- 26 Jul, 2024 1 commit
-
-
Jason Wang authored
remap_pfn_page() should not be called in the fault handler as it may change the vma->flags which may trigger lockdep warning since the vma write lock is not held. Actually there's no need to modify the vma->flags as it has been set in the mmap(). So this patch switches to use vmf_insert_pfn() instead. Reported-by:
Dragos Tatulea <dtatulea@nvidia.com> Tested-by:
Jason Wang <jasowang@redhat.com> Message-Id: <20240701033159.18133-1-jasowang@redhat.com> Signed-off-by:
Michael S. Tsirkin <mst@redhat.com> Reviewed-by:
Michal Kubiak <michal.kubiak@intel.com>
-
- 17 Jul, 2024 34 commits
-
-
Jiri Pirko authored
The admin queue operations are protected by newly introduced spin lock. To make it possible to issue parallel commands, remove the admin queue serialization lock. Signed-off-by:
Jiri Pirko <jiri@nvidia.com> Message-Id: <20240716113552.80599-14-jiri@resnulli.us> Signed-off-by:
-
Jiri Pirko authored
Currently, the code waits in a busy loop on every admin virtqueue issued command to get a reply. That prevents callers from issuing multiple commands in parallel. To overcome this limitation, introduce a virtqueue event callback for admin virtqueue. For every issued command, use completion mechanism to wait on a reply. In the event callback, trigger the completion is done for every incoming reply. Alongside with that, introduce a spin lock to protect the admin virtqueue operations. Signed-off-by:
-
Jiri Pirko authored
In preparation to asynchronous admin queue processing, pass cmd pointer as a data arg to virtqueue_add_sgs(). Signed-off-by:
-
Jiri Pirko authored
Don't limit the admin queue size to VIRTIO_AVQ_SGS_MAX and rather rely on the queried queue size. Signed-off-by:
-
Jiri Pirko authored
Admin virtqueue is just another virtqueue nothing that special about it. The current implementation treats it somehow separate though in terms of creation and deletion. Unify the admin virtqueue creation and deletion flows to be aligned with the rest of virtqueues, creating it from vp_find_vqs_*() helpers. Let the admin virtqueue to be deleted by vp_del_vqs() as the rest. Call vp_find_one_vq_msix() with slow_path argument being "true" to make sure that in case of limited interrupt vectors the config vector is used for admin queue. Signed-off-by:
-
Jiri Pirko authored
Instead vp_setup_vq() storing vq info directly to vp_dev->vqs, let the caller provide a pointer to store the info to. This prepares vp_setup_vq() to be able to store admin queue info as well. Signed-off-by:
-
Jiri Pirko authored
To prepare for the follow-up patch to use the code as an op, push out the code that gets admin virtqueue base index and count to a separate helper. Signed-off-by:
-
Jiri Pirko authored
It is guaranteed by the virtio_pci and PCI layers that none of the VFs is probed before setup_vq() is called for admin queue and after del_vq() is called for admin queue. Therefore treat vp_dev->admin_vq.info.vq as static, don't null it and don't take cmd lock during assign. Signed-off-by:
-
Jiri Pirko authored
If there is not enough vectors to satisfy all virtqueues, currently the fallback is to use one vector for all virtqueues. That may be unnecessary in some cases, when there is enough vectors per data queues. Introduce another fallback policy that tries to allocate vector for all data queues, however for slow path queues (control/admin) it shares config vector. Signed-off-by:
-
Jiri Pirko authored
Instead of accessing vp_dev->per_vq_vectors, pass vector policy enum as an argument of vp_find_one_vq_msix() in preparation for another irq allocation policy. Signed-off-by:
-
Jiri Pirko authored
In preparation for another irq allocation fallback, introduce vector policy enum and pass the values to vp_find_vqs_msix() instead of bool arg. Signed-off-by:
-
Jiri Pirko authored
Pass desc arg as it is always to vp_request_msix_vectors(). There rely on per_vq_vectors arg and null desc in case it is false. Signed-off-by:
-
Jiri Pirko authored
In order to be reused for admin queue setup, push out common code to setup and configure irq for one vq into a separate helper. Signed-off-by:
-
Dan Carpenter authored
Return -EINVAL for invalid signatures. Don't return success. Fixes: 8b6c724c ("virtio: vdpa: vDPA driver for Marvell OCTEON DPU devices") Signed-off-by:
Dan Carpenter <dan.carpenter@linaro.org> Message-Id: <623e885b-1a05-479e-ab97-01bcf10bf5b8@stanley.mountain> Signed-off-by:
-
Jeff Johnson authored
make allmodconfig && make W=1 C=1 reports: WARNING: modpost: missing MODULE_DESCRIPTION() in drivers/virtio/virtio_dma_buf.o Add the missing invocation of the MODULE_DESCRIPTION() macro. Signed-off-by:
Jeff Johnson <quic_jjohnson@quicinc.com> Message-Id: <20240602-md-virtio_dma_buf-v1-1-ce602d47e257@quicinc.com> Signed-off-by:
-
Jiri Pirko authored
Since the original virtio_find_vqs() is no longer present, rename virtio_find_vqs_info() back to virtio_find_vqs(). Signed-off-by:
-
Jiri Pirko authored
All callers of virtio_find_vqs() and virtio_find_vqs_ctx() were converted to use virtio_find_vqs_info(). Remove no longer used helpers. Signed-off-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), have one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
Xuan Zhuo <xuanzhuo@linux.alibaba.com> Signed-off-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), have one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs_ctx(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Instead of passing separate names and callbacks arrays to virtio_find_vqs(), allocate one of virtual_queue_info structs and pass it to virtio_find_vqs_info(). Suggested-by:
-
Jiri Pirko authored
Since the original find_vqs() is no longer present, rename find_vqs_info() back to find_vqs(). Signed-off-by:
-
Jiri Pirko authored
As it is no longer used, remove it. Signed-off-by:
-
Jiri Pirko authored
Since there are no more implementations of find_vqs() op, call virtio_find_vqs_info() from virtio_find_single_vq() directly. Signed-off-by:
-
Jiri Pirko authored
Convert existing find_vqs() transport implementations to use find_vqs_info() config op. Signed-off-by:
-
Jiri Pirko authored
Convert existing vp_find_vqs() and vp_modern_find_vqs() implementations to find_vqs_info() config op. Signed-off-by:
-
Jiri Pirko authored
Introduce a structure virtio_queue_info to carry name, callback and ctx together. In order to allow config implementations to accept config op with array of virtio_queue_info structures, introduce a new find_vqs_info() op. Do the needed conversion in virtio_find_vqs_ctx(). Note that whole virtio_find_vqs_ctx() is going to be eventually removed at the and of this patchset. Suggested-by:
-
Jiri Pirko authored
In order to prepare for conversion of virtio_find_vqs*() arguments, make virtio_find_single_vq() to call virtio_find_vqs() instead of op directly. Signed-off-by:
-
Jiri Pirko authored
In order to prepare for conversion of virtio_find_vqs*() arguments, make virtio_find_vqs() to call virtio_find_vqs_ctx() instead of op directly. Signed-off-by:
-
Jiri Pirko authored
Since caif uses only one queue, convert to virtio_find_single_vq() helper which is made for this purpose. Signed-off-by:
-
- 09 Jul, 2024 5 commits
-
-
Dragos Tatulea authored
VQ indices in the range [cur_num_qps, max_vqs) represent queues that have not yet been activated. .set_vq_ready should not activate these VQs. Reviewed-by:
Cosmin Ratiu <cratiu@nvidia.com> Acked-by:
Eugenio Pérez <eperezma@redhat.com> Signed-off-by:
-
Dragos Tatulea authored
The vdpa device can be reset many times in sequence without any significant state changes in between. Previously this was not a problem: VQs were torn down only on first reset. But after VQ pre-creation was introduced, each reset will delete and re-create the hardware VQs and their associated resources. To solve this problem, avoid resetting hardware VQs if the VQs are still in a blank state. Reviewed-by:
-
Dragos Tatulea authored
There are a few conditions under which the hardware VQs need a full teardown and setup: - VQ size changed to something else than default value. Hardware VQ size modification is not supported. - User turns off certain device features: mergeable buffers, checksum virtio 1.0 compliance. In these cases, the TIR and RQT need to be re-created. Add a needs_teardown configuration variable and set it when detecting the above scenarios. On next DRIVER_OK, the resources will be torn down first. Reviewed-by:
-
Dragos Tatulea authored
Currently, hardware VQs are created right when the vdpa device gets into DRIVER_OK state. That is easier because most of the VQ state is known by then. This patch switches to creating all VQs and their associated resources at device creation time. The motivation is to reduce the vdpa device live migration downtime by moving the expensive operation of creating all the hardware VQs and their associated resources out of downtime on the destination VM. The VQs are now created in a blank state. The VQ configuration will happen later, on DRIVER_OK. Then the configuration will be applied when the VQs are moved to the Ready state. When .set_vq_ready() is called on a VQ before DRIVER_OK, special care is needed: now that the VQ is already created a resume_vq() will be triggered too early when no mr has been configured yet. Skip calling resume_vq() in this case, let it be handled during DRIVER_OK. For virtio-vdpa, the device configuration is done earlier during .vdpa_dev_add() by vdpa_register_device(). Avoid calling setup_vq_resources() a second time in that case. On a 64 CPU, 256 GB VM with 1 vDPA device of 16 VQps, the full VQ resource creation + resume time was ~370ms. Now it's down to 60 ms (only VQ config and resume). The measurements were done on a ConnectX6DX based vDPA device. Signed-off-by:
-
Dragos Tatulea authored
Resume a VQ if it is already created when the number of VQ pairs increases. This is done in preparation for VQ pre-creation which is coming in a later patch. It is necessary because calling setup_vq() on an already created VQ will return early and will not enable the queue. For symmetry, suspend a VQ instead of tearing it down when the number of VQ pairs decreases. But only if the resume operation is supported. Reviewed-by:
-
