summaryrefslogtreecommitdiffstats
path: root/drivers/dma-buf
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-02-01 17:48:47 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-02-01 17:48:47 -0800
commit4bf772b14675411a69b3c807f73006de0fe4b649 (patch)
treeb841e3ba0e3429695589cb0ab73871fa12f42c38 /drivers/dma-buf
parent3879ae653a3e98380fe2daf653338830b7ca0097 (diff)
parent24b8ef699e8221d2b7f813adaab13eec053e1507 (diff)
downloadlinux-4bf772b14675411a69b3c807f73006de0fe4b649.tar.gz
linux-4bf772b14675411a69b3c807f73006de0fe4b649.tar.bz2
linux-4bf772b14675411a69b3c807f73006de0fe4b649.zip
Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie: "This seems to have been a comparatively quieter merge window, I assume due to holidays etc. The "biggest" change is AMD header cleanups, which merge/remove a bunch of them. The AMD gpu scheduler is now being made generic with the etnaviv driver wanting to reuse the code, hopefully other drivers can go in the same direction. Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff elsewhere. Core: - Add .last_close and .output_poll_changed helpers to reduce driver footprints - Fix plane clipping - Improved debug printing support - Add panel orientation property - Update edid derived properties at edid setting - Reduction in fbdev driver footprint - Move amdgpu scheduler into core for other drivers to use. i915: - Selftest and IGT improvements - Fast boot prep work on IPS, pipe config - HW workarounds for Cannonlake, Geminilake - Cannonlake clock and HDMI2.0 fixes - GPU cache invalidation and context switch improvements - Display planes cleanup - New PMU interface for perf queries - New firmware support for KBL/SKL - Geminilake HW workaround for perforamce - Coffeelake stolen memory improvements - GPU reset robustness work - Cannonlake horizontal plane flipping - GVT work amdgpu/radeon: - RV and Vega header file cleanups (lots of lines gone!) - TTM operation context support - 48-bit GPUVM support for Vega/RV - ECC support for Vega - Resizeable BAR support - Multi-display sync support - Enable swapout for reserved BOs during allocation - S3 fixes on Raven - GPU reset cleanup and fixes - 2+1 level GPU page table amdkfd: - GFX7/8 SDMA user queues support - Hardware scheduling for multiple processes - dGPU prep work rcar: - Added R8A7743/5 support - System suspend/resume support sun4i: - Multi-plane support for YUV formats - A83T and LVDS support msm: - Devfreq support for GPU tegra: - Prep work for adding Tegra186 support - Tegra186 HDMI support - HDMI2.0 and zpos support by using generic helpers tilcdc: - Misc fixes omapdrm: - Support memory bandwidth limits - DSI command mode panel cleanups - DMM error handling exynos: - drop the old IPP subdriver. etnaviv: - Occlusion query fixes - Job handling fixes - Prep work for hooking in gpu scheduler armada: - Move closer to atomic modesetting - Allow disabling primary plane if overlay is full screen imx: - Format modifier support - Add tile prefetch to PRE - Runtime PM support for PRG ast: - fix LUT loading" * tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits) drm/ast: Load lut in crtc_commit drm: Check for lessee in DROP_MASTER ioctl drm: fix gpu scheduler link order drm/amd/display: Demote error print to debug print when ATOM impl missing dma-buf: fix reservation_object_wait_timeout_rcu once more v2 drm/amdgpu: Avoid leaking PM domain on driver unbind (v2) drm/amd/amdgpu: Add Polaris version check drm/amdgpu: Reenable manual GPU reset from sysfs drm/amdgpu: disable MMHUB power gating on raven drm/ttm: Don't unreserve swapped BOs that were previously reserved drm/ttm: Don't add swapped BOs to swap-LRU list drm/amdgpu: only check for ECC on Vega10 drm/amd/powerplay: Fix smu_table_entry.handle type drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig drm/radeon: fill in rb backend map on evergreen/ni. drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2) drm/ttm: only free pages rather than update global memory count together drm/amdgpu: fix CPU based VM updates drm/amdgpu: fix typo in amdgpu_vce_validate_bo ...
Diffstat (limited to 'drivers/dma-buf')
-rw-r--r--drivers/dma-buf/dma-buf.c9
-rw-r--r--drivers/dma-buf/dma-fence-array.c14
-rw-r--r--drivers/dma-buf/reservation.c66
3 files changed, 58 insertions, 31 deletions
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 12b62d0aac27..539450713838 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -351,13 +351,13 @@ static inline int is_dma_buf_file(struct file *file)
*
* 2. Userspace passes this file-descriptors to all drivers it wants this buffer
* to share with: First the filedescriptor is converted to a &dma_buf using
- * dma_buf_get(). The the buffer is attached to the device using
+ * dma_buf_get(). Then the buffer is attached to the device using
* dma_buf_attach().
*
* Up to this stage the exporter is still free to migrate or reallocate the
* backing storage.
*
- * 3. Once the buffer is attached to all devices userspace can inniate DMA
+ * 3. Once the buffer is attached to all devices userspace can initiate DMA
* access to the shared buffer. In the kernel this is done by calling
* dma_buf_map_attachment() and dma_buf_unmap_attachment().
*
@@ -617,7 +617,7 @@ EXPORT_SYMBOL_GPL(dma_buf_detach);
* Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
* on error. May return -EINTR if it is interrupted by a signal.
*
- * A mapping must be unmapped again using dma_buf_map_attachment(). Note that
+ * A mapping must be unmapped by using dma_buf_unmap_attachment(). Note that
* the underlying backing storage is pinned for as long as a mapping exists,
* therefore users/importers should not hold onto a mapping for undue amounts of
* time.
@@ -1179,8 +1179,7 @@ static int dma_buf_init_debugfs(void)
static void dma_buf_uninit_debugfs(void)
{
- if (dma_buf_debugfs_dir)
- debugfs_remove_recursive(dma_buf_debugfs_dir);
+ debugfs_remove_recursive(dma_buf_debugfs_dir);
}
#else
static inline int dma_buf_init_debugfs(void)
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index 0350829ba62e..dd1edfb27b61 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -31,6 +31,14 @@ static const char *dma_fence_array_get_timeline_name(struct dma_fence *fence)
return "unbound";
}
+static void irq_dma_fence_array_work(struct irq_work *wrk)
+{
+ struct dma_fence_array *array = container_of(wrk, typeof(*array), work);
+
+ dma_fence_signal(&array->base);
+ dma_fence_put(&array->base);
+}
+
static void dma_fence_array_cb_func(struct dma_fence *f,
struct dma_fence_cb *cb)
{
@@ -39,8 +47,9 @@ static void dma_fence_array_cb_func(struct dma_fence *f,
struct dma_fence_array *array = array_cb->array;
if (atomic_dec_and_test(&array->num_pending))
- dma_fence_signal(&array->base);
- dma_fence_put(&array->base);
+ irq_work_queue(&array->work);
+ else
+ dma_fence_put(&array->base);
}
static bool dma_fence_array_enable_signaling(struct dma_fence *fence)
@@ -136,6 +145,7 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
spin_lock_init(&array->lock);
dma_fence_init(&array->base, &dma_fence_array_ops, &array->lock,
context, seqno);
+ init_irq_work(&array->work, irq_dma_fence_array_work);
array->num_fences = num_fences;
atomic_set(&array->num_pending, signal_on_any ? 1 : num_fences);
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index b44d9d7db347..04ebe2204c12 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -104,7 +104,8 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
struct reservation_object_list *fobj,
struct dma_fence *fence)
{
- u32 i;
+ struct dma_fence *signaled = NULL;
+ u32 i, signaled_idx;
dma_fence_get(fence);
@@ -126,17 +127,28 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
dma_fence_put(old_fence);
return;
}
+
+ if (!signaled && dma_fence_is_signaled(old_fence)) {
+ signaled = old_fence;
+ signaled_idx = i;
+ }
}
/*
* memory barrier is added by write_seqcount_begin,
* fobj->shared_count is protected by this lock too
*/
- RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
- fobj->shared_count++;
+ if (signaled) {
+ RCU_INIT_POINTER(fobj->shared[signaled_idx], fence);
+ } else {
+ RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
+ fobj->shared_count++;
+ }
write_seqcount_end(&obj->seq);
preempt_enable();
+
+ dma_fence_put(signaled);
}
static void
@@ -145,8 +157,7 @@ reservation_object_add_shared_replace(struct reservation_object *obj,
struct reservation_object_list *fobj,
struct dma_fence *fence)
{
- unsigned i;
- struct dma_fence *old_fence = NULL;
+ unsigned i, j, k;
dma_fence_get(fence);
@@ -162,24 +173,21 @@ reservation_object_add_shared_replace(struct reservation_object *obj,
* references from the old struct are carried over to
* the new.
*/
- fobj->shared_count = old->shared_count;
-
- for (i = 0; i < old->shared_count; ++i) {
+ for (i = 0, j = 0, k = fobj->shared_max; i < old->shared_count; ++i) {
struct dma_fence *check;
check = rcu_dereference_protected(old->shared[i],
reservation_object_held(obj));
- if (!old_fence && check->context == fence->context) {
- old_fence = check;
- RCU_INIT_POINTER(fobj->shared[i], fence);
- } else
- RCU_INIT_POINTER(fobj->shared[i], check);
- }
- if (!old_fence) {
- RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
- fobj->shared_count++;
+ if (check->context == fence->context ||
+ dma_fence_is_signaled(check))
+ RCU_INIT_POINTER(fobj->shared[--k], check);
+ else
+ RCU_INIT_POINTER(fobj->shared[j++], check);
}
+ fobj->shared_count = j;
+ RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
+ fobj->shared_count++;
done:
preempt_disable();
@@ -192,10 +200,18 @@ done:
write_seqcount_end(&obj->seq);
preempt_enable();
- if (old)
- kfree_rcu(old, rcu);
+ if (!old)
+ return;
- dma_fence_put(old_fence);
+ /* Drop the references to the signaled fences */
+ for (i = k; i < fobj->shared_max; ++i) {
+ struct dma_fence *f;
+
+ f = rcu_dereference_protected(fobj->shared[i],
+ reservation_object_held(obj));
+ dma_fence_put(f);
+ }
+ kfree_rcu(old, rcu);
}
/**
@@ -318,7 +334,7 @@ retry:
continue;
}
- dst_list->shared[dst_list->shared_count++] = fence;
+ rcu_assign_pointer(dst_list->shared[dst_list->shared_count++], fence);
}
} else {
dst_list = NULL;
@@ -455,13 +471,15 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj,
unsigned long timeout)
{
struct dma_fence *fence;
- unsigned seq, shared_count, i = 0;
+ unsigned seq, shared_count;
long ret = timeout ? timeout : 1;
+ int i;
retry:
shared_count = 0;
seq = read_seqcount_begin(&obj->seq);
rcu_read_lock();
+ i = -1;
fence = rcu_dereference(obj->fence_excl);
if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
@@ -477,14 +495,14 @@ retry:
fence = NULL;
}
- if (!fence && wait_all) {
+ if (wait_all) {
struct reservation_object_list *fobj =
rcu_dereference(obj->fence);
if (fobj)
shared_count = fobj->shared_count;
- for (i = 0; i < shared_count; ++i) {
+ for (i = 0; !fence && i < shared_count; ++i) {
struct dma_fence *lfence = rcu_dereference(fobj->shared[i]);
if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,