Re: [PATCH v7 05/12] util/dsa: Implement DSA task asynchronous completion thread model.

[Fabiano Rosas]

Yichen Wang <yichen.wang@bytedance.com> writes:

> From: Hao Xiang <hao.xiang@linux.dev>
>
> * Create a dedicated thread for DSA task completion.
> * DSA completion thread runs a loop and poll for completed tasks.
> * Start and stop DSA completion thread during DSA device start stop.
>
> User space application can directly submit task to Intel DSA
> accelerator by writing to DSA's device memory (mapped in user space).
> Once a task is submitted, the device starts processing it and write
> the completion status back to the task. A user space application can
> poll the task's completion status to check for completion. This change
> uses a dedicated thread to perform DSA task completion checking.
>
> Signed-off-by: Hao Xiang <hao.xiang@linux.dev>
> Signed-off-by: Yichen Wang <yichen.wang@bytedance.com>
> ---
>  include/qemu/dsa.h |   1 +
>  util/dsa.c         | 274 ++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 274 insertions(+), 1 deletion(-)
>
> diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
> index 04ee8924ab..d24567f0be 100644
> --- a/include/qemu/dsa.h
> +++ b/include/qemu/dsa.h
> @@ -69,6 +69,7 @@ typedef struct QemuDsaBatchTask {
>      QemuDsaTaskType task_type;
>      QemuDsaTaskStatus status;
>      int batch_size;
> +    bool *results;
>      QSIMPLEQ_ENTRY(QemuDsaBatchTask) entry;
>  } QemuDsaBatchTask;
>  
> diff --git a/util/dsa.c b/util/dsa.c
> index b55fa599f0..c3ca71df86 100644
> --- a/util/dsa.c
> +++ b/util/dsa.c
> @@ -33,9 +33,20 @@
>  #define DSA_WQ_PORTAL_SIZE 4096
>  #define DSA_WQ_DEPTH 128
>  #define MAX_DSA_DEVICES 16
> +#define DSA_COMPLETION_THREAD "qemu_dsa_completion"
> +
> +typedef struct {
> +    bool stopping;
> +    bool running;
> +    QemuThread thread;
> +    int thread_id;
> +    QemuSemaphore sem_init_done;
> +    QemuDsaDeviceGroup *group;
> +} QemuDsaCompletionThread;
>  
>  uint32_t max_retry_count;
>  static QemuDsaDeviceGroup dsa_group;
> +static QemuDsaCompletionThread completion_thread;
>  
>  
>  /**
> @@ -403,6 +414,265 @@ submit_batch_wi_async(QemuDsaBatchTask *batch_task)
>      return dsa_task_enqueue(device_group, batch_task);
>  }
>  
> +/**
> + * @brief Poll for the DSA work item completion.
> + *
> + * @param completion A pointer to the DSA work item completion record.
> + * @param opcode The DSA opcode.
> + *
> + * @return Zero if successful, non-zero otherwise.
> + */
> +static int
> +poll_completion(struct dsa_completion_record *completion,
> +                enum dsa_opcode opcode)
> +{
> +    uint8_t status;
> +    uint64_t retry = 0;
> +
> +    while (true) {
> +        /* The DSA operation completes successfully or fails. */
> +        status = completion->status;
> +        if (status == DSA_COMP_SUCCESS ||
> +            status == DSA_COMP_PAGE_FAULT_NOBOF ||
> +            status == DSA_COMP_BATCH_PAGE_FAULT ||
> +            status == DSA_COMP_BATCH_FAIL) {
> +            break;
> +        } else if (status != DSA_COMP_NONE) {
> +            error_report("DSA opcode %d failed with status = %d.",
> +                    opcode, status);
> +            return 1;
> +        }
> +        retry++;
> +        if (retry > max_retry_count) {
> +            error_report("DSA wait for completion retry %lu times.", retry);
> +            return 1;
> +        }
> +        _mm_pause();
> +    }
> +
> +    return 0;
> +}
> +
> +/**
> + * @brief Complete a single DSA task in the batch task.
> + *
> + * @param task A pointer to the batch task structure.
> + *
> + * @return Zero if successful, otherwise non-zero.
> + */
> +static int
> +poll_task_completion(QemuDsaBatchTask *task)
> +{
> +    assert(task->task_type == QEMU_DSA_TASK);
> +
> +    struct dsa_completion_record *completion = &task->completions[0];
> +    uint8_t status;
> +    int ret;
> +
> +    ret = poll_completion(completion, task->descriptors[0].opcode);
> +    if (ret != 0) {
> +        goto exit;
> +    }
> +
> +    status = completion->status;
> +    if (status == DSA_COMP_SUCCESS) {
> +        task->results[0] = (completion->result == 0);
> +        goto exit;
> +    }
> +
> +    assert(status == DSA_COMP_PAGE_FAULT_NOBOF);
> +
> +exit:
> +    return ret;
> +}
> +
> +/**
> + * @brief Poll a batch task status until it completes. If DSA task doesn't
> + *        complete properly, use CPU to complete the task.
> + *
> + * @param batch_task A pointer to the DSA batch task.
> + *
> + * @return Zero if successful, otherwise non-zero.
> + */
> +static int
> +poll_batch_task_completion(QemuDsaBatchTask *batch_task)
> +{
> +    struct dsa_completion_record *batch_completion =
> +        &batch_task->batch_completion;
> +    struct dsa_completion_record *completion;
> +    uint8_t batch_status;
> +    uint8_t status;
> +    bool *results = batch_task->results;
> +    uint32_t count = batch_task->batch_descriptor.desc_count;
> +    int ret;
> +
> +    ret = poll_completion(batch_completion,
> +                          batch_task->batch_descriptor.opcode);
> +    if (ret != 0) {
> +        goto exit;
> +    }
> +
> +    batch_status = batch_completion->status;
> +
> +    if (batch_status == DSA_COMP_SUCCESS) {
> +        if (batch_completion->bytes_completed == count) {
> +            /*
> +             * Let's skip checking for each descriptors' completion status
> +             * if the batch descriptor says all succedded.
> +             */
> +            for (int i = 0; i < count; i++) {
> +                assert(batch_task->completions[i].status == 
> DSA_COMP_SUCCESS);
> +                results[i] = (batch_task->completions[i].result == 0);
> +            }
> +            goto exit;
> +        }
> +    } else {
> +        assert(batch_status == DSA_COMP_BATCH_FAIL ||
> +            batch_status == DSA_COMP_BATCH_PAGE_FAULT);
> +    }
> +
> +    for (int i = 0; i < count; i++) {
> +
> +        completion = &batch_task->completions[i];
> +        status = completion->status;
> +
> +        if (status == DSA_COMP_SUCCESS) {
> +            results[i] = (completion->result == 0);
> +            continue;
> +        }
> +
> +        assert(status == DSA_COMP_PAGE_FAULT_NOBOF);
> +
> +        if (status != DSA_COMP_PAGE_FAULT_NOBOF) {
> +            error_report("Unexpected DSA completion status = %u.", status);

Unreachable with the assert above.

With that fixed:

Reviewed-by: Fabiano Rosas <farosas@suse.de>