[Qemu-devel] [PATCH v8 39/54] Page request: Process incoming page request

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

On receiving MIG_RPCOMM_REQ_PAGES look up the address and
queue the page.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
---
 include/migration/migration.h | 22 +++++++++++
 migration/migration.c         | 31 +++++++++++++++-
 migration/ram.c               | 85 +++++++++++++++++++++++++++++++++++++++++++
 trace-events                  |  1 +
 4 files changed, 138 insertions(+), 1 deletion(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 9be08c8..fbf3b99 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -105,6 +105,18 @@ MigrationIncomingState *migration_incoming_get_current(void);
 MigrationIncomingState *migration_incoming_state_new(QEMUFile *f);
 void migration_incoming_state_destroy(void);
 
+/*
+ * An outstanding page request, on the source, having been received
+ * and queued
+ */
+struct MigrationSrcPageRequest {
+    RAMBlock *rb;
+    hwaddr    offset;
+    hwaddr    len;
+
+    QSIMPLEQ_ENTRY(MigrationSrcPageRequest) next_req;
+};
+
 struct MigrationState
 {
     int64_t bandwidth_limit;
@@ -148,6 +160,12 @@ struct MigrationState
      * of the postcopy phase
      */
     unsigned long *sentmap;
+
+    /* Queue of outstanding page requests from the destination */
+    QemuMutex src_page_req_mutex;
+    QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests;
+    /* The RAMBlock used in the last src_page_request */
+    RAMBlock *last_req_rb;
 };
 
 void process_incoming_migration(QEMUFile *f);
@@ -295,6 +313,10 @@ void savevm_skip_configuration(void);
 int global_state_store(void);
 void global_state_store_running(void);
 
+void flush_page_queue(MigrationState *ms);
+int ram_save_queue_pages(MigrationState *ms, const char *rbname,
+                         ram_addr_t start, ram_addr_t len);
+
 PostcopyState postcopy_state_get(void);
 /* Set the state and return the old state */
 PostcopyState postcopy_state_set(PostcopyState new_state);
diff --git a/migration/migration.c b/migration/migration.c
index e994164..6160259 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -21,6 +21,7 @@
 #include "sysemu/sysemu.h"
 #include "block/block.h"
 #include "qapi/qmp/qerror.h"
+#include "qapi/util.h"
 #include "qemu/sockets.h"
 #include "qemu/rcu.h"
 #include "migration/block.h"
@@ -28,8 +29,9 @@
 #include "qemu/thread.h"
 #include "qmp-commands.h"
 #include "trace.h"
-#include "qapi/util.h"
 #include "qapi-event.h"
+#include "exec/memory.h"
+#include "exec/address-spaces.h"
 
 #define MAX_THROTTLE  (32 << 20)      /* Migration speed throttling */
 
@@ -68,6 +70,7 @@ static PostcopyState incoming_postcopy_state;
 /* For outgoing */
 MigrationState *migrate_get_current(void)
 {
+    static bool once;
     static MigrationState current_migration = {
         .state = MIGRATION_STATUS_NONE,
         .bandwidth_limit = MAX_THROTTLE,
@@ -81,6 +84,10 @@ MigrationState *migrate_get_current(void)
                 DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT,
     };
 
+    if (!once) {
+        qemu_mutex_init(&current_migration.src_page_req_mutex);
+        once = true;
+    }
     return &current_migration;
 }
 
@@ -718,6 +725,8 @@ static void migrate_fd_cleanup(void *opaque)
     qemu_bh_delete(s->cleanup_bh);
     s->cleanup_bh = NULL;
 
+    flush_page_queue(s);
+
     if (s->file) {
         trace_migrate_fd_cleanup();
         qemu_mutex_unlock_iothread();
@@ -845,6 +854,8 @@ MigrationState *migrate_init(const MigrationParams *params)
     s->bandwidth_limit = bandwidth_limit;
     migrate_set_state(s, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
 
+    QSIMPLEQ_INIT(&s->src_page_requests);
+
     s->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     return s;
 }
@@ -1134,7 +1145,25 @@ static struct rp_cmd_args {
 static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
                                        ram_addr_t start, size_t len)
 {
+    long our_host_ps = getpagesize();
+
     trace_migrate_handle_rp_req_pages(rbname, start, len);
+
+    /*
+     * Since we currently insist on matching page sizes, just sanity check
+     * we're being asked for whole host pages.
+     */
+    if (start & (our_host_ps-1) ||
+       (len & (our_host_ps-1))) {
+        error_report("%s: Misaligned page request, start: " RAM_ADDR_FMT
+                     " len: " RAM_ADDR_FMT, __func__, start, len);
+        mark_source_rp_bad(ms);
+        return;
+    }
+
+    if (ram_save_queue_pages(ms, rbname, start, len)) {
+        mark_source_rp_bad(ms);
+    }
 }
 
 /*
diff --git a/migration/ram.c b/migration/ram.c
index d005aca..5771983 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1002,6 +1002,91 @@ static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss,
 }
 
 /**
+ * flush_page_queue: Flush any remaining pages in the ram request queue
+ *    it should be empty at the end anyway, but in error cases there may be
+ *    some left.
+ *
+ * ms: MigrationState
+ */
+void flush_page_queue(MigrationState *ms)
+{
+    struct MigrationSrcPageRequest *mspr, *next_mspr;
+    /* This queue generally should be empty - but in the case of a failed
+     * migration might have some droppings in.
+     */
+    rcu_read_lock();
+    QSIMPLEQ_FOREACH_SAFE(mspr, &ms->src_page_requests, next_req, next_mspr) {
+        memory_region_unref(mspr->rb->mr);
+        QSIMPLEQ_REMOVE_HEAD(&ms->src_page_requests, next_req);
+        g_free(mspr);
+    }
+    rcu_read_unlock();
+}
+
+/**
+ * Queue the pages for transmission, e.g. a request from postcopy destination
+ *   ms: MigrationStatus in which the queue is held
+ *   rbname: The RAMBlock the request is for - may be NULL (to mean reuse last)
+ *   start: Offset from the start of the RAMBlock
+ *   len: Length (in bytes) to send
+ *   Return: 0 on success
+ */
+int ram_save_queue_pages(MigrationState *ms, const char *rbname,
+                         ram_addr_t start, ram_addr_t len)
+{
+    RAMBlock *ramblock;
+
+    rcu_read_lock();
+    if (!rbname) {
+        /* Reuse last RAMBlock */
+        ramblock = ms->last_req_rb;
+
+        if (!ramblock) {
+            /*
+             * Shouldn't happen, we can't reuse the last RAMBlock if
+             * it's the 1st request.
+             */
+            error_report("ram_save_queue_pages no previous block");
+            goto err;
+        }
+    } else {
+        ramblock = ram_find_block_by_id(rbname);
+
+        if (!ramblock) {
+            /* We shouldn't be asked for a non-existent RAMBlock */
+            error_report("ram_save_queue_pages no block '%s'", rbname);
+            goto err;
+        }
+        ms->last_req_rb = ramblock;
+    }
+    trace_ram_save_queue_pages(ramblock->idstr, start, len);
+    if (start+len > ramblock->used_length) {
+        error_report("%s request overrun start=%zx len=%zx blocklen=%zx",
+                     __func__, start, len, ramblock->used_length);
+        goto err;
+    }
+
+    struct MigrationSrcPageRequest *new_entry =
+        g_malloc0(sizeof(struct MigrationSrcPageRequest));
+    new_entry->rb = ramblock;
+    new_entry->offset = start;
+    new_entry->len = len;
+
+    memory_region_ref(ramblock->mr);
+    qemu_mutex_lock(&ms->src_page_req_mutex);
+    QSIMPLEQ_INSERT_TAIL(&ms->src_page_requests, new_entry, next_req);
+    qemu_mutex_unlock(&ms->src_page_req_mutex);
+    rcu_read_unlock();
+
+    return 0;
+
+err:
+    rcu_read_unlock();
+    return -1;
+}
+
+
+/**
  * ram_find_and_save_block: Finds a dirty page and sends it to f
  *
  * Called within an RCU critical section.
diff --git a/trace-events b/trace-events
index b58077f..e40f00e 100644
--- a/trace-events
+++ b/trace-events
@@ -1248,6 +1248,7 @@ migration_bitmap_sync_start(void) ""
 migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64""
 migration_throttle(void) ""
 ram_postcopy_send_discard_bitmap(void) ""
+ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: start: %zx len: %zx"
 
 # hw/display/qxl.c
 disable qxl_interface_set_mm_time(int qid, uint32_t mm_time) "%d %d"
-- 
2.5.0