Merge tag 'pull-replay-fixes-080124-1' of https://gitlab.com/stsquad/qemu into staging

Record/replay fixes for replay_kernel tests

  - add a 32 bit x86 replay test case
  - fix some typos
  - use modern snapshot setting for tests
  - update replay_dump for current ABI
  - remove stale replay variables
  - improve kdoc for ReplayState
  - introduce common error path for replay
  - always fully drain chardevs when in replay
  - catch unexpected waitio on playback
  - remove flaky tags from replay_kernel tests

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCgAdFiEEZoWumedRZ7yvyN81+9DbCVqeKkQFAmWcAJgACgkQ+9DbCVqe
# KkS/TQf+PuIPtuX71ENajfRBjz6450IbGqLUJ1HEaPGYGRj+fR6rg5g5u8qaBrT7
# TUv9ef9L22NtyL+Gbs1OGpGDWKoqV6RQc+A/MHa8IKFpcS24nUo3k4psIC6NSGRH
# 6w3++fPC1Q5cDk9Lei3Qt8fXzcnUZz+NTiIK05aC0xh7D6uGfdADvKqHeLav7qi+
# X2ztNdBsy/WJWCuWcMVzb/dGwDBtuyyxvqTD4EF+zn+gSYq9od2G8XdF+0o6ZVLM
# mXEHwNwB6UjOkLt2cYaay59SXcJFvwxKbEGTDnA7T+kgd3rknuBaWdVBIazoSPQh
# +522nPz5qq/3wO1l7+iQXuvd38fWyw==
# =nKRx
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 08 Jan 2024 14:03:04 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* tag 'pull-replay-fixes-080124-1' of https://gitlab.com/stsquad/qemu:
  tests/avocado: remove skips from replay_kernel
  chardev: force write all when recording replay logs
  replay: stop us hanging in rr_wait_io_event
  replay/replay-char: use report_sync_error
  replay: introduce a central report point for sync errors
  replay: make has_unread_data a bool
  replay: add proper kdoc for ReplayState
  replay: remove host_clock_last
  scripts/replay_dump: track total number of instructions
  scripts/replay-dump: update to latest format
  tests/avocado: modernise the drive args for replay_linux
  tests/avocado: fix typo in replay_linux
  tests/avocado: add a simple i386 replay kernel test

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

accel/tcg/tcg-accel-ops-rr.c

@@ -109,7 +109,7 @@ static void rr_wait_io_event(void)
 {
     CPUState *cpu;
 
-    while (all_cpu_threads_idle()) {
+    while (all_cpu_threads_idle() && replay_can_wait()) {
         rr_stop_kick_timer();
         qemu_cond_wait_iothread(first_cpu->halt_cond);
     }

chardev/char.c

@@ -171,6 +171,18 @@ int qemu_chr_write(Chardev *s, const uint8_t *buf, int len, bool write_all)
         return res;
     }
 
+    if (replay_mode == REPLAY_MODE_RECORD) {
+        /*
+         * When recording we don't want temporary conditions to
+         * perturb the result. By ensuring we write everything we can
+         * while recording we avoid playback being out of sync if it
+         * doesn't encounter the same temporary conditions (usually
+         * triggered by external programs not reading the chardev fast
+         * enough and pipes filling up).
+         */
+        write_all = true;
+    }
+
     res = qemu_chr_write_buffer(s, buf, len, &offset, write_all);
 
     if (qemu_chr_replay(s) && replay_mode == REPLAY_MODE_RECORD) {

include/sysemu/replay.h

@@ -70,6 +70,11 @@ int replay_get_instructions(void);
 /*! Updates instructions counter in replay mode. */
 void replay_account_executed_instructions(void);
 
+/**
+ * replay_can_wait: check if we should pause for wait-io
+ */
+bool replay_can_wait(void);
+
 /* Processing clocks and other time sources */
 
 /*! Save the specified clock */

replay/replay-char.c

@@ -113,8 +113,7 @@ void replay_char_write_event_load(int *res, int *offset)
         *offset = replay_get_dword();
         replay_finish_event();
     } else {
-        error_report("Missing character write event in the replay log");
-        exit(1);
+        replay_sync_error("Missing character write event in the replay log");
     }
 }
 
@@ -135,8 +134,7 @@ int replay_char_read_all_load(uint8_t *buf)
         replay_finish_event();
         return res;
     } else {
-        error_report("Missing character read all event in the replay log");
-        exit(1);
+        replay_sync_error("Missing character read all event in the replay log");
     }
 }
 

replay/replay-internal.c

@@ -175,11 +175,12 @@ void replay_fetch_data_kind(void)
     if (replay_file) {
         if (!replay_state.has_unread_data) {
             replay_state.data_kind = replay_get_byte();
+            replay_state.current_event++;
             if (replay_state.data_kind == EVENT_INSTRUCTION) {
                 replay_state.instruction_count = replay_get_dword();
             }
             replay_check_error();
-            replay_state.has_unread_data = 1;
+            replay_state.has_unread_data = true;
             if (replay_state.data_kind >= EVENT_COUNT) {
                 error_report("Replay: unknown event kind %d",
                              replay_state.data_kind);
@@ -191,7 +192,7 @@ void replay_fetch_data_kind(void)
 
 void replay_finish_event(void)
 {
-    replay_state.has_unread_data = 0;
+    replay_state.has_unread_data = false;
     replay_fetch_data_kind();
 }
 

replay/replay-internal.h

@@ -25,7 +25,12 @@ typedef enum ReplayAsyncEventKind {
     REPLAY_ASYNC_COUNT
 } ReplayAsyncEventKind;
 
-/* Any changes to order/number of events will need to bump REPLAY_VERSION */
+/*
+ * Any changes to order/number of events will need to bump
+ * REPLAY_VERSION to prevent confusion with old logs. Also don't
+ * forget to update replay_event_name() to make your debugging life
+ * easier.
+ */
 enum ReplayEvents {
     /* for instruction event */
     EVENT_INSTRUCTION,
@@ -63,26 +68,33 @@ enum ReplayEvents {
     EVENT_COUNT
 };
 
+/**
+ * typedef ReplayState - global tracking Replay state
+ *
+ * This structure tracks where we are in the current ReplayState
+ * including the logged events from the recorded replay stream. Some
+ * of the data is also stored/restored from VMStateDescription when VM
+ * save/restore events take place.
+ *
+ * @cached_clock: Cached clocks values
+ * @current_icount: number of processed instructions
+ * @instruction_count: number of instructions until next event
+ * @current_event: current event index
+ * @data_kind: current event
+ * @has_unread_data: true if event not yet processed
+ * @file_offset: offset into replay log at replay snapshot
+ * @block_request_id: current serialised block request id
+ * @read_event_id: current async read event id
+ */
 typedef struct ReplayState {
-    /*! Cached clock values. */
     int64_t cached_clock[REPLAY_CLOCK_COUNT];
-    /*! Current icount - number of processed instructions. */
     uint64_t current_icount;
-    /*! Number of instructions to be executed before other events happen. */
     int instruction_count;
-    /*! Type of the currently executed event. */
+    unsigned int current_event;
     unsigned int data_kind;
-    /*! Flag which indicates that event is not processed yet. */
-    unsigned int has_unread_data;
-    /*! Temporary variable for saving current log offset. */
+    bool has_unread_data;
     uint64_t file_offset;
-    /*! Next block operation id.
-        This counter is global, because requests from different
-        block devices should not get overlapping ids. */
     uint64_t block_request_id;
-    /*! Prior value of the host clock */
-    uint64_t host_clock_last;
-    /*! Asynchronous event id read from the log */
     uint64_t read_event_id;
 } ReplayState;
 extern ReplayState replay_state;
@@ -183,6 +195,16 @@ void replay_event_net_save(void *opaque);
 /*! Reads network from the file. */
 void *replay_event_net_load(void);
 
+/* Diagnostics */
+
+/**
+ * replay_sync_error(): report sync error and exit
+ *
+ * When we reach an error condition we want to report it centrally so
+ * we can also dump some useful information into the logs.
+ */
+G_NORETURN void replay_sync_error(const char *error);
+
 /* VMState-related functions */
 
 /* Registers replay VMState.

replay/replay-snapshot.c

@@ -47,16 +47,17 @@ static int replay_post_load(void *opaque, int version_id)
 
 static const VMStateDescription vmstate_replay = {
     .name = "replay",
-    .version_id = 2,
-    .minimum_version_id = 2,
+    .version_id = 3,
+    .minimum_version_id = 3,
     .pre_save = replay_pre_save,
     .post_load = replay_post_load,
     .fields = (const VMStateField[]) {
         VMSTATE_INT64_ARRAY(cached_clock, ReplayState, REPLAY_CLOCK_COUNT),
         VMSTATE_UINT64(current_icount, ReplayState),
         VMSTATE_INT32(instruction_count, ReplayState),
+        VMSTATE_UINT32(current_event, ReplayState),
         VMSTATE_UINT32(data_kind, ReplayState),
-        VMSTATE_UINT32(has_unread_data, ReplayState),
+        VMSTATE_BOOL(has_unread_data, ReplayState),
         VMSTATE_UINT64(file_offset, ReplayState),
         VMSTATE_UINT64(block_request_id, ReplayState),
         VMSTATE_UINT64(read_event_id, ReplayState),

replay/replay.c

@@ -38,6 +38,107 @@ static GSList *replay_blockers;
 uint64_t replay_break_icount = -1ULL;
 QEMUTimer *replay_break_timer;
 
+/* Pretty print event names */
+
+static const char *replay_async_event_name(ReplayAsyncEventKind event)
+{
+    switch (event) {
+#define ASYNC_EVENT(_x) case REPLAY_ASYNC_EVENT_ ## _x: return "ASYNC_EVENT_"#_x
+        ASYNC_EVENT(BH);
+        ASYNC_EVENT(BH_ONESHOT);
+        ASYNC_EVENT(INPUT);
+        ASYNC_EVENT(INPUT_SYNC);
+        ASYNC_EVENT(CHAR_READ);
+        ASYNC_EVENT(BLOCK);
+        ASYNC_EVENT(NET);
+#undef ASYNC_EVENT
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static const char *replay_clock_event_name(ReplayClockKind clock)
+{
+    switch (clock) {
+#define CLOCK_EVENT(_x) case REPLAY_CLOCK_ ## _x: return "CLOCK_" #_x
+        CLOCK_EVENT(HOST);
+        CLOCK_EVENT(VIRTUAL_RT);
+#undef CLOCK_EVENT
+    default:
+        g_assert_not_reached();
+    }
+}
+
+/* Pretty print shutdown event names */
+static const char *replay_shutdown_event_name(ShutdownCause cause)
+{
+    switch (cause) {
+#define SHUTDOWN_EVENT(_x) case SHUTDOWN_CAUSE_ ## _x: return "SHUTDOWN_CAUSE_" #_x
+        SHUTDOWN_EVENT(NONE);
+        SHUTDOWN_EVENT(HOST_ERROR);
+        SHUTDOWN_EVENT(HOST_QMP_QUIT);
+        SHUTDOWN_EVENT(HOST_QMP_SYSTEM_RESET);
+        SHUTDOWN_EVENT(HOST_SIGNAL);
+        SHUTDOWN_EVENT(HOST_UI);
+        SHUTDOWN_EVENT(GUEST_SHUTDOWN);
+        SHUTDOWN_EVENT(GUEST_RESET);
+        SHUTDOWN_EVENT(GUEST_PANIC);
+        SHUTDOWN_EVENT(SUBSYSTEM_RESET);
+        SHUTDOWN_EVENT(SNAPSHOT_LOAD);
+#undef SHUTDOWN_EVENT
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static const char *replay_checkpoint_event_name(enum ReplayCheckpoint checkpoint)
+{
+    switch (checkpoint) {
+#define CHECKPOINT_EVENT(_x) case CHECKPOINT_ ## _x: return "CHECKPOINT_" #_x
+        CHECKPOINT_EVENT(CLOCK_WARP_START);
+        CHECKPOINT_EVENT(CLOCK_WARP_ACCOUNT);
+        CHECKPOINT_EVENT(RESET_REQUESTED);
+        CHECKPOINT_EVENT(SUSPEND_REQUESTED);
+        CHECKPOINT_EVENT(CLOCK_VIRTUAL);
+        CHECKPOINT_EVENT(CLOCK_HOST);
+        CHECKPOINT_EVENT(CLOCK_VIRTUAL_RT);
+        CHECKPOINT_EVENT(INIT);
+        CHECKPOINT_EVENT(RESET);
+#undef CHECKPOINT_EVENT
+    default:
+        g_assert_not_reached();
+    }
+}
+
+static const char *replay_event_name(enum ReplayEvents event)
+{
+    /* First deal with the simple ones */
+    switch (event) {
+#define EVENT(_x) case EVENT_ ## _x: return "EVENT_"#_x
+        EVENT(INSTRUCTION);
+        EVENT(INTERRUPT);
+        EVENT(EXCEPTION);
+        EVENT(CHAR_WRITE);
+        EVENT(CHAR_READ_ALL);
+        EVENT(AUDIO_OUT);
+        EVENT(AUDIO_IN);
+        EVENT(RANDOM);
+#undef EVENT
+    default:
+        if (event >= EVENT_ASYNC && event <= EVENT_ASYNC_LAST) {
+            return replay_async_event_name(event - EVENT_ASYNC);
+        } else if (event >= EVENT_SHUTDOWN && event <= EVENT_SHUTDOWN_LAST) {
+            return replay_shutdown_event_name(event - EVENT_SHUTDOWN);
+        } else if (event >= EVENT_CLOCK && event <= EVENT_CLOCK_LAST) {
+            return replay_clock_event_name(event - EVENT_CLOCK);
+        } else if (event >= EVENT_CHECKPOINT && event <= EVENT_CHECKPOINT_LAST) {
+            return replay_checkpoint_event_name(event - EVENT_CHECKPOINT);
+        }
+    }
+
+    g_assert_not_reached();
+}
+
 bool replay_next_event_is(int event)
 {
     bool res = false;
@@ -226,6 +327,15 @@ bool replay_has_event(void)
     return res;
 }
 
+G_NORETURN void replay_sync_error(const char *error)
+{
+    error_report("%s (insn total %"PRId64"/%d left, event %d is %s)", error,
+                 replay_state.current_icount, replay_state.instruction_count,
+                 replay_state.current_event,
+                 replay_event_name(replay_state.data_kind));
+    abort();
+}
+
 static void replay_enable(const char *fname, int mode)
 {
     const char *fmode = NULL;
@@ -258,6 +368,7 @@ static void replay_enable(const char *fname, int mode)
     replay_state.data_kind = -1;
     replay_state.instruction_count = 0;
     replay_state.current_icount = 0;
+    replay_state.current_event = 0;
     replay_state.has_unread_data = 0;
 
     /* skip file header for RECORD and check it for PLAY */
@@ -338,6 +449,27 @@ void replay_start(void)
     replay_enable_events();
 }
 
+/*
+ * For none/record the answer is yes.
+ */
+bool replay_can_wait(void)
+{
+    if (replay_mode == REPLAY_MODE_PLAY) {
+        /*
+         * For playback we shouldn't ever be at a point we wait. If
+         * the instruction count has reached zero and we have an
+         * unconsumed event we should go around again and consume it.
+         */
+        if (replay_state.instruction_count == 0 && replay_state.has_unread_data) {
+            return false;
+        } else {
+            replay_sync_error("Playback shouldn't have to iowait");
+        }
+    }
+    return true;
+}
+
+
 void replay_finish(void)
 {
     if (replay_mode == REPLAY_MODE_NONE) {

scripts/replay-dump.py

@@ -21,6 +21,7 @@
 import argparse
 import struct
 from collections import namedtuple
+from os import path
 
 # This mirrors some of the global replay state which some of the
 # stream loading refers to. Some decoders may read the next event so
@@ -82,6 +83,12 @@ def read_qword(fin):
     "Read a 64 bit word"
     return struct.unpack('>Q', fin.read(8))[0]
 
+def read_array(fin):
+    "Read a sized array"
+    size = read_dword(fin)
+    data = fin.read(size)
+    return data
+
 # Generic decoder structure
 Decoder = namedtuple("Decoder", "eid name fn")
 
@@ -115,6 +122,11 @@ def decode_unimp(eid, name, _unused_dumpfile):
     print("%s not handled - will now stop" % (name))
     return False
 
+def decode_plain(eid, name, _unused_dumpfile):
+    "Plain events without additional data"
+    print_event(eid, name, "no data")
+    return True
+
 # Checkpoint decoder
 def swallow_async_qword(eid, name, dumpfile):
     "Swallow a qword of data without looking at it"
@@ -145,10 +157,19 @@ def decode_async(eid, name, dumpfile):
 
     return call_decode(async_decode_table, async_event_kind, dumpfile)
 
+total_insns = 0
 
 def decode_instruction(eid, name, dumpfile):
+    global total_insns
     ins_diff = read_dword(dumpfile)
-    print_event(eid, name, "0x%x" % (ins_diff))
+    total_insns += ins_diff
+    print_event(eid, name, "+ %d -> %d" % (ins_diff, total_insns))
+    return True
+
+def decode_char_write(eid, name, dumpfile):
+    res = read_dword(dumpfile)
+    offset = read_dword(dumpfile)
+    print_event(eid, name, "%d -> %d" % (offset, res))
     return True
 
 def decode_audio_out(eid, name, dumpfile):
@@ -189,14 +210,19 @@ def decode_clock(eid, name, dumpfile):
     print_event(eid, name, "0x%x" % (clock_data))
     return True
 
+def decode_random(eid, name, dumpfile):
+    ret = read_dword(dumpfile)
+    data = read_array(dumpfile)
+    print_event(eid, "%d bytes of random data" % len(data))
+    return True
 
 # pre-MTTCG merge
 v5_event_table = [Decoder(0, "EVENT_INSTRUCTION", decode_instruction),
                   Decoder(1, "EVENT_INTERRUPT", decode_interrupt),
-                  Decoder(2, "EVENT_EXCEPTION", decode_unimp),
+                  Decoder(2, "EVENT_EXCEPTION", decode_plain),
                   Decoder(3, "EVENT_ASYNC", decode_async),
                   Decoder(4, "EVENT_SHUTDOWN", decode_unimp),
-                  Decoder(5, "EVENT_CHAR_WRITE", decode_unimp),
+                  Decoder(5, "EVENT_CHAR_WRITE", decode_char_write),
                   Decoder(6, "EVENT_CHAR_READ_ALL", decode_unimp),
                   Decoder(7, "EVENT_CHAR_READ_ALL_ERROR", decode_unimp),
                   Decoder(8, "EVENT_CLOCK_HOST", decode_clock),
@@ -215,10 +241,10 @@ def decode_clock(eid, name, dumpfile):
 # post-MTTCG merge, AUDIO support added
 v6_event_table = [Decoder(0, "EVENT_INSTRUCTION", decode_instruction),
                   Decoder(1, "EVENT_INTERRUPT", decode_interrupt),
-                  Decoder(2, "EVENT_EXCEPTION", decode_unimp),
+                  Decoder(2, "EVENT_EXCEPTION", decode_plain),
                   Decoder(3, "EVENT_ASYNC", decode_async),
                   Decoder(4, "EVENT_SHUTDOWN", decode_unimp),
-                  Decoder(5, "EVENT_CHAR_WRITE", decode_unimp),
+                  Decoder(5, "EVENT_CHAR_WRITE", decode_char_write),
                   Decoder(6, "EVENT_CHAR_READ_ALL", decode_unimp),
                   Decoder(7, "EVENT_CHAR_READ_ALL_ERROR", decode_unimp),
                   Decoder(8, "EVENT_AUDIO_OUT", decode_audio_out),
@@ -250,7 +276,7 @@ def decode_clock(eid, name, dumpfile):
                   Decoder(10, "EVENT_SHUTDOWN_GUEST_RESET", decode_unimp),
                   Decoder(11, "EVENT_SHUTDOWN_GUEST_PANIC", decode_unimp),
                   Decoder(12, "EVENT_SHUTDOWN___MAX", decode_unimp),
-                  Decoder(13, "EVENT_CHAR_WRITE", decode_unimp),
+                  Decoder(13, "EVENT_CHAR_WRITE", decode_char_write),
                   Decoder(14, "EVENT_CHAR_READ_ALL", decode_unimp),
                   Decoder(15, "EVENT_CHAR_READ_ALL_ERROR", decode_unimp),
                   Decoder(16, "EVENT_AUDIO_OUT", decode_audio_out),
@@ -268,6 +294,48 @@ def decode_clock(eid, name, dumpfile):
                   Decoder(28, "EVENT_CP_RESET", decode_checkpoint),
 ]
 
+v12_event_table = [Decoder(0, "EVENT_INSTRUCTION", decode_instruction),
+                  Decoder(1, "EVENT_INTERRUPT", decode_interrupt),
+                  Decoder(2, "EVENT_EXCEPTION", decode_plain),
+                  Decoder(3, "EVENT_ASYNC", decode_async),
+                  Decoder(4, "EVENT_ASYNC", decode_async),
+                  Decoder(5, "EVENT_ASYNC", decode_async),
+                  Decoder(6, "EVENT_ASYNC", decode_async),
+                  Decoder(6, "EVENT_ASYNC", decode_async),
+                  Decoder(8, "EVENT_ASYNC", decode_async),
+                  Decoder(9, "EVENT_ASYNC", decode_async),
+                  Decoder(10, "EVENT_ASYNC", decode_async),
+                  Decoder(11, "EVENT_SHUTDOWN", decode_unimp),
+                  Decoder(12, "EVENT_SHUTDOWN_HOST_ERR", decode_unimp),
+                  Decoder(13, "EVENT_SHUTDOWN_HOST_QMP_QUIT", decode_unimp),
+                  Decoder(14, "EVENT_SHUTDOWN_HOST_QMP_RESET", decode_unimp),
+                  Decoder(14, "EVENT_SHUTDOWN_HOST_SIGNAL", decode_unimp),
+                  Decoder(15, "EVENT_SHUTDOWN_HOST_UI", decode_unimp),
+                  Decoder(16, "EVENT_SHUTDOWN_GUEST_SHUTDOWN", decode_unimp),
+                  Decoder(17, "EVENT_SHUTDOWN_GUEST_RESET", decode_unimp),
+                  Decoder(18, "EVENT_SHUTDOWN_GUEST_PANIC", decode_unimp),
+                  Decoder(19, "EVENT_SHUTDOWN_GUEST_SUBSYSTEM_RESET", decode_unimp),
+                  Decoder(20, "EVENT_SHUTDOWN_GUEST_SNAPSHOT_LOAD", decode_unimp),
+                  Decoder(21, "EVENT_SHUTDOWN___MAX", decode_unimp),
+                  Decoder(22, "EVENT_CHAR_WRITE", decode_char_write),
+                  Decoder(23, "EVENT_CHAR_READ_ALL", decode_unimp),
+                  Decoder(24, "EVENT_CHAR_READ_ALL_ERROR", decode_unimp),
+                  Decoder(25, "EVENT_AUDIO_IN", decode_unimp),
+                  Decoder(26, "EVENT_AUDIO_OUT", decode_audio_out),
+                  Decoder(27, "EVENT_RANDOM", decode_random),
+                  Decoder(28, "EVENT_CLOCK_HOST", decode_clock),
+                  Decoder(29, "EVENT_CLOCK_VIRTUAL_RT", decode_clock),
+                  Decoder(30, "EVENT_CP_CLOCK_WARP_START", decode_checkpoint),
+                  Decoder(31, "EVENT_CP_CLOCK_WARP_ACCOUNT", decode_checkpoint),
+                  Decoder(32, "EVENT_CP_RESET_REQUESTED", decode_checkpoint),
+                  Decoder(33, "EVENT_CP_SUSPEND_REQUESTED", decode_checkpoint),
+                  Decoder(34, "EVENT_CP_CLOCK_VIRTUAL", decode_checkpoint),
+                  Decoder(35, "EVENT_CP_CLOCK_HOST", decode_checkpoint),
+                  Decoder(36, "EVENT_CP_CLOCK_VIRTUAL_RT", decode_checkpoint),
+                  Decoder(37, "EVENT_CP_INIT", decode_checkpoint_init),
+                  Decoder(38, "EVENT_CP_RESET", decode_checkpoint),
+]
+
 def parse_arguments():
     "Grab arguments for script"
     parser = argparse.ArgumentParser()
@@ -278,14 +346,18 @@ def parse_arguments():
 def decode_file(filename):
     "Decode a record/replay dump"
     dumpfile = open(filename, "rb")
-
+    dumpsize = path.getsize(filename)
     # read and throwaway the header
     version = read_dword(dumpfile)
     junk = read_qword(dumpfile)
 
+    # see REPLAY_VERSION
     print("HEADER: version 0x%x" % (version))
 
-    if version == 0xe02007:
+    if version == 0xe0200c:
+        event_decode_table = v12_event_table
+        replay_state.checkpoint_start = 30
+    elif version == 0xe02007:
         event_decode_table = v7_event_table
         replay_state.checkpoint_start = 12
     elif version == 0xe02006:
@@ -299,8 +371,13 @@ def decode_file(filename):
         decode_ok = True
         while decode_ok:
             event = read_event(dumpfile)
-            decode_ok = call_decode(event_decode_table, event, dumpfile)
+            decode_ok = call_decode(event_decode_table, event,
+                                    dumpfile)
+    except Exception as inst:
+        print(f"error {inst}")
+
     finally:
+        print(f"Reached {dumpfile.tell()} of {dumpsize} bytes")
         dumpfile.close()
 
 if __name__ == "__main__":

tests/avocado/replay_kernel.py

@@ -82,13 +82,26 @@ def run_rr(self, kernel_path, kernel_command_line, console_pattern,
 
 class ReplayKernelNormal(ReplayKernelBase):
 
-    # See https://gitlab.com/qemu-project/qemu/-/issues/2010
-    @skipUnless(os.getenv('QEMU_TEST_FLAKY_TESTS'), 'Test sometimes gets stuck')
+    def test_i386_pc(self):
+        """
+        :avocado: tags=arch:i386
+        :avocado: tags=machine:pc
+        """
+        kernel_url = ('https://storage.tuxboot.com/20230331/i386/bzImage')
+        kernel_hash = 'a3e5b32a354729e65910f5a1ffcda7c14a6c12a55e8213fb86e277f1b76ed956'
+        kernel_path = self.fetch_asset(kernel_url,
+                                       asset_hash=kernel_hash,
+                                       algorithm = "sha256")
+
+        kernel_command_line = self.KERNEL_COMMON_COMMAND_LINE + 'console=ttyS0'
+        console_pattern = 'VFS: Cannot open root device'
+
+        self.run_rr(kernel_path, kernel_command_line, console_pattern, shift=5)
+
     def test_x86_64_pc(self):
         """
         :avocado: tags=arch:x86_64
         :avocado: tags=machine:pc
-        :avocado: tags=flaky
         """
         kernel_url = ('https://archives.fedoraproject.org/pub/archive/fedora'
                       '/linux/releases/29/Everything/x86_64/os/images/pxeboot'
@@ -119,8 +132,6 @@ def test_mips_malta(self):
 
         self.run_rr(kernel_path, kernel_command_line, console_pattern, shift=5)
 
-    # See https://gitlab.com/qemu-project/qemu/-/issues/2013
-    @skipUnless(os.getenv('QEMU_TEST_FLAKY_TESTS'), 'Test is unstable on GitLab')
     def test_mips64el_malta(self):
         """
         This test requires the ar tool to extract "data.tar.gz" from
@@ -136,7 +147,6 @@ def test_mips64el_malta(self):
 
         :avocado: tags=arch:mips64el
         :avocado: tags=machine:malta
-        :avocado: tags=flaky
         """
         deb_url = ('http://snapshot.debian.org/archive/debian/'
                    '20130217T032700Z/pool/main/l/linux-2.6/'
@@ -184,13 +194,10 @@ def test_arm_virt(self):
 
         self.run_rr(kernel_path, kernel_command_line, console_pattern, shift=1)
 
-    @skipUnless(os.getenv('QEMU_TEST_FLAKY_TESTS'), 'Test is unstable on GitLab')
-
     def test_arm_cubieboard_initrd(self):
         """
         :avocado: tags=arch:arm
         :avocado: tags=machine:cubieboard
-        :avocado: tags=flaky
         """
         deb_url = ('https://apt.armbian.com/pool/main/l/'
                    'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb')
@@ -338,7 +345,6 @@ def test_m68k_mcf5208evb(self):
         file_path = self.fetch_asset(tar_url, asset_hash=tar_hash)
         self.do_test_advcal_2018(file_path, 'sanity-clause.elf')
 
-    @skip("Test currently broken") # Console stuck as of 5.2-rc1
     def test_microblaze_s3adsp1800(self):
         """
         :avocado: tags=arch:microblaze
@@ -373,7 +379,6 @@ def test_or1k_sim(self):
         file_path = self.fetch_asset(tar_url, asset_hash=tar_hash)
         self.do_test_advcal_2018(file_path, 'vmlinux')
 
-    @skip("nios2 emulation is buggy under record/replay")
     def test_nios2_10m50(self):
         """
         :avocado: tags=arch:nios2

tests/avocado/replay_linux.py

@@ -48,12 +48,15 @@ def vm_add_disk(self, vm, path, id, device):
         bus_string = ''
         if self.bus:
             bus_string = ',bus=%s.%d' % (self.bus, id,)
-        vm.add_args('-drive', 'file=%s,snapshot,id=disk%s,if=none' % (path, id))
+        vm.add_args('-drive', 'file=%s,snapshot=on,id=disk%s,if=none' % (path, id))
         vm.add_args('-drive',
             'driver=blkreplay,id=disk%s-rr,if=none,image=disk%s' % (id, id))
         vm.add_args('-device',
             '%s,drive=disk%s-rr%s' % (device, id, bus_string))
 
+    def vm_add_cdrom(self, vm, path, id, device):
+        vm.add_args('-drive', 'file=%s,id=disk%s,if=none,media=cdrom' % (path, id))
+
     def launch_and_wait(self, record, args, shift):
         self.require_netdev('user')
         vm = self.get_vm()
@@ -65,7 +68,7 @@ def launch_and_wait(self, record, args, shift):
         if args:
             vm.add_args(*args)
         self.vm_add_disk(vm, self.boot_path, 0, self.hdd)
-        self.vm_add_disk(vm, self.cloudinit_path, 1, self.cd)
+        self.vm_add_cdrom(vm, self.cloudinit_path, 1, self.cd)
         logger = logging.getLogger('replay')
         if record:
             logger.info('recording the execution...')
@@ -94,7 +97,7 @@ def launch_and_wait(self, record, args, shift):
         else:
             vm.event_wait('SHUTDOWN', self.timeout)
             vm.wait()
-            logger.info('successfully fihished the replay')
+            logger.info('successfully finished the replay')
         elapsed = time.time() - start_time
         logger.info('elapsed time %.2f sec' % elapsed)
         return elapsed