raw-posix: add Linux native AIO support

Now that do have a nicer interface to work against we can add Linux native
AIO support.  It's an extremly thing layer just setting up an iocb for
the io_submit system call in the submission path, and registering an
eventfd with the qemu poll handler to do complete the iocbs directly
from there.

This started out based on Anthony's earlier AIO patch, but after
estimated 42,000 rewrites and just as many build system changes
there's not much left of it.

To enable native kernel aio use the aio=native sub-command on the
drive command line.  I have also added an option to qemu-io to
test the aio support without needing a guest.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

11 files changed, 305 insertions, 8 deletions

diff --git a/Makefile b/Makefile
index b0a84f36e4..bdac9b331c 100644
--- a/Makefile
+++ b/Makefile
@@ -56,6 +56,7 @@ recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
 block-obj-y = cutils.o cache-utils.o qemu-malloc.o qemu-option.o module.o
 block-obj-y += nbd.o block.o aio.o aes.o osdep.o
 block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
+block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 
 block-nested-y += cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o
diff --git a/block.c b/block.c
index 82ffea8753..033957daf6 100644
--- a/block.c
+++ b/block.c
@@ -411,7 +411,8 @@ int bdrv_open2(BlockDriverState *bs, const char *filename, int flags,
     /* Note: for compatibility, we open disk image files as RDWR, and
        RDONLY as fallback */
     if (!(flags & BDRV_O_FILE))
-        open_flags = BDRV_O_RDWR | (flags & BDRV_O_CACHE_MASK);
+        open_flags = BDRV_O_RDWR |
+		(flags & (BDRV_O_CACHE_MASK|BDRV_O_NATIVE_AIO));
     else
         open_flags = flags & ~(BDRV_O_FILE | BDRV_O_SNAPSHOT);
     ret = drv->bdrv_open(bs, filename, open_flags);
diff --git a/block.h b/block.h
index ccd4c1e700..28bf357091 100644
--- a/block.h
+++ b/block.h
@@ -37,6 +37,7 @@ typedef struct QEMUSnapshotInfo {
                                      bdrv_file_open()) */
 #define BDRV_O_NOCACHE     0x0020 /* do not use the host page cache */
 #define BDRV_O_CACHE_WB    0x0040 /* use write-back caching */
+#define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the thread pool */
 
 #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB)
 
diff --git a/block/raw-posix-aio.h b/block/raw-posix-aio.h
index 6761cd39f3..244bc8b798 100644
--- a/block/raw-posix-aio.h
+++ b/block/raw-posix-aio.h
@@ -33,4 +33,10 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
         unsigned long int req, void *buf,
         BlockDriverCompletionFunc *cb, void *opaque);
 
+/* linux-aio.c - Linux native implementation */
+void *laio_init(void);
+BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type);
+
 #endif /* QEMU_RAW_POSIX_AIO_H */
diff --git a/block/raw-posix.c b/block/raw-posix.c
index ca9bc616a7..8a7dc1570c 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -115,6 +115,7 @@ typedef struct BDRVRawState {
     int fd_got_error;
     int fd_media_changed;
 #endif
+    int use_aio;
     uint8_t* aligned_buf;
 } BDRVRawState;
 
@@ -159,6 +160,7 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
     }
     s->fd = fd;
     s->aligned_buf = NULL;
+
     if ((bdrv_flags & BDRV_O_NOCACHE)) {
         s->aligned_buf = qemu_blockalign(bs, ALIGNED_BUFFER_SIZE);
         if (s->aligned_buf == NULL) {
@@ -166,9 +168,22 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
         }
     }
 
-    s->aio_ctx = paio_init();
-    if (!s->aio_ctx) {
-        goto out_free_buf;
+#ifdef CONFIG_LINUX_AIO
+    if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
+                      (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
+        s->aio_ctx = laio_init();
+        if (!s->aio_ctx) {
+            goto out_free_buf;
+        }
+        s->use_aio = 1;
+    } else
+#endif
+    {
+        s->aio_ctx = paio_init();
+        if (!s->aio_ctx) {
+            goto out_free_buf;
+        }
+        s->use_aio = 0;
     }
 
     return 0;
@@ -524,8 +539,13 @@ static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
      * boundary.  Check if this is the case or telll the low-level
      * driver that it needs to copy the buffer.
      */
-    if (s->aligned_buf && !qiov_is_aligned(qiov)) {
-        type |= QEMU_AIO_MISALIGNED;
+    if (s->aligned_buf) {
+        if (!qiov_is_aligned(qiov)) {
+            type |= QEMU_AIO_MISALIGNED;
+        } else if (s->use_aio) {
+            return laio_submit(bs, s->aio_ctx, s->fd, sector_num, qiov,
+	                       nb_sectors, cb, opaque, type);
+        }
     }
 
     return paio_submit(bs, s->aio_ctx, s->fd, sector_num, qiov, nb_sectors,
diff --git a/configure b/configure
index b993b656af..81272fa4ca 100755
--- a/configure
+++ b/configure
@@ -191,6 +191,7 @@ vde=""
 vnc_tls=""
 vnc_sasl=""
 xen=""
+linux_aio=""
 
 gprof="no"
 debug_tcg="no"
@@ -523,6 +524,10 @@ for opt do
   ;;
   --enable-mixemu) mixemu="yes"
   ;;
+  --disable-linux-aio) linux_aio="no"
+  ;;
+  --enable-linux-aio) linux_aio="yes"
+  ;;
   --enable-io-thread) io_thread="yes"
   ;;
   --disable-blobs) blobs="no"
@@ -674,6 +679,8 @@ echo "  --enable-uname-release=R Return R for uname -r in usermode emulation"
 echo "  --sparc_cpu=V            Build qemu for Sparc architecture v7, v8, v8plus, v8plusa, v9"
 echo "  --disable-vde            disable support for vde network"
 echo "  --enable-vde             enable support for vde network"
+echo "  --disable-linux-aio      disable Linux AIO support"
+echo "  --enable-linux-aio       enable Linux AIO support"
 echo "  --enable-io-thread       enable IO thread"
 echo "  --disable-blobs          disable installing provided firmware blobs"
 echo "  --kerneldir=PATH         look for kernel includes in PATH"
@@ -1304,6 +1311,26 @@ if test "$pthread" = no; then
 fi
 
 ##########################################
+# linux-aio probe
+AIOLIBS=""
+
+if test "$linux_aio" != "no" ; then
+  cat > $TMPC <<EOF
+#include <libaio.h>
+#include <sys/eventfd.h>
+int main(void) { io_setup(0, NULL); io_set_eventfd(NULL, 0); eventfd(0, 0); return 0; }
+EOF
+  if compile_prog "" "-laio" ; then
+    linux_aio=yes
+    LIBS="$LIBS -laio"
+  else
+    if test "$linux_aio" = "yes" ; then
+      feature_not_found "linux AIO"
+    fi
+  fi
+fi
+
+##########################################
 # iovec probe
 cat > $TMPC <<EOF
 #include <sys/types.h>
@@ -1638,6 +1665,7 @@ echo "NPTL support      $nptl"
 echo "GUEST_BASE        $guest_base"
 echo "vde support       $vde"
 echo "IO thread         $io_thread"
+echo "Linux AIO support $linux_aio"
 echo "Install blobs     $blobs"
 echo "KVM support       $kvm"
 echo "fdt support       $fdt"
@@ -1811,6 +1839,9 @@ fi
 if test "$io_thread" = "yes" ; then
   echo "CONFIG_IOTHREAD=y" >> $config_host_mak
 fi
+if test "$linux_aio" = "yes" ; then
+  echo "CONFIG_LINUX_AIO=y" >> $config_host_mak
+fi
 if test "$blobs" = "yes" ; then
   echo "INSTALL_BLOBS=yes" >> $config_host_mak
 fi
diff --git a/linux-aio.c b/linux-aio.c
new file mode 100644
index 0000000000..f53a08cb0c
--- /dev/null
+++ b/linux-aio.c
@@ -0,0 +1,204 @@
+/*
+ * Linux native AIO support.
+ *
+ * Copyright (C) 2009 IBM, Corp.
+ * Copyright (C) 2009 Red Hat, Inc.
+ *
+ * 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 "qemu-common.h"
+#include "qemu-aio.h"
+#include "block_int.h"
+#include "block/raw-posix-aio.h"
+
+#include <sys/eventfd.h>
+#include <libaio.h>
+
+/*
+ * Queue size (per-device).
+ *
+ * XXX: eventually we need to communicate this to the guest and/or make it
+ *      tunable by the guest.  If we get more outstanding requests at a time
+ *      than this we will get EAGAIN from io_submit which is communicated to
+ *      the guest as an I/O error.
+ */
+#define MAX_EVENTS 128
+
+struct qemu_laiocb {
+    BlockDriverAIOCB common;
+    struct qemu_laio_state *ctx;
+    struct iocb iocb;
+    ssize_t ret;
+    size_t nbytes;
+};
+
+struct qemu_laio_state {
+    io_context_t ctx;
+    int efd;
+    int count;
+};
+
+static inline ssize_t io_event_ret(struct io_event *ev)
+{
+    return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
+}
+
+static void qemu_laio_completion_cb(void *opaque)
+{
+    struct qemu_laio_state *s = opaque;
+
+    while (1) {
+        struct io_event events[MAX_EVENTS];
+        uint64_t val;
+        ssize_t ret;
+        struct timespec ts = { 0 };
+        int nevents, i;
+
+        do {
+            ret = read(s->efd, &val, sizeof(val));
+        } while (ret == 1 && errno == EINTR);
+
+        if (ret == -1 && errno == EAGAIN)
+            break;
+
+        if (ret != 8)
+            break;
+
+        do {
+            nevents = io_getevents(s->ctx, val, MAX_EVENTS, events, &ts);
+        } while (nevents == -EINTR);
+
+        for (i = 0; i < nevents; i++) {
+            struct iocb *iocb = events[i].obj;
+            struct qemu_laiocb *laiocb =
+                    container_of(iocb, struct qemu_laiocb, iocb);
+
+            s->count--;
+
+            ret = laiocb->ret = io_event_ret(&events[i]);
+            if (ret != -ECANCELED) {
+                if (ret == laiocb->nbytes)
+                    ret = 0;
+                else if (ret >= 0)
+                    ret = -EINVAL;
+
+                laiocb->common.cb(laiocb->common.opaque, ret);
+            }
+
+            qemu_aio_release(laiocb);
+        }
+    }
+}
+
+static int qemu_laio_flush_cb(void *opaque)
+{
+    struct qemu_laio_state *s = opaque;
+
+    return (s->count > 0) ? 1 : 0;
+}
+
+static void laio_cancel(BlockDriverAIOCB *blockacb)
+{
+    struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
+    struct io_event event;
+    int ret;
+
+    if (laiocb->ret != -EINPROGRESS)
+        return;
+
+    /*
+     * Note that as of Linux 2.6.31 neither the block device code nor any
+     * filesystem implements cancellation of AIO request.
+     * Thus the polling loop below is the normal code path.
+     */
+    ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
+    if (ret == 0) {
+        laiocb->ret = -ECANCELED;
+        return;
+    }
+
+    /*
+     * We have to wait for the iocb to finish.
+     *
+     * The only way to get the iocb status update is by polling the io context.
+     * We might be able to do this slightly more optimal by removing the
+     * O_NONBLOCK flag.
+     */
+    while (laiocb->ret == -EINPROGRESS)
+        qemu_laio_completion_cb(laiocb->ctx);
+}
+
+static AIOPool laio_pool = {
+    .aiocb_size         = sizeof(struct qemu_laiocb),
+    .cancel             = laio_cancel,
+};
+
+BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type)
+{
+    struct qemu_laio_state *s = aio_ctx;
+    struct qemu_laiocb *laiocb;
+    struct iocb *iocbs;
+    off_t offset = sector_num * 512;
+
+    laiocb = qemu_aio_get(&laio_pool, bs, cb, opaque);
+    if (!laiocb)
+        return NULL;
+    laiocb->nbytes = nb_sectors * 512;
+    laiocb->ctx = s;
+    laiocb->ret = -EINPROGRESS;
+
+    iocbs = &laiocb->iocb;
+
+    switch (type) {
+    case QEMU_AIO_WRITE:
+        io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
+	break;
+    case QEMU_AIO_READ:
+        io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset);
+	break;
+    default:
+        fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
+                        __func__, type);
+        goto out_free_aiocb;
+    }
+    io_set_eventfd(&laiocb->iocb, s->efd);
+    s->count++;
+
+    if (io_submit(s->ctx, 1, &iocbs) < 0)
+        goto out_dec_count;
+    return &laiocb->common;
+
+out_free_aiocb:
+    qemu_aio_release(laiocb);
+out_dec_count:
+    s->count--;
+    return NULL;
+}
+
+void *laio_init(void)
+{
+    struct qemu_laio_state *s;
+
+    s = qemu_mallocz(sizeof(*s));
+    s->efd = eventfd(0, 0);
+    if (s->efd == -1)
+        goto out_free_state;
+    fcntl(s->efd, F_SETFL, O_NONBLOCK);
+
+    if (io_setup(MAX_EVENTS, &s->ctx) != 0)
+        goto out_close_efd;
+
+    qemu_aio_set_fd_handler(s->efd, qemu_laio_completion_cb,
+                            NULL, qemu_laio_flush_cb, s);
+
+    return s;
+
+out_close_efd:
+    close(s->efd);
+out_free_state:
+    qemu_free(s);
+    return NULL;
+}
diff --git a/qemu-config.c b/qemu-config.c
index 3dd473a710..4808db0531 100644
--- a/qemu-config.c
+++ b/qemu-config.c
@@ -53,6 +53,10 @@ QemuOptsList qemu_drive_opts = {
             .type = QEMU_OPT_STRING,
             .help = "host cache usage (none, writeback, writethrough)",
         },{
+            .name = "aio",
+            .type = QEMU_OPT_STRING,
+            .help = "host AIO implementation (threads, native)",
+        },{
             .name = "format",
             .type = QEMU_OPT_STRING,
             .help = "disk format (raw, qcow2, ...)",
diff --git a/qemu-io.c b/qemu-io.c
index a68f195c11..f96a4de6b4 100644
--- a/qemu-io.c
+++ b/qemu-io.c
@@ -1401,6 +1401,7 @@ static void usage(const char *name)
 "  -n, --nocache        disable host cache\n"
 "  -g, --growable       allow file to grow (only applies to protocols)\n"
 "  -m, --misalign       misalign allocations for O_DIRECT\n"
+"  -k, --native-aio     use kernel AIO implementation (on Linux only)\n"
 "  -h, --help           display this help and exit\n"
 "  -V, --version        output version information and exit\n"
 "\n",
@@ -1412,7 +1413,7 @@ int main(int argc, char **argv)
 {
 	int readonly = 0;
 	int growable = 0;
-	const char *sopt = "hVc:Crsnmg";
+	const char *sopt = "hVc:Crsnmgk";
 	struct option lopt[] = {
 		{ "help", 0, NULL, 'h' },
 		{ "version", 0, NULL, 'V' },
@@ -1424,6 +1425,7 @@ int main(int argc, char **argv)
 		{ "nocache", 0, NULL, 'n' },
 		{ "misalign", 0, NULL, 'm' },
 		{ "growable", 0, NULL, 'g' },
+		{ "native-aio", 0, NULL, 'k' },
 		{ NULL, 0, NULL, 0 }
 	};
 	int c;
@@ -1455,6 +1457,9 @@ int main(int argc, char **argv)
 		case 'g':
 			growable = 1;
 			break;
+		case 'k':
+			flags |= BDRV_O_NATIVE_AIO;
+			break;
 		case 'V':
 			printf("%s version %s\n", progname, VERSION);
 			exit(0);
diff --git a/qemu-options.hx b/qemu-options.hx
index e3bd314509..0c2b310562 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -95,7 +95,7 @@ DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n"
     "       [,cyls=c,heads=h,secs=s[,trans=t]][,snapshot=on|off]\n"
     "       [,cache=writethrough|writeback|none][,format=f][,serial=s]\n"
-    "       [,addr=A][,id=name]\n"
+    "       [,addr=A][,id=name][,aio=threads|native]\n"
     "                use 'file' as a drive image\n")
 DEF("set", HAS_ARG, QEMU_OPTION_set,
     "-set group.id.arg=value\n"
@@ -128,6 +128,8 @@ These options have the same definition as they have in @option{-hdachs}.
 @var{snapshot} is "on" or "off" and allows to enable snapshot for given drive (see @option{-snapshot}).
 @item cache=@var{cache}
 @var{cache} is "none", "writeback", or "writethrough" and controls how the host cache is used to access block data.
+@item aio=@var{aio}
+@var{aio} is "threads", or "native" and selects between pthread based disk I/O and native Linux AIO.
 @item format=@var{format}
 Specify which disk @var{format} will be used rather than detecting
 the format.  Can be used to specifiy format=raw to avoid interpreting
diff --git a/vl.c b/vl.c
index 9b2bf00a72..1085794190 100644
--- a/vl.c
+++ b/vl.c
@@ -1916,6 +1916,7 @@ DriveInfo *drive_init(QemuOpts *opts, void *opaque,
     int max_devs;
     int index;
     int cache;
+    int aio = 0;
     int bdrv_flags, onerror;
     const char *devaddr;
     DriveInfo *dinfo;
@@ -2049,6 +2050,19 @@ DriveInfo *drive_init(QemuOpts *opts, void *opaque,
         }
     }
 
+#ifdef CONFIG_LINUX_AIO
+    if ((buf = qemu_opt_get(opts, "aio")) != NULL) {
+        if (!strcmp(buf, "threads"))
+            aio = 0;
+        else if (!strcmp(buf, "native"))
+            aio = 1;
+        else {
+           fprintf(stderr, "qemu: invalid aio option\n");
+           return NULL;
+        }
+    }
+#endif
+
     if ((buf = qemu_opt_get(opts, "format")) != NULL) {
        if (strcmp(buf, "?") == 0) {
             fprintf(stderr, "qemu: Supported formats:");
@@ -2218,11 +2232,19 @@ DriveInfo *drive_init(QemuOpts *opts, void *opaque,
         bdrv_flags |= BDRV_O_NOCACHE;
     else if (cache == 2) /* write-back */
         bdrv_flags |= BDRV_O_CACHE_WB;
+
+    if (aio == 1) {
+        bdrv_flags |= BDRV_O_NATIVE_AIO;
+    } else {
+        bdrv_flags &= ~BDRV_O_NATIVE_AIO;
+    }
+
     if (bdrv_open2(dinfo->bdrv, file, bdrv_flags, drv) < 0) {
         fprintf(stderr, "qemu: could not open disk image %s\n",
                         file);
         return NULL;
     }
+
     if (bdrv_key_required(dinfo->bdrv))
         autostart = 0;
     *fatal_error = 0;