Migration pull 2021-02-08

v2
   Dropped vmstate: Fix memory leak in vmstate_handle_alloc
     Broke on Power
   Added migration: only check page size match if RAM postcopy is enabled
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEERfXHG0oMt/uXep+pBRYzHrxb/ecFAmAhIE4ACgkQBRYzHrxb
 /ecPuA/+Pgo++1ZSseJUgbLePwyTVc0jahdcvYEDmLUn8UM6ikBcBXBgUKHdkFW3
 bjSSVgB/xxvXSiafBK4xFNrCqSgqMSr3DJcHmvWgv2wVARcYf6Z26Da53LZq1Qru
 0tvRyb40Od1f9zb8Zj7e2Y3pjQ9ybLLbjfNhgnOBbQivqWkjZI31oV2KUCWY2+eV
 T1BEwr6mgYepqhmeB6OvQZtaQVC5toirS6NajNF4nt0vZEIGIvK6/A9erCVU8Tze
 5ch1J0MUqgc3q6ZSE/I9BHEy6MaL0X8G6H+ezjxdoRQtbt1iM/YqZJCSrXkAxiLC
 ROohryb6qVk26+UYuana79faLwrw359WlkwNEE6SEIRSENu+6p7bgN3LZuCILCO7
 xJEkeTgy6r40IGCkDC9aWa8pyLHpNX9gyLpGBHdIRD6zEOWaKNtzh7E2uo/T0ann
 BpcfgQOsYN25hIHiiXnxozUREbx71VDfMq7GqGB6eC3u2+a3U6jpSJb1nNq5NB89
 FJYLZy5Rbuy7OStMwfMsxRs7E63XvGgnwrN8FczU/pumCPX4lDYIpnocqinUmP8p
 XubRQQVaVDSKIq1mvzw7iR/1NsP9vfYvnrAIv941f38NBmDKqdPuMOXR/qB/Kp2Y
 jB7b1L5/JcXbWsQmK7fda9jmPzFwSO2cTeTiUonk9RfuuDEws0A=
 =4tbe
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20210208a' into staging

Migration pull 2021-02-08

v2
  Dropped vmstate: Fix memory leak in vmstate_handle_alloc
    Broke on Power
  Added migration: only check page size match if RAM postcopy is enabled

# gpg: Signature made Mon 08 Feb 2021 11:28:14 GMT
# 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-20210208a: (27 commits)
  migration: only check page size match if RAM postcopy is enabled
  migration: introduce snapshot-{save, load, delete} QMP commands
  iotests: fix loading of common.config from tests/ subdir
  iotests: add support for capturing and matching QMP events
  migration: introduce a delete_snapshot wrapper
  migration: wire up support for snapshot device selection
  migration: control whether snapshots are ovewritten
  block: rename and alter bdrv_all_find_snapshot semantics
  block: allow specifying name of block device for vmstate storage
  block: add ability to specify list of blockdevs during snapshot
  migration: stop returning errno from load_snapshot()
  migration: Make save_snapshot() return bool, not 0/-1
  block: push error reporting into bdrv_all_*_snapshot functions
  migration: Display the migration blockers
  migration: Add blocker information
  migration: Fix a few absurdly defective error messages
  migration: Fix cache_init()'s "Failed to allocate" error messages
  migration: Clean up signed vs. unsigned XBZRLE cache-size
  migration: Fix migrate-set-parameters argument validation
  migration: introduce 'userfaultfd-wrlat.py' script
  ...

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

scripts/userfaultfd-wrlat.py

@@ -0,0 +1,122 @@
+#!/usr/bin/python3
+#
+# userfaultfd-wrlat Summarize userfaultfd write fault latencies.
+#                   Events are continuously accumulated for the
+#                   run, while latency distribution histogram is
+#                   dumped each 'interval' seconds.
+#
+#                   For Linux, uses BCC, eBPF.
+#
+# USAGE: userfaultfd-lat [interval [count]]
+#
+# Copyright Virtuozzo GmbH, 2020
+#
+# Authors:
+#   Andrey Gruzdev   <andrey.gruzdev@virtuozzo.com>
+#
+# This work is licensed under the terms of the GNU GPL, version 2 or
+# later.  See the COPYING file in the top-level directory.
+
+from __future__ import print_function
+from bcc import BPF
+from ctypes import c_ushort, c_int, c_ulonglong
+from time import sleep
+from sys import argv
+
+def usage():
+    print("USAGE: %s [interval [count]]" % argv[0])
+    exit()
+
+# define BPF program
+bpf_text = """
+#include <uapi/linux/ptrace.h>
+#include <linux/mm.h>
+
+BPF_HASH(ev_start, u32, u64);
+BPF_HISTOGRAM(ev_delta_hist, u64);
+
+/* Trace UFFD page fault start event. */
+static void do_event_start()
+{
+    /* Using "(u32)" to drop group ID which is upper 32 bits */
+    u32 tid = (u32) bpf_get_current_pid_tgid();
+    u64 ts = bpf_ktime_get_ns();
+
+    ev_start.update(&tid, &ts);
+}
+
+/* Trace UFFD page fault end event. */
+static void do_event_end()
+{
+    /* Using "(u32)" to drop group ID which is upper 32 bits */
+    u32 tid = (u32) bpf_get_current_pid_tgid();
+    u64 ts = bpf_ktime_get_ns();
+    u64 *tsp;
+
+    tsp = ev_start.lookup(&tid);
+    if (tsp) {
+        u64 delta = ts - (*tsp);
+        /* Transform time delta to milliseconds */
+        ev_delta_hist.increment(bpf_log2l(delta / 1000000));
+        ev_start.delete(&tid);
+    }
+}
+
+/* KPROBE for handle_userfault(). */
+int probe_handle_userfault(struct pt_regs *ctx, struct vm_fault *vmf,
+        unsigned long reason)
+{
+    /* Trace only UFFD write faults. */
+    if (reason & VM_UFFD_WP) {
+        do_event_start();
+    }
+    return 0;
+}
+
+/* KRETPROBE for handle_userfault(). */
+int retprobe_handle_userfault(struct pt_regs *ctx)
+{
+    do_event_end();
+    return 0;
+}
+"""
+
+# arguments
+interval = 10
+count = -1
+if len(argv) > 1:
+    try:
+        interval = int(argv[1])
+        if interval == 0:
+            raise
+        if len(argv) > 2:
+            count = int(argv[2])
+    except:    # also catches -h, --help
+        usage()
+
+# load BPF program
+b = BPF(text=bpf_text)
+# attach KRPOBEs
+b.attach_kprobe(event="handle_userfault", fn_name="probe_handle_userfault")
+b.attach_kretprobe(event="handle_userfault", fn_name="retprobe_handle_userfault")
+
+# header
+print("Tracing UFFD-WP write fault latency... Hit Ctrl-C to end.")
+
+# output
+loop = 0
+do_exit = 0
+while (1):
+    if count > 0:
+        loop += 1
+        if loop > count:
+            exit()
+    try:
+        sleep(interval)
+    except KeyboardInterrupt:
+        pass; do_exit = 1
+
+    print()
+    b["ev_delta_hist"].print_log2_hist("msecs")
+    if do_exit:
+        exit()