/*
 * QEMU posix-aio emulation
 *
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include <sys/ioctl.h>
#include <sys/types.h>
#include <pthread.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>
#include <signal.h>
#include <string.h>
#include <stdlib.h>
#include <stdio.h>

#include "qemu-queue.h"
#include "osdep.h"
#include "qemu-common.h"
#include "block_int.h"
#include "compatfd.h"

#include "block/raw-posix-aio.h"


struct qemu_paiocb {
    BlockDriverAIOCB common;
    int aio_fildes;
    union {
        struct iovec *aio_iov;
	void *aio_ioctl_buf;
    };
    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;
    int aio_type;
    ssize_t ret;
    int active;
    struct qemu_paiocb *next;

    int async_context_id;
};

typedef struct PosixAioState {
    int fd;
    struct qemu_paiocb *first_aio;
} PosixAioState;


static pthread_mutex_t lock = PTHREAD_MUTEX_INITIALIZER;
static pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
static pthread_t thread_id;
static pthread_attr_t attr;
static int max_threads = 64;
static int cur_threads = 0;
static int idle_threads = 0;
static QTAILQ_HEAD(, qemu_paiocb) request_list;

#ifdef CONFIG_PREADV
static int preadv_present = 1;
#else
static int preadv_present = 0;
#endif

static void die2(int err, const char *what)
{
    fprintf(stderr, "%s failed: %s\n", what, strerror(err));
    abort();
}

static void die(const char *what)
{
    die2(errno, what);
}

static void mutex_lock(pthread_mutex_t *mutex)
{
    int ret = pthread_mutex_lock(mutex);
    if (ret) die2(ret, "pthread_mutex_lock");
}

static void mutex_unlock(pthread_mutex_t *mutex)
{
    int ret = pthread_mutex_unlock(mutex);
    if (ret) die2(ret, "pthread_mutex_unlock");
}

static int cond_timedwait(pthread_cond_t *cond, pthread_mutex_t *mutex,
                           struct timespec *ts)
{
    int ret = pthread_cond_timedwait(cond, mutex, ts);
    if (ret && ret != ETIMEDOUT) die2(ret, "pthread_cond_timedwait");
    return ret;
}

static void cond_signal(pthread_cond_t *cond)
{
    int ret = pthread_cond_signal(cond);
    if (ret) die2(ret, "pthread_cond_signal");
}

static void thread_create(pthread_t *thread, pthread_attr_t *attr,
                          void *(*start_routine)(void*), void *arg)
{
    int ret = pthread_create(thread, attr, start_routine, arg);
    if (ret) die2(ret, "pthread_create");
}

static size_t handle_aiocb_ioctl(struct qemu_paiocb *aiocb)
{
	int ret;

	ret = ioctl(aiocb->aio_fildes, aiocb->aio_ioctl_cmd, aiocb->aio_ioctl_buf);
	if (ret == -1)
		return -errno;

	/*
	 * This looks weird, but the aio code only consideres a request
	 * successfull if it has written the number full number of bytes.
	 *
	 * Now we overload aio_nbytes as aio_ioctl_cmd for the ioctl command,
	 * so in fact we return the ioctl command here to make posix_aio_read()
	 * happy..
	 */
	return aiocb->aio_nbytes;
}

static size_t handle_aiocb_flush(struct qemu_paiocb *aiocb)
{
    int ret;

    ret = qemu_fdatasync(aiocb->aio_fildes);
    if (ret == -1)
        return -errno;
    return 0;
}

#ifdef CONFIG_PREADV

static ssize_t
qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return preadv(fd, iov, nr_iov, offset);
}

static ssize_t
qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return pwritev(fd, iov, nr_iov, offset);
}

#else

static ssize_t
qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return -ENOSYS;
}

static ssize_t
qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return -ENOSYS;
}

#endif

static size_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb)
{
    size_t offset = 0;
    ssize_t len;

    do {
        if (aiocb->aio_type & QEMU_AIO_WRITE)
            len = qemu_pwritev(aiocb->aio_fildes,
                               aiocb->aio_iov,
                               aiocb->aio_niov,
                               aiocb->aio_offset + offset);
         else
            len = qemu_preadv(aiocb->aio_fildes,
                              aiocb->aio_iov,
                              aiocb->aio_niov,
                              aiocb->aio_offset + offset);
    } while (len == -1 && errno == EINTR);

    if (len == -1)
        return -errno;
    return len;
}

static size_t handle_aiocb_rw_linear(struct qemu_paiocb *aiocb, char *buf)
{
    size_t offset = 0;
    size_t len;

    while (offset < aiocb->aio_nbytes) {
         if (aiocb->aio_type & QEMU_AIO_WRITE)
             len = pwrite(aiocb->aio_fildes,
                          (const char *)buf + offset,
                          aiocb->aio_nbytes - offset,
                          aiocb->aio_offset + offset);
         else
             len = pread(aiocb->aio_fildes,
                         buf + offset,
                         aiocb->aio_nbytes - offset,
                         aiocb->aio_offset + offset);

         if (len == -1 && errno == EINTR)
             continue;
         else if (len == -1) {
             offset = -errno;
             break;
         } else if (len == 0)
             break;

         offset += len;
    }

    return offset;
}

static size_t handle_aiocb_rw(struct qemu_paiocb *aiocb)
{
    size_t nbytes;
    char *buf;

    if (!(aiocb->aio_type & QEMU_AIO_MISALIGNED)) {
        /*
         * If there is just a single buffer, and it is properly aligned
         * we can just use plain pread/pwrite without any problems.
         */
        if (aiocb->aio_niov == 1)
             return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);

        /*
         * We have more than one iovec, and all are properly aligned.
         *
         * Try preadv/pwritev first and fall back to linearizing the
         * buffer if it's not supported.
         */
	if (preadv_present) {
            nbytes = handle_aiocb_rw_vector(aiocb);
            if (nbytes == aiocb->aio_nbytes)
	        return nbytes;
            if (nbytes < 0 && nbytes != -ENOSYS)
                return nbytes;
            preadv_present = 0;
        }

        /*
         * XXX(hch): short read/write.  no easy way to handle the reminder
         * using these interfaces.  For now retry using plain
         * pread/pwrite?
         */
    }

    /*
     * Ok, we have to do it the hard way, copy all segments into
     * a single aligned buffer.
     */
    buf = qemu_memalign(512, aiocb->aio_nbytes);
    if (aiocb->aio_type & QEMU_AIO_WRITE) {
        char *p = buf;
        int i;

        for (i = 0; i < aiocb->aio_niov; ++i) {
            memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
            p += aiocb->aio_iov[i].iov_len;
        }
    }

    nbytes = handle_aiocb_rw_linear(aiocb, buf);
    if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
        char *p = buf;
        size_t count = aiocb->aio_nbytes, copy;
        int i;

        for (i = 0; i < aiocb->aio_niov && count; ++i) {
            copy = count;
            if (copy > aiocb->aio_iov[i].iov_len)
                copy = aiocb->aio_iov[i].iov_len;
            memcpy(aiocb->aio_iov[i].iov_base, p, copy);
            p     += copy;
            count -= copy;
        }
    }
    qemu_vfree(buf);

    return nbytes;
}

static void *aio_thread(void *unused)
{
    pid_t pid;

    pid = getpid();

    while (1) {
        struct qemu_paiocb *aiocb;
        size_t ret = 0;
        qemu_timeval tv;
        struct timespec ts;

        qemu_gettimeofday(&tv);
        ts.tv_sec = tv.tv_sec + 10;
        ts.tv_nsec = 0;

        mutex_lock(&lock);

        while (QTAILQ_EMPTY(&request_list) &&
               !(ret == ETIMEDOUT)) {
            ret = cond_timedwait(&cond, &lock, &ts);
        }

        if (QTAILQ_EMPTY(&request_list))
            break;

        aiocb = QTAILQ_FIRST(&request_list);
        QTAILQ_REMOVE(&request_list, aiocb, node);
        aiocb->active = 1;
        idle_threads--;
        mutex_unlock(&lock);

        switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
        case QEMU_AIO_READ:
        case QEMU_AIO_WRITE:
		ret = handle_aiocb_rw(aiocb);
		break;
        case QEMU_AIO_FLUSH:
                ret = handle_aiocb_flush(aiocb);
                break;
        case QEMU_AIO_IOCTL:
		ret = handle_aiocb_ioctl(aiocb);
		break;
	default:
		fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
		ret = -EINVAL;
		break;
	}

        mutex_lock(&lock);
        aiocb->ret = ret;
        idle_threads++;
        mutex_unlock(&lock);

        if (kill(pid, aiocb->ev_signo)) die("kill failed");
    }

    idle_threads--;
    cur_threads--;
    mutex_unlock(&lock);

    return NULL;
}

static void spawn_thread(void)
{
    sigset_t set, oldset;

    cur_threads++;
    idle_threads++;

    /* block all signals */
    if (sigfillset(&set)) die("sigfillset");
    if (sigprocmask(SIG_SETMASK, &set, &oldset)) die("sigprocmask");

    thread_create(&thread_id, &attr, aio_thread, NULL);

    if (sigprocmask(SIG_SETMASK, &oldset, NULL)) die("sigprocmask restore");
}

static void qemu_paio_submit(struct qemu_paiocb *aiocb)
{
    aiocb->ret = -EINPROGRESS;
    aiocb->active = 0;
    mutex_lock(&lock);
    if (idle_threads == 0 && cur_threads < max_threads)
        spawn_thread();
    QTAILQ_INSERT_TAIL(&request_list, aiocb, node);
    mutex_unlock(&lock);
    cond_signal(&cond);
}

static ssize_t qemu_paio_return(struct qemu_paiocb *aiocb)
{
    ssize_t ret;

    mutex_lock(&lock);
    ret = aiocb->ret;
    mutex_unlock(&lock);

    return ret;
}

static int qemu_paio_error(struct qemu_paiocb *aiocb)
{
    ssize_t ret = qemu_paio_return(aiocb);

    if (ret < 0)
        ret = -ret;
    else
        ret = 0;

    return ret;
}

static int posix_aio_process_queue(void *opaque)
{
    PosixAioState *s = opaque;
    struct qemu_paiocb *acb, **pacb;
    int ret;
    int result = 0;
    int async_context_id = get_async_context_id();

    for(;;) {
        pacb = &s->first_aio;
        for(;;) {
            acb = *pacb;
            if (!acb)
                return result;

            /* we're only interested in requests in the right context */
            if (acb->async_context_id != async_context_id) {
                pacb = &acb->next;
                continue;
            }

            ret = qemu_paio_error(acb);
            if (ret == ECANCELED) {
                /* remove the request */
                *pacb = acb->next;
                qemu_aio_release(acb);
                result = 1;
            } else if (ret != EINPROGRESS) {
                /* end of aio */
                if (ret == 0) {
                    ret = qemu_paio_return(acb);
                    if (ret == acb->aio_nbytes)
                        ret = 0;
                    else
                        ret = -EINVAL;
                } else {
                    ret = -ret;
                }
                /* remove the request */
                *pacb = acb->next;
                /* call the callback */
                acb->common.cb(acb->common.opaque, ret);
                qemu_aio_release(acb);
                result = 1;
                break;
            } else {
                pacb = &acb->next;
            }
        }
    }

    return result;
}

static void posix_aio_read(void *opaque)
{
    PosixAioState *s = opaque;
    union {
        struct qemu_signalfd_siginfo siginfo;
        char buf[128];
    } sig;
    size_t offset;

    /* 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);
        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;
    }

    posix_aio_process_queue(s);
}

static int posix_aio_flush(void *opaque)
{
    PosixAioState *s = opaque;
    return !!s->first_aio;
}

static PosixAioState *posix_aio_state;

static void paio_remove(struct qemu_paiocb *acb)
{
    struct qemu_paiocb **pacb;

    /* remove the callback from the queue */
    pacb = &posix_aio_state->first_aio;
    for(;;) {
        if (*pacb == NULL) {
            fprintf(stderr, "paio_remove: aio request not found!\n");
            break;
        } else if (*pacb == acb) {
            *pacb = acb->next;
            qemu_aio_release(acb);
            break;
        }
        pacb = &(*pacb)->next;
    }
}

static void paio_cancel(BlockDriverAIOCB *blockacb)
{
    struct qemu_paiocb *acb = (struct qemu_paiocb *)blockacb;
    int active = 0;

    mutex_lock(&lock);
    if (!acb->active) {
        QTAILQ_REMOVE(&request_list, acb, node);
        acb->ret = -ECANCELED;
    } else if (acb->ret == -EINPROGRESS) {
        active = 1;
    }
    mutex_unlock(&lock);

    if (active) {
        /* fail safe: if the aio could not be canceled, we wait for
           it */
        while (qemu_paio_error(acb) == EINPROGRESS)
            ;
    }

    paio_remove(acb);
}

static AIOPool raw_aio_pool = {
    .aiocb_size         = sizeof(struct qemu_paiocb),
    .cancel             = paio_cancel,
};

BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type)
{
    struct qemu_paiocb *acb;

    acb = qemu_aio_get(&raw_aio_pool, bs, cb, opaque);
    if (!acb)
        return NULL;
    acb->aio_type = type;
    acb->aio_fildes = fd;
    acb->ev_signo = SIGUSR2;
    acb->async_context_id = get_async_context_id();

    if (qiov) {
        acb->aio_iov = qiov->iov;
        acb->aio_niov = qiov->niov;
    }
    acb->aio_nbytes = nb_sectors * 512;
    acb->aio_offset = sector_num * 512;

    acb->next = posix_aio_state->first_aio;
    posix_aio_state->first_aio = acb;

    qemu_paio_submit(acb);
    return &acb->common;
}

BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
        unsigned long int req, void *buf,
        BlockDriverCompletionFunc *cb, void *opaque)
{
    struct qemu_paiocb *acb;

    acb = qemu_aio_get(&raw_aio_pool, bs, cb, opaque);
    if (!acb)
        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;

    acb->next = posix_aio_state->first_aio;
    posix_aio_state->first_aio = acb;

    qemu_paio_submit(acb);
    return &acb->common;
}

int paio_init(void)
{
    sigset_t mask;
    PosixAioState *s;
    int ret;

    if (posix_aio_state)
        return 0;

    s = qemu_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");
        return -1;
    }

    fcntl(s->fd, F_SETFL, O_NONBLOCK);

    qemu_aio_set_fd_handler(s->fd, posix_aio_read, NULL, posix_aio_flush,
        posix_aio_process_queue, s);

    ret = pthread_attr_init(&attr);
    if (ret)
        die2(ret, "pthread_attr_init");

    ret = pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
    if (ret)
        die2(ret, "pthread_attr_setdetachstate");

    QTAILQ_INIT(&request_list);

    posix_aio_state = s;
    return 0;
}