Try to save whatever is on the rings when we encounter an lockup.
Signed-off-by: Christian König deathsimple@vodafone.de --- drivers/gpu/drm/radeon/radeon.h | 4 ++ drivers/gpu/drm/radeon/radeon_device.c | 44 ++++++++++++++++---- drivers/gpu/drm/radeon/radeon_ring.c | 69 ++++++++++++++++++++++++++++++++ 3 files changed, 109 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 9c11be8..1265840 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -770,6 +770,10 @@ int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp); void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring); void radeon_ring_lockup_update(struct radeon_ring *ring); bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring); +unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring, + uint32_t **data); +int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring, + unsigned size, uint32_t *data); int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size, unsigned align, unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg, diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index bbd0971..97696e5 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -996,7 +996,12 @@ int radeon_resume_kms(struct drm_device *dev)
int radeon_gpu_reset(struct radeon_device *rdev) { - int r; + unsigned ring_sizes[RADEON_NUM_RINGS]; + uint32_t *ring_data[RADEON_NUM_RINGS]; + + bool saved = false; + + int i, r; int resched;
down_write(&rdev->exclusive_lock); @@ -1005,20 +1010,43 @@ int radeon_gpu_reset(struct radeon_device *rdev) resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev); radeon_suspend(rdev);
+ for (i = 0; i < RADEON_NUM_RINGS; ++i) { + ring_sizes[i] = radeon_ring_backup(rdev, &rdev->ring[i], + &ring_data[i]); + if (ring_sizes[i]) { + saved = true; + dev_info(rdev->dev, "Saved %d dwords of commands " + "on ring %d.\n", ring_sizes[i], i); + } + } + +retry: r = radeon_asic_reset(rdev); if (!r) { - dev_info(rdev->dev, "GPU reset succeed\n"); + dev_info(rdev->dev, "GPU reset succeed trying to resume\n"); radeon_resume(rdev); + }
- r = radeon_ib_ring_tests(rdev); - if (r) - DRM_ERROR("ib ring test failed (%d).\n", r); + radeon_restore_bios_scratch_regs(rdev); + drm_helper_resume_force_mode(rdev->ddev); + + if (!r) { + for (i = 0; i < RADEON_NUM_RINGS; ++i) { + radeon_ring_restore(rdev, &rdev->ring[i], + ring_sizes[i], ring_data[i]); + }
- radeon_restore_bios_scratch_regs(rdev); - drm_helper_resume_force_mode(rdev->ddev); - ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); + r = radeon_ib_ring_tests(rdev); + if (r) { + dev_err(rdev->dev, "ib ring test failed (%d).\n", r); + if (saved) { + radeon_suspend(rdev); + goto retry; + } + } }
+ ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); if (r) { /* bad news, how to tell it to userspace ? */ dev_info(rdev->dev, "GPU reset failed\n"); diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 994c98c..6ce51d6 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -385,6 +385,75 @@ static unsigned radeon_ring_first_valid_commit(struct radeon_ring *ring) return result; }
+unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring, + uint32_t **data) +{ + unsigned size, ptr, i; + int commit; + + /* just in case lock the ring */ + mutex_lock(&rdev->ring_lock); + *data = NULL; + + if (ring->ring_obj == NULL) { + mutex_unlock(&rdev->ring_lock); + return 0; + } + + /* first of all update the rptr directly from the hw */ + ring->rptr = (RREG32(ring->rptr_reg) & ring->ptr_reg_mask) + >> ring->ptr_reg_shift; + + /* find the first commit not processed so far */ + commit = radeon_ring_first_valid_commit(ring); + if (commit == ring->track_ptr) { + mutex_unlock(&rdev->ring_lock); + return 0; + } + + /* calculate the number of dw on the ring */ + ptr = ring->track_back[commit]; + size = ring->wptr + (ring->ring_size / 4); + size -= ptr; + size &= ring->ptr_mask; + if (size == 0) { + mutex_unlock(&rdev->ring_lock); + return 0; + } + + /* and then save the content of the ring */ + *data = kmalloc(size * 4, GFP_KERNEL); + for (i = 0; i < size; ++i) { + (*data)[i] = ring->ring[ptr++]; + ptr &= ring->ptr_mask; + } + + mutex_unlock(&rdev->ring_lock); + return size; +} + +int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring, + unsigned size, uint32_t *data) +{ + int i, r; + + if (!size || !data) + return 0; + + /* restore the saved ring content */ + r = radeon_ring_lock(rdev, ring, size); + if (r) + return r; + + for (i = 0; i < size; ++i) { + radeon_ring_write(ring, data[i]); + } + + radeon_ring_unlock_commit(rdev, ring); + kfree(data); + return 0; +} + int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size, unsigned align, unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,