Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* Miscellaneous exec.c fixes (Markus, myself)
* Q35 support for -machine kernel_irqchip=split (Rita)
* Chardev replay support (Pavel)
* icount "warping" cleanups (Pavel)

# gpg: Signature made Tue 15 Mar 2016 17:24:08 GMT using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"

* remotes/bonzini/tags/for-upstream:
  icount: decouple warp calls
  icount: remove obsolete warp call
  replay: character devices
  exec: fix early return from ram_block_add
  exec: Fix memory allocation when memory path isn't on hugetlbfs
  exec: Fix memory allocation when memory path names new file
  update-linux-headers: Add userfaultfd.h
  kvm: x86: q35: Add support for -machine kernel_irqchip=split for q35
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

cpus.c

@@ -370,9 +370,12 @@ static void icount_warp_rt(void)
     }
 }
 
-static void icount_dummy_timer(void *opaque)
+static void icount_timer_cb(void *opaque)
 {
-    (void)opaque;
+    /* No need for a checkpoint because the timer already synchronizes
+     * with CHECKPOINT_CLOCK_VIRTUAL_RT.
+     */
+    icount_warp_rt();
 }
 
 void qtest_clock_warp(int64_t dest)
@@ -396,17 +399,12 @@ void qtest_clock_warp(int64_t dest)
     qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
 }
 
-void qemu_clock_warp(QEMUClockType type)
+void qemu_start_warp_timer(void)
 {
     int64_t clock;
     int64_t deadline;
 
-    /*
-     * There are too many global variables to make the "warp" behavior
-     * applicable to other clocks.  But a clock argument removes the
-     * need for if statements all over the place.
-     */
-    if (type != QEMU_CLOCK_VIRTUAL || !use_icount) {
+    if (!use_icount) {
         return;
     }
 
@@ -418,29 +416,17 @@ void qemu_clock_warp(QEMUClockType type)
     }
 
     /* warp clock deterministically in record/replay mode */
-    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP)) {
+    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_START)) {
         return;
     }
 
-    if (icount_sleep) {
-        /*
-         * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer now.
-         * This ensures that the deadline for the timer is computed correctly
-         * below.
-         * This also makes sure that the insn counter is synchronized before
-         * the CPU starts running, in case the CPU is woken by an event other
-         * than the earliest QEMU_CLOCK_VIRTUAL timer.
-         */
-        icount_warp_rt();
-        timer_del(icount_warp_timer);
-    }
     if (!all_cpu_threads_idle()) {
         return;
     }
 
     if (qtest_enabled()) {
         /* When testing, qtest commands advance icount.  */
-	return;
+        return;
     }
 
     /* We want to use the earliest deadline from ALL vm_clocks */
@@ -496,6 +482,28 @@ void qemu_clock_warp(QEMUClockType type)
     }
 }
 
+static void qemu_account_warp_timer(void)
+{
+    if (!use_icount || !icount_sleep) {
+        return;
+    }
+
+    /* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
+     * do not fire, so computing the deadline does not make sense.
+     */
+    if (!runstate_is_running()) {
+        return;
+    }
+
+    /* warp clock deterministically in record/replay mode */
+    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_ACCOUNT)) {
+        return;
+    }
+
+    timer_del(icount_warp_timer);
+    icount_warp_rt();
+}
+
 static bool icount_state_needed(void *opaque)
 {
     return use_icount;
@@ -624,7 +632,7 @@ void configure_icount(QemuOpts *opts, Error **errp)
     icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
     if (icount_sleep) {
         icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
-                                         icount_dummy_timer, NULL);
+                                         icount_timer_cb, NULL);
     }
 
     icount_align_option = qemu_opt_get_bool(opts, "align", false);
@@ -995,9 +1003,6 @@ static void qemu_wait_io_event_common(CPUState *cpu)
 static void qemu_tcg_wait_io_event(CPUState *cpu)
 {
     while (all_cpu_threads_idle()) {
-       /* Start accounting real time to the virtual clock if the CPUs
-          are idle.  */
-        qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
         qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
     }
 
@@ -1499,7 +1504,7 @@ static void tcg_exec_all(void)
     int r;
 
     /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
-    qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
+    qemu_account_warp_timer();
 
     if (next_cpu == NULL) {
         next_cpu = first_cpu;

docs/replay.txt

@@ -107,7 +107,7 @@ at the specified moments of time. There are several kinds of timers:
    sources (e.g. real time clock chip). Host clock is the one of the sources
    of non-determinism. Host clock read operations should be logged to
    make the execution deterministic.
- * Real time clock for icount. This clock is similar to real time clock but
+ * Virtual real time clock. This clock is similar to real time clock but
    it is used only for increasing virtual clock while virtual machine is
    sleeping. Due to its nature it is also non-deterministic as the host clock
    and has to be logged too.
@@ -134,11 +134,20 @@ of time. That's why we do not process a group of timers until the checkpoint
 event will be read from the log. Such an event allows synchronizing CPU
 execution and timer events.
 
-Another checkpoints application in record/replay is instruction counting
-while the virtual machine is idle. This function (qemu_clock_warp) is called
-from the wait loop. It changes virtual machine state and must be deterministic
-then. That is why we added checkpoint to this function to prevent its
-operation in replay mode when it does not correspond to record mode.
+Two other checkpoints govern the "warping" of the virtual clock.
+While the virtual machine is idle, the virtual clock increments at
+1 ns per *real time* nanosecond.  This is done by setting up a timer
+(called the warp timer) on the virtual real time clock, so that the
+timer fires at the next deadline of the virtual clock; the virtual clock
+is then incremented (which is called "warping" the virtual clock) as
+soon as the timer fires or the CPUs need to go out of the idle state.
+Two functions are used for this purpose; because these actions change
+virtual machine state and must be deterministic, each of them creates a
+checkpoint.  qemu_start_warp_timer checks if the CPUs are idle and if so
+starts accounting real time to virtual clock.  qemu_account_warp_timer
+is called when the CPUs get an interrupt or when the warp timer fires,
+and it warps the virtual clock by the amount of real time that has passed
+since qemu_start_warp_timer.
 
 Bottom halves
 -------------

exec.c

@@ -1228,92 +1228,83 @@ void qemu_mutex_unlock_ramlist(void)
 }
 
 #ifdef __linux__
-
-#include <sys/vfs.h>
-
-#define HUGETLBFS_MAGIC       0x958458f6
-
-static long gethugepagesize(const char *path, Error **errp)
-{
-    struct statfs fs;
-    int ret;
-
-    do {
-        ret = statfs(path, &fs);
-    } while (ret != 0 && errno == EINTR);
-
-    if (ret != 0) {
-        error_setg_errno(errp, errno, "failed to get page size of file %s",
-                         path);
-        return 0;
-    }
-
-    return fs.f_bsize;
-}
-
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
                             const char *path,
                             Error **errp)
 {
-    struct stat st;
+    bool unlink_on_error = false;
     char *filename;
     char *sanitized_name;
     char *c;
     void *area;
     int fd;
-    uint64_t hpagesize;
-    Error *local_err = NULL;
-
-    hpagesize = gethugepagesize(path, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto error;
-    }
-    block->mr->align = hpagesize;
-
-    if (memory < hpagesize) {
-        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
-                   "or larger than huge page size 0x%" PRIx64,
-                   memory, hpagesize);
-        goto error;
-    }
+    int64_t page_size;
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
         error_setg(errp,
                    "host lacks kvm mmu notifiers, -mem-path unsupported");
-        goto error;
+        return NULL;
     }
 
-    if (!stat(path, &st) && S_ISDIR(st.st_mode)) {
-        /* Make name safe to use with mkstemp by replacing '/' with '_'. */
-        sanitized_name = g_strdup(memory_region_name(block->mr));
-        for (c = sanitized_name; *c != '\0'; c++) {
-            if (*c == '/') {
-                *c = '_';
-            }
+    for (;;) {
+        fd = open(path, O_RDWR);
+        if (fd >= 0) {
+            /* @path names an existing file, use it */
+            break;
         }
+        if (errno == ENOENT) {
+            /* @path names a file that doesn't exist, create it */
+            fd = open(path, O_RDWR | O_CREAT | O_EXCL, 0644);
+            if (fd >= 0) {
+                unlink_on_error = true;
+                break;
+            }
+        } else if (errno == EISDIR) {
+            /* @path names a directory, create a file there */
+            /* Make name safe to use with mkstemp by replacing '/' with '_'. */
+            sanitized_name = g_strdup(memory_region_name(block->mr));
+            for (c = sanitized_name; *c != '\0'; c++) {
+                if (*c == '/') {
+                    *c = '_';
+                }
+            }
 
-        filename = g_strdup_printf("%s/qemu_back_mem.%s.XXXXXX", path,
-                                   sanitized_name);
-        g_free(sanitized_name);
+            filename = g_strdup_printf("%s/qemu_back_mem.%s.XXXXXX", path,
+                                       sanitized_name);
+            g_free(sanitized_name);
 
-        fd = mkstemp(filename);
-        if (fd >= 0) {
-            unlink(filename);
+            fd = mkstemp(filename);
+            if (fd >= 0) {
+                unlink(filename);
+                g_free(filename);
+                break;
+            }
+            g_free(filename);
         }
-        g_free(filename);
-    } else {
-        fd = open(path, O_RDWR | O_CREAT, 0644);
+        if (errno != EEXIST && errno != EINTR) {
+            error_setg_errno(errp, errno,
+                             "can't open backing store %s for guest RAM",
+                             path);
+            goto error;
+        }
+        /*
+         * Try again on EINTR and EEXIST.  The latter happens when
+         * something else creates the file between our two open().
+         */
     }
 
-    if (fd < 0) {
-        error_setg_errno(errp, errno,
-                         "unable to create backing store for hugepages");
+    page_size = qemu_fd_getpagesize(fd);
+    block->mr->align = page_size;
+
+    if (memory < page_size) {
+        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
+                   "or larger than page size 0x%" PRIx64,
+                   memory, page_size);
         goto error;
     }
 
-    memory = ROUND_UP(memory, hpagesize);
+    memory = ROUND_UP(memory, page_size);
 
     /*
      * ftruncate is not supported by hugetlbfs in older
@@ -1325,10 +1316,10 @@ static void *file_ram_alloc(RAMBlock *block,
         perror("ftruncate");
     }
 
-    area = qemu_ram_mmap(fd, memory, hpagesize, block->flags & RAM_SHARED);
+    area = qemu_ram_mmap(fd, memory, page_size, block->flags & RAM_SHARED);
     if (area == MAP_FAILED) {
         error_setg_errno(errp, errno,
-                         "unable to map backing store for hugepages");
+                         "unable to map backing store for guest RAM");
         close(fd);
         goto error;
     }
@@ -1341,6 +1332,10 @@ static void *file_ram_alloc(RAMBlock *block,
     return area;
 
 error:
+    if (unlink_on_error) {
+        unlink(path);
+    }
+    close(fd);
     return NULL;
 }
 #endif
@@ -1594,6 +1589,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
             if (err) {
                 error_propagate(errp, err);
                 qemu_mutex_unlock_ramlist();
+                return;
             }
         } else {
             new_block->host = phys_mem_alloc(new_block->max_length,
@@ -1603,6 +1599,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
                                  "cannot set up guest memory '%s'",
                                  memory_region_name(new_block->mr));
                 qemu_mutex_unlock_ramlist();
+                return;
             }
             memory_try_enable_merging(new_block->host, new_block->max_length);
         }

gdbstub.c

@@ -1752,7 +1752,7 @@ int gdbserver_start(const char *device)
             sigaction(SIGINT, &act, NULL);
         }
 #endif
-        chr = qemu_chr_new("gdb", device, NULL);
+        chr = qemu_chr_new_noreplay("gdb", device, NULL);
         if (!chr)
             return -1;
 

hw/i386/pc_q35.c

@@ -39,6 +39,7 @@
 #include "hw/kvm/clock.h"
 #include "hw/pci-host/q35.h"
 #include "exec/address-spaces.h"
+#include "hw/i386/pc.h"
 #include "hw/i386/ich9.h"
 #include "hw/smbios/smbios.h"
 #include "hw/ide/pci.h"
@@ -146,7 +147,7 @@ static void pc_q35_init(MachineState *machine)
 
     /* irq lines */
     gsi_state = g_malloc0(sizeof(*gsi_state));
-    if (kvm_irqchip_in_kernel()) {
+    if (kvm_ioapic_in_kernel()) {
         kvm_pc_setup_irq_routing(pcmc->pci_enabled);
         gsi = qemu_allocate_irqs(kvm_pc_gsi_handler, gsi_state,
                                  GSI_NUM_PINS);
@@ -193,7 +194,7 @@ static void pc_q35_init(MachineState *machine)
     /*end early*/
     isa_bus_irqs(isa_bus, gsi);
 
-    if (kvm_irqchip_in_kernel()) {
+    if (kvm_pic_in_kernel()) {
         i8259 = kvm_i8259_init(isa_bus);
     } else if (xen_enabled()) {
         i8259 = xen_interrupt_controller_init();

include/qemu/timer.h

@@ -210,12 +210,11 @@ void qemu_clock_notify(QEMUClockType type);
 void qemu_clock_enable(QEMUClockType type, bool enabled);
 
 /**
- * qemu_clock_warp:
- * @type: the clock type
+ * qemu_start_warp_timer:
  *
- * Warp a clock to a new value
+ * Starts a timer for virtual clock update
  */
-void qemu_clock_warp(QEMUClockType type);
+void qemu_start_warp_timer(void);
 
 /**
  * qemu_clock_register_reset_notifier:

include/sysemu/char.h

@@ -86,6 +86,7 @@ struct CharDriverState {
     int is_mux;
     guint fd_in_tag;
     QemuOpts *opts;
+    bool replay;
     QTAILQ_ENTRY(CharDriverState) next;
 };
 
@@ -138,6 +139,22 @@ void qemu_chr_parse_common(QemuOpts *opts, ChardevCommon *backend);
 CharDriverState *qemu_chr_new(const char *label, const char *filename,
                               void (*init)(struct CharDriverState *s));
 
+/**
+ * @qemu_chr_new_noreplay:
+ *
+ * Create a new character backend from a URI.
+ * Character device communications are not written
+ * into the replay log.
+ *
+ * @label the name of the backend
+ * @filename the URI
+ * @init not sure..
+ *
+ * Returns: a new character backend
+ */
+CharDriverState *qemu_chr_new_noreplay(const char *label, const char *filename,
+                                       void (*init)(struct CharDriverState *s));
+
 /**
  * @qemu_chr_delete:
  *
@@ -341,6 +358,15 @@ int qemu_chr_be_can_write(CharDriverState *s);
  */
 void qemu_chr_be_write(CharDriverState *s, uint8_t *buf, int len);
 
+/**
+ * @qemu_chr_be_write_impl:
+ *
+ * Implementation of back end writing. Used by replay module.
+ *
+ * @buf a buffer to receive data from the front end
+ * @len the number of bytes to receive from the front end
+ */
+void qemu_chr_be_write_impl(CharDriverState *s, uint8_t *buf, int len);
 
 /**
  * @qemu_chr_be_event:

include/sysemu/replay.h

@@ -27,7 +27,8 @@ typedef enum ReplayClockKind ReplayClockKind;
 
 /* IDs of the checkpoints */
 enum ReplayCheckpoint {
-    CHECKPOINT_CLOCK_WARP,
+    CHECKPOINT_CLOCK_WARP_START,
+    CHECKPOINT_CLOCK_WARP_ACCOUNT,
     CHECKPOINT_RESET_REQUESTED,
     CHECKPOINT_SUSPEND_REQUESTED,
     CHECKPOINT_CLOCK_VIRTUAL,
@@ -114,4 +115,21 @@ void replay_input_event(QemuConsole *src, InputEvent *evt);
 /*! Adds input sync event to the queue */
 void replay_input_sync_event(void);
 
+/* Character device */
+
+/*! Registers char driver to save it's events */
+void replay_register_char_driver(struct CharDriverState *chr);
+/*! Saves write to char device event to the log */
+void replay_chr_be_write(struct CharDriverState *s, uint8_t *buf, int len);
+/*! Writes char write return value to the replay log. */
+void replay_char_write_event_save(int res, int offset);
+/*! Reads char write return value from the replay log. */
+void replay_char_write_event_load(int *res, int *offset);
+/*! Reads information about read_all character event. */
+int replay_char_read_all_load(uint8_t *buf);
+/*! Writes character read_all error code into the replay log. */
+void replay_char_read_all_save_error(int res);
+/*! Writes character read_all execution result into the replay log. */
+void replay_char_read_all_save_buf(uint8_t *buf, int offset);
+
 #endif

main-loop.c

@@ -509,7 +509,7 @@ int main_loop_wait(int nonblocking)
 
     /* CPU thread can infinitely wait for event after
        missing the warp */
-    qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
+    qemu_start_warp_timer();
     qemu_clock_run_all_timers();
 
     return ret;

qemu-char.c

@@ -37,6 +37,7 @@
 #include "io/channel-socket.h"
 #include "io/channel-file.h"
 #include "io/channel-tls.h"
+#include "sysemu/replay.h"
 
 #include <zlib.h>
 
@@ -234,10 +235,46 @@ static void qemu_chr_fe_write_log(CharDriverState *s,
     }
 }
 
+static int qemu_chr_fe_write_buffer(CharDriverState *s, const uint8_t *buf, int len, int *offset)
+{
+    int res = 0;
+    *offset = 0;
+
+    qemu_mutex_lock(&s->chr_write_lock);
+    while (*offset < len) {
+        do {
+            res = s->chr_write(s, buf + *offset, len - *offset);
+            if (res == -1 && errno == EAGAIN) {
+                g_usleep(100);
+            }
+        } while (res == -1 && errno == EAGAIN);
+
+        if (res <= 0) {
+            break;
+        }
+
+        *offset += res;
+    }
+    if (*offset > 0) {
+        qemu_chr_fe_write_log(s, buf, *offset);
+    }
+    qemu_mutex_unlock(&s->chr_write_lock);
+
+    return res;
+}
+
 int qemu_chr_fe_write(CharDriverState *s, const uint8_t *buf, int len)
 {
     int ret;
 
+    if (s->replay && replay_mode == REPLAY_MODE_PLAY) {
+        int offset;
+        replay_char_write_event_load(&ret, &offset);
+        assert(offset <= len);
+        qemu_chr_fe_write_buffer(s, buf, offset, &offset);
+        return ret;
+    }
+
     qemu_mutex_lock(&s->chr_write_lock);
     ret = s->chr_write(s, buf, len);
 
@@ -246,34 +283,31 @@ int qemu_chr_fe_write(CharDriverState *s, const uint8_t *buf, int len)
     }
 
     qemu_mutex_unlock(&s->chr_write_lock);
+    
+    if (s->replay && replay_mode == REPLAY_MODE_RECORD) {
+        replay_char_write_event_save(ret, ret < 0 ? 0 : ret);
+    }
+    
     return ret;
 }
 
 int qemu_chr_fe_write_all(CharDriverState *s, const uint8_t *buf, int len)
 {
-    int offset = 0;
-    int res = 0;
+    int offset;
+    int res;
 
-    qemu_mutex_lock(&s->chr_write_lock);
-    while (offset < len) {
-        do {
-            res = s->chr_write(s, buf + offset, len - offset);
-            if (res == -1 && errno == EAGAIN) {
-                g_usleep(100);
-            }
-        } while (res == -1 && errno == EAGAIN);
+    if (s->replay && replay_mode == REPLAY_MODE_PLAY) {
+        replay_char_write_event_load(&res, &offset);
+        assert(offset <= len);
+        qemu_chr_fe_write_buffer(s, buf, offset, &offset);
+        return res;
+    }
 
-        if (res <= 0) {
-            break;
-        }
+    res = qemu_chr_fe_write_buffer(s, buf, len, &offset);
 
-        offset += res;
+    if (s->replay && replay_mode == REPLAY_MODE_RECORD) {
+        replay_char_write_event_save(res, offset);
     }
-    if (offset > 0) {
-        qemu_chr_fe_write_log(s, buf, offset);
-    }
-
-    qemu_mutex_unlock(&s->chr_write_lock);
 
     if (res < 0) {
         return res;
@@ -289,6 +323,10 @@ int qemu_chr_fe_read_all(CharDriverState *s, uint8_t *buf, int len)
     if (!s->chr_sync_read) {
         return 0;
     }
+    
+    if (s->replay && replay_mode == REPLAY_MODE_PLAY) {
+        return replay_char_read_all_load(buf);
+    }
 
     while (offset < len) {
         do {
@@ -303,6 +341,9 @@ int qemu_chr_fe_read_all(CharDriverState *s, uint8_t *buf, int len)
         }
 
         if (res < 0) {
+            if (s->replay && replay_mode == REPLAY_MODE_RECORD) {
+                replay_char_read_all_save_error(res);
+            }
             return res;
         }
 
@@ -313,14 +354,22 @@ int qemu_chr_fe_read_all(CharDriverState *s, uint8_t *buf, int len)
         }
     }
 
+    if (s->replay && replay_mode == REPLAY_MODE_RECORD) {
+        replay_char_read_all_save_buf(buf, offset);
+    }
     return offset;
 }
 
 int qemu_chr_fe_ioctl(CharDriverState *s, int cmd, void *arg)
 {
-    if (!s->chr_ioctl)
-        return -ENOTSUP;
-    return s->chr_ioctl(s, cmd, arg);
+    int res;
+    if (!s->chr_ioctl || s->replay) {
+        res = -ENOTSUP;
+    } else {
+        res = s->chr_ioctl(s, cmd, arg);
+    }
+
+    return res;
 }
 
 int qemu_chr_be_can_write(CharDriverState *s)
@@ -330,17 +379,35 @@ int qemu_chr_be_can_write(CharDriverState *s)
     return s->chr_can_read(s->handler_opaque);
 }
 
-void qemu_chr_be_write(CharDriverState *s, uint8_t *buf, int len)
+void qemu_chr_be_write_impl(CharDriverState *s, uint8_t *buf, int len)
 {
     if (s->chr_read) {
         s->chr_read(s->handler_opaque, buf, len);
     }
 }
 
+void qemu_chr_be_write(CharDriverState *s, uint8_t *buf, int len)
+{
+    if (s->replay) {
+        if (replay_mode == REPLAY_MODE_PLAY) {
+            return;
+        }
+        replay_chr_be_write(s, buf, len);
+    } else {
+        qemu_chr_be_write_impl(s, buf, len);
+    }
+}
+
 int qemu_chr_fe_get_msgfd(CharDriverState *s)
 {
     int fd;
-    return (qemu_chr_fe_get_msgfds(s, &fd, 1) == 1) ? fd : -1;
+    int res = (qemu_chr_fe_get_msgfds(s, &fd, 1) == 1) ? fd : -1;
+    if (s->replay) {
+        fprintf(stderr,
+                "Replay: get msgfd is not supported for serial devices yet\n");
+        exit(1);
+    }
+    return res;
 }
 
 int qemu_chr_fe_get_msgfds(CharDriverState *s, int *fds, int len)
@@ -3821,7 +3888,8 @@ err:
     return NULL;
 }
 
-CharDriverState *qemu_chr_new(const char *label, const char *filename, void (*init)(struct CharDriverState *s))
+CharDriverState *qemu_chr_new_noreplay(const char *label, const char *filename,
+                                       void (*init)(struct CharDriverState *s))
 {
     const char *p;
     CharDriverState *chr;
@@ -3847,6 +3915,21 @@ CharDriverState *qemu_chr_new(const char *label, const char *filename, void (*in
     return chr;
 }
 
+CharDriverState *qemu_chr_new(const char *label, const char *filename, void (*init)(struct CharDriverState *s))
+{
+    CharDriverState *chr;
+    chr = qemu_chr_new_noreplay(label, filename, init);
+    if (chr) {
+        chr->replay = replay_mode != REPLAY_MODE_NONE;
+        if (chr->replay && chr->chr_ioctl) {
+            fprintf(stderr,
+                    "Replay: ioctl is not supported for serial devices yet\n");
+        }
+        replay_register_char_driver(chr);
+    }
+    return chr;
+}
+
 void qemu_chr_fe_set_echo(struct CharDriverState *chr, bool echo)
 {
     if (chr->chr_set_echo) {
@@ -4455,6 +4538,11 @@ void qmp_chardev_remove(const char *id, Error **errp)
         error_setg(errp, "Chardev '%s' is busy", id);
         return;
     }
+    if (chr->replay) {
+        error_setg(errp,
+            "Chardev '%s' cannot be unplugged in record/replay mode", id);
+        return;
+    }
     qemu_chr_delete(chr);
 }
 

qemu-timer.c

@@ -394,7 +394,9 @@ static bool timer_mod_ns_locked(QEMUTimerList *timer_list,
 static void timerlist_rearm(QEMUTimerList *timer_list)
 {
     /* Interrupt execution to force deadline recalculation.  */
-    qemu_clock_warp(timer_list->clock->type);
+    if (timer_list->clock->type == QEMU_CLOCK_VIRTUAL) {
+        qemu_start_warp_timer();
+    }
     timerlist_notify(timer_list);
 }
 

replay/Makefile.objs

@@ -3,3 +3,4 @@ common-obj-y += replay-internal.o
 common-obj-y += replay-events.o
 common-obj-y += replay-time.o
 common-obj-y += replay-input.o
+common-obj-y += replay-char.o

replay/replay-char.c

+/*
+ * replay-char.c
+ *
+ * Copyright (c) 2010-2016 Institute for System Programming
+ *                         of the Russian Academy of Sciences.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "sysemu/replay.h"
+#include "replay-internal.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/char.h"
+
+/* Char drivers that generate qemu_chr_be_write events
+   that should be saved into the log. */
+static CharDriverState **char_drivers;
+static int drivers_count;
+
+/* Char event attributes. */
+typedef struct CharEvent {
+    int id;
+    uint8_t *buf;
+    size_t len;
+} CharEvent;
+
+static int find_char_driver(CharDriverState *chr)
+{
+    int i = 0;
+    for ( ; i < drivers_count ; ++i) {
+        if (char_drivers[i] == chr) {
+            return i;
+        }
+    }
+    return -1;
+}
+
+void replay_register_char_driver(CharDriverState *chr)
+{
+    if (replay_mode == REPLAY_MODE_NONE) {
+        return;
+    }
+    char_drivers = g_realloc(char_drivers,
+                             sizeof(*char_drivers) * (drivers_count + 1));
+    char_drivers[drivers_count++] = chr;
+}
+
+void replay_chr_be_write(CharDriverState *s, uint8_t *buf, int len)
+{
+    CharEvent *event = g_malloc0(sizeof(CharEvent));
+
+    event->id = find_char_driver(s);
+    if (event->id < 0) {
+        fprintf(stderr, "Replay: cannot find char driver\n");
+        exit(1);
+    }
+    event->buf = g_malloc(len);
+    memcpy(event->buf, buf, len);
+    event->len = len;
+
+    replay_add_event(REPLAY_ASYNC_EVENT_CHAR_READ, event, NULL, 0);
+}
+
+void replay_event_char_read_run(void *opaque)
+{
+    CharEvent *event = (CharEvent *)opaque;
+
+    qemu_chr_be_write_impl(char_drivers[event->id], event->buf,
+                           (int)event->len);
+
+    g_free(event->buf);
+    g_free(event);
+}
+
+void replay_event_char_read_save(void *opaque)
+{
+    CharEvent *event = (CharEvent *)opaque;
+
+    replay_put_byte(event->id);
+    replay_put_array(event->buf, event->len);
+}
+
+void *replay_event_char_read_load(void)
+{
+    CharEvent *event = g_malloc0(sizeof(CharEvent));
+
+    event->id = replay_get_byte();
+    replay_get_array_alloc(&event->buf, &event->len);
+
+    return event;
+}
+
+void replay_char_write_event_save(int res, int offset)
+{
+    replay_save_instructions();
+    replay_mutex_lock();
+    replay_put_event(EVENT_CHAR_WRITE);
+    replay_put_dword(res);
+    replay_put_dword(offset);
+    replay_mutex_unlock();
+}
+
+void replay_char_write_event_load(int *res, int *offset)
+{
+    replay_account_executed_instructions();
+    replay_mutex_lock();
+    if (replay_next_event_is(EVENT_CHAR_WRITE)) {
+        *res = replay_get_dword();
+        *offset = replay_get_dword();
+        replay_finish_event();
+        replay_mutex_unlock();
+    } else {
+        replay_mutex_unlock();
+        error_report("Missing character write event in the replay log");
+        exit(1);
+    }
+}
+
+int replay_char_read_all_load(uint8_t *buf)
+{
+    replay_mutex_lock();
+    if (replay_next_event_is(EVENT_CHAR_READ_ALL)) {
+        size_t size;
+        int res;
+        replay_get_array(buf, &size);
+        replay_finish_event();
+        replay_mutex_unlock();
+        res = (int)size;
+        assert(res >= 0);
+        return res;
+    } else if (replay_next_event_is(EVENT_CHAR_READ_ALL_ERROR)) {
+        int res = replay_get_dword();
+        replay_finish_event();
+        replay_mutex_unlock();
+        return res;
+    } else {
+        replay_mutex_unlock();
+        error_report("Missing character read all event in the replay log");
+        exit(1);
+    }
+}
+
+void replay_char_read_all_save_error(int res)
+{
+    assert(res < 0);
+    replay_save_instructions();
+    replay_mutex_lock();
+    replay_put_event(EVENT_CHAR_READ_ALL_ERROR);
+    replay_put_dword(res);
+    replay_mutex_unlock();
+}
+
+void replay_char_read_all_save_buf(uint8_t *buf, int offset)
+{
+    replay_save_instructions();
+    replay_mutex_lock();
+    replay_put_event(EVENT_CHAR_READ_ALL);
+    replay_put_array(buf, offset);
+    replay_mutex_unlock();
+}

replay/replay-events.c

@@ -48,6 +48,9 @@ static void replay_run_event(Event *event)
     case REPLAY_ASYNC_EVENT_INPUT_SYNC:
         qemu_input_event_sync_impl();
         break;
+    case REPLAY_ASYNC_EVENT_CHAR_READ:
+        replay_event_char_read_run(event->opaque);
+        break;
     default:
         error_report("Replay: invalid async event ID (%d) in the queue",
                     event->event_kind);
@@ -102,9 +105,9 @@ void replay_clear_events(void)
 }
 
 /*! Adds specified async event to the queue */
-static void replay_add_event(ReplayAsyncEventKind event_kind,
-                             void *opaque,
-                             void *opaque2, uint64_t id)
+void replay_add_event(ReplayAsyncEventKind event_kind,
+                      void *opaque,
+                      void *opaque2, uint64_t id)
 {
     assert(event_kind < REPLAY_ASYNC_COUNT);
 
@@ -168,6 +171,9 @@ static void replay_save_event(Event *event, int checkpoint)
             break;
         case REPLAY_ASYNC_EVENT_INPUT_SYNC:
             break;
+        case REPLAY_ASYNC_EVENT_CHAR_READ:
+            replay_event_char_read_save(event->opaque);
+            break;
         default:
             error_report("Unknown ID %d of replay event", read_event_kind);
             exit(1);
@@ -221,6 +227,11 @@ static Event *replay_read_event(int checkpoint)
         event->event_kind = read_event_kind;
         event->opaque = 0;
         return event;
+    case REPLAY_ASYNC_EVENT_CHAR_READ:
+        event = g_malloc0(sizeof(Event));
+        event->event_kind = read_event_kind;
+        event->opaque = replay_event_char_read_load();
+        return event;
     default:
         error_report("Unknown ID %d of replay event", read_event_kind);
         exit(1);

replay/replay-internal.h

@@ -24,6 +24,11 @@ enum ReplayEvents {
     EVENT_ASYNC,
     /* for shutdown request */
     EVENT_SHUTDOWN,
+    /* for character device write event */
+    EVENT_CHAR_WRITE,
+    /* for character device read all event */
+    EVENT_CHAR_READ_ALL,
+    EVENT_CHAR_READ_ALL_ERROR,
     /* for clock read/writes */
     /* some of greater codes are reserved for clocks */
     EVENT_CLOCK,
@@ -43,6 +48,7 @@ enum ReplayAsyncEventKind {
     REPLAY_ASYNC_EVENT_BH,
     REPLAY_ASYNC_EVENT_INPUT,
     REPLAY_ASYNC_EVENT_INPUT_SYNC,
+    REPLAY_ASYNC_EVENT_CHAR_READ,
     REPLAY_ASYNC_COUNT
 };
 
@@ -124,6 +130,9 @@ bool replay_has_events(void);
 void replay_save_events(int checkpoint);
 /*! Read events from the file into the input queue */
 void replay_read_events(int checkpoint);
+/*! Adds specified async event to the queue */
+void replay_add_event(ReplayAsyncEventKind event_kind, void *opaque,
+                      void *opaque2, uint64_t id);
 
 /* Input events */
 
@@ -136,4 +145,13 @@ void replay_add_input_event(struct InputEvent *event);
 /*! Adds input sync event to the queue */
 void replay_add_input_sync_event(void);
 
+/* Character devices */
+
+/*! Called to run char device read event. */
+void replay_event_char_read_run(void *opaque);
+/*! Writes char read event to the file. */
+void replay_event_char_read_save(void *opaque);
+/*! Reads char event read from the file. */
+void *replay_event_char_read_load(void);
+
 #endif

replay/replay.c

@@ -20,7 +20,7 @@
 
 /* Current version of the replay mechanism.
    Increase it when file format changes. */
-#define REPLAY_VERSION              0xe02002
+#define REPLAY_VERSION              0xe02003
 /* Size of replay log header */
 #define HEADER_SIZE                 (sizeof(uint32_t) + sizeof(uint64_t))
 

scripts/update-linux-headers.sh

@@ -103,7 +103,7 @@ done
 rm -rf "$output/linux-headers/linux"
 mkdir -p "$output/linux-headers/linux"
 for header in kvm.h kvm_para.h vfio.h vhost.h \
-              psci.h; do
+              psci.h userfaultfd.h; do
     cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux"
 done
 rm -rf "$output/linux-headers/asm-generic"

stubs/clock-warp.c

@@ -2,7 +2,7 @@
 #include "qemu-common.h"
 #include "qemu/timer.h"
 
-void qemu_clock_warp(QEMUClockType type)
+void qemu_start_warp_timer(void)
 {
 }
 

stubs/replay.c

@@ -29,3 +29,37 @@ bool replay_events_enabled(void)
 void replay_finish(void)
 {
 }
+
+void replay_register_char_driver(CharDriverState *chr)
+{
+}
+
+void replay_chr_be_write(CharDriverState *s, uint8_t *buf, int len)
+{
+    abort();
+}
+
+void replay_char_write_event_save(int res, int offset)
+{
+    abort();
+}
+
+void replay_char_write_event_load(int *res, int *offset)
+{
+    abort();
+}
+
+int replay_char_read_all_load(uint8_t *buf)
+{
+    abort();
+}
+
+void replay_char_read_all_save_error(int res)
+{
+    abort();
+}
+
+void replay_char_read_all_save_buf(uint8_t *buf, int offset)
+{
+    abort();
+}