migration/ram: Add outgoing 'mapped-ram' migration

Implement the outgoing migration side for the 'mapped-ram' capability.

A bitmap is introduced to track which pages have been written in the
migration file. Pages are written at a fixed location for every
ramblock. Zero pages are ignored as they'd be zero in the destination
migration as well.

The migration stream is altered to put the dirty pages for a ramblock
after its header instead of having a sequential stream of pages that
follow the ramblock headers.

Without mapped-ram (current):        With mapped-ram (new):

 ---------------------               --------------------------------
 | ramblock 1 header |               | ramblock 1 header            |
 ---------------------               --------------------------------
 | ramblock 2 header |               | ramblock 1 mapped-ram header |
 ---------------------               --------------------------------
 | ...               |               | padding to next 1MB boundary |
 ---------------------               | ...                          |
 | ramblock n header |               --------------------------------
 ---------------------               | ramblock 1 pages             |
 | RAM_SAVE_FLAG_EOS |               | ...                          |
 ---------------------               --------------------------------
 | stream of pages   |               | ramblock 2 header            |
 | (iter 1)          |               --------------------------------
 | ...               |               | ramblock 2 mapped-ram header |
 ---------------------               --------------------------------
 | RAM_SAVE_FLAG_EOS |               | padding to next 1MB boundary |
 ---------------------               | ...                          |
 | stream of pages   |               --------------------------------
 | (iter 2)          |               | ramblock 2 pages             |
 | ...               |               | ...                          |
 ---------------------               --------------------------------
 | ...               |               | ...                          |
 ---------------------               --------------------------------
                                     | RAM_SAVE_FLAG_EOS            |
                                     --------------------------------
                                     | ...                          |
                                     --------------------------------

where:
 - ramblock header: the generic information for a ramblock, such as
   idstr, used_len, etc.

 - ramblock mapped-ram header: the new information added by this
   feature: bitmap of pages written, bitmap size and offset of pages
   in the migration file.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240229153017.2221-10-farosas@suse.de
Signed-off-by: Peter Xu <peterx@redhat.com>

include/exec/ramblock.h

@@ -44,6 +44,19 @@ struct RAMBlock {
     size_t page_size;
     /* dirty bitmap used during migration */
     unsigned long *bmap;
+
+    /*
+     * Below fields are only used by mapped-ram migration
+     */
+    /* bitmap of pages present in the migration file */
+    unsigned long *file_bmap;
+    /*
+     * offset in the file pages belonging to this ramblock are saved,
+     * used only during migration to a file.
+     */
+    off_t bitmap_offset;
+    uint64_t pages_offset;
+
     /* bitmap of already received pages in postcopy */
     unsigned long *receivedmap;
 

migration/ram.c

@@ -94,6 +94,18 @@
 #define RAM_SAVE_FLAG_MULTIFD_FLUSH    0x200
 /* We can't use any flag that is bigger than 0x200 */
 
+/*
+ * mapped-ram migration supports O_DIRECT, so we need to make sure the
+ * userspace buffer, the IO operation size and the file offset are
+ * aligned according to the underlying device's block size. The first
+ * two are already aligned to page size, but we need to add padding to
+ * the file to align the offset.  We cannot read the block size
+ * dynamically because the migration file can be moved between
+ * different systems, so use 1M to cover most block sizes and to keep
+ * the file offset aligned at page size as well.
+ */
+#define MAPPED_RAM_FILE_OFFSET_ALIGNMENT 0x100000
+
 XBZRLECacheStats xbzrle_counters;
 
 /* used by the search for pages to send */
@@ -1126,12 +1138,18 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss,
         return 0;
     }
 
+    stat64_add(&mig_stats.zero_pages, 1);
+
+    if (migrate_mapped_ram()) {
+        /* zero pages are not transferred with mapped-ram */
+        clear_bit(offset >> TARGET_PAGE_BITS, pss->block->file_bmap);
+        return 1;
+    }
+
     len += save_page_header(pss, file, pss->block, offset | RAM_SAVE_FLAG_ZERO);
     qemu_put_byte(file, 0);
     len += 1;
     ram_release_page(pss->block->idstr, offset);
-
-    stat64_add(&mig_stats.zero_pages, 1);
     ram_transferred_add(len);
 
     /*
@@ -1189,14 +1207,20 @@ static int save_normal_page(PageSearchStatus *pss, RAMBlock *block,
 {
     QEMUFile *file = pss->pss_channel;
 
-    ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
-                                         offset | RAM_SAVE_FLAG_PAGE));
-    if (async) {
-        qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
-                              migrate_release_ram() &&
-                              migration_in_postcopy());
+    if (migrate_mapped_ram()) {
+        qemu_put_buffer_at(file, buf, TARGET_PAGE_SIZE,
+                           block->pages_offset + offset);
+        set_bit(offset >> TARGET_PAGE_BITS, block->file_bmap);
     } else {
-        qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
+        ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
+                                             offset | RAM_SAVE_FLAG_PAGE));
+        if (async) {
+            qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
+                                  migrate_release_ram() &&
+                                  migration_in_postcopy());
+        } else {
+            qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
+        }
     }
     ram_transferred_add(TARGET_PAGE_SIZE);
     stat64_add(&mig_stats.normal_pages, 1);
@@ -2411,6 +2435,8 @@ static void ram_save_cleanup(void *opaque)
         block->clear_bmap = NULL;
         g_free(block->bmap);
         block->bmap = NULL;
+        g_free(block->file_bmap);
+        block->file_bmap = NULL;
     }
 
     xbzrle_cleanup();
@@ -2778,6 +2804,9 @@ static void ram_list_init_bitmaps(void)
              */
             block->bmap = bitmap_new(pages);
             bitmap_set(block->bmap, 0, pages);
+            if (migrate_mapped_ram()) {
+                block->file_bmap = bitmap_new(pages);
+            }
             block->clear_bmap_shift = shift;
             block->clear_bmap = bitmap_new(clear_bmap_size(pages, shift));
         }
@@ -2915,6 +2944,60 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
     }
 }
 
+#define MAPPED_RAM_HDR_VERSION 1
+struct MappedRamHeader {
+    uint32_t version;
+    /*
+     * The target's page size, so we know how many pages are in the
+     * bitmap.
+     */
+    uint64_t page_size;
+    /*
+     * The offset in the migration file where the pages bitmap is
+     * stored.
+     */
+    uint64_t bitmap_offset;
+    /*
+     * The offset in the migration file where the actual pages (data)
+     * are stored.
+     */
+    uint64_t pages_offset;
+} QEMU_PACKED;
+typedef struct MappedRamHeader MappedRamHeader;
+
+static void mapped_ram_setup_ramblock(QEMUFile *file, RAMBlock *block)
+{
+    g_autofree MappedRamHeader *header = NULL;
+    size_t header_size, bitmap_size;
+    long num_pages;
+
+    header = g_new0(MappedRamHeader, 1);
+    header_size = sizeof(MappedRamHeader);
+
+    num_pages = block->used_length >> TARGET_PAGE_BITS;
+    bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+
+    /*
+     * Save the file offsets of where the bitmap and the pages should
+     * go as they are written at the end of migration and during the
+     * iterative phase, respectively.
+     */
+    block->bitmap_offset = qemu_get_offset(file) + header_size;
+    block->pages_offset = ROUND_UP(block->bitmap_offset +
+                                   bitmap_size,
+                                   MAPPED_RAM_FILE_OFFSET_ALIGNMENT);
+
+    header->version = cpu_to_be32(MAPPED_RAM_HDR_VERSION);
+    header->page_size = cpu_to_be64(TARGET_PAGE_SIZE);
+    header->bitmap_offset = cpu_to_be64(block->bitmap_offset);
+    header->pages_offset = cpu_to_be64(block->pages_offset);
+
+    qemu_put_buffer(file, (uint8_t *) header, header_size);
+
+    /* prepare offset for next ramblock */
+    qemu_set_offset(file, block->pages_offset + block->used_length, SEEK_SET);
+}
+
 /*
  * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
  * long-running RCU critical section.  When rcu-reclaims in the code
@@ -2964,6 +3047,10 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
             if (migrate_ignore_shared()) {
                 qemu_put_be64(f, block->mr->addr);
             }
+
+            if (migrate_mapped_ram()) {
+                mapped_ram_setup_ramblock(f, block);
+            }
         }
     }
 
@@ -2997,6 +3084,20 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     return qemu_fflush(f);
 }
 
+static void ram_save_file_bmap(QEMUFile *f)
+{
+    RAMBlock *block;
+
+    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+        long num_pages = block->used_length >> TARGET_PAGE_BITS;
+        long bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
+
+        qemu_put_buffer_at(f, (uint8_t *)block->file_bmap, bitmap_size,
+                           block->bitmap_offset);
+        ram_transferred_add(bitmap_size);
+    }
+}
+
 /**
  * ram_save_iterate: iterative stage for migration
  *
@@ -3186,6 +3287,18 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         return ret;
     }
 
+    if (migrate_mapped_ram()) {
+        ram_save_file_bmap(f);
+
+        if (qemu_file_get_error(f)) {
+            Error *local_err = NULL;
+            int err = qemu_file_get_error_obj(f, &local_err);
+
+            error_reportf_err(local_err, "Failed to write bitmap to file: ");
+            return -err;
+        }
+    }
+
     if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
         qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
     }