[PULL 23/27] migration/multifd: Support outgoing mapped-ram stream format

[peterx@redhat.com]

From: Fabiano Rosas <farosas@suse.de>

The new mapped-ram stream format uses a file transport and puts ram
pages in the migration file at their respective offsets and can be
done in parallel by using the pwritev system call which takes iovecs
and an offset.

Add support to enabling the new format along with multifd to make use
of the threading and page handling already in place.

This requires multifd to stop sending headers and leaving the stream
format to the mapped-ram code. When it comes time to write the data, we
need to call a version of qio_channel_write that can take an offset.

Usage on HMP is:

(qemu) stop
(qemu) migrate_set_capability multifd on
(qemu) migrate_set_capability mapped-ram on
(qemu) migrate_set_parameter max-bandwidth 0
(qemu) migrate_set_parameter multifd-channels 8
(qemu) migrate file:migfile

Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240229153017.2221-21-farosas@suse.de
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/qemu/bitops.h | 13 +++++++++++
 migration/file.h      |  2 ++
 migration/ram.h       |  1 +
 migration/file.c      | 54 +++++++++++++++++++++++++++++++++++++++++++
 migration/migration.c | 17 ++++++++++----
 migration/multifd.c   | 24 +++++++++++++++++--
 migration/options.c   | 13 ++++++-----
 migration/ram.c       | 17 +++++++++++---
 8 files changed, 125 insertions(+), 16 deletions(-)

diff --git a/include/qemu/bitops.h b/include/qemu/bitops.h
index cb3526d1f4..2c0a2fe751 100644
--- a/include/qemu/bitops.h
+++ b/include/qemu/bitops.h
@@ -67,6 +67,19 @@ static inline void clear_bit(long nr, unsigned long *addr)
     *p &= ~mask;
 }
 
+/**
+ * clear_bit_atomic - Clears a bit in memory atomically
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+static inline void clear_bit_atomic(long nr, unsigned long *addr)
+{
+    unsigned long mask = BIT_MASK(nr);
+    unsigned long *p = addr + BIT_WORD(nr);
+
+    return qatomic_and(p, ~mask);
+}
+
 /**
  * change_bit - Toggle a bit in memory
  * @nr: Bit to change
diff --git a/migration/file.h b/migration/file.h
index 4577f9efdd..01a338cac7 100644
--- a/migration/file.h
+++ b/migration/file.h
@@ -19,4 +19,6 @@ void file_start_outgoing_migration(MigrationState *s,
 int file_parse_offset(char *filespec, uint64_t *offsetp, Error **errp);
 void file_cleanup_outgoing_migration(void);
 bool file_send_channel_create(gpointer opaque, Error **errp);
+int file_write_ramblock_iov(QIOChannel *ioc, const struct iovec *iov,
+                            int niov, RAMBlock *block, Error **errp);
 #endif
diff --git a/migration/ram.h b/migration/ram.h
index 9b937a446b..b9ac0da587 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -75,6 +75,7 @@ bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp);
 bool ramblock_page_is_discarded(RAMBlock *rb, ram_addr_t start);
 void postcopy_preempt_shutdown_file(MigrationState *s);
 void *postcopy_preempt_thread(void *opaque);
+void ramblock_set_file_bmap_atomic(RAMBlock *block, ram_addr_t offset);
 
 /* ram cache */
 int colo_init_ram_cache(void);
diff --git a/migration/file.c b/migration/file.c
index 2f8b626b27..d949a941d0 100644
--- a/migration/file.c
+++ b/migration/file.c
@@ -150,3 +150,57 @@ void file_start_incoming_migration(FileMigrationArgs *file_args, Error **errp)
         }
     } while (++i < channels);
 }
+
+int file_write_ramblock_iov(QIOChannel *ioc, const struct iovec *iov,
+                            int niov, RAMBlock *block, Error **errp)
+{
+    ssize_t ret = -1;
+    int i, slice_idx, slice_num;
+    uintptr_t base, next, offset;
+    size_t len;
+
+    slice_idx = 0;
+    slice_num = 1;
+
+    /*
+     * If the iov array doesn't have contiguous elements, we need to
+     * split it in slices because we only have one file offset for the
+     * whole iov. Do this here so callers don't need to break the iov
+     * array themselves.
+     */
+    for (i = 0; i < niov; i++, slice_num++) {
+        base = (uintptr_t) iov[i].iov_base;
+
+        if (i != niov - 1) {
+            len = iov[i].iov_len;
+            next = (uintptr_t) iov[i + 1].iov_base;
+
+            if (base + len == next) {
+                continue;
+            }
+        }
+
+        /*
+         * Use the offset of the first element of the segment that
+         * we're sending.
+         */
+        offset = (uintptr_t) iov[slice_idx].iov_base - (uintptr_t) block->host;
+        if (offset >= block->used_length) {
+            error_setg(errp, "offset " RAM_ADDR_FMT
+                       "outside of ramblock %s range", offset, block->idstr);
+            ret = -1;
+            break;
+        }
+
+        ret = qio_channel_pwritev(ioc, &iov[slice_idx], slice_num,
+                                  block->pages_offset + offset, errp);
+        if (ret < 0) {
+            break;
+        }
+
+        slice_idx += slice_num;
+        slice_num = 0;
+    }
+
+    return (ret < 0) ? ret : 0;
+}
diff --git a/migration/migration.c b/migration/migration.c
index faeb75a59b..b9baab543a 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -140,12 +140,14 @@ static bool transport_supports_multi_channels(MigrationAddress *addr)
     if (addr->transport == MIGRATION_ADDRESS_TYPE_SOCKET) {
         SocketAddress *saddr = &addr->u.socket;
 
-        return saddr->type == SOCKET_ADDRESS_TYPE_INET ||
-               saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
-               saddr->type == SOCKET_ADDRESS_TYPE_VSOCK;
+        return (saddr->type == SOCKET_ADDRESS_TYPE_INET ||
+                saddr->type == SOCKET_ADDRESS_TYPE_UNIX ||
+                saddr->type == SOCKET_ADDRESS_TYPE_VSOCK);
+    } else if (addr->transport == MIGRATION_ADDRESS_TYPE_FILE) {
+        return migrate_mapped_ram();
+    } else {
+        return false;
     }
-
-    return false;
 }
 
 static bool migration_needs_seekable_channel(void)
@@ -1985,6 +1987,11 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
             error_setg(errp, "Cannot use TLS with mapped-ram");
             return false;
         }
+
+        if (migrate_multifd_compression()) {
+            error_setg(errp, "Cannot use compression with mapped-ram");
+            return false;
+        }
     }
 
     if (migrate_mode_is_cpr(s)) {
diff --git a/migration/multifd.c b/migration/multifd.c
index ea08f1aa9e..8118145428 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -108,6 +108,17 @@ void multifd_send_channel_created(void)
     qemu_sem_post(&multifd_send_state->channels_created);
 }
 
+static void multifd_set_file_bitmap(MultiFDSendParams *p)
+{
+    MultiFDPages_t *pages = p->pages;
+
+    assert(pages->block);
+
+    for (int i = 0; i < p->pages->num; i++) {
+        ramblock_set_file_bmap_atomic(pages->block, pages->offset[i]);
+    }
+}
+
 /* Multifd without compression */
 
 /**
@@ -169,6 +180,8 @@ static int nocomp_send_prepare(MultiFDSendParams *p, Error **errp)
 
     if (!multifd_use_packets()) {
         multifd_send_prepare_iovs(p);
+        multifd_set_file_bitmap(p);
+
         return 0;
     }
 
@@ -867,8 +880,15 @@ static void *multifd_send_thread(void *opaque)
                 break;
             }
 
-            ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
-                                              0, p->write_flags, &local_err);
+            if (migrate_mapped_ram()) {
+                ret = file_write_ramblock_iov(p->c, p->iov, p->iovs_num,
+                                              p->pages->block, &local_err);
+            } else {
+                ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num,
+                                                  NULL, 0, p->write_flags,
+                                                  &local_err);
+            }
+
             if (ret != 0) {
                 break;
             }
diff --git a/migration/options.c b/migration/options.c
index 5df89820fd..40eb930940 100644
--- a/migration/options.c
+++ b/migration/options.c
@@ -654,12 +654,6 @@ bool migrate_caps_check(bool *old_caps, bool *new_caps, Error **errp)
     }
 
     if (new_caps[MIGRATION_CAPABILITY_MAPPED_RAM]) {
-        if (new_caps[MIGRATION_CAPABILITY_MULTIFD]) {
-            error_setg(errp,
-                       "Mapped-ram migration is incompatible with multifd");
-            return false;
-        }
-
         if (new_caps[MIGRATION_CAPABILITY_XBZRLE]) {
             error_setg(errp,
                        "Mapped-ram migration is incompatible with xbzrle");
@@ -1252,6 +1246,13 @@ bool migrate_params_check(MigrationParameters *params, Error **errp)
     }
 #endif
 
+    if (migrate_mapped_ram() &&
+        (migrate_multifd_compression() || migrate_tls())) {
+        error_setg(errp,
+                   "Mapped-ram only available for non-compressed non-TLS multifd migration");
+        return false;
+    }
+
     if (params->has_x_vcpu_dirty_limit_period &&
         (params->x_vcpu_dirty_limit_period < 1 ||
          params->x_vcpu_dirty_limit_period > 1000)) {
diff --git a/migration/ram.c b/migration/ram.c
index 329153d97d..87cb73fd76 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1148,7 +1148,7 @@ static int save_zero_page(RAMState *rs, PageSearchStatus *pss,
 
     if (migrate_mapped_ram()) {
         /* zero pages are not transferred with mapped-ram */
-        clear_bit(offset >> TARGET_PAGE_BITS, pss->block->file_bmap);
+        clear_bit_atomic(offset >> TARGET_PAGE_BITS, pss->block->file_bmap);
         return 1;
     }
 
@@ -2445,8 +2445,6 @@ 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();
@@ -3135,9 +3133,22 @@ static void ram_save_file_bmap(QEMUFile *f)
         qemu_put_buffer_at(f, (uint8_t *)block->file_bmap, bitmap_size,
                            block->bitmap_offset);
         ram_transferred_add(bitmap_size);
+
+        /*
+         * Free the bitmap here to catch any synchronization issues
+         * with multifd channels. No channels should be sending pages
+         * after we've written the bitmap to file.
+         */
+        g_free(block->file_bmap);
+        block->file_bmap = NULL;
     }
 }
 
+void ramblock_set_file_bmap_atomic(RAMBlock *block, ram_addr_t offset)
+{
+    set_bit_atomic(offset >> TARGET_PAGE_BITS, block->file_bmap);
+}
+
 /**
  * ram_save_iterate: iterative stage for migration
  *
-- 
2.44.0