summaryrefslogtreecommitdiff
path: root/drivers/net/macvtap.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 14:27:06 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-11 14:27:06 -0800
commit70e71ca0af244f48a5dcf56dc435243792e3a495 (patch)
treef7d9c4c4d9a857a00043e9bf6aa2d6f533a34778 /drivers/net/macvtap.c
parentbae41e45b7400496b9bf0c70c6004419d9987819 (diff)
parent00c83b01d58068dfeb2e1351cca6fccf2a83fa8f (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) New offloading infrastructure and example 'rocker' driver for offloading of switching and routing to hardware. This work was done by a large group of dedicated individuals, not limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend, Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu 2) Start making the networking operate on IOV iterators instead of modifying iov objects in-situ during transfers. Thanks to Al Viro and Herbert Xu. 3) A set of new netlink interfaces for the TIPC stack, from Richard Alpe. 4) Remove unnecessary looping during ipv6 routing lookups, from Martin KaFai Lau. 5) Add PAUSE frame generation support to gianfar driver, from Matei Pavaluca. 6) Allow for larger reordering levels in TCP, which are easily achievable in the real world right now, from Eric Dumazet. 7) Add a variable of napi_schedule that doesn't need to disable cpu interrupts, from Eric Dumazet. 8) Use a doubly linked list to optimize neigh_parms_release(), from Nicolas Dichtel. 9) Various enhancements to the kernel BPF verifier, and allow eBPF programs to actually be attached to sockets. From Alexei Starovoitov. 10) Support TSO/LSO in sunvnet driver, from David L Stevens. 11) Allow controlling ECN usage via routing metrics, from Florian Westphal. 12) Remote checksum offload, from Tom Herbert. 13) Add split-header receive, BQL, and xmit_more support to amd-xgbe driver, from Thomas Lendacky. 14) Add MPLS support to openvswitch, from Simon Horman. 15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen Klassert. 16) Do gro flushes on a per-device basis using a timer, from Eric Dumazet. This tries to resolve the conflicting goals between the desired handling of bulk vs. RPC-like traffic. 17) Allow userspace to ask for the CPU upon what a packet was received/steered, via SO_INCOMING_CPU. From Eric Dumazet. 18) Limit GSO packets to half the current congestion window, from Eric Dumazet. 19) Add a generic helper so that all drivers set their RSS keys in a consistent way, from Eric Dumazet. 20) Add xmit_more support to enic driver, from Govindarajulu Varadarajan. 21) Add VLAN packet scheduler action, from Jiri Pirko. 22) Support configurable RSS hash functions via ethtool, from Eyal Perry. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits) Fix race condition between vxlan_sock_add and vxlan_sock_release net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header net/mlx4: Add support for A0 steering net/mlx4: Refactor QUERY_PORT net/mlx4_core: Add explicit error message when rule doesn't meet configuration net/mlx4: Add A0 hybrid steering net/mlx4: Add mlx4_bitmap zone allocator net/mlx4: Add a check if there are too many reserved QPs net/mlx4: Change QP allocation scheme net/mlx4_core: Use tasklet for user-space CQ completion events net/mlx4_core: Mask out host side virtualization features for guests net/mlx4_en: Set csum level for encapsulated packets be2net: Export tunnel offloads only when a VxLAN tunnel is created gianfar: Fix dma check map error when DMA_API_DEBUG is enabled cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call net: fec: only enable mdio interrupt before phy device link up net: fec: clear all interrupt events to support i.MX6SX net: fec: reset fep link status in suspend function net: sock: fix access via invalid file descriptor net: introduce helper macro for_each_cmsghdr ...
Diffstat (limited to 'drivers/net/macvtap.c')
-rw-r--r--drivers/net/macvtap.c140
1 files changed, 64 insertions, 76 deletions
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index af90ab5e5768..60f7ee5fafbe 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -15,6 +15,7 @@
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/fs.h>
+#include <linux/uio.h>
#include <net/ipv6.h>
#include <net/net_namespace.h>
@@ -656,12 +657,12 @@ static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
/* Get packet from user space buffer */
static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
- const struct iovec *iv, unsigned long total_len,
- size_t count, int noblock)
+ struct iov_iter *from, int noblock)
{
int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
struct sk_buff *skb;
struct macvlan_dev *vlan;
+ unsigned long total_len = iov_iter_count(from);
unsigned long len = total_len;
int err;
struct virtio_net_hdr vnet_hdr = { 0 };
@@ -669,6 +670,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
int copylen = 0;
bool zerocopy = false;
size_t linear;
+ ssize_t n;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
@@ -678,10 +680,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
goto err;
len -= vnet_hdr_len;
- err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0,
- sizeof(vnet_hdr));
- if (err < 0)
+ err = -EFAULT;
+ n = copy_from_iter(&vnet_hdr, sizeof(vnet_hdr), from);
+ if (n != sizeof(vnet_hdr))
goto err;
+ iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
macvtap16_to_cpu(q, vnet_hdr.csum_start) +
macvtap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
@@ -698,18 +701,17 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
if (unlikely(len < ETH_HLEN))
goto err;
- err = -EMSGSIZE;
- if (unlikely(count > UIO_MAXIOV))
- goto err;
-
if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
+ struct iov_iter i;
+
copylen = vnet_hdr.hdr_len ?
macvtap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
if (copylen > good_linear)
copylen = good_linear;
linear = copylen;
- if (iov_pages(iv, vnet_hdr_len + copylen, count)
- <= MAX_SKB_FRAGS)
+ i = *from;
+ iov_iter_advance(&i, copylen);
+ if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
zerocopy = true;
}
@@ -727,10 +729,9 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
goto err;
if (zerocopy)
- err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
+ err = zerocopy_sg_from_iter(skb, from);
else {
- err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
- len);
+ err = skb_copy_datagram_from_iter(skb, 0, from, len);
if (!err && m && m->msg_control) {
struct ubuf_info *uarg = m->msg_control;
uarg->callback(uarg, false);
@@ -783,46 +784,42 @@ err:
return err;
}
-static ssize_t macvtap_aio_write(struct kiocb *iocb, const struct iovec *iv,
- unsigned long count, loff_t pos)
+static ssize_t macvtap_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
- ssize_t result = -ENOLINK;
struct macvtap_queue *q = file->private_data;
- result = macvtap_get_user(q, NULL, iv, iov_length(iv, count), count,
- file->f_flags & O_NONBLOCK);
- return result;
+ return macvtap_get_user(q, NULL, from, file->f_flags & O_NONBLOCK);
}
/* Put packet to the user space buffer */
static ssize_t macvtap_put_user(struct macvtap_queue *q,
const struct sk_buff *skb,
- const struct iovec *iv, int len)
+ struct iov_iter *iter)
{
int ret;
int vnet_hdr_len = 0;
int vlan_offset = 0;
- int copied, total;
+ int total;
if (q->flags & IFF_VNET_HDR) {
struct virtio_net_hdr vnet_hdr;
vnet_hdr_len = q->vnet_hdr_sz;
- if ((len -= vnet_hdr_len) < 0)
+ if (iov_iter_count(iter) < vnet_hdr_len)
return -EINVAL;
macvtap_skb_to_vnet_hdr(q, skb, &vnet_hdr);
- if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
+ if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
+ sizeof(vnet_hdr))
return -EFAULT;
+
+ iov_iter_advance(iter, vnet_hdr_len - sizeof(vnet_hdr));
}
- total = copied = vnet_hdr_len;
+ total = vnet_hdr_len;
total += skb->len;
- if (!vlan_tx_tag_present(skb))
- len = min_t(int, skb->len, len);
- else {
- int copy;
+ if (vlan_tx_tag_present(skb)) {
struct {
__be16 h_vlan_proto;
__be16 h_vlan_TCI;
@@ -831,86 +828,77 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
- len = min_t(int, skb->len + VLAN_HLEN, len);
total += VLAN_HLEN;
- copy = min_t(int, vlan_offset, len);
- ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
- len -= copy;
- copied += copy;
- if (ret || !len)
+ ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
+ if (ret || !iov_iter_count(iter))
goto done;
- copy = min_t(int, sizeof(veth), len);
- ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
- len -= copy;
- copied += copy;
- if (ret || !len)
+ ret = copy_to_iter(&veth, sizeof(veth), iter);
+ if (ret != sizeof(veth) || !iov_iter_count(iter))
goto done;
}
- ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
+ ret = skb_copy_datagram_iter(skb, vlan_offset, iter,
+ skb->len - vlan_offset);
done:
return ret ? ret : total;
}
static ssize_t macvtap_do_read(struct macvtap_queue *q,
- const struct iovec *iv, unsigned long len,
+ struct iov_iter *to,
int noblock)
{
DEFINE_WAIT(wait);
struct sk_buff *skb;
ssize_t ret = 0;
- while (len) {
+ if (!iov_iter_count(to))
+ return 0;
+
+ while (1) {
if (!noblock)
prepare_to_wait(sk_sleep(&q->sk), &wait,
TASK_INTERRUPTIBLE);
/* Read frames from the queue */
skb = skb_dequeue(&q->sk.sk_receive_queue);
- if (!skb) {
- if (noblock) {
- ret = -EAGAIN;
- break;
- }
- if (signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- /* Nothing to read, let's sleep */
- schedule();
- continue;
+ if (skb)
+ break;
+ if (noblock) {
+ ret = -EAGAIN;
+ break;
}
- ret = macvtap_put_user(q, skb, iv, len);
- kfree_skb(skb);
- break;
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+ /* Nothing to read, let's sleep */
+ schedule();
+ }
+ if (skb) {
+ ret = macvtap_put_user(q, skb, to);
+ if (unlikely(ret < 0))
+ kfree_skb(skb);
+ else
+ consume_skb(skb);
}
-
if (!noblock)
finish_wait(sk_sleep(&q->sk), &wait);
return ret;
}
-static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv,
- unsigned long count, loff_t pos)
+static ssize_t macvtap_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct macvtap_queue *q = file->private_data;
- ssize_t len, ret = 0;
+ ssize_t len = iov_iter_count(to), ret;
- len = iov_length(iv, count);
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
-
- ret = macvtap_do_read(q, iv, len, file->f_flags & O_NONBLOCK);
+ ret = macvtap_do_read(q, to, file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
if (ret > 0)
iocb->ki_pos = ret;
-out:
return ret;
}
@@ -1109,8 +1097,10 @@ static const struct file_operations macvtap_fops = {
.owner = THIS_MODULE,
.open = macvtap_open,
.release = macvtap_release,
- .aio_read = macvtap_aio_read,
- .aio_write = macvtap_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = macvtap_read_iter,
+ .write_iter = macvtap_write_iter,
.poll = macvtap_poll,
.llseek = no_llseek,
.unlocked_ioctl = macvtap_ioctl,
@@ -1123,8 +1113,7 @@ static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock);
- return macvtap_get_user(q, m, m->msg_iov, total_len, m->msg_iovlen,
- m->msg_flags & MSG_DONTWAIT);
+ return macvtap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
}
static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
@@ -1135,8 +1124,7 @@ static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock,
int ret;
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
- ret = macvtap_do_read(q, m->msg_iov, total_len,
- flags & MSG_DONTWAIT);
+ ret = macvtap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
ret = flags & MSG_TRUNC ? ret : total_len;