| Message ID | 20240816090159.1967650-4-dtatulea@nvidia.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | vdpa/mlx5: Parallelize device suspend/resume | expand |
On Fri, Aug 16, 2024 at 11:02 AM Dragos Tatulea <dtatulea@nvidia.com> wrote: > > Introduce a new function mlx5_vdpa_exec_async_cmds() which > wraps the mlx5_core async firmware command API in a way > that will be used to parallelize certain operation in this > driver. > > The wrapper deals with the case when mlx5_cmd_exec_cb() returns > EBUSY due to the command being throttled. > > Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com> > Reviewed-by: Tariq Toukan <tariqt@nvidia.com> Acked-by: Eugenio Pérez <eperezma@redhat.com> > --- > drivers/vdpa/mlx5/core/mlx5_vdpa.h | 15 ++++++ > drivers/vdpa/mlx5/core/resources.c | 73 ++++++++++++++++++++++++++++++ > 2 files changed, 88 insertions(+) > > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > index 424d445ebee4..b34e9b93d56e 100644 > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > @@ -105,6 +105,18 @@ struct mlx5_vdpa_dev { > bool suspended; > }; > > +struct mlx5_vdpa_async_cmd { > + int err; > + struct mlx5_async_work cb_work; > + struct completion cmd_done; > + > + void *in; > + size_t inlen; > + > + void *out; > + size_t outlen; > +}; > + > int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn); > void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn); > int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn); > @@ -134,6 +146,9 @@ int mlx5_vdpa_update_cvq_iotlb(struct mlx5_vdpa_dev *mvdev, > unsigned int asid); > int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev); > int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid); > +int mlx5_vdpa_exec_async_cmds(struct mlx5_vdpa_dev *mvdev, > + struct mlx5_vdpa_async_cmd *cmds, > + int num_cmds); > > #define mlx5_vdpa_err(__dev, format, ...) \ > dev_err((__dev)->mdev->device, "%s:%d:(pid %d) error: " format, __func__, __LINE__, \ > diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c > index 5c5a41b64bfc..22ea32fe007b 100644 > --- a/drivers/vdpa/mlx5/core/resources.c > +++ b/drivers/vdpa/mlx5/core/resources.c > @@ -321,3 +321,76 @@ void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev) > mutex_destroy(&mvdev->mr_mtx); > res->valid = false; > } > + > +static void virtqueue_cmd_callback(int status, struct mlx5_async_work *context) > +{ > + struct mlx5_vdpa_async_cmd *cmd = > + container_of(context, struct mlx5_vdpa_async_cmd, cb_work); > + > + cmd->err = mlx5_cmd_check(context->ctx->dev, status, cmd->in, cmd->out); > + complete(&cmd->cmd_done); > +} > + > +static int issue_async_cmd(struct mlx5_vdpa_dev *mvdev, > + struct mlx5_vdpa_async_cmd *cmds, > + int issued, > + int *completed) > + > +{ > + struct mlx5_vdpa_async_cmd *cmd = &cmds[issued]; > + int err; > + > +retry: > + err = mlx5_cmd_exec_cb(&mvdev->async_ctx, > + cmd->in, cmd->inlen, > + cmd->out, cmd->outlen, > + virtqueue_cmd_callback, > + &cmd->cb_work); > + if (err == -EBUSY) { > + if (*completed < issued) { > + /* Throttled by own commands: wait for oldest completion. */ > + wait_for_completion(&cmds[*completed].cmd_done); > + (*completed)++; > + > + goto retry; > + } else { > + /* Throttled by external commands: switch to sync api. */ > + err = mlx5_cmd_exec(mvdev->mdev, > + cmd->in, cmd->inlen, > + cmd->out, cmd->outlen); > + if (!err) > + (*completed)++; > + } > + } > + > + return err; > +} > + > +int mlx5_vdpa_exec_async_cmds(struct mlx5_vdpa_dev *mvdev, > + struct mlx5_vdpa_async_cmd *cmds, > + int num_cmds) > +{ > + int completed = 0; > + int issued = 0; > + int err = 0; > + > + for (int i = 0; i < num_cmds; i++) > + init_completion(&cmds[i].cmd_done); > + > + while (issued < num_cmds) { > + > + err = issue_async_cmd(mvdev, cmds, issued, &completed); > + if (err) { > + mlx5_vdpa_err(mvdev, "error issuing command %d of %d: %d\n", > + issued, num_cmds, err); > + break; > + } > + > + issued++; > + } > + > + while (completed < issued) > + wait_for_completion(&cmds[completed++].cmd_done); > + > + return err; > +} > -- > 2.45.1 >
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 424d445ebee4..b34e9b93d56e 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -105,6 +105,18 @@ struct mlx5_vdpa_dev { bool suspended; }; +struct mlx5_vdpa_async_cmd { + int err; + struct mlx5_async_work cb_work; + struct completion cmd_done; + + void *in; + size_t inlen; + + void *out; + size_t outlen; +}; + int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn); void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn); int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn); @@ -134,6 +146,9 @@ int mlx5_vdpa_update_cvq_iotlb(struct mlx5_vdpa_dev *mvdev, unsigned int asid); int mlx5_vdpa_create_dma_mr(struct mlx5_vdpa_dev *mvdev); int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid); +int mlx5_vdpa_exec_async_cmds(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_async_cmd *cmds, + int num_cmds); #define mlx5_vdpa_err(__dev, format, ...) \ dev_err((__dev)->mdev->device, "%s:%d:(pid %d) error: " format, __func__, __LINE__, \ diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 5c5a41b64bfc..22ea32fe007b 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -321,3 +321,76 @@ void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev) mutex_destroy(&mvdev->mr_mtx); res->valid = false; } + +static void virtqueue_cmd_callback(int status, struct mlx5_async_work *context) +{ + struct mlx5_vdpa_async_cmd *cmd = + container_of(context, struct mlx5_vdpa_async_cmd, cb_work); + + cmd->err = mlx5_cmd_check(context->ctx->dev, status, cmd->in, cmd->out); + complete(&cmd->cmd_done); +} + +static int issue_async_cmd(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_async_cmd *cmds, + int issued, + int *completed) + +{ + struct mlx5_vdpa_async_cmd *cmd = &cmds[issued]; + int err; + +retry: + err = mlx5_cmd_exec_cb(&mvdev->async_ctx, + cmd->in, cmd->inlen, + cmd->out, cmd->outlen, + virtqueue_cmd_callback, + &cmd->cb_work); + if (err == -EBUSY) { + if (*completed < issued) { + /* Throttled by own commands: wait for oldest completion. */ + wait_for_completion(&cmds[*completed].cmd_done); + (*completed)++; + + goto retry; + } else { + /* Throttled by external commands: switch to sync api. */ + err = mlx5_cmd_exec(mvdev->mdev, + cmd->in, cmd->inlen, + cmd->out, cmd->outlen); + if (!err) + (*completed)++; + } + } + + return err; +} + +int mlx5_vdpa_exec_async_cmds(struct mlx5_vdpa_dev *mvdev, + struct mlx5_vdpa_async_cmd *cmds, + int num_cmds) +{ + int completed = 0; + int issued = 0; + int err = 0; + + for (int i = 0; i < num_cmds; i++) + init_completion(&cmds[i].cmd_done); + + while (issued < num_cmds) { + + err = issue_async_cmd(mvdev, cmds, issued, &completed); + if (err) { + mlx5_vdpa_err(mvdev, "error issuing command %d of %d: %d\n", + issued, num_cmds, err); + break; + } + + issued++; + } + + while (completed < issued) + wait_for_completion(&cmds[completed++].cmd_done); + + return err; +}