diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/SubmittingPatches | 26 | ||||
| -rw-r--r-- | Documentation/feature-removal-schedule.txt | 24 | ||||
| -rw-r--r-- | Documentation/i2c/upgrading-clients | 281 | ||||
| -rw-r--r-- | Documentation/kdump/kdump.txt | 20 | ||||
| -rw-r--r-- | Documentation/lguest/lguest.c | 519 | ||||
| -rw-r--r-- | Documentation/video4linux/CARDLIST.au0828 | 1 | ||||
| -rw-r--r-- | Documentation/video4linux/CARDLIST.em28xx | 45 | ||||
| -rw-r--r-- | Documentation/video4linux/gspca.txt | 2 |
8 files changed, 771 insertions, 147 deletions
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 118ca6e9404..f79ad9ff603 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -528,7 +528,33 @@ See more details on the proper patch format in the following references. +16) Sending "git pull" requests (from Linus emails) +Please write the git repo address and branch name alone on the same line +so that I can't even by mistake pull from the wrong branch, and so +that a triple-click just selects the whole thing. + +So the proper format is something along the lines of: + + "Please pull from + + git://jdelvare.pck.nerim.net/jdelvare-2.6 i2c-for-linus + + to get these changes:" + +so that I don't have to hunt-and-peck for the address and inevitably +get it wrong (actually, I've only gotten it wrong a few times, and +checking against the diffstat tells me when I get it wrong, but I'm +just a lot more comfortable when I don't have to "look for" the right +thing to pull, and double-check that I have the right branch-name). + + +Please use "git diff -M --stat --summary" to generate the diffstat: +the -M enables rename detection, and the summary enables a summary of +new/deleted or renamed files. + +With rename detection, the statistics are rather different [...] +because git will notice that a fair number of the changes are renames. ----------------------------------- SECTION 2 - HINTS, TIPS, AND TRICKS diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 721c71b86e0..c23955404bf 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -47,6 +47,30 @@ Who: Mauro Carvalho Chehab <mchehab@infradead.org> --------------------------- +What: old tuner-3036 i2c driver +When: 2.6.28 +Why: This driver is for VERY old i2c-over-parallel port teletext receiver + boxes. Rather then spending effort on converting this driver to V4L2, + and since it is extremely unlikely that anyone still uses one of these + devices, it was decided to drop it. +Who: Hans Verkuil <hverkuil@xs4all.nl> + Mauro Carvalho Chehab <mchehab@infradead.org> + + --------------------------- + +What: V4L2 dpc7146 driver +When: 2.6.28 +Why: Old driver for the dpc7146 demonstration board that is no longer + relevant. The last time this was tested on actual hardware was + probably around 2002. Since this is a driver for a demonstration + board the decision was made to remove it rather than spending a + lot of effort continually updating this driver to stay in sync + with the latest internal V4L2 or I2C API. +Who: Hans Verkuil <hverkuil@xs4all.nl> + Mauro Carvalho Chehab <mchehab@infradead.org> + +--------------------------- + What: PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl]) When: November 2005 Files: drivers/pcmcia/: pcmcia_ioctl.c diff --git a/Documentation/i2c/upgrading-clients b/Documentation/i2c/upgrading-clients new file mode 100644 index 00000000000..9a45f9bb6a2 --- /dev/null +++ b/Documentation/i2c/upgrading-clients @@ -0,0 +1,281 @@ +Upgrading I2C Drivers to the new 2.6 Driver Model +================================================= + +Ben Dooks <ben-linux@fluff.org> + +Introduction +------------ + +This guide outlines how to alter existing Linux 2.6 client drivers from +the old to the new new binding methods. + + +Example old-style driver +------------------------ + + +struct example_state { + struct i2c_client client; + .... +}; + +static struct i2c_driver example_driver; + +static unsigned short ignore[] = { I2C_CLIENT_END }; +static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END }; + +I2C_CLIENT_INSMOD; + +static int example_attach(struct i2c_adapter *adap, int addr, int kind) +{ + struct example_state *state; + struct device *dev = &adap->dev; /* to use for dev_ reports */ + int ret; + + state = kzalloc(sizeof(struct example_state), GFP_KERNEL); + if (state == NULL) { + dev_err(dev, "failed to create our state\n"); + return -ENOMEM; + } + + example->client.addr = addr; + example->client.flags = 0; + example->client.adapter = adap; + + i2c_set_clientdata(&state->i2c_client, state); + strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE); + + ret = i2c_attach_client(&state->i2c_client); + if (ret < 0) { + dev_err(dev, "failed to attach client\n"); + kfree(state); + return ret; + } + + dev = &state->i2c_client.dev; + + /* rest of the initialisation goes here. */ + + dev_info(dev, "example client created\n"); + + return 0; +} + +static int __devexit example_detach(struct i2c_client *client) +{ + struct example_state *state = i2c_get_clientdata(client); + + i2c_detach_client(client); + kfree(state); + return 0; +} + +static int example_attach_adapter(struct i2c_adapter *adap) +{ + return i2c_probe(adap, &addr_data, example_attach); +} + +static struct i2c_driver example_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "example", + }, + .attach_adapter = example_attach_adapter, + .detach_client = __devexit_p(example_detach), + .suspend = example_suspend, + .resume = example_resume, +}; + + +Updating the client +------------------- + +The new style binding model will check against a list of supported +devices and their associated address supplied by the code registering +the busses. This means that the driver .attach_adapter and +.detach_adapter methods can be removed, along with the addr_data, +as follows: + +- static struct i2c_driver example_driver; + +- static unsigned short ignore[] = { I2C_CLIENT_END }; +- static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END }; + +- I2C_CLIENT_INSMOD; + +- static int example_attach_adapter(struct i2c_adapter *adap) +- { +- return i2c_probe(adap, &addr_data, example_attach); +- } + + static struct i2c_driver example_driver = { +- .attach_adapter = example_attach_adapter, +- .detach_client = __devexit_p(example_detach), + } + +Add the probe and remove methods to the i2c_driver, as so: + + static struct i2c_driver example_driver = { ++ .probe = example_probe, ++ .remove = __devexit_p(example_remove), + } + +Change the example_attach method to accept the new parameters +which include the i2c_client that it will be working with: + +- static int example_attach(struct i2c_adapter *adap, int addr, int kind) ++ static int example_probe(struct i2c_client *client, ++ const struct i2c_device_id *id) + +Change the name of example_attach to example_probe to align it with the +i2c_driver entry names. The rest of the probe routine will now need to be +changed as the i2c_client has already been setup for use. + +The necessary client fields have already been setup before +the probe function is called, so the following client setup +can be removed: + +- example->client.addr = addr; +- example->client.flags = 0; +- example->client.adapter = adap; +- +- strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE); + +The i2c_set_clientdata is now: + +- i2c_set_clientdata(&state->client, state); ++ i2c_set_clientdata(client, state); + +The call to i2c_attach_client is no longer needed, if the probe +routine exits successfully, then the driver will be automatically +attached by the core. Change the probe routine as so: + +- ret = i2c_attach_client(&state->i2c_client); +- if (ret < 0) { +- dev_err(dev, "failed to attach client\n"); +- kfree(state); +- return ret; +- } + + +Remove the storage of 'struct i2c_client' from the 'struct example_state' +as we are provided with the i2c_client in our example_probe. Instead we +store a pointer to it for when it is needed. + +struct example_state { +- struct i2c_client client; ++ struct i2c_client *client; + +the new i2c client as so: + +- struct device *dev = &adap->dev; /* to use for dev_ reports */ ++ struct device *dev = &i2c_client->dev; /* to use for dev_ reports */ + +And remove the change after our client is attached, as the driver no +longer needs to register a new client structure with the core: + +- dev = &state->i2c_client.dev; + +In the probe routine, ensure that the new state has the client stored +in it: + +static int example_probe(struct i2c_client *i2c_client, + const struct i2c_device_id *id) +{ + struct example_state *state; + struct device *dev = &i2c_client->dev; + int ret; + + state = kzalloc(sizeof(struct example_state), GFP_KERNEL); + if (state == NULL) { + dev_err(dev, "failed to create our state\n"); + return -ENOMEM; + } + ++ state->client = i2c_client; + +Update the detach method, by changing the name to _remove and +to delete the i2c_detach_client call. It is possible that you +can also remove the ret variable as it is not not needed for +any of the core functions. + +- static int __devexit example_detach(struct i2c_client *client) ++ static int __devexit example_remove(struct i2c_client *client) +{ + struct example_state *state = i2c_get_clientdata(client); + +- i2c_detach_client(client); + +And finally ensure that we have the correct ID table for the i2c-core +and other utilities: + ++ struct i2c_device_id example_idtable[] = { ++ { "example", 0 }, ++ { } ++}; ++ ++MODULE_DEVICE_TABLE(i2c, example_idtable); + +static struct i2c_driver example_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "example", + }, ++ .id_table = example_ids, + + +Our driver should now look like this: + +struct example_state { + struct i2c_client *client; + .... +}; + +static int example_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct example_state *state; + struct device *dev = &client->dev; + + state = kzalloc(sizeof(struct example_state), GFP_KERNEL); + if (state == NULL) { + dev_err(dev, "failed to create our state\n"); + return -ENOMEM; + } + + state->client = client; + i2c_set_clientdata(client, state); + + /* rest of the initialisation goes here. */ + + dev_info(dev, "example client created\n"); + + return 0; +} + +static int __devexit example_remove(struct i2c_client *client) +{ + struct example_state *state = i2c_get_clientdata(client); + + kfree(state); + return 0; +} + +static struct i2c_device_id example_idtable[] = { + { "example", 0 }, + { } +}; + +MODULE_DEVICE_TABLE(i2c, example_idtable); + +static struct i2c_driver example_driver = { + .driver = { + .owner = THIS_MODULE, + .name = "example", + }, + .id_table = example_idtable, + .probe = example_probe, + .remove = __devexit_p(example_remove), + .suspend = example_suspend, + .resume = example_resume, +}; diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 9691c7f5166..0705040531a 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -65,26 +65,26 @@ Install kexec-tools 2) Download the kexec-tools user-space package from the following URL: -http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools-testing.tar.gz +http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools.tar.gz -This is a symlink to the latest version, which at the time of writing is -20061214, the only release of kexec-tools-testing so far. As other versions -are released, the older ones will remain available at -http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/ +This is a symlink to the latest version. -Note: Latest kexec-tools-testing git tree is available at +The latest kexec-tools git tree is available at: -git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools-testing.git +git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools.git or -http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools-testing.git;a=summary +http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools.git + +More information about kexec-tools can be found at +http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/README.html 3) Unpack the tarball with the tar command, as follows: - tar xvpzf kexec-tools-testing.tar.gz + tar xvpzf kexec-tools.tar.gz 4) Change to the kexec-tools directory, as follows: - cd kexec-tools-testing-VERSION + cd kexec-tools-VERSION 5) Configure the package, as follows: diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 82fafe0429f..b88b0ea54e9 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -36,11 +36,13 @@ #include <sched.h> #include <limits.h> #include <stddef.h> +#include <signal.h> #include "linux/lguest_launcher.h" #include "linux/virtio_config.h" #include "linux/virtio_net.h" #include "linux/virtio_blk.h" #include "linux/virtio_console.h" +#include "linux/virtio_rng.h" #include "linux/virtio_ring.h" #include "asm-x86/bootparam.h" /*L:110 We can ignore the 39 include files we need for this program, but I do @@ -64,8 +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. */ @@ -74,12 +76,19 @@ 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. */ static unsigned long guest_limit, guest_max; +/* The pipe for signal hander to write to. */ +static int timeoutpipe[2]; +static unsigned int timeout_usec = 500; /* a per-cpu variable indicating whose vcpu is currently running */ static unsigned int __thread cpu_id; @@ -155,11 +164,14 @@ struct virtqueue /* Last available index we saw. */ u16 last_avail_idx; - /* The routine to call when the Guest pings us. */ - void (*handle_output)(int fd, struct virtqueue *me); + /* The routine to call when the Guest pings us, or timeout. */ + void (*handle_output)(int fd, struct virtqueue *me, bool timeout); /* Outstanding buffers */ unsigned int inflight; + + /* Is this blocked awaiting a timer? */ + bool blocked; }; /* Remember the arguments to the program so we can "reboot" */ @@ -190,6 +202,9 @@ static void *_convert(struct iovec *iov, size_t size, size_t align, return iov->iov_base; } +/* Wrapper for the last available index. Makes it easier to change. */ +#define lg_last_avail(vq) ((vq)->last_avail_idx) + /* The virtio configuration space is defined to be little-endian. x86 is * little-endian too, but it's nice to be explicit so we have these helpers. */ #define cpu_to_le16(v16) (v16) @@ -199,6 +214,33 @@ static void *_convert(struct iovec *iov, size_t size, size_t align, #define le32_to_cpu(v32) (v32) #define le64_to_cpu(v64) (v64) +/* Is this iovec empty? */ +static bool iov_empty(const struct iovec iov[], unsigned int num_iov) +{ + unsigned int i; + + for (i = 0; i < num_iov; i++) + if (iov[i].iov_len) + return false; + return true; +} + +/* Take len bytes from the front of this iovec. */ +static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len) +{ + unsigned int i; + + for (i = 0; i < num_iov; i++) { + unsigned int used; + + used = iov[i].iov_len < len ? iov[i].iov_len : len; + iov[i].iov_base += used; + iov[i].iov_len -= used; + len -= used; + } + assert(len == 0); +} + /* The device virtqueue descriptors are followed by feature bitmasks. */ static u8 *get_feature_bits(struct device *dev) { @@ -254,6 +296,7 @@ static void *map_zeroed_pages(unsigned int num) PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0); if (addr == MAP_FAILED) err(1, "Mmaping %u pages of /dev/zero", num); + close(fd); return addr; } @@ -540,69 +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"); - /* Here is the fd used to talk to the waker. */ - return pipefd[1]; + /* Waker also needs to know the lguest fd */ + waker_fds.lguest_fd = lguest_fd; + + if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1) + err(1, "Creating Waker"); } /* @@ -661,19 +699,22 @@ static unsigned get_vq_desc(struct virtqueue *vq, unsigned int *out_num, unsigned int *in_num) { unsigned int i, head; + u16 last_avail; /* Check it isn't doing very strange things with descriptor numbers. */ - if ((u16)(vq->vring.avail->idx - vq->last_avail_idx) > vq->vring.num) + last_avail = lg_last_avail(vq); + if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) errx(1, "Guest moved used index from %u to %u", - vq->last_avail_idx, vq->vring.avail->idx); + last_avail, vq->vring.avail->idx); /* If there's nothing new since last we looked, return invalid. */ - if (vq->vring.avail->idx == vq->last_avail_idx) + if (vq->vring.avail->idx == last_avail) return vq->vring.num; /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ - head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num]; + head = vq->vring.avail->ring[last_avail % vq->vring.num]; + lg_last_avail(vq)++; /* If their number is silly, that's a fatal mistake. */ if (head >= vq->vring.num) @@ -821,8 +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); @@ -839,7 +880,7 @@ static bool handle_console_input(int fd, struct device *dev) /* Handling output for console is simple: we just get all the output buffers * and write them to stdout. */ -static void handle_console_output(int fd, struct virtqueue *vq) +static void handle_console_output(int fd, struct virtqueue *vq, bool timeout) { unsigned int head, out, in; int len; @@ -854,6 +895,21 @@ static void handle_console_output(int fd, struct virtqueue *vq) } } +static void block_vq(struct virtqueue *vq) +{ + struct itimerval itm; + + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + vq->blocked = true; + + itm.it_interval.tv_sec = 0; + itm.it_interval.tv_usec = 0; + itm.it_value.tv_sec = 0; + itm.it_value.tv_usec = timeout_usec; + + setitimer(ITIMER_REAL, &itm, NULL); +} + /* * The Network * @@ -861,22 +917,34 @@ static void handle_console_output(int fd, struct virtqueue *vq) * and write them (ignoring the first element) to this device's file descriptor * (/dev/net/tun). */ -static void handle_net_output(int fd, struct virtqueue *vq) +static void handle_net_output(int fd, struct virtqueue *vq, bool timeout) { - unsigned int head, out, in; + unsigned int head, out, in, num = 0; int len; struct iovec iov[vq->vring.num]; + static int last_timeout_num; /* Keep getting output buffers from the Guest until we run out. */ 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++; + } + + /* Block further kicks and set up a timer if we saw anything. */ + if (!timeout && num) + block_vq(vq); + + if (timeout) { + if (num < last_timeout_num) + timeout_usec += 10; + else if (timeout_usec > 1) + timeout_usec--; + last_timeout_num = num; } } @@ -887,7 +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); @@ -896,25 +963,23 @@ static bool handle_tun_input(int fd, struct device *dev) * early, the Guest won't be ready yet. Wait until the device * status says it's ready. */ /* FIXME: Actually want DRIVER_ACTIVE here. */ - if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK) - warn("network: no dma buffer!"); + + /* Now tell it we want to know if new things appear. */ + dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; + wmb(); + /* We'll turn this back on if input buffers are registered. */ return false; } 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], @@ -927,11 +992,18 @@ static bool handle_tun_input(int fd, struct device *dev) /*L:215 This is the callback attached to the network and console input * virtqueues: it ensures we try again, in case we stopped console or net * delivery because Guest didn't have any buffers. */ -static void enable_fd(int fd, struct virtqueue *vq) +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) +{ + /* We don't need to know again when Guest refills receive buffer. */ + vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; + enable_fd(fd, vq, timeout); } /* When the Guest tells us they updated the status field, we handle it. */ @@ -951,7 +1023,7 @@ static void update_device_status(struct device *dev) for (vq = dev->vq; vq; vq = vq->next) { memset(vq->vring.desc, 0, vring_size(vq->config.num, getpagesize())); - vq->last_avail_idx = 0; + lg_last_avail(vq) = 0; } } else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) { warnx("Device %s configuration FAILED", dev->name); @@ -960,10 +1032,10 @@ static void update_device_status(struct device *dev) verbose("Device %s OK: offered", dev->name); for (i = 0; i < dev->desc->feature_len; i++) - verbose(" %08x", get_feature_bits(dev)[i]); + verbose(" %02x", get_feature_bits(dev)[i]); verbose(", accepted"); for (i = 0; i < dev->desc->feature_len; i++) - verbose(" %08x", get_feature_bits(dev) + verbose(" %02x", get_feature_bits(dev) [dev->desc->feature_len+i]); if (dev->ready) @@ -1000,7 +1072,7 @@ static void handle_output(int fd, unsigned long addr) if (strcmp(vq->dev->name, "console") != 0) verbose("Output to %s\n", vq->dev->name); if (vq->handle_output) - vq->handle_output(fd, vq); + vq->handle_output(fd, vq, false); return; } } @@ -1014,6 +1086,29 @@ static void handle_output(int fd, unsigned long addr) strnlen(from_guest_phys(addr), guest_limit - addr)); } +static void handle_timeout(int fd) +{ + char buf[32]; + struct device *i; + struct virtqueue *vq; + + /* Clear the pipe */ + read(timeoutpipe[0], buf, sizeof(buf)); + + /* Check each device and virtqueue: flush blocked ones. */ + for (i = devices.dev; i; i = i->next) { + for (vq = i->vq; vq; vq = vq->next) { + if (!vq->blocked) + continue; + + vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; + vq->blocked = false; + if (vq->handle_output) + vq->handle_output(fd, vq, true); + } + } +} + /* This is called when the Waker wakes us up: check for incoming file * descriptors. */ static void handle_input(int fd) @@ -1024,16 +1119,20 @@ static void handle_input(int fd) for (;;) { struct device *i; fd_set fds = devices.infds; + int num; + num = select(devices.max_infd+1, &fds, NULL, NULL, &poll); + /* Could get interrupted */ + if (num < 0) + continue; /* If nothing is ready, we're done. */ - if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0) + if (num == 0) break; /* Otherwise, call the device(s) which have readable file * 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; @@ -1043,13 +1142,12 @@ 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)); } } + + /* Is this the timeout fd? */ + if (FD_ISSET(timeoutpipe[0], &fds)) + handle_timeout(fd); } } @@ -1098,7 +1196,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type) /* Each device descriptor is followed by the description of its virtqueues. We * specify how many descriptors the virtqueue is to have. */ static void add_virtqueue(struct device *dev, unsigned int num_descs, - void (*handle_output)(int fd, struct virtqueue *me)) + void (*handle_output)(int, struct virtqueue *, bool)) { unsigned int pages; struct virtqueue **i, *vq = malloc(sizeof(*vq)); @@ -1114,6 +1212,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, vq->last_avail_idx = 0; vq->dev = dev; vq->inflight = 0; + vq->blocked = false; /* Initialize the configuration. */ vq->config.num = num_descs; @@ -1246,6 +1345,24 @@ static void setup_console(void) } /*:*/ +static void timeout_alarm(int sig) +{ + write(timeoutpipe[1], "", 1); +} + +static void setup_timeout(void) +{ + if (pipe(timeoutpipe) != 0) + err(1, "Creating timeout pipe"); + + if (fcntl(timeoutpipe[1], F_SETFL, + fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0) + err(1, "Making timeout pipe nonblocking"); + + add_device_fd(timeoutpipe[0]); + signal(SIGALRM, timeout_alarm); +} + /*M:010 Inter-guest networking is an interesting area. Simplest is to have a * --sharenet=<name> option which opens or creates a named pipe. This can be * used to send packets to another guest in a 1:1 manner. @@ -1264,10 +1381,25 @@ static void setup_console(void) static u32 str2ip(const char *ipaddr) { - unsigned int byte[4]; + unsigned int b[4]; - sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]); - return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3]; + if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4) + errx(1, "Failed to parse IP address '%s'", ipaddr); + return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]; +} + +static void str2mac(const char *macaddr, unsigned char mac[6]) +{ + unsigned int m[6]; + if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x", + &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6) + errx(1, "Failed to parse mac address '%s'", macaddr); + mac[0] = m[0]; + mac[1] = m[1]; + mac[2] = m[2]; + mac[3] = m[3]; + mac[4] = m[4]; + mac[5] = m[5]; } /* This code is "adapted" from libbridge: it attaches the Host end of the @@ -1288,6 +1420,7 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name) errx(1, "interface %s does not exist!", if_name); strncpy(ifr.ifr_name, br_name, IFNAMSIZ); + ifr.ifr_name[IFNAMSIZ-1] = '\0'; ifr.ifr_ifindex = ifidx; if (ioctl(fd, SIOCBRADDIF, &ifr) < 0) err(1, "can't add %s to bridge %s", if_name, br_name); @@ -1296,64 +1429,90 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name) /* This sets up the Host end of the network device with an IP address, brings * it up so packets will flow, the copies the MAC address into the hwaddr * pointer. */ -static void configure_device(int fd, const char *devname, u32 ipaddr, - unsigned char hwaddr[6]) +static void configure_device(int fd, const char *tapif, u32 ipaddr) { struct ifreq ifr; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr; - /* Don't read these incantations. Just cut & paste them like I did! */ memset(&ifr, 0, sizeof(ifr)); - strcpy(ifr.ifr_name, devname); + strcpy(ifr.ifr_name, tapif); + + /* Don't read these incantations. Just cut & paste them like I did! */ sin->sin_family = AF_INET; sin->sin_addr.s_addr = htonl(ipaddr); if (ioctl(fd, SIOCSIFADDR, &ifr) != 0) - err(1, "Setting %s interface address", devname); + err(1, "Setting %s interface address", tapif); ifr.ifr_flags = IFF_UP; if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0) - err(1, "Bringing interface %s up", devname); + err(1, "Bringing interface %s up", tapif); +} + +static void get_mac(int fd, const char *tapif, unsigned char hwaddr[6]) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + strcpy(ifr.ifr_name, tapif); /* SIOC stands for Socket I/O Control. G means Get (vs S for Set * above). IF means Interface, and HWADDR is hardware address. * Simple! */ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0) - err(1, "getting hw address for %s", devname); + err(1, "getting hw address for %s", tapif); memcpy(hwaddr, ifr.if |