[PATCH v6 07/12] util/dsa: Implement DSA task asynchronous submission and wait for completion.

[Yichen Wang <yichen.wang@bytedance.com>]

From: Hao Xiang <hao.xiang@linux.dev>

* Add a DSA task completion callback.
* DSA completion thread will call the tasks's completion callback
on every task/batch task completion.
* DSA submission path to wait for completion.
* Implement CPU fallback if DSA is not able to complete the task.

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 |  14 +++++
 util/dsa.c         | 125 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 135 insertions(+), 4 deletions(-)

diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
index 89841a6ffa..a3b502ee41 100644
--- a/include/qemu/dsa.h
+++ b/include/qemu/dsa.h
@@ -123,6 +123,20 @@ buffer_zero_batch_task_init(int batch_size);
  */
 void buffer_zero_batch_task_destroy(QemuDsaBatchTask *task);
 
+/**
+ * @brief Performs buffer zero comparison on a DSA batch task synchronously.
+ *
+ * @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 buffer length.
+ *
+ * @return Zero if successful, otherwise non-zero.
+ */
+int
+buffer_is_zero_dsa_batch_sync(QemuDsaBatchTask *batch_task,
+                              const void **buf, size_t count, size_t len);
+
 #else
 
 typedef struct QemuDsaBatchTask {} QemuDsaBatchTask;
diff --git a/util/dsa.c b/util/dsa.c
index d9c066ff00..cbaa47c360 100644
--- a/util/dsa.c
+++ b/util/dsa.c
@@ -435,6 +435,42 @@ poll_completion(struct dsa_completion_record *completion,
     return 0;
 }
 
+/**
+ * @brief Helper function to use CPU to complete a single
+ *        zero page checking task.
+ *
+ * @param completion A pointer to a DSA task completion record.
+ * @param descriptor A pointer to a DSA task descriptor.
+ * @param result A pointer to the result of a zero page checking.
+ */
+static void
+task_cpu_fallback_int(struct dsa_completion_record *completion,
+                      struct dsa_hw_desc *descriptor, bool *result)
+{
+    const uint8_t *buf;
+    size_t len;
+
+    if (completion->status == DSA_COMP_SUCCESS) {
+        return;
+    }
+
+    /*
+     * DSA was able to partially complete the operation. Check the
+     * result. If we already know this is not a zero page, we can
+     * return now.
+     */
+    if (completion->bytes_completed != 0 && completion->result != 0) {
+        *result = false;
+        return;
+    }
+
+    /* Let's fallback to use CPU to complete it. */
+    buf = (const uint8_t *)descriptor->src_addr;
+    len = descriptor->xfer_size;
+    *result = buffer_is_zero(buf + completion->bytes_completed,
+                             len - completion->bytes_completed);
+}
+
 /**
  * @brief Complete a single DSA task in the batch task.
  *
@@ -563,7 +599,7 @@ dsa_completion_loop(void *opaque)
         (QemuDsaCompletionThread *)opaque;
     QemuDsaBatchTask *batch_task;
     QemuDsaDeviceGroup *group = thread_context->group;
-    int ret;
+    int ret = 0;
 
     rcu_register_thread();
 
@@ -831,7 +867,6 @@ buffer_zero_batch_task_set(QemuDsaBatchTask *batch_task,
  *
  * @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)
@@ -850,7 +885,6 @@ buffer_zero_dsa_async(QemuDsaBatchTask *task,
  * @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)
@@ -881,13 +915,61 @@ buffer_zero_dsa_completion(void *context)
  *
  * @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 Use CPU to complete the zero page checking task if DSA
+ *        is not able to complete it.
+ *
+ * @param batch_task A pointer to the batch task.
+ */
+static void
+buffer_zero_cpu_fallback(QemuDsaBatchTask *batch_task)
+{
+    if (batch_task->task_type == QEMU_DSA_TASK) {
+        if (batch_task->completions[0].status == DSA_COMP_SUCCESS) {
+            return;
+        }
+        task_cpu_fallback_int(&batch_task->completions[0],
+                              &batch_task->descriptors[0],
+                              &batch_task->results[0]);
+    } else if (batch_task->task_type == QEMU_DSA_BATCH_TASK) {
+        struct dsa_completion_record *batch_completion =
+            &batch_task->batch_completion;
+        struct dsa_completion_record *completion;
+        uint8_t status;
+        bool *results = batch_task->results;
+        uint32_t count = batch_task->batch_descriptor.desc_count;
+
+        /* DSA is able to complete the entire batch task. */
+        if (batch_completion->status == DSA_COMP_SUCCESS) {
+            assert(count == batch_completion->bytes_completed);
+            return;
+        }
+
+        /*
+         * DSA encounters some error and is not able to complete
+         * the entire batch task. Use CPU fallback.
+         */
+        for (int i = 0; i < count; i++) {
+
+            completion = &batch_task->completions[i];
+            status = completion->status;
+
+            assert(status == DSA_COMP_SUCCESS ||
+                status == DSA_COMP_PAGE_FAULT_NOBOF);
+
+            task_cpu_fallback_int(completion,
+                                  &batch_task->descriptors[i],
+                                  &results[i]);
+        }
+    }
+}
+
 /**
  * @brief Initializes a buffer zero comparison DSA task.
  *
@@ -964,3 +1046,38 @@ buffer_zero_batch_task_destroy(QemuDsaBatchTask *task)
     qemu_sem_destroy(&task->sem_task_complete);
     qemu_vfree(task);
 }
+
+/**
+ * @brief Performs buffer zero comparison on a DSA batch task synchronously.
+ *
+ * @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 buffer length.
+ *
+ * @return Zero if successful, otherwise non-zero.
+ */
+int
+buffer_is_zero_dsa_batch_sync(QemuDsaBatchTask *batch_task,
+                              const void **buf, size_t count, size_t len)
+{
+    if (count <= 0 || count > batch_task->batch_size) {
+        return -1;
+    }
+
+    assert(batch_task != NULL);
+    assert(len != 0);
+    assert(buf != NULL);
+
+    if (count == 1) {
+        /* DSA doesn't take batch operation with only 1 task. */
+        buffer_zero_dsa_async(batch_task, buf[0], len);
+    } else {
+        buffer_zero_dsa_batch_async(batch_task, buf, count, len);
+    }
+
+    buffer_zero_dsa_wait(batch_task);
+    buffer_zero_cpu_fallback(batch_task);
+
+    return 0;
+}
-- 
Yichen Wang