diff mbox series

[v5,04/13] util/dsa: Implement DSA task enqueue and dequeue.

Message ID 20240711215244.19237-5-yichen.wang@bytedance.com (mailing list archive)
State New, archived
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>

* Use a safe thread queue for DSA task enqueue/dequeue.
* Implement DSA task submission.
* Implement DSA batch task submission.

Signed-off-by: Hao Xiang <hao.xiang@linux.dev>
Signed-off-by: Yichen Wang <yichen.wang@bytedance.com>
---
 include/qemu/dsa.h |  46 ++++++++++
 util/dsa.c         | 222 ++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 246 insertions(+), 22 deletions(-)
diff mbox series

Patch

diff --git a/include/qemu/dsa.h b/include/qemu/dsa.h
index 29b60654e9..9cc836b64c 100644
--- a/include/qemu/dsa.h
+++ b/include/qemu/dsa.h
@@ -27,6 +27,52 @@ 
 #include <linux/idxd.h>
 #include "x86intrin.h"
 
+typedef enum QemuDsaTaskType {
+    QEMU_DSA_TASK = 0,
+    QEMU_DSA_BATCH_TASK
+} QemuDsaTaskType;
+
+typedef enum QemuDsaTaskStatus {
+    QEMU_DSA_TASK_READY = 0,
+    QEMU_DSA_TASK_PROCESSING,
+    QEMU_DSA_TASK_COMPLETION
+} QemuDsaTaskStatus;
+
+typedef struct {
+    void *work_queue;
+} QemuDsaDevice;
+
+typedef QSIMPLEQ_HEAD(QemuDsaTaskQueue, QemuDsaBatchTask) QemuDsaTaskQueue;
+
+typedef struct {
+    QemuDsaDevice *dsa_devices;
+    int num_dsa_devices;
+    /* The index of the next DSA device to be used. */
+    uint32_t device_allocator_index;
+    bool running;
+    QemuMutex task_queue_lock;
+    QemuCond task_queue_cond;
+    QemuDsaTaskQueue task_queue;
+} QemuDsaDeviceGroup;
+
+typedef void (*qemu_dsa_completion_fn)(void *);
+
+typedef struct QemuDsaBatchTask {
+    struct dsa_hw_desc batch_descriptor;
+    struct dsa_hw_desc *descriptors;
+    struct dsa_completion_record batch_completion __attribute__((aligned(32)));
+    struct dsa_completion_record *completions;
+    QemuDsaDeviceGroup *group;
+    QemuDsaDevice *device;
+    qemu_dsa_completion_fn completion_callback;
+    QemuSemaphore sem_task_complete;
+    QemuDsaTaskType task_type;
+    QemuDsaTaskStatus status;
+    int batch_size;
+    QSIMPLEQ_ENTRY(QemuDsaBatchTask) entry;
+} QemuDsaBatchTask;
+
+
 /**
  * @brief Initializes DSA devices.
  *
diff --git a/util/dsa.c b/util/dsa.c
index cdb0b9dda2..43280b31cd 100644
--- a/util/dsa.c
+++ b/util/dsa.c
@@ -30,27 +30,11 @@ 
 #include <linux/idxd.h>
 #include "x86intrin.h"
 
-#define DSA_WQ_SIZE 4096
+#define DSA_WQ_PORTAL_SIZE 4096
+#define DSA_WQ_DEPTH 128
 #define MAX_DSA_DEVICES 16
 
-typedef QSIMPLEQ_HEAD(dsa_task_queue, dsa_batch_task) dsa_task_queue;
-
-typedef struct {
-    void *work_queue;
-} QemuDsaDevice;
-
-typedef struct {
-    QemuDsaDevice *dsa_devices;
-    int num_dsa_devices;
-    /* The index of the next DSA device to be used. */
-    uint32_t device_allocator_index;
-    bool running;
-    QemuMutex task_queue_lock;
-    QemuCond task_queue_cond;
-    dsa_task_queue task_queue;
-} QemuDsaDeviceGroup;
-
-uint64_t max_retry_count;
+uint32_t max_retry_count;
 static QemuDsaDeviceGroup dsa_group;
 
 
@@ -73,7 +57,7 @@  map_dsa_device(const char *dsa_wq_path)
                 dsa_wq_path, errno);
         return MAP_FAILED;
     }
-    dsa_device = mmap(NULL, DSA_WQ_SIZE, PROT_WRITE,
+    dsa_device = mmap(NULL, DSA_WQ_PORTAL_SIZE, PROT_WRITE,
                       MAP_SHARED | MAP_POPULATE, fd, 0);
     close(fd);
     if (dsa_device == MAP_FAILED) {
@@ -105,7 +89,7 @@  static void
 dsa_device_cleanup(QemuDsaDevice *instance)
 {
     if (instance->work_queue != MAP_FAILED) {
-        munmap(instance->work_queue, DSA_WQ_SIZE);
+        munmap(instance->work_queue, DSA_WQ_PORTAL_SIZE);
     }
 }
 
@@ -233,6 +217,198 @@  dsa_device_group_get_next_device(QemuDsaDeviceGroup *group)
     return &group->dsa_devices[current];
 }
 
+/**
+ * @brief Empties out the DSA task queue.
+ *
+ * @param group A pointer to the DSA device group.
+ */
+static void
+dsa_empty_task_queue(QemuDsaDeviceGroup *group)
+{
+    qemu_mutex_lock(&group->task_queue_lock);
+    QemuDsaTaskQueue *task_queue = &group->task_queue;
+    while (!QSIMPLEQ_EMPTY(task_queue)) {
+        QSIMPLEQ_REMOVE_HEAD(task_queue, entry);
+    }
+    qemu_mutex_unlock(&group->task_queue_lock);
+}
+
+/**
+ * @brief Adds a task to the DSA task queue.
+ *
+ * @param group A pointer to the DSA device group.
+ * @param task A pointer to the DSA task to enqueue.
+ *
+ * @return int Zero if successful, otherwise a proper error code.
+ */
+static int
+dsa_task_enqueue(QemuDsaDeviceGroup *group,
+                 QemuDsaBatchTask *task)
+{
+    bool notify = false;
+
+    qemu_mutex_lock(&group->task_queue_lock);
+
+    if (!group->running) {
+        error_report("DSA: Tried to queue task to stopped device queue.");
+        qemu_mutex_unlock(&group->task_queue_lock);
+        return -1;
+    }
+
+    /* The queue is empty. This enqueue operation is a 0->1 transition. */
+    if (QSIMPLEQ_EMPTY(&group->task_queue)) {
+        notify = true;
+    }
+
+    QSIMPLEQ_INSERT_TAIL(&group->task_queue, task, entry);
+
+    /* We need to notify the waiter for 0->1 transitions. */
+    if (notify) {
+        qemu_cond_signal(&group->task_queue_cond);
+    }
+
+    qemu_mutex_unlock(&group->task_queue_lock);
+
+    return 0;
+}
+
+/**
+ * @brief Takes a DSA task out of the task queue.
+ *
+ * @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)
+{
+    QemuDsaBatchTask *task = NULL;
+
+    qemu_mutex_lock(&group->task_queue_lock);
+
+    while (true) {
+        if (!group->running) {
+            goto exit;
+        }
+        task = QSIMPLEQ_FIRST(&group->task_queue);
+        if (task != NULL) {
+            break;
+        }
+        qemu_cond_wait(&group->task_queue_cond, &group->task_queue_lock);
+    }
+
+    QSIMPLEQ_REMOVE_HEAD(&group->task_queue, entry);
+
+exit:
+    qemu_mutex_unlock(&group->task_queue_lock);
+    return task;
+}
+
+/**
+ * @brief 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 Zero if successful, non-zero otherwise.
+ */
+static int
+submit_wi_int(void *wq, struct dsa_hw_desc *descriptor)
+{
+    uint32_t retry = 0;
+
+    _mm_sfence();
+
+    while (true) {
+        if (_enqcmd(wq, descriptor) == 0) {
+            break;
+        }
+        retry++;
+        if (retry > max_retry_count) {
+            error_report("Submit work retry %u times.", retry);
+            return -1;
+        }
+    }
+
+    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.
+ *
+ * @param task A pointer to the task.
+ *
+ * @return int Zero if successful, non-zero otherwise.
+ */
+__attribute__((unused))
+static int
+submit_wi_async(QemuDsaBatchTask *task)
+{
+    QemuDsaDeviceGroup *device_group = task->group;
+    QemuDsaDevice *device_instance = task->device;
+    int ret;
+
+    assert(task->task_type == QEMU_DSA_TASK);
+
+    task->status = QEMU_DSA_TASK_PROCESSING;
+
+    ret = submit_wi_int(device_instance->work_queue,
+                        &task->descriptors[0]);
+    if (ret != 0) {
+        return ret;
+    }
+
+    return dsa_task_enqueue(device_group, task);
+}
+
+/**
+ * @brief Asynchronously submits a DSA batch work item to the
+ *        device work queue.
+ *
+ * @param batch_task A pointer to the batch task.
+ *
+ * @return int Zero if successful, non-zero otherwise.
+ */
+__attribute__((unused))
+static int
+submit_batch_wi_async(QemuDsaBatchTask *batch_task)
+{
+    QemuDsaDeviceGroup *device_group = batch_task->group;
+    QemuDsaDevice *device_instance = batch_task->device;
+    int ret;
+
+    assert(batch_task->task_type == QEMU_DSA_BATCH_TASK);
+    assert(batch_task->batch_descriptor.desc_count <= batch_task->batch_size);
+    assert(batch_task->status == QEMU_DSA_TASK_READY);
+
+    batch_task->status = QEMU_DSA_TASK_PROCESSING;
+
+    ret = submit_wi_int(device_instance->work_queue,
+                        &batch_task->batch_descriptor);
+    if (ret != 0) {
+        return ret;
+    }
+
+    return dsa_task_enqueue(device_group, batch_task);
+}
+
 /**
  * @brief Check if DSA is running.
  *
@@ -246,7 +422,7 @@  bool qemu_dsa_is_running(void)
 static void
 dsa_globals_init(void)
 {
-    max_retry_count = UINT64_MAX;
+    max_retry_count = DSA_WQ_DEPTH;
 }
 
 /**
@@ -289,6 +465,8 @@  void qemu_dsa_stop(void)
     if (!group->running) {
         return;
     }
+
+    dsa_empty_task_queue(group);
 }
 
 /**