
>>
>>> void __shmem_writeback(size_t size, struct address_space
>>> *mapping);
>>>
>>> #ifdef CONFIG_MMU_NOTIFIER
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>> b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>> index a4b69a43b898..604ed5ad77f5 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>> @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
>>> */
>>> struct list_head region_link;
>>>
>>> + struct i915_refct_sgt *rsgt;
>>> struct sg_table *pages;
>>> void *mapping;
>>>
>>> @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
>>> } mm;
>>>
>>> struct {
>>> - struct sg_table *cached_io_st;
>>> + struct i915_refct_sgt *cached_io_rsgt;
>>> struct i915_gem_object_page_iter get_io_page;
>>> struct drm_i915_gem_object *backup;
>>> bool created:1;
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>> b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>> index 01f332d8dbde..67c6bee695c7 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>> @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec
>>> *pvec)
>>> cond_resched();
>>> }
>>>
>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>> *mapping,
>>> - bool dirty, bool backup)
>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>> *mapping,
>>> + bool dirty, bool backup)
>>> {
>>> struct sgt_iter sgt_iter;
>>> struct pagevec pvec;
>>> @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct
>>> address_space *mapping,
>>> check_release_pagevec(&pvec);
>>>
>>> sg_free_table(st);
>>> - kfree(st);
>>> }
>>>
>>> struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
>>> @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct
>>> drm_i915_private *i915,
>>> err_sg:
>>> sg_mark_end(sg);
>>> if (sg != st->sgl) {
>>> - shmem_free_st(st, mapping, false, false);
>>> + shmem_free_st_table(st, mapping, false, false);
>>> + kfree(st);
>>> } else {
>>> mapping_clear_unevictable(mapping);
>>> sg_free_table(st);
>>> @@ -254,7 +254,8 @@ static int shmem_get_pages(struct
>>> drm_i915_gem_object *obj)
>>> return 0;
>>>
>>> err_pages:
>>> - shmem_free_st(st, mapping, false, false);
>>> + shmem_free_st_table(st, mapping, false, false);
>>> + kfree(st);
>>> /*
>>> * shmemfs first checks if there is enough memory to
>>> allocate the page
>>> * and reports ENOSPC should there be insufficient, along
>>> with the usual
>>> @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct
>>> drm_i915_gem_object *obj, struct sg_
>>> if (i915_gem_object_needs_bit17_swizzle(obj))
>>> i915_gem_object_save_bit_17_swizzle(obj, pages);
>>>
>>> - shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
>>> - obj->mm.dirty, obj->mm.madv ==
>>> I915_MADV_WILLNEED);
>>> + shmem_free_st_table(pages, file_inode(obj->base.filp)-
>>>> i_mapping,
>>> + obj->mm.dirty, obj->mm.madv ==
>>> I915_MADV_WILLNEED);
>>> + kfree(pages);
>>> obj->mm.dirty = false;
>>> }
>>>
>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>> b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>> index 4fd2edb20dd9..6826e3859e18 100644
>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>> @@ -34,7 +34,7 @@
>>> * struct i915_ttm_tt - TTM page vector with additional private
>>> information
>>> * @ttm: The base TTM page vector.
>>> * @dev: The struct device used for dma mapping and unmapping.
>>> - * @cached_st: The cached scatter-gather table.
>>> + * @cached_rsgt: The cached scatter-gather table.
>>> * @is_shmem: Set if using shmem.
>>> * @filp: The shmem file, if using shmem backend.
>>> *
>>> @@ -47,7 +47,7 @@
>>> struct i915_ttm_tt {
>>> struct ttm_tt ttm;
>>> struct device *dev;
>>> - struct sg_table *cached_st;
>>> + struct i915_refct_sgt cached_rsgt;
>>>
>>> bool is_shmem;
>>> struct file *filp;
>>> @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct
>>> ttm_device *bdev,
>>> if (IS_ERR(st))
>>> return PTR_ERR(st);
>>>
>>> - err = dma_map_sg_attrs(i915_tt->dev,
>>> - st->sgl, st->nents,
>>> - DMA_BIDIRECTIONAL,
>>> - DMA_ATTR_SKIP_CPU_SYNC);
>>> - if (err <= 0) {
>>> - err = -EINVAL;
>>> + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
>>> + DMA_ATTR_SKIP_CPU_SYNC);
>>> + if (err)
>>> goto err_free_st;
>>> - }
>>>
>>> i = 0;
>>> for_each_sgt_page(page, sgt_iter, st)
>>> @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct
>>> ttm_device *bdev,
>>> if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
>>> ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
>>>
>>> - i915_tt->cached_st = st;
>>> + i915_tt->cached_rsgt.table = *st;
>>> + kfree(st);
>>
>> Will it work if the above just operates on the rsgt.table?
>
> I'll change the shmem utility here to not allocate the struct sg_table
> and then we can operate on it directly.
>
>>
>>> +
>>> return 0;
>>>
>>> err_free_st:
>>> - shmem_free_st(st, filp->f_mapping, false, false);
>>> + shmem_free_st_table(st, filp->f_mapping, false, false);
>>> + kfree(st);
>>> +
>>> return err;
>>> }
>>>
>>> @@ -249,16 +249,29 @@ static void
>>> i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
>>> {
>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>> typeof(*i915_tt), ttm);
>>> bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>>
>>> - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
>>> - i915_tt->cached_st->nents,
>>> - DMA_BIDIRECTIONAL);
>>> + if (st->sgl)
>>
>> Can we ever hit this? I would have presumed not? Below also.
>
> Yes, here's where we typically free the scatterlist.
What I meant to say: can the above ever not be true? i.e sgl == NULL
>
>>
>>> + shmem_free_st_table(st,
>>> + file_inode(i915_tt->filp)-
>>>> i_mapping,
>>> + backup, backup);
>>> +}
>>>
>>> - shmem_free_st(fetch_and_zero(&i915_tt->cached_st),
>>> - file_inode(i915_tt->filp)->i_mapping,
>>> - backup, backup);
>>> +static void i915_ttm_tt_release(struct kref *ref)
>>> +{
>>> + struct i915_ttm_tt *i915_tt =
>>> + container_of(ref, typeof(*i915_tt),
>>> cached_rsgt.kref);
>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>> +
>>> + GEM_WARN_ON(st->sgl);
>>> +
>>> + kfree(i915_tt);
>>> }
>>>
>>> +static const struct i915_refct_sgt_ops tt_rsgt_ops = {
>>> + .release = i915_ttm_tt_release
>>> +};
>>> +
>>> static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object
>>> *bo,
>>> uint32_t page_flags)
>>> {
>>> @@ -287,6 +300,9 @@ static struct ttm_tt *i915_ttm_tt_create(struct
>>> ttm_buffer_object *bo,
>>> if (ret)
>>> goto err_free;
>>>
>>> + i915_refct_sgt_init_ops(&i915_tt->cached_rsgt, bo-
>>>> base.size,
>>> + &tt_rsgt_ops);
>>> +
>>> i915_tt->dev = obj->base.dev->dev;
>>>
>>> return &i915_tt->ttm;
>>> @@ -311,17 +327,15 @@ static int i915_ttm_tt_populate(struct
>>> ttm_device *bdev,
>>> static void i915_ttm_tt_unpopulate(struct ttm_device *bdev,
>>> struct ttm_tt *ttm)
>>> {
>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>> typeof(*i915_tt), ttm);
>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>> +
>>> + if (st->sgl)
>>> + dma_unmap_sgtable(i915_tt->dev, st,
>>> DMA_BIDIRECTIONAL, 0);
>>>
>>> if (i915_tt->is_shmem) {
>>> i915_ttm_tt_shmem_unpopulate(ttm);
>>> } else {
>>> - if (i915_tt->cached_st) {
>>> - dma_unmap_sgtable(i915_tt->dev, i915_tt-
>>>> cached_st,
>>> - DMA_BIDIRECTIONAL, 0);
>>> - sg_free_table(i915_tt->cached_st);
>>> - kfree(i915_tt->cached_st);
>>> - i915_tt->cached_st = NULL;
>>> - }
>>> + sg_free_table(st);
>>> ttm_pool_free(&bdev->pool, ttm);
>>> }
>>> }
>>> @@ -334,7 +348,7 @@ static void i915_ttm_tt_destroy(struct
>>> ttm_device *bdev, struct ttm_tt *ttm)
>>> fput(i915_tt->filp);
>>>
>>> ttm_tt_fini(ttm);
>>> - kfree(i915_tt);
>>> + i915_refct_sgt_put(&i915_tt->cached_rsgt);
>>> }
>>>
>>> static bool i915_ttm_eviction_valuable(struct ttm_buffer_object
>>> *bo,
>>> @@ -376,12 +390,12 @@ static int i915_ttm_move_notify(struct
>>> ttm_buffer_object *bo)
>>> return 0;
>>> }
>>>
>>> -static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object
>>> *obj)
>>> +static void i915_ttm_free_cached_io_rsgt(struct
>>> drm_i915_gem_object *obj)
>>> {
>>> struct radix_tree_iter iter;
>>> void __rcu **slot;
>>>
>>> - if (!obj->ttm.cached_io_st)
>>> + if (!obj->ttm.cached_io_rsgt)
>>> return;
>>>
>>> rcu_read_lock();
>>> @@ -389,9 +403,8 @@ static void i915_ttm_free_cached_io_st(struct
>>> drm_i915_gem_object *obj)
>>> radix_tree_delete(&obj->ttm.get_io_page.radix,
>>> iter.index);
>>> rcu_read_unlock();
>>>
>>> - sg_free_table(obj->ttm.cached_io_st);
>>> - kfree(obj->ttm.cached_io_st);
>>> - obj->ttm.cached_io_st = NULL;
>>> + i915_refct_sgt_put(obj->ttm.cached_io_rsgt);
>>> + obj->ttm.cached_io_rsgt = NULL;
>>> }
>>>
>>> static void
>>> @@ -477,7 +490,7 @@ static int i915_ttm_purge(struct
>>> drm_i915_gem_object *obj)
>>> obj->write_domain = 0;
>>> obj->read_domains = 0;
>>> i915_ttm_adjust_gem_after_move(obj);
>>> - i915_ttm_free_cached_io_st(obj);
>>> + i915_ttm_free_cached_io_rsgt(obj);
>>> obj->mm.madv = __I915_MADV_PURGED;
>>> return 0;
>>> }
>>> @@ -532,7 +545,7 @@ static void i915_ttm_swap_notify(struct
>>> ttm_buffer_object *bo)
>>> int ret = i915_ttm_move_notify(bo);
>>>
>>> GEM_WARN_ON(ret);
>>> - GEM_WARN_ON(obj->ttm.cached_io_st);
>>> + GEM_WARN_ON(obj->ttm.cached_io_rsgt);
>>> if (!ret && obj->mm.madv != I915_MADV_WILLNEED)
>>> i915_ttm_purge(obj);
>>> }
>>> @@ -543,7 +556,7 @@ static void i915_ttm_delete_mem_notify(struct
>>> ttm_buffer_object *bo)
>>>
>>> if (likely(obj)) {
>>> __i915_gem_object_pages_fini(obj);
>>> - i915_ttm_free_cached_io_st(obj);
>>> + i915_ttm_free_cached_io_rsgt(obj);
>>> }
>>> }
>>>
>>> @@ -563,40 +576,35 @@ i915_ttm_region(struct ttm_device *bdev, int
>>> ttm_mem_type)
>>> ttm_mem_type -
>>> I915_PL_LMEM0);
>>> }
>>>
>>> -static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm)
>>> +static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt
>>> *ttm)
>>> {
>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>> typeof(*i915_tt), ttm);
>>> struct sg_table *st;
>>> int ret;
>>>
>>> - if (i915_tt->cached_st)
>>> - return i915_tt->cached_st;
>>> -
>>> - st = kzalloc(sizeof(*st), GFP_KERNEL);
>>> - if (!st)
>>> - return ERR_PTR(-ENOMEM);
>>> + if (i915_tt->cached_rsgt.table.sgl)
>>> + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
>>>
>>> + st = &i915_tt->cached_rsgt.table;
>>> ret = sg_alloc_table_from_pages_segment(st,
>>> ttm->pages, ttm->num_pages,
>>> 0, (unsigned long)ttm->num_pages <<
>>> PAGE_SHIFT,
>>> i915_sg_segment_size(), GFP_KERNEL);
>>> if (ret) {
>>> - kfree(st);
>>> + st->sgl = NULL;
>>> return ERR_PTR(ret);
>>> }
>>>
>>> ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
>>> 0);
>>> if (ret) {
>>> sg_free_table(st);
>>> - kfree(st);
>>> return ERR_PTR(ret);
>>> }
>>>
>>> - i915_tt->cached_st = st;
>>> - return st;
>>> + return i915_refct_sgt_get(&i915_tt->cached_rsgt);
>>> }
>>>
>>> -static struct sg_table *
>>> +static struct i915_refct_sgt *
>>> i915_ttm_resource_get_st(struct drm_i915_gem_object *obj,
>>> struct ttm_resource *res)
>>> {
>>> @@ -610,7 +618,21 @@ i915_ttm_resource_get_st(struct
>>> drm_i915_gem_object *obj,
>>> * the resulting st. Might make sense for GGTT.
>>> */
>>> GEM_WARN_ON(!cpu_maps_iomem(res));
>>> - return intel_region_ttm_resource_to_st(obj->mm.region,
>>> res);
>>> + if (bo->resource == res) {
>>> + if (!obj->ttm.cached_io_rsgt) {
>>> + struct i915_refct_sgt *rsgt;
>>> +
>>> + rsgt =
>>> intel_region_ttm_resource_to_rsgt(obj->mm.region,
>>> +
>>> res);
>>> + if (IS_ERR(rsgt))
>>> + return rsgt;
>>> +
>>> + obj->ttm.cached_io_rsgt = rsgt;
>>> + }
>>> + return i915_refct_sgt_get(obj->ttm.cached_io_rsgt);
>>> + }
>>> +
>>> + return intel_region_ttm_resource_to_rsgt(obj->mm.region,
>>> res);
>>> }
>>>
>>> static int i915_ttm_accel_move(struct ttm_buffer_object *bo,
>>> @@ -621,10 +643,7 @@ static int i915_ttm_accel_move(struct
>>> ttm_buffer_object *bo,
>>> {
>>> struct drm_i915_private *i915 = container_of(bo->bdev,
>>> typeof(*i915),
>>> bdev);
>>> - struct ttm_resource_manager *src_man =
>>> - ttm_manager_type(bo->bdev, bo->resource->mem_type);
>>> struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
>>> - struct sg_table *src_st;
>>> struct i915_request *rq;
>>> struct ttm_tt *src_ttm = bo->ttm;
>>> enum i915_cache_level src_level, dst_level;
>>> @@ -650,17 +669,22 @@ static int i915_ttm_accel_move(struct
>>> ttm_buffer_object *bo,
>>> }
>>> intel_engine_pm_put(i915->gt.migrate.context-
>>>> engine);
>>> } else {
>>> - src_st = src_man->use_tt ?
>>> i915_ttm_tt_get_st(src_ttm) :
>>> - obj->ttm.cached_io_st;
>>> + struct i915_refct_sgt *src_rsgt =
>>> + i915_ttm_resource_get_st(obj, bo-
>>>> resource);
>>> +
>>> + if (IS_ERR(src_rsgt))
>>> + return PTR_ERR(src_rsgt);
>>>
>>> src_level = i915_ttm_cache_level(i915, bo-
>>>> resource, src_ttm);
>>> intel_engine_pm_get(i915->gt.migrate.context-
>>>> engine);
>>> ret = intel_context_migrate_copy(i915-
>>>> gt.migrate.context,
>>> - NULL, src_st->sgl,
>>> src_level,
>>> + NULL, src_rsgt-
>>>> table.sgl,
>>> + src_level,
>>>
>>> gpu_binds_iomem(bo->resource),
>>> dst_st->sgl,
>>> dst_level,
>>>
>>> gpu_binds_iomem(dst_mem),
>>> &rq);
>>> + i915_refct_sgt_put(src_rsgt);
>>> if (!ret && rq) {
>>> i915_request_wait(rq, 0,
>>> MAX_SCHEDULE_TIMEOUT);
>>> i915_request_put(rq);
>>> @@ -674,13 +698,14 @@ static int i915_ttm_accel_move(struct
>>> ttm_buffer_object *bo,
>>> static void __i915_ttm_move(struct ttm_buffer_object *bo, bool
>>> clear,
>>> struct ttm_resource *dst_mem,
>>> struct ttm_tt *dst_ttm,
>>> - struct sg_table *dst_st,
>>> + struct i915_refct_sgt *dst_rsgt,
>>> bool allow_accel)
>>> {
>>> int ret = -EINVAL;
>>>
>>> if (allow_accel)
>>> - ret = i915_ttm_accel_move(bo, clear, dst_mem,
>>> dst_ttm, dst_st);
>>> + ret = i915_ttm_accel_move(bo, clear, dst_mem,
>>> dst_ttm,
>>> + &dst_rsgt->table);
>>> if (ret) {
>>> struct drm_i915_gem_object *obj =
>>> i915_ttm_to_gem(bo);
>>> struct intel_memory_region *dst_reg, *src_reg;
>>> @@ -697,12 +722,13 @@ static void __i915_ttm_move(struct
>>> ttm_buffer_object *bo, bool clear,
>>> dst_iter = !cpu_maps_iomem(dst_mem) ?
>>> ttm_kmap_iter_tt_init(&_dst_iter.tt,
>>> dst_ttm) :
>>> ttm_kmap_iter_iomap_init(&_dst_iter.io,
>>> &dst_reg->iomap,
>>> - dst_st, dst_reg-
>>>> region.start);
>>> + &dst_rsgt->table,
>>> + dst_reg-
>>>> region.start);
>>>
>>> src_iter = !cpu_maps_iomem(bo->resource) ?
>>> ttm_kmap_iter_tt_init(&_src_iter.tt, bo-
>>>> ttm) :
>>> ttm_kmap_iter_iomap_init(&_src_iter.io,
>>> &src_reg->iomap,
>>> - obj-
>>>> ttm.cached_io_st,
>>> + &obj-
>>>> ttm.cached_io_rsgt->table,
>>> src_reg-
>>>> region.start);
>>>
>>> ttm_move_memcpy(clear, dst_mem->num_pages,
>>> dst_iter, src_iter);
>>> @@ -718,7 +744,7 @@ static int i915_ttm_move(struct
>>> ttm_buffer_object *bo, bool evict,
>>> struct ttm_resource_manager *dst_man =
>>> ttm_manager_type(bo->bdev, dst_mem->mem_type);
>>> struct ttm_tt *ttm = bo->ttm;
>>> - struct sg_table *dst_st;
>>> + struct i915_refct_sgt *dst_rsgt;
>>> bool clear;
>>> int ret;
>>>
>>> @@ -744,22 +770,24 @@ static int i915_ttm_move(struct
>>> ttm_buffer_object *bo, bool evict,
>>> return ret;
>>> }
>>>
>>> - dst_st = i915_ttm_resource_get_st(obj, dst_mem);
>>> - if (IS_ERR(dst_st))
>>> - return PTR_ERR(dst_st);
>>> + dst_rsgt = i915_ttm_resource_get_st(obj, dst_mem);
>>> + if (IS_ERR(dst_rsgt))
>>> + return PTR_ERR(dst_rsgt);
>>>
>>> clear = !cpu_maps_iomem(bo->resource) && (!ttm ||
>>> !ttm_tt_is_populated(ttm));
>>> if (!(clear && ttm && !(ttm->page_flags &
>>> TTM_TT_FLAG_ZERO_ALLOC)))
>>> - __i915_ttm_move(bo, clear, dst_mem, bo->ttm,
>>> dst_st, true);
>>> + __i915_ttm_move(bo, clear, dst_mem, bo->ttm,
>>> dst_rsgt, true);
>>>
>>> ttm_bo_move_sync_cleanup(bo, dst_mem);
>>> i915_ttm_adjust_domains_after_move(obj);
>>> - i915_ttm_free_cached_io_st(obj);
>>> + i915_ttm_free_cached_io_rsgt(obj);
>>>
>>> if (gpu_binds_iomem(dst_mem) || cpu_maps_iomem(dst_mem)) {
>>> - obj->ttm.cached_io_st = dst_st;
>>> - obj->ttm.get_io_page.sg_pos = dst_st->sgl;
>>> + obj->ttm.cached_io_rsgt = dst_rsgt;
>>> + obj->ttm.get_io_page.sg_pos = dst_rsgt->table.sgl;
>>> obj->ttm.get_io_page.sg_idx = 0;
>>> + } else {
>>> + i915_refct_sgt_put(dst_rsgt);
>>> }
>>>
>>> i915_ttm_adjust_lru(obj);
>>> @@ -825,7 +853,6 @@ static int __i915_ttm_get_pages(struct
>>> drm_i915_gem_object *obj,
>>> .interruptible = true,
>>> .no_wait_gpu = false,
>>> };
>>> - struct sg_table *st;
>>> int real_num_busy;
>>> int ret;
>>>
>>> @@ -862,12 +889,16 @@ static int __i915_ttm_get_pages(struct
>>> drm_i915_gem_object *obj,
>>> }
>>>
>>> if (!i915_gem_object_has_pages(obj)) {
>>> - /* Object either has a page vector or is an iomem
>>> object */
>>> - st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj-
>>>> ttm.cached_io_st;
>>> - if (IS_ERR(st))
>>> - return PTR_ERR(st);
>>> + struct i915_refct_sgt *rsgt =
>>> + i915_ttm_resource_get_st(obj, bo-
>>>> resource);
>>> +
>>> + if (IS_ERR(rsgt))
>>> + return PTR_ERR(rsgt);
>>>
>>> - __i915_gem_object_set_pages(obj, st,
>>> i915_sg_dma_sizes(st->sgl));
>>> + GEM_BUG_ON(obj->mm.rsgt);
>>> + obj->mm.rsgt = rsgt;
>>> + __i915_gem_object_set_pages(obj, &rsgt->table,
>>> + i915_sg_dma_sizes(rsgt-
>>>> table.sgl));
>>> }
>>>
>>> i915_ttm_adjust_lru(obj);
>>> @@ -941,6 +972,13 @@ static void i915_ttm_put_pages(struct
>>> drm_i915_gem_object *obj,
>>> * If the object is not destroyed next, The TTM eviction
>>> logic
>>> * and shrinkers will move it out if needed.
>>> */
>>> +
>>> + if (obj->mm.rsgt) {
>>> + i915_refct_sgt_put(obj->mm.rsgt);
>>> + obj->mm.rsgt = NULL;
>>> + }
>>
>> i915_refct_sgt_put(fetch_and_zero(&obj->mm.rsgt)) ?
>>
>>> +
>>> + i915_ttm_adjust_lru(obj);
>>
>> Unrelated change, or do I need to look closer?
>
> No that's unrelated. Probably a rebase mistake. Will remove.
>
>>
>>> }
>>>
>>> static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj)
>>> @@ -1278,7 +1316,7 @@ int i915_gem_obj_copy_ttm(struct
>>> drm_i915_gem_object *dst,
>>> struct ttm_operation_ctx ctx = {
>>> .interruptible = intr,
>>> };
>>> - struct sg_table *dst_st;
>>> + struct i915_refct_sgt *dst_rsgt;
>>> int ret;
>>>
>>> assert_object_held(dst);
>>> @@ -1293,11 +1331,11 @@ int i915_gem_obj_copy_ttm(struct
>>> drm_i915_gem_object *dst,
>>> if (ret)
>>> return ret;
>>>
>>> - dst_st = gpu_binds_iomem(dst_bo->resource) ?
>>> - dst->ttm.cached_io_st : i915_ttm_tt_get_st(dst_bo-
>>>> ttm);
>>> -
>>> + dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource);
>>> __i915_ttm_move(src_bo, false, dst_bo->resource, dst_bo-
>>>> ttm,
>>> - dst_st, allow_accel);
>>> + dst_rsgt, allow_accel);
>>> +
>>> + i915_refct_sgt_put(dst_rsgt);
>>>
>>> return 0;
>>> }
>>> diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c
>>> b/drivers/gpu/drm/i915/i915_scatterlist.c
>>> index 4a6712dca838..8a510ee5d1ad 100644
>>> --- a/drivers/gpu/drm/i915/i915_scatterlist.c
>>> +++ b/drivers/gpu/drm/i915/i915_scatterlist.c
>>> @@ -41,8 +41,32 @@ bool i915_sg_trim(struct sg_table *orig_st)
>>> return true;
>>> }
>>>
>>> +static void i915_refct_sgt_release(struct kref *ref)
>>> +{
>>> + struct i915_refct_sgt *rsgt =
>>> + container_of(ref, typeof(*rsgt), kref);
>>> +
>>> + sg_free_table(&rsgt->table);
>>> + kfree(rsgt);
>>> +}
>>> +
>>> +static const struct i915_refct_sgt_ops rsgt_ops = {
>>> + .release = i915_refct_sgt_release
>>> +};
>>> +
>>> +/**
>>> + * i915_refct_sgt_init - Initialize a struct i915_refct_sgt with
>>> default ops
>>> + * @rsgt: The struct i915_refct_sgt to initialize.
>>> + * size: The size of the underlying memory buffer.
>>> + */
>>> +void i915_refct_sgt_init(struct i915_refct_sgt *rsgt, size_t size)
>>> +{
>>> + i915_refct_sgt_init_ops(rsgt, size, &rsgt_ops);
>>> +}
>>> +
>>> /**
>>> - * i915_sg_from_mm_node - Create an sg_table from a struct
>>> drm_mm_node
>>> + * i915_rsgt_from_mm_node - Create a refcounted sg_table from a
>>> struct
>>> + * drm_mm_node
>>> * @node: The drm_mm_node.
>>> * @region_start: An offset to add to the dma addresses of the sg
>>> list.
>>> *
>>> @@ -50,25 +74,28 @@ bool i915_sg_trim(struct sg_table *orig_st)
>>> * taking a maximum segment length into account, splitting into
>>> segments
>>> * if necessary.
>>> *
>>> - * Return: A pointer to a kmalloced struct sg_table on success,
>>> negative
>>> + * Return: A pointer to a kmalloced struct i915_refct_sgt on
>>> success, negative
>>> * error code cast to an error pointer on failure.
>>> */
>>> -struct sg_table *i915_sg_from_mm_node(const struct drm_mm_node
>>> *node,
>>> - u64 region_start)
>>> +struct i915_refct_sgt *i915_rsgt_from_mm_node(const struct
>>> drm_mm_node *node,
>>> + u64 region_start)
>>> {
>>> const u64 max_segment = SZ_1G; /* Do we have a limit on
>>> this? */
>>> u64 segment_pages = max_segment >> PAGE_SHIFT;
>>> u64 block_size, offset, prev_end;
>>> + struct i915_refct_sgt *rsgt;
>>> struct sg_table *st;
>>> struct scatterlist *sg;
>>>
>>> - st = kmalloc(sizeof(*st), GFP_KERNEL);
>>> - if (!st)
>>> + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
>>> + if (!rsgt)
>>> return ERR_PTR(-ENOMEM);
>>>
>>> + i915_refct_sgt_init(rsgt, node->size << PAGE_SHIFT);
>>> + st = &rsgt->table;
>>> if (sg_alloc_table(st, DIV_ROUND_UP(node->size,
>>> segment_pages),
>>> GFP_KERNEL)) {
>>> - kfree(st);
>>> + i915_refct_sgt_put(rsgt);
>>> return ERR_PTR(-ENOMEM);
>>> }
>>>
>>> @@ -104,11 +131,11 @@ struct sg_table *i915_sg_from_mm_node(const
>>> struct drm_mm_node *node,
>>> sg_mark_end(sg);
>>> i915_sg_trim(st);
>>>
>>> - return st;
>>> + return rsgt;
>>> }
>>>
>>> /**
>>> - * i915_sg_from_buddy_resource - Create an sg_table from a struct
>>> + * i915_rsgt_from_buddy_resource - Create a refcounted sg_table
>>> from a struct
>>> * i915_buddy_block list
>>> * @res: The struct i915_ttm_buddy_resource.
>>> * @region_start: An offset to add to the dma addresses of the sg
>>> list.
>>> @@ -117,11 +144,11 @@ struct sg_table *i915_sg_from_mm_node(const
>>> struct drm_mm_node *node,
>>> * taking a maximum segment length into account, splitting into
>>> segments
>>> * if necessary.
>>> *
>>> - * Return: A pointer to a kmalloced struct sg_table on success,
>>> negative
>>> + * Return: A pointer to a kmalloced struct i915_refct_sgts 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_refct_sgt *i915_rsgt_from_buddy_resource(struct
>>> ttm_resource *res,
>>> + u64
>>> region_start)
>>> {
>>> struct i915_ttm_buddy_resource *bman_res =
>>> to_ttm_buddy_resource(res);
>>> const u64 size = res->num_pages << PAGE_SHIFT;
>>> @@ -129,18 +156,21 @@ struct sg_table
>>> *i915_sg_from_buddy_resource(struct ttm_resource *res,
>>> struct i915_buddy_mm *mm = bman_res->mm;
>>> struct list_head *blocks = &bman_res->blocks;
>>> struct i915_buddy_block *block;
>>> + struct i915_refct_sgt *rsgt;
>>> 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)
>>> + rsgt = kmalloc(sizeof(*rsgt), GFP_KERNEL);
>>> + if (!rsgt)
>>> return ERR_PTR(-ENOMEM);
>>>
>>> + i915_refct_sgt_init(rsgt, size);
>>> + st = &rsgt->table;
>>> if (sg_alloc_table(st, res->num_pages, GFP_KERNEL)) {
>>> - kfree(st);
>>> + i915_refct_sgt_put(rsgt);
>>> return ERR_PTR(-ENOMEM);
>>> }
>>>
>>> @@ -181,7 +211,7 @@ struct sg_table
>>> *i915_sg_from_buddy_resource(struct ttm_resource *res,
>>> sg_mark_end(sg);
>>> i915_sg_trim(st);
>>>
>>> - return st;
>>> + return rsgt;
>>> }
>>>
>>> #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
>>> diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h
>>> b/drivers/gpu/drm/i915/i915_scatterlist.h
>>> index b8bd5925b03f..321fd4a9f777 100644
>>> --- a/drivers/gpu/drm/i915/i915_scatterlist.h
>>> +++ b/drivers/gpu/drm/i915/i915_scatterlist.h
>>> @@ -144,10 +144,78 @@ static inline unsigned int
>>> i915_sg_segment_size(void)
>>>
>>> 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 i915_refct_sgt_ops - Operations structure for struct
>>> i915_refct_sgt
>>> + */
>>> +struct i915_refct_sgt_ops {
>>> + /**
>>> + * release() - Free the memory of the struct i915_refct_sgt
>>> + * @ref: struct kref that is embedded in the struct
>>> i915_refct_sgt
>>> + */
>>> + void (*release)(struct kref *ref);
>>> +};
>>> +
>>> +/**
>>> + * struct i915_refct_sgt - A refcounted scatter-gather table
>>> + * @kref: struct kref for refcounting
>>> + * @table: struct sg_table holding the scatter-gather table
>>> itself. Note that
>>> + * @table->sgl = NULL can be used to determine whether a scatter-
>>> gather table
>>> + * is present or not.
>>> + * @size: The size in bytes of the underlying memory buffer
>>> + * @ops: The operations structure.
>>> + */
>>> +struct i915_refct_sgt {
>>> + struct kref kref;
>>> + struct sg_table table;
>>> + size_t size;
>>> + const struct i915_refct_sgt_ops *ops;
>>> +};
>>> +
>>> +/**
>>> + * i915_refct_sgt_put - Put a refcounted sg-table
>>> + * @rsgt the struct i915_refct_sgt to put.
>>> + */
>>> +static inline void i915_refct_sgt_put(struct i915_refct_sgt *rsgt)
>>> +{
>>> + if (rsgt)
>>> + kref_put(&rsgt->kref, rsgt->ops->release);
>>> +}
>>> +
>>> +/**
>>> + * i915_refct_sgt_get - Get a refcounted sg-table
>>> + * @rsgt the struct i915_refct_sgt to get.
>>> + */
>>> +static inline struct i915_refct_sgt *
>>> +i915_refct_sgt_get(struct i915_refct_sgt *rsgt)
>>> +{
>>> + kref_get(&rsgt->kref);
>>> + return rsgt;
>>> +}
>>> +
>>> +/**
>>> + * i915_refct_sgt_init_ops - Initialize a refcounted sg-list with
>>> a custom
>>> + * operations structure
>>> + * @rsgt The struct i915_refct_sgt to initialize.
>>> + * @size: Size in bytes of the underlying memory buffer.
>>> + * @ops: A customized operations structure in case the refcounted
>>> sg-list
>>> + * is embedded into another structure.
>>> + */
>>> +static inline void i915_refct_sgt_init_ops(struct i915_refct_sgt
>>> *rsgt,
>>> + size_t size,
>>> + const struct
>>> i915_refct_sgt_ops *ops)
>>> +{
>>> + kref_init(&rsgt->kref);
>>> + rsgt->table.sgl = NULL;
>>> + rsgt->size = size;
>>> + rsgt->ops = ops;
>>> +}
>>
>> Could maybe make this __i915_refct_sgt_init(), since it inits more
>> than
>> just the ops?
>>
>>
>
> Will change.
>
> Thanks,
> Thomas
>
>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-28 8:47 ` Matthew Auld
@ 2021-10-28 9:35 ` Thomas Hellström
2021-10-28 9:58 ` Matthew Auld
0 siblings, 1 reply; 15+ messages in thread
From: Thomas Hellström @ 2021-10-28 9:35 UTC (permalink / raw)
To: Matthew Auld, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On 10/28/21 10:47, Matthew Auld wrote:
> On 28/10/2021 08:04, Thomas Hellström wrote:
>> On Wed, 2021-10-27 at 19:03 +0100, Matthew Auld wrote:
>>> On 27/10/2021 11:52, Thomas Hellström wrote:
>>>> As we start to introduce asynchronous failsafe object migration,
>>>> where we update the object state and then submit asynchronous
>>>> commands we need to record what memory resources are actually used
>>>> by various part of the command stream. Initially for three
>>>> purposes:
>>>>
>>>> 1) Error capture.
>>>> 2) Asynchronous migration error recovery.
>>>> 3) Asynchronous vma bind.
>>>>
>>>> At the time where these happens, the object state may have been
>>>> updated
>>>> to be several migrations ahead and object sg-tables discarded.
>>>>
>>>> In order to make it possible to keep sg-tables with memory resource
>>>> information for these operations, introduce refcounted sg-tables
>>>> that
>>>> aren't freed until the last user is done with them.
>>>>
>>>> The alternative would be to reference information sitting on the
>>>> corresponding ttm_resources which typically have the same lifetime
>>>> as
>>>> these refcountes sg_tables, but that leads to other awkward
>>>> constructs:
>>>> Due to the design direction chosen for ttm resource managers that
>>>> would
>>>> lead to diamond-style inheritance, the LMEM resources may sometimes
>>>> be
>>>> prematurely freed, and finally the subclassed struct ttm_resource
>>>> would
>>>> have to bleed into the asynchronous vma bind code.
>>>>
>>>> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>>> ---
>>>> drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
>>>> .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
>>>> drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
>>>> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++--
>>>> -----
>>>> drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
>>>> drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
>>>> drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
>>>> drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
>>>> drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
>>>> 9 files changed, 262 insertions(+), 119 deletions(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>> index a5479ac7a4ad..c5ab364d4311 100644
>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>> @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct
>>>> drm_i915_private *i915,
>>>> size_t size, struct
>>>> intel_memory_region *mr,
>>>> struct address_space *mapping,
>>>> unsigned int max_segment);
>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>> *mapping,
>>>> - bool dirty, bool backup);
>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>> *mapping,
>>>> + bool dirty, bool backup);
>>>
>>> s/st_table/sg_table/?
>>>
>>> I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
>>
>> Yes the naming is indeed a bit unfortunate here. To be consistent with
>> the core's sg_free_table(), I changed to
>> shmem_sg_free_table() / shmem_sg_alloc_table.
>>
>>>
>>>
>>>> void __shmem_writeback(size_t size, struct address_space
>>>> *mapping);
>>>> #ifdef CONFIG_MMU_NOTIFIER
>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>> index a4b69a43b898..604ed5ad77f5 100644
>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>> @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
>>>> */
>>>> struct list_head region_link;
>>>> + struct i915_refct_sgt *rsgt;
>>>> struct sg_table *pages;
>>>> void *mapping;
>>>> @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
>>>> } mm;
>>>> struct {
>>>> - struct sg_table *cached_io_st;
>>>> + struct i915_refct_sgt *cached_io_rsgt;
>>>> struct i915_gem_object_page_iter get_io_page;
>>>> struct drm_i915_gem_object *backup;
>>>> bool created:1;
>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>> b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>> index 01f332d8dbde..67c6bee695c7 100644
>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>> @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec
>>>> *pvec)
>>>> cond_resched();
>>>> }
>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>> *mapping,
>>>> - bool dirty, bool backup)
>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>> *mapping,
>>>> + bool dirty, bool backup)
>>>> {
>>>> struct sgt_iter sgt_iter;
>>>> struct pagevec pvec;
>>>> @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct
>>>> address_space *mapping,
>>>> check_release_pagevec(&pvec);
>>>> sg_free_table(st);
>>>> - kfree(st);
>>>> }
>>>> struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
>>>> @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct
>>>> drm_i915_private *i915,
>>>> err_sg:
>>>> sg_mark_end(sg);
>>>> if (sg != st->sgl) {
>>>> - shmem_free_st(st, mapping, false, false);
>>>> + shmem_free_st_table(st, mapping, false, false);
>>>> + kfree(st);
>>>> } else {
>>>> mapping_clear_unevictable(mapping);
>>>> sg_free_table(st);
>>>> @@ -254,7 +254,8 @@ static int shmem_get_pages(struct
>>>> drm_i915_gem_object *obj)
>>>> return 0;
>>>> err_pages:
>>>> - shmem_free_st(st, mapping, false, false);
>>>> + shmem_free_st_table(st, mapping, false, false);
>>>> + kfree(st);
>>>> /*
>>>> * shmemfs first checks if there is enough memory to
>>>> allocate the page
>>>> * and reports ENOSPC should there be insufficient, along
>>>> with the usual
>>>> @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct
>>>> drm_i915_gem_object *obj, struct sg_
>>>> if (i915_gem_object_needs_bit17_swizzle(obj))
>>>> i915_gem_object_save_bit_17_swizzle(obj, pages);
>>>> - shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
>>>> - obj->mm.dirty, obj->mm.madv ==
>>>> I915_MADV_WILLNEED);
>>>> + shmem_free_st_table(pages, file_inode(obj->base.filp)-
>>>>> i_mapping,
>>>> + obj->mm.dirty, obj->mm.madv ==
>>>> I915_MADV_WILLNEED);
>>>> + kfree(pages);
>>>> obj->mm.dirty = false;
>>>> }
>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>> b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>> index 4fd2edb20dd9..6826e3859e18 100644
>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>> @@ -34,7 +34,7 @@
>>>> * struct i915_ttm_tt - TTM page vector with additional private
>>>> information
>>>> * @ttm: The base TTM page vector.
>>>> * @dev: The struct device used for dma mapping and unmapping.
>>>> - * @cached_st: The cached scatter-gather table.
>>>> + * @cached_rsgt: The cached scatter-gather table.
>>>> * @is_shmem: Set if using shmem.
>>>> * @filp: The shmem file, if using shmem backend.
>>>> *
>>>> @@ -47,7 +47,7 @@
>>>> struct i915_ttm_tt {
>>>> struct ttm_tt ttm;
>>>> struct device *dev;
>>>> - struct sg_table *cached_st;
>>>> + struct i915_refct_sgt cached_rsgt;
>>>> bool is_shmem;
>>>> struct file *filp;
>>>> @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct
>>>> ttm_device *bdev,
>>>> if (IS_ERR(st))
>>>> return PTR_ERR(st);
>>>> - err = dma_map_sg_attrs(i915_tt->dev,
>>>> - st->sgl, st->nents,
>>>> - DMA_BIDIRECTIONAL,
>>>> - DMA_ATTR_SKIP_CPU_SYNC);
>>>> - if (err <= 0) {
>>>> - err = -EINVAL;
>>>> + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
>>>> + DMA_ATTR_SKIP_CPU_SYNC);
>>>> + if (err)
>>>> goto err_free_st;
>>>> - }
>>>> i = 0;
>>>> for_each_sgt_page(page, sgt_iter, st)
>>>> @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct
>>>> ttm_device *bdev,
>>>> if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
>>>> ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
>>>> - i915_tt->cached_st = st;
>>>> + i915_tt->cached_rsgt.table = *st;
>>>> + kfree(st);
>>>
>>> Will it work if the above just operates on the rsgt.table?
>>
>> I'll change the shmem utility here to not allocate the struct sg_table
>> and then we can operate on it directly.
>>
>>>
>>>> +
>>>> return 0;
>>>> err_free_st:
>>>> - shmem_free_st(st, filp->f_mapping, false, false);
>>>> + shmem_free_st_table(st, filp->f_mapping, false, false);
>>>> + kfree(st);
>>>> +
>>>> return err;
>>>> }
>>>> @@ -249,16 +249,29 @@ static void
>>>> i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
>>>> {
>>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>>> typeof(*i915_tt), ttm);
>>>> bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
>>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>>> - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
>>>> - i915_tt->cached_st->nents,
>>>> - DMA_BIDIRECTIONAL);
>>>> + if (st->sgl)
>>>
>>> Can we ever hit this? I would have presumed not? Below also.
>>
>> Yes, here's where we typically free the scatterlist.
>
> What I meant to say: can the above ever not be true? i.e sgl == NULL
Hm, Yes I think it can. If we're populating a non-shmem ttm tt, that
sg-list is, IIRC allocated lazily on first use. Although I haven't
analyzed in detail whether it can actually be populated and then not
lazily allocated under the same lock.
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-28 9:35 ` Thomas Hellström
@ 2021-10-28 9:58 ` Matthew Auld
2021-10-28 11:20 ` Thomas Hellström
0 siblings, 1 reply; 15+ messages in thread
From: Matthew Auld @ 2021-10-28 9:58 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On 28/10/2021 10:35, Thomas Hellström wrote:
>
> On 10/28/21 10:47, Matthew Auld wrote:
>> On 28/10/2021 08:04, Thomas Hellström wrote:
>>> On Wed, 2021-10-27 at 19:03 +0100, Matthew Auld wrote:
>>>> On 27/10/2021 11:52, Thomas Hellström wrote:
>>>>> As we start to introduce asynchronous failsafe object migration,
>>>>> where we update the object state and then submit asynchronous
>>>>> commands we need to record what memory resources are actually used
>>>>> by various part of the command stream. Initially for three
>>>>> purposes:
>>>>>
>>>>> 1) Error capture.
>>>>> 2) Asynchronous migration error recovery.
>>>>> 3) Asynchronous vma bind.
>>>>>
>>>>> At the time where these happens, the object state may have been
>>>>> updated
>>>>> to be several migrations ahead and object sg-tables discarded.
>>>>>
>>>>> In order to make it possible to keep sg-tables with memory resource
>>>>> information for these operations, introduce refcounted sg-tables
>>>>> that
>>>>> aren't freed until the last user is done with them.
>>>>>
>>>>> The alternative would be to reference information sitting on the
>>>>> corresponding ttm_resources which typically have the same lifetime
>>>>> as
>>>>> these refcountes sg_tables, but that leads to other awkward
>>>>> constructs:
>>>>> Due to the design direction chosen for ttm resource managers that
>>>>> would
>>>>> lead to diamond-style inheritance, the LMEM resources may sometimes
>>>>> be
>>>>> prematurely freed, and finally the subclassed struct ttm_resource
>>>>> would
>>>>> have to bleed into the asynchronous vma bind code.
>>>>>
>>>>> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>>>> ---
>>>>> drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
>>>>> .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
>>>>> drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
>>>>> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++--
>>>>> -----
>>>>> drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
>>>>> drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
>>>>> drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
>>>>> drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
>>>>> drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
>>>>> 9 files changed, 262 insertions(+), 119 deletions(-)
>>>>>
>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>> index a5479ac7a4ad..c5ab364d4311 100644
>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>> @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct
>>>>> drm_i915_private *i915,
>>>>> size_t size, struct
>>>>> intel_memory_region *mr,
>>>>> struct address_space *mapping,
>>>>> unsigned int max_segment);
>>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>>> *mapping,
>>>>> - bool dirty, bool backup);
>>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>>> *mapping,
>>>>> + bool dirty, bool backup);
>>>>
>>>> s/st_table/sg_table/?
>>>>
>>>> I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
>>>
>>> Yes the naming is indeed a bit unfortunate here. To be consistent with
>>> the core's sg_free_table(), I changed to
>>> shmem_sg_free_table() / shmem_sg_alloc_table.
>>>
>>>>
>>>>
>>>>> void __shmem_writeback(size_t size, struct address_space
>>>>> *mapping);
>>>>> #ifdef CONFIG_MMU_NOTIFIER
>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>> index a4b69a43b898..604ed5ad77f5 100644
>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>> @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
>>>>> */
>>>>> struct list_head region_link;
>>>>> + struct i915_refct_sgt *rsgt;
>>>>> struct sg_table *pages;
>>>>> void *mapping;
>>>>> @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
>>>>> } mm;
>>>>> struct {
>>>>> - struct sg_table *cached_io_st;
>>>>> + struct i915_refct_sgt *cached_io_rsgt;
>>>>> struct i915_gem_object_page_iter get_io_page;
>>>>> struct drm_i915_gem_object *backup;
>>>>> bool created:1;
>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>> index 01f332d8dbde..67c6bee695c7 100644
>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>> @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec
>>>>> *pvec)
>>>>> cond_resched();
>>>>> }
>>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>>> *mapping,
>>>>> - bool dirty, bool backup)
>>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>>> *mapping,
>>>>> + bool dirty, bool backup)
>>>>> {
>>>>> struct sgt_iter sgt_iter;
>>>>> struct pagevec pvec;
>>>>> @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct
>>>>> address_space *mapping,
>>>>> check_release_pagevec(&pvec);
>>>>> sg_free_table(st);
>>>>> - kfree(st);
>>>>> }
>>>>> struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
>>>>> @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct
>>>>> drm_i915_private *i915,
>>>>> err_sg:
>>>>> sg_mark_end(sg);
>>>>> if (sg != st->sgl) {
>>>>> - shmem_free_st(st, mapping, false, false);
>>>>> + shmem_free_st_table(st, mapping, false, false);
>>>>> + kfree(st);
>>>>> } else {
>>>>> mapping_clear_unevictable(mapping);
>>>>> sg_free_table(st);
>>>>> @@ -254,7 +254,8 @@ static int shmem_get_pages(struct
>>>>> drm_i915_gem_object *obj)
>>>>> return 0;
>>>>> err_pages:
>>>>> - shmem_free_st(st, mapping, false, false);
>>>>> + shmem_free_st_table(st, mapping, false, false);
>>>>> + kfree(st);
>>>>> /*
>>>>> * shmemfs first checks if there is enough memory to
>>>>> allocate the page
>>>>> * and reports ENOSPC should there be insufficient, along
>>>>> with the usual
>>>>> @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct
>>>>> drm_i915_gem_object *obj, struct sg_
>>>>> if (i915_gem_object_needs_bit17_swizzle(obj))
>>>>> i915_gem_object_save_bit_17_swizzle(obj, pages);
>>>>> - shmem_free_st(pages, file_inode(obj->base.filp)->i_mapping,
>>>>> - obj->mm.dirty, obj->mm.madv ==
>>>>> I915_MADV_WILLNEED);
>>>>> + shmem_free_st_table(pages, file_inode(obj->base.filp)-
>>>>>> i_mapping,
>>>>> + obj->mm.dirty, obj->mm.madv ==
>>>>> I915_MADV_WILLNEED);
>>>>> + kfree(pages);
>>>>> obj->mm.dirty = false;
>>>>> }
>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>> index 4fd2edb20dd9..6826e3859e18 100644
>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>> @@ -34,7 +34,7 @@
>>>>> * struct i915_ttm_tt - TTM page vector with additional private
>>>>> information
>>>>> * @ttm: The base TTM page vector.
>>>>> * @dev: The struct device used for dma mapping and unmapping.
>>>>> - * @cached_st: The cached scatter-gather table.
>>>>> + * @cached_rsgt: The cached scatter-gather table.
>>>>> * @is_shmem: Set if using shmem.
>>>>> * @filp: The shmem file, if using shmem backend.
>>>>> *
>>>>> @@ -47,7 +47,7 @@
>>>>> struct i915_ttm_tt {
>>>>> struct ttm_tt ttm;
>>>>> struct device *dev;
>>>>> - struct sg_table *cached_st;
>>>>> + struct i915_refct_sgt cached_rsgt;
>>>>> bool is_shmem;
>>>>> struct file *filp;
>>>>> @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct
>>>>> ttm_device *bdev,
>>>>> if (IS_ERR(st))
>>>>> return PTR_ERR(st);
>>>>> - err = dma_map_sg_attrs(i915_tt->dev,
>>>>> - st->sgl, st->nents,
>>>>> - DMA_BIDIRECTIONAL,
>>>>> - DMA_ATTR_SKIP_CPU_SYNC);
>>>>> - if (err <= 0) {
>>>>> - err = -EINVAL;
>>>>> + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
>>>>> + DMA_ATTR_SKIP_CPU_SYNC);
>>>>> + if (err)
>>>>> goto err_free_st;
>>>>> - }
>>>>> i = 0;
>>>>> for_each_sgt_page(page, sgt_iter, st)
>>>>> @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct
>>>>> ttm_device *bdev,
>>>>> if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
>>>>> ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
>>>>> - i915_tt->cached_st = st;
>>>>> + i915_tt->cached_rsgt.table = *st;
>>>>> + kfree(st);
>>>>
>>>> Will it work if the above just operates on the rsgt.table?
>>>
>>> I'll change the shmem utility here to not allocate the struct sg_table
>>> and then we can operate on it directly.
>>>
>>>>
>>>>> +
>>>>> return 0;
>>>>> err_free_st:
>>>>> - shmem_free_st(st, filp->f_mapping, false, false);
>>>>> + shmem_free_st_table(st, filp->f_mapping, false, false);
>>>>> + kfree(st);
>>>>> +
>>>>> return err;
>>>>> }
>>>>> @@ -249,16 +249,29 @@ static void
>>>>> i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
>>>>> {
>>>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>>>> typeof(*i915_tt), ttm);
>>>>> bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
>>>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>>>> - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
>>>>> - i915_tt->cached_st->nents,
>>>>> - DMA_BIDIRECTIONAL);
>>>>> + if (st->sgl)
>>>>
>>>> Can we ever hit this? I would have presumed not? Below also.
>>>
>>> Yes, here's where we typically free the scatterlist.
>>
>> What I meant to say: can the above ever not be true? i.e sgl == NULL
>
> Hm, Yes I think it can. If we're populating a non-shmem ttm tt, that
> sg-list is, IIRC allocated lazily on first use. Although I haven't
> analyzed in detail whether it can actually be populated and then not
> lazily allocated under the same lock.
Oh right. I guess we could maybe drop the check in the shmem part?
>
>
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables
2021-10-28 9:58 ` Matthew Auld
@ 2021-10-28 11:20 ` Thomas Hellström
0 siblings, 0 replies; 15+ messages in thread
From: Thomas Hellström @ 2021-10-28 11:20 UTC (permalink / raw)
To: Matthew Auld, intel-gfx, dri-devel; +Cc: maarten.lankhorst
On 10/28/21 11:58, Matthew Auld wrote:
> On 28/10/2021 10:35, Thomas Hellström wrote:
>>
>> On 10/28/21 10:47, Matthew Auld wrote:
>>> On 28/10/2021 08:04, Thomas Hellström wrote:
>>>> On Wed, 2021-10-27 at 19:03 +0100, Matthew Auld wrote:
>>>>> On 27/10/2021 11:52, Thomas Hellström wrote:
>>>>>> As we start to introduce asynchronous failsafe object migration,
>>>>>> where we update the object state and then submit asynchronous
>>>>>> commands we need to record what memory resources are actually used
>>>>>> by various part of the command stream. Initially for three
>>>>>> purposes:
>>>>>>
>>>>>> 1) Error capture.
>>>>>> 2) Asynchronous migration error recovery.
>>>>>> 3) Asynchronous vma bind.
>>>>>>
>>>>>> At the time where these happens, the object state may have been
>>>>>> updated
>>>>>> to be several migrations ahead and object sg-tables discarded.
>>>>>>
>>>>>> In order to make it possible to keep sg-tables with memory resource
>>>>>> information for these operations, introduce refcounted sg-tables
>>>>>> that
>>>>>> aren't freed until the last user is done with them.
>>>>>>
>>>>>> The alternative would be to reference information sitting on the
>>>>>> corresponding ttm_resources which typically have the same lifetime
>>>>>> as
>>>>>> these refcountes sg_tables, but that leads to other awkward
>>>>>> constructs:
>>>>>> Due to the design direction chosen for ttm resource managers that
>>>>>> would
>>>>>> lead to diamond-style inheritance, the LMEM resources may sometimes
>>>>>> be
>>>>>> prematurely freed, and finally the subclassed struct ttm_resource
>>>>>> would
>>>>>> have to bleed into the asynchronous vma bind code.
>>>>>>
>>>>>> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
>>>>>> ---
>>>>>> drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +-
>>>>>> .../gpu/drm/i915/gem/i915_gem_object_types.h | 3 +-
>>>>>> drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 16 +-
>>>>>> drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 188 +++++++++++--
>>>>>> -----
>>>>>> drivers/gpu/drm/i915/i915_scatterlist.c | 62 ++++--
>>>>>> drivers/gpu/drm/i915/i915_scatterlist.h | 76 ++++++-
>>>>>> drivers/gpu/drm/i915/intel_region_ttm.c | 15 +-
>>>>>> drivers/gpu/drm/i915/intel_region_ttm.h | 5 +-
>>>>>> drivers/gpu/drm/i915/selftests/mock_region.c | 12 +-
>>>>>> 9 files changed, 262 insertions(+), 119 deletions(-)
>>>>>>
>>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>>> index a5479ac7a4ad..c5ab364d4311 100644
>>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
>>>>>> @@ -624,8 +624,8 @@ struct sg_table *shmem_alloc_st(struct
>>>>>> drm_i915_private *i915,
>>>>>> size_t size, struct
>>>>>> intel_memory_region *mr,
>>>>>> struct address_space *mapping,
>>>>>> unsigned int max_segment);
>>>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>>>> *mapping,
>>>>>> - bool dirty, bool backup);
>>>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>>>> *mapping,
>>>>>> + bool dirty, bool backup);
>>>>>
>>>>> s/st_table/sg_table/?
>>>>>
>>>>> I thought st was shorthand for sg_table? Maybe shmem_sg_free_table?
>>>>
>>>> Yes the naming is indeed a bit unfortunate here. To be consistent with
>>>> the core's sg_free_table(), I changed to
>>>> shmem_sg_free_table() / shmem_sg_alloc_table.
>>>>
>>>>>
>>>>>
>>>>>> void __shmem_writeback(size_t size, struct address_space
>>>>>> *mapping);
>>>>>> #ifdef CONFIG_MMU_NOTIFIER
>>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>>> index a4b69a43b898..604ed5ad77f5 100644
>>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
>>>>>> @@ -544,6 +544,7 @@ struct drm_i915_gem_object {
>>>>>> */
>>>>>> struct list_head region_link;
>>>>>> + struct i915_refct_sgt *rsgt;
>>>>>> struct sg_table *pages;
>>>>>> void *mapping;
>>>>>> @@ -597,7 +598,7 @@ struct drm_i915_gem_object {
>>>>>> } mm;
>>>>>> struct {
>>>>>> - struct sg_table *cached_io_st;
>>>>>> + struct i915_refct_sgt *cached_io_rsgt;
>>>>>> struct i915_gem_object_page_iter get_io_page;
>>>>>> struct drm_i915_gem_object *backup;
>>>>>> bool created:1;
>>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>>> index 01f332d8dbde..67c6bee695c7 100644
>>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
>>>>>> @@ -25,8 +25,8 @@ static void check_release_pagevec(struct pagevec
>>>>>> *pvec)
>>>>>> cond_resched();
>>>>>> }
>>>>>> -void shmem_free_st(struct sg_table *st, struct address_space
>>>>>> *mapping,
>>>>>> - bool dirty, bool backup)
>>>>>> +void shmem_free_st_table(struct sg_table *st, struct address_space
>>>>>> *mapping,
>>>>>> + bool dirty, bool backup)
>>>>>> {
>>>>>> struct sgt_iter sgt_iter;
>>>>>> struct pagevec pvec;
>>>>>> @@ -49,7 +49,6 @@ void shmem_free_st(struct sg_table *st, struct
>>>>>> address_space *mapping,
>>>>>> check_release_pagevec(&pvec);
>>>>>> sg_free_table(st);
>>>>>> - kfree(st);
>>>>>> }
>>>>>> struct sg_table *shmem_alloc_st(struct drm_i915_private *i915,
>>>>>> @@ -171,7 +170,8 @@ struct sg_table *shmem_alloc_st(struct
>>>>>> drm_i915_private *i915,
>>>>>> err_sg:
>>>>>> sg_mark_end(sg);
>>>>>> if (sg != st->sgl) {
>>>>>> - shmem_free_st(st, mapping, false, false);
>>>>>> + shmem_free_st_table(st, mapping, false, false);
>>>>>> + kfree(st);
>>>>>> } else {
>>>>>> mapping_clear_unevictable(mapping);
>>>>>> sg_free_table(st);
>>>>>> @@ -254,7 +254,8 @@ static int shmem_get_pages(struct
>>>>>> drm_i915_gem_object *obj)
>>>>>> return 0;
>>>>>> err_pages:
>>>>>> - shmem_free_st(st, mapping, false, false);
>>>>>> + shmem_free_st_table(st, mapping, false, false);
>>>>>> + kfree(st);
>>>>>> /*
>>>>>> * shmemfs first checks if there is enough memory to
>>>>>> allocate the page
>>>>>> * and reports ENOSPC should there be insufficient, along
>>>>>> with the usual
>>>>>> @@ -374,8 +375,9 @@ void i915_gem_object_put_pages_shmem(struct
>>>>>> drm_i915_gem_object *obj, struct sg_
>>>>>> if (i915_gem_object_needs_bit17_swizzle(obj))
>>>>>> i915_gem_object_save_bit_17_swizzle(obj, pages);
>>>>>> - shmem_free_st(pages,
>>>>>> file_inode(obj->base.filp)->i_mapping,
>>>>>> - obj->mm.dirty, obj->mm.madv ==
>>>>>> I915_MADV_WILLNEED);
>>>>>> + shmem_free_st_table(pages, file_inode(obj->base.filp)-
>>>>>>> i_mapping,
>>>>>> + obj->mm.dirty, obj->mm.madv ==
>>>>>> I915_MADV_WILLNEED);
>>>>>> + kfree(pages);
>>>>>> obj->mm.dirty = false;
>>>>>> }
>>>>>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>>> b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>>> index 4fd2edb20dd9..6826e3859e18 100644
>>>>>> --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
>>>>>> @@ -34,7 +34,7 @@
>>>>>> * struct i915_ttm_tt - TTM page vector with additional private
>>>>>> information
>>>>>> * @ttm: The base TTM page vector.
>>>>>> * @dev: The struct device used for dma mapping and unmapping.
>>>>>> - * @cached_st: The cached scatter-gather table.
>>>>>> + * @cached_rsgt: The cached scatter-gather table.
>>>>>> * @is_shmem: Set if using shmem.
>>>>>> * @filp: The shmem file, if using shmem backend.
>>>>>> *
>>>>>> @@ -47,7 +47,7 @@
>>>>>> struct i915_ttm_tt {
>>>>>> struct ttm_tt ttm;
>>>>>> struct device *dev;
>>>>>> - struct sg_table *cached_st;
>>>>>> + struct i915_refct_sgt cached_rsgt;
>>>>>> bool is_shmem;
>>>>>> struct file *filp;
>>>>>> @@ -221,14 +221,10 @@ static int i915_ttm_tt_shmem_populate(struct
>>>>>> ttm_device *bdev,
>>>>>> if (IS_ERR(st))
>>>>>> return PTR_ERR(st);
>>>>>> - err = dma_map_sg_attrs(i915_tt->dev,
>>>>>> - st->sgl, st->nents,
>>>>>> - DMA_BIDIRECTIONAL,
>>>>>> - DMA_ATTR_SKIP_CPU_SYNC);
>>>>>> - if (err <= 0) {
>>>>>> - err = -EINVAL;
>>>>>> + err = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL,
>>>>>> + DMA_ATTR_SKIP_CPU_SYNC);
>>>>>> + if (err)
>>>>>> goto err_free_st;
>>>>>> - }
>>>>>> i = 0;
>>>>>> for_each_sgt_page(page, sgt_iter, st)
>>>>>> @@ -237,11 +233,15 @@ static int i915_ttm_tt_shmem_populate(struct
>>>>>> ttm_device *bdev,
>>>>>> if (ttm->page_flags & TTM_TT_FLAG_SWAPPED)
>>>>>> ttm->page_flags &= ~TTM_TT_FLAG_SWAPPED;
>>>>>> - i915_tt->cached_st = st;
>>>>>> + i915_tt->cached_rsgt.table = *st;
>>>>>> + kfree(st);
>>>>>
>>>>> Will it work if the above just operates on the rsgt.table?
>>>>
>>>> I'll change the shmem utility here to not allocate the struct sg_table
>>>> and then we can operate on it directly.
>>>>
>>>>>
>>>>>> +
>>>>>> return 0;
>>>>>> err_free_st:
>>>>>> - shmem_free_st(st, filp->f_mapping, false, false);
>>>>>> + shmem_free_st_table(st, filp->f_mapping, false, false);
>>>>>> + kfree(st);
>>>>>> +
>>>>>> return err;
>>>>>> }
>>>>>> @@ -249,16 +249,29 @@ static void
>>>>>> i915_ttm_tt_shmem_unpopulate(struct ttm_tt *ttm)
>>>>>> {
>>>>>> struct i915_ttm_tt *i915_tt = container_of(ttm,
>>>>>> typeof(*i915_tt), ttm);
>>>>>> bool backup = ttm->page_flags & TTM_TT_FLAG_SWAPPED;
>>>>>> + struct sg_table *st = &i915_tt->cached_rsgt.table;
>>>>>> - dma_unmap_sg(i915_tt->dev, i915_tt->cached_st->sgl,
>>>>>> - i915_tt->cached_st->nents,
>>>>>> - DMA_BIDIRECTIONAL);
>>>>>> + if (st->sgl)
>>>>>
>>>>> Can we ever hit this? I would have presumed not? Below also.
>>>>
>>>> Yes, here's where we typically free the scatterlist.
>>>
>>> What I meant to say: can the above ever not be true? i.e sgl == NULL
>>
>> Hm, Yes I think it can. If we're populating a non-shmem ttm tt, that
>> sg-list is, IIRC allocated lazily on first use. Although I haven't
>> analyzed in detail whether it can actually be populated and then not
>> lazily allocated under the same lock.
>
> Oh right. I guess we could maybe drop the check in the shmem part?
Ah yes, that should be safe. Will do that. Thanks.
/Thomas
>
>>
>>
^ permalink raw reply [flat|nested] 15+ messages in thread
* [Intel-gfx] [PATCH v2 2/3] drm/i915: Update error capture code to avoid using the current vma state
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables Thomas Hellström
@ 2021-10-27 10:52 ` Thomas Hellström
2021-10-28 8:46 ` kernel test robot
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 3/3] drm/i915: Initial introduction of vma resources Thomas Hellström
` (3 subsequent siblings)
5 siblings, 1 reply; 15+ messages in thread
From: Thomas Hellström @ 2021-10-27 10:52 UTC (permalink / raw)
To: intel-gfx, dri-devel
Cc: maarten.lankhorst, matthew.auld, Thomas Hellström
With asynchronous migrations, the vma state may be several migrations
ahead of the state that matches the request we're capturing.
Address that by introducing an i915_vma_snapshot structure that
can be used to snapshot relevant state at request submission.
In order to make sure we access the correct memory, the snapshots take
references on relevant sg-tables and memory regions.
Also move the capture list allocation out of the fence signaling
critical path and use the CONFIG_DRM_I915_CAPTURE_ERROR define to
avoid compiling in members and functions used for error capture
when they're not used.
Finally, correct lockdep annotation would reveal that error capture is
typically done in the fence signalling critical path. Alter the
error capture memory allocation mode accordingly.
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
drivers/gpu/drm/i915/Makefile | 1 +
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 135 ++++++++++---
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 8 +-
.../drm/i915/gt/intel_execlists_submission.c | 2 +-
drivers/gpu/drm/i915/i915_gpu_error.c | 180 +++++++++++++-----
drivers/gpu/drm/i915/i915_request.c | 63 ++++--
drivers/gpu/drm/i915/i915_request.h | 18 +-
drivers/gpu/drm/i915/i915_vma_snapshot.c | 137 +++++++++++++
drivers/gpu/drm/i915/i915_vma_snapshot.h | 112 +++++++++++
9 files changed, 558 insertions(+), 98 deletions(-)
create mode 100644 drivers/gpu/drm/i915/i915_vma_snapshot.c
create mode 100644 drivers/gpu/drm/i915/i915_vma_snapshot.h
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 467872cca027..2424c19cd0bc 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -173,6 +173,7 @@ i915-y += \
i915_trace_points.o \
i915_ttm_buddy_manager.o \
i915_vma.o \
+ i915_vma_snapshot.o \
intel_wopcm.o
# general-purpose microcontroller (GuC) support
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index ea5b7b2a4d70..301eb58bebd1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -29,6 +29,7 @@
#include "i915_gem_ioctls.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
+#include "i915_vma_snapshot.h"
struct eb_vma {
struct i915_vma *vma;
@@ -307,11 +308,15 @@ struct i915_execbuffer {
struct eb_fence *fences;
unsigned long num_fences;
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+ struct i915_capture_list *capture_lists[MAX_ENGINE_INSTANCE + 1];
+#endif
};
static int eb_parse(struct i915_execbuffer *eb);
static int eb_pin_engine(struct i915_execbuffer *eb, bool throttle);
static void eb_unpin_engine(struct i915_execbuffer *eb);
+static void eb_capture_release(struct i915_execbuffer *eb);
static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
{
@@ -1054,6 +1059,7 @@ static void eb_release_vmas(struct i915_execbuffer *eb, bool final)
i915_vma_put(vma);
}
+ eb_capture_release(eb);
eb_unpin_engine(eb);
}
@@ -1891,36 +1897,113 @@ eb_find_first_request_added(struct i915_execbuffer *eb)
return NULL;
}
-static int eb_move_to_gpu(struct i915_execbuffer *eb)
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
+/* Stage with GFP_KERNEL allocations before we enter the signaling critical path */
+static void eb_capture_stage(struct i915_execbuffer *eb)
{
const unsigned int count = eb->buffer_count;
- unsigned int i = count;
- int err = 0, j;
+ unsigned int i = count, j;
+ struct i915_vma_snapshot *vsnap;
while (i--) {
struct eb_vma *ev = &eb->vma[i];
struct i915_vma *vma = ev->vma;
unsigned int flags = ev->flags;
- struct drm_i915_gem_object *obj = vma->obj;
- assert_vma_held(vma);
+ if (!(flags & EXEC_OBJECT_CAPTURE))
+ continue;
- if (flags & EXEC_OBJECT_CAPTURE) {
+ vsnap = i915_vma_snapshot_alloc(GFP_KERNEL);
+ if (!vsnap)
+ continue;
+
+ i915_vma_snapshot_init(vsnap, vma, "user");
+ for_each_batch_create_order(eb, j) {
struct i915_capture_list *capture;
- for_each_batch_create_order(eb, j) {
- if (!eb->requests[j])
- break;
+ capture = kmalloc(sizeof(*capture), GFP_KERNEL);
+ if (!capture)
+ continue;
- capture = kmalloc(sizeof(*capture), GFP_KERNEL);
- if (capture) {
- capture->next =
- eb->requests[j]->capture_list;
- capture->vma = vma;
- eb->requests[j]->capture_list = capture;
- }
- }
+ capture->next = eb->capture_lists[j];
+ capture->vma_snapshot = i915_vma_snapshot_get(vsnap);
+ eb->capture_lists[j] = capture;
+ }
+ i915_vma_snapshot_put(vsnap);
+ }
+}
+
+/* Commit once we're in the critical path */
+static void eb_capture_commit(struct i915_execbuffer *eb)
+{
+ unsigned int j;
+
+ for_each_batch_create_order(eb, j) {
+ struct i915_request *rq = eb->requests[j];
+
+ if (!rq)
+ break;
+
+ rq->capture_list = eb->capture_lists[j];
+ eb->capture_lists[j] = NULL;
+ }
+}
+
+/*
+ * Release anything that didn't get committed due to errors.
+ * The capture_list will otherwise be freed at request retire.
+ */
+static void eb_capture_release(struct i915_execbuffer *eb)
+{
+ unsigned int j;
+
+ for_each_batch_create_order(eb, j) {
+ if (eb->capture_lists[j]) {
+ i915_request_free_capture_list(eb->capture_lists[j]);
+ eb->capture_lists[j] = NULL;
}
+ }
+}
+
+static void eb_capture_list_clear(struct i915_execbuffer *eb)
+{
+ memset(eb->capture_lists, 0, sizeof(eb->capture_lists));
+}
+
+#else
+
+static void eb_capture_stage(struct i915_execbuffer *eb)
+{
+}
+
+static void eb_capture_commit(struct i915_execbuffer *eb)
+{
+}
+
+static void eb_capture_release(struct i915_execbuffer *eb)
+{
+}
+
+static void eb_capture_list_clear(struct i915_execbuffer *eb)
+{
+}
+
+#endif
+
+static int eb_move_to_gpu(struct i915_execbuffer *eb)
+{
+ const unsigned int count = eb->buffer_count;
+ unsigned int i = count;
+ int err = 0, j;
+
+ while (i--) {
+ struct eb_vma *ev = &eb->vma[i];
+ struct i915_vma *vma = ev->vma;
+ unsigned int flags = ev->flags;
+ struct drm_i915_gem_object *obj = vma->obj;
+
+ assert_vma_held(vma);
/*
* If the GPU is not _reading_ through the CPU cache, we need
@@ -2001,6 +2084,8 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
/* Unconditionally flush any chipset caches (for streaming writes). */
intel_gt_chipset_flush(eb->gt);
+ eb_capture_commit(eb);
+
return 0;
err_skip:
@@ -3143,13 +3228,14 @@ eb_requests_create(struct i915_execbuffer *eb, struct dma_fence *in_fence,
}
/*
- * Whilst this request exists, batch_obj will be on the
- * active_list, and so will hold the active reference. Only when
- * this request is retired will the batch_obj be moved onto
- * the inactive_list and lose its active reference. Hence we do
- * not need to explicitly hold another reference here.
+ * Not really on stack, but we don't want to call
+ * kfree on the batch_snapshot when we put it, so use the
+ * _onstack interface.
*/
- eb->requests[i]->batch = eb->batches[i]->vma;
+ if (eb->batches[i]->vma)
+ i915_vma_snapshot_init_onstack(&eb->requests[i]->batch_snapshot,
+ eb->batches[i]->vma,
+ "batch");
if (eb->batch_pool) {
GEM_BUG_ON(intel_context_is_parallel(eb->context));
intel_gt_buffer_pool_mark_active(eb->batch_pool,
@@ -3198,6 +3284,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
eb.fences = NULL;
eb.num_fences = 0;
+ eb_capture_list_clear(&eb);
+
memset(eb.requests, 0, sizeof(struct i915_request *) *
ARRAY_SIZE(eb.requests));
eb.composite_fence = NULL;
@@ -3284,6 +3372,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
}
ww_acquire_done(&eb.ww.ctx);
+ eb_capture_stage(&eb);
out_fence = eb_requests_create(&eb, in_fence, out_fence_fd);
if (IS_ERR(out_fence)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index ff6753ccb129..61e44185990a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1676,14 +1676,18 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
{
+ struct i915_vma_snapshot *vsnap = &rq->batch_snapshot;
void *ring;
int size;
+ if (!i915_vma_snapshot_present(vsnap))
+ vsnap = NULL;
+
drm_printf(m,
"[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
rq->head, rq->postfix, rq->tail,
- rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
- rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+ vsnap ? upper_32_bits(vsnap->gtt_offset) : ~0u,
+ vsnap ? lower_32_bits(vsnap->gtt_offset) : ~0u);
size = rq->tail - rq->head;
if (rq->tail < rq->head)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index bedb80057046..620c7a262ad0 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2186,7 +2186,7 @@ struct execlists_capture {
static void execlists_capture_work(struct work_struct *work)
{
struct execlists_capture *cap = container_of(work, typeof(*cap), work);
- const gfp_t gfp = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
+ const gfp_t gfp = GFP_NOWAIT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
struct intel_engine_cs *engine = cap->rq->engine;
struct intel_gt_coredump *gt = cap->error->gt;
struct intel_engine_capture_vma *vma;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2a2d7643b551..397df5e473fd 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -48,8 +48,9 @@
#include "i915_gpu_error.h"
#include "i915_memcpy.h"
#include "i915_scatterlist.h"
+#include "i915_vma_snapshot.h"
-#define ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
+#define ALLOW_FAIL (GFP_NOWAIT | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
#define ATOMIC_MAYFAIL (GFP_ATOMIC | __GFP_NOWARN)
static void __sg_set_buf(struct scatterlist *sg,
@@ -1009,8 +1010,7 @@ void __i915_gpu_coredump_free(struct kref *error_ref)
static struct i915_vma_coredump *
i915_vma_coredump_create(const struct intel_gt *gt,
- const struct i915_vma *vma,
- const char *name,
+ const struct i915_vma_snapshot *vsnap,
struct i915_vma_compress *compress)
{
struct i915_ggtt *ggtt = gt->ggtt;
@@ -1022,10 +1022,10 @@ i915_vma_coredump_create(const struct intel_gt *gt,
might_sleep();
- if (!vma || !vma->pages || !compress)
+ if (!vsnap || !vsnap->pages || !compress)
return NULL;
- num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
+ num_pages = min_t(u64, vsnap->size, vsnap->obj_size) >> PAGE_SHIFT;
num_pages = DIV_ROUND_UP(10 * num_pages, 8); /* worstcase zlib growth */
dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), ALLOW_FAIL);
if (!dst)
@@ -1036,12 +1036,12 @@ i915_vma_coredump_create(const struct intel_gt *gt,
return NULL;
}
- strcpy(dst->name, name);
+ strcpy(dst->name, vsnap->name);
dst->next = NULL;
- dst->gtt_offset = vma->node.start;
- dst->gtt_size = vma->node.size;
- dst->gtt_page_sizes = vma->page_sizes.gtt;
+ dst->gtt_offset = vsnap->gtt_offset;
+ dst->gtt_size = vsnap->gtt_size;
+ dst->gtt_page_sizes = vsnap->page_sizes;
dst->num_pages = num_pages;
dst->page_count = 0;
dst->unused = 0;
@@ -1051,7 +1051,7 @@ i915_vma_coredump_create(const struct intel_gt *gt,
void __iomem *s;
dma_addr_t dma;
- for_each_sgt_daddr(dma, iter, vma->pages) {
+ for_each_sgt_daddr(dma, iter, vsnap->pages) {
mutex_lock(&ggtt->error_mutex);
ggtt->vm.insert_page(&ggtt->vm, dma, slot,
I915_CACHE_NONE, 0);
@@ -1069,11 +1069,11 @@ i915_vma_coredump_create(const struct intel_gt *gt,
if (ret)
break;
}
- } else if (__i915_gem_object_is_lmem(vma->obj)) {
- struct intel_memory_region *mem = vma->obj->mm.region;
+ } else if (vsnap->mr && vsnap->mr->type != INTEL_MEMORY_SYSTEM) {
+ struct intel_memory_region *mem = vsnap->mr;
dma_addr_t dma;
- for_each_sgt_daddr(dma, iter, vma->pages) {
+ for_each_sgt_daddr(dma, iter, vsnap->pages) {
void __iomem *s;
s = io_mapping_map_wc(&mem->iomap,
@@ -1089,7 +1089,7 @@ i915_vma_coredump_create(const struct intel_gt *gt,
} else {
struct page *page;
- for_each_sgt_page(page, iter, vma->pages) {
+ for_each_sgt_page(page, iter, vsnap->pages) {
void *s;
drm_clflush_pages(&page, 1);
@@ -1320,37 +1320,71 @@ static bool record_context(struct i915_gem_context_coredump *e,
struct intel_engine_capture_vma {
struct intel_engine_capture_vma *next;
- struct i915_vma *vma;
+ struct i915_vma_snapshot *vsnap;
char name[16];
+ bool lockdep_cookie;
};
static struct intel_engine_capture_vma *
-capture_vma(struct intel_engine_capture_vma *next,
- struct i915_vma *vma,
- const char *name,
- gfp_t gfp)
+capture_vma_snapshot(struct intel_engine_capture_vma *next,
+ struct i915_vma_snapshot *vsnap,
+ gfp_t gfp)
{
struct intel_engine_capture_vma *c;
- if (!vma)
+ if (!i915_vma_snapshot_present(vsnap))
return next;
c = kmalloc(sizeof(*c), gfp);
if (!c)
return next;
- if (!i915_active_acquire_if_busy(&vma->active)) {
+ if (!i915_vma_snapshot_resource_pin(vsnap, &c->lockdep_cookie)) {
kfree(c);
return next;
}
- strcpy(c->name, name);
- c->vma = vma; /* reference held while active */
+ strcpy(c->name, vsnap->name);
+ c->vsnap = vsnap;
+ i915_vma_snapshot_get(vsnap);
c->next = next;
return c;
}
+static struct intel_engine_capture_vma *
+capture_vma(struct intel_engine_capture_vma *next,
+ struct i915_vma *vma,
+ const char *name,
+ gfp_t gfp)
+{
+ struct i915_vma_snapshot *vsnap;
+
+ if (!vma)
+ return next;
+
+ /*
+ * If the vma isn't pinned, then the vma should be snapshotted
+ * to a struct i915_vma_snapshot at command submission time.
+ * Not here.
+ */
+ GEM_WARN_ON(!i915_vma_is_pinned(vma));
+ if (!i915_vma_is_pinned(vma))
+ return next;
+
+ vsnap = i915_vma_snapshot_alloc(gfp);
+ if (!vsnap)
+ return next;
+
+ i915_vma_snapshot_init(vsnap, vma, name);
+ next = capture_vma_snapshot(next, vsnap, gfp);
+
+ /* FIXME: Replace on async unbind. */
+ i915_vma_snapshot_put(vsnap);
+
+ return next;
+}
+
static struct intel_engine_capture_vma *
capture_user(struct intel_engine_capture_vma *capture,
const struct i915_request *rq,
@@ -1359,7 +1393,7 @@ capture_user(struct intel_engine_capture_vma *capture,
struct i915_capture_list *c;
for (c = rq->capture_list; c; c = c->next)
- capture = capture_vma(capture, c->vma, "user", gfp);
+ capture = capture_vma_snapshot(capture, c->vma_snapshot, gfp);
return capture;
}
@@ -1373,6 +1407,36 @@ static void add_vma(struct intel_engine_coredump *ee,
}
}
+static struct i915_vma_coredump *
+create_vma_coredump(const struct intel_gt *gt, struct i915_vma *vma,
+ const char *name, struct i915_vma_compress *compress)
+{
+ struct i915_vma_coredump *ret = NULL;
+ struct i915_vma_snapshot tmp;
+ bool lockdep_cookie;
+
+ if (!vma)
+ return NULL;
+
+ i915_vma_snapshot_init_onstack(&tmp, vma, name);
+ if (i915_vma_snapshot_resource_pin(&tmp, &lockdep_cookie)) {
+ ret = i915_vma_coredump_create(gt, &tmp, compress);
+ i915_vma_snapshot_resource_unpin(&tmp, lockdep_cookie);
+ }
+ i915_vma_snapshot_put_onstack(&tmp);
+
+ return ret;
+}
+
+static void add_vma_coredump(struct intel_engine_coredump *ee,
+ const struct intel_gt *gt,
+ struct i915_vma *vma,
+ const char *name,
+ struct i915_vma_compress *compress)
+{
+ add_vma(ee, create_vma_coredump(gt, vma, name, compress));
+}
+
struct intel_engine_coredump *
intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
{
@@ -1406,7 +1470,7 @@ intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
* as the simplest method to avoid being overwritten
* by userspace.
*/
- vma = capture_vma(vma, rq->batch, "batch", gfp);
+ vma = capture_vma_snapshot(vma, &rq->batch_snapshot, gfp);
vma = capture_user(vma, rq, gfp);
vma = capture_vma(vma, rq->ring->vma, "ring", gfp);
vma = capture_vma(vma, rq->context->state, "HW context", gfp);
@@ -1427,30 +1491,24 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
while (capture) {
struct intel_engine_capture_vma *this = capture;
- struct i915_vma *vma = this->vma;
+ struct i915_vma_snapshot *vsnap = this->vsnap;
add_vma(ee,
i915_vma_coredump_create(engine->gt,
- vma, this->name,
- compress));
+ vsnap, compress));
- i915_active_release(&vma->active);
+ i915_vma_snapshot_resource_unpin(vsnap, this->lockdep_cookie);
+ i915_vma_snapshot_put(vsnap);
capture = this->next;
kfree(this);
}
- add_vma(ee,
- i915_vma_coredump_create(engine->gt,
- engine->status_page.vma,
- "HW Status",
- compress));
+ add_vma_coredump(ee, engine->gt, engine->status_page.vma,
+ "HW Status", compress);
- add_vma(ee,
- i915_vma_coredump_create(engine->gt,
- engine->wa_ctx.vma,
- "WA context",
- compress));
+ add_vma_coredump(ee, engine->gt, engine->wa_ctx.vma,
+ "WA context", compress);
}
static struct intel_engine_coredump *
@@ -1486,17 +1544,25 @@ capture_engine(struct intel_engine_cs *engine,
}
}
if (rq)
- capture = intel_engine_coredump_add_request(ee, rq,
- ATOMIC_MAYFAIL);
+ rq = i915_request_get_rcu(rq);
+
+ if (!rq)
+ goto no_request_capture;
+
+ capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
if (!capture) {
-no_request_capture:
- kfree(ee);
- return NULL;
+ i915_request_put(rq);
+ goto no_request_capture;
}
intel_engine_coredump_add_vma(ee, capture, compress);
+ i915_request_put(rq);
return ee;
+
+no_request_capture:
+ kfree(ee);
+ return NULL;
}
static void
@@ -1550,10 +1616,8 @@ gt_record_uc(struct intel_gt_coredump *gt,
*/
error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL);
error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL);
- error_uc->guc_log =
- i915_vma_coredump_create(gt->_gt,
- uc->guc.log.vma, "GuC log buffer",
- compress);
+ error_uc->guc_log = create_vma_coredump(gt->_gt, uc->guc.log.vma,
+ "GuC log buffer", compress);
return error_uc;
}
@@ -1839,8 +1903,8 @@ void i915_vma_capture_finish(struct intel_gt_coredump *gt,
kfree(compress);
}
-struct i915_gpu_coredump *
-i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+static struct i915_gpu_coredump *
+__i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
{
struct drm_i915_private *i915 = gt->i915;
struct i915_gpu_coredump *error;
@@ -1881,6 +1945,22 @@ i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
return error;
}
+struct i915_gpu_coredump *
+i915_gpu_coredump(struct intel_gt *gt, intel_engine_mask_t engine_mask)
+{
+ static DEFINE_MUTEX(capture_mutex);
+ int ret = mutex_lock_interruptible(&capture_mutex);
+ struct i915_gpu_coredump *dump;
+
+ if (ret)
+ return ERR_PTR(ret);
+
+ dump = __i915_gpu_coredump(gt, engine_mask);
+ mutex_unlock(&capture_mutex);
+
+ return dump;
+}
+
void i915_error_state_store(struct i915_gpu_coredump *error)
{
struct drm_i915_private *i915;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 820a1f38b271..24ec2a9beb2f 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -113,6 +113,10 @@ static void i915_fence_release(struct dma_fence *fence)
GEM_BUG_ON(rq->guc_prio != GUC_PRIO_INIT &&
rq->guc_prio != GUC_PRIO_FINI);
+ i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
+ if (i915_vma_snapshot_present(&rq->batch_snapshot))
+ i915_vma_snapshot_put_onstack(&rq->batch_snapshot);
+
/*
* The request is put onto a RCU freelist (i.e. the address
* is immediately reused), mark the fences as being freed now.
@@ -186,19 +190,6 @@ void i915_request_notify_execute_cb_imm(struct i915_request *rq)
__notify_execute_cb(rq, irq_work_imm);
}
-static void free_capture_list(struct i915_request *request)
-{
- struct i915_capture_list *capture;
-
- capture = fetch_and_zero(&request->capture_list);
- while (capture) {
- struct i915_capture_list *next = capture->next;
-
- kfree(capture);
- capture = next;
- }
-}
-
static void __i915_request_fill(struct i915_request *rq, u8 val)
{
void *vaddr = rq->ring->vaddr;
@@ -303,6 +294,37 @@ static void __rq_cancel_watchdog(struct i915_request *rq)
i915_request_put(rq);
}
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
+
+/**
+ * i915_request_free_capture_list - Free a capture list
+ * @capture: Pointer to the first list item or NULL
+ *
+ */
+void i915_request_free_capture_list(struct i915_capture_list *capture)
+{
+ while (capture) {
+ struct i915_capture_list *next = capture->next;
+
+ i915_vma_snapshot_put(capture->vma_snapshot);
+ capture = next;
+ }
+}
+
+#define assert_capture_list_is_null(_rq) GEM_BUG_ON((_rq)->capture_list)
+
+#define clear_capture_list(_rq) ((_rq)->capture_list = NULL)
+
+#else
+
+#define i915_request_free_capture_list(_a) do {} while (0)
+
+#define assert_capture_list_is_null(_a) do {} while (0)
+
+#define clear_capture_list(_rq) do {} while (0)
+
+#endif
+
bool i915_request_retire(struct i915_request *rq)
{
if (!__i915_request_is_complete(rq))
@@ -359,7 +381,6 @@ bool i915_request_retire(struct i915_request *rq)
intel_context_exit(rq->context);
intel_context_unpin(rq->context);
- free_capture_list(rq);
i915_sched_node_fini(&rq->sched);
i915_request_put(rq);
@@ -829,11 +850,18 @@ static void __i915_request_ctor(void *arg)
i915_sw_fence_init(&rq->submit, submit_notify);
i915_sw_fence_init(&rq->semaphore, semaphore_notify);
- rq->capture_list = NULL;
+ clear_capture_list(rq);
+ rq->batch_snapshot.present = false;
init_llist_head(&rq->execute_cb);
}
+#ifdef CONFIG_DRM_I915_SELFTEST
+#define clear_batch_ptr(_rq) ((_rq)->batch = NULL)
+#else
+#define clear_batch_ptr(_a) do {} while (0)
+#endif
+
struct i915_request *
__i915_request_create(struct intel_context *ce, gfp_t gfp)
{
@@ -925,10 +953,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
i915_sched_node_reinit(&rq->sched);
/* No zalloc, everything must be cleared after use */
- rq->batch = NULL;
+ clear_batch_ptr(rq);
__rq_init_watchdog(rq);
- GEM_BUG_ON(rq->capture_list);
+ assert_capture_list_is_null(rq);
GEM_BUG_ON(!llist_empty(&rq->execute_cb));
+ GEM_BUG_ON(i915_vma_snapshot_present(&rq->batch_snapshot));
/*
* Reserve space in the ring buffer for all the commands required to
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index dc359242d1ae..f439bf968517 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -40,6 +40,7 @@
#include "i915_scheduler.h"
#include "i915_selftest.h"
#include "i915_sw_fence.h"
+#include "i915_vma_snapshot.h"
#include <uapi/drm/i915_drm.h>
@@ -48,11 +49,15 @@ struct drm_i915_gem_object;
struct drm_printer;
struct i915_request;
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
struct i915_capture_list {
+ struct i915_vma_snapshot *vma_snapshot;
struct i915_capture_list *next;
- struct i915_vma *vma;
};
+void i915_request_free_capture_list(struct i915_capture_list *capture);
+#endif
+
#define RQ_TRACE(rq, fmt, ...) do { \
const struct i915_request *rq__ = (rq); \
ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt, \
@@ -289,10 +294,12 @@ struct i915_request {
/** Preallocate space in the ring for the emitting the request */
u32 reserved_space;
- /** Batch buffer related to this request if any (used for
- * error state dump only).
- */
- struct i915_vma *batch;
+ /** Batch buffer pointer for selftest internal use. */
+ I915_SELFTEST_DECLARE(struct i915_vma *batch);
+
+ struct i915_vma_snapshot batch_snapshot;
+
+#ifdef CONFIG_DRM_I915_CAPTURE_ERROR
/**
* Additional buffers requested by userspace to be captured upon
* a GPU hang. The vma/obj on this list are protected by their
@@ -300,6 +307,7 @@ struct i915_request {
* on the active_list (of their final request).
*/
struct i915_capture_list *capture_list;
+#endif
/** Time at which this request was emitted, in jiffies. */
unsigned long emitted_jiffies;
diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.c b/drivers/gpu/drm/i915/i915_vma_snapshot.c
new file mode 100644
index 000000000000..44985d600f96
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_vma_snapshot.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include "i915_vma_snapshot.h"
+#include "i915_vma_types.h"
+#include "i915_vma.h"
+
+/**
+ * i915_vma_snapshot_init - Initialize a struct i915_vma_snapshot from
+ * a struct i915_vma.
+ * @vsnap: The i915_vma_snapshot to init.
+ * @vma: A struct i915_vma used to initialize @vsnap.
+ * @name: Name associated with the snapshot. The character pointer needs to
+ * stay alive over the lifitime of the shapsot
+ */
+void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap,
+ struct i915_vma *vma,
+ const char *name)
+{
+ if (!i915_vma_is_pinned(vma))
+ assert_object_held(vma->obj);
+
+ vsnap->name = name;
+ vsnap->size = vma->size;
+ vsnap->obj_size = vma->obj->base.size;
+ vsnap->gtt_offset = vma->node.start;
+ vsnap->gtt_size = vma->node.size;
+ vsnap->page_sizes = vma->page_sizes.gtt;
+ vsnap->pages = vma->pages;
+ vsnap->pages_rsgt = NULL;
+ vsnap->mr = NULL;
+ if (vma->obj->mm.rsgt)
+ vsnap->pages_rsgt = i915_refct_sgt_get(vma->obj->mm.rsgt);
+ if (vma->obj->mm.region)
+ vsnap->mr = intel_memory_region_get(vma->obj->mm.region);
+ kref_init(&vsnap->kref);
+ vsnap->vma_resource = &vma->active;
+ vsnap->onstack = false;
+ vsnap->present = true;
+}
+
+/**
+ * i915_vma_snapshot_init_onstack - Initialize a struct i915_vma_snapshot from
+ * a struct i915_vma, but avoid kfreeing it on last put.
+ * @vsnap: The i915_vma_snapshot to init.
+ * @vma: A struct i915_vma used to initialize @vsnap.
+ * @name: Name associated with the snapshot. The character pointer needs to
+ * stay alive over the lifitime of the shapsot
+ */
+void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap,
+ struct i915_vma *vma,
+ const char *name)
+{
+ i915_vma_snapshot_init(vsnap, vma, name);
+ vsnap->onstack = true;
+}
+
+static void vma_snapshot_release(struct kref *ref)
+{
+ struct i915_vma_snapshot *vsnap =
+ container_of(ref, typeof(*vsnap), kref);
+
+ vsnap->present = false;
+ if (vsnap->mr)
+ intel_memory_region_put(vsnap->mr);
+ if (vsnap->pages_rsgt)
+ i915_refct_sgt_put(vsnap->pages_rsgt);
+ if (!vsnap->onstack)
+ kfree(vsnap);
+}
+
+/**
+ * i915_vma_snapshot_put - Put an i915_vma_snapshot pointer reference
+ * @vsnap: The pointer reference
+ */
+void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap)
+{
+ kref_put(&vsnap->kref, vma_snapshot_release);
+}
+
+/**
+ * i915_vma_snapshot_put_onstack - Put an onstcak i915_vma_snapshot pointer
+ * reference and varify that the structure is released
+ * @vsnap: The pointer reference
+ *
+ * This function is intended to be paired with a i915_vma_init_onstack()
+ * and should be called before exiting the scope that declared or
+ * freeing the structure that embedded @vsnap to verify that all references
+ * have been released.
+ */
+void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap)
+{
+ if (!kref_put(&vsnap->kref, vma_snapshot_release))
+ GEM_BUG_ON(1);
+}
+
+/**
+ * i915_vma_snapshot_resource_pin - Temporarily block the memory the
+ * vma snapshot is pointing to from being released.
+ * @vsnap: The vma snapshot.
+ * @lockdep_cookie: Pointer to bool needed for lockdep support. This needs
+ * to be passed to the paired i915_vma_snapshot_resource_unpin.
+ *
+ * This function will temporarily try to hold up a fence or similar structure
+ * and will therefore enter a fence signaling critical section.
+ *
+ * Return: true if we succeeded in blocking the memory from being released,
+ * false otherwise.
+ */
+bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap,
+ bool *lockdep_cookie)
+{
+ bool pinned = i915_active_acquire_if_busy(vsnap->vma_resource);
+
+ if (pinned)
+ *lockdep_cookie = dma_fence_begin_signalling();
+
+ return pinned;
+}
+
+/**
+ * i915_vma_snapshot_resource_unpin - Unblock vma snapshot memory from
+ * being released.
+ * @vsnap: The vma snapshot.
+ * @lockdep_cookie: Cookie returned from matching i915_vma_resource_pin().
+ *
+ * Might leave a fence signalling critical section and signal a fence.
+ */
+void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap,
+ bool lockdep_cookie)
+{
+ dma_fence_end_signalling(lockdep_cookie);
+
+ return i915_active_release(vsnap->vma_resource);
+}
diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.h b/drivers/gpu/drm/i915/i915_vma_snapshot.h
new file mode 100644
index 000000000000..940581df4622
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_vma_snapshot.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+#ifndef _I915_VMA_SNAPSHOT_H_
+#define _I915_VMA_SNAPSHOT_H_
+
+#include <linux/kref.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+struct i915_active;
+struct i915_refct_sgt;
+struct i915_vma;
+struct intel_memory_region;
+struct sg_table;
+
+/**
+ * DOC: Simple utilities for snapshotting GPU vma metadata, later used for
+ * error capture. Vi use a separate header for this to avoid issues due to
+ * recursive header includes.
+ */
+
+/**
+ * struct i915_vma_snapshot - Snapshot of vma metadata.
+ * @size: The vma size in bytes.
+ * @obj_size: The size of the underlying object in bytes.
+ * @gtt_offset: The gtt offset the vma is bound to.
+ * @gtt_size: The size in bytes allocated for the vma in the GTT.
+ * @pages: The struct sg_table pointing to the pages bound.
+ * @pages_rsgt: The refcounted sg_table holding the reference for @pages if any.
+ * @mr: The memory region pointed for the pages bound.
+ * @kref: Reference for this structure.
+ * @vma_resource: FIXME: A means to keep the unbind fence from signaling.
+ * Temporarily while we have only sync unbinds, and still use the vma
+ * active, we use that. With async unbinding we need a signaling refcount
+ * for the unbind fence.
+ * @page_sizes: The vma GTT page sizes information.
+ * @onstack: Whether the structure shouldn't be freed on final put.
+ * @present: Whether the structure is present and initialized.
+ */
+struct i915_vma_snapshot {
+ const char *name;
+ size_t size;
+ size_t obj_size;
+ size_t gtt_offset;
+ size_t gtt_size;
+ struct sg_table *pages;
+ struct i915_refct_sgt *pages_rsgt;
+ struct intel_memory_region *mr;
+ struct kref kref;
+ struct i915_active *vma_resource;
+ u32 page_sizes;
+ bool onstack:1;
+ bool present:1;
+};
+
+void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap,
+ struct i915_vma *vma,
+ const char *name);
+
+void i915_vma_snapshot_init_onstack(struct i915_vma_snapshot *vsnap,
+ struct i915_vma *vma,
+ const char *name);
+
+void i915_vma_snapshot_put(struct i915_vma_snapshot *vsnap);
+
+void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap);
+
+bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap,
+ bool *lockdep_cookie);
+
+void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap,
+ bool lockdep_cookie);
+
+/**
+ * i915_vma_snapshot_alloc - Allocate a struct i915_vma_snapshot
+ * @gfp: Allocation mode.
+ *
+ * Return: A pointer to a struct i915_vma_snapshot if successful.
+ * NULL otherwise.
+ */
+static inline struct i915_vma_snapshot *i915_vma_snapshot_alloc(gfp_t gfp)
+{
+ return kmalloc(sizeof(struct i915_vma_snapshot), gfp);
+}
+
+/**
+ * i915_vma_snapshot_get - Take a reference on a struct i915_vma_snapshot
+ *
+ * Return: A pointer to a struct i915_vma_snapshot.
+ */
+static inline struct i915_vma_snapshot *
+i915_vma_snapshot_get(struct i915_vma_snapshot *vsnap)
+{
+ kref_get(&vsnap->kref);
+ return vsnap;
+}
+
+/**
+ * i915_vma_snapshot_present - Whether a struct i915_vma_snapshot is
+ * present and initialized.
+ *
+ * Return: true if present and initialized; false otherwise.
+ */
+static inline bool
+i915_vma_snapshot_present(const struct i915_vma_snapshot *vsnap)
+{
+ return vsnap && vsnap->present;
+}
+
+#endif
--
2.31.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 2/3] drm/i915: Update error capture code to avoid using the current vma state
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 2/3] drm/i915: Update error capture code to avoid using the current vma state Thomas Hellström
@ 2021-10-28 8:46 ` kernel test robot
0 siblings, 0 replies; 15+ messages in thread
From: kernel test robot @ 2021-10-28 8:46 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx, dri-devel
Cc: kbuild-all, maarten.lankhorst, matthew.auld,
Thomas Hellström
[-- Attachment #1: Type: text/plain, Size: 5478 bytes --]
Hi "Thomas,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on drm-tip/drm-tip]
[cannot apply to drm-intel/for-linux-next drm-exynos/exynos-drm-next drm/drm-next tegra-drm/drm/tegra/for-next airlied/drm-next v5.15-rc7 next-20211027]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Thomas-Hellstr-m/Prepare-error-capture-for-asynchronous-migration/20211027-185501
base: git://anongit.freedesktop.org/drm/drm-tip drm-tip
config: i386-randconfig-s001-20211027 (attached as .config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce:
# apt-get install sparse
# sparse version: v0.6.4-dirty
# https://github.com/0day-ci/linux/commit/565a7c79aff3eb84fffc704407b376e939360857
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Thomas-Hellstr-m/Prepare-error-capture-for-asynchronous-migration/20211027-185501
git checkout 565a7c79aff3eb84fffc704407b376e939360857
# save the attached .config to linux build tree
make W=1 C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__' ARCH=i386
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
drivers/gpu/drm/i915/i915_request.c: In function 'i915_fence_release':
>> drivers/gpu/drm/i915/i915_request.c:116:2: error: implicit declaration of function 'i915_request_free_capture_list' [-Werror=implicit-function-declaration]
116 | i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/i915_active_types.h:18,
from drivers/gpu/drm/i915/gt/intel_context_types.h:15,
from drivers/gpu/drm/i915/gem/i915_gem_context_types.h:20,
from drivers/gpu/drm/i915/gem/i915_gem_context.h:10,
from drivers/gpu/drm/i915/i915_request.c:33:
>> drivers/gpu/drm/i915/i915_request.c:116:51: error: 'struct i915_request' has no member named 'capture_list'
116 | i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
| ^~
drivers/gpu/drm/i915/i915_utils.h:199:10: note: in definition of macro 'fetch_and_zero'
199 | typeof(*ptr) __T = *(ptr); \
| ^~~
>> drivers/gpu/drm/i915/i915_request.c:116:51: error: 'struct i915_request' has no member named 'capture_list'
116 | i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
| ^~
drivers/gpu/drm/i915/i915_utils.h:199:23: note: in definition of macro 'fetch_and_zero'
199 | typeof(*ptr) __T = *(ptr); \
| ^~~
>> drivers/gpu/drm/i915/i915_request.c:116:51: error: 'struct i915_request' has no member named 'capture_list'
116 | i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
| ^~
drivers/gpu/drm/i915/i915_utils.h:200:4: note: in definition of macro 'fetch_and_zero'
200 | *(ptr) = (typeof(*ptr))0; \
| ^~~
>> drivers/gpu/drm/i915/i915_request.c:116:51: error: 'struct i915_request' has no member named 'capture_list'
116 | i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
| ^~
drivers/gpu/drm/i915/i915_utils.h:200:20: note: in definition of macro 'fetch_and_zero'
200 | *(ptr) = (typeof(*ptr))0; \
| ^~~
cc1: some warnings being treated as errors
vim +/i915_request_free_capture_list +116 drivers/gpu/drm/i915/i915_request.c
108
109 static void i915_fence_release(struct dma_fence *fence)
110 {
111 struct i915_request *rq = to_request(fence);
112
113 GEM_BUG_ON(rq->guc_prio != GUC_PRIO_INIT &&
114 rq->guc_prio != GUC_PRIO_FINI);
115
> 116 i915_request_free_capture_list(fetch_and_zero(&rq->capture_list));
117 if (i915_vma_snapshot_present(&rq->batch_snapshot))
118 i915_vma_snapshot_put_onstack(&rq->batch_snapshot);
119
120 /*
121 * The request is put onto a RCU freelist (i.e. the address
122 * is immediately reused), mark the fences as being freed now.
123 * Otherwise the debugobjects for the fences are only marked as
124 * freed when the slab cache itself is freed, and so we would get
125 * caught trying to reuse dead objects.
126 */
127 i915_sw_fence_fini(&rq->submit);
128 i915_sw_fence_fini(&rq->semaphore);
129
130 /*
131 * Keep one request on each engine for reserved use under mempressure,
132 * do not use with virtual engines as this really is only needed for
133 * kernel contexts.
134 */
135 if (!intel_engine_is_virtual(rq->engine) &&
136 !cmpxchg(&rq->engine->request_pool, NULL, rq)) {
137 intel_context_put(rq->context);
138 return;
139 }
140
141 intel_context_put(rq->context);
142
143 kmem_cache_free(slab_requests, rq);
144 }
145
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 35838 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread
* [Intel-gfx] [PATCH v2 3/3] drm/i915: Initial introduction of vma resources
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 1/3] drm/i915: Introduce refcounted sg-tables Thomas Hellström
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 2/3] drm/i915: Update error capture code to avoid using the current vma state Thomas Hellström
@ 2021-10-27 10:52 ` Thomas Hellström
2021-10-27 22:07 ` kernel test robot
2021-10-27 14:40 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Prepare error capture for asynchronous migration (rev2) Patchwork
` (2 subsequent siblings)
5 siblings, 1 reply; 15+ messages in thread
From: Thomas Hellström @ 2021-10-27 10:52 UTC (permalink / raw)
To: intel-gfx, dri-devel
Cc: maarten.lankhorst, matthew.auld, Thomas Hellström
From: Thomas Hellström <thomas.hellstrom@intel.com>
The vma resource are needed for asynchronous bind management and are
similar to TTM resources. They contain the data needed for
asynchronous unbinding (typically the vm range, any backend
private information and a means to do refcounting and to hold
the unbinding for error capture).
When a vma is bound, a vma resource is created and attached to the
vma, and on async unbinding it is detached from the vma, and instead
the vm records the fence marking unbind complete. This fence needs to
be waited on before we can bind the same region again, so either
the fence can be recorded for this particular range only, using an
interval tree, or as a simpler approach, for the whole vm. The latter
means no binding can take place on a vm until all detached vma
resources scheduled for unbind are signaled. With an interval tree
fence recording, the interval tree needs to be searched for fences
to be signaled before binding can take place.
But most of that is for later, this patch only introduces stub vma
resources without unbind capability and the fences of which are waited
for sync during unbinding. At this point we're interested in the hold
capability as a POC for error capture. Note that the current sync waiting
at unbind time is done uninterruptible, but that's OK since we're
only ever waiting during error capture, and in that case there's very
little gpu activity (if any) that can stall.
v2:
- Fix the mock gtt selftest to bind with vma resources.
- Update a code comment.
- Account for rebinding the same vma with different I915_VMA_*_BIND flags
Signed-off-by: Thomas Hellström <thomas.hellstrom@intel.com>
---
.../gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +-
drivers/gpu/drm/i915/i915_vma.c | 201 +++++++++++++++++-
drivers/gpu/drm/i915/i915_vma.h | 20 +-
drivers/gpu/drm/i915/i915_vma_snapshot.c | 14 +-
drivers/gpu/drm/i915/i915_vma_snapshot.h | 2 +-
drivers/gpu/drm/i915/i915_vma_types.h | 5 +
drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 99 +++++----
7 files changed, 284 insertions(+), 59 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 301eb58bebd1..69915c00ce18 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1376,7 +1376,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
GRAPHICS_VER(eb->i915) == 6) {
err = i915_vma_bind(target->vma,
target->vma->obj->cache_level,
- PIN_GLOBAL, NULL);
+ PIN_GLOBAL, NULL, NULL);
if (err)
return err;
}
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 90546fa58fc1..9a8fcf89f7d8 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -38,8 +38,33 @@
#include "i915_trace.h"
#include "i915_vma.h"
+/**
+ * struct i915_vma_resource - Snapshotted unbind information.
+ * @unbind_fence: Fence to mark unbinding complete. Note that this fence
+ * is not considered published until unbind is scheduled, and as such it
+ * is illegal to access this fence before scheduled unbind other than
+ * for refcounting.
+ * @lock: The @unbind_fence lock. We're also using it to protect the weak
+ * pointer to the struct i915_vma, @vma during lookup and takedown.
+ * @vma: Weak back-pointer to the parent vma struct. This pointer is
+ * protected by @lock, and a reference on @vma needs to be taken
+ * using kref_get_unless_zero.
+ * @hold_count: Number of holders blocking the fence from finishing.
+ * The vma itself is keeping a hold, which is released when unbind
+ * is scheduled.
+ */
+struct i915_vma_resource {
+ struct dma_fence unbind_fence;
+ /* See above for description of the lock. */
+ spinlock_t lock;
+ struct i915_vma *vma;
+ refcount_t hold_count;
+};
+
static struct kmem_cache *slab_vmas;
+static struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res);
+
struct i915_vma *i915_vma_alloc(void)
{
return kmem_cache_zalloc(slab_vmas, GFP_KERNEL);
@@ -363,6 +388,8 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
* @cache_level: mapping cache level
* @flags: flags like global or local mapping
* @work: preallocated worker for allocating and binding the PTE
+ * @vma_res: pointer to a preallocated vma resource. The resource is either
+ * consumed or freed.
*
* DMA addresses are taken from the scatter-gather table of this object (or of
* this VMA in case of non-default GGTT views) and PTE entries set up.
@@ -371,7 +398,8 @@ int i915_vma_wait_for_bind(struct i915_vma *vma)
int i915_vma_bind(struct i915_vma *vma,
enum i915_cache_level cache_level,
u32 flags,
- struct i915_vma_work *work)
+ struct i915_vma_work *work,
+ struct i915_vma_resource *vma_res)
{
u32 bind_flags;
u32 vma_flags;
@@ -381,11 +409,15 @@ int i915_vma_bind(struct i915_vma *vma,
if (GEM_DEBUG_WARN_ON(range_overflows(vma->node.start,
vma->node.size,
- vma->vm->total)))
+ vma->vm->total))) {
+ kfree(vma_res);
return -ENODEV;
+ }
- if (GEM_DEBUG_WARN_ON(!flags))
+ if (GEM_DEBUG_WARN_ON(!flags)) {
+ kfree(vma_res);
return -EINVAL;
+ }
bind_flags = flags;
bind_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
@@ -394,11 +426,25 @@ int i915_vma_bind(struct i915_vma *vma,
vma_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
bind_flags &= ~vma_flags;
- if (bind_flags == 0)
+ if (bind_flags == 0) {
+ kfree(vma_res);
return 0;
+ }
GEM_BUG_ON(!vma->pages);
+ if (!i915_vma_is_pinned(vma))
+ lockdep_assert_held(&vma->vm->mutex);
+
+ if ((vma->resource) || !vma_res) {
+ /* Rebinding with an additional I915_VMA_*_BIND */
+ GEM_WARN_ON(!vma_flags);
+ kfree(vma_res);
+ } else {
+ lockdep_assert_held(&vma->vm->mutex);
+ i915_vma_resource_init(vma_res, vma);
+ vma->resource = vma_res;
+ }
trace_i915_vma_bind(vma, bind_flags);
if (work && bind_flags & vma->vm->bind_async_flags) {
struct dma_fence *prev;
@@ -870,6 +916,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
u64 size, u64 alignment, u64 flags)
{
struct i915_vma_work *work = NULL;
+ struct i915_vma_resource *vma_res;
intel_wakeref_t wakeref = 0;
unsigned int bound;
int err;
@@ -923,6 +970,12 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
}
}
+ vma_res = i915_vma_resource_alloc();
+ if (IS_ERR(vma_res)) {
+ err = PTR_ERR(vma_res);
+ goto err_fence;
+ }
+
/*
* Differentiate between user/kernel vma inside the aliasing-ppgtt.
*
@@ -984,7 +1037,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
GEM_BUG_ON(!vma->pages);
err = i915_vma_bind(vma,
vma->obj ? vma->obj->cache_level : 0,
- flags, work);
+ flags, work, vma_res);
if (err)
goto err_remove;
@@ -1014,6 +1067,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
if (wakeref)
intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
vma_put_pages(vma);
+
return err;
}
@@ -1331,6 +1385,7 @@ void __i915_vma_evict(struct i915_vma *vma)
int __i915_vma_unbind(struct i915_vma *vma)
{
+ struct dma_fence *unbind_fence;
int ret;
lockdep_assert_held(&vma->vm->mutex);
@@ -1356,6 +1411,16 @@ int __i915_vma_unbind(struct i915_vma *vma)
__i915_vma_evict(vma);
drm_mm_remove_node(&vma->node); /* pairs with i915_vma_release() */
+ unbind_fence = i915_vma_resource_unbind(vma->resource);
+
+ /*
+ * This uninterruptible wait under the vm mutex is currently
+ * only ever blocking while the vma is being captured from.
+ * With async unbinding, this wait here will be removed.
+ */
+ dma_fence_wait(unbind_fence, false);
+ dma_fence_put(unbind_fence);
+
return 0;
}
@@ -1388,7 +1453,6 @@ int i915_vma_unbind(struct i915_vma *vma)
err = __i915_vma_unbind(vma);
mutex_unlock(&vm->mutex);
-
out_rpm:
if (wakeref)
intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
@@ -1411,6 +1475,131 @@ void i915_vma_make_purgeable(struct i915_vma *vma)
i915_gem_object_make_purgeable(vma->obj);
}
+static const char *get_driver_name(struct dma_fence *fence)
+{
+ return "vma unbind fence";
+}
+
+static const char *get_timeline_name(struct dma_fence *fence)
+{
+ return "unbound";
+}
+
+static struct dma_fence_ops unbind_fence_ops = {
+ .get_driver_name = get_driver_name,
+ .get_timeline_name = get_timeline_name,
+};
+
+struct i915_vma_resource *i915_vma_resource_alloc(void)
+{
+ struct i915_vma_resource *vma_res =
+ kzalloc(sizeof(*vma_res), GFP_KERNEL);
+
+ return vma_res ? vma_res : ERR_PTR(-ENOMEM);
+}
+
+I915_SELFTEST_EXPORT void
+i915_vma_resource_init(struct i915_vma_resource *vma_res,
+ struct i915_vma *vma)
+{
+ vma_res->vma = vma;
+ spin_lock_init(&vma_res->lock);
+ dma_fence_init(&vma_res->unbind_fence, &unbind_fence_ops,
+ &vma_res->lock, 0, 0);
+ refcount_set(&vma_res->hold_count, 1);
+}
+
+static void __i915_vma_resource_unhold(struct i915_vma_resource *vma_res)
+{
+ if (refcount_dec_and_test(&vma_res->hold_count))
+ dma_fence_signal(&vma_res->unbind_fence);
+}
+
+/**
+ * i915_vma_resource_unhold - Unhold the signaling of the vma resource unbind
+ * fence.
+ * @vma_res: The vma resource.
+ * @lockdep_cookie: The lockdep cookie returned from i915_vma_resource_hold.
+ *
+ * The function may leave a dma_fence critical section.
+ */
+void i915_vma_resource_unhold(struct i915_vma_resource *vma_res,
+ bool lockdep_cookie)
+{
+ dma_fence_end_signalling(lockdep_cookie);
+
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+ unsigned long irq_flags;
+
+ /* Inefficient open-coded might_lock_irqsave() */
+ spin_lock_irqsave(&vma_res->lock, irq_flags);
+ spin_unlock_irqrestore(&vma_res->lock, irq_flags);
+ }
+
+ __i915_vma_resource_unhold(vma_res);
+}
+
+/**
+ * i915_vma_resource_hold - Hold the signaling of the vma resource unbind fence.
+ * @vma_res: The vma resource.
+ * @lockdep_cookie: Pointer to a bool serving as a lockdep cooke that should
+ * be given as an argument to the pairing i915_vma_resource_unhold.
+ *
+ * If returning true, the function enters a dma_fence signalling critical
+ * section is not in one already.
+ *
+ * Return: true if holding successful, false if not.
+ */
+bool i915_vma_resource_hold(struct i915_vma_resource *vma_res,
+ bool *lockdep_cookie)
+{
+ bool held = refcount_inc_not_zero(&vma_res->hold_count);
+
+ if (held)
+ *lockdep_cookie = dma_fence_begin_signalling();
+
+ return held;
+}
+
+/**
+ * i915_vma_get_current_resource - Return the vma's current vma resource
+ * @vma: The vma referencing the resource.
+ *
+ * Return: A refcounted pointer to the vma's current vma resource.
+ */
+struct i915_vma_resource *i915_vma_get_current_resource(struct i915_vma *vma)
+{
+ GEM_BUG_ON(!vma->resource);
+
+ dma_fence_get(&vma->resource->unbind_fence);
+ return vma->resource;
+}
+
+/**
+ * i915_vma_resource_put - Release a reference to a struct i915_vma_resource
+ * @vma_res: The resource
+ */
+void i915_vma_resource_put(struct i915_vma_resource *vma_res)
+{
+ dma_fence_put(&vma_res->unbind_fence);
+}
+
+static struct dma_fence *
+i915_vma_resource_unbind(struct i915_vma_resource *vma_res)
+{
+ /* Reference is transferred to the returned dma_fence pointer */
+ vma_res->vma->resource = NULL;
+
+ spin_lock(&vma_res->lock);
+ /* Kill the weak reference under the spinlock. */
+ vma_res->vma = NULL;
+ spin_unlock(&vma_res->lock);
+
+ /* With async unbind, schedule it here. */
+ __i915_vma_resource_unhold(vma_res);
+ return &vma_res->unbind_fence;
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/i915_vma.c"
#endif
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 648dbe744c96..aa13d0d5bb91 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -206,7 +206,8 @@ struct i915_vma_work *i915_vma_work(void);
int i915_vma_bind(struct i915_vma *vma,
enum i915_cache_level cache_level,
u32 flags,
- struct i915_vma_work *work);
+ struct i915_vma_work *work,
+ struct i915_vma_resource *vma_res);
bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color);
bool i915_vma_misplaced(const struct i915_vma *vma,
@@ -433,7 +434,24 @@ static inline int i915_vma_sync(struct i915_vma *vma)
return i915_active_wait(&vma->active);
}
+bool i915_vma_resource_hold(struct i915_vma_resource *vma_res,
+ bool *lockdep_cookie);
+
+void i915_vma_resource_unhold(struct i915_vma_resource *vma_res,
+ bool lockdep_cookie);
+
+void i915_vma_resource_put(struct i915_vma_resource *vma_res);
+
+struct i915_vma_resource *i915_vma_get_current_resource(struct i915_vma *vma);
+
+struct i915_vma_resource *i915_vma_resource_alloc(void);
+
void i915_vma_module_exit(void);
int i915_vma_module_init(void);
+#ifdef CONFIG_DRM_I915_SELFTEST
+void i915_vma_resource_init(struct i915_vma_resource *vma_res,
+ struct i915_vma *vma);
+#endif
+
#endif
diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.c b/drivers/gpu/drm/i915/i915_vma_snapshot.c
index 44985d600f96..b4ee8220df85 100644
--- a/drivers/gpu/drm/i915/i915_vma_snapshot.c
+++ b/drivers/gpu/drm/i915/i915_vma_snapshot.c
@@ -36,7 +36,7 @@ void i915_vma_snapshot_init(struct i915_vma_snapshot *vsnap,
if (vma->obj->mm.region)
vsnap->mr = intel_memory_region_get(vma->obj->mm.region);
kref_init(&vsnap->kref);
- vsnap->vma_resource = &vma->active;
+ vsnap->vma_resource = i915_vma_get_current_resource(vma);
vsnap->onstack = false;
vsnap->present = true;
}
@@ -63,6 +63,7 @@ static void vma_snapshot_release(struct kref *ref)
container_of(ref, typeof(*vsnap), kref);
vsnap->present = false;
+ i915_vma_resource_put(vsnap->vma_resource);
if (vsnap->mr)
intel_memory_region_put(vsnap->mr);
if (vsnap->pages_rsgt)
@@ -112,12 +113,7 @@ void i915_vma_snapshot_put_onstack(struct i915_vma_snapshot *vsnap)
bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap,
bool *lockdep_cookie)
{
- bool pinned = i915_active_acquire_if_busy(vsnap->vma_resource);
-
- if (pinned)
- *lockdep_cookie = dma_fence_begin_signalling();
-
- return pinned;
+ return i915_vma_resource_hold(vsnap->vma_resource, lockdep_cookie);
}
/**
@@ -131,7 +127,5 @@ bool i915_vma_snapshot_resource_pin(struct i915_vma_snapshot *vsnap,
void i915_vma_snapshot_resource_unpin(struct i915_vma_snapshot *vsnap,
bool lockdep_cookie)
{
- dma_fence_end_signalling(lockdep_cookie);
-
- return i915_active_release(vsnap->vma_resource);
+ i915_vma_resource_unhold(vsnap->vma_resource, lockdep_cookie);
}
diff --git a/drivers/gpu/drm/i915/i915_vma_snapshot.h b/drivers/gpu/drm/i915/i915_vma_snapshot.h
index 940581df4622..d083b6bf1b11 100644
--- a/drivers/gpu/drm/i915/i915_vma_snapshot.h
+++ b/drivers/gpu/drm/i915/i915_vma_snapshot.h
@@ -49,7 +49,7 @@ struct i915_vma_snapshot {
struct i915_refct_sgt *pages_rsgt;
struct intel_memory_region *mr;
struct kref kref;
- struct i915_active *vma_resource;
+ struct i915_vma_resource *vma_resource;
u32 page_sizes;
bool onstack:1;
bool present:1;
diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h
index 80e93bf00f2e..14d20ac5350c 100644
--- a/drivers/gpu/drm/i915/i915_vma_types.h
+++ b/drivers/gpu/drm/i915/i915_vma_types.h
@@ -95,6 +95,8 @@ enum i915_cache_level;
*
*/
+struct i915_vma_resource;
+
struct intel_remapped_plane_info {
/* in gtt pages */
u32 offset;
@@ -284,6 +286,9 @@ struct i915_vma {
struct list_head evict_link;
struct list_head closed_link;
+
+ /** The async vma resource. Protected by the vm_mutex */
+ struct i915_vma_resource *resource;
};
#endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 46f4236039a9..c76fb85dd3d9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1336,6 +1336,33 @@ static int igt_mock_drunk(void *arg)
return exercise_mock(ggtt->vm.i915, drunk_hole);
}
+static int reserve_gtt_with_resource(struct i915_vma *vma, u64 offset)
+{
+ struct i915_address_space *vm = vma->vm;
+ struct i915_vma_resource *vma_res;
+ struct drm_i915_gem_object *obj = vma->obj;
+ int err;
+
+ vma_res = i915_vma_resource_alloc();
+ if (IS_ERR(vma_res))
+ return PTR_ERR(vma_res);
+
+ mutex_lock(&vm->mutex);
+ err = i915_gem_gtt_reserve(vm, &vma->node, obj->base.size,
+ offset,
+ obj->cache_level,
+ 0);
+ if (!err) {
+ i915_vma_resource_init(vma_res, vma);
+ vma->resource = vma_res;
+ } else {
+ kfree(vma_res);
+ }
+ mutex_unlock(&vm->mutex);
+
+ return err;
+}
+
static int igt_gtt_reserve(void *arg)
{
struct i915_ggtt *ggtt = arg;
@@ -1370,20 +1397,13 @@ static int igt_gtt_reserve(void *arg)
}
list_add(&obj->st_link, &objects);
-
vma = i915_vma_instance(obj, &ggtt->vm, NULL);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto out;
}
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
- obj->base.size,
- total,
- obj->cache_level,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+ err = reserve_gtt_with_resource(vma, total);
if (err) {
pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n",
total, ggtt->vm.total, err);
@@ -1429,13 +1449,7 @@ static int igt_gtt_reserve(void *arg)
goto out;
}
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
- obj->base.size,
- total,
- obj->cache_level,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+ err = reserve_gtt_with_resource(vma, total);
if (err) {
pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n",
total, ggtt->vm.total, err);
@@ -1476,13 +1490,8 @@ static int igt_gtt_reserve(void *arg)
2 * I915_GTT_PAGE_SIZE,
I915_GTT_MIN_ALIGNMENT);
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
- obj->base.size,
- offset,
- obj->cache_level,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+
+ err = reserve_gtt_with_resource(vma, offset);
if (err) {
pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n",
total, ggtt->vm.total, err);
@@ -1509,6 +1518,31 @@ static int igt_gtt_reserve(void *arg)
return err;
}
+static int insert_gtt_with_resource(struct i915_vma *vma)
+{
+ struct i915_address_space *vm = vma->vm;
+ struct i915_vma_resource *vma_res;
+ struct drm_i915_gem_object *obj = vma->obj;
+ int err;
+
+ vma_res = i915_vma_resource_alloc();
+ if (IS_ERR(vma_res))
+ return PTR_ERR(vma_res);
+
+ mutex_lock(&vm->mutex);
+ err = i915_gem_gtt_insert(vm, &vma->node, obj->base.size, 0,
+ obj->cache_level, 0, vm->total, 0);
+ if (!err) {
+ i915_vma_resource_init(vma_res, vma);
+ vma->resource = vma_res;
+ } else {
+ kfree(vma_res);
+ }
+ mutex_unlock(&vm->mutex);
+
+ return err;
+}
+
static int igt_gtt_insert(void *arg)
{
struct i915_ggtt *ggtt = arg;
@@ -1593,12 +1627,7 @@ static int igt_gtt_insert(void *arg)
goto out;
}
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
- obj->base.size, 0, obj->cache_level,
- 0, ggtt->vm.total,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+ err = insert_gtt_with_resource(vma);
if (err == -ENOSPC) {
/* maxed out the GGTT space */
i915_gem_object_put(obj);
@@ -1653,12 +1682,7 @@ static int igt_gtt_insert(void *arg)
goto out;
}
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
- obj->base.size, 0, obj->cache_level,
- 0, ggtt->vm.total,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+ err = insert_gtt_with_resource(vma);
if (err) {
pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n",
total, ggtt->vm.total, err);
@@ -1702,12 +1726,7 @@ static int igt_gtt_insert(void *arg)
goto out;
}
- mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
- obj->base.size, 0, obj->cache_level,
- 0, ggtt->vm.total,
- 0);
- mutex_unlock(&ggtt->vm.mutex);
+ err = insert_gtt_with_resource(vma);
if (err) {
pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n",
total, ggtt->vm.total, err);
--
2.31.1
^ permalink raw reply related [flat|nested] 15+ messages in thread* Re: [Intel-gfx] [PATCH v2 3/3] drm/i915: Initial introduction of vma resources
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 3/3] drm/i915: Initial introduction of vma resources Thomas Hellström
@ 2021-10-27 22:07 ` kernel test robot
0 siblings, 0 replies; 15+ messages in thread
From: kernel test robot @ 2021-10-27 22:07 UTC (permalink / raw)
To: Thomas Hellström, intel-gfx, dri-devel
Cc: kbuild-all, maarten.lankhorst, matthew.auld,
Thomas Hellström
[-- Attachment #1: Type: text/plain, Size: 6257 bytes --]
Hi "Thomas,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on drm-tip/drm-tip]
[cannot apply to drm-intel/for-linux-next drm-exynos/exynos-drm-next drm/drm-next tegra-drm/drm/tegra/for-next airlied/drm-next v5.15-rc7 next-20211027]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Thomas-Hellstr-m/Prepare-error-capture-for-asynchronous-migration/20211027-185501
base: git://anongit.freedesktop.org/drm/drm-tip drm-tip
config: i386-defconfig (attached as .config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce (this is a W=1 build):
# https://github.com/0day-ci/linux/commit/ce3de63c87b40e04e9a9960549435085aa55fb27
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Thomas-Hellstr-m/Prepare-error-capture-for-asynchronous-migration/20211027-185501
git checkout ce3de63c87b40e04e9a9960549435085aa55fb27
# save the attached .config to linux build tree
make W=1 ARCH=i386
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
drivers/gpu/drm/i915/i915_vma.c: In function 'i915_vma_bind':
>> drivers/gpu/drm/i915/i915_vma.c:445:3: error: implicit declaration of function 'i915_vma_resource_init'; did you mean 'i915_vma_resource_put'? [-Werror=implicit-function-declaration]
445 | i915_vma_resource_init(vma_res, vma);
| ^~~~~~~~~~~~~~~~~~~~~~
| i915_vma_resource_put
drivers/gpu/drm/i915/i915_vma.c: At top level:
drivers/gpu/drm/i915/i915_vma.c:1502:1: error: conflicting types for 'i915_vma_resource_init' [-Werror]
1502 | i915_vma_resource_init(struct i915_vma_resource *vma_res,
| ^~~~~~~~~~~~~~~~~~~~~~
>> drivers/gpu/drm/i915/i915_vma.c:1502:1: error: static declaration of 'i915_vma_resource_init' follows non-static declaration
drivers/gpu/drm/i915/i915_vma.c:445:3: note: previous implicit declaration of 'i915_vma_resource_init' was here
445 | i915_vma_resource_init(vma_res, vma);
| ^~~~~~~~~~~~~~~~~~~~~~
>> drivers/gpu/drm/i915/i915_vma.c:1502:1: error: 'i915_vma_resource_init' defined but not used [-Werror=unused-function]
1502 | i915_vma_resource_init(struct i915_vma_resource *vma_res,
| ^~~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
vim +445 drivers/gpu/drm/i915/i915_vma.c
384
385 /**
386 * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space.
387 * @vma: VMA to map
388 * @cache_level: mapping cache level
389 * @flags: flags like global or local mapping
390 * @work: preallocated worker for allocating and binding the PTE
391 * @vma_res: pointer to a preallocated vma resource. The resource is either
392 * consumed or freed.
393 *
394 * DMA addresses are taken from the scatter-gather table of this object (or of
395 * this VMA in case of non-default GGTT views) and PTE entries set up.
396 * Note that DMA addresses are also the only part of the SG table we care about.
397 */
398 int i915_vma_bind(struct i915_vma *vma,
399 enum i915_cache_level cache_level,
400 u32 flags,
401 struct i915_vma_work *work,
402 struct i915_vma_resource *vma_res)
403 {
404 u32 bind_flags;
405 u32 vma_flags;
406
407 GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
408 GEM_BUG_ON(vma->size > vma->node.size);
409
410 if (GEM_DEBUG_WARN_ON(range_overflows(vma->node.start,
411 vma->node.size,
412 vma->vm->total))) {
413 kfree(vma_res);
414 return -ENODEV;
415 }
416
417 if (GEM_DEBUG_WARN_ON(!flags)) {
418 kfree(vma_res);
419 return -EINVAL;
420 }
421
422 bind_flags = flags;
423 bind_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
424
425 vma_flags = atomic_read(&vma->flags);
426 vma_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
427
428 bind_flags &= ~vma_flags;
429 if (bind_flags == 0) {
430 kfree(vma_res);
431 return 0;
432 }
433
434 GEM_BUG_ON(!vma->pages);
435
436 if (!i915_vma_is_pinned(vma))
437 lockdep_assert_held(&vma->vm->mutex);
438
439 if ((vma->resource) || !vma_res) {
440 /* Rebinding with an additional I915_VMA_*_BIND */
441 GEM_WARN_ON(!vma_flags);
442 kfree(vma_res);
443 } else {
444 lockdep_assert_held(&vma->vm->mutex);
> 445 i915_vma_resource_init(vma_res, vma);
446 vma->resource = vma_res;
447 }
448 trace_i915_vma_bind(vma, bind_flags);
449 if (work && bind_flags & vma->vm->bind_async_flags) {
450 struct dma_fence *prev;
451
452 work->vma = vma;
453 work->cache_level = cache_level;
454 work->flags = bind_flags;
455
456 /*
457 * Note we only want to chain up to the migration fence on
458 * the pages (not the object itself). As we don't track that,
459 * yet, we have to use the exclusive fence instead.
460 *
461 * Also note that we do not want to track the async vma as
462 * part of the obj->resv->excl_fence as it only affects
463 * execution and not content or object's backing store lifetime.
464 */
465 prev = i915_active_set_exclusive(&vma->active, &work->base.dma);
466 if (prev) {
467 __i915_sw_fence_await_dma_fence(&work->base.chain,
468 prev,
469 &work->cb);
470 dma_fence_put(prev);
471 }
472
473 work->base.dma.error = 0; /* enable the queue_work() */
474
475 if (vma->obj) {
476 __i915_gem_object_pin_pages(vma->obj);
477 work->pinned = i915_gem_object_get(vma->obj);
478 }
479 } else {
480 vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
481 }
482
483 atomic_or(bind_flags, &vma->flags);
484 return 0;
485 }
486
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 29349 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread
* [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Prepare error capture for asynchronous migration (rev2)
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
` (2 preceding siblings ...)
2021-10-27 10:52 ` [Intel-gfx] [PATCH v2 3/3] drm/i915: Initial introduction of vma resources Thomas Hellström
@ 2021-10-27 14:40 ` Patchwork
2021-10-27 15:13 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-10-27 18:54 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
5 siblings, 0 replies; 15+ messages in thread
From: Patchwork @ 2021-10-27 14:40 UTC (permalink / raw)
To: Thomas Hellström; +Cc: intel-gfx
== Series Details ==
Series: Prepare error capture for asynchronous migration (rev2)
URL : https://patchwork.freedesktop.org/series/96281/
State : warning
== Summary ==
$ dim checkpatch origin/drm-tip
bf0df3812af8 drm/i915: Introduce refcounted sg-tables
69d21354f04a drm/i915: Update error capture code to avoid using the current vma state
-:803: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#803:
new file mode 100644
total: 0 errors, 1 warnings, 0 checks, 958 lines checked
ff852d0fa9df drm/i915: Initial introduction of vma resources
-:144: CHECK:UNNECESSARY_PARENTHESES: Unnecessary parentheses around 'vma->resource'
#144: FILE: drivers/gpu/drm/i915/i915_vma.c:439:
+ if ((vma->resource) || !vma_res) {
-:564: CHECK:LINE_SPACING: Please don't use multiple blank lines
#564: FILE: drivers/gpu/drm/i915/selftests/i915_gem_gtt.c:1493:
+
total: 0 errors, 0 warnings, 2 checks, 543 lines checked
^ permalink raw reply [flat|nested] 15+ messages in thread* [Intel-gfx] ✓ Fi.CI.BAT: success for Prepare error capture for asynchronous migration (rev2)
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
` (3 preceding siblings ...)
2021-10-27 14:40 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Prepare error capture for asynchronous migration (rev2) Patchwork
@ 2021-10-27 15:13 ` Patchwork
2021-10-27 18:54 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
5 siblings, 0 replies; 15+ messages in thread
From: Patchwork @ 2021-10-27 15:13 UTC (permalink / raw)
To: Thomas Hellström; +Cc: intel-gfx
[-- Attachment #1: Type: text/plain, Size: 3266 bytes --]
== Series Details ==
Series: Prepare error capture for asynchronous migration (rev2)
URL : https://patchwork.freedesktop.org/series/96281/
State : success
== Summary ==
CI Bug Log - changes from CI_DRM_10796 -> Patchwork_21460
====================================================
Summary
-------
**SUCCESS**
No regressions found.
External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/index.html
Participating hosts (39 -> 33)
------------------------------
Missing (6): bat-dg1-6 bat-dg1-5 fi-bsw-cyan fi-icl-u2 bat-adlp-4 fi-pnv-d510
Known issues
------------
Here are the changes found in Patchwork_21460 that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@debugfs_test@read_all_entries:
- fi-apl-guc: [PASS][1] -> [DMESG-WARN][2] ([i915#1610])
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/fi-apl-guc/igt@debugfs_test@read_all_entries.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/fi-apl-guc/igt@debugfs_test@read_all_entries.html
* igt@i915_selftest@live@hangcheck:
- fi-snb-2600: [PASS][3] -> [INCOMPLETE][4] ([i915#3921])
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/fi-snb-2600/igt@i915_selftest@live@hangcheck.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/fi-snb-2600/igt@i915_selftest@live@hangcheck.html
* igt@kms_frontbuffer_tracking@basic:
- fi-cml-u2: [PASS][5] -> [DMESG-WARN][6] ([i915#4269])
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/fi-cml-u2/igt@kms_frontbuffer_tracking@basic.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/fi-cml-u2/igt@kms_frontbuffer_tracking@basic.html
#### Possible fixes ####
* igt@kms_frontbuffer_tracking@basic:
- {fi-hsw-gt1}: [DMESG-WARN][7] ([i915#4290]) -> [PASS][8]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/fi-hsw-gt1/igt@kms_frontbuffer_tracking@basic.html
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/fi-hsw-gt1/igt@kms_frontbuffer_tracking@basic.html
{name}: This element is suppressed. This means it is ignored when computing
the status of the difference (SUCCESS, WARNING, or FAILURE).
[i915#1610]: https://gitlab.freedesktop.org/drm/intel/issues/1610
[i915#3921]: https://gitlab.freedesktop.org/drm/intel/issues/3921
[i915#4269]: https://gitlab.freedesktop.org/drm/intel/issues/4269
[i915#4290]: https://gitlab.freedesktop.org/drm/intel/issues/4290
Build changes
-------------
* Linux: CI_DRM_10796 -> Patchwork_21460
CI-20190529: 20190529
CI_DRM_10796: c2698ab428a9398c02ef1ee3a03f51608cf97a86 @ git://anongit.freedesktop.org/gfx-ci/linux
IGT_6262: d1c793b26e31cc6ae3f9fa3239805a9bbcc749fb @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
Patchwork_21460: ff852d0fa9dfdea483c8c2af48d1ea23e75be309 @ git://anongit.freedesktop.org/gfx-ci/linux
== Linux commits ==
ff852d0fa9df drm/i915: Initial introduction of vma resources
69d21354f04a drm/i915: Update error capture code to avoid using the current vma state
bf0df3812af8 drm/i915: Introduce refcounted sg-tables
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/index.html
[-- Attachment #2: Type: text/html, Size: 3974 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread* [Intel-gfx] ✗ Fi.CI.IGT: failure for Prepare error capture for asynchronous migration (rev2)
2021-10-27 10:52 [Intel-gfx] [PATCH v2 0/3] Prepare error capture for asynchronous migration Thomas Hellström
` (4 preceding siblings ...)
2021-10-27 15:13 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
@ 2021-10-27 18:54 ` Patchwork
5 siblings, 0 replies; 15+ messages in thread
From: Patchwork @ 2021-10-27 18:54 UTC (permalink / raw)
To: Thomas Hellström; +Cc: intel-gfx
[-- Attachment #1: Type: text/plain, Size: 30278 bytes --]
== Series Details ==
Series: Prepare error capture for asynchronous migration (rev2)
URL : https://patchwork.freedesktop.org/series/96281/
State : failure
== Summary ==
CI Bug Log - changes from CI_DRM_10796_full -> Patchwork_21460_full
====================================================
Summary
-------
**FAILURE**
Serious unknown changes coming with Patchwork_21460_full absolutely need to be
verified manually.
If you think the reported changes have nothing to do with the changes
introduced in Patchwork_21460_full, please notify your bug team to allow them
to document this new failure mode, which will reduce false positives in CI.
Participating hosts (10 -> 10)
------------------------------
No changes in participating hosts
Possible new issues
-------------------
Here are the unknown changes that may have been introduced in Patchwork_21460_full:
### IGT changes ###
#### Possible regressions ####
* igt@gem_softpin@noreloc-s3:
- shard-iclb: [PASS][1] -> [DMESG-WARN][2]
[1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb5/igt@gem_softpin@noreloc-s3.html
[2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb6/igt@gem_softpin@noreloc-s3.html
- shard-snb: [PASS][3] -> [DMESG-WARN][4]
[3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-snb2/igt@gem_softpin@noreloc-s3.html
[4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-snb5/igt@gem_softpin@noreloc-s3.html
* igt@i915_pm_rpm@cursor:
- shard-iclb: [PASS][5] -> [INCOMPLETE][6]
[5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb8/igt@i915_pm_rpm@cursor.html
[6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb4/igt@i915_pm_rpm@cursor.html
* igt@kms_flip@single-buffer-flip-vs-dpms-off-vs-modeset@a-edp1:
- shard-tglb: [PASS][7] -> [INCOMPLETE][8]
[7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb5/igt@kms_flip@single-buffer-flip-vs-dpms-off-vs-modeset@a-edp1.html
[8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb6/igt@kms_flip@single-buffer-flip-vs-dpms-off-vs-modeset@a-edp1.html
### Piglit changes ###
#### Possible regressions ####
* spec@arb_gpu_shader5@texturegatheroffset@fs-r-0-unorm-2darray-const (NEW):
- pig-kbl-iris: NOTRUN -> [INCOMPLETE][9] +7 similar issues
[9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/pig-kbl-iris/spec@arb_gpu_shader5@texturegatheroffset@fs-r-0-unorm-2darray-const.html
New tests
---------
New tests have been introduced between CI_DRM_10796_full and Patchwork_21460_full:
### New Piglit tests (8) ###
* spec@arb_gpu_shader5@texturegather@fs-r-0-unorm-2darray:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegather@fs-r-0-unorm-cube:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegather@fs-r-0-unorm-cubearray:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegatheroffset@fs-r-0-unorm-2d-const:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegatheroffset@fs-r-0-unorm-2darray:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegatheroffset@fs-r-0-unorm-2darray-const:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegatheroffsets@fs-r-0-unorm-2d:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
* spec@arb_gpu_shader5@texturegatheroffsets@fs-r-0-unorm-2darray:
- Statuses : 1 incomplete(s)
- Exec time: [0.0] s
Known issues
------------
Here are the changes found in Patchwork_21460_full that come from known issues:
### IGT changes ###
#### Issues hit ####
* igt@feature_discovery@psr2:
- shard-iclb: [PASS][10] -> [SKIP][11] ([i915#658])
[10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb2/igt@feature_discovery@psr2.html
[11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb8/igt@feature_discovery@psr2.html
* igt@gem_exec_fair@basic-none-share@rcs0:
- shard-apl: [PASS][12] -> [SKIP][13] ([fdo#109271])
[12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-apl3/igt@gem_exec_fair@basic-none-share@rcs0.html
[13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl2/igt@gem_exec_fair@basic-none-share@rcs0.html
* igt@gem_exec_fair@basic-none@rcs0:
- shard-glk: [PASS][14] -> [FAIL][15] ([i915#2842])
[14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-glk7/igt@gem_exec_fair@basic-none@rcs0.html
[15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk8/igt@gem_exec_fair@basic-none@rcs0.html
* igt@gem_exec_fair@basic-none@vcs0:
- shard-apl: [PASS][16] -> [FAIL][17] ([i915#2842])
[16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-apl2/igt@gem_exec_fair@basic-none@vcs0.html
[17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl7/igt@gem_exec_fair@basic-none@vcs0.html
* igt@gem_exec_fair@basic-pace@rcs0:
- shard-kbl: [PASS][18] -> [SKIP][19] ([fdo#109271]) +1 similar issue
[18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-kbl7/igt@gem_exec_fair@basic-pace@rcs0.html
[19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl3/igt@gem_exec_fair@basic-pace@rcs0.html
* igt@gem_exec_fair@basic-pace@vcs1:
- shard-iclb: NOTRUN -> [FAIL][20] ([i915#2842])
[20]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb1/igt@gem_exec_fair@basic-pace@vcs1.html
* igt@gem_exec_fair@basic-throttle@rcs0:
- shard-tglb: NOTRUN -> [FAIL][21] ([i915#2842])
[21]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@gem_exec_fair@basic-throttle@rcs0.html
* igt@gem_huc_copy@huc-copy:
- shard-kbl: NOTRUN -> [SKIP][22] ([fdo#109271] / [i915#2190])
[22]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@gem_huc_copy@huc-copy.html
* igt@gem_pxp@verify-pxp-stale-ctx-execution:
- shard-tglb: NOTRUN -> [SKIP][23] ([i915#4270]) +1 similar issue
[23]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@gem_pxp@verify-pxp-stale-ctx-execution.html
* igt@gem_workarounds@suspend-resume:
- shard-tglb: [PASS][24] -> [INCOMPLETE][25] ([i915#456]) +1 similar issue
[24]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb6/igt@gem_workarounds@suspend-resume.html
[25]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb7/igt@gem_workarounds@suspend-resume.html
* igt@gen9_exec_parse@allowed-all:
- shard-skl: [PASS][26] -> [DMESG-WARN][27] ([i915#1436] / [i915#716])
[26]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl4/igt@gen9_exec_parse@allowed-all.html
[27]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl10/igt@gen9_exec_parse@allowed-all.html
* igt@i915_pm_rpm@gem-execbuf-stress-pc8:
- shard-tglb: NOTRUN -> [SKIP][28] ([fdo#109506] / [i915#2411])
[28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@i915_pm_rpm@gem-execbuf-stress-pc8.html
* igt@i915_query@query-topology-known-pci-ids:
- shard-tglb: NOTRUN -> [SKIP][29] ([fdo#109303])
[29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@i915_query@query-topology-known-pci-ids.html
* igt@i915_query@query-topology-unsupported:
- shard-tglb: NOTRUN -> [SKIP][30] ([fdo#109302])
[30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@i915_query@query-topology-unsupported.html
* igt@kms_big_fb@x-tiled-64bpp-rotate-270:
- shard-tglb: NOTRUN -> [SKIP][31] ([fdo#111614]) +2 similar issues
[31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_big_fb@x-tiled-64bpp-rotate-270.html
* igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-async-flip:
- shard-skl: NOTRUN -> [FAIL][32] ([i915#3743])
[32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-180-async-flip.html
* igt@kms_big_fb@y-tiled-16bpp-rotate-0:
- shard-glk: [PASS][33] -> [DMESG-WARN][34] ([i915#118]) +1 similar issue
[33]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-glk5/igt@kms_big_fb@y-tiled-16bpp-rotate-0.html
[34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk4/igt@kms_big_fb@y-tiled-16bpp-rotate-0.html
* igt@kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180-hflip:
- shard-kbl: NOTRUN -> [SKIP][35] ([fdo#109271] / [i915#3777])
[35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@kms_big_fb@y-tiled-max-hw-stride-64bpp-rotate-180-hflip.html
* igt@kms_big_fb@yf-tiled-32bpp-rotate-0:
- shard-tglb: NOTRUN -> [SKIP][36] ([fdo#111615]) +4 similar issues
[36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_big_fb@yf-tiled-32bpp-rotate-0.html
* igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_rc_ccs_cc:
- shard-skl: NOTRUN -> [SKIP][37] ([fdo#109271] / [i915#3886]) +1 similar issue
[37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_rc_ccs_cc.html
* igt@kms_ccs@pipe-b-random-ccs-data-y_tiled_gen12_mc_ccs:
- shard-kbl: NOTRUN -> [SKIP][38] ([fdo#109271] / [i915#3886]) +6 similar issues
[38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_ccs@pipe-b-random-ccs-data-y_tiled_gen12_mc_ccs.html
* igt@kms_ccs@pipe-c-ccs-on-another-bo-y_tiled_gen12_mc_ccs:
- shard-glk: NOTRUN -> [SKIP][39] ([fdo#109271] / [i915#3886]) +1 similar issue
[39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@kms_ccs@pipe-c-ccs-on-another-bo-y_tiled_gen12_mc_ccs.html
* igt@kms_ccs@pipe-c-random-ccs-data-y_tiled_gen12_mc_ccs:
- shard-tglb: NOTRUN -> [SKIP][40] ([i915#3689] / [i915#3886]) +1 similar issue
[40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_ccs@pipe-c-random-ccs-data-y_tiled_gen12_mc_ccs.html
* igt@kms_ccs@pipe-d-bad-rotation-90-yf_tiled_ccs:
- shard-tglb: NOTRUN -> [SKIP][41] ([i915#3689]) +2 similar issues
[41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_ccs@pipe-d-bad-rotation-90-yf_tiled_ccs.html
* igt@kms_ccs@pipe-d-crc-primary-rotation-180-yf_tiled_ccs:
- shard-apl: NOTRUN -> [SKIP][42] ([fdo#109271]) +13 similar issues
[42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl8/igt@kms_ccs@pipe-d-crc-primary-rotation-180-yf_tiled_ccs.html
* igt@kms_chamelium@dp-crc-multiple:
- shard-tglb: NOTRUN -> [SKIP][43] ([fdo#109284] / [fdo#111827]) +4 similar issues
[43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_chamelium@dp-crc-multiple.html
* igt@kms_chamelium@hdmi-aspect-ratio:
- shard-glk: NOTRUN -> [SKIP][44] ([fdo#109271] / [fdo#111827]) +5 similar issues
[44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@kms_chamelium@hdmi-aspect-ratio.html
* igt@kms_chamelium@hdmi-crc-nonplanar-formats:
- shard-iclb: NOTRUN -> [SKIP][45] ([fdo#109284] / [fdo#111827])
[45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_chamelium@hdmi-crc-nonplanar-formats.html
* igt@kms_color_chamelium@pipe-a-ctm-negative:
- shard-kbl: NOTRUN -> [SKIP][46] ([fdo#109271] / [fdo#111827]) +10 similar issues
[46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@kms_color_chamelium@pipe-a-ctm-negative.html
* igt@kms_color_chamelium@pipe-d-ctm-0-25:
- shard-skl: NOTRUN -> [SKIP][47] ([fdo#109271] / [fdo#111827]) +2 similar issues
[47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_color_chamelium@pipe-d-ctm-0-25.html
* igt@kms_color_chamelium@pipe-d-ctm-max:
- shard-apl: NOTRUN -> [SKIP][48] ([fdo#109271] / [fdo#111827])
[48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl8/igt@kms_color_chamelium@pipe-d-ctm-max.html
* igt@kms_content_protection@atomic:
- shard-kbl: NOTRUN -> [TIMEOUT][49] ([i915#1319])
[49]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_content_protection@atomic.html
* igt@kms_content_protection@type1:
- shard-tglb: NOTRUN -> [SKIP][50] ([fdo#111828])
[50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_content_protection@type1.html
* igt@kms_cursor_crc@pipe-a-cursor-32x32-sliding:
- shard-tglb: NOTRUN -> [SKIP][51] ([i915#3319])
[51]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_cursor_crc@pipe-a-cursor-32x32-sliding.html
* igt@kms_cursor_crc@pipe-b-cursor-512x512-random:
- shard-tglb: NOTRUN -> [SKIP][52] ([fdo#109279] / [i915#3359])
[52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_cursor_crc@pipe-b-cursor-512x512-random.html
* igt@kms_cursor_crc@pipe-c-cursor-max-size-offscreen:
- shard-tglb: NOTRUN -> [SKIP][53] ([i915#3359]) +2 similar issues
[53]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_cursor_crc@pipe-c-cursor-max-size-offscreen.html
* igt@kms_cursor_crc@pipe-c-cursor-suspend:
- shard-kbl: NOTRUN -> [DMESG-WARN][54] ([i915#180]) +2 similar issues
[54]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_cursor_crc@pipe-c-cursor-suspend.html
* igt@kms_cursor_crc@pipe-d-cursor-512x512-sliding:
- shard-glk: NOTRUN -> [SKIP][55] ([fdo#109271]) +31 similar issues
[55]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@kms_cursor_crc@pipe-d-cursor-512x512-sliding.html
* igt@kms_cursor_legacy@basic-busy-flip-before-cursor-atomic:
- shard-tglb: NOTRUN -> [SKIP][56] ([i915#4103]) +1 similar issue
[56]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_cursor_legacy@basic-busy-flip-before-cursor-atomic.html
* igt@kms_cursor_legacy@flip-vs-cursor-atomic:
- shard-skl: [PASS][57] -> [FAIL][58] ([i915#2346]) +1 similar issue
[57]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl6/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html
[58]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl2/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html
* igt@kms_fbcon_fbt@fbc-suspend:
- shard-apl: [PASS][59] -> [INCOMPLETE][60] ([i915#180] / [i915#1982])
[59]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-apl1/igt@kms_fbcon_fbt@fbc-suspend.html
[60]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl4/igt@kms_fbcon_fbt@fbc-suspend.html
* igt@kms_flip@2x-plain-flip-ts-check-interruptible:
- shard-iclb: NOTRUN -> [SKIP][61] ([fdo#109274])
[61]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_flip@2x-plain-flip-ts-check-interruptible.html
* igt@kms_flip@plain-flip-fb-recreate-interruptible@c-edp1:
- shard-skl: [PASS][62] -> [FAIL][63] ([i915#2122]) +3 similar issues
[62]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl7/igt@kms_flip@plain-flip-fb-recreate-interruptible@c-edp1.html
[63]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl2/igt@kms_flip@plain-flip-fb-recreate-interruptible@c-edp1.html
* igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile:
- shard-iclb: [PASS][64] -> [SKIP][65] ([i915#3701])
[64]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb7/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile.html
[65]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb2/igt@kms_flip_scaled_crc@flip-32bpp-ytileccs-to-64bpp-ytile.html
* igt@kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-blt:
- shard-iclb: NOTRUN -> [SKIP][66] ([fdo#109280])
[66]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_frontbuffer_tracking@fbc-2p-primscrn-spr-indfb-draw-blt.html
* igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-blt:
- shard-skl: NOTRUN -> [SKIP][67] ([fdo#109271]) +51 similar issues
[67]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_frontbuffer_tracking@fbc-2p-scndscrn-pri-indfb-draw-blt.html
* igt@kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-move:
- shard-tglb: NOTRUN -> [SKIP][68] ([fdo#111825]) +11 similar issues
[68]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_frontbuffer_tracking@psr-2p-scndscrn-cur-indfb-move.html
* igt@kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-wc:
- shard-kbl: NOTRUN -> [SKIP][69] ([fdo#109271]) +145 similar issues
[69]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl3/igt@kms_frontbuffer_tracking@psr-rgb101010-draw-mmap-wc.html
* igt@kms_frontbuffer_tracking@psr-suspend:
- shard-tglb: [PASS][70] -> [INCOMPLETE][71] ([i915#2411] / [i915#456])
[70]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb3/igt@kms_frontbuffer_tracking@psr-suspend.html
[71]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb7/igt@kms_frontbuffer_tracking@psr-suspend.html
* igt@kms_hdr@bpc-switch-suspend:
- shard-apl: [PASS][72] -> [DMESG-WARN][73] ([i915#180]) +4 similar issues
[72]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-apl3/igt@kms_hdr@bpc-switch-suspend.html
[73]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl2/igt@kms_hdr@bpc-switch-suspend.html
* igt@kms_pipe_crc_basic@read-crc-pipe-d-frame-sequence:
- shard-kbl: NOTRUN -> [SKIP][74] ([fdo#109271] / [i915#533])
[74]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_pipe_crc_basic@read-crc-pipe-d-frame-sequence.html
* igt@kms_plane@plane-panning-bottom-right-suspend@pipe-b-planes:
- shard-kbl: [PASS][75] -> [DMESG-WARN][76] ([i915#180])
[75]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-kbl3/igt@kms_plane@plane-panning-bottom-right-suspend@pipe-b-planes.html
[76]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_plane@plane-panning-bottom-right-suspend@pipe-b-planes.html
* igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max:
- shard-glk: NOTRUN -> [FAIL][77] ([fdo#108145] / [i915#265])
[77]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max.html
- shard-apl: NOTRUN -> [FAIL][78] ([fdo#108145] / [i915#265])
[78]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl8/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-max.html
* igt@kms_plane_alpha_blend@pipe-b-alpha-transparent-fb:
- shard-kbl: NOTRUN -> [FAIL][79] ([i915#265])
[79]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl3/igt@kms_plane_alpha_blend@pipe-b-alpha-transparent-fb.html
- shard-skl: NOTRUN -> [FAIL][80] ([i915#265])
[80]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_plane_alpha_blend@pipe-b-alpha-transparent-fb.html
* igt@kms_plane_alpha_blend@pipe-b-constant-alpha-min:
- shard-skl: [PASS][81] -> [FAIL][82] ([fdo#108145] / [i915#265])
[81]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl7/igt@kms_plane_alpha_blend@pipe-b-constant-alpha-min.html
[82]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl2/igt@kms_plane_alpha_blend@pipe-b-constant-alpha-min.html
* igt@kms_plane_alpha_blend@pipe-c-alpha-7efc:
- shard-kbl: NOTRUN -> [FAIL][83] ([fdo#108145] / [i915#265])
[83]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@kms_plane_alpha_blend@pipe-c-alpha-7efc.html
* igt@kms_plane_lowres@pipe-b-tiling-y:
- shard-tglb: NOTRUN -> [SKIP][84] ([i915#3536])
[84]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_plane_lowres@pipe-b-tiling-y.html
* igt@kms_plane_lowres@pipe-c-tiling-yf:
- shard-iclb: NOTRUN -> [SKIP][85] ([i915#3536])
[85]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_plane_lowres@pipe-c-tiling-yf.html
* igt@kms_plane_lowres@pipe-d-tiling-yf:
- shard-tglb: NOTRUN -> [SKIP][86] ([fdo#112054]) +1 similar issue
[86]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_plane_lowres@pipe-d-tiling-yf.html
* igt@kms_psr2_sf@overlay-plane-update-sf-dmg-area-1:
- shard-kbl: NOTRUN -> [SKIP][87] ([fdo#109271] / [i915#658]) +2 similar issues
[87]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@kms_psr2_sf@overlay-plane-update-sf-dmg-area-1.html
- shard-tglb: NOTRUN -> [SKIP][88] ([i915#2920])
[88]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_psr2_sf@overlay-plane-update-sf-dmg-area-1.html
* igt@kms_psr2_sf@overlay-plane-update-sf-dmg-area-5:
- shard-skl: NOTRUN -> [SKIP][89] ([fdo#109271] / [i915#658])
[89]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl1/igt@kms_psr2_sf@overlay-plane-update-sf-dmg-area-5.html
* igt@kms_psr2_sf@primary-plane-update-sf-dmg-area-5:
- shard-iclb: NOTRUN -> [SKIP][90] ([i915#658])
[90]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_psr2_sf@primary-plane-update-sf-dmg-area-5.html
* igt@kms_psr@psr2_cursor_plane_onoff:
- shard-tglb: NOTRUN -> [FAIL][91] ([i915#132] / [i915#3467]) +1 similar issue
[91]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@kms_psr@psr2_cursor_plane_onoff.html
* igt@kms_psr@psr2_primary_mmap_cpu:
- shard-iclb: [PASS][92] -> [SKIP][93] ([fdo#109441]) +1 similar issue
[92]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb2/igt@kms_psr@psr2_primary_mmap_cpu.html
[93]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb4/igt@kms_psr@psr2_primary_mmap_cpu.html
* igt@kms_psr@psr2_primary_render:
- shard-iclb: NOTRUN -> [SKIP][94] ([fdo#109441])
[94]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_psr@psr2_primary_render.html
* igt@kms_universal_plane@universal-plane-gen9-features-pipe-d:
- shard-iclb: NOTRUN -> [SKIP][95] ([fdo#109278])
[95]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@kms_universal_plane@universal-plane-gen9-features-pipe-d.html
* igt@kms_writeback@writeback-check-output:
- shard-kbl: NOTRUN -> [SKIP][96] ([fdo#109271] / [i915#2437])
[96]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl4/igt@kms_writeback@writeback-check-output.html
* igt@kms_writeback@writeback-fb-id:
- shard-glk: NOTRUN -> [SKIP][97] ([fdo#109271] / [i915#2437])
[97]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@kms_writeback@writeback-fb-id.html
* igt@nouveau_crc@pipe-b-ctx-flip-detection:
- shard-tglb: NOTRUN -> [SKIP][98] ([i915#2530])
[98]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@nouveau_crc@pipe-b-ctx-flip-detection.html
* igt@prime_nv_test@i915_import_gtt_mmap:
- shard-iclb: NOTRUN -> [SKIP][99] ([fdo#109291])
[99]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb3/igt@prime_nv_test@i915_import_gtt_mmap.html
* igt@sysfs_clients@create:
- shard-kbl: NOTRUN -> [SKIP][100] ([fdo#109271] / [i915#2994])
[100]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl3/igt@sysfs_clients@create.html
* igt@sysfs_clients@fair-0:
- shard-glk: NOTRUN -> [SKIP][101] ([fdo#109271] / [i915#2994])
[101]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk7/igt@sysfs_clients@fair-0.html
* igt@sysfs_clients@pidname:
- shard-tglb: NOTRUN -> [SKIP][102] ([i915#2994])
[102]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@sysfs_clients@pidname.html
#### Possible fixes ####
* igt@gem_ctx_shared@q-smoketest-all:
- shard-glk: [DMESG-WARN][103] ([i915#118]) -> [PASS][104]
[103]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-glk6/igt@gem_ctx_shared@q-smoketest-all.html
[104]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk6/igt@gem_ctx_shared@q-smoketest-all.html
* igt@gem_exec_fair@basic-none@vcs0:
- shard-kbl: [FAIL][105] ([i915#2842]) -> [PASS][106] +1 similar issue
[105]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-kbl1/igt@gem_exec_fair@basic-none@vcs0.html
[106]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@gem_exec_fair@basic-none@vcs0.html
* igt@gem_exec_fair@basic-none@vecs0:
- shard-iclb: [FAIL][107] ([i915#2842]) -> [PASS][108]
[107]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb3/igt@gem_exec_fair@basic-none@vecs0.html
[108]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb7/igt@gem_exec_fair@basic-none@vecs0.html
* igt@gem_exec_fair@basic-pace@rcs0:
- shard-tglb: [FAIL][109] ([i915#2842]) -> [PASS][110]
[109]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb1/igt@gem_exec_fair@basic-pace@rcs0.html
[110]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb3/igt@gem_exec_fair@basic-pace@rcs0.html
* igt@gem_workarounds@suspend-resume:
- shard-apl: [DMESG-WARN][111] ([i915#180]) -> [PASS][112]
[111]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-apl4/igt@gem_workarounds@suspend-resume.html
[112]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-apl8/igt@gem_workarounds@suspend-resume.html
* igt@i915_suspend@debugfs-reader:
- shard-tglb: [INCOMPLETE][113] ([i915#456]) -> [PASS][114]
[113]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb7/igt@i915_suspend@debugfs-reader.html
[114]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb5/igt@i915_suspend@debugfs-reader.html
* igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy:
- shard-glk: [FAIL][115] ([i915#72]) -> [PASS][116]
[115]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-glk5/igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy.html
[116]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-glk3/igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy.html
* igt@kms_cursor_legacy@flip-vs-cursor-toggle:
- shard-iclb: [FAIL][117] ([i915#2346]) -> [PASS][118]
[117]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-iclb7/igt@kms_cursor_legacy@flip-vs-cursor-toggle.html
[118]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-iclb5/igt@kms_cursor_legacy@flip-vs-cursor-toggle.html
* igt@kms_fbcon_fbt@fbc-suspend:
- shard-kbl: [INCOMPLETE][119] ([i915#180] / [i915#636]) -> [PASS][120]
[119]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-kbl6/igt@kms_fbcon_fbt@fbc-suspend.html
[120]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl3/igt@kms_fbcon_fbt@fbc-suspend.html
* igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1:
- shard-skl: [FAIL][121] ([i915#79]) -> [PASS][122]
[121]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl4/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html
[122]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl10/igt@kms_flip@flip-vs-expired-vblank-interruptible@a-edp1.html
* igt@kms_flip@modeset-vs-vblank-race-interruptible@b-edp1:
- shard-tglb: [INCOMPLETE][123] -> [PASS][124]
[123]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-tglb8/igt@kms_flip@modeset-vs-vblank-race-interruptible@b-edp1.html
[124]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-tglb2/igt@kms_flip@modeset-vs-vblank-race-interruptible@b-edp1.html
* igt@kms_flip@plain-flip-fb-recreate@a-edp1:
- shard-skl: [FAIL][125] ([i915#2122]) -> [PASS][126]
[125]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl9/igt@kms_flip@plain-flip-fb-recreate@a-edp1.html
[126]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl7/igt@kms_flip@plain-flip-fb-recreate@a-edp1.html
* igt@kms_hdr@bpc-switch-dpms:
- shard-skl: [FAIL][127] ([i915#1188]) -> [PASS][128]
[127]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-skl4/igt@kms_hdr@bpc-switch-dpms.html
[128]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-skl10/igt@kms_hdr@bpc-switch-dpms.html
* igt@kms_hdr@bpc-switch-suspend:
- shard-kbl: [DMESG-WARN][129] ([i915#180]) -> [PASS][130] +4 similar issues
[129]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/shard-kbl1/igt@kms_hdr@bpc-switch-suspend.html
[130]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/shard-kbl6/igt@kms_hdr@bpc-switch-suspend.html
* igt@kms_plane_alpha_blend@pipe-a-coverage-7efc:
- shard-skl: [FAIL][131] ([fdo#108145] / [i915#265]) -> [PASS][132]
[131]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_10796/
== Logs ==
For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_21460/index.html
[-- Attachment #2: Type: text/html, Size: 33751 bytes --]
^ permalink raw reply [flat|nested] 15+ messages in thread