drm/radeon/kms: fix indirect buffer management V2
There is 3 different distinct states for an indirect buffer (IB) :
1- free with no fence
2- free with a fence
3- non free (fence doesn't matter)
Previous code mixed case 2 & 3 in a single one leading to possible
catastrophique failure. This patch rework the handling and properly
separate each case. So when you get ib we set the ib as non free and
fence status doesn't matter. Fence become active (ie has a meaning
for the ib code) once the ib is scheduled or free. This patch also
get rid of the alloc bitmap as it was overkill, we know go through
IB pool list like in a ring buffer as the oldest IB is the first
one the will be free.
Fix :
https://bugs.freedesktop.org/show_bug.cgi?id=26438
and likely other bugs.
V2 remove the scheduled list, it's useless now, fix free ib scanning
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index af1c3ca..446b765 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -543,9 +543,6 @@
void r600_vb_ib_put(struct radeon_device *rdev)
{
radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence);
- mutex_lock(&rdev->ib_pool.mutex);
- list_add_tail(&rdev->r600_blit.vb_ib->list, &rdev->ib_pool.scheduled_ibs);
- mutex_unlock(&rdev->ib_pool.mutex);
radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f57480b..c0356bb 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -96,6 +96,7 @@
* symbol;
*/
#define RADEON_MAX_USEC_TIMEOUT 100000 /* 100 ms */
+/* RADEON_IB_POOL_SIZE must be a power of 2 */
#define RADEON_IB_POOL_SIZE 16
#define RADEON_DEBUGFS_MAX_NUM_FILES 32
#define RADEONFB_CONN_LIMIT 4
@@ -363,11 +364,12 @@
*/
struct radeon_ib {
struct list_head list;
- unsigned long idx;
+ unsigned idx;
uint64_t gpu_addr;
struct radeon_fence *fence;
- uint32_t *ptr;
+ uint32_t *ptr;
uint32_t length_dw;
+ bool free;
};
/*
@@ -377,10 +379,9 @@
struct radeon_ib_pool {
struct mutex mutex;
struct radeon_bo *robj;
- struct list_head scheduled_ibs;
struct radeon_ib ibs[RADEON_IB_POOL_SIZE];
bool ready;
- DECLARE_BITMAP(alloc_bm, RADEON_IB_POOL_SIZE);
+ unsigned head_id;
};
struct radeon_cp {
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 4d12b2d..694799f 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -41,68 +41,55 @@
{
struct radeon_fence *fence;
struct radeon_ib *nib;
- unsigned long i;
- int r = 0;
+ int r = 0, i, c;
*ib = NULL;
r = radeon_fence_create(rdev, &fence);
if (r) {
- DRM_ERROR("failed to create fence for new IB\n");
+ dev_err(rdev->dev, "failed to create fence for new IB\n");
return r;
}
mutex_lock(&rdev->ib_pool.mutex);
- i = find_first_zero_bit(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
- if (i < RADEON_IB_POOL_SIZE) {
- set_bit(i, rdev->ib_pool.alloc_bm);
- rdev->ib_pool.ibs[i].length_dw = 0;
- *ib = &rdev->ib_pool.ibs[i];
- mutex_unlock(&rdev->ib_pool.mutex);
- goto out;
+ for (i = rdev->ib_pool.head_id, c = 0, nib = NULL; c < RADEON_IB_POOL_SIZE; c++, i++) {
+ i &= (RADEON_IB_POOL_SIZE - 1);
+ if (rdev->ib_pool.ibs[i].free) {
+ nib = &rdev->ib_pool.ibs[i];
+ break;
+ }
}
- if (list_empty(&rdev->ib_pool.scheduled_ibs)) {
- /* we go do nothings here */
+ if (nib == NULL) {
+ /* This should never happen, it means we allocated all
+ * IB and haven't scheduled one yet, return EBUSY to
+ * userspace hoping that on ioctl recall we get better
+ * luck
+ */
+ dev_err(rdev->dev, "no free indirect buffer !\n");
mutex_unlock(&rdev->ib_pool.mutex);
- DRM_ERROR("all IB allocated none scheduled.\n");
- r = -EINVAL;
- goto out;
+ radeon_fence_unref(&fence);
+ return -EBUSY;
}
- /* get the first ib on the scheduled list */
- nib = list_entry(rdev->ib_pool.scheduled_ibs.next,
- struct radeon_ib, list);
- if (nib->fence == NULL) {
- /* we go do nothings here */
+ rdev->ib_pool.head_id = (nib->idx + 1) & (RADEON_IB_POOL_SIZE - 1);
+ nib->free = false;
+ if (nib->fence) {
mutex_unlock(&rdev->ib_pool.mutex);
- DRM_ERROR("IB %lu scheduled without a fence.\n", nib->idx);
- r = -EINVAL;
- goto out;
- }
- mutex_unlock(&rdev->ib_pool.mutex);
-
- r = radeon_fence_wait(nib->fence, false);
- if (r) {
- DRM_ERROR("radeon: IB(%lu:0x%016lX:%u)\n", nib->idx,
- (unsigned long)nib->gpu_addr, nib->length_dw);
- DRM_ERROR("radeon: GPU lockup detected, fail to get a IB\n");
- goto out;
+ r = radeon_fence_wait(nib->fence, false);
+ if (r) {
+ dev_err(rdev->dev, "error waiting fence of IB(%u:0x%016lX:%u)\n",
+ nib->idx, (unsigned long)nib->gpu_addr, nib->length_dw);
+ mutex_lock(&rdev->ib_pool.mutex);
+ nib->free = true;
+ mutex_unlock(&rdev->ib_pool.mutex);
+ radeon_fence_unref(&fence);
+ return r;
+ }
+ mutex_lock(&rdev->ib_pool.mutex);
}
radeon_fence_unref(&nib->fence);
-
+ nib->fence = fence;
nib->length_dw = 0;
-
- /* scheduled list is accessed here */
- mutex_lock(&rdev->ib_pool.mutex);
- list_del(&nib->list);
- INIT_LIST_HEAD(&nib->list);
mutex_unlock(&rdev->ib_pool.mutex);
-
*ib = nib;
-out:
- if (r) {
- radeon_fence_unref(&fence);
- } else {
- (*ib)->fence = fence;
- }
- return r;
+ return 0;
}
void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
@@ -114,18 +101,7 @@
return;
}
mutex_lock(&rdev->ib_pool.mutex);
- if (!list_empty(&tmp->list) && !radeon_fence_signaled(tmp->fence)) {
- /* IB is scheduled & not signaled don't do anythings */
- mutex_unlock(&rdev->ib_pool.mutex);
- return;
- }
- list_del(&tmp->list);
- INIT_LIST_HEAD(&tmp->list);
- if (tmp->fence)
- radeon_fence_unref(&tmp->fence);
-
- tmp->length_dw = 0;
- clear_bit(tmp->idx, rdev->ib_pool.alloc_bm);
+ tmp->free = true;
mutex_unlock(&rdev->ib_pool.mutex);
}
@@ -135,7 +111,7 @@
if (!ib->length_dw || !rdev->cp.ready) {
/* TODO: Nothings in the ib we should report. */
- DRM_ERROR("radeon: couldn't schedule IB(%lu).\n", ib->idx);
+ DRM_ERROR("radeon: couldn't schedule IB(%u).\n", ib->idx);
return -EINVAL;
}
@@ -148,7 +124,8 @@
radeon_ring_ib_execute(rdev, ib);
radeon_fence_emit(rdev, ib->fence);
mutex_lock(&rdev->ib_pool.mutex);
- list_add_tail(&ib->list, &rdev->ib_pool.scheduled_ibs);
+ /* once scheduled IB is considered free and protected by the fence */
+ ib->free = true;
mutex_unlock(&rdev->ib_pool.mutex);
radeon_ring_unlock_commit(rdev);
return 0;
@@ -164,7 +141,6 @@
if (rdev->ib_pool.robj)
return 0;
/* Allocate 1M object buffer */
- INIT_LIST_HEAD(&rdev->ib_pool.scheduled_ibs);
r = radeon_bo_create(rdev, NULL, RADEON_IB_POOL_SIZE*64*1024,
true, RADEON_GEM_DOMAIN_GTT,
&rdev->ib_pool.robj);
@@ -195,9 +171,9 @@
rdev->ib_pool.ibs[i].ptr = ptr + offset;
rdev->ib_pool.ibs[i].idx = i;
rdev->ib_pool.ibs[i].length_dw = 0;
- INIT_LIST_HEAD(&rdev->ib_pool.ibs[i].list);
+ rdev->ib_pool.ibs[i].free = true;
}
- bitmap_zero(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
+ rdev->ib_pool.head_id = 0;
rdev->ib_pool.ready = true;
DRM_INFO("radeon: ib pool ready.\n");
if (radeon_debugfs_ib_init(rdev)) {
@@ -214,7 +190,6 @@
return;
}
mutex_lock(&rdev->ib_pool.mutex);
- bitmap_zero(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
if (rdev->ib_pool.robj) {
r = radeon_bo_reserve(rdev->ib_pool.robj, false);
if (likely(r == 0)) {
@@ -363,7 +338,7 @@
if (ib == NULL) {
return 0;
}
- seq_printf(m, "IB %04lu\n", ib->idx);
+ seq_printf(m, "IB %04u\n", ib->idx);
seq_printf(m, "IB fence %p\n", ib->fence);
seq_printf(m, "IB size %05u dwords\n", ib->length_dw);
for (i = 0; i < ib->length_dw; i++) {