[PATCH] qemu-kvm: Switch POSIX compat AIO implementation to upstream

[Jan Kiszka <jan.kiszka@xxxxxxxxxxx>]

Upstream's version is about to be signal-free and will stop handling
SIGUSR2 specially. So it's time to adopt its implementation, ie. switch
from signalfd to a pipe.

Signed-off-by: Jan Kiszka <jan.kiszka@xxxxxxxxxxx>
---

This should help pulling upstream into qemu-kvm when "block: avoid
SIGUSR2" is merged. And will help merging further cleanups of this code
I'm working on.

 posix-aio-compat.c |   73 ++++++++++++++++++++++-----------------------------
 1 files changed, 32 insertions(+), 41 deletions(-)

diff --git a/posix-aio-compat.c b/posix-aio-compat.c
index d8ad9ef..d375b56 100644
--- a/posix-aio-compat.c
+++ b/posix-aio-compat.c
@@ -27,7 +27,6 @@
 #include "qemu-common.h"
 #include "trace.h"
 #include "block_int.h"
-#include "compatfd.h"
 
 #include "block/raw-posix-aio.h"
 
@@ -43,7 +42,6 @@ struct qemu_paiocb {
     int aio_niov;
     size_t aio_nbytes;
 #define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
-    int ev_signo;
     off_t aio_offset;
 
     QTAILQ_ENTRY(qemu_paiocb) node;
@@ -54,7 +52,7 @@ struct qemu_paiocb {
 };
 
 typedef struct PosixAioState {
-    int fd;
+    int rfd, wfd;
     struct qemu_paiocb *first_aio;
 } PosixAioState;
 
@@ -310,12 +308,10 @@ static ssize_t handle_aiocb_rw(struct qemu_paiocb *aiocb)
     return nbytes;
 }
 
+static void posix_aio_notify_event(void);
+
 static void *aio_thread(void *unused)
 {
-    pid_t pid;
-
-    pid = getpid();
-
     mutex_lock(&lock);
     pending_threads--;
     mutex_unlock(&lock);
@@ -382,7 +378,7 @@ static void *aio_thread(void *unused)
         aiocb->ret = ret;
         mutex_unlock(&lock);
 
-        if (kill(pid, aiocb->ev_signo)) die("kill failed");
+        posix_aio_notify_event();
     }
 
     cur_threads--;
@@ -524,29 +520,18 @@ static int posix_aio_process_queue(void *opaque)
 static void posix_aio_read(void *opaque)
 {
     PosixAioState *s = opaque;
-    union {
-        struct qemu_signalfd_siginfo siginfo;
-        char buf[128];
-    } sig;
-    size_t offset;
+    ssize_t len;
 
-    /* try to read from signalfd, don't freak out if we can't read anything */
-    offset = 0;
-    while (offset < 128) {
-        ssize_t len;
+    /* read all bytes from signal pipe */
+    for (;;) {
+        char bytes[16];
 
-        len = read(s->fd, sig.buf + offset, 128 - offset);
+        len = read(s->rfd, bytes, sizeof(bytes));
         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;
+            continue; /* try again */
+        if (len == sizeof(bytes))
+            continue; /* more to read */
+        break;
     }
 
     posix_aio_process_queue(s);
@@ -560,6 +545,16 @@ static int posix_aio_flush(void *opaque)
 
 static PosixAioState *posix_aio_state;
 
+static void posix_aio_notify_event(void)
+{
+    char byte = 0;
+    ssize_t ret;
+
+    ret = write(posix_aio_state->wfd, &byte, sizeof(byte));
+    if (ret < 0 && errno != EAGAIN)
+        die("write()");
+}
+
 static void paio_remove(struct qemu_paiocb *acb)
 {
     struct qemu_paiocb **pacb;
@@ -621,7 +616,6 @@ BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
         return NULL;
     acb->aio_type = type;
     acb->aio_fildes = fd;
-    acb->ev_signo = SIGUSR2;
 
     if (qiov) {
         acb->aio_iov = qiov->iov;
@@ -649,7 +643,6 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
         return NULL;
     acb->aio_type = QEMU_AIO_IOCTL;
     acb->aio_fildes = fd;
-    acb->ev_signo = SIGUSR2;
     acb->aio_offset = 0;
     acb->aio_ioctl_buf = buf;
     acb->aio_ioctl_cmd = req;
@@ -663,8 +656,8 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
 
 int paio_init(void)
 {
-    sigset_t mask;
     PosixAioState *s;
+    int fds[2];
     int ret;
 
     if (posix_aio_state)
@@ -672,21 +665,19 @@ int paio_init(void)
 
     s = g_malloc(sizeof(PosixAioState));
 
-    /* Make sure to block AIO signal */
-    sigemptyset(&mask);
-    sigaddset(&mask, SIGUSR2);
-    sigprocmask(SIG_BLOCK, &mask, NULL);
-
     s->first_aio = NULL;
-    s->fd = qemu_signalfd(&mask);
-    if (s->fd == -1) {
-        fprintf(stderr, "failed to create signalfd\n");
+    if (qemu_pipe(fds) == -1) {
+        fprintf(stderr, "failed to create pipe\n");
         return -1;
     }
 
-    fcntl(s->fd, F_SETFL, O_NONBLOCK);
+    s->rfd = fds[0];
+    s->wfd = fds[1];
+
+    fcntl(s->rfd, F_SETFL, O_NONBLOCK);
+    fcntl(s->wfd, F_SETFL, O_NONBLOCK);
 
-    qemu_aio_set_fd_handler(s->fd, posix_aio_read, NULL, posix_aio_flush,
+    qemu_aio_set_fd_handler(s->rfd, posix_aio_read, NULL, posix_aio_flush,
         posix_aio_process_queue, s);
 
     ret = pthread_attr_init(&attr);
-- 
1.7.3.4
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html