Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20210407b' into staging

V2 migration+virtiofs fixes pull 2021-04-07

A seg fix in virtiofsd, a bunch of fixes for background snapshots, and
a migration test fix.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

v2
  Fix for !linux build

# gpg: Signature made Wed 07 Apr 2021 18:53:13 BST
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20210407b:
  tests/migration: fix parameter of auto-converge migration
  migration: Rename 'bs' to 'block' in background snapshot code
  migration: Pre-fault memory before starting background snasphot
  migration: Inhibit virtio-balloon for the duration of background snapshot
  migration: Fix missing qemu_fflush() on buffer file in bg_migration_thread
  virtiofsd: Fix security.capability comparison

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

7 files changed, 121 insertions, 40 deletions

diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index e770955176..d120bf8f43 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -66,8 +66,12 @@ static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp,
 
 static bool virtio_balloon_inhibited(void)
 {
-    /* Postcopy cannot deal with concurrent discards, so it's special. */
-    return ram_block_discard_is_disabled() || migration_in_incoming_postcopy();
+    /*
+     * Postcopy cannot deal with concurrent discards,
+     * so it's special, as well as background snapshots.
+     */
+    return ram_block_discard_is_disabled() || migration_in_incoming_postcopy() ||
+            migration_in_bg_snapshot();
 }
 
 static void balloon_inflate_page(VirtIOBalloon *balloon,
diff --git a/include/migration/misc.h b/include/migration/misc.h
index bccc1b6b44..738675ef52 100644
--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@@ -70,6 +70,8 @@ bool migration_in_postcopy_after_devices(MigrationState *);
 void migration_global_dump(Monitor *mon);
 /* True if incomming migration entered POSTCOPY_INCOMING_DISCARD */
 bool migration_in_incoming_postcopy(void);
+/* True if background snapshot is active */
+bool migration_in_bg_snapshot(void);
 
 /* migration/block-dirty-bitmap.c */
 void dirty_bitmap_mig_init(void);
diff --git a/migration/migration.c b/migration/migration.c
index ca8b97baa5..8ca034136b 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1976,6 +1976,14 @@ bool migration_in_incoming_postcopy(void)
     return ps >= POSTCOPY_INCOMING_DISCARD && ps < POSTCOPY_INCOMING_END;
 }
 
+bool migration_in_bg_snapshot(void)
+{
+    MigrationState *s = migrate_get_current();
+
+    return migrate_background_snapshot() &&
+            migration_is_setup_or_active(s->state);
+}
+
 bool migration_is_idle(void)
 {
     MigrationState *s = current_migration;
@@ -3812,13 +3820,21 @@ static void *bg_migration_thread(void *opaque)
      * with vCPUs running and, finally, write stashed non-RAM part of
      * the vmstate from the buffer to the migration stream.
      */
-    s->bioc = qio_channel_buffer_new(128 * 1024);
+    s->bioc = qio_channel_buffer_new(512 * 1024);
     qio_channel_set_name(QIO_CHANNEL(s->bioc), "vmstate-buffer");
     fb = qemu_fopen_channel_output(QIO_CHANNEL(s->bioc));
     object_unref(OBJECT(s->bioc));
 
     update_iteration_initial_status(s);
 
+    /*
+     * Prepare for tracking memory writes with UFFD-WP - populate
+     * RAM pages before protecting.
+     */
+#ifdef __linux__
+    ram_write_tracking_prepare();
+#endif
+
     qemu_savevm_state_header(s->to_dst_file);
     qemu_savevm_state_setup(s->to_dst_file);
 
@@ -3866,6 +3882,12 @@ static void *bg_migration_thread(void *opaque)
     if (qemu_savevm_state_complete_precopy_non_iterable(fb, false, false)) {
         goto fail;
     }
+    /*
+     * Since we are going to get non-iterable state data directly
+     * from s->bioc->data, explicit flush is needed here.
+     */
+    qemu_fflush(fb);
+
     /* Now initialize UFFD context and start tracking RAM writes */
     if (ram_write_tracking_start()) {
         goto fail;
diff --git a/migration/ram.c b/migration/ram.c
index 40e78952ad..4682f3625c 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1455,7 +1455,7 @@ static RAMBlock *poll_fault_page(RAMState *rs, ram_addr_t *offset)
 {
     struct uffd_msg uffd_msg;
     void *page_address;
-    RAMBlock *bs;
+    RAMBlock *block;
     int res;
 
     if (!migrate_background_snapshot()) {
@@ -1468,9 +1468,9 @@ static RAMBlock *poll_fault_page(RAMState *rs, ram_addr_t *offset)
     }
 
     page_address = (void *)(uintptr_t) uffd_msg.arg.pagefault.address;
-    bs = qemu_ram_block_from_host(page_address, false, offset);
-    assert(bs && (bs->flags & RAM_UF_WRITEPROTECT) != 0);
-    return bs;
+    block = qemu_ram_block_from_host(page_address, false, offset);
+    assert(block && (block->flags & RAM_UF_WRITEPROTECT) != 0);
+    return block;
 }
 
 /**
@@ -1526,7 +1526,7 @@ bool ram_write_tracking_compatible(void)
 {
     const uint64_t uffd_ioctls_mask = BIT(_UFFDIO_WRITEPROTECT);
     int uffd_fd;
-    RAMBlock *bs;
+    RAMBlock *block;
     bool ret = false;
 
     /* Open UFFD file descriptor */
@@ -1537,15 +1537,15 @@ bool ram_write_tracking_compatible(void)
 
     RCU_READ_LOCK_GUARD();
 
-    RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         uint64_t uffd_ioctls;
 
         /* Nothing to do with read-only and MMIO-writable regions */
-        if (bs->mr->readonly || bs->mr->rom_device) {
+        if (block->mr->readonly || block->mr->rom_device) {
             continue;
         }
         /* Try to register block memory via UFFD-IO to track writes */
-        if (uffd_register_memory(uffd_fd, bs->host, bs->max_length,
+        if (uffd_register_memory(uffd_fd, block->host, block->max_length,
                 UFFDIO_REGISTER_MODE_WP, &uffd_ioctls)) {
             goto out;
         }
@@ -1561,6 +1561,55 @@ out:
 }
 
 /*
+ * ram_block_populate_pages: populate memory in the RAM block by reading
+ *   an integer from the beginning of each page.
+ *
+ * Since it's solely used for userfault_fd WP feature, here we just
+ *   hardcode page size to qemu_real_host_page_size.
+ *
+ * @block: RAM block to populate
+ */
+static void ram_block_populate_pages(RAMBlock *block)
+{
+    char *ptr = (char *) block->host;
+
+    for (ram_addr_t offset = 0; offset < block->used_length;
+            offset += qemu_real_host_page_size) {
+        char tmp = *(ptr + offset);
+
+        /* Don't optimize the read out */
+        asm volatile("" : "+r" (tmp));
+    }
+}
+
+/*
+ * ram_write_tracking_prepare: prepare for UFFD-WP memory tracking
+ */
+void ram_write_tracking_prepare(void)
+{
+    RAMBlock *block;
+
+    RCU_READ_LOCK_GUARD();
+
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+        /* Nothing to do with read-only and MMIO-writable regions */
+        if (block->mr->readonly || block->mr->rom_device) {
+            continue;
+        }
+
+        /*
+         * Populate pages of the RAM block before enabling userfault_fd
+         * write protection.
+         *
+         * This stage is required since ioctl(UFFDIO_WRITEPROTECT) with
+         * UFFDIO_WRITEPROTECT_MODE_WP mode setting would silently skip
+         * pages with pte_none() entries in page table.
+         */
+        ram_block_populate_pages(block);
+    }
+}
+
+/*
  * ram_write_tracking_start: start UFFD-WP memory tracking
  *
  * Returns 0 for success or negative value in case of error
@@ -1569,7 +1618,7 @@ int ram_write_tracking_start(void)
 {
     int uffd_fd;
     RAMState *rs = ram_state;
-    RAMBlock *bs;
+    RAMBlock *block;
 
     /* Open UFFD file descriptor */
     uffd_fd = uffd_create_fd(UFFD_FEATURE_PAGEFAULT_FLAG_WP, true);
@@ -1580,27 +1629,27 @@ int ram_write_tracking_start(void)
 
     RCU_READ_LOCK_GUARD();
 
-    RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         /* Nothing to do with read-only and MMIO-writable regions */
-        if (bs->mr->readonly || bs->mr->rom_device) {
+        if (block->mr->readonly || block->mr->rom_device) {
             continue;
         }
 
         /* Register block memory with UFFD to track writes */
-        if (uffd_register_memory(rs->uffdio_fd, bs->host,
-                bs->max_length, UFFDIO_REGISTER_MODE_WP, NULL)) {
+        if (uffd_register_memory(rs->uffdio_fd, block->host,
+                block->max_length, UFFDIO_REGISTER_MODE_WP, NULL)) {
             goto fail;
         }
         /* Apply UFFD write protection to the block memory range */
-        if (uffd_change_protection(rs->uffdio_fd, bs->host,
-                bs->max_length, true, false)) {
+        if (uffd_change_protection(rs->uffdio_fd, block->host,
+                block->max_length, true, false)) {
             goto fail;
         }
-        bs->flags |= RAM_UF_WRITEPROTECT;
-        memory_region_ref(bs->mr);
+        block->flags |= RAM_UF_WRITEPROTECT;
+        memory_region_ref(block->mr);
 
-        trace_ram_write_tracking_ramblock_start(bs->idstr, bs->page_size,
-                bs->host, bs->max_length);
+        trace_ram_write_tracking_ramblock_start(block->idstr, block->page_size,
+                block->host, block->max_length);
     }
 
     return 0;
@@ -1608,19 +1657,20 @@ int ram_write_tracking_start(void)
 fail:
     error_report("ram_write_tracking_start() failed: restoring initial memory state");
 
-    RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
-        if ((bs->flags & RAM_UF_WRITEPROTECT) == 0) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+        if ((block->flags & RAM_UF_WRITEPROTECT) == 0) {
             continue;
         }
         /*
          * In case some memory block failed to be write-protected
          * remove protection and unregister all succeeded RAM blocks
          */
-        uffd_change_protection(rs->uffdio_fd, bs->host, bs->max_length, false, false);
-        uffd_unregister_memory(rs->uffdio_fd, bs->host, bs->max_length);
+        uffd_change_protection(rs->uffdio_fd, block->host, block->max_length,
+                false, false);
+        uffd_unregister_memory(rs->uffdio_fd, block->host, block->max_length);
         /* Cleanup flags and remove reference */
-        bs->flags &= ~RAM_UF_WRITEPROTECT;
-        memory_region_unref(bs->mr);
+        block->flags &= ~RAM_UF_WRITEPROTECT;
+        memory_region_unref(block->mr);
     }
 
     uffd_close_fd(uffd_fd);
@@ -1634,24 +1684,25 @@ fail:
 void ram_write_tracking_stop(void)
 {
     RAMState *rs = ram_state;
-    RAMBlock *bs;
+    RAMBlock *block;
 
     RCU_READ_LOCK_GUARD();
 
-    RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
-        if ((bs->flags & RAM_UF_WRITEPROTECT) == 0) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+        if ((block->flags & RAM_UF_WRITEPROTECT) == 0) {
             continue;
         }
         /* Remove protection and unregister all affected RAM blocks */
-        uffd_change_protection(rs->uffdio_fd, bs->host, bs->max_length, false, false);
-        uffd_unregister_memory(rs->uffdio_fd, bs->host, bs->max_length);
+        uffd_change_protection(rs->uffdio_fd, block->host, block->max_length,
+                false, false);
+        uffd_unregister_memory(rs->uffdio_fd, block->host, block->max_length);
 
-        trace_ram_write_tracking_ramblock_stop(bs->idstr, bs->page_size,
-                bs->host, bs->max_length);
+        trace_ram_write_tracking_ramblock_stop(block->idstr, block->page_size,
+                block->host, block->max_length);
 
         /* Cleanup flags and remove reference */
-        bs->flags &= ~RAM_UF_WRITEPROTECT;
-        memory_region_unref(bs->mr);
+        block->flags &= ~RAM_UF_WRITEPROTECT;
+        memory_region_unref(block->mr);
     }
 
     /* Finally close UFFD file descriptor */
diff --git a/migration/ram.h b/migration/ram.h
index 6378bb3ebc..4833e9fd5b 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -82,6 +82,7 @@ void colo_incoming_start_dirty_log(void);
 /* Background snapshot */
 bool ram_write_tracking_available(void);
 bool ram_write_tracking_compatible(void);
+void ram_write_tracking_prepare(void);
 int ram_write_tracking_start(void);
 void ram_write_tracking_stop(void);
 
diff --git a/tests/migration/guestperf/engine.py b/tests/migration/guestperf/engine.py
index e399447940..6b49aed579 100644
--- a/tests/migration/guestperf/engine.py
+++ b/tests/migration/guestperf/engine.py
@@ -102,7 +102,7 @@ class Engine(object):
             info.get("downtime", 0),
             info.get("expected-downtime", 0),
             info.get("setup-time", 0),
-            info.get("x-cpu-throttle-percentage", 0),
+            info.get("cpu-throttle-percentage", 0),
         )
 
     def _migrate(self, hardware, scenario, src, dst, connect_uri):
@@ -135,7 +135,7 @@ class Engine(object):
                                      "state": True }
                                ])
             resp = src.command("migrate-set-parameters",
-                               x_cpu_throttle_increment=scenario._auto_converge_step)
+                               cpu_throttle_increment=scenario._auto_converge_step)
 
         if scenario._post_copy:
             resp = src.command("migrate-set-capabilities",
diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
index b144320e48..1553d2ef45 100644
--- a/tools/virtiofsd/passthrough_ll.c
+++ b/tools/virtiofsd/passthrough_ll.c
@@ -2636,7 +2636,8 @@ static void parse_xattrmap(struct lo_data *lo)
                 strerror(ret));
         exit(1);
     }
-    if (!strcmp(lo->xattr_security_capability, "security.capability")) {
+    if (!lo->xattr_security_capability ||
+        !strcmp(lo->xattr_security_capability, "security.capability")) {
         /* 1-1 mapping, don't need to do anything */
         free(lo->xattr_security_capability);
         lo->xattr_security_capability = NULL;