diff mbox series

[v5,05/13] util/dsa: Implement DSA task asynchronous completion thread model.

Message ID 20240711215244.19237-6-yichen.wang@bytedance.com
State New
Headers show
Series WIP: Use Intel DSA accelerator to offload zero page checking in multifd live migration. | expand

Commit Message

Yichen Wang July 11, 2024, 9:52 p.m. UTC
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 mbox series

Patch

diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
index 9cc836b64c..d46a9f42a5 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 43280b31cd..1eb85f37f1 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;
 
 
 /**
@@ -409,6 +420,265 @@  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);
+            ret = 1;
+            goto exit;
+        }
+    }
+
+exit:
+    return ret;
+}
+
+/**
+ * @brief Handles an asynchronous DSA batch task completion.
+ *
+ * @param task A pointer to the batch buffer zero task structure.
+ */
+static void
+dsa_batch_task_complete(QemuDsaBatchTask *batch_task)
+{
+    batch_task->status = QEMU_DSA_TASK_COMPLETION;
+    batch_task->completion_callback(batch_task);
+}
+
+/**
+ * @brief The function entry point called by a dedicated DSA
+ *        work item completion thread.
+ *
+ * @param opaque A pointer to the thread context.
+ *
+ * @return void* Not used.
+ */
+static void *
+dsa_completion_loop(void *opaque)
+{
+    QemuDsaCompletionThread *thread_context =
+        (QemuDsaCompletionThread *)opaque;
+    QemuDsaBatchTask *batch_task;
+    QemuDsaDeviceGroup *group = thread_context->group;
+    int ret;
+
+    rcu_register_thread();
+
+    thread_context->thread_id = qemu_get_thread_id();
+    qemu_sem_post(&thread_context->sem_init_done);
+
+    while (thread_context->running) {
+        batch_task = dsa_task_dequeue(group);
+        assert(batch_task != NULL || !group->running);
+        if (!group->running) {
+            assert(!thread_context->running);
+            break;
+        }
+        if (batch_task->task_type == QEMU_DSA_TASK) {
+            ret = poll_task_completion(batch_task);
+        } else {
+            assert(batch_task->task_type == QEMU_DSA_BATCH_TASK);
+            ret = poll_batch_task_completion(batch_task);
+        }
+
+        if (ret != 0) {
+            goto exit;
+        }
+
+        dsa_batch_task_complete(batch_task);
+    }
+
+exit:
+    if (ret != 0) {
+        error_report("DSA completion thread exited due to internal error.");
+    }
+    rcu_unregister_thread();
+    return NULL;
+}
+
+/**
+ * @brief Initializes a DSA completion thread.
+ *
+ * @param completion_thread A pointer to the completion thread context.
+ * @param group A pointer to the DSA device group.
+ */
+static void
+dsa_completion_thread_init(
+    QemuDsaCompletionThread *completion_thread,
+    QemuDsaDeviceGroup *group)
+{
+    completion_thread->stopping = false;
+    completion_thread->running = true;
+    completion_thread->thread_id = -1;
+    qemu_sem_init(&completion_thread->sem_init_done, 0);
+    completion_thread->group = group;
+
+    qemu_thread_create(&completion_thread->thread,
+                       DSA_COMPLETION_THREAD,
+                       dsa_completion_loop,
+                       completion_thread,
+                       QEMU_THREAD_JOINABLE);
+
+    /* Wait for initialization to complete */
+    qemu_sem_wait(&completion_thread->sem_init_done);
+}
+
+/**
+ * @brief Stops the completion thread (and implicitly, the device group).
+ *
+ * @param opaque A pointer to the completion thread.
+ */
+static void dsa_completion_thread_stop(void *opaque)
+{
+    QemuDsaCompletionThread *thread_context =
+        (QemuDsaCompletionThread *)opaque;
+
+    QemuDsaDeviceGroup *group = thread_context->group;
+
+    qemu_mutex_lock(&group->task_queue_lock);
+
+    thread_context->stopping = true;
+    thread_context->running = false;
+
+    /* Prevent the compiler from setting group->running first. */
+    barrier();
+    dsa_device_group_stop(group);
+
+    qemu_cond_signal(&group->task_queue_cond);
+    qemu_mutex_unlock(&group->task_queue_lock);
+
+    qemu_thread_join(&thread_context->thread);
+
+    qemu_sem_destroy(&thread_context->sem_init_done);
+}
+
 /**
  * @brief Check if DSA is running.
  *
@@ -416,7 +686,7 @@  submit_batch_wi_async(QemuDsaBatchTask *batch_task)
  */
 bool qemu_dsa_is_running(void)
 {
-    return false;
+    return completion_thread.running;
 }
 
 static void
@@ -452,6 +722,7 @@  void qemu_dsa_start(void)
         return;
     }
     dsa_device_group_start(&dsa_group);
+    dsa_completion_thread_init(&completion_thread, &dsa_group);
 }
 
 /**
@@ -466,6 +737,7 @@  void qemu_dsa_stop(void)
         return;
     }
 
+    dsa_completion_thread_stop(&completion_thread);
     dsa_empty_task_queue(group);
 }