Merge tag 'migration-20230412-pull-request' of https://gitlab.com/juan.quintela/qemu into staging
Migration Pull request for 8.0
Last patches found:
- peter xu preempt channel fixes.
needed for backward compatibility with old machine types.
- lukas fix to get compress working again.
- fix ram on s390x. Get back to the old code, even when it shouldn't
be needed, but as it fails on s390x, just revert.
Later, Juan.
# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmQ3HgQACgkQ9IfvGFhy
# 1yPXGQ/+Pf6HepNUlIr7naYOcpRriXPQF+q1zqo74F9fy2vrGcwJOI6qmRTjsX4E
# 9KgXipOz7+b5wSemF7PDKcnBiwyt6UHCH+XXe0h4TpyuORbtABKRgtOhA1/sa84D
# HnKp0TwImpAO26tzPa7u49aau/EEVBKAzFVcyn4w56S9qiDWicOpd5kG0CJBIsMJ
# Mnvy5fXaqQRewnKiwFoJGWfyhzEToDO6Z/SkT5xYON94P+eiM2xMwXOC5WcGfmY7
# wFGDB+SuyEP8TTn7mV0mmnlFjYe4G07hVARHSDFX3ho4b6q5F+WzfW095G6QKiu9
# n3Pzr7IBGX3sgetPtYwOwGsE9JrfHMFzBRxQZZwq5GSmjk7+agkbXmV7RyV82EYs
# KYOhuNF91ca0qvCrGA/eGbbJqVrd7SR5FhS4SQ7oKd5n2au/ZHoKwAgm5lBdcvES
# 2TB0MBN1s0JPh6KMV8tPB2miZyqPRa++oA8qIX7Asoe1X4xVT1FwiDaFL8TO8i2A
# 7uBis3KLZqOHC6dAiXlCDtaADAWgQxjcdoS1l8jTF6MgBSe+zQhXG+pcIDuSiV9N
# WfDiUPY97iqPTvpzdz3Is+LbBax2uY5ZR05KSdmCBpIgfvSWMqXtwRydclt6G5h7
# ZiOcTwrgMpXdbhdsFZTqVWAJG2sTkj4TA+IezVpXzPeQNLZ+T8k=
# =kW3P
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 12 Apr 2023 22:09:24 BST
# gpg: using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [full]
# gpg: aka "Juan Quintela <quintela@trasno.org>" [full]
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03 4B82 F487 EF18 5872 D723
* tag 'migration-20230412-pull-request' of https://gitlab.com/juan.quintela/qemu:
migration: fix ram_state_pending_exact()
migration/ram.c: Fix migration with compress enabled
migration: Recover behavior of preempt channel creation for pre-7.2
migration: Fix potential race on postcopy_qemufile_src
io: tls: Inherit QIO_CHANNEL_FEATURE_SHUTDOWN on server side
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 45e3d24..cd13b8b 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -42,6 +42,7 @@
GlobalProperty hw_compat_7_2[] = {
{ "e1000e", "migrate-timadj", "off" },
{ "virtio-mem", "x-early-migration", "false" },
+ { "migration", "x-preempt-pre-7-2", "true" },
};
const size_t hw_compat_7_2_len = G_N_ELEMENTS(hw_compat_7_2);
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 5a7a3d4..9805dd0 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -74,6 +74,9 @@
ioc = QIO_CHANNEL_TLS(object_new(TYPE_QIO_CHANNEL_TLS));
ioc->master = master;
+ if (qio_channel_has_feature(master, QIO_CHANNEL_FEATURE_SHUTDOWN)) {
+ qio_channel_set_feature(QIO_CHANNEL(ioc), QIO_CHANNEL_FEATURE_SHUTDOWN);
+ }
object_ref(OBJECT(master));
ioc->session = qcrypto_tls_session_new(
diff --git a/migration/migration.c b/migration/migration.c
index ae2025d..bda4789 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3464,8 +3464,12 @@
qemu_savevm_state_complete_postcopy(s->to_dst_file);
qemu_mutex_unlock_iothread();
- /* Shutdown the postcopy fast path thread */
- if (migrate_postcopy_preempt()) {
+ /*
+ * Shutdown the postcopy fast path thread. This is only needed
+ * when dest QEMU binary is old (7.1/7.2). QEMU 8.0+ doesn't need
+ * this.
+ */
+ if (migrate_postcopy_preempt() && s->preempt_pre_7_2) {
postcopy_preempt_shutdown_file(s);
}
@@ -4384,6 +4388,15 @@
}
}
+ /*
+ * This needs to be done before resuming a postcopy. Note: for newer
+ * QEMUs we will delay the channel creation until postcopy_start(), to
+ * avoid disorder of channel creations.
+ */
+ if (migrate_postcopy_preempt() && s->preempt_pre_7_2) {
+ postcopy_preempt_setup(s);
+ }
+
if (resume) {
/* Wakeup the main migration thread to do the recovery */
migrate_set_state(&s->state, MIGRATION_STATUS_POSTCOPY_PAUSED,
@@ -4443,6 +4456,8 @@
decompress_error_check, true),
DEFINE_PROP_UINT8("x-clear-bitmap-shift", MigrationState,
clear_bitmap_shift, CLEAR_BITMAP_SHIFT_DEFAULT),
+ DEFINE_PROP_BOOL("x-preempt-pre-7-2", MigrationState,
+ preempt_pre_7_2, false),
/* Migration parameters */
DEFINE_PROP_UINT8("x-compress-level", MigrationState,
diff --git a/migration/migration.h b/migration/migration.h
index 2da2f8a..310ae89 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -65,6 +65,12 @@
bool all_zero;
} PostcopyTmpPage;
+typedef enum {
+ PREEMPT_THREAD_NONE = 0,
+ PREEMPT_THREAD_CREATED,
+ PREEMPT_THREAD_QUIT,
+} PreemptThreadStatus;
+
/* State for the incoming migration */
struct MigrationIncomingState {
QEMUFile *from_src_file;
@@ -124,7 +130,12 @@
QemuSemaphore postcopy_qemufile_dst_done;
/* Postcopy priority thread is used to receive postcopy requested pages */
QemuThread postcopy_prio_thread;
- bool postcopy_prio_thread_created;
+ /*
+ * Always set by the main vm load thread only, but can be read by the
+ * postcopy preempt thread. "volatile" makes sure all reads will be
+ * uptodate across cores.
+ */
+ volatile PreemptThreadStatus preempt_thread_status;
/*
* Used to sync between the ram load main thread and the fast ram load
* thread. It protects postcopy_qemufile_dst, which is the postcopy
@@ -364,6 +375,34 @@
* do not trigger spurious decompression errors.
*/
bool decompress_error_check;
+ /*
+ * This variable only affects behavior when postcopy preempt mode is
+ * enabled.
+ *
+ * When set:
+ *
+ * - postcopy preempt src QEMU instance will generate an EOS message at
+ * the end of migration to shut the preempt channel on dest side.
+ *
+ * - postcopy preempt channel will be created at the setup phase on src
+ QEMU.
+ *
+ * When clear:
+ *
+ * - postcopy preempt src QEMU instance will _not_ generate an EOS
+ * message at the end of migration, the dest qemu will shutdown the
+ * channel itself.
+ *
+ * - postcopy preempt channel will be created at the switching phase
+ * from precopy -> postcopy (to avoid race condtion of misordered
+ * creation of channels).
+ *
+ * NOTE: See message-id <ZBoShWArKDPpX/D7@work-vm> on qemu-devel
+ * mailing list for more information on the possible race. Everyone
+ * should probably just keep this value untouched after set by the
+ * machine type (or the default).
+ */
+ bool preempt_pre_7_2;
/*
* This decides the size of guest memory chunk that will be used
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 41c0713..93f39f8 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -568,9 +568,14 @@
{
trace_postcopy_ram_incoming_cleanup_entry();
- if (mis->postcopy_prio_thread_created) {
+ if (mis->preempt_thread_status == PREEMPT_THREAD_CREATED) {
+ /* Notify the fast load thread to quit */
+ mis->preempt_thread_status = PREEMPT_THREAD_QUIT;
+ if (mis->postcopy_qemufile_dst) {
+ qemu_file_shutdown(mis->postcopy_qemufile_dst);
+ }
qemu_thread_join(&mis->postcopy_prio_thread);
- mis->postcopy_prio_thread_created = false;
+ mis->preempt_thread_status = PREEMPT_THREAD_NONE;
}
if (mis->have_fault_thread) {
@@ -1203,7 +1208,7 @@
*/
postcopy_thread_create(mis, &mis->postcopy_prio_thread, "fault-fast",
postcopy_preempt_thread, QEMU_THREAD_JOINABLE);
- mis->postcopy_prio_thread_created = true;
+ mis->preempt_thread_status = PREEMPT_THREAD_CREATED;
}
trace_postcopy_ram_enable_notify();
@@ -1625,8 +1630,14 @@
return 0;
}
- /* Kick off async task to establish preempt channel */
- postcopy_preempt_setup(s);
+ /*
+ * Kick off async task to establish preempt channel. Only do so with
+ * 8.0+ machines, because 7.1/7.2 require the channel to be created in
+ * setup phase of migration (even if racy in an unreliable network).
+ */
+ if (!s->preempt_pre_7_2) {
+ postcopy_preempt_setup(s);
+ }
/*
* We need the postcopy preempt channel to be established before
@@ -1652,6 +1663,11 @@
trace_postcopy_pause_fast_load_continued();
}
+static bool preempt_thread_should_run(MigrationIncomingState *mis)
+{
+ return mis->preempt_thread_status != PREEMPT_THREAD_QUIT;
+}
+
void *postcopy_preempt_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
@@ -1671,11 +1687,11 @@
/* Sending RAM_SAVE_FLAG_EOS to terminate this thread */
qemu_mutex_lock(&mis->postcopy_prio_thread_mutex);
- while (1) {
+ while (preempt_thread_should_run(mis)) {
ret = ram_load_postcopy(mis->postcopy_qemufile_dst,
RAM_CHANNEL_POSTCOPY);
/* If error happened, go into recovery routine */
- if (ret) {
+ if (ret && preempt_thread_should_run(mis)) {
postcopy_pause_ram_fast_load(mis);
} else {
/* We're done */
diff --git a/migration/ram.c b/migration/ram.c
index 96e8a19..79d881f 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -688,12 +688,11 @@
* @offset: offset inside the block for the page
* in the lower bits, it contains flags
*/
-static size_t save_page_header(PageSearchStatus *pss, RAMBlock *block,
- ram_addr_t offset)
+static size_t save_page_header(PageSearchStatus *pss, QEMUFile *f,
+ RAMBlock *block, ram_addr_t offset)
{
size_t size, len;
bool same_block = (block == pss->last_sent_block);
- QEMUFile *f = pss->pss_channel;
if (same_block) {
offset |= RAM_SAVE_FLAG_CONTINUE;
@@ -867,7 +866,7 @@
}
/* Send XBZRLE based compressed page */
- bytes_xbzrle = save_page_header(pss, block,
+ bytes_xbzrle = save_page_header(pss, pss->pss_channel, block,
offset | RAM_SAVE_FLAG_XBZRLE);
qemu_put_byte(file, ENCODING_FLAG_XBZRLE);
qemu_put_be16(file, encoded_len);
@@ -1302,15 +1301,14 @@
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
*/
-static int save_zero_page_to_file(PageSearchStatus *pss,
+static int save_zero_page_to_file(PageSearchStatus *pss, QEMUFile *file,
RAMBlock *block, ram_addr_t offset)
{
uint8_t *p = block->host + offset;
- QEMUFile *file = pss->pss_channel;
int len = 0;
if (buffer_is_zero(p, TARGET_PAGE_SIZE)) {
- len += save_page_header(pss, block, offset | RAM_SAVE_FLAG_ZERO);
+ len += save_page_header(pss, file, block, offset | RAM_SAVE_FLAG_ZERO);
qemu_put_byte(file, 0);
len += 1;
ram_release_page(block->idstr, offset);
@@ -1327,10 +1325,10 @@
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
*/
-static int save_zero_page(PageSearchStatus *pss, RAMBlock *block,
+static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block,
ram_addr_t offset)
{
- int len = save_zero_page_to_file(pss, block, offset);
+ int len = save_zero_page_to_file(pss, f, block, offset);
if (len) {
stat64_add(&ram_atomic_counters.duplicate, 1);
@@ -1394,7 +1392,7 @@
{
QEMUFile *file = pss->pss_channel;
- ram_transferred_add(save_page_header(pss, block,
+ 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,
@@ -1473,11 +1471,11 @@
uint8_t *p = block->host + offset;
int ret;
- if (save_zero_page_to_file(pss, block, offset)) {
+ if (save_zero_page_to_file(pss, f, block, offset)) {
return true;
}
- save_page_header(pss, block, offset | RAM_SAVE_FLAG_COMPRESS_PAGE);
+ save_page_header(pss, f, block, offset | RAM_SAVE_FLAG_COMPRESS_PAGE);
/*
* copy it to a internal buffer to avoid it being modified by VM
@@ -2355,7 +2353,7 @@
return 1;
}
- res = save_zero_page(pss, block, offset);
+ res = save_zero_page(pss, pss->pss_channel, block, offset);
if (res > 0) {
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
@@ -3508,12 +3506,13 @@
static void ram_state_pending_exact(void *opaque, uint64_t *must_precopy,
uint64_t *can_postcopy)
{
+ MigrationState *s = migrate_get_current();
RAMState **temp = opaque;
RAMState *rs = *temp;
uint64_t remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
- if (!migration_in_postcopy()) {
+ if (!migration_in_postcopy() && remaining_size < s->threshold_size) {
qemu_mutex_lock_iothread();
WITH_RCU_READ_LOCK_GUARD() {
migration_bitmap_sync_precopy(rs);
