@@ -21,7 +21,9 @@
static bool multifd_zero_page_enabled(void)
{
- return migrate_zero_page_detection() == ZERO_PAGE_DETECTION_MULTIFD;
+ ZeroPageDetection curMethod = migrate_zero_page_detection();
+ return (curMethod == ZERO_PAGE_DETECTION_MULTIFD ||
+ curMethod == ZERO_PAGE_DETECTION_DSA_ACCEL);
}
static void swap_page_offset(ram_addr_t *pages_offset, int a, int b)
@@ -37,26 +39,49 @@ static void swap_page_offset(ram_addr_t *pages_offset, int a, int b)
pages_offset[b] = temp;
}
+#ifdef CONFIG_DSA_OPT
+
+static void swap_result(bool *results, int a, int b)
+{
+ bool temp;
+
+ if (a == b) {
+ return;
+ }
+
+ temp = results[a];
+ results[a] = results[b];
+ results[b] = temp;
+}
+
/**
- * multifd_send_zero_page_detect: Perform zero page detection on all pages.
+ * zero_page_detect_dsa: Perform zero page detection using
+ * Intel Data Streaming Accelerator (DSA).
*
- * Sorts normal pages before zero pages in p->pages->offset and updates
- * p->pages->normal_num.
+ * Sorts normal pages before zero pages in pages->offset and updates
+ * pages->normal_num.
*
* @param p A pointer to the send params.
*/
-void multifd_send_zero_page_detect(MultiFDSendParams *p)
+static void zero_page_detect_dsa(MultiFDSendParams *p)
{
MultiFDPages_t *pages = &p->data->u.ram;
RAMBlock *rb = pages->block;
- int i = 0;
- int j = pages->num - 1;
+ bool *results = p->dsa_batch_task->results;
- if (!multifd_zero_page_enabled()) {
- pages->normal_num = pages->num;
- goto out;
+ for (int i = 0; i < pages->num; i++) {
+ p->dsa_batch_task->addr[i] =
+ (ram_addr_t)(rb->host + pages->offset[i]);
}
+ buffer_is_zero_dsa_batch_sync(p->dsa_batch_task,
+ (const void **)p->dsa_batch_task->addr,
+ pages->num,
+ multifd_ram_page_size());
+
+ int i = 0;
+ int j = pages->num - 1;
+
/*
* Sort the page offset array by moving all normal pages to
* the left and all zero pages to the right of the array.
@@ -64,23 +89,39 @@ void multifd_send_zero_page_detect(MultiFDSendParams *p)
while (i <= j) {
uint64_t offset = pages->offset[i];
- if (!buffer_is_zero(rb->host + offset, multifd_ram_page_size())) {
+ if (!results[i]) {
i++;
continue;
}
+ swap_result(results, i, j);
swap_page_offset(pages->offset, i, j);
ram_release_page(rb->idstr, offset);
j--;
}
pages->normal_num = i;
+}
-out:
- stat64_add(&mig_stats.normal_pages, pages->normal_num);
- stat64_add(&mig_stats.zero_pages, pages->num - pages->normal_num);
+void multifd_dsa_cleanup(void)
+{
+ qemu_dsa_cleanup();
+}
+
+#else
+
+static void zero_page_detect_dsa(MultiFDSendParams *p)
+{
+ g_assert_not_reached();
+}
+
+void multifd_dsa_cleanup(void)
+{
+ return ;
}
+#endif
+
void multifd_recv_zero_page_process(MultiFDRecvParams *p)
{
for (int i = 0; i < p->zero_num; i++) {
@@ -92,3 +133,63 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p)
}
}
}
+
+/**
+ * zero_page_detect_cpu: Perform zero page detection using CPU.
+ *
+ * Sorts normal pages before zero pages in p->pages->offset and updates
+ * p->pages->normal_num.
+ *
+ * @param p A pointer to the send params.
+ */
+static void zero_page_detect_cpu(MultiFDSendParams *p)
+{
+ MultiFDPages_t *pages = &p->data->u.ram;
+ RAMBlock *rb = pages->block;
+ int i = 0;
+ int j = pages->num - 1;
+
+ /*
+ * Sort the page offset array by moving all normal pages to
+ * the left and all zero pages to the right of the array.
+ */
+ while (i <= j) {
+ uint64_t offset = pages->offset[i];
+
+ if (!buffer_is_zero(rb->host + offset, multifd_ram_page_size())) {
+ i++;
+ continue;
+ }
+
+ swap_page_offset(pages->offset, i, j);
+ ram_release_page(rb->idstr, offset);
+ j--;
+ }
+
+ pages->normal_num = i;
+}
+
+/**
+ * multifd_send_zero_page_detect: Perform zero page detection on all pages.
+ *
+ * @param p A pointer to the send params.
+ */
+void multifd_send_zero_page_detect(MultiFDSendParams *p)
+{
+ MultiFDPages_t *pages = &p->data->u.ram;
+
+ if (!multifd_zero_page_enabled()) {
+ pages->normal_num = pages->num;
+ goto out;
+ }
+
+ if (qemu_dsa_is_running()) {
+ zero_page_detect_dsa(p);
+ } else {
+ zero_page_detect_cpu(p);
+ }
+
+out:
+ stat64_add(&mig_stats.normal_pages, pages->normal_num);
+ stat64_add(&mig_stats.zero_pages, pages->num - pages->normal_num);
+}
@@ -13,6 +13,7 @@
#include "qemu/osdep.h"
#include "qemu/cutils.h"
#include "qemu/rcu.h"
+#include "qemu/dsa.h"
#include "exec/target_page.h"
#include "sysemu/sysemu.h"
#include "exec/ramblock.h"
@@ -462,6 +463,8 @@ static bool multifd_send_cleanup_channel(MultiFDSendParams *p, Error **errp)
p->name = NULL;
g_free(p->data);
p->data = NULL;
+ buffer_zero_batch_task_destroy(p->dsa_batch_task);
+ p->dsa_batch_task = NULL;
p->packet_len = 0;
g_free(p->packet);
p->packet = NULL;
@@ -493,6 +496,8 @@ void multifd_send_shutdown(void)
multifd_send_terminate_threads();
+ multifd_dsa_cleanup();
+
for (i = 0; i < migrate_multifd_channels(); i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
Error *local_err = NULL;
@@ -814,11 +819,31 @@ bool multifd_send_setup(void)
uint32_t page_count = multifd_ram_page_count();
bool use_packets = multifd_use_packets();
uint8_t i;
+ Error *local_err = NULL;
if (!migrate_multifd()) {
return true;
}
+ if (s &&
+ s->parameters.zero_page_detection == ZERO_PAGE_DETECTION_DSA_ACCEL) {
+ // Populate the dsa device path from accel-path
+ const strList *accel_path = migrate_accel_path();
+ g_autofree strList *dsa_parameter = g_malloc0(sizeof(strList));
+ strList **tail = &dsa_parameter;
+ while (accel_path) {
+ if (strncmp(accel_path->value, "dsa:", 4) == 0) {
+ QAPI_LIST_APPEND(tail, &accel_path->value[4]);
+ }
+ accel_path = accel_path->next;
+ }
+ if (qemu_dsa_init(dsa_parameter, &local_err)) {
+ ret = -1;
+ } else {
+ qemu_dsa_start();
+ }
+ }
+
thread_count = migrate_multifd_channels();
multifd_send_state = g_malloc0(sizeof(*multifd_send_state));
multifd_send_state->params = g_new0(MultiFDSendParams, thread_count);
@@ -829,12 +854,12 @@ bool multifd_send_setup(void)
for (i = 0; i < thread_count; i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
- Error *local_err = NULL;
qemu_sem_init(&p->sem, 0);
qemu_sem_init(&p->sem_sync, 0);
p->id = i;
p->data = multifd_send_data_alloc();
+ p->dsa_batch_task = buffer_zero_batch_task_init(page_count);
if (use_packets) {
p->packet_len = sizeof(MultiFDPacket_t)
@@ -865,7 +890,6 @@ bool multifd_send_setup(void)
for (i = 0; i < thread_count; i++) {
MultiFDSendParams *p = &multifd_send_state->params[i];
- Error *local_err = NULL;
ret = multifd_send_state->ops->send_setup(p, &local_err);
if (ret) {
@@ -1047,6 +1071,7 @@ void multifd_recv_cleanup(void)
qemu_thread_join(&p->thread);
}
}
+ multifd_dsa_cleanup();
for (i = 0; i < migrate_multifd_channels(); i++) {
multifd_recv_cleanup_channel(&multifd_recv_state->params[i]);
}
@@ -15,6 +15,7 @@
#include "exec/target_page.h"
#include "ram.h"
+#include "qemu/dsa.h"
typedef struct MultiFDRecvData MultiFDRecvData;
typedef struct MultiFDSendData MultiFDSendData;
@@ -155,6 +156,9 @@ typedef struct {
bool pending_sync;
MultiFDSendData *data;
+ /* Zero page checking batch task */
+ QemuDsaBatchTask *dsa_batch_task;
+
/* thread local variables. No locking required */
/* pointer to the packet */
@@ -313,6 +317,7 @@ void multifd_send_fill_packet(MultiFDSendParams *p);
bool multifd_send_prepare_common(MultiFDSendParams *p);
void multifd_send_zero_page_detect(MultiFDSendParams *p);
void multifd_recv_zero_page_process(MultiFDRecvParams *p);
+void multifd_dsa_cleanup(void);
static inline void multifd_send_prepare_header(MultiFDSendParams *p)
{