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 |  18 ++++
 util/dsa.c         | 247 +++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 244 insertions(+), 21 deletions(-)

diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
index d46a9f42a5..1b4baf1c80 100644
--- a/include/qemu/dsa.h
+++ b/include/qemu/dsa.h
@@ -105,6 +105,24 @@ void qemu_dsa_cleanup(void);
  */
 bool qemu_dsa_is_running(void);
 
+/**
+ * @brief Initializes a buffer zero batch task.
+ *
+ * @param task A pointer to the batch task to initialize.
+ * @param results A pointer to an array of zero page checking results.
+ * @param batch_size The number of DSA tasks in the batch.
+ */
+void
+buffer_zero_batch_task_init(QemuDsaBatchTask *task,
+                            bool *results, 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
 
 static inline bool qemu_dsa_is_running(void)
diff --git a/util/dsa.c b/util/dsa.c
index 1eb85f37f1..f0d8cce210 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
@@ -180,7 +181,6 @@ 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)
 {
@@ -216,7 +216,6 @@ 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)
 {
@@ -289,7 +288,6 @@ 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)
 {
@@ -344,22 +342,6 @@ 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);
-}
-
 /**
  * @brief Asynchronously submits a DSA work item to the
  *        device work queue.
@@ -368,7 +350,6 @@ 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)
 {
@@ -397,7 +378,6 @@ submit_wi_async(QemuDsaBatchTask *task)
  *
  * @return int Zero if successful, non-zero otherwise.
  */
-__attribute__((unused))
 static int
 submit_batch_wi_async(QemuDsaBatchTask *batch_task)
 {
@@ -679,6 +659,231 @@ static void dsa_completion_thread_stop(void *opaque)
     qemu_sem_destroy(&thread_context->sem_init_done);
 }
 
+/**
+ * @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 batch task.
+ *
+ * @param task A pointer to the batch task to initialize.
+ * @param results A pointer to an array of zero page checking results.
+ * @param batch_size The number of DSA tasks in the batch.
+ */
+void
+buffer_zero_batch_task_init(QemuDsaBatchTask *task,
+                            bool *results, int batch_size)
+{
+    int descriptors_size = sizeof(*task->descriptors) * batch_size;
+    memset(task, 0, sizeof(*task));
+
+    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->results = results;
+    task->batch_size = 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;
+}
+
+/**
+ * @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)
+{
+    qemu_vfree(task->descriptors);
+    qemu_vfree(task->completions);
+    task->results = NULL;
+
+    qemu_sem_destroy(&task->sem_task_complete);
+}
+
+/**
+ * @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 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 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 Check if DSA is running.
  *
-- 
Yichen Wang