linux/net/9p/trans_virtio.c

839 lines
21 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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
*/
#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
* @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
net: 9p: Fix kerneldoc warnings of missing parameters etc net/9p/client.c:420: warning: Function parameter or member 'c' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'req' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'status' not described in 'p9_client_cb' net/9p/client.c:568: warning: Function parameter or member 'uidata' not described in 'p9_check_zc_errors' net/9p/trans_common.c:23: warning: Function parameter or member 'nr_pages' not described in 'p9_release_pages' net/9p/trans_common.c:23: warning: Function parameter or member 'pages' not described in 'p9_release_pages' net/9p/trans_fd.c:132: warning: Function parameter or member 'rreq' not described in 'p9_conn' net/9p/trans_fd.c:132: warning: Function parameter or member 'wreq' not described in 'p9_conn' net/9p/trans_fd.c:56: warning: Function parameter or member 'privport' not described in 'p9_fd_opts' net/9p/trans_rdma.c:113: warning: Function parameter or member 'cqe' not described in 'p9_rdma_context' net/9p/trans_rdma.c:129: warning: Function parameter or member 'privport' not described in 'p9_rdma_opts' net/9p/trans_virtio.c:215: warning: Function parameter or member 'limit' not described in 'pack_sg_list_p' net/9p/trans_virtio.c:83: warning: Function parameter or member 'chan_list' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'p9_max_pages' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'ring_bufs_avail' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'tag' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'vc_wq' not described in 'virtio_chan' Signed-off-by: Andrew Lunn <andrew@lunn.ch> Acked-by: Dominique Martinet <asmadeus@codewreck.org> Link: https://lore.kernel.org/r/20201031182655.1082065-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-10-31 18:26:55 +00:00
* @ring_bufs_avail: flag to indicate there is some available in the ring buf
* @vc_wq: wait queue for waiting for thing to be added to ring buf
* @p9_max_pages: maximum number of pinned pages
* @sg: scatter gather list which is used to pack a request (protected?)
net: 9p: Fix kerneldoc warnings of missing parameters etc net/9p/client.c:420: warning: Function parameter or member 'c' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'req' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'status' not described in 'p9_client_cb' net/9p/client.c:568: warning: Function parameter or member 'uidata' not described in 'p9_check_zc_errors' net/9p/trans_common.c:23: warning: Function parameter or member 'nr_pages' not described in 'p9_release_pages' net/9p/trans_common.c:23: warning: Function parameter or member 'pages' not described in 'p9_release_pages' net/9p/trans_fd.c:132: warning: Function parameter or member 'rreq' not described in 'p9_conn' net/9p/trans_fd.c:132: warning: Function parameter or member 'wreq' not described in 'p9_conn' net/9p/trans_fd.c:56: warning: Function parameter or member 'privport' not described in 'p9_fd_opts' net/9p/trans_rdma.c:113: warning: Function parameter or member 'cqe' not described in 'p9_rdma_context' net/9p/trans_rdma.c:129: warning: Function parameter or member 'privport' not described in 'p9_rdma_opts' net/9p/trans_virtio.c:215: warning: Function parameter or member 'limit' not described in 'pack_sg_list_p' net/9p/trans_virtio.c:83: warning: Function parameter or member 'chan_list' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'p9_max_pages' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'ring_bufs_avail' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'tag' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'vc_wq' not described in 'virtio_chan' Signed-off-by: Andrew Lunn <andrew@lunn.ch> Acked-by: Dominique Martinet <asmadeus@codewreck.org> Link: https://lore.kernel.org/r/20201031182655.1082065-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-10-31 18:26:55 +00:00
* @chan_list: linked list of channels
*
* 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];
net: 9p: Fix kerneldoc warnings of missing parameters etc net/9p/client.c:420: warning: Function parameter or member 'c' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'req' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'status' not described in 'p9_client_cb' net/9p/client.c:568: warning: Function parameter or member 'uidata' not described in 'p9_check_zc_errors' net/9p/trans_common.c:23: warning: Function parameter or member 'nr_pages' not described in 'p9_release_pages' net/9p/trans_common.c:23: warning: Function parameter or member 'pages' not described in 'p9_release_pages' net/9p/trans_fd.c:132: warning: Function parameter or member 'rreq' not described in 'p9_conn' net/9p/trans_fd.c:132: warning: Function parameter or member 'wreq' not described in 'p9_conn' net/9p/trans_fd.c:56: warning: Function parameter or member 'privport' not described in 'p9_fd_opts' net/9p/trans_rdma.c:113: warning: Function parameter or member 'cqe' not described in 'p9_rdma_context' net/9p/trans_rdma.c:129: warning: Function parameter or member 'privport' not described in 'p9_rdma_opts' net/9p/trans_virtio.c:215: warning: Function parameter or member 'limit' not described in 'pack_sg_list_p' net/9p/trans_virtio.c:83: warning: Function parameter or member 'chan_list' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'p9_max_pages' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'ring_bufs_avail' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'tag' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'vc_wq' not described in 'virtio_chan' Signed-off-by: Andrew Lunn <andrew@lunn.ch> Acked-by: Dominique Martinet <asmadeus@codewreck.org> Link: https://lore.kernel.org/r/20201031182655.1082065-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-10-31 18:26:55 +00:00
/**
* @tag: name to identify a mount 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 - offset_in_page(data);
}
/**
* p9_virtio_close - reclaim resources of a channel
* @client: client instance
*
* This reclaims a channel by freeing its resources and
* resetting 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;
unsigned int len;
struct p9_req_t *req;
bool need_wakeup = false;
unsigned long flags;
p9_debug(P9_DEBUG_TRANS, ": request done\n");
spin_lock_irqsave(&chan->lock, flags);
while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) {
if (!chan->ring_bufs_avail) {
chan->ring_bufs_avail = 1;
need_wakeup = true;
}
if (len) {
req->rc.size = len;
p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
}
}
spin_unlock_irqrestore(&chan->lock, flags);
/* Wakeup if anyone waiting for VirtIO ring space. */
if (need_wakeup)
wake_up(chan->vc_wq);
}
/**
* 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;
}
/* Reply won't come, so drop req ref */
static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
{
p9_req_put(client, req);
return 0;
}
/**
* 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
net: 9p: Fix kerneldoc warnings of missing parameters etc net/9p/client.c:420: warning: Function parameter or member 'c' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'req' not described in 'p9_client_cb' net/9p/client.c:420: warning: Function parameter or member 'status' not described in 'p9_client_cb' net/9p/client.c:568: warning: Function parameter or member 'uidata' not described in 'p9_check_zc_errors' net/9p/trans_common.c:23: warning: Function parameter or member 'nr_pages' not described in 'p9_release_pages' net/9p/trans_common.c:23: warning: Function parameter or member 'pages' not described in 'p9_release_pages' net/9p/trans_fd.c:132: warning: Function parameter or member 'rreq' not described in 'p9_conn' net/9p/trans_fd.c:132: warning: Function parameter or member 'wreq' not described in 'p9_conn' net/9p/trans_fd.c:56: warning: Function parameter or member 'privport' not described in 'p9_fd_opts' net/9p/trans_rdma.c:113: warning: Function parameter or member 'cqe' not described in 'p9_rdma_context' net/9p/trans_rdma.c:129: warning: Function parameter or member 'privport' not described in 'p9_rdma_opts' net/9p/trans_virtio.c:215: warning: Function parameter or member 'limit' not described in 'pack_sg_list_p' net/9p/trans_virtio.c:83: warning: Function parameter or member 'chan_list' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'p9_max_pages' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'ring_bufs_avail' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'tag' not described in 'virtio_chan' net/9p/trans_virtio.c:83: warning: Function parameter or member 'vc_wq' not described in 'virtio_chan' Signed-off-by: Andrew Lunn <andrew@lunn.ch> Acked-by: Dominique Martinet <asmadeus@codewreck.org> Link: https://lore.kernel.org/r/20201031182655.1082065-1-andrew@lunn.ch Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-10-31 18:26:55 +00:00
* @limit: maximum number of pages in sg list.
* @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;
BUG_ON(index >= limit);
/* 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,
GFP_ATOMIC);
if (err < 0) {
if (err == -ENOSPC) {
chan->ring_bufs_avail = 0;
spin_unlock_irqrestore(&chan->lock, flags);
err = wait_event_killable(*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;
iov_iter: Fix 9p virtio breakage When switching to the new iovec accessors, a negation got subtly dropped, leading to 9p being remarkably broken (here with kvmtool): [ 7.430941] VFS: Mounted root (9p filesystem) on device 0:15. [ 7.432080] devtmpfs: mounted [ 7.432717] Freeing unused kernel memory: 1344K [ 7.433658] Run /virt/init as init process Warning: unable to translate guest address 0x7e00902ff000 to host Warning: unable to translate guest address 0x7e00902fefc0 to host Warning: unable to translate guest address 0x7e00902ff000 to host Warning: unable to translate guest address 0x7e008febef80 to host Warning: unable to translate guest address 0x7e008febf000 to host Warning: unable to translate guest address 0x7e008febef00 to host Warning: unable to translate guest address 0x7e008febf000 to host [ 7.436376] Kernel panic - not syncing: Requested init /virt/init failed (error -8). [ 7.437554] CPU: 29 PID: 1 Comm: swapper/0 Not tainted 4.19.0-rc8-02267-g00e23707442a #291 [ 7.439006] Hardware name: linux,dummy-virt (DT) [ 7.439902] Call trace: [ 7.440387] dump_backtrace+0x0/0x148 [ 7.441104] show_stack+0x14/0x20 [ 7.441768] dump_stack+0x90/0xb4 [ 7.442425] panic+0x120/0x27c [ 7.443036] kernel_init+0xa4/0x100 [ 7.443725] ret_from_fork+0x10/0x18 [ 7.444444] SMP: stopping secondary CPUs [ 7.445391] Kernel Offset: disabled [ 7.446169] CPU features: 0x0,23000438 [ 7.446974] Memory Limit: none [ 7.447645] ---[ end Kernel panic - not syncing: Requested init /virt/init failed (error -8). ]--- Restoring the missing "!" brings the guest back to life. Fixes: 00e23707442a ("iov_iter: Use accessor function") Reported-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-02 17:16:51 +00:00
if (!iov_iter_is_kvec(data)) {
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_killable(vp_wq,
(atomic_read(&vp_pinned) < chan->p9_max_pages));
if (err == -ERESTARTSYS)
return err;
}
n = iov_iter_get_pages_alloc2(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;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 20:55:00 +00:00
*pages = kmalloc_array(nr_pages, sizeof(struct page *),
GFP_NOFS);
if (!*pages)
return -ENOMEM;
*need_drop = 0;
p -= (*offs = offset_in_page(p));
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;
}
iov_iter_advance(data, len);
return len;
}
}
9p: handling Rerror without copy_from_iter_full() p9_client_zc_rpc()/p9_check_zc_errors() are playing fast and loose with copy_from_iter_full(). Reading from file is done by sending Tread request. Response consists of fixed-sized header (including the amount of data actually read) followed by the data itself. For zero-copy case we arrange the things so that the first 11 bytes of reply go into the fixed-sized buffer, with the rest going straight into the pages we want to read into. What makes the things inconvenient is that sglist describing what should go where has to be set *before* the reply arrives. As the result, if reply is an error, the things get interesting. On success we get size[4] Rread tag[2] count[4] data[count] For error layout varies depending upon the protocol variant - in original 9P and 9P2000 it's size[4] Rerror tag[2] len[2] error[len] in 9P2000.U size[4] Rerror tag[2] len[2] error[len] errno[4] in 9P2000.L size[4] Rlerror tag[2] errno[4] The last case is nice and simple - we have an 11-byte response that fits into the fixed-sized buffer we hoped to get an Rread into. In other two, though, we get a variable-length string spill into the pages we'd prepared for the data to be read. Had that been in fixed-sized buffer (which is actually 4K), we would've dealt with that the same way we handle non-zerocopy case. However, for zerocopy it doesn't end up there, so we need to copy it from those pages. The trouble is, by the time we get around to that, the references to pages in question are already dropped. As the result, p9_zc_check_errors() tries to get the data using copy_from_iter_full(). Unfortunately, the iov_iter it's trying to read from might *NOT* be capable of that. It is, after all, a data destination, not data source. In particular, if it's an ITER_PIPE one, copy_from_iter_full() will simply fail. In ->zc_request() itself we do have those pages and dealing with the problem in there would be a simple matter of memcpy_from_page() into the fixed-sized buffer. Moreover, it isn't hard to recognize the (rare) case when such copying is needed. That way we get rid of p9_zc_check_errors() entirely - p9_check_errors() can be used instead both for zero-copy and non-zero-copy cases. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2022-06-09 14:01:34 +00:00
static void handle_rerror(struct p9_req_t *req, int in_hdr_len,
size_t offs, struct page **pages)
{
unsigned size, n;
void *to = req->rc.sdata + in_hdr_len;
// Fits entirely into the static data? Nothing to do.
if (req->rc.size < in_hdr_len)
return;
// Really long error message? Tough, truncate the reply. Might get
// rejected (we can't be arsed to adjust the size encoded in header,
// or string size for that matter), but it wouldn't be anything valid
// anyway.
if (unlikely(req->rc.size > P9_ZC_HDR_SZ))
req->rc.size = P9_ZC_HDR_SZ;
// data won't span more than two pages
size = req->rc.size - in_hdr_len;
n = PAGE_SIZE - offs;
if (size > n) {
memcpy_from_page(to, *pages++, offs, n);
offs = 0;
to += n;
size -= n;
}
memcpy_from_page(to, *pages, offs, size);
}
/**
* p9_virtio_zc_request - issue a zero copy request
* @client: client instance issuing the request
* @req: request to be issued
* @uidata: user buffer that should be used for zero copy read
* @uodata: user buffer that should be used for zero copy write
* @inlen: read buffer size
* @outlen: write buffer size
* @in_hdr_len: 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;
int kicked = 0;
p9_debug(P9_DEBUG_TRANS, "virtio request\n");
if (uodata) {
__le32 sz;
int n = p9_get_mapped_pages(chan, &out_pages, uodata,
outlen, &offs, &need_drop);
if (n < 0) {
err = n;
goto err_out;
}
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;
}
/* The size field of the message must include the length of the
* header and the length of the data. We didn't actually know
* the length of the data until this point so add it in now.
*/
sz = cpu_to_le32(req->tc.size + outlen);
memcpy(&req->tc.sdata[0], &sz, sizeof(sz));
} else if (uidata) {
int n = p9_get_mapped_pages(chan, &in_pages, uidata,
inlen, &offs, &need_drop);
if (n < 0) {
err = n;
goto err_out;
}
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
* allocated 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,
GFP_ATOMIC);
if (err < 0) {
if (err == -ENOSPC) {
chan->ring_bufs_avail = 0;
spin_unlock_irqrestore(&chan->lock, flags);
err = wait_event_killable(*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);
kicked = 1;
p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
9p: handling Rerror without copy_from_iter_full() p9_client_zc_rpc()/p9_check_zc_errors() are playing fast and loose with copy_from_iter_full(). Reading from file is done by sending Tread request. Response consists of fixed-sized header (including the amount of data actually read) followed by the data itself. For zero-copy case we arrange the things so that the first 11 bytes of reply go into the fixed-sized buffer, with the rest going straight into the pages we want to read into. What makes the things inconvenient is that sglist describing what should go where has to be set *before* the reply arrives. As the result, if reply is an error, the things get interesting. On success we get size[4] Rread tag[2] count[4] data[count] For error layout varies depending upon the protocol variant - in original 9P and 9P2000 it's size[4] Rerror tag[2] len[2] error[len] in 9P2000.U size[4] Rerror tag[2] len[2] error[len] errno[4] in 9P2000.L size[4] Rlerror tag[2] errno[4] The last case is nice and simple - we have an 11-byte response that fits into the fixed-sized buffer we hoped to get an Rread into. In other two, though, we get a variable-length string spill into the pages we'd prepared for the data to be read. Had that been in fixed-sized buffer (which is actually 4K), we would've dealt with that the same way we handle non-zerocopy case. However, for zerocopy it doesn't end up there, so we need to copy it from those pages. The trouble is, by the time we get around to that, the references to pages in question are already dropped. As the result, p9_zc_check_errors() tries to get the data using copy_from_iter_full(). Unfortunately, the iov_iter it's trying to read from might *NOT* be capable of that. It is, after all, a data destination, not data source. In particular, if it's an ITER_PIPE one, copy_from_iter_full() will simply fail. In ->zc_request() itself we do have those pages and dealing with the problem in there would be a simple matter of memcpy_from_page() into the fixed-sized buffer. Moreover, it isn't hard to recognize the (rare) case when such copying is needed. That way we get rid of p9_zc_check_errors() entirely - p9_check_errors() can be used instead both for zero-copy and non-zero-copy cases. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2022-06-09 14:01:34 +00:00
// RERROR needs reply (== error string) in static data
if (req->status == REQ_STATUS_RCVD &&
unlikely(req->rc.sdata[4] == P9_RERROR))
handle_rerror(req, in_hdr_len, offs, in_pages);
/*
* 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);
}
9p/trans_virtio: use kvfree() for iov_iter_get_pages_alloc() The memory allocated by iov_iter_get_pages_alloc() can be allocated with vmalloc() if kmalloc() failed -- see get_pages_array(). In that case we need to free it with vfree(), so let's use kvfree(). The bug manifests like this: BUG: unable to handle kernel paging request at ffffeb0400072da0 IP: [<ffffffff8139c67b>] kfree+0x4b/0x140 PGD 0 Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 2 PID: 675 Comm: trinity-c2 Not tainted 4.7.0-rc7+ #14 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 task: ffff8800badef2c0 ti: ffff880069208000 task.ti: ffff880069208000 RIP: 0010:[<ffffffff8139c67b>] [<ffffffff8139c67b>] kfree+0x4b/0x140 RSP: 0000:ffff88006920f3f0 EFLAGS: 00010282 RAX: ffffea0000000000 RBX: ffffc90001cb6000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000246 RDI: ffffc90001cb6000 RBP: ffff88006920f410 R08: 0000000000000000 R09: dffffc0000000000 R10: ffff8800badefa30 R11: 0000056a3d3b0d9f R12: ffff88006920f620 R13: ffffeb0400072d80 R14: ffff8800baa94078 R15: 0000000000000000 FS: 00007fbd2b437700(0000) GS:ffff88011af00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffeb0400072da0 CR3: 000000006926d000 CR4: 00000000000006e0 Stack: 0000000000000001 ffff88006920f620 ffffed001755280f ffff8800baa94078 ffff88006920f6a8 ffffffff8310442b dffffc0000000000 ffff8800badefa30 ffff8800badefa28 ffff88011af1fba0 1ffff1000d241e98 ffff8800ba892150 Call Trace: [<ffffffff8310442b>] p9_virtio_zc_request+0x72b/0xdb0 [<ffffffff830f2116>] p9_client_zc_rpc.constprop.8+0x246/0xb10 [<ffffffff830f5d79>] p9_client_read+0x4c9/0x750 [<ffffffff8175ceac>] v9fs_fid_readpage+0x14c/0x320 [<ffffffff8175d0b6>] v9fs_vfs_readpage+0x36/0x50 [<ffffffff812c6f13>] filemap_fault+0x9a3/0xe60 [<ffffffff81331878>] __do_fault+0x158/0x300 [<ffffffff81339e01>] handle_mm_fault+0x1cf1/0x3c80 [<ffffffff810c0aaa>] __do_page_fault+0x30a/0x8e0 [<ffffffff810c10df>] do_page_fault+0x2f/0x80 [<ffffffff810b5b07>] do_async_page_fault+0x27/0xa0 [<ffffffff83296c48>] async_page_fault+0x28/0x30 Code: 00 80 41 54 53 49 01 fd 48 0f 42 05 b0 39 67 02 48 89 fb 49 01 c5 48 b8 00 00 00 00 00 ea ff ff 49 c1 ed 0c 49 c1 e5 06 49 01 c5 <49> 8b 45 20 48 8d 50 ff a8 01 4c 0f 45 ea 49 8b 55 20 48 8d 42 RIP [<ffffffff8139c67b>] kfree+0x4b/0x140 RSP <ffff88006920f3f0> CR2: ffffeb0400072da0 ---[ end trace f3d59a04bafec038 ]--- Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2016-08-03 16:59:47 +00:00
kvfree(in_pages);
kvfree(out_pages);
if (!kicked) {
/* reply won't come */
p9_req_put(client, req);
}
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;
int tag_len;
vdev = dev_to_virtio(dev);
chan = vdev->priv;
tag_len = strlen(chan->tag);
memcpy(buf, chan->tag, tag_len + 1);
return 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_chan;
}
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 = kzalloc(tag_len + 1, 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;
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_remove_file;
}
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_remove_file:
sysfs_remove_file(&vdev->dev.kobj, &dev_attr_mount_tag.attr);
out_free_tag:
kfree(tag);
out_free_vq:
vdev->config->del_vqs(vdev);
out_free_chan:
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 could look 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;
if (devname == NULL)
return -EINVAL;
mutex_lock(&virtio_9p_lock);
list_for_each_entry(chan, &virtio_chan_list, chan_list) {
if (!strcmp(devname, chan->tag)) {
if (!chan->inuse) {
chan->inuse = true;
found = 1;
break;
}
ret = -EBUSY;
}
}
mutex_unlock(&virtio_9p_lock);
if (!found) {
pr_err("no channels available for device %s\n", devname);
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);
virtio_reset_device(vdev);
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,
.cancelled = p9_virtio_cancelled,
/*
* We leave one entry for input and one entry for response
* headers. We also skip one more entry to accommodate, address
* that are not at page boundary, that can result in an extra
* page in zero copy.
*/
.maxsize = PAGE_SIZE * (VIRTQUEUE_NUM - 3),
.pooled_rbuffers = false,
.def = 1,
.owner = THIS_MODULE,
};
/* The standard init function */
static int __init p9_virtio_init(void)
{
9p/virtio: Add cleanup path in p9_virtio_init KASAN report this: BUG: unable to handle kernel paging request at ffffffffa0097000 PGD 3870067 P4D 3870067 PUD 3871063 PMD 2326e2067 PTE 0 Oops: 0000 [#1 CPU: 0 PID: 5340 Comm: modprobe Not tainted 5.1.0-rc7+ #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__list_add_valid+0x10/0x70 Code: c3 48 8b 06 55 48 89 e5 5d 48 39 07 0f 94 c0 0f b6 c0 c3 90 90 90 90 90 90 90 55 48 89 d0 48 8b 52 08 48 89 e5 48 39 f2 75 19 <48> 8b 32 48 39 f0 75 3a RSP: 0018:ffffc90000e23c68 EFLAGS: 00010246 RAX: ffffffffa00ad000 RBX: ffffffffa009d000 RCX: 0000000000000000 RDX: ffffffffa0097000 RSI: ffffffffa0097000 RDI: ffffffffa009d000 RBP: ffffc90000e23c68 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffa0097000 R13: ffff888231797180 R14: 0000000000000000 R15: ffffc90000e23e78 FS: 00007fb215285540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa0097000 CR3: 000000022f144000 CR4: 00000000000006f0 Call Trace: v9fs_register_trans+0x2f/0x60 [9pnet ? 0xffffffffa0087000 p9_virtio_init+0x25/0x1000 [9pnet_virtio do_one_initcall+0x6c/0x3cc ? kmem_cache_alloc_trace+0x248/0x3b0 do_init_module+0x5b/0x1f1 load_module+0x1db1/0x2690 ? m_show+0x1d0/0x1d0 __do_sys_finit_module+0xc5/0xd0 __x64_sys_finit_module+0x15/0x20 do_syscall_64+0x6b/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb214d8e839 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 RSP: 002b:00007ffc96554278 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000055e67eed2aa0 RCX: 00007fb214d8e839 RDX: 0000000000000000 RSI: 000055e67ce95c2e RDI: 0000000000000003 RBP: 000055e67ce95c2e R08: 0000000000000000 R09: 000055e67eed2aa0 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000 R13: 000055e67eeda500 R14: 0000000000040000 R15: 000055e67eed2aa0 Modules linked in: 9pnet_virtio(+) 9pnet gre rfkill vmw_vsock_virtio_transport_common vsock [last unloaded: 9pnet_virtio CR2: ffffffffa0097000 ---[ end trace 4a52bb13ff07b761 If register_virtio_driver() fails in p9_virtio_init, we should call v9fs_unregister_trans() to do cleanup. Link: http://lkml.kernel.org/r/20190430115942.41840-1-yuehaibing@huawei.com Cc: stable@vger.kernel.org Reported-by: Hulk Robot <hulkci@huawei.com> Fixes: b530cc794024 ("9p: add virtio transport") Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-04-30 11:59:42 +00:00
int rc;
INIT_LIST_HEAD(&virtio_chan_list);
v9fs_register_trans(&p9_virtio_trans);
9p/virtio: Add cleanup path in p9_virtio_init KASAN report this: BUG: unable to handle kernel paging request at ffffffffa0097000 PGD 3870067 P4D 3870067 PUD 3871063 PMD 2326e2067 PTE 0 Oops: 0000 [#1 CPU: 0 PID: 5340 Comm: modprobe Not tainted 5.1.0-rc7+ #25 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__list_add_valid+0x10/0x70 Code: c3 48 8b 06 55 48 89 e5 5d 48 39 07 0f 94 c0 0f b6 c0 c3 90 90 90 90 90 90 90 55 48 89 d0 48 8b 52 08 48 89 e5 48 39 f2 75 19 <48> 8b 32 48 39 f0 75 3a RSP: 0018:ffffc90000e23c68 EFLAGS: 00010246 RAX: ffffffffa00ad000 RBX: ffffffffa009d000 RCX: 0000000000000000 RDX: ffffffffa0097000 RSI: ffffffffa0097000 RDI: ffffffffa009d000 RBP: ffffc90000e23c68 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffa0097000 R13: ffff888231797180 R14: 0000000000000000 R15: ffffc90000e23e78 FS: 00007fb215285540(0000) GS:ffff888237a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa0097000 CR3: 000000022f144000 CR4: 00000000000006f0 Call Trace: v9fs_register_trans+0x2f/0x60 [9pnet ? 0xffffffffa0087000 p9_virtio_init+0x25/0x1000 [9pnet_virtio do_one_initcall+0x6c/0x3cc ? kmem_cache_alloc_trace+0x248/0x3b0 do_init_module+0x5b/0x1f1 load_module+0x1db1/0x2690 ? m_show+0x1d0/0x1d0 __do_sys_finit_module+0xc5/0xd0 __x64_sys_finit_module+0x15/0x20 do_syscall_64+0x6b/0x1d0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb214d8e839 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 RSP: 002b:00007ffc96554278 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000055e67eed2aa0 RCX: 00007fb214d8e839 RDX: 0000000000000000 RSI: 000055e67ce95c2e RDI: 0000000000000003 RBP: 000055e67ce95c2e R08: 0000000000000000 R09: 000055e67eed2aa0 R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000 R13: 000055e67eeda500 R14: 0000000000040000 R15: 000055e67eed2aa0 Modules linked in: 9pnet_virtio(+) 9pnet gre rfkill vmw_vsock_virtio_transport_common vsock [last unloaded: 9pnet_virtio CR2: ffffffffa0097000 ---[ end trace 4a52bb13ff07b761 If register_virtio_driver() fails in p9_virtio_init, we should call v9fs_unregister_trans() to do cleanup. Link: http://lkml.kernel.org/r/20190430115942.41840-1-yuehaibing@huawei.com Cc: stable@vger.kernel.org Reported-by: Hulk Robot <hulkci@huawei.com> Fixes: b530cc794024 ("9p: add virtio transport") Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-04-30 11:59:42 +00:00
rc = register_virtio_driver(&p9_virtio_drv);
if (rc)
v9fs_unregister_trans(&p9_virtio_trans);
return rc;
}
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_ALIAS_9P("virtio");
MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
MODULE_DESCRIPTION("Virtio 9p Transport");
MODULE_LICENSE("GPL");