Fix IO performance regression in sparc

Replace signalfd with signal handler/pipe.  There is no way to interrupt
the CPU execution loop when a file descriptor becomes readable.  This
results in a large performance regression in sparc emulation during
bootup.
   
This patch switches us to signal handler/pipe which was originally
suggested by Ian Jackson.  The signal handler lets us interrupt the
CPU emulation loop while the write to a pipe lets us avoid the
select/signal race condition.
    
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5451 c046a42c-6fe2-441c-8c8c-71466251a162

Makefile

@@ -59,10 +59,6 @@ else
 BLOCK_OBJS += block-raw-posix.o
 endif
 
-ifdef CONFIG_AIO
-BLOCK_OBJS += compatfd.o
-endif
-
 ######################################################################
 # libqemu_common.a: Target independent part of system emulation. The
 # long term path is to suppress *all* target specific code in case of

Makefile.target

@@ -481,10 +481,6 @@ else
 OBJS+=block-raw-posix.o
 endif
 
-ifdef CONFIG_AIO
-OBJS+=compatfd.o
-endif
-
 LIBS+=-lz
 ifdef CONFIG_ALSA
 LIBS += -lasound

block-raw-posix.c

@@ -25,7 +25,6 @@
 #include "qemu-timer.h"
 #include "qemu-char.h"
 #include "block_int.h"
-#include "compatfd.h"
 #include <assert.h>
 #ifdef CONFIG_AIO
 #include <aio.h>
@@ -453,7 +452,7 @@ typedef struct RawAIOCB {
 
 typedef struct PosixAioState
 {
-    int fd;
+    int rfd, wfd;
     RawAIOCB *first_aio;
 } PosixAioState;
 
@@ -494,30 +493,17 @@ static void posix_aio_read(void *opaque)
     PosixAioState *s = opaque;
     RawAIOCB *acb, **pacb;
     int ret;
-    size_t offset;
-    union {
-        struct qemu_signalfd_siginfo siginfo;
-        char buf[128];
-    } sig;
-
-    /* try to read from signalfd, don't freak out if we can't read anything */
-    offset = 0;
-    while (offset < 128) {
-        ssize_t len;
-
-        len = read(s->fd, sig.buf + offset, 128 - offset);
+    ssize_t len;
+
+    do {
+        char byte;
+
+        len = read(s->rfd, &byte, 1);
         if (len == -1 && errno == EINTR)
             continue;
-        if (len == -1 && errno == EAGAIN) {
-            /* there is no natural reason for this to happen,
-             * so we'll spin hard until we get everything just
-             * to be on the safe side. */
-            if (offset > 0)
-                continue;
-        }
-
-        offset += len;
-    }
+        if (len == -1 && errno == EAGAIN)
+            break;
+    } while (len == -1);
 
     for(;;) {
         pacb = &s->first_aio;
@@ -565,10 +551,22 @@ static int posix_aio_flush(void *opaque)
 
 static PosixAioState *posix_aio_state;
 
+static void aio_signal_handler(int signum)
+{
+    if (posix_aio_state) {
+        char byte = 0;
+
+        write(posix_aio_state->wfd, &byte, sizeof(byte));
+    }
+
+    qemu_service_io();
+}
+
 static int posix_aio_init(void)
 {
-    sigset_t mask;
+    struct sigaction act;
     PosixAioState *s;
+    int fds[2];
 
     if (posix_aio_state)
         return 0;
@@ -577,21 +575,23 @@ static int posix_aio_init(void)
     if (s == NULL)
         return -ENOMEM;
 
-    /* Make sure to block AIO signal */
-    sigemptyset(&mask);
-    sigaddset(&mask, SIGUSR2);
-    sigprocmask(SIG_BLOCK, &mask, NULL);
-    
+    sigfillset(&act.sa_mask);
+    act.sa_flags = 0; /* do not restart syscalls to interrupt select() */
+    act.sa_handler = aio_signal_handler;
+    sigaction(SIGUSR2, &act, NULL);
+
     s->first_aio = NULL;
-    s->fd = qemu_signalfd(&mask);
-    if (s->fd == -1) {
-        fprintf(stderr, "failed to create signalfd\n");
+    if (pipe(fds) == -1) {
+        fprintf(stderr, "failed to create pipe\n");
         return -errno;
     }
 
-    fcntl(s->fd, F_SETFL, O_NONBLOCK);
+    s->rfd = fds[0];
+    s->wfd = fds[1];
+
+    fcntl(s->wfd, F_SETFL, O_NONBLOCK);
 
-    qemu_aio_set_fd_handler(s->fd, posix_aio_read, NULL, posix_aio_flush, s);
+    qemu_aio_set_fd_handler(s->rfd, posix_aio_read, NULL, posix_aio_flush, s);
 
 #if defined(__linux__)
     {

configure

@@ -113,8 +113,6 @@ aio="yes"
 nptl="yes"
 mixemu="no"
 bluez="yes"
-signalfd="no"
-eventfd="no"
 
 # OS specific
 targetos=`uname -s`
@@ -930,33 +928,6 @@ EOF
   fi
 fi
 
-##########################################
-# signalfd probe
-cat > $TMPC << EOF
-#define _GNU_SOURCE
-#include <unistd.h>
-#include <sys/syscall.h>
-#include <signal.h>
-int main(void) { return syscall(SYS_signalfd, -1, NULL, _NSIG / 8); }
-EOF
-
-if $cc $ARCH_CFLAGS -o $TMPE $TMPC 2> /dev/null ; then
-  signalfd=yes
-fi
-
-##########################################
-# eventfd probe
-cat > $TMPC << EOF
-#define _GNU_SOURCE
-#include <unistd.h>
-#include <sys/syscall.h>
-int main(void) { return syscall(SYS_eventfd, 0); }
-EOF
-
-if $cc $ARCH_CFLAGS -o $TMPE $TMPC 2> /dev/null ; then
-  eventfd=yes
-fi
-
 # Check if tools are available to build documentation.
 if [ -x "`which texi2html 2>/dev/null`" ] && \
    [ -x "`which pod2man 2>/dev/null`" ]; then
@@ -1297,12 +1268,6 @@ if test "$aio" = "yes" ; then
   echo "#define CONFIG_AIO 1" >> $config_h
   echo "CONFIG_AIO=yes" >> $config_mak
 fi
-if test "$signalfd" = "yes" ; then
-  echo "#define CONFIG_signalfd 1" >> $config_h
-fi
-if test "$eventfd" = "yes" ; then
-  echo "#define CONFIG_eventfd 1" >> $config_h
-fi
 
 # XXX: suppress that
 if [ "$bsd" = "yes" ] ; then

qemu-common.h

@@ -139,4 +139,7 @@ struct pcmcia_card_s;
 void cpu_save(QEMUFile *f, void *opaque);
 int cpu_load(QEMUFile *f, void *opaque, int version_id);
 
+/* Force QEMU to stop what it's doing and service IO */
+void qemu_service_io(void);
+
 #endif

qemu-tool.c

@@ -26,6 +26,10 @@ struct QEMUBH
     void *opaque;
 };
 
+void qemu_service_io(void)
+{
+}
+
 void term_printf(const char *fmt, ...)
 {
 }

vl.c

@@ -7475,6 +7475,19 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
     return 0;
 }
 
+void qemu_service_io(void)
+{
+    CPUState *env = cpu_single_env;
+    if (env) {
+        cpu_interrupt(env, CPU_INTERRUPT_EXIT);
+#ifdef USE_KQEMU
+        if (env->kqemu_enabled) {
+            kqemu_cpu_interrupt(env);
+        }
+#endif
+    }
+}
+
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */