linux/net/9p/trans_virtio.c

777 lines
19 KiB
C
Raw Normal View History

/*
* The Virtio 9p transport driver
*
* This is a block based transport driver based on the lguest block driver
* code.
*
* Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
*
* Based on virtio console driver
* Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to:
* Free Software Foundation
* 51 Franklin Street, Fifth Floor
* Boston, MA 02111-1301 USA
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/ipv6.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/un.h>
#include <linux/uaccess.h>
#include <linux/inet.h>
#include <linux/idr.h>
#include <linux/file.h>
#include <linux/highmem.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <net/9p/9p.h>
#include <linux/parser.h>
#include <net/9p/client.h>
#include <net/9p/transport.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/virtio.h>
#include <linux/virtio_9p.h>
#include "trans_common.h"
#define VIRTQUEUE_NUM 128
/* a single mutex to manage channel initialization and attachment */
static DEFINE_MUTEX(virtio_9p_lock);
static DECLARE_WAIT_QUEUE_HEAD(vp_wq);
static atomic_t vp_pinned = ATOMIC_INIT(0);
/**
* struct virtio_chan - per-instance transport information
* @initialized: whether the channel is initialized
* @inuse: whether the channel is in use
* @lock: protects multiple elements within this structure
* @client: client instance
* @vdev: virtio dev associated with this channel
* @vq: virtio queue associated with this channel
* @sg: scatter gather list which is used to pack a request (protected?)
*
* We keep all per-channel information in a structure.
* This structure is allocated within the devices dev->mem space.
* A pointer to the structure will get put in the transport private.
*
*/
struct virtio_chan {
bool inuse;
spinlock_t lock;
struct p9_client *client;
struct virtio_device *vdev;
struct virtqueue *vq;
int ring_bufs_avail;
wait_queue_head_t *vc_wq;
/* This is global limit. Since we don't have a global structure,
* will be placing it in each channel.
*/
unsigned long p9_max_pages;
/* Scatterlist: can be too big for stack. */
struct scatterlist sg[VIRTQUEUE_NUM];
int tag_len;
/*
* tag name to identify a mount Non-null terminated
*/
char *tag;
struct list_head chan_list;
};
static struct list_head virtio_chan_list;
/* How many bytes left in this page. */
static unsigned int rest_of_page(void *data)
{
return PAGE_SIZE - ((unsigned long)data % PAGE_SIZE);
}
/**
* p9_virtio_close - reclaim resources of a channel
* @client: client instance
*
* This reclaims a channel by freeing its resources and
* reseting its inuse flag.
*
*/
static void p9_virtio_close(struct p9_client *client)
{
struct virtio_chan *chan = client->trans;
mutex_lock(&virtio_9p_lock);
if (chan)
chan->inuse = false;
mutex_unlock(&virtio_9p_lock);
}
/**
* req_done - callback which signals activity from the server
* @vq: virtio queue activity was received on
*
* This notifies us that the server has triggered some activity
* on the virtio channel - most likely a response to request we
* sent. Figure out which requests now have responses and wake up
* those threads.
*
* Bugs: could do with some additional sanity checking, but appears to work.
*
*/
static void req_done(struct virtqueue *vq)
{
struct virtio_chan *chan = vq->vdev->priv;
struct p9_fcall *rc;
unsigned int len;
struct p9_req_t *req;
unsigned long flags;
p9_debug(P9_DEBUG_TRANS, ": request done\n");
while (1) {
spin_lock_irqsave(&chan->lock, flags);
rc = virtqueue_get_buf(chan->vq, &len);
if (rc == NULL) {
spin_unlock_irqrestore(&chan->lock, flags);
break;
}
chan->ring_bufs_avail = 1;
spin_unlock_irqrestore(&chan->lock, flags);
/* Wakeup if anyone waiting for VirtIO ring space. */
wake_up(chan->vc_wq);
p9_debug(P9_DEBUG_TRANS, ": rc %p\n", rc);
p9_debug(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
req = p9_tag_lookup(chan->client, rc->tag);
p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
}
}
/**
* pack_sg_list - pack a scatter gather list from a linear buffer
* @sg: scatter/gather list to pack into
* @start: which segment of the sg_list to start at
* @limit: maximum segment to pack data to
* @data: data to pack into scatter/gather list
* @count: amount of data to pack into the scatter/gather list
*
* sg_lists have multiple segments of various sizes. This will pack
* arbitrary data into an existing scatter gather list, segmenting the
* data as necessary within constraints.
*
*/
static int pack_sg_list(struct scatterlist *sg, int start,
int limit, char *data, int count)
{
int s;
int index = start;
while (count) {
s = rest_of_page(data);
if (s > count)
s = count;
BUG_ON(index > limit);
/* Make sure we don't terminate early. */
sg_unmark_end(&sg[index]);
sg_set_buf(&sg[index++], data, s);
count -= s;
data += s;
}
if (index-start)
sg_mark_end(&sg[index - 1]);
return index-start;
}
/* We don't currently allow canceling of virtio requests */
static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
{
return 1;
}
/**
* pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
* this takes a list of pages.
* @sg: scatter/gather list to pack into
* @start: which segment of the sg_list to start at
* @pdata: a list of pages to add into sg.
* @nr_pages: number of pages to pack into the scatter/gather list
* @offs: amount of data in the beginning of first page _not_ to pack
* @count: amount of data to pack into the scatter/gather list
*/
static int
pack_sg_list_p(struct scatterlist *sg, int start, int limit,
struct page **pdata, int nr_pages, size_t offs, int count)
{
int i = 0, s;
int data_off = offs;
int index = start;
BUG_ON(nr_pages > (limit - start));
/*
* if the first page doesn't start at
* page boundary find the offset
*/
while (nr_pages) {
s = PAGE_SIZE - data_off;
if (s > count)
s = count;
/* Make sure we don't terminate early. */
sg_unmark_end(&sg[index]);
sg_set_page(&sg[index++], pdata[i++], s, data_off);
data_off = 0;
count -= s;
nr_pages--;
}
if (index-start)
sg_mark_end(&sg[index - 1]);
return index - start;
}
/**
* p9_virtio_request - issue a request
* @client: client instance issuing the request
* @req: request to be issued
*
*/
static int
p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
{
int err;
int in, out, out_sgs, in_sgs;
unsigned long flags;
struct virtio_chan *chan = client->trans;
struct scatterlist *sgs[2];
p9_debug(P9_DEBUG_TRANS, "9p debug: virtio request\n");
req->status = REQ_STATUS_SENT;
req_retry:
spin_lock_irqsave(&chan->lock, flags);
out_sgs = in_sgs = 0;
/* Handle out VirtIO ring buffers */
out = pack_sg_list(chan->sg, 0,
VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
if (out)
sgs[out_sgs++] = chan->sg;
in = pack_sg_list(chan->sg, out,
VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
if (in)
sgs[out_sgs + in_sgs++] = chan->sg + out;
err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
GFP_ATOMIC);
if (err < 0) {
if (err == -ENOSPC) {
chan->ring_bufs_avail = 0;
spin_unlock_irqrestore(&chan->lock, flags);
err = wait_event_interruptible(*chan->vc_wq,
chan->ring_bufs_avail);
if (err == -ERESTARTSYS)
return err;
p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
goto req_retry;
} else {
spin_unlock_irqrestore(&chan->lock, flags);
p9_debug(P9_DEBUG_TRANS,
"virtio rpc add_sgs returned failure\n");
return -EIO;
}
}
virtqueue_kick(chan->vq);
spin_unlock_irqrestore(&chan->lock, flags);
p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
return 0;
}
static int p9_get_mapped_pages(struct virtio_chan *chan,
struct page ***pages,
struct iov_iter *data,
int count,
size_t *offs,
int *need_drop)
{
int nr_pages;
int err;
if (!iov_iter_count(data))
return 0;
if (!(data->type & ITER_KVEC)) {
int n;
/*
* We allow only p9_max_pages pinned. We wait for the
* Other zc request to finish here
*/
if (atomic_read(&vp_pinned) >= chan->p9_max_pages) {
err = wait_event_interruptible(vp_wq,
(atomic_read(&vp_pinned) < chan->p9_max_pages));
if (err == -ERESTARTSYS)
return err;
}
n = iov_iter_get_pages_alloc(data, pages, count, offs);
if (n < 0)
return n;
*need_drop = 1;
nr_pages = DIV_ROUND_UP(n + *offs, PAGE_SIZE);
atomic_add(nr_pages, &vp_pinned);
return n;
} else {
/* kernel buffer, no need to pin pages */
int index;
size_t len;
void *p;
/* we'd already checked that it's non-empty */
while (1) {
len = iov_iter_single_seg_count(data);
if (likely(len)) {
p = data->kvec->iov_base + data->iov_offset;
break;
}
iov_iter_advance(data, 0);
}
if (len > count)
len = count;
nr_pages = DIV_ROUND_UP((unsigned long)p + len, PAGE_SIZE) -
(unsigned long)p / PAGE_SIZE;
*pages = kmalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
if (!*pages)
return -ENOMEM;
*need_drop = 0;
p -= (*offs = (unsigned long)p % PAGE_SIZE);
for (index = 0; index < nr_pages; index++) {
if (is_vmalloc_addr(p))
(*pages)[index] = vmalloc_to_page(p);
9p/trans_virtio.c: Fix broken zero-copy on vmalloc() buffers The 9p-virtio transport does zero copy on things larger than 1024 bytes in size. It accomplishes this by returning the physical addresses of pages to the virtio-pci device. At present, the translation is usually a bit shift. That approach produces an invalid page address when we read/write to vmalloc buffers, such as those used for Linux kernel modules. Any attempt to load a Linux kernel module from 9p-virtio produces the following stack. [<ffffffff814878ce>] p9_virtio_zc_request+0x45e/0x510 [<ffffffff814814ed>] p9_client_zc_rpc.constprop.16+0xfd/0x4f0 [<ffffffff814839dd>] p9_client_read+0x15d/0x240 [<ffffffff811c8440>] v9fs_fid_readn+0x50/0xa0 [<ffffffff811c84a0>] v9fs_file_readn+0x10/0x20 [<ffffffff811c84e7>] v9fs_file_read+0x37/0x70 [<ffffffff8114e3fb>] vfs_read+0x9b/0x160 [<ffffffff81153571>] kernel_read+0x41/0x60 [<ffffffff810c83ab>] copy_module_from_fd.isra.34+0xfb/0x180 Subsequently, QEMU will die printing: qemu-system-x86_64: virtio: trying to map MMIO memory This patch enables 9p-virtio to correctly handle this case. This not only enables us to load Linux kernel modules off virtfs, but also enables ZFS file-based vdevs on virtfs to be used without killing QEMU. Special thanks to both Avi Kivity and Alexander Graf for their interpretation of QEMU backtraces. Without their guidence, tracking down this bug would have taken much longer. Also, special thanks to Linus Torvalds for his insightful explanation of why this should use is_vmalloc_addr() instead of is_vmalloc_or_module_addr(): https://lkml.org/lkml/2014/2/8/272 Signed-off-by: Richard Yao <ryao@gentoo.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-02-09 00:32:01 +00:00
else
(*pages)[index] = kmap_to_page(p);
p += PAGE_SIZE;
}
return len;
}
}
/**
* p9_virtio_zc_request - issue a zero copy request
* @client: client instance issuing the request
* @req: request to be issued
* @uidata: user bffer that should be ued for zero copy read
* @uodata: user buffer that shoud be user for zero copy write
* @inlen: read buffer size
* @olen: write buffer size
* @hdrlen: reader header size, This is the size of response protocol data
*
*/
static int
p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct iov_iter *uidata, struct iov_iter *uodata,
int inlen, int outlen, int in_hdr_len)
{
int in, out, err, out_sgs, in_sgs;
unsigned long flags;
int in_nr_pages = 0, out_nr_pages = 0;
struct page **in_pages = NULL, **out_pages = NULL;
struct virtio_chan *chan = client->trans;
struct scatterlist *sgs[4];
size_t offs;
int need_drop = 0;
p9_debug(P9_DEBUG_TRANS, "virtio request\n");
if (uodata) {
int n = p9_get_mapped_pages(chan, &out_pages, uodata,
outlen, &offs, &need_drop);
if (n < 0)
return n;
out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != outlen) {
__le32 v = cpu_to_le32(n);
memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
outlen = n;
}
} else if (uidata) {
int n = p9_get_mapped_pages(chan, &in_pages, uidata,
inlen, &offs, &need_drop);
if (n < 0)
return n;
in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != inlen) {
__le32 v = cpu_to_le32(n);
memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
inlen = n;
}
}
req->status = REQ_STATUS_SENT;
req_retry_pinned:
spin_lock_irqsave(&chan->lock, flags);
out_sgs = in_sgs = 0;
/* out data */
out = pack_sg_list(chan->sg, 0,
VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
if (out)
sgs[out_sgs++] = chan->sg;
if (out_pages) {
sgs[out_sgs++] = chan->sg + out;
out += pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
out_pages, out_nr_pages, offs, outlen);
}
/*
* Take care of in data
* For example TREAD have 11.
* 11 is the read/write header = PDU Header(7) + IO Size (4).
* Arrange in such a way that server places header in the
* alloced memory and payload onto the user buffer.
*/
in = pack_sg_list(chan->sg, out,
VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
if (in)
sgs[out_sgs + in_sgs++] = chan->sg + out;
if (in_pages) {
sgs[out_sgs + in_sgs++] = chan->sg + out + in;
in += pack_sg_list_p(chan->sg, out + in, VIRTQUEUE_NUM,
in_pages, in_nr_pages, offs, inlen);
}
BUG_ON(out_sgs + in_sgs > ARRAY_SIZE(sgs));
err = virtqueue_add_sgs(chan->vq, sgs, out_sgs, in_sgs, req->tc,
GFP_ATOMIC);
if (err < 0) {
if (err == -ENOSPC) {
chan->ring_bufs_avail = 0;
spin_unlock_irqrestore(&chan->lock, flags);
err = wait_event_interruptible(*chan->vc_wq,
chan->ring_bufs_avail);
if (err == -ERESTARTSYS)
goto err_out;
p9_debug(P9_DEBUG_TRANS, "Retry virtio request\n");
goto req_retry_pinned;
} else {
spin_unlock_irqrestore(&chan->lock, flags);
p9_debug(P9_DEBUG_TRANS,
"virtio rpc add_sgs returned failure\n");
err = -EIO;
goto err_out;
}
}
virtqueue_kick(chan->vq);
spin_unlock_irqrestore(&chan->lock, flags);
p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
err = wait_event_interruptible(*req->wq,
req->status >= REQ_STATUS_RCVD);
/*
* Non kernel buffers are pinned, unpin them
*/
err_out:
if (need_drop) {
if (in_pages) {
p9_release_pages(in_pages, in_nr_pages);
atomic_sub(in_nr_pages, &vp_pinned);
}
if (out_pages) {
p9_release_pages(out_pages, out_nr_pages);
atomic_sub(out_nr_pages, &vp_pinned);
}
/* wakeup anybody waiting for slots to pin pages */
wake_up(&vp_wq);
}
kfree(in_pages);
kfree(out_pages);
return err;
}
static ssize_t p9_mount_tag_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct virtio_chan *chan;
struct virtio_device *vdev;
vdev = dev_to_virtio(dev);
chan = vdev->priv;
memcpy(buf, chan->tag, chan->tag_len);
buf[chan->tag_len] = 0;
return chan->tag_len + 1;
}
static DEVICE_ATTR(mount_tag, 0444, p9_mount_tag_show, NULL);
/**
* p9_virtio_probe - probe for existence of 9P virtio channels
* @vdev: virtio device to probe
*
* This probes for existing virtio channels.
*
*/
static int p9_virtio_probe(struct virtio_device *vdev)
{
__u16 tag_len;
char *tag;
int err;
struct virtio_chan *chan;
if (!vdev->config->get) {
dev_err(&vdev->dev, "%s failure: config access disabled\n",
__func__);
return -EINVAL;
}
chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL);
if (!chan) {
pr_err("Failed to allocate virtio 9P channel\n");
err = -ENOMEM;
goto fail;
}
chan->vdev = vdev;
/* We expect one virtqueue, for requests. */
chan->vq = virtio_find_single_vq(vdev, req_done, "requests");
if (IS_ERR(chan->vq)) {
err = PTR_ERR(chan->vq);
goto out_free_vq;
}
chan->vq->vdev->priv = chan;
spin_lock_init(&chan->lock);
sg_init_table(chan->sg, VIRTQUEUE_NUM);
chan->inuse = false;
if (virtio_has_feature(vdev, VIRTIO_9P_MOUNT_TAG)) {
virtio_cread(vdev, struct virtio_9p_config, tag_len, &tag_len);
} else {
err = -EINVAL;
goto out_free_vq;
}
tag = kmalloc(tag_len, GFP_KERNEL);
if (!tag) {
err = -ENOMEM;
goto out_free_vq;
}
virtio_cread_bytes(vdev, offsetof(struct virtio_9p_config, tag),
tag, tag_len);
chan->tag = tag;
chan->tag_len = tag_len;
err = sysfs_create_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
if (err) {
goto out_free_tag;
}
chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
if (!chan->vc_wq) {
err = -ENOMEM;
goto out_free_tag;
}
init_waitqueue_head(chan->vc_wq);
chan->ring_bufs_avail = 1;
/* Ceiling limit to avoid denial of service attacks */
chan->p9_max_pages = nr_free_buffer_pages()/4;
virtio_device_ready(vdev);
mutex_lock(&virtio_9p_lock);
list_add_tail(&chan->chan_list, &virtio_chan_list);
mutex_unlock(&virtio_9p_lock);
/* Let udev rules use the new mount_tag attribute. */
kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
return 0;
out_free_tag:
kfree(tag);
out_free_vq:
vdev->config->del_vqs(vdev);
kfree(chan);
fail:
return err;
}
/**
* p9_virtio_create - allocate a new virtio channel
* @client: client instance invoking this transport
* @devname: string identifying the channel to connect to (unused)
* @args: args passed from sys_mount() for per-transport options (unused)
*
* This sets up a transport channel for 9p communication. Right now
* we only match the first available channel, but eventually we couldlook up
* alternate channels by matching devname versus a virtio_config entry.
* We use a simple reference count mechanism to ensure that only a single
* mount has a channel open at a time.
*
*/
static int
p9_virtio_create(struct p9_client *client, const char *devname, char *args)
{
struct virtio_chan *chan;
int ret = -ENOENT;
int found = 0;
mutex_lock(&virtio_9p_lock);
list_for_each_entry(chan, &virtio_chan_list, chan_list) {
if (!strncmp(devname, chan->tag, chan->tag_len) &&
strlen(devname) == chan->tag_len) {
if (!chan->inuse) {
chan->inuse = true;
found = 1;
break;
}
ret = -EBUSY;
}
}
mutex_unlock(&virtio_9p_lock);
if (!found) {
pr_err("no channels available\n");
return ret;
}
client->trans = (void *)chan;
client->status = Connected;
chan->client = client;
return 0;
}
/**
* p9_virtio_remove - clean up resources associated with a virtio device
* @vdev: virtio device to remove
*
*/
static void p9_virtio_remove(struct virtio_device *vdev)
{
struct virtio_chan *chan = vdev->priv;
unsigned long warning_time;
mutex_lock(&virtio_9p_lock);
/* Remove self from list so we don't get new users. */
list_del(&chan->chan_list);
warning_time = jiffies;
/* Wait for existing users to close. */
while (chan->inuse) {
mutex_unlock(&virtio_9p_lock);
msleep(250);
if (time_after(jiffies, warning_time + 10 * HZ)) {
dev_emerg(&vdev->dev,
"p9_virtio_remove: waiting for device in use.\n");
warning_time = jiffies;
}
mutex_lock(&virtio_9p_lock);
}
mutex_unlock(&virtio_9p_lock);
vdev->config->del_vqs(vdev);
sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
kfree(chan->tag);
kfree(chan->vc_wq);
kfree(chan);
}
static struct virtio_device_id id_table[] = {
{ VIRTIO_ID_9P, VIRTIO_DEV_ANY_ID },
{ 0 },
};
static unsigned int features[] = {
VIRTIO_9P_MOUNT_TAG,
};
/* The standard "struct lguest_driver": */
static struct virtio_driver p9_virtio_drv = {
.feature_table = features,
.feature_table_size = ARRAY_SIZE(features),
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = id_table,
.probe = p9_virtio_probe,
.remove = p9_virtio_remove,
};
static struct p9_trans_module p9_virtio_trans = {
.name = "virtio",
.create = p9_virtio_create,
.close = p9_virtio_close,
.request = p9_virtio_request,
.zc_request = p9_virtio_zc_request,
.cancel = p9_virtio_cancel,
/*
* We leave one entry for input and one entry for response
* headers. We also skip one more entry to accomodate, address
* that are not at page boundary, that can result in an extra
* page in zero copy.
*/
.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
.def = 1,
.owner = THIS_MODULE,
};
/* The standard init function */
static int __init p9_virtio_init(void)
{
INIT_LIST_HEAD(&virtio_chan_list);
v9fs_register_trans(&p9_virtio_trans);
return register_virtio_driver(&p9_virtio_drv);
}
static void __exit p9_virtio_cleanup(void)
{
unregister_virtio_driver(&p9_virtio_drv);
v9fs_unregister_trans(&p9_virtio_trans);
}
module_init(p9_virtio_init);
module_exit(p9_virtio_cleanup);
MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
MODULE_DESCRIPTION("Virtio 9p Transport");
MODULE_LICENSE("GPL");