Hi everyone,
hopefully the last iteration of those patches.
For now I've addressed the issue of unmapping imported BOs from the amdgpu page tables immediately by locking the page tables in place.
For HMM handling we are getting the ability to invalidate BOs without locking the VM anyway, so this last TODO will probably go away rather soon.
Place comment, Christian.
On the exporter side we add optional explicit pinning callbacks. Which are called when the importer doesn't implement dynamic handling, move notification or need the DMA-buf locked in place for its use case.
On the importer side we add an optional move_notify callback. This callback is used by the exporter to inform the importers that their mappings should be destroyed as soon as possible.
This allows the exporter to provide the mappings without the need to pin the backing store.
v2: don't try to invalidate mappings when the callback is NULL, lock the reservation obj while using the attachments, add helper to set the callback v3: move flag for invalidation support into the DMA-buf, use new attach_info structure to set the callback v4: use importer_priv field instead of mangling exporter priv. v5: drop invalidation_supported flag v6: squash together with pin/unpin changes v7: pin/unpin takes an attachment now v8: nuke dma_buf_attachment_(map|unmap)_locked, everything is now handled backward compatible v9: always cache when export/importer don't agree on dynamic handling v10: minimal style cleanup v11: drop automatically re-entry avoidance v12: rename callback to move_notify v13: add might_lock in appropriate places v14: rebase on separated locking change
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 106 ++++++++++++++++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 6 +- include/linux/dma-buf.h | 78 ++++++++++++-- 3 files changed, 170 insertions(+), 20 deletions(-)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d377b4ca66bf..ce293cee76ed 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -529,6 +529,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) exp_info->ops->dynamic_mapping)) return ERR_PTR(-EINVAL);
+ if (WARN_ON(!exp_info->ops->dynamic_mapping && + (exp_info->ops->pin || exp_info->ops->unpin))) + return ERR_PTR(-EINVAL); + if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT);
@@ -653,7 +657,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put); * calls attach() of dma_buf_ops to allow device-specific attach functionality * @dmabuf: [in] buffer to attach device to. * @dev: [in] device to be attached. - * @dynamic_mapping: [in] calling convention for map/unmap + * @importer_ops [in] importer operations for the attachment + * @importer_priv [in] importer private pointer for the attachment * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). @@ -669,7 +674,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put); */ struct dma_buf_attachment * dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, - bool dynamic_mapping) + const struct dma_buf_attach_ops *importer_ops, + void *importer_priv) { struct dma_buf_attachment *attach; int ret; @@ -683,7 +689,8 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
attach->dev = dev; attach->dmabuf = dmabuf; - attach->dynamic_mapping = dynamic_mapping; + attach->importer_ops = importer_ops; + attach->importer_priv = importer_priv;
if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, attach); @@ -702,15 +709,19 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, dma_buf_is_dynamic(dmabuf)) { struct sg_table *sgt;
- if (dma_buf_is_dynamic(attach->dmabuf)) + if (dma_buf_is_dynamic(attach->dmabuf)) { dma_resv_lock(attach->dmabuf->resv, NULL); + ret = dma_buf_pin(attach); + if (ret) + goto err_unlock; + }
sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); if (!sgt) sgt = ERR_PTR(-ENOMEM); if (IS_ERR(sgt)) { ret = PTR_ERR(sgt); - goto err_unlock; + goto err_unpin; } if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_unlock(attach->dmabuf->resv); @@ -724,6 +735,10 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, kfree(attach); return ERR_PTR(ret);
+err_unpin: + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_buf_unpin(attach); + err_unlock: if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_unlock(attach->dmabuf->resv); @@ -744,7 +759,7 @@ EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach); struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev) { - return dma_buf_dynamic_attach(dmabuf, dev, false); + return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL); } EXPORT_SYMBOL_GPL(dma_buf_attach);
@@ -767,8 +782,10 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir);
- if (dma_buf_is_dynamic(attach->dmabuf)) + if (dma_buf_is_dynamic(attach->dmabuf)) { + dma_buf_unpin(attach); dma_resv_unlock(attach->dmabuf->resv); + } }
dma_resv_lock(dmabuf->resv, NULL); @@ -781,6 +798,44 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) } EXPORT_SYMBOL_GPL(dma_buf_detach);
+/** + * dma_buf_pin - Lock down the DMA-buf + * + * @attach: [in] attachment which should be pinned + * + * Returns: + * 0 on success, negative error code on failure. + */ +int dma_buf_pin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + int ret = 0; + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->pin) + ret = dmabuf->ops->pin(attach); + + return ret; +} +EXPORT_SYMBOL_GPL(dma_buf_pin); + +/** + * dma_buf_unpin - Remove lock from DMA-buf + * + * @attach: [in] attachment which should be unpinned + */ +void dma_buf_unpin(struct dma_buf_attachment *attach) +{ + struct dma_buf *dmabuf = attach->dmabuf; + + dma_resv_assert_held(dmabuf->resv); + + if (dmabuf->ops->unpin) + dmabuf->ops->unpin(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_unpin); + /** * dma_buf_map_attachment - Returns the scatterlist table of the attachment; * mapped into _device_ address space. Is a wrapper for map_dma_buf() of the @@ -800,6 +855,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; + int r;
might_sleep();
@@ -821,13 +877,23 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, return attach->sgt; }
- if (dma_buf_is_dynamic(attach->dmabuf)) + if (dma_buf_is_dynamic(attach->dmabuf)) { dma_resv_assert_held(attach->dmabuf->resv); + if (!attach->importer_ops->move_notify) { + r = dma_buf_pin(attach); + if (r) + return ERR_PTR(r); + } + }
sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM);
+ if (IS_ERR(sg_table) && dma_buf_is_dynamic(attach->dmabuf) && + !attach->importer_ops->move_notify) + dma_buf_unpin(attach); + if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) { attach->sgt = sg_table; attach->dir = direction; @@ -866,9 +932,33 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, dma_resv_assert_held(attach->dmabuf->resv);
attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); + + if (dma_buf_is_dynamic(attach->dmabuf) && + !attach->importer_ops->move_notify) + dma_buf_unpin(attach); } EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
+/** + * dma_buf_move_notify - notify attachments that DMA-buf is moving + * + * @dmabuf: [in] buffer which is moving + * + * Informs all attachmenst that they need to destroy and recreated all their + * mappings. + */ +void dma_buf_move_notify(struct dma_buf *dmabuf) +{ + struct dma_buf_attachment *attach; + + dma_resv_assert_held(dmabuf->resv); + + list_for_each_entry(attach, &dmabuf->attachments, node) + if (attach->importer_ops && attach->importer_ops->move_notify) + attach->importer_ops->move_notify(attach); +} +EXPORT_SYMBOL_GPL(dma_buf_move_notify); + /** * DOC: cpu access * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e2eec7b66334..b2ca78b6abce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -414,6 +414,9 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); }
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { +}; + /** * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation * @dev: DRM device @@ -446,7 +449,8 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, if (IS_ERR(obj)) return obj;
- attach = dma_buf_dynamic_attach(dma_buf, dev->dev, true); + attach = dma_buf_dynamic_attach(dma_buf, dev->dev, + &amdgpu_dma_buf_attach_ops, NULL); if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index af73f835c51c..7456bb937635 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -93,14 +93,40 @@ struct dma_buf_ops { */ void (*detach)(struct dma_buf *, struct dma_buf_attachment *);
+ /** + * @pin: + * + * This is called by dma_buf_pin and lets the exporter know that the + * DMA-buf can't be moved any more. + * + * This is called with the dmabuf->resv object locked. + * + * This callback is optional. + * + * Returns: + * + * 0 on success, negative error code on failure. + */ + int (*pin)(struct dma_buf_attachment *attach); + + /** + * @unpin: + * + * This is called by dma_buf_unpin and lets the exporter know that the + * DMA-buf can be moved again. + * + * This is called with the dmabuf->resv object locked. + * + * This callback is optional. + */ + void (*unpin)(struct dma_buf_attachment *attach); + /** * @map_dma_buf: * * This is called by dma_buf_map_attachment() and is used to map a * shared &dma_buf into device address space, and it is mandatory. It - * can only be called if @attach has been called successfully. This - * essentially pins the DMA buffer into place, and it cannot be moved - * any more + * can only be called if @attach has been called successfully. * * This call may sleep, e.g. when the backing storage first needs to be * allocated, or moved to a location suitable for all currently attached @@ -141,9 +167,6 @@ struct dma_buf_ops { * * This is called by dma_buf_unmap_attachment() and should unmap and * release the &sg_table allocated in @map_dma_buf, and it is mandatory. - * It should also unpin the backing storage if this is the last mapping - * of the DMA buffer, it the exporter supports backing storage - * migration. */ void (*unmap_dma_buf)(struct dma_buf_attachment *, struct sg_table *, @@ -336,6 +359,34 @@ struct dma_buf { } cb_excl, cb_shared; };
+/** + * struct dma_buf_attach_ops - importer operations for an attachment + * @move_notify: [optional] notification that the DMA-buf is moving + * + * Attachment operations implemented by the importer. + */ +struct dma_buf_attach_ops { + /** + * @move_notify + * + * If this callback is provided the framework can avoid pinning the + * backing store while mappings exists. + * + * This callback is called with the lock of the reservation object + * associated with the dma_buf held and the mapping function must be + * called with this lock held as well. This makes sure that no mapping + * is created concurrently with an ongoing move operation. + * + * Mappings stay valid and are not directly affected by this callback. + * But the DMA-buf can now be in a different physical location, so all + * mappings should be destroyed and re-created as soon as possible. + * + * New mappings can be created after this callback returns, and will + * point to the new location of the DMA-buf. + */ + void (*move_notify)(struct dma_buf_attachment *attach); +}; + /** * struct dma_buf_attachment - holds device-buffer attachment data * @dmabuf: buffer for this attachment. @@ -344,8 +395,9 @@ struct dma_buf { * @sgt: cached mapping. * @dir: direction of cached mapping. * @priv: exporter specific attachment data. - * @dynamic_mapping: true if dma_buf_map/unmap_attachment() is called with the - * dma_resv lock held. + * @importer_ops: importer operations for this attachment, if provided + * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. + * @importer_priv: importer specific attachment data. * * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device @@ -362,7 +414,8 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir; - bool dynamic_mapping; + const struct dma_buf_attach_ops *importer_ops; + void *importer_priv; void *priv; };
@@ -438,16 +491,19 @@ static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf) static inline bool dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) { - return attach->dynamic_mapping; + return !!attach->importer_ops; }
struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); struct dma_buf_attachment * dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, - bool dynamic_mapping); + const struct dma_buf_attach_ops *importer_ops, + void *importer_priv); void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach); +int dma_buf_pin(struct dma_buf_attachment *attach); +void dma_buf_unpin(struct dma_buf_attachment *attach);
struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info);
Please ignore this one, I've send out the wrong version without Daniels latest comment nit picks fixed.
The interesting one in this series is the last patch.
Regards, Christian.
Am 17.02.20 um 16:45 schrieb Christian König:
On the exporter side we add optional explicit pinning callbacks. Which are called when the importer doesn't implement dynamic handling, move notification or need the DMA-buf locked in place for its use case.
On the importer side we add an optional move_notify callback. This callback is used by the exporter to inform the importers that their mappings should be destroyed as soon as possible.
This allows the exporter to provide the mappings without the need to pin the backing store.
v2: don't try to invalidate mappings when the callback is NULL, lock the reservation obj while using the attachments, add helper to set the callback v3: move flag for invalidation support into the DMA-buf, use new attach_info structure to set the callback v4: use importer_priv field instead of mangling exporter priv. v5: drop invalidation_supported flag v6: squash together with pin/unpin changes v7: pin/unpin takes an attachment now v8: nuke dma_buf_attachment_(map|unmap)_locked, everything is now handled backward compatible v9: always cache when export/importer don't agree on dynamic handling v10: minimal style cleanup v11: drop automatically re-entry avoidance v12: rename callback to move_notify v13: add might_lock in appropriate places v14: rebase on separated locking change
Signed-off-by: Christian König christian.koenig@amd.com
drivers/dma-buf/dma-buf.c | 106 ++++++++++++++++++-- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 6 +- include/linux/dma-buf.h | 78 ++++++++++++-- 3 files changed, 170 insertions(+), 20 deletions(-)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index d377b4ca66bf..ce293cee76ed 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -529,6 +529,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) exp_info->ops->dynamic_mapping)) return ERR_PTR(-EINVAL);
- if (WARN_ON(!exp_info->ops->dynamic_mapping &&
(exp_info->ops->pin || exp_info->ops->unpin)))
return ERR_PTR(-EINVAL);
- if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT);
@@ -653,7 +657,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
- calls attach() of dma_buf_ops to allow device-specific attach functionality
- @dmabuf: [in] buffer to attach device to.
- @dev: [in] device to be attached.
- @dynamic_mapping: [in] calling convention for map/unmap
- @importer_ops [in] importer operations for the attachment
- @importer_priv [in] importer private pointer for the attachment
- Returns struct dma_buf_attachment pointer for this attachment. Attachments
- must be cleaned up by calling dma_buf_detach().
@@ -669,7 +674,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put); */ struct dma_buf_attachment * dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
bool dynamic_mapping)
const struct dma_buf_attach_ops *importer_ops,
{ struct dma_buf_attachment *attach; int ret;void *importer_priv)
@@ -683,7 +689,8 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, attach->dev = dev; attach->dmabuf = dmabuf;
- attach->dynamic_mapping = dynamic_mapping;
- attach->importer_ops = importer_ops;
- attach->importer_priv = importer_priv;
if (dmabuf->ops->attach) { ret = dmabuf->ops->attach(dmabuf, attach); @@ -702,15 +709,19 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, dma_buf_is_dynamic(dmabuf)) { struct sg_table *sgt;
if (dma_buf_is_dynamic(attach->dmabuf))
if (dma_buf_is_dynamic(attach->dmabuf)) { dma_resv_lock(attach->dmabuf->resv, NULL);
ret = dma_buf_pin(attach);
if (ret)
goto err_unlock;
}
sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); if (!sgt) sgt = ERR_PTR(-ENOMEM); if (IS_ERR(sgt)) { ret = PTR_ERR(sgt);
goto err_unlock;
} if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_unlock(attach->dmabuf->resv);goto err_unpin;
@@ -724,6 +735,10 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, kfree(attach); return ERR_PTR(ret); +err_unpin:
- if (dma_buf_is_dynamic(attach->dmabuf))
dma_buf_unpin(attach);
- err_unlock: if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_unlock(attach->dmabuf->resv);
@@ -744,7 +759,7 @@ EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach); struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev) {
- return dma_buf_dynamic_attach(dmabuf, dev, false);
- return dma_buf_dynamic_attach(dmabuf, dev, NULL, NULL); } EXPORT_SYMBOL_GPL(dma_buf_attach);
@@ -767,8 +782,10 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir);
if (dma_buf_is_dynamic(attach->dmabuf))
if (dma_buf_is_dynamic(attach->dmabuf)) {
dma_buf_unpin(attach); dma_resv_unlock(attach->dmabuf->resv);
}}
dma_resv_lock(dmabuf->resv, NULL); @@ -781,6 +798,44 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) } EXPORT_SYMBOL_GPL(dma_buf_detach); +/**
- dma_buf_pin - Lock down the DMA-buf
- @attach: [in] attachment which should be pinned
- Returns:
- 0 on success, negative error code on failure.
- */
+int dma_buf_pin(struct dma_buf_attachment *attach) +{
- struct dma_buf *dmabuf = attach->dmabuf;
- int ret = 0;
- dma_resv_assert_held(dmabuf->resv);
- if (dmabuf->ops->pin)
ret = dmabuf->ops->pin(attach);
- return ret;
+} +EXPORT_SYMBOL_GPL(dma_buf_pin);
+/**
- dma_buf_unpin - Remove lock from DMA-buf
- @attach: [in] attachment which should be unpinned
- */
+void dma_buf_unpin(struct dma_buf_attachment *attach) +{
- struct dma_buf *dmabuf = attach->dmabuf;
- dma_resv_assert_held(dmabuf->resv);
- if (dmabuf->ops->unpin)
dmabuf->ops->unpin(attach);
+} +EXPORT_SYMBOL_GPL(dma_buf_unpin);
- /**
- dma_buf_map_attachment - Returns the scatterlist table of the attachment;
- mapped into _device_ address space. Is a wrapper for map_dma_buf() of the
@@ -800,6 +855,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table;
- int r;
might_sleep(); @@ -821,13 +877,23 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, return attach->sgt; }
- if (dma_buf_is_dynamic(attach->dmabuf))
- if (dma_buf_is_dynamic(attach->dmabuf)) { dma_resv_assert_held(attach->dmabuf->resv);
if (!attach->importer_ops->move_notify) {
r = dma_buf_pin(attach);
if (r)
return ERR_PTR(r);
}
- }
sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM);
- if (IS_ERR(sg_table) && dma_buf_is_dynamic(attach->dmabuf) &&
!attach->importer_ops->move_notify)
dma_buf_unpin(attach);
- if (!IS_ERR(sg_table) && attach->dmabuf->ops->cache_sgt_mapping) { attach->sgt = sg_table; attach->dir = direction;
@@ -866,9 +932,33 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, dma_resv_assert_held(attach->dmabuf->resv); attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
- if (dma_buf_is_dynamic(attach->dmabuf) &&
!attach->importer_ops->move_notify)
} EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);dma_buf_unpin(attach);
+/**
- dma_buf_move_notify - notify attachments that DMA-buf is moving
- @dmabuf: [in] buffer which is moving
- Informs all attachmenst that they need to destroy and recreated all their
- mappings.
- */
+void dma_buf_move_notify(struct dma_buf *dmabuf) +{
- struct dma_buf_attachment *attach;
- dma_resv_assert_held(dmabuf->resv);
- list_for_each_entry(attach, &dmabuf->attachments, node)
if (attach->importer_ops && attach->importer_ops->move_notify)
attach->importer_ops->move_notify(attach);
+} +EXPORT_SYMBOL_GPL(dma_buf_move_notify);
- /**
- DOC: cpu access
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index e2eec7b66334..b2ca78b6abce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -414,6 +414,9 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); } +static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { +};
- /**
- amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
- @dev: DRM device
@@ -446,7 +449,8 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, if (IS_ERR(obj)) return obj;
- attach = dma_buf_dynamic_attach(dma_buf, dev->dev, true);
- attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach);&amdgpu_dma_buf_attach_ops, NULL);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index af73f835c51c..7456bb937635 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -93,14 +93,40 @@ struct dma_buf_ops { */ void (*detach)(struct dma_buf *, struct dma_buf_attachment *);
- /**
* @pin:
*
* This is called by dma_buf_pin and lets the exporter know that the
* DMA-buf can't be moved any more.
*
* This is called with the dmabuf->resv object locked.
*
* This callback is optional.
*
* Returns:
*
* 0 on success, negative error code on failure.
*/
- int (*pin)(struct dma_buf_attachment *attach);
- /**
* @unpin:
*
* This is called by dma_buf_unpin and lets the exporter know that the
* DMA-buf can be moved again.
*
* This is called with the dmabuf->resv object locked.
*
* This callback is optional.
*/
- void (*unpin)(struct dma_buf_attachment *attach);
- /**
- @map_dma_buf:
- This is called by dma_buf_map_attachment() and is used to map a
- shared &dma_buf into device address space, and it is mandatory. It
* can only be called if @attach has been called successfully. This
* essentially pins the DMA buffer into place, and it cannot be moved
* any more
* can only be called if @attach has been called successfully.
- This call may sleep, e.g. when the backing storage first needs to be
- allocated, or moved to a location suitable for all currently attached
@@ -141,9 +167,6 @@ struct dma_buf_ops { * * This is called by dma_buf_unmap_attachment() and should unmap and * release the &sg_table allocated in @map_dma_buf, and it is mandatory.
* It should also unpin the backing storage if this is the last mapping
* of the DMA buffer, it the exporter supports backing storage
*/ void (*unmap_dma_buf)(struct dma_buf_attachment *, struct sg_table *,* migration.
@@ -336,6 +359,34 @@ struct dma_buf { } cb_excl, cb_shared; }; +/**
- struct dma_buf_attach_ops - importer operations for an attachment
- @move_notify: [optional] notification that the DMA-buf is moving
- Attachment operations implemented by the importer.
- */
+struct dma_buf_attach_ops {
- /**
* @move_notify
*
* If this callback is provided the framework can avoid pinning the
* backing store while mappings exists.
*
* This callback is called with the lock of the reservation object
* associated with the dma_buf held and the mapping function must be
* called with this lock held as well. This makes sure that no mapping
* is created concurrently with an ongoing move operation.
*
* Mappings stay valid and are not directly affected by this callback.
* But the DMA-buf can now be in a different physical location, so all
* mappings should be destroyed and re-created as soon as possible.
*
* New mappings can be created after this callback returns, and will
* point to the new location of the DMA-buf.
*/
- void (*move_notify)(struct dma_buf_attachment *attach);
+};
- /**
- struct dma_buf_attachment - holds device-buffer attachment data
- @dmabuf: buffer for this attachment.
@@ -344,8 +395,9 @@ struct dma_buf {
- @sgt: cached mapping.
- @dir: direction of cached mapping.
- @priv: exporter specific attachment data.
- @dynamic_mapping: true if dma_buf_map/unmap_attachment() is called with the
- dma_resv lock held.
- @importer_ops: importer operations for this attachment, if provided
- dma_buf_map/unmap_attachment() must be called with the dma_resv lock held.
- @importer_priv: importer specific attachment data.
- This structure holds the attachment information between the dma_buf buffer
- and its user device(s). The list contains one attachment struct per device
@@ -362,7 +414,8 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir;
- bool dynamic_mapping;
- const struct dma_buf_attach_ops *importer_ops;
- void *importer_priv; void *priv; };
@@ -438,16 +491,19 @@ static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf) static inline bool dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) {
- return attach->dynamic_mapping;
- return !!attach->importer_ops; }
struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); struct dma_buf_attachment * dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
bool dynamic_mapping);
const struct dma_buf_attach_ops *importer_ops,
void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach);void *importer_priv);
+int dma_buf_pin(struct dma_buf_attachment *attach); +void dma_buf_unpin(struct dma_buf_attachment *attach); struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info);
Pipeline removal of the BOs backing store when no placement is given during validation.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/ttm/ttm_bo.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 229205e499db..a56cb2a2b4ad 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1225,6 +1225,18 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, uint32_t new_flags;
dma_resv_assert_held(bo->base.resv); + + /* + * Remove the backing store if no placement is given. + */ + if (!placement->num_placement && !placement->num_busy_placement) { + ret = ttm_bo_pipeline_gutting(bo); + if (ret) + return ret; + + return ttm_tt_create(bo, false); + } + /* * Check whether we need to move buffer. */
Avoid that we ping/pong the buffers when we stop to pin DMA-buf exports by using the allowed domains for exported buffers.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 80ba6dfc54e2..d938d458e22d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -28,6 +28,7 @@ #include <linux/file.h> #include <linux/pagemap.h> #include <linux/sync_file.h> +#include <linux/dma-buf.h>
#include <drm/amdgpu_drm.h> #include <drm/drm_syncobj.h> @@ -417,7 +418,9 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p, /* Don't move this buffer if we have depleted our allowance * to move it. Don't move anything if the threshold is zero. */ - if (p->bytes_moved < p->bytes_moved_threshold) { + if (p->bytes_moved < p->bytes_moved_threshold && + (!bo->tbo.base.dma_buf || + list_empty(&bo->tbo.base.dma_buf->attachments))) { if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) { /* And don't move a CPU_ACCESS_REQUIRED BO to limited
This implements the exporter side of unpinned DMA-buf handling.
v2: fix minor coding style issues
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 53 ++++++++++++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 ++ 2 files changed, 51 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index b2ca78b6abce..770baba621b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -222,6 +222,37 @@ static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf, bo->prime_shared_count--; }
+/** + * amdgpu_dma_buf_pin - &dma_buf_ops.pin implementation + * + * @attach: attachment to pin down + * + * Pin the BO which is backing the DMA-buf so that it can't move any more. + */ +static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach) +{ + struct drm_gem_object *obj = attach->dmabuf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + /* pin buffer into GTT */ + return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); +} + +/** + * amdgpu_dma_buf_unpin - &dma_buf_ops.unpin implementation + * + * @attach: attachment to unpin + * + * Unpin a previously pinned BO to make it movable again. + */ +static void amdgpu_dma_buf_unpin(struct dma_buf_attachment *attach) +{ + struct drm_gem_object *obj = attach->dmabuf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + amdgpu_bo_unpin(bo); +} + /** * amdgpu_dma_buf_map - &dma_buf_ops.map_dma_buf implementation * @attach: DMA-buf attachment @@ -244,9 +275,19 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, struct sg_table *sgt; long r;
- r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); - if (r) - return ERR_PTR(r); + if (!bo->pin_count) { + /* move buffer into GTT */ + struct ttm_operation_ctx ctx = { false, false }; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) + return ERR_PTR(r); + + } else if (!(amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type) & + AMDGPU_GEM_DOMAIN_GTT)) { + return ERR_PTR(-EBUSY); + }
sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages); if (IS_ERR(sgt)) @@ -277,13 +318,9 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach, struct sg_table *sgt, enum dma_data_direction dir) { - struct drm_gem_object *obj = attach->dmabuf->priv; - struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); - dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir); sg_free_table(sgt); kfree(sgt); - amdgpu_bo_unpin(bo); }
/** @@ -330,6 +367,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = { .dynamic_mapping = true, .attach = amdgpu_dma_buf_attach, .detach = amdgpu_dma_buf_detach, + .pin = amdgpu_dma_buf_pin, + .unpin = amdgpu_dma_buf_unpin, .map_dma_buf = amdgpu_dma_buf_map, .unmap_dma_buf = amdgpu_dma_buf_unmap, .release = drm_gem_dmabuf_release, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 6f60a581e3ba..8ae260822908 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -31,6 +31,7 @@ */ #include <linux/list.h> #include <linux/slab.h> +#include <linux/dma-buf.h>
#include <drm/amdgpu_drm.h> #include <drm/drm_cache.h> @@ -1274,6 +1275,10 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
amdgpu_bo_kunmap(abo);
+ if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && + bo->mem.mem_type != TTM_PL_SYSTEM) + dma_buf_move_notify(abo->tbo.base.dma_buf); + /* remember the eviction */ if (evict) atomic64_inc(&adev->num_evictions);
Implement the importer side of unpinned DMA-buf handling.
v2: update page tables immediately
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 66 ++++++++++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ 2 files changed, 71 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 770baba621b3..48de7624d49c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -453,7 +453,71 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); }
+/** + * amdgpu_dma_buf_move_notify - &attach.move_notify implementation + * + * @attach: the DMA-buf attachment + * + * Invalidate the DMA-buf attachment, making sure that the we re-create the + * mapping before the next use. + */ +static void +amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) +{ + struct drm_gem_object *obj = attach->importer_priv; + struct ww_acquire_ctx *ticket = dma_resv_locking_ctx(obj->resv); + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_operation_ctx ctx = { false, false }; + struct ttm_placement placement = {}; + struct amdgpu_vm_bo_base *bo_base; + int r; + + if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + return; + + r = ttm_bo_validate(&bo->tbo, &placement, &ctx); + if (r) { + DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r); + return; + } + + for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { + struct amdgpu_vm *vm = bo_base->vm; + struct dma_resv *resv = vm->root.base.bo->tbo.base.resv; + + if (ticket) { + /* When we get an error here it means that somebody + * else is holding the VM lock and updating page tables + * So we can just continue here. + */ + r = dma_resv_lock(resv, ticket); + if (r) + continue; + + } else { + /* TODO: This is more problematic and we actually need + * to allow page tables updates without holding the + * lock. + */ + if (!dma_resv_trylock(resv)) + continue; + } + + r = amdgpu_vm_clear_freed(adev, vm, NULL); + if (!r) + r = amdgpu_vm_handle_moved(adev, vm); + + if (r && r != -EBUSY) + DRM_ERROR("Failed to invalidate VM page tables (%d))\n", + r); + + dma_resv_unlock(resv); + } +} + static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = { + .move_notify = amdgpu_dma_buf_move_notify };
/** @@ -489,7 +553,7 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, return obj;
attach = dma_buf_dynamic_attach(dma_buf, dev->dev, - &amdgpu_dma_buf_attach_ops, NULL); + &amdgpu_dma_buf_attach_ops, obj); if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8ae260822908..8c480c898b0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -926,6 +926,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return 0; }
+ if (bo->tbo.base.import_attach) + dma_buf_pin(bo->tbo.base.import_attach); + bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; /* force to pin into visible video ram */ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) @@ -1009,6 +1012,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
amdgpu_bo_subtract_pin_size(bo);
+ if (bo->tbo.base.import_attach) + dma_buf_unpin(bo->tbo.base.import_attach); + for (i = 0; i < bo->placement.num_placement; i++) { bo->placements[i].lpfn = 0; bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
On Mon, Feb 17, 2020 at 04:45:09PM +0100, Christian König wrote:
Implement the importer side of unpinned DMA-buf handling.
v2: update page tables immediately
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 66 ++++++++++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ 2 files changed, 71 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 770baba621b3..48de7624d49c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -453,7 +453,71 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); } +/**
- amdgpu_dma_buf_move_notify - &attach.move_notify implementation
- @attach: the DMA-buf attachment
- Invalidate the DMA-buf attachment, making sure that the we re-create the
- mapping before the next use.
- */
+static void +amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) +{
- struct drm_gem_object *obj = attach->importer_priv;
- struct ww_acquire_ctx *ticket = dma_resv_locking_ctx(obj->resv);
- struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- struct ttm_operation_ctx ctx = { false, false };
- struct ttm_placement placement = {};
- struct amdgpu_vm_bo_base *bo_base;
- int r;
- if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM)
return;
- r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
- if (r) {
DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
return;
- }
- for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
struct amdgpu_vm *vm = bo_base->vm;
struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
if (ticket) {
Yeah so this is kinda why I've been a total pain about the exact semantics of the move_notify hook. I think we should flat-out require that importers _always_ have a ticket attach when they call this, and that they can cope with additional locks being taken (i.e. full EDEADLCK) handling.
Simplest way to force that contract is to add a dummy 2nd ww_mutex lock to the dma_resv object, which we then can take #ifdef CONFIG_WW_MUTEX_SLOWPATH_DEBUG. Plus mabye a WARN_ON(!ticket).
Now the real disaster is how we handle deadlocks. Two issues:
- Ideally we'd keep any lock we've taken locked until the end, it helps needless backoffs. I've played around a bit with that but not even poc level, just an idea:
https://cgit.freedesktop.org/~danvet/drm/commit/?id=b1799c5a0f02df9e1bb08d27...
Idea is essentially to track a list of objects we had to lock as part of the ttm_bo_validate of the main object.
- Second one is if we get a EDEADLCK on one of these sublocks (like the one here). We need to pass that up the entire callchain, including a temporary reference (we have to drop locks to do the ww_mutex_lock_slow call), and need a custom callback to drop that temporary reference (since that's all driver specific, might even be internal ww_mutex and not anything remotely looking like a normal dma_buf). This probably needs the exec util helpers from ttm, but at the dma_resv level, so that we can do something like this:
struct dma_resv_ticket { struct ww_acquire_ctx base;
/* can be set by anyone (including other drivers) that got hold of * this ticket and had to acquire some new lock. This lock might * protect anything, including driver-internal stuff, and isn't * required to be a dma_buf or even just a dma_resv. */ struct ww_mutex *contended_lock;
/* callback which the driver (which might be a dma-buf exporter * and not matching the driver that started this locking ticket) * sets together with @contended_lock, for the main driver to drop * when it calls dma_resv_unlock on the contended_lock. */ void (drop_ref*)(struct ww_mutex *contended_lock); };
This is all supremely nasty (also ttm_bo_validate would need to be improved to handle these sublocks and random new objects that could force a ww_mutex_lock_slow).
Plan B would be to throw our hands into and declare that "move_notify is best effort only and can fail for any reason". Exactly like ttm eviction currently does, even with all your hacks to do at least some dma_resv_lock (but not the full slowpath).
Given how much "fun" you have with all the low memory handling and ttm fundamentally being best-effort only (despite that dma_resv would allow us to do this right, with some work) I'm not sure that's a good idea to extend to a cross-driver interface. Personally I'd lean towards fixing this first fully (in ttm/amdgpu), and then using that to implement move_notify correctly.
Or just add an int return value here and mandate that importers must handle eviction failures. Exactly like ttm_mem_evict_first can currently still fail for various reasons.
(Sorry this isn't exactly the mail you hoped for)
Cheers, Daniel
/* When we get an error here it means that somebody
* else is holding the VM lock and updating page tables
* So we can just continue here.
*/
r = dma_resv_lock(resv, ticket);
if (r)
continue;
} else {
/* TODO: This is more problematic and we actually need
* to allow page tables updates without holding the
* lock.
*/
if (!dma_resv_trylock(resv))
continue;
}
r = amdgpu_vm_clear_freed(adev, vm, NULL);
if (!r)
r = amdgpu_vm_handle_moved(adev, vm);
if (r && r != -EBUSY)
DRM_ERROR("Failed to invalidate VM page tables (%d))\n",
r);
dma_resv_unlock(resv);
- }
+}
static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
- .move_notify = amdgpu_dma_buf_move_notify
}; /** @@ -489,7 +553,7 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, return obj; attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
&amdgpu_dma_buf_attach_ops, NULL);
if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach);&amdgpu_dma_buf_attach_ops, obj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8ae260822908..8c480c898b0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -926,6 +926,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return 0; }
- if (bo->tbo.base.import_attach)
dma_buf_pin(bo->tbo.base.import_attach);
- bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; /* force to pin into visible video ram */ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
@@ -1009,6 +1012,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo) amdgpu_bo_subtract_pin_size(bo);
- if (bo->tbo.base.import_attach)
dma_buf_unpin(bo->tbo.base.import_attach);
- for (i = 0; i < bo->placement.num_placement; i++) { bo->placements[i].lpfn = 0; bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-- 2.17.1
Am 17.02.20 um 18:55 schrieb Daniel Vetter:
On Mon, Feb 17, 2020 at 04:45:09PM +0100, Christian König wrote:
Implement the importer side of unpinned DMA-buf handling.
v2: update page tables immediately
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 66 ++++++++++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ 2 files changed, 71 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 770baba621b3..48de7624d49c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -453,7 +453,71 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); } +/**
- amdgpu_dma_buf_move_notify - &attach.move_notify implementation
- @attach: the DMA-buf attachment
- Invalidate the DMA-buf attachment, making sure that the we re-create the
- mapping before the next use.
- */
+static void +amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) +{
- struct drm_gem_object *obj = attach->importer_priv;
- struct ww_acquire_ctx *ticket = dma_resv_locking_ctx(obj->resv);
- struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- struct ttm_operation_ctx ctx = { false, false };
- struct ttm_placement placement = {};
- struct amdgpu_vm_bo_base *bo_base;
- int r;
- if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM)
return;
- r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
- if (r) {
DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
return;
- }
- for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
struct amdgpu_vm *vm = bo_base->vm;
struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
if (ticket) {
Yeah so this is kinda why I've been a total pain about the exact semantics of the move_notify hook. I think we should flat-out require that importers _always_ have a ticket attach when they call this, and that they can cope with additional locks being taken (i.e. full EDEADLCK) handling.
That is pretty much exactly my thinking as well.
And is also the sole reason why I started looking into the ww_mutex cursor handling a while back (e.g. the initial version with the horrible macro hack).
But this is really really hard to get right. So my thinking for now is to push this series upstream to at least unblock my ongoing P2P work.
Simplest way to force that contract is to add a dummy 2nd ww_mutex lock to the dma_resv object, which we then can take #ifdef CONFIG_WW_MUTEX_SLOWPATH_DEBUG. Plus mabye a WARN_ON(!ticket).
Now the real disaster is how we handle deadlocks. Two issues:
- Ideally we'd keep any lock we've taken locked until the end, it helps needless backoffs. I've played around a bit with that but not even poc level, just an idea:
https://cgit.freedesktop.org/~danvet/drm/commit/?id=b1799c5a0f02df9e1bb08d27...
Idea is essentially to track a list of objects we had to lock as part of the ttm_bo_validate of the main object.
- Second one is if we get a EDEADLCK on one of these sublocks (like the one here). We need to pass that up the entire callchain, including a temporary reference (we have to drop locks to do the ww_mutex_lock_slow call), and need a custom callback to drop that temporary reference (since that's all driver specific, might even be internal ww_mutex and not anything remotely looking like a normal dma_buf). This probably needs the exec util helpers from ttm, but at the dma_resv level, so that we can do something like this:
struct dma_resv_ticket { struct ww_acquire_ctx base;
/* can be set by anyone (including other drivers) that got hold of * this ticket and had to acquire some new lock. This lock might * protect anything, including driver-internal stuff, and isn't * required to be a dma_buf or even just a dma_resv. */ struct ww_mutex *contended_lock;
/* callback which the driver (which might be a dma-buf exporter * and not matching the driver that started this locking ticket) * sets together with @contended_lock, for the main driver to drop * when it calls dma_resv_unlock on the contended_lock. */ void (drop_ref*)(struct ww_mutex *contended_lock); };
My initial thinking was to make all of this part of the core ww_mutex implementation, but then I quickly found that this won't work.
This is all supremely nasty (also ttm_bo_validate would need to be improved to handle these sublocks and random new objects that could force a ww_mutex_lock_slow).
The next idea was to have it based on dma_resv objects, but as you also figured out you then need to drop the reference to the contended lock somehow...
So my current working plan was to use GEM object to avoid the callback...
Plan B would be to throw our hands into and declare that "move_notify is best effort only and can fail for any reason". Exactly like ttm eviction currently does, even with all your hacks to do at least some dma_resv_lock (but not the full slowpath).
I would seriously NAK that. We have tried that with TTM and the whole idea is just braindead.
You can use trylock based eviction for things like best effort shrinker callbacks. But that's pretty much it.
Given how much "fun" you have with all the low memory handling and ttm fundamentally being best-effort only (despite that dma_resv would allow us to do this right, with some work) I'm not sure that's a good idea to extend to a cross-driver interface. Personally I'd lean towards fixing this first fully (in ttm/amdgpu), and then using that to implement move_notify correctly.
Well have you seen this: https://fosdem.org/2020/schedule/event/ttm/ :)
Or just add an int return value here and mandate that importers must handle eviction failures. Exactly like ttm_mem_evict_first can currently still fail for various reasons.
(Sorry this isn't exactly the mail you hoped for)
Well it's actually the mail I expected. I'm thinking about exactly those problems for over a year now as well.
For the rather specific amdgpu case I could work around that by utilizing the HMM work to invalidate page tables on the fly, but that doesn't really help with memory management in general.
So YES, I totally agree that we need some sort of GEM execution context or something like this to lock buffers on the fly as we try to make room for others.
Regards, Christian.
Cheers, Daniel
/* When we get an error here it means that somebody
* else is holding the VM lock and updating page tables
* So we can just continue here.
*/
r = dma_resv_lock(resv, ticket);
if (r)
continue;
} else {
/* TODO: This is more problematic and we actually need
* to allow page tables updates without holding the
* lock.
*/
if (!dma_resv_trylock(resv))
continue;
}
r = amdgpu_vm_clear_freed(adev, vm, NULL);
if (!r)
r = amdgpu_vm_handle_moved(adev, vm);
if (r && r != -EBUSY)
DRM_ERROR("Failed to invalidate VM page tables (%d))\n",
r);
dma_resv_unlock(resv);
- }
+}
- static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
- .move_notify = amdgpu_dma_buf_move_notify };
/** @@ -489,7 +553,7 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, return obj; attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
&amdgpu_dma_buf_attach_ops, NULL);
if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach);&amdgpu_dma_buf_attach_ops, obj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8ae260822908..8c480c898b0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -926,6 +926,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return 0; }
- if (bo->tbo.base.import_attach)
dma_buf_pin(bo->tbo.base.import_attach);
- bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; /* force to pin into visible video ram */ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
@@ -1009,6 +1012,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo) amdgpu_bo_subtract_pin_size(bo);
- if (bo->tbo.base.import_attach)
dma_buf_unpin(bo->tbo.base.import_attach);
- for (i = 0; i < bo->placement.num_placement; i++) { bo->placements[i].lpfn = 0; bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-- 2.17.1
On Mon, Feb 17, 2020 at 7:58 PM Christian König ckoenig.leichtzumerken@gmail.com wrote:
Am 17.02.20 um 18:55 schrieb Daniel Vetter:
On Mon, Feb 17, 2020 at 04:45:09PM +0100, Christian König wrote:
Implement the importer side of unpinned DMA-buf handling.
v2: update page tables immediately
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 66 ++++++++++++++++++++- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ 2 files changed, 71 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 770baba621b3..48de7624d49c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -453,7 +453,71 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) return ERR_PTR(ret); }
+/**
- amdgpu_dma_buf_move_notify - &attach.move_notify implementation
- @attach: the DMA-buf attachment
- Invalidate the DMA-buf attachment, making sure that the we re-create the
- mapping before the next use.
- */
+static void +amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) +{
- struct drm_gem_object *obj = attach->importer_priv;
- struct ww_acquire_ctx *ticket = dma_resv_locking_ctx(obj->resv);
- struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- struct ttm_operation_ctx ctx = { false, false };
- struct ttm_placement placement = {};
- struct amdgpu_vm_bo_base *bo_base;
- int r;
- if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM)
return;
- r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
- if (r) {
DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
return;
- }
- for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
struct amdgpu_vm *vm = bo_base->vm;
struct dma_resv *resv = vm->root.base.bo->tbo.base.resv;
if (ticket) {
Yeah so this is kinda why I've been a total pain about the exact semantics of the move_notify hook. I think we should flat-out require that importers _always_ have a ticket attach when they call this, and that they can cope with additional locks being taken (i.e. full EDEADLCK) handling.
That is pretty much exactly my thinking as well.
And is also the sole reason why I started looking into the ww_mutex cursor handling a while back (e.g. the initial version with the horrible macro hack).
But this is really really hard to get right. So my thinking for now is to push this series upstream to at least unblock my ongoing P2P work.
Hm, but at least the move_notify stuff and the locking nightmare around that feels rushed if we just push that. Otoh it's indeed getting painful, and we'll probably have another few rounds of headaches to sort this all out. What about a
config EXPERIMENTAL_DYNAMIC_DMA_BUF depends on BROKEN
Wrapped around the new ->move_notify hook, plus all relevant code? That way you can land at least something, in-tree refactoring might become easier with at least some example of what it needs to achieve. But we're also not tricking anyone into believing that this is production ready.
Simplest way to force that contract is to add a dummy 2nd ww_mutex lock to the dma_resv object, which we then can take #ifdef CONFIG_WW_MUTEX_SLOWPATH_DEBUG. Plus mabye a WARN_ON(!ticket).
Now the real disaster is how we handle deadlocks. Two issues:
- Ideally we'd keep any lock we've taken locked until the end, it helps needless backoffs. I've played around a bit with that but not even poc level, just an idea:
https://cgit.freedesktop.org/~danvet/drm/commit/?id=b1799c5a0f02df9e1bb08d27...
Idea is essentially to track a list of objects we had to lock as part of the ttm_bo_validate of the main object.
- Second one is if we get a EDEADLCK on one of these sublocks (like the one here). We need to pass that up the entire callchain, including a temporary reference (we have to drop locks to do the ww_mutex_lock_slow call), and need a custom callback to drop that temporary reference (since that's all driver specific, might even be internal ww_mutex and not anything remotely looking like a normal dma_buf). This probably needs the exec util helpers from ttm, but at the dma_resv level, so that we can do something like this:
struct dma_resv_ticket { struct ww_acquire_ctx base;
/* can be set by anyone (including other drivers) that got hold of * this ticket and had to acquire some new lock. This lock might * protect anything, including driver-internal stuff, and isn't * required to be a dma_buf or even just a dma_resv. */ struct ww_mutex *contended_lock; /* callback which the driver (which might be a dma-buf exporter * and not matching the driver that started this locking ticket) * sets together with @contended_lock, for the main driver to drop * when it calls dma_resv_unlock on the contended_lock. */ void (drop_ref*)(struct ww_mutex *contended_lock);
};
My initial thinking was to make all of this part of the core ww_mutex implementation, but then I quickly found that this won't work.
This is all supremely nasty (also ttm_bo_validate would need to be improved to handle these sublocks and random new objects that could force a ww_mutex_lock_slow).
The next idea was to have it based on dma_resv objects, but as you also figured out you then need to drop the reference to the contended lock somehow...
So my current working plan was to use GEM object to avoid the callback...
I've heard noise that someone is looking into adding dynamic dma-buf support to stuff like rdma drivers. Because interconnects and big machines. Plus feels a bit awkward to mandate a gem library if you want to use dynamic dma-buf support in your driver. Hence why I think something around dma_resv (but with enough flexibility that it doesn't insist that the contending lock must be a dma_resv itself).
Plan B would be to throw our hands into and declare that "move_notify is best effort only and can fail for any reason". Exactly like ttm eviction currently does, even with all your hacks to do at least some dma_resv_lock (but not the full slowpath).
I would seriously NAK that. We have tried that with TTM and the whole idea is just braindead.
You can use trylock based eviction for things like best effort shrinker callbacks. But that's pretty much it.
Yeah trylock works pretty well for balancing caches, right up to the point where you actually have to shrink stuff. Then suddenly all the locks are contended because everyone is running low on memory :-/ We have glorious amounts of experience with our best effort system memory shrinker in i915 ...
Given how much "fun" you have with all the low memory handling and ttm fundamentally being best-effort only (despite that dma_resv would allow us to do this right, with some work) I'm not sure that's a good idea to extend to a cross-driver interface. Personally I'd lean towards fixing this first fully (in ttm/amdgpu), and then using that to implement move_notify correctly.
Well have you seen this: https://fosdem.org/2020/schedule/event/ttm/ :)
Oh cool, I was waiting for the upload. Will watch asap. btw slides somewhere?
Or just add an int return value here and mandate that importers must handle eviction failures. Exactly like ttm_mem_evict_first can currently still fail for various reasons.
(Sorry this isn't exactly the mail you hoped for)
Well it's actually the mail I expected. I'm thinking about exactly those problems for over a year now as well.
For the rather specific amdgpu case I could work around that by utilizing the HMM work to invalidate page tables on the fly, but that doesn't really help with memory management in general.
Yeah, so move_notify is maybe solveable with better hw and hmm, but there's other scenarios where I think the cross-driver ww_mutex locking will be needed, for fundamental reasons. Scenario: - a bunch of gpus in pcie slots, all in the same machine - because pcie is slot a nice interconnect (iirc you guys call yours xgmi or something like that) - working sets that are bigger than vram of a single gpu - lots of buffer sharing ofc
1. So driver has an imported dma-buf, currently not mapped anywhere because ti got thrown out (or first use). 2. Importer calls dma_buf_map_attachement 3. Exporter realizes there's a nice xgmi link and p2p would be much better if that object is in vram. 4. Exporter does ttm_bo_validate or equivalent to get the bo into vram, including eviction and lots of locking 5. In turn this might bite back to the importer through some move_notify of objects still mapped, but at the end of the lru.
So ->move_notify might not be the worst, eventually I think we'll need the full locking dance across drivers (or at least across drm_device instances, there might be internal upcasting going on so you get your buffers placed in the right vram and all that directly).
So YES, I totally agree that we need some sort of GEM execution context or something like this to lock buffers on the fly as we try to make room for others.
So what's the plan? Merge current series (with the bikesheds address) under this CONFIG_EXPERIMENTAL_DYN_DMABUF and then see where we land from there? Trying to get all the pieces lined up out of tree feels like it's going to be too much :-/ -Daniel
Regards, Christian.
Cheers, Daniel
/* When we get an error here it means that somebody
* else is holding the VM lock and updating page tables
* So we can just continue here.
*/
r = dma_resv_lock(resv, ticket);
if (r)
continue;
} else {
/* TODO: This is more problematic and we actually need
* to allow page tables updates without holding the
* lock.
*/
if (!dma_resv_trylock(resv))
continue;
}
r = amdgpu_vm_clear_freed(adev, vm, NULL);
if (!r)
r = amdgpu_vm_handle_moved(adev, vm);
if (r && r != -EBUSY)
DRM_ERROR("Failed to invalidate VM page tables (%d))\n",
r);
dma_resv_unlock(resv);
- }
+}
static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
.move_notify = amdgpu_dma_buf_move_notify };
/**
@@ -489,7 +553,7 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev, return obj;
attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
&amdgpu_dma_buf_attach_ops, NULL);
if (IS_ERR(attach)) { drm_gem_object_put(obj); return ERR_CAST(attach);&amdgpu_dma_buf_attach_ops, obj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8ae260822908..8c480c898b0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -926,6 +926,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return 0; }
- if (bo->tbo.base.import_attach)
dma_buf_pin(bo->tbo.base.import_attach);
- bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; /* force to pin into visible video ram */ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
@@ -1009,6 +1012,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
amdgpu_bo_subtract_pin_size(bo);
- if (bo->tbo.base.import_attach)
dma_buf_unpin(bo->tbo.base.import_attach);
- for (i = 0; i < bo->placement.num_placement; i++) { bo->placements[i].lpfn = 0; bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
-- 2.17.1
linaro-mm-sig@lists.linaro.org