Merge remote-tracking branch 'remotes/juanquintela/tags/migration-20211031-pull-request' into staging

Migration Pull request

Hi

this includes pending bits of migration patches.

- virtio-mem support by David Hildenbrand
- dirtyrate improvements by Hyman Huang
- fix rdma wrid by Li Zhijian
- dump-guest-memory fixes by Peter Xu

Pleas apply.

Thanks, Juan.

# gpg: Signature made Mon 01 Nov 2021 06:03:44 PM EDT
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [full]

* remotes/juanquintela/tags/migration-20211031-pull-request:
  migration/dirtyrate: implement dirty-bitmap dirtyrate calculation
  memory: introduce total_dirty_pages to stat dirty pages
  migration/ram: Handle RAMBlocks with a RamDiscardManager on background snapshots
  migration/ram: Factor out populating pages readable in ram_block_populate_pages()
  migration: Simplify alignment and alignment checks
  migration/postcopy: Handle RAMBlocks with a RamDiscardManager on the destination
  virtio-mem: Drop precopy notifier
  migration/ram: Handle RAMBlocks with a RamDiscardManager on the migration source
  virtio-mem: Implement replay_discarded RamDiscardManager callback
  memory: Introduce replay_discarded callback for RamDiscardManager
  dump-guest-memory: Block live migration
  migration: Add migrate_add_blocker_internal()
  migration: Make migration blocker work for snapshots too
  migration/dirtyrate: implement dirty-ring dirtyrate calculation
  migration/dirtyrate: move init step of calculation to main thread
  migration/dirtyrate: adjust order of registering thread
  migration/dirtyrate: introduce struct and adjust DirtyRateStat
  memory: make global_dirty_tracking a bitmask
  KVM: introduce dirty_pages and kvm_dirty_ring_enabled
  migration/rdma: Fix out of order wrid

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 31 insertions, 9 deletions

diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 2e9697bdd2..e721f69d0f 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -402,7 +402,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState *mis)
                      strerror(errno));
         goto out;
     }
-    g_assert(((size_t)testarea & (pagesize - 1)) == 0);
+    g_assert(QEMU_PTR_IS_ALIGNED(testarea, pagesize));
 
     reg_struct.range.start = (uintptr_t)testarea;
     reg_struct.range.len = pagesize;
@@ -660,7 +660,7 @@ int postcopy_wake_shared(struct PostCopyFD *pcfd,
     struct uffdio_range range;
     int ret;
     trace_postcopy_wake_shared(client_addr, qemu_ram_get_idstr(rb));
-    range.start = client_addr & ~(pagesize - 1);
+    range.start = ROUND_DOWN(client_addr, pagesize);
     range.len = pagesize;
     ret = ioctl(pcfd->fd, UFFDIO_WAKE, &range);
     if (ret) {
@@ -671,6 +671,29 @@ int postcopy_wake_shared(struct PostCopyFD *pcfd,
     return ret;
 }
 
+static int postcopy_request_page(MigrationIncomingState *mis, RAMBlock *rb,
+                                 ram_addr_t start, uint64_t haddr)
+{
+    void *aligned = (void *)(uintptr_t)ROUND_DOWN(haddr, qemu_ram_pagesize(rb));
+
+    /*
+     * Discarded pages (via RamDiscardManager) are never migrated. On unlikely
+     * access, place a zeropage, which will also set the relevant bits in the
+     * recv_bitmap accordingly, so we won't try placing a zeropage twice.
+     *
+     * Checking a single bit is sufficient to handle pagesize > TPS as either
+     * all relevant bits are set or not.
+     */
+    assert(QEMU_IS_ALIGNED(start, qemu_ram_pagesize(rb)));
+    if (ramblock_page_is_discarded(rb, start)) {
+        bool received = ramblock_recv_bitmap_test_byte_offset(rb, start);
+
+        return received ? 0 : postcopy_place_page_zero(mis, aligned, rb);
+    }
+
+    return migrate_send_rp_req_pages(mis, rb, start, haddr);
+}
+
 /*
  * Callback from shared fault handlers to ask for a page,
  * the page must be specified by a RAMBlock and an offset in that rb
@@ -679,8 +702,7 @@ int postcopy_wake_shared(struct PostCopyFD *pcfd,
 int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
                                  uint64_t client_addr, uint64_t rb_offset)
 {
-    size_t pagesize = qemu_ram_pagesize(rb);
-    uint64_t aligned_rbo = rb_offset & ~(pagesize - 1);
+    uint64_t aligned_rbo = ROUND_DOWN(rb_offset, qemu_ram_pagesize(rb));
     MigrationIncomingState *mis = migration_incoming_get_current();
 
     trace_postcopy_request_shared_page(pcfd->idstr, qemu_ram_get_idstr(rb),
@@ -690,7 +712,7 @@ int postcopy_request_shared_page(struct PostCopyFD *pcfd, RAMBlock *rb,
                                         qemu_ram_get_idstr(rb), rb_offset);
         return postcopy_wake_shared(pcfd, client_addr, rb);
     }
-    migrate_send_rp_req_pages(mis, rb, aligned_rbo, client_addr);
+    postcopy_request_page(mis, rb, aligned_rbo, client_addr);
     return 0;
 }
 
@@ -970,7 +992,7 @@ static void *postcopy_ram_fault_thread(void *opaque)
                 break;
             }
 
-            rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
+            rb_offset = ROUND_DOWN(rb_offset, qemu_ram_pagesize(rb));
             trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
                                                 qemu_ram_get_idstr(rb),
                                                 rb_offset,
@@ -984,8 +1006,8 @@ retry:
              * Send the request to the source - we want to request one
              * of our host page sizes (which is >= TPS)
              */
-            ret = migrate_send_rp_req_pages(mis, rb, rb_offset,
-                                            msg.arg.pagefault.address);
+            ret = postcopy_request_page(mis, rb, rb_offset,
+                                        msg.arg.pagefault.address);
             if (ret) {
                 /* May be network failure, try to wait for recovery */
                 if (ret == -EIO && postcopy_pause_fault_thread(mis)) {
@@ -993,7 +1015,7 @@ retry:
                     goto retry;
                 } else {
                     /* This is a unavoidable fault */
-                    error_report("%s: migrate_send_rp_req_pages() get %d",
+                    error_report("%s: postcopy_request_page() get %d",
                                  __func__, ret);
                     break;
                 }