qemu-kvm/kvm-Revert-migration-Simplify-unqueue_page.patch

135 lines
5.4 KiB
Diff
Raw Normal View History

From 5ea59b17866add54e5ae8c76d3cb472c67e1fa91 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Tue, 2 Aug 2022 08:19:49 +0200
Subject: [PATCH 32/32] Revert "migration: Simplify unqueue_page()"
RH-Author: Thomas Huth <thuth@redhat.com>
RH-MergeRequest: 112: Fix postcopy migration on s390x
RH-Commit: [2/2] 3913c9ed3f27f4b66245913da29d0c46db0c6567 (thuth/qemu-kvm-cs9)
RH-Bugzilla: 2099934
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Cornelia Huck <cohuck@redhat.com>
RH-Acked-by: David Hildenbrand <david@redhat.com>
RH-Acked-by: Peter Xu <peterx@redhat.com>
This reverts commit cfd66f30fb0f735df06ff4220e5000290a43dad3.
The simplification of unqueue_page() introduced a bug that sometimes
breaks migration on s390x hosts.
The problem is not fully understood yet, but since we are already in
the freeze for QEMU 7.1 and we need something working there, let's
revert this patch for the upcoming release. The optimization can be
redone later again in a proper way if necessary.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2099934
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20220802061949.331576-1-thuth@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 777f53c75983dd10756f5dbfc8af50fe11da81c1)
Conflicts:
migration/trace-events
(trivial contextual conflict)
Signed-off-by: Thomas Huth <thuth@redhat.com>
---
migration/ram.c | 37 ++++++++++++++++++++++++++-----------
migration/trace-events | 3 ++-
2 files changed, 28 insertions(+), 12 deletions(-)
diff --git a/migration/ram.c b/migration/ram.c
index fb6db54642..ee40e4a718 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1548,7 +1548,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
{
struct RAMSrcPageRequest *entry;
RAMBlock *block = NULL;
- size_t page_size;
if (!postcopy_has_request(rs)) {
return NULL;
@@ -1565,13 +1564,10 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
entry = QSIMPLEQ_FIRST(&rs->src_page_requests);
block = entry->rb;
*offset = entry->offset;
- page_size = qemu_ram_pagesize(block);
- /* Each page request should only be multiple page size of the ramblock */
- assert((entry->len % page_size) == 0);
- if (entry->len > page_size) {
- entry->len -= page_size;
- entry->offset += page_size;
+ if (entry->len > TARGET_PAGE_SIZE) {
+ entry->len -= TARGET_PAGE_SIZE;
+ entry->offset += TARGET_PAGE_SIZE;
} else {
memory_region_unref(block->mr);
QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
@@ -1579,9 +1575,6 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
migration_consume_urgent_request();
}
- trace_unqueue_page(block->idstr, *offset,
- test_bit((*offset >> TARGET_PAGE_BITS), block->bmap));
-
return block;
}
@@ -1956,8 +1949,30 @@ static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
{
RAMBlock *block;
ram_addr_t offset;
+ bool dirty;
+
+ do {
+ block = unqueue_page(rs, &offset);
+ /*
+ * We're sending this page, and since it's postcopy nothing else
+ * will dirty it, and we must make sure it doesn't get sent again
+ * even if this queue request was received after the background
+ * search already sent it.
+ */
+ if (block) {
+ unsigned long page;
+
+ page = offset >> TARGET_PAGE_BITS;
+ dirty = test_bit(page, block->bmap);
+ if (!dirty) {
+ trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset,
+ page);
+ } else {
+ trace_get_queued_page(block->idstr, (uint64_t)offset, page);
+ }
+ }
- block = unqueue_page(rs, &offset);
+ } while (block && !dirty);
if (!block) {
/*
diff --git a/migration/trace-events b/migration/trace-events
index 1aec580e92..09d61ed1f4 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -85,6 +85,8 @@ put_qlist_end(const char *field_name, const char *vmsd_name) "%s(%s)"
qemu_file_fclose(void) ""
# ram.c
+get_queued_page(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
+get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/0x%" PRIx64 " page_abs=0x%lx"
migration_bitmap_sync_start(void) ""
migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
migration_bitmap_clear_dirty(char *str, uint64_t start, uint64_t size, unsigned long page) "rb %s start 0x%"PRIx64" size 0x%"PRIx64" page 0x%lx"
@@ -110,7 +112,6 @@ ram_save_iterate_big_wait(uint64_t milliconds, int iterations) "big wait: %" PRI
ram_load_complete(int ret, uint64_t seq_iter) "exit_code %d seq iteration %" PRIu64
ram_write_tracking_ramblock_start(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
ram_write_tracking_ramblock_stop(const char *block_id, size_t page_size, void *addr, size_t length) "%s: page_size: %zu addr: %p length: %zu"
-unqueue_page(char *block, uint64_t offset, bool dirty) "ramblock '%s' offset 0x%"PRIx64" dirty %d"
# multifd.c
multifd_new_send_channel_async(uint8_t id) "channel %u"
--
2.31.1