[PATCH 54/54] mm-resvlock
Chris Wilson
chris at chris-wilson.co.uk
Wed Jun 17 20:44:20 UTC 2020
---
drivers/gpu/drm/i915/gem/i915_gem_domain.c | 24 +++------
drivers/gpu/drm/i915/gem/i915_gem_object.c | 6 ---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 20 +-------
.../gpu/drm/i915/gem/i915_gem_object_types.h | 1 -
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 49 ++++++++++---------
drivers/gpu/drm/i915/gem/i915_gem_phys.c | 6 +--
drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 15 +++---
drivers/gpu/drm/i915/gem/i915_gem_tiling.c | 2 -
drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 4 +-
.../gpu/drm/i915/gem/selftests/huge_pages.c | 5 +-
.../i915/gem/selftests/i915_gem_coherency.c | 14 ++++--
.../drm/i915/gem/selftests/i915_gem_context.c | 10 +++-
drivers/gpu/drm/i915/gt/intel_renderstate.c | 29 ++++-------
drivers/gpu/drm/i915/gvt/cmd_parser.c | 14 +-----
drivers/gpu/drm/i915/gvt/scheduler.c | 26 +---------
drivers/gpu/drm/i915/gvt/scheduler.h | 2 -
drivers/gpu/drm/i915/i915_gem.c | 16 ++++--
17 files changed, 92 insertions(+), 151 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 7f76fc68f498..9b555e5d4b41 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -572,11 +572,13 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
{
int ret;
+ assert_object_held(obj);
+
*needs_clflush = 0;
if (!i915_gem_object_has_struct_page(obj))
return -ENODEV;
- ret = i915_gem_object_lock_interruptible(obj);
+ ret = __i915_gem_object_get_pages_locked(obj);
if (ret)
return ret;
@@ -584,11 +586,7 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
I915_WAIT_INTERRUPTIBLE,
MAX_SCHEDULE_TIMEOUT);
if (ret)
- goto err_unlock;
-
- ret = i915_gem_object_pin_pages(obj);
- if (ret)
- goto err_unlock;
+ goto err_unpin;
if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ ||
!static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -616,8 +614,6 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
err_unpin:
i915_gem_object_unpin_pages(obj);
-err_unlock:
- i915_gem_object_unlock(obj);
return ret;
}
@@ -626,11 +622,13 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
{
int ret;
+ assert_object_held(obj);
+
*needs_clflush = 0;
if (!i915_gem_object_has_struct_page(obj))
return -ENODEV;
- ret = i915_gem_object_lock_interruptible(obj);
+ ret = __i915_gem_object_get_pages_locked(obj);
if (ret)
return ret;
@@ -639,11 +637,7 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
I915_WAIT_ALL,
MAX_SCHEDULE_TIMEOUT);
if (ret)
- goto err_unlock;
-
- ret = i915_gem_object_pin_pages(obj);
- if (ret)
- goto err_unlock;
+ goto err_unpin;
if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE ||
!static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -680,7 +674,5 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
err_unpin:
i915_gem_object_unpin_pages(obj);
-err_unlock:
- i915_gem_object_unlock(obj);
return ret;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index b6ec5b50d93b..e15a250f84a1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -53,8 +53,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_object_ops *ops,
struct lock_class_key *key)
{
- __mutex_init(&obj->mm.lock, ops->name ?: "obj->mm.lock", key);
-
spin_lock_init(&obj->vma.lock);
INIT_LIST_HEAD(&obj->vma.list);
@@ -72,10 +70,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
obj->mm.madv = I915_MADV_WILLNEED;
INIT_RADIX_TREE(&obj->mm.get_page.radix, GFP_KERNEL | __GFP_NOWARN);
mutex_init(&obj->mm.get_page.lock);
-
- if (IS_ENABLED(CONFIG_LOCKDEP) && i915_gem_object_is_shrinkable(obj))
- i915_gem_shrinker_taints_mutex(to_i915(obj->base.dev),
- &obj->mm.lock);
}
/**
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 7bcd2661de4c..a2def934b33f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -277,28 +277,12 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
-
-enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
- I915_MM_NORMAL = 0,
- /*
- * Only used by struct_mutex, when called "recursively" from
- * direct-reclaim-esque. Safe because there is only every one
- * struct_mutex in the entire system.
- */
- I915_MM_SHRINKER = 1,
- /*
- * Used for obj->mm.lock when allocating pages. Safe because the object
- * isn't yet on any LRU, and therefore the shrinker can't deadlock on
- * it. As soon as the object has pages, obj->mm.lock nests within
- * fs_reclaim.
- */
- I915_MM_GET_PAGES = 1,
-};
+int __i915_gem_object_get_pages_locked(struct drm_i915_gem_object *obj);
static inline int __must_check
i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
{
- might_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
+ might_lock(&obj->base.resv->lock.base);
if (atomic_inc_not_zero(&obj->mm.pages_pin_count))
return 0;
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 b1f82a11aef2..dbb33aac7828 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -186,7 +186,6 @@ struct drm_i915_gem_object {
* Protects the pages and their use. Do not use directly, but
* instead go through the pin/unpin interfaces.
*/
- struct mutex lock;
atomic_t pages_pin_count;
atomic_t shrink_pin;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index af9e48ee4a33..be051239e0ac 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -18,7 +18,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
unsigned long supported = INTEL_INFO(i915)->page_sizes;
int i;
- lockdep_assert_held(&obj->mm.lock);
+ lockdep_assert_held(&obj->base.resv->lock.base);
if (i915_gem_object_is_volatile(obj))
obj->mm.madv = I915_MADV_DONTNEED;
@@ -105,27 +105,34 @@ int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
* either as a result of memory pressure (reaping pages under the shrinker)
* or as the object is itself released.
*/
-int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
+int __i915_gem_object_get_pages_locked(struct drm_i915_gem_object *obj)
{
int err;
- err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
- if (err)
- return err;
-
if (unlikely(!i915_gem_object_has_pages(obj))) {
GEM_BUG_ON(i915_gem_object_has_pinned_pages(obj));
err = ____i915_gem_object_get_pages(obj);
if (err)
- goto unlock;
+ return err;
smp_mb__before_atomic();
}
atomic_inc(&obj->mm.pages_pin_count);
-unlock:
- mutex_unlock(&obj->mm.lock);
+ return 0;
+}
+
+int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
+{
+ int err;
+
+ err = i915_gem_object_lock_interruptible(obj);
+ if (err)
+ return err;
+
+ err = __i915_gem_object_get_pages_locked(obj);
+ i915_gem_object_unlock(obj);
return err;
}
@@ -140,7 +147,7 @@ void i915_gem_object_truncate(struct drm_i915_gem_object *obj)
/* Try to discard unwanted pages */
void i915_gem_object_writeback(struct drm_i915_gem_object *obj)
{
- lockdep_assert_held(&obj->mm.lock);
+ lockdep_assert_held(&obj->base.resv->lock.base);
GEM_BUG_ON(i915_gem_object_has_pages(obj));
if (obj->ops->writeback)
@@ -194,17 +201,15 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
{
struct sg_table *pages;
- int err;
+
+ /* May be called by shrinker from within get_pages() (on another bo) */
+ lockdep_assert_held(&obj->base.resv->lock.base);
if (i915_gem_object_has_pinned_pages(obj))
return -EBUSY;
- /* May be called by shrinker from within get_pages() (on another bo) */
- mutex_lock(&obj->mm.lock);
- if (unlikely(atomic_read(&obj->mm.pages_pin_count))) {
- err = -EBUSY;
- goto unlock;
- }
+ if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
+ return -EBUSY;
i915_gem_object_release_mmap_offset(obj);
@@ -227,11 +232,7 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
if (!IS_ERR(pages))
obj->ops->put_pages(obj, pages);
- err = 0;
-unlock:
- mutex_unlock(&obj->mm.lock);
-
- return err;
+ return 0;
}
static inline pte_t iomap_pte(resource_size_t base,
@@ -325,7 +326,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
if (!i915_gem_object_type_has(obj, flags))
return ERR_PTR(-ENXIO);
- err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
+ err = i915_gem_object_lock_interruptible(obj);
if (err)
return ERR_PTR(err);
@@ -370,7 +371,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
}
out_unlock:
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
return ptr;
err_unpin:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 28147aab47b9..099bcfa8f978 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -165,7 +165,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
if (err)
return err;
- mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
+ i915_gem_object_lock(obj);
if (obj->mm.madv != I915_MADV_WILLNEED) {
err = -EFAULT;
@@ -198,7 +198,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
i915_gem_object_release_memory_region(obj);
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
return 0;
err_xfer:
@@ -209,7 +209,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
}
err_unlock:
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
return err;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 5b65ce738b16..5fe2c1dd82ee 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -45,10 +45,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj,
if (!(shrink & I915_SHRINK_BOUND))
flags = I915_GEM_OBJECT_UNBIND_TEST;
- if (i915_gem_object_unbind(obj, flags) == 0)
- __i915_gem_object_put_pages(obj);
-
- return !i915_gem_object_has_pages(obj);
+ return i915_gem_object_unbind(obj, flags) == 0;
}
static void try_to_writeback(struct drm_i915_gem_object *obj,
@@ -192,14 +189,14 @@ i915_gem_shrink(struct drm_i915_private *i915,
spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
- if (unsafe_drop_pages(obj, shrink)) {
- /* May arrive from get_pages on another bo */
- mutex_lock(&obj->mm.lock);
+ if (unsafe_drop_pages(obj, shrink) &&
+ i915_gem_object_trylock(obj)) {
+ __i915_gem_object_put_pages(obj);
if (!i915_gem_object_has_pages(obj)) {
try_to_writeback(obj, shrink);
count += obj->base.size >> PAGE_SHIFT;
}
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
}
scanned += obj->base.size >> PAGE_SHIFT;
@@ -415,7 +412,7 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
if (!lockdep_is_held_type(&i915->drm.struct_mutex, -1)) {
mutex_acquire(&i915->drm.struct_mutex.dep_map,
- I915_MM_NORMAL, 0, _RET_IP_);
+ 0, 0, _RET_IP_);
unlock = true;
}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 0158e49bf9bb..a5a272c2e43b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -265,7 +265,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
* pages to prevent them being swapped out and causing corruption
* due to the change in swizzling.
*/
- mutex_lock(&obj->mm.lock);
if (i915_gem_object_has_pages(obj) &&
obj->mm.madv == I915_MADV_WILLNEED &&
i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) {
@@ -280,7 +279,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
obj->mm.quirked = true;
}
}
- mutex_unlock(&obj->mm.lock);
spin_lock(&obj->vma.lock);
for_each_ggtt_vma(vma, obj) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 84766414a1f0..e1f1563a98f6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -481,7 +481,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
}
}
- mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
+ i915_gem_object_lock(obj);
if (obj->userptr.work == &work->work) {
struct sg_table *pages = ERR_PTR(ret);
@@ -498,7 +498,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
if (IS_ERR(pages))
__i915_gem_userptr_set_active(obj, false);
}
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
unpin_user_pages(pvec, pinned);
kvfree(pvec);
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 8291ede6902c..5b60e4a79750 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -964,9 +964,10 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
unsigned long n;
int err;
+ i915_gem_object_lock(obj);
err = i915_gem_object_prepare_read(obj, &needs_flush);
if (err)
- return err;
+ goto unlock;
for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
u32 *ptr = kmap_atomic(i915_gem_object_get_page(obj, n));
@@ -986,6 +987,8 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
}
i915_gem_object_finish_access(obj);
+unlock:
+ i915_gem_object_unlock(obj);
return err;
}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 87d7d8aa080f..b8dd6fabe70a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -27,9 +27,10 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
u32 *cpu;
int err;
+ i915_gem_object_lock(ctx->obj);
err = i915_gem_object_prepare_write(ctx->obj, &needs_clflush);
if (err)
- return err;
+ goto unlock;
page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
map = kmap_atomic(page);
@@ -46,7 +47,9 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
kunmap_atomic(map);
i915_gem_object_finish_access(ctx->obj);
- return 0;
+unlock:
+ i915_gem_object_unlock(ctx->obj);
+ return err;
}
static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
@@ -57,9 +60,10 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
u32 *cpu;
int err;
+ i915_gem_object_lock(ctx->obj);
err = i915_gem_object_prepare_read(ctx->obj, &needs_clflush);
if (err)
- return err;
+ goto unlock;
page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
map = kmap_atomic(page);
@@ -73,7 +77,9 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
kunmap_atomic(map);
i915_gem_object_finish_access(ctx->obj);
- return 0;
+unlock:
+ i915_gem_object_unlock(ctx->obj);
+ return err;
}
static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index bb57687aea99..7e373a5b5c3c 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -461,9 +461,10 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
unsigned int n, m, need_flush;
int err;
+ i915_gem_object_lock(obj);
err = i915_gem_object_prepare_write(obj, &need_flush);
if (err)
- return err;
+ goto unlock;
for (n = 0; n < real_page_count(obj); n++) {
u32 *map;
@@ -479,6 +480,8 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
i915_gem_object_finish_access(obj);
obj->read_domains = I915_GEM_DOMAIN_GTT | I915_GEM_DOMAIN_CPU;
obj->write_domain = 0;
+unlock:
+ i915_gem_object_unlock(obj);
return 0;
}
@@ -488,9 +491,10 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj,
unsigned int n, m, needs_flush;
int err;
+ i915_gem_object_lock(obj);
err = i915_gem_object_prepare_read(obj, &needs_flush);
if (err)
- return err;
+ goto unlock;
for (n = 0; n < real_page_count(obj); n++) {
u32 *map;
@@ -527,6 +531,8 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj,
}
i915_gem_object_finish_access(obj);
+unlock:
+ i915_gem_object_unlock(obj);
return err;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index f59e7875cc5e..84d35581d3d9 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -61,7 +61,7 @@ render_state_get_rodata(const struct intel_engine_cs *engine)
#define OUT_BATCH(batch, i, val) \
do { \
if ((i) >= PAGE_SIZE / sizeof(u32)) \
- goto err; \
+ goto out; \
(batch)[(i)++] = (val); \
} while(0)
@@ -70,15 +70,12 @@ static int render_state_setup(struct intel_renderstate *so,
{
const struct intel_renderstate_rodata *rodata = so->rodata;
unsigned int i = 0, reloc_index = 0;
- unsigned int needs_clflush;
+ int ret = -EINVAL;
u32 *d;
- int ret;
- ret = i915_gem_object_prepare_write(so->vma->obj, &needs_clflush);
- if (ret)
- return ret;
-
- d = kmap_atomic(i915_gem_object_get_dirty_page(so->vma->obj, 0));
+ d = i915_gem_object_pin_map(so->vma->obj, i915_coherent_map_type(i915));
+ if (IS_ERR(d))
+ return PTR_ERR(d);
while (i < rodata->batch_items) {
u32 s = rodata->batch[i];
@@ -89,7 +86,7 @@ static int render_state_setup(struct intel_renderstate *so,
if (HAS_64BIT_RELOC(i915)) {
if (i + 1 >= rodata->batch_items ||
rodata->batch[i + 1] != 0)
- goto err;
+ goto out;
d[i++] = s;
s = upper_32_bits(r);
@@ -103,7 +100,7 @@ static int render_state_setup(struct intel_renderstate *so,
if (rodata->reloc[reloc_index] != -1) {
drm_err(&i915->drm, "only %d relocs resolved\n", reloc_index);
- goto err;
+ goto out;
}
so->batch_offset = i915_ggtt_offset(so->vma);
@@ -150,19 +147,11 @@ static int render_state_setup(struct intel_renderstate *so,
*/
so->aux_size = ALIGN(so->aux_size, 8);
- if (needs_clflush)
- drm_clflush_virt_range(d, i * sizeof(u32));
- kunmap_atomic(d);
-
ret = 0;
out:
- i915_gem_object_finish_access(so->vma->obj);
+ __i915_gem_object_flush_map(so->vma->obj, 0, i * sizeof(u32));
+ i915_gem_object_unpin_map(so->vma->obj);
return ret;
-
-err:
- kunmap_atomic(d);
- ret = -EINVAL;
- goto out;
}
#undef OUT_BATCH
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 8b87f130f7f1..f1940939260a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1904,19 +1904,10 @@ static int perform_bb_shadow(struct parser_exec_state *s)
goto err_free_bb;
}
- ret = i915_gem_object_prepare_write(bb->obj, &bb->clflush);
- if (ret)
- goto err_free_obj;
-
bb->va = i915_gem_object_pin_map(bb->obj, I915_MAP_WB);
if (IS_ERR(bb->va)) {
ret = PTR_ERR(bb->va);
- goto err_finish_shmem_access;
- }
-
- if (bb->clflush & CLFLUSH_BEFORE) {
- drm_clflush_virt_range(bb->va, bb->obj->base.size);
- bb->clflush &= ~CLFLUSH_BEFORE;
+ goto err_free_obj;
}
ret = copy_gma_to_hva(s->vgpu, mm,
@@ -1935,7 +1926,6 @@ static int perform_bb_shadow(struct parser_exec_state *s)
INIT_LIST_HEAD(&bb->list);
list_add(&bb->list, &s->workload->shadow_bb);
- bb->accessing = true;
bb->bb_start_cmd_va = s->ip_va;
if ((s->buf_type == BATCH_BUFFER_INSTRUCTION) && (!s->is_ctx_wa))
@@ -1956,8 +1946,6 @@ static int perform_bb_shadow(struct parser_exec_state *s)
return 0;
err_unmap:
i915_gem_object_unpin_map(bb->obj);
-err_finish_shmem_access:
- i915_gem_object_finish_access(bb->obj);
err_free_obj:
i915_gem_object_put(bb->obj);
err_free_bb:
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 8fc2ad4517e9..f1db9f6aad37 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -518,14 +518,7 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
* gma address, and send original bb to hardware
* directly
*/
- if (bb->clflush & CLFLUSH_AFTER) {
- drm_clflush_virt_range(bb->va,
- bb->obj->base.size);
- bb->clflush &= ~CLFLUSH_AFTER;
- }
- i915_gem_object_finish_access(bb->obj);
- bb->accessing = false;
-
+ i915_gem_object_flush_map(bb->obj);
} else {
bb->vma = i915_gem_object_ggtt_pin(bb->obj,
NULL, 0, 0, 0);
@@ -540,25 +533,13 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
bb->bb_start_cmd_va[2] = 0;
/* No one is going to touch shadow bb from now on. */
- if (bb->clflush & CLFLUSH_AFTER) {
- drm_clflush_virt_range(bb->va,
- bb->obj->base.size);
- bb->clflush &= ~CLFLUSH_AFTER;
- }
-
- ret = i915_gem_object_set_to_gtt_domain(bb->obj,
- false);
- if (ret)
- goto err;
+ i915_gem_object_flush_map(bb->obj);
ret = i915_vma_move_to_active(bb->vma,
workload->req,
0);
if (ret)
goto err;
-
- i915_gem_object_finish_access(bb->obj);
- bb->accessing = false;
}
}
return 0;
@@ -630,9 +611,6 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) {
if (bb->obj) {
- if (bb->accessing)
- i915_gem_object_finish_access(bb->obj);
-
if (bb->va && !IS_ERR(bb->va))
i915_gem_object_unpin_map(bb->obj);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 15d317f2a4a4..64e7a0b791c3 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -124,8 +124,6 @@ struct intel_vgpu_shadow_bb {
struct i915_vma *vma;
void *va;
u32 *bb_start_cmd_va;
- unsigned int clflush;
- bool accessing;
unsigned long bb_offset;
bool ppgtt;
};
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e998f25f30a3..0fbe438c4523 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -335,12 +335,16 @@ i915_gem_shmem_pread(struct drm_i915_gem_object *obj,
u64 remain;
int ret;
+ i915_gem_object_lock(obj);
ret = i915_gem_object_prepare_read(obj, &needs_clflush);
- if (ret)
+ if (ret) {
+ i915_gem_object_unlock(obj);
return ret;
+ }
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_finish_access(obj);
+ i915_gem_object_unlock(obj);
if (!fence)
return -ENOMEM;
@@ -734,12 +738,16 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj,
u64 remain;
int ret;
+ i915_gem_object_lock(obj);
ret = i915_gem_object_prepare_write(obj, &needs_clflush);
- if (ret)
+ if (ret) {
+ i915_gem_object_unlock(obj);
return ret;
+ }
fence = i915_gem_object_lock_fence(obj);
i915_gem_object_finish_access(obj);
+ i915_gem_object_unlock(obj);
if (!fence)
return -ENOMEM;
@@ -1063,7 +1071,7 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
if (!obj)
return -ENOENT;
- err = mutex_lock_interruptible(&obj->mm.lock);
+ err = i915_gem_object_lock_interruptible(obj);
if (err)
goto out;
@@ -1109,7 +1117,7 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
i915_gem_object_truncate(obj);
args->retained = obj->mm.madv != __I915_MADV_PURGED;
- mutex_unlock(&obj->mm.lock);
+ i915_gem_object_unlock(obj);
out:
i915_gem_object_put(obj);
--
2.20.1
More information about the Intel-gfx-trybot
mailing list