view src/os/unix/ngx_writev_chain.c @ 8018:5119c8150478

Fixed runtime handling of systems without EPOLLRDHUP support. In 7583:efd71d49bde0 (nginx 1.17.5) along with introduction of the ioctl(FIONREAD) support proper handling of systems without EPOLLRDHUP support in the kernel (but with EPOLLRDHUP in headers) was broken. Before the change, rev->available was never set to 0 unless ngx_use_epoll_rdhup was also set (that is, runtime test for EPOLLRDHUP introduced in 6536:f7849bfb6d21 succeeded). After the change, rev->available might reach 0 on systems without runtime EPOLLRDHUP support, stopping further reading in ngx_readv_chain() and ngx_unix_recv(). And, if EOF happened to be already reported along with the last event, it is not reported again by epoll_wait(), leading to connection hangs and timeouts on such systems. This affects Linux kernels before 2.6.17 if nginx was compiled with newer headers, and, more importantly, emulation layers, such as DigitalOcean's App Platform's / gVisor's epoll emulation layer. Fix is to explicitly check ngx_use_epoll_rdhup before the corresponding rev->pending_eof tests in ngx_readv_chain() and ngx_unix_recv().
author Marcus Ball <marcus.ball@live.com>
date Mon, 30 May 2022 02:38:07 +0300
parents 2c64b69daec5
children
line wrap: on
line source


/*
 * Copyright (C) Igor Sysoev
 * Copyright (C) Nginx, Inc.
 */


#include <ngx_config.h>
#include <ngx_core.h>
#include <ngx_event.h>


ngx_chain_t *
ngx_writev_chain(ngx_connection_t *c, ngx_chain_t *in, off_t limit)
{
    ssize_t        n, sent;
    off_t          send, prev_send;
    ngx_chain_t   *cl;
    ngx_event_t   *wev;
    ngx_iovec_t    vec;
    struct iovec   iovs[NGX_IOVS_PREALLOCATE];

    wev = c->write;

    if (!wev->ready) {
        return in;
    }

#if (NGX_HAVE_KQUEUE)

    if ((ngx_event_flags & NGX_USE_KQUEUE_EVENT) && wev->pending_eof) {
        (void) ngx_connection_error(c, wev->kq_errno,
                               "kevent() reported about an closed connection");
        wev->error = 1;
        return NGX_CHAIN_ERROR;
    }

#endif

    /* the maximum limit size is the maximum size_t value - the page size */

    if (limit == 0 || limit > (off_t) (NGX_MAX_SIZE_T_VALUE - ngx_pagesize)) {
        limit = NGX_MAX_SIZE_T_VALUE - ngx_pagesize;
    }

    send = 0;

    vec.iovs = iovs;
    vec.nalloc = NGX_IOVS_PREALLOCATE;

    for ( ;; ) {
        prev_send = send;

        /* create the iovec and coalesce the neighbouring bufs */

        cl = ngx_output_chain_to_iovec(&vec, in, limit - send, c->log);

        if (cl == NGX_CHAIN_ERROR) {
            return NGX_CHAIN_ERROR;
        }

        if (cl && cl->buf->in_file) {
            ngx_log_error(NGX_LOG_ALERT, c->log, 0,
                          "file buf in writev "
                          "t:%d r:%d f:%d %p %p-%p %p %O-%O",
                          cl->buf->temporary,
                          cl->buf->recycled,
                          cl->buf->in_file,
                          cl->buf->start,
                          cl->buf->pos,
                          cl->buf->last,
                          cl->buf->file,
                          cl->buf->file_pos,
                          cl->buf->file_last);

            ngx_debug_point();

            return NGX_CHAIN_ERROR;
        }

        send += vec.size;

        n = ngx_writev(c, &vec);

        if (n == NGX_ERROR) {
            return NGX_CHAIN_ERROR;
        }

        sent = (n == NGX_AGAIN) ? 0 : n;

        c->sent += sent;

        in = ngx_chain_update_sent(in, sent);

        if (send - prev_send != sent) {
            wev->ready = 0;
            return in;
        }

        if (send >= limit || in == NULL) {
            return in;
        }
    }
}


ngx_chain_t *
ngx_output_chain_to_iovec(ngx_iovec_t *vec, ngx_chain_t *in, size_t limit,
    ngx_log_t *log)
{
    size_t         total, size;
    u_char        *prev;
    ngx_uint_t     n;
    struct iovec  *iov;

    iov = NULL;
    prev = NULL;
    total = 0;
    n = 0;

    for ( /* void */ ; in && total < limit; in = in->next) {

        if (ngx_buf_special(in->buf)) {
            continue;
        }

        if (in->buf->in_file) {
            break;
        }

        if (!ngx_buf_in_memory(in->buf)) {
            ngx_log_error(NGX_LOG_ALERT, log, 0,
                          "bad buf in output chain "
                          "t:%d r:%d f:%d %p %p-%p %p %O-%O",
                          in->buf->temporary,
                          in->buf->recycled,
                          in->buf->in_file,
                          in->buf->start,
                          in->buf->pos,
                          in->buf->last,
                          in->buf->file,
                          in->buf->file_pos,
                          in->buf->file_last);

            ngx_debug_point();

            return NGX_CHAIN_ERROR;
        }

        size = in->buf->last - in->buf->pos;

        if (size > limit - total) {
            size = limit - total;
        }

        if (prev == in->buf->pos) {
            iov->iov_len += size;

        } else {
            if (n == vec->nalloc) {
                break;
            }

            iov = &vec->iovs[n++];

            iov->iov_base = (void *) in->buf->pos;
            iov->iov_len = size;
        }

        prev = in->buf->pos + size;
        total += size;
    }

    vec->count = n;
    vec->size = total;

    return in;
}


ssize_t
ngx_writev(ngx_connection_t *c, ngx_iovec_t *vec)
{
    ssize_t    n;
    ngx_err_t  err;

eintr:

    n = writev(c->fd, vec->iovs, vec->count);

    ngx_log_debug2(NGX_LOG_DEBUG_EVENT, c->log, 0,
                   "writev: %z of %uz", n, vec->size);

    if (n == -1) {
        err = ngx_errno;

        switch (err) {
        case NGX_EAGAIN:
            ngx_log_debug0(NGX_LOG_DEBUG_EVENT, c->log, err,
                           "writev() not ready");
            return NGX_AGAIN;

        case NGX_EINTR:
            ngx_log_debug0(NGX_LOG_DEBUG_EVENT, c->log, err,
                           "writev() was interrupted");
            goto eintr;

        default:
            c->write->error = 1;
            ngx_connection_error(c, err, "writev() failed");
            return NGX_ERROR;
        }
    }

    return n;
}