Re: [PATCH v7 06/12] util/dsa: Implement zero page checking in DSA task.

[Fabiano Rosas <farosas@suse.de>]

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

> From: Hao Xiang <hao.xiang@linux.dev>
>
> Create DSA task with operation code DSA_OPCODE_COMPVAL.
> Here we create two types of DSA tasks, a single DSA task and
> a batch DSA task. Batch DSA task reduces task submission overhead
> and hence should be the default option. However, due to the way DSA
> hardware works, a DSA batch task must contain at least two individual
> tasks. There are times we need to submit a single task and hence a
> single DSA task submission is also required.
>
> Signed-off-by: Hao Xiang <hao.xiang@linux.dev>
> Signed-off-by: Bryan Zhang <bryan.zhang@bytedance.com>
> Signed-off-by: Yichen Wang <yichen.wang@bytedance.com>
> ---
>  include/qemu/dsa.h |  44 ++++++--
>  util/dsa.c         | 254 +++++++++++++++++++++++++++++++++++++++++----
>  2 files changed, 269 insertions(+), 29 deletions(-)
>
> diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
> index d24567f0be..cb407b8b49 100644
> --- a/include/qemu/dsa.h
> +++ b/include/qemu/dsa.h
> @@ -16,6 +16,7 @@
>  #define QEMU_DSA_H
>  
>  #include "qapi/error.h"
> +#include "exec/cpu-common.h"
>  #include "qemu/thread.h"
>  #include "qemu/queue.h"
>  
> @@ -70,10 +71,11 @@ typedef struct QemuDsaBatchTask {
>      QemuDsaTaskStatus status;
>      int batch_size;
>      bool *results;
> +    /* Address of each pages in pages */
> +    ram_addr_t *addr;
>      QSIMPLEQ_ENTRY(QemuDsaBatchTask) entry;
>  } QemuDsaBatchTask;
>  
> -
>  /**
>   * @brief Initializes DSA devices.
>   *
> @@ -105,8 +107,26 @@ void qemu_dsa_cleanup(void);
>   */
>  bool qemu_dsa_is_running(void);
>  
> +/**
> + * @brief Initializes a buffer zero DSA batch task.
> + *
> + * @param batch_size The number of zero page checking tasks in the batch.
> + * @return A pointer to the zero page checking tasks initialized.
> + */
> +QemuDsaBatchTask *
> +buffer_zero_batch_task_init(int batch_size);
> +
> +/**
> + * @brief Performs the proper cleanup on a DSA batch task.
> + *
> + * @param task A pointer to the batch task to cleanup.
> + */
> +void buffer_zero_batch_task_destroy(QemuDsaBatchTask *task);
> +
>  #else
>  
> +typedef struct QemuDsaBatchTask {} QemuDsaBatchTask;
> +
>  static inline bool qemu_dsa_is_running(void)
>  {
>      return false;
> @@ -114,19 +134,27 @@ static inline bool qemu_dsa_is_running(void)
>  
>  static inline int qemu_dsa_init(const strList *dsa_parameter, Error **errp)
>  {
> -    if (dsa_parameter != NULL && strlen(dsa_parameter) != 0) {
> -        error_setg(errp, "DSA is not supported.");
> -        return -1;
> -    }
> -
> -    return 0;
> +    error_setg(errp, "DSA accelerator is not enabled.");
> +    return -1;

This should have been fixed in the patch that introduced this function.

>  }
>  
>  static inline void qemu_dsa_start(void) {}
>  
>  static inline void qemu_dsa_stop(void) {}
>  
> -static inline void qemu_dsa_cleanup(void) {}

Where did this go?

> +static inline QemuDsaBatchTask *buffer_zero_batch_task_init(int batch_size)
> +{
> +    return NULL;
> +}
> +
> +static inline void buffer_zero_batch_task_destroy(QemuDsaBatchTask *task) {}
> +
> +static inline int
> +buffer_is_zero_dsa_batch_sync(QemuDsaBatchTask *batch_task,
> +                              const void **buf, size_t count, size_t len)
> +{
> +    return -1;
> +}
>  
>  #endif
>  
> diff --git a/util/dsa.c b/util/dsa.c
> index c3ca71df86..408c163195 100644
> --- a/util/dsa.c
> +++ b/util/dsa.c
> @@ -48,6 +48,7 @@ uint32_t max_retry_count;
>  static QemuDsaDeviceGroup dsa_group;
>  static QemuDsaCompletionThread completion_thread;
>  
> +static void buffer_zero_dsa_completion(void *context);
>  
>  /**
>   * @brief This function opens a DSA device's work queue and
> @@ -174,7 +175,6 @@ dsa_device_group_start(QemuDsaDeviceGroup *group)
>   *
>   * @param group A pointer to the DSA device group.
>   */
> -__attribute__((unused))
>  static void
>  dsa_device_group_stop(QemuDsaDeviceGroup *group)
>  {
> @@ -210,7 +210,6 @@ dsa_device_group_cleanup(QemuDsaDeviceGroup *group)
>   * @return struct QemuDsaDevice* A pointer to the next available DSA device
>   *         in the group.
>   */
> -__attribute__((unused))
>  static QemuDsaDevice *
>  dsa_device_group_get_next_device(QemuDsaDeviceGroup *group)
>  {
> @@ -283,7 +282,6 @@ dsa_task_enqueue(QemuDsaDeviceGroup *group,
>   * @param group A pointer to the DSA device group.
>   * @return QemuDsaBatchTask* The DSA task being dequeued.
>   */
> -__attribute__((unused))
>  static QemuDsaBatchTask *
>  dsa_task_dequeue(QemuDsaDeviceGroup *group)
>  {
> @@ -338,22 +336,6 @@ submit_wi_int(void *wq, struct dsa_hw_desc *descriptor)
>      return 0;
>  }
>  
> -/**
> - * @brief Synchronously submits a DSA work item to the
> - *        device work queue.
> - *
> - * @param wq A pointer to the DSA work queue's device memory.
> - * @param descriptor A pointer to the DSA work item descriptor.
> - *
> - * @return int Zero if successful, non-zero otherwise.
> - */
> -__attribute__((unused))
> -static int
> -submit_wi(void *wq, struct dsa_hw_desc *descriptor)
> -{
> -    return submit_wi_int(wq, descriptor);
> -}
> -

Why is this being removed?

>  /**
>   * @brief Asynchronously submits a DSA work item to the
>   *        device work queue.
> @@ -362,7 +344,6 @@ submit_wi(void *wq, struct dsa_hw_desc *descriptor)
>   *
>   * @return int Zero if successful, non-zero otherwise.
>   */
> -__attribute__((unused))
>  static int
>  submit_wi_async(QemuDsaBatchTask *task)
>  {
> @@ -391,7 +372,6 @@ submit_wi_async(QemuDsaBatchTask *task)
>   *
>   * @return int Zero if successful, non-zero otherwise.
>   */
> -__attribute__((unused))
>  static int
>  submit_batch_wi_async(QemuDsaBatchTask *batch_task)
>  {
> @@ -750,3 +730,235 @@ void qemu_dsa_cleanup(void)
>      dsa_device_group_cleanup(&dsa_group);
>  }
>  
> +
> +/* Buffer zero comparison DSA task implementations */
> +/* =============================================== */
> +
> +/**
> + * @brief Sets a buffer zero comparison DSA task.
> + *
> + * @param descriptor A pointer to the DSA task descriptor.
> + * @param buf A pointer to the memory buffer.
> + * @param len The length of the buffer.
> + */
> +static void
> +buffer_zero_task_set_int(struct dsa_hw_desc *descriptor,
> +                         const void *buf,
> +                         size_t len)
> +{
> +    struct dsa_completion_record *completion =
> +        (struct dsa_completion_record *)descriptor->completion_addr;
> +
> +    descriptor->xfer_size = len;
> +    descriptor->src_addr = (uintptr_t)buf;
> +    completion->status = 0;
> +    completion->result = 0;
> +}
> +
> +/**
> + * @brief Resets a buffer zero comparison DSA batch task.
> + *
> + * @param task A pointer to the DSA batch task.
> + */
> +static void
> +buffer_zero_task_reset(QemuDsaBatchTask *task)
> +{
> +    task->completions[0].status = DSA_COMP_NONE;
> +    task->task_type = QEMU_DSA_TASK;
> +    task->status = QEMU_DSA_TASK_READY;
> +}
> +
> +/**
> + * @brief Resets a buffer zero comparison DSA batch task.
> + *
> + * @param task A pointer to the batch task.
> + * @param count The number of DSA tasks this batch task will contain.
> + */
> +static void
> +buffer_zero_batch_task_reset(QemuDsaBatchTask *task, size_t count)
> +{
> +    task->batch_completion.status = DSA_COMP_NONE;
> +    task->batch_descriptor.desc_count = count;
> +    task->task_type = QEMU_DSA_BATCH_TASK;
> +    task->status = QEMU_DSA_TASK_READY;
> +}
> +
> +/**
> + * @brief Sets a buffer zero comparison DSA task.
> + *
> + * @param task A pointer to the DSA task.
> + * @param buf A pointer to the memory buffer.
> + * @param len The buffer length.
> + */
> +static void
> +buffer_zero_task_set(QemuDsaBatchTask *task,
> +                     const void *buf,
> +                     size_t len)
> +{
> +    buffer_zero_task_reset(task);
> +    buffer_zero_task_set_int(&task->descriptors[0], buf, len);
> +}
> +
> +/**
> + * @brief Sets a buffer zero comparison batch task.
> + *
> + * @param batch_task A pointer to the batch task.
> + * @param buf An array of memory buffers.
> + * @param count The number of buffers in the array.
> + * @param len The length of the buffers.
> + */
> +static void
> +buffer_zero_batch_task_set(QemuDsaBatchTask *batch_task,
> +                           const void **buf, size_t count, size_t len)
> +{
> +    assert(count > 0);
> +    assert(count <= batch_task->batch_size);
> +
> +    buffer_zero_batch_task_reset(batch_task, count);
> +    for (int i = 0; i < count; i++) {
> +        buffer_zero_task_set_int(&batch_task->descriptors[i], buf[i], len);
> +    }
> +}
> +
> +/**
> + * @brief Asychronously perform a buffer zero DSA operation.
> + *
> + * @param task A pointer to the batch task structure.
> + * @param buf A pointer to the memory buffer.
> + * @param len The length of the memory buffer.
> + *
> + * @return int Zero if successful, otherwise an appropriate error code.
> + */
> +__attribute__((unused))
> +static int
> +buffer_zero_dsa_async(QemuDsaBatchTask *task,
> +                      const void *buf, size_t len)
> +{
> +    buffer_zero_task_set(task, buf, len);
> +
> +    return submit_wi_async(task);
> +}
> +
> +/**
> + * @brief Sends a memory comparison batch task to a DSA device and wait
> + *        for completion.
> + *
> + * @param batch_task The batch task to be submitted to DSA device.
> + * @param buf An array of memory buffers to check for zero.
> + * @param count The number of buffers.
> + * @param len The buffer length.
> + */
> +__attribute__((unused))
> +static int
> +buffer_zero_dsa_batch_async(QemuDsaBatchTask *batch_task,
> +                            const void **buf, size_t count, size_t len)
> +{
> +    assert(count <= batch_task->batch_size);
> +    buffer_zero_batch_task_set(batch_task, buf, count, len);
> +
> +    return submit_batch_wi_async(batch_task);
> +}
> +
> +/**
> + * @brief The completion callback function for buffer zero
> + *        comparison DSA task completion.
> + *
> + * @param context A pointer to the callback context.
> + */
> +static void
> +buffer_zero_dsa_completion(void *context)
> +{
> +    assert(context != NULL);
> +
> +    QemuDsaBatchTask *task = (QemuDsaBatchTask *)context;
> +    qemu_sem_post(&task->sem_task_complete);
> +}
> +
> +/**
> + * @brief Wait for the asynchronous DSA task to complete.
> + *
> + * @param batch_task A pointer to the buffer zero comparison batch task.
> + */
> +__attribute__((unused))
> +static void
> +buffer_zero_dsa_wait(QemuDsaBatchTask *batch_task)
> +{
> +    qemu_sem_wait(&batch_task->sem_task_complete);
> +}
> +
> +/**
> + * @brief Initializes a buffer zero comparison DSA task.
> + *
> + * @param descriptor A pointer to the DSA task descriptor.
> + * @param completion A pointer to the DSA task completion record.
> + */
> +static void
> +buffer_zero_task_init_int(struct dsa_hw_desc *descriptor,
> +                          struct dsa_completion_record *completion)
> +{
> +    descriptor->opcode = DSA_OPCODE_COMPVAL;
> +    descriptor->flags = IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CRAV;
> +    descriptor->comp_pattern = (uint64_t)0;
> +    descriptor->completion_addr = (uint64_t)completion;
> +}
> +
> +/**
> + * @brief Initializes a buffer zero DSA batch task.
> + *
> + * @param batch_size The number of zero page checking tasks in the batch.
> + * @return A pointer to the zero page checking tasks initialized.
> + */
> +QemuDsaBatchTask *
> +buffer_zero_batch_task_init(int batch_size)
> +{
> +    QemuDsaBatchTask *task = qemu_memalign(64, sizeof(QemuDsaBatchTask));
> +    int descriptors_size = sizeof(*task->descriptors) * batch_size;
> +
> +    memset(task, 0, sizeof(*task));
> +    task->addr = g_new0(ram_addr_t, batch_size);
> +    task->results = g_new0(bool, batch_size);
> +    task->batch_size = batch_size;
> +    task->descriptors =
> +        (struct dsa_hw_desc *)qemu_memalign(64, descriptors_size);
> +    memset(task->descriptors, 0, descriptors_size);
> +    task->completions = (struct dsa_completion_record *)qemu_memalign(
> +        32, sizeof(*task->completions) * batch_size);
> +
> +    task->batch_completion.status = DSA_COMP_NONE;
> +    task->batch_descriptor.completion_addr = (uint64_t)&task->batch_completion;
> +    /* TODO: Ensure that we never send a batch with count <= 1 */
> +    task->batch_descriptor.desc_count = 0;
> +    task->batch_descriptor.opcode = DSA_OPCODE_BATCH;
> +    task->batch_descriptor.flags = IDXD_OP_FLAG_RCR | IDXD_OP_FLAG_CRAV;
> +    task->batch_descriptor.desc_list_addr = (uintptr_t)task->descriptors;
> +    task->status = QEMU_DSA_TASK_READY;
> +    task->group = &dsa_group;
> +    task->device = dsa_device_group_get_next_device(&dsa_group);
> +
> +    for (int i = 0; i < task->batch_size; i++) {
> +        buffer_zero_task_init_int(&task->descriptors[i],
> +                                  &task->completions[i]);
> +    }
> +
> +    qemu_sem_init(&task->sem_task_complete, 0);
> +    task->completion_callback = buffer_zero_dsa_completion;
> +
> +    return task;
> +}
> +
> +/**
> + * @brief Performs the proper cleanup on a DSA batch task.
> + *
> + * @param task A pointer to the batch task to cleanup.
> + */
> +void
> +buffer_zero_batch_task_destroy(QemuDsaBatchTask *task)
> +{
> +    g_free(task->addr);
> +    g_free(task->results);
> +    qemu_vfree(task->descriptors);
> +    qemu_vfree(task->completions);
> +    task->results = NULL;
> +    qemu_sem_destroy(&task->sem_task_complete);
> +    qemu_vfree(task);
> +}