[PATCH 4/6] drm/amdgpu: Wait for all clients importing out dma-bufs.
Andrey Grodzovsky
andrey.grodzovsky at amd.com
Sat May 9 18:51:48 UTC 2020
Also avoid GPU recovery if device is unplagged
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 27 +++++++++++++++++++++++++--
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 +++-
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +++++++++
4 files changed, 38 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 79274d5..f212622 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -992,6 +992,7 @@ struct amdgpu_device {
char serial[16];
wait_queue_head_t user_clients_done;
+ atomic_t exported_dma_bufs_count;
};
static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index ffeb20f..479ff98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -36,6 +36,7 @@
#include "amdgpu_gem.h"
#include "amdgpu_dma_buf.h"
#include <drm/amdgpu_drm.h>
+#include <drm/drm_drv.h>
#include <linux/dma-buf.h>
#include <linux/dma-fence-array.h>
@@ -116,6 +117,7 @@ int amdgpu_gem_prime_mmap(struct drm_gem_object *obj,
return ret;
ret = ttm_bo_mmap(vma->vm_file, vma, &adev->mman.bdev);
+
drm_vma_node_revoke(&obj->vma_node, vma->vm_file->private_data);
return ret;
@@ -179,6 +181,9 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
int r;
+ if (drm_dev_is_unplugged(adev->ddev))
+ return -ENODEV;
+
if (attach->dev->driver == adev->dev->driver)
return 0;
@@ -363,6 +368,19 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
return ret;
}
+
+static void amdgpu_dma_buf_release(struct dma_buf *dma_buf)
+{
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(dma_buf->priv);
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+ drm_gem_dmabuf_release(dma_buf);
+
+ atomic_dec(&adev->exported_dma_bufs_count);
+ wake_up(&adev->user_clients_done);
+
+}
+
const struct dma_buf_ops amdgpu_dmabuf_ops = {
.attach = amdgpu_dma_buf_attach,
.detach = amdgpu_dma_buf_detach,
@@ -370,13 +388,14 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = {
.unpin = amdgpu_dma_buf_unpin,
.map_dma_buf = amdgpu_dma_buf_map,
.unmap_dma_buf = amdgpu_dma_buf_unmap,
- .release = drm_gem_dmabuf_release,
+ .release = amdgpu_dma_buf_release,
.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
.mmap = drm_gem_dmabuf_mmap,
.vmap = drm_gem_dmabuf_vmap,
.vunmap = drm_gem_dmabuf_vunmap,
};
+
/**
* amdgpu_gem_prime_export - &drm_driver.gem_prime_export implementation
* @gobj: GEM BO
@@ -391,6 +410,7 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
int flags)
{
struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct dma_buf *buf;
if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) ||
@@ -398,8 +418,10 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
return ERR_PTR(-EPERM);
buf = drm_gem_prime_export(gobj, flags);
- if (!IS_ERR(buf))
+ if (!IS_ERR(buf)) {
buf->ops = &amdgpu_dmabuf_ops;
+ atomic_inc(&((adev)->exported_dma_bufs_count));
+ }
return buf;
}
@@ -558,5 +580,6 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
get_dma_buf(dma_buf);
obj->import_attach = attach;
+
return obj;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0531727..11410a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1146,7 +1146,9 @@ amdgpu_pci_remove(struct pci_dev *pdev)
drm_dev_unplug(dev);
amdgpu_force_unmap_user_space_mappings(dev);
- wait_event(adev->user_clients_done, (dev->open_count == 0));
+ wait_event(adev->user_clients_done,
+ !atomic_read(&dev->open_count) &&
+ !atomic_read(&adev->exported_dma_bufs_count));
amdgpu_driver_unload_kms(dev);
pci_disable_device(pdev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4720718..20cf36d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -28,6 +28,9 @@
#include "amdgpu.h"
#include "amdgpu_trace.h"
+#include <drm/drm_drv.h>
+
+
static void amdgpu_job_timedout(struct drm_sched_job *s_job)
{
struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
@@ -37,6 +40,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
memset(&ti, 0, sizeof(struct amdgpu_task_info));
+
+ if (drm_dev_is_unplugged(adev->ddev)) {
+ DRM_WARN("amdgpu_job_timedout - device is unplugged, skiping!");
+ return;
+ }
+
if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
DRM_ERROR("ring %s timeout, but soft recovered\n",
s_job->sched->name);
--
2.7.4
More information about the amd-gfx
mailing list