X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=Documentation%2Flguest%2Flguest.c;h=b88b0ea54e90c597896aac6eb478e1b56bab8bd0;hb=8c79873da0d2bedf4ad6b868c54e426bb0a2fe38;hp=0d1b0265d8e213478ce5262eb22cadd3fe624afa;hpb=9254926f85466979ef5f0e16386c294bf0973a90;p=linux-2.6-omap-h63xx.git diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 0d1b0265d8e..b88b0ea54e9 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -66,8 +66,8 @@ typedef uint8_t u8; #endif /* We can have up to 256 pages for devices. */ #define DEVICE_PAGES 256 -/* This will occupy 2 pages: it must be a power of 2. */ -#define VIRTQUEUE_NUM 128 +/* This will occupy 3 pages: it must be a power of 2. */ +#define VIRTQUEUE_NUM 256 /*L:120 verbose is both a global flag and a macro. The C preprocessor allows * this, and although I wouldn't recommend it, it works quite nicely here. */ @@ -76,8 +76,12 @@ static bool verbose; do { if (verbose) printf(args); } while(0) /*:*/ -/* The pipe to send commands to the waker process */ -static int waker_fd; +/* File descriptors for the Waker. */ +struct { + int pipe[2]; + int lguest_fd; +} waker_fds; + /* The pointer to the start of guest memory. */ static void *guest_base; /* The maximum guest physical address allowed, and maximum possible. */ @@ -579,69 +583,64 @@ static void add_device_fd(int fd) * watch, but handing a file descriptor mask through to the kernel is fairly * icky. * - * Instead, we fork off a process which watches the file descriptors and writes + * Instead, we clone off a thread which watches the file descriptors and writes * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host * stop running the Guest. This causes the Launcher to return from the * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset * the LHREQ_BREAK and wake us up again. * * This, of course, is merely a different *kind* of icky. + * + * Given my well-known antipathy to threads, I'd prefer to use processes. But + * it's easier to share Guest memory with threads, and trivial to share the + * devices.infds as the Launcher changes it. */ -static void wake_parent(int pipefd, int lguest_fd) +static int waker(void *unused) { - /* Add the pipe from the Launcher to the fdset in the device_list, so - * we watch it, too. */ - add_device_fd(pipefd); + /* Close the write end of the pipe: only the Launcher has it open. */ + close(waker_fds.pipe[1]); for (;;) { fd_set rfds = devices.infds; unsigned long args[] = { LHREQ_BREAK, 1 }; + unsigned int maxfd = devices.max_infd; + + /* We also listen to the pipe from the Launcher. */ + FD_SET(waker_fds.pipe[0], &rfds); + if (waker_fds.pipe[0] > maxfd) + maxfd = waker_fds.pipe[0]; /* Wait until input is ready from one of the devices. */ - select(devices.max_infd+1, &rfds, NULL, NULL, NULL); - /* Is it a message from the Launcher? */ - if (FD_ISSET(pipefd, &rfds)) { - int fd; - /* If read() returns 0, it means the Launcher has - * exited. We silently follow. */ - if (read(pipefd, &fd, sizeof(fd)) == 0) - exit(0); - /* Otherwise it's telling us to change what file - * descriptors we're to listen to. Positive means - * listen to a new one, negative means stop - * listening. */ - if (fd >= 0) - FD_SET(fd, &devices.infds); - else - FD_CLR(-fd - 1, &devices.infds); - } else /* Send LHREQ_BREAK command. */ - pwrite(lguest_fd, args, sizeof(args), cpu_id); + select(maxfd+1, &rfds, NULL, NULL, NULL); + + /* Message from Launcher? */ + if (FD_ISSET(waker_fds.pipe[0], &rfds)) { + char c; + /* If this fails, then assume Launcher has exited. + * Don't do anything on exit: we're just a thread! */ + if (read(waker_fds.pipe[0], &c, 1) != 1) + _exit(0); + continue; + } + + /* Send LHREQ_BREAK command to snap the Launcher out of it. */ + pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id); } + return 0; } /* This routine just sets up a pipe to the Waker process. */ -static int setup_waker(int lguest_fd) -{ - int pipefd[2], child; - - /* We create a pipe to talk to the Waker, and also so it knows when the - * Launcher dies (and closes pipe). */ - pipe(pipefd); - child = fork(); - if (child == -1) - err(1, "forking"); - - if (child == 0) { - /* We are the Waker: close the "writing" end of our copy of the - * pipe and start waiting for input. */ - close(pipefd[1]); - wake_parent(pipefd[0], lguest_fd); - } - /* Close the reading end of our copy of the pipe. */ - close(pipefd[0]); +static void setup_waker(int lguest_fd) +{ + /* This pipe is closed when Launcher dies, telling Waker. */ + if (pipe(waker_fds.pipe) != 0) + err(1, "Creating pipe for Waker"); + + /* Waker also needs to know the lguest fd */ + waker_fds.lguest_fd = lguest_fd; - /* Here is the fd used to talk to the waker. */ - return pipefd[1]; + if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1) + err(1, "Creating Waker"); } /* @@ -863,8 +862,8 @@ static bool handle_console_input(int fd, struct device *dev) unsigned long args[] = { LHREQ_BREAK, 0 }; /* Close the fd so Waker will know it has to * exit. */ - close(waker_fd); - /* Just in case waker is blocked in BREAK, send + close(waker_fds.pipe[1]); + /* Just in case Waker is blocked in BREAK, send * unbreak now. */ write(fd, args, sizeof(args)); exit(2); @@ -929,11 +928,9 @@ static void handle_net_output(int fd, struct virtqueue *vq, bool timeout) while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) { if (in) errx(1, "Input buffers in output queue?"); - /* Check header, but otherwise ignore it (we told the Guest we - * supported no features, so it shouldn't have anything - * interesting). */ - (void)convert(&iov[0], struct virtio_net_hdr); - len = writev(vq->dev->fd, iov+1, out-1); + len = writev(vq->dev->fd, iov, out); + if (len < 0) + err(1, "Writing network packet to tun"); add_used_and_trigger(fd, vq, head, len); num++; } @@ -958,7 +955,6 @@ static bool handle_tun_input(int fd, struct device *dev) unsigned int head, in_num, out_num; int len; struct iovec iov[dev->vq->vring.num]; - struct virtio_net_hdr *hdr; /* First we need a network buffer from the Guests's recv virtqueue. */ head = get_vq_desc(dev->vq, iov, &out_num, &in_num); @@ -977,18 +973,13 @@ static bool handle_tun_input(int fd, struct device *dev) } else if (out_num) errx(1, "Output buffers in network recv queue?"); - /* First element is the header: we set it to 0 (no features). */ - hdr = convert(&iov[0], struct virtio_net_hdr); - hdr->flags = 0; - hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; - /* Read the packet from the device directly into the Guest's buffer. */ - len = readv(dev->fd, iov+1, in_num-1); + len = readv(dev->fd, iov, in_num); if (len <= 0) err(1, "reading network"); /* Tell the Guest about the new packet. */ - add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len); + add_used_and_trigger(fd, dev->vq, head, len); verbose("tun input packet len %i [%02x %02x] (%s)\n", len, ((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1], @@ -1004,8 +995,8 @@ static bool handle_tun_input(int fd, struct device *dev) static void enable_fd(int fd, struct virtqueue *vq, bool timeout) { add_device_fd(vq->dev->fd); - /* Tell waker to listen to it again */ - write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd)); + /* Snap the Waker out of its select loop. */ + write(waker_fds.pipe[1], "", 1); } static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout) @@ -1142,7 +1133,6 @@ static void handle_input(int fd) * descriptors and a method of handling them. */ for (i = devices.dev; i; i = i->next) { if (i->handle_input && FD_ISSET(i->fd, &fds)) { - int dev_fd; if (i->handle_input(fd, i)) continue; @@ -1152,11 +1142,6 @@ static void handle_input(int fd) * buffers to deliver into. Console also uses * it when it discovers that stdin is closed. */ FD_CLR(i->fd, &devices.infds); - /* Tell waker to ignore it too, by sending a - * negative fd number (-1, since 0 is a valid - * FD number). */ - dev_fd = -i->fd - 1; - write(waker_fd, &dev_fd, sizeof(dev_fd)); } } @@ -1490,11 +1475,15 @@ static int get_tun_device(char tapif[IFNAMSIZ]) * the truth, I completely blundered my way through this code, but it * works now! */ netfd = open_or_die("/dev/net/tun", O_RDWR); - ifr.ifr_flags = IFF_TAP | IFF_NO_PI; + ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; strcpy(ifr.ifr_name, "tap%d"); if (ioctl(netfd, TUNSETIFF, &ifr) != 0) err(1, "configuring /dev/net/tun"); + if (ioctl(netfd, TUNSETOFFLOAD, + TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) + err(1, "Could not set features for tun device"); + /* We don't need checksums calculated for packets coming in this * device: trust us! */ ioctl(netfd, TUNSETNOCSUM, 1); @@ -1561,6 +1550,16 @@ static void setup_tun_net(char *arg) /* Tell Guest what MAC address to use. */ add_feature(dev, VIRTIO_NET_F_MAC); add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY); + /* Expect Guest to handle everything except UFO */ + add_feature(dev, VIRTIO_NET_F_CSUM); + add_feature(dev, VIRTIO_NET_F_GUEST_CSUM); + add_feature(dev, VIRTIO_NET_F_MAC); + add_feature(dev, VIRTIO_NET_F_GUEST_TSO4); + add_feature(dev, VIRTIO_NET_F_GUEST_TSO6); + add_feature(dev, VIRTIO_NET_F_GUEST_ECN); + add_feature(dev, VIRTIO_NET_F_HOST_TSO4); + add_feature(dev, VIRTIO_NET_F_HOST_TSO6); + add_feature(dev, VIRTIO_NET_F_HOST_ECN); set_config(dev, sizeof(conf), &conf); /* We don't need the socket any more; setup is done. */ @@ -1874,11 +1873,12 @@ static void __attribute__((noreturn)) restart_guest(void) { unsigned int i; - /* Closing pipes causes the Waker thread and io_threads to die, and - * closing /dev/lguest cleans up the Guest. Since we don't track all - * open fds, we simply close everything beyond stderr. */ + /* Since we don't track all open fds, we simply close everything beyond + * stderr. */ for (i = 3; i < FD_SETSIZE; i++) close(i); + + /* The exec automatically gets rid of the I/O and Waker threads. */ execv(main_args[0], main_args); err(1, "Could not exec %s", main_args[0]); } @@ -2079,10 +2079,10 @@ int main(int argc, char *argv[]) * /dev/lguest file descriptor. */ lguest_fd = tell_kernel(pgdir, start); - /* We fork off a child process, which wakes the Launcher whenever one - * of the input file descriptors needs attention. We call this the - * Waker, and we'll cover it in a moment. */ - waker_fd = setup_waker(lguest_fd); + /* We clone off a thread, which wakes the Launcher whenever one of the + * input file descriptors needs attention. We call this the Waker, and + * we'll cover it in a moment. */ + setup_waker(lguest_fd); /* Finally, run the Guest. This doesn't return. */ run_guest(lguest_fd);