summaryrefslogtreecommitdiff
path: root/net/core
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 /net/core
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 'net/core')
-rw-r--r--net/core/datagram.c301
-rw-r--r--net/core/dev.c172
-rw-r--r--net/core/dev_addr_lists.c4
-rw-r--r--net/core/dev_ioctl.c9
-rw-r--r--net/core/dst.c24
-rw-r--r--net/core/ethtool.c81
-rw-r--r--net/core/filter.c97
-rw-r--r--net/core/iovec.c47
-rw-r--r--net/core/link_watch.c2
-rw-r--r--net/core/neighbour.c279
-rw-r--r--net/core/net-sysfs.c44
-rw-r--r--net/core/netpoll.c4
-rw-r--r--net/core/pktgen.c3
-rw-r--r--net/core/rtnetlink.c154
-rw-r--r--net/core/scm.c3
-rw-r--r--net/core/skbuff.c347
-rw-r--r--net/core/sock.c20
-rw-r--r--net/core/sysctl_net_core.c21
-rw-r--r--net/core/utils.c3
19 files changed, 985 insertions, 630 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index fdbc9a81d4c2..df493d68330c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -49,6 +49,7 @@
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
+#include <linux/uio.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
@@ -309,16 +310,14 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
EXPORT_SYMBOL(skb_kill_datagram);
/**
- * skb_copy_datagram_iovec - Copy a datagram to an iovec.
+ * skb_copy_datagram_iter - Copy a datagram to an iovec iterator.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
- * @to: io vector to copy to
+ * @to: iovec iterator to copy to
* @len: amount of data to copy from buffer to iovec
- *
- * Note: the iovec is modified during the copy.
*/
-int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
- struct iovec *to, int len)
+int skb_copy_datagram_iter(const struct sk_buff *skb, int offset,
+ struct iov_iter *to, int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
@@ -330,8 +329,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
if (copy > 0) {
if (copy > len)
copy = len;
- if (memcpy_toiovec(to, skb->data + offset, copy))
- goto fault;
+ if (copy_to_iter(skb->data + offset, copy, to) != copy)
+ goto short_copy;
if ((len -= copy) == 0)
return 0;
offset += copy;
@@ -346,18 +345,12 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
- int err;
- u8 *vaddr;
- struct page *page = skb_frag_page(frag);
-
if (copy > len)
copy = len;
- vaddr = kmap(page);
- err = memcpy_toiovec(to, vaddr + frag->page_offset +
- offset - start, copy);
- kunmap(page);
- if (err)
- goto fault;
+ if (copy_page_to_iter(skb_frag_page(frag),
+ frag->page_offset + offset -
+ start, copy, to) != copy)
+ goto short_copy;
if (!(len -= copy))
return 0;
offset += copy;
@@ -374,9 +367,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
- if (skb_copy_datagram_iovec(frag_iter,
- offset - start,
- to, copy))
+ if (skb_copy_datagram_iter(frag_iter, offset - start,
+ to, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
@@ -387,113 +379,33 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
if (!len)
return 0;
+ /* This is not really a user copy fault, but rather someone
+ * gave us a bogus length on the skb. We should probably
+ * print a warning here as it may indicate a kernel bug.
+ */
+
fault:
return -EFAULT;
-}
-EXPORT_SYMBOL(skb_copy_datagram_iovec);
-/**
- * skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
- * @skb: buffer to copy
- * @offset: offset in the buffer to start copying from
- * @to: io vector to copy to
- * @to_offset: offset in the io vector to start copying to
- * @len: amount of data to copy from buffer to iovec
- *
- * Returns 0 or -EFAULT.
- * Note: the iovec is not modified during the copy.
- */
-int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
- const struct iovec *to, int to_offset,
- int len)
-{
- int start = skb_headlen(skb);
- int i, copy = start - offset;
- struct sk_buff *frag_iter;
+short_copy:
+ if (iov_iter_count(to))
+ goto fault;
- /* Copy header. */
- if (copy > 0) {
- if (copy > len)
- copy = len;
- if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
- goto fault;
- if ((len -= copy) == 0)
- return 0;
- offset += copy;
- to_offset += copy;
- }
-
- /* Copy paged appendix. Hmm... why does this look so complicated? */
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- int end;
- const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
- WARN_ON(start > offset + len);
-
- end = start + skb_frag_size(frag);
- if ((copy = end - offset) > 0) {
- int err;
- u8 *vaddr;
- struct page *page = skb_frag_page(frag);
-
- if (copy > len)
- copy = len;
- vaddr = kmap(page);
- err = memcpy_toiovecend(to, vaddr + frag->page_offset +
- offset - start, to_offset, copy);
- kunmap(page);
- if (err)
- goto fault;
- if (!(len -= copy))
- return 0;
- offset += copy;
- to_offset += copy;
- }
- start = end;
- }
-
- skb_walk_frags(skb, frag_iter) {
- int end;
-
- WARN_ON(start > offset + len);
-
- end = start + frag_iter->len;
- if ((copy = end - offset) > 0) {
- if (copy > len)
- copy = len;
- if (skb_copy_datagram_const_iovec(frag_iter,
- offset - start,
- to, to_offset,
- copy))
- goto fault;
- if ((len -= copy) == 0)
- return 0;
- offset += copy;
- to_offset += copy;
- }
- start = end;
- }
- if (!len)
- return 0;
-
-fault:
- return -EFAULT;
+ return 0;
}
-EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
+EXPORT_SYMBOL(skb_copy_datagram_iter);
/**
- * skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ * skb_copy_datagram_from_iter - Copy a datagram from an iov_iter.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying to
- * @from: io vector to copy to
- * @from_offset: offset in the io vector to start copying from
+ * @from: the copy source
* @len: amount of data to copy to buffer from iovec
*
* Returns 0 or -EFAULT.
- * Note: the iovec is not modified during the copy.
*/
-int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
- const struct iovec *from, int from_offset,
+int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
+ struct iov_iter *from,
int len)
{
int start = skb_headlen(skb);
@@ -504,13 +416,11 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
if (copy > 0) {
if (copy > len)
copy = len;
- if (memcpy_fromiovecend(skb->data + offset, from, from_offset,
- copy))
+ if (copy_from_iter(skb->data + offset, copy, from) != copy)
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
- from_offset += copy;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
@@ -522,24 +432,19 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
- int err;
- u8 *vaddr;
- struct page *page = skb_frag_page(frag);
+ size_t copied;
if (copy > len)
copy = len;
- vaddr = kmap(page);
- err = memcpy_fromiovecend(vaddr + frag->page_offset +
- offset - start,
- from, from_offset, copy);
- kunmap(page);
- if (err)
+ copied = copy_page_from_iter(skb_frag_page(frag),
+ frag->page_offset + offset - start,
+ copy, from);
+ if (copied != copy)
goto fault;
if (!(len -= copy))
return 0;
offset += copy;
- from_offset += copy;
}
start = end;
}
@@ -553,16 +458,13 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
- if (skb_copy_datagram_from_iovec(frag_iter,
- offset - start,
- from,
- from_offset,
- copy))
+ if (skb_copy_datagram_from_iter(frag_iter,
+ offset - start,
+ from, copy))
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
- from_offset += copy;
}
start = end;
}
@@ -572,101 +474,82 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
fault:
return -EFAULT;
}
-EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
+EXPORT_SYMBOL(skb_copy_datagram_from_iter);
/**
- * zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
+ * zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter
* @skb: buffer to copy
- * @from: io vector to copy from
- * @offset: offset in the io vector to start copying from
- * @count: amount of vectors to copy to buffer from
+ * @from: the source to copy from
*
* The function will first copy up to headlen, and then pin the userspace
* pages and build frags through them.
*
* Returns 0, -EFAULT or -EMSGSIZE.
- * Note: the iovec is not modified during the copy
*/
-int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
- int offset, size_t count)
+int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
{
- int len = iov_length(from, count) - offset;
+ int len = iov_iter_count(from);
int copy = min_t(int, skb_headlen(skb), len);
- int size;
- int i = 0;
+ int frag = 0;
/* copy up to skb headlen */
- if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy))
+ if (skb_copy_datagram_from_iter(skb, 0, from, copy))
return -EFAULT;
- if (len == copy)
- return 0;
-
- offset += copy;
- while (count--) {
- struct page *page[MAX_SKB_FRAGS];
- int num_pages;
- unsigned long base;
+ while (iov_iter_count(from)) {
+ struct page *pages[MAX_SKB_FRAGS];
+ size_t start;
+ ssize_t copied;
unsigned long truesize;
+ int n = 0;
- /* Skip over from offset and copied */
- if (offset >= from->iov_len) {
- offset -= from->iov_len;
- ++from;
- continue;
- }
- len = from->iov_len - offset;
- base = (unsigned long)from->iov_base + offset;
- size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
- if (i + size > MAX_SKB_FRAGS)
+ if (frag == MAX_SKB_FRAGS)
return -EMSGSIZE;
- num_pages = get_user_pages_fast(base, size, 0, &page[i]);
- if (num_pages != size) {
- release_pages(&page[i], num_pages, 0);
+
+ copied = iov_iter_get_pages(from, pages, ~0U,
+ MAX_SKB_FRAGS - frag, &start);
+ if (copied < 0)
return -EFAULT;
- }
- truesize = size * PAGE_SIZE;
- skb->data_len += len;
- skb->len += len;
+
+ iov_iter_advance(from, copied);
+
+ truesize = PAGE_ALIGN(copied + start);
+ skb->data_len += copied;
+ skb->len += copied;
skb->truesize += truesize;
atomic_add(truesize, &skb->sk->sk_wmem_alloc);
- while (len) {
- int off = base & ~PAGE_MASK;
- int size = min_t(int, len, PAGE_SIZE - off);
- skb_fill_page_desc(skb, i, page[i], off, size);
- base += size;
- len -= size;
- i++;
+ while (copied) {
+ int size = min_t(int, copied, PAGE_SIZE - start);
+ skb_fill_page_desc(skb, frag++, pages[n], start, size);
+ start = 0;
+ copied -= size;
+ n++;
}
- offset = 0;
- ++from;
}
return 0;
}
-EXPORT_SYMBOL(zerocopy_sg_from_iovec);
+EXPORT_SYMBOL(zerocopy_sg_from_iter);
static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
- u8 __user *to, int len,
+ struct iov_iter *to, int len,
__wsum *csump)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int pos = 0;
+ int n;
/* Copy header. */
if (copy > 0) {
- int err = 0;
if (copy > len)
copy = len;
- *csump = csum_and_copy_to_user(skb->data + offset, to, copy,
- *csump, &err);
- if (err)
+ n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+ if (n != copy)
goto fault;
if ((len -= copy) == 0)
return 0;
offset += copy;
- to += copy;
pos = copy;
}
@@ -678,26 +561,22 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
- __wsum csum2;
- int err = 0;
- u8 *vaddr;
+ __wsum csum2 = 0;
struct page *page = skb_frag_page(frag);
+ u8 *vaddr = kmap(page);
if (copy > len)
copy = len;
- vaddr = kmap(page);
- csum2 = csum_and_copy_to_user(vaddr +
- frag->page_offset +
- offset - start,
- to, copy, 0, &err);
+ n = csum_and_copy_to_iter(vaddr + frag->page_offset +
+ offset - start, copy,
+ &csum2, to);
kunmap(page);
- if (err)
+ if (n != copy)
goto fault;
*csump = csum_block_add(*csump, csum2, pos);
if (!(len -= copy))
return 0;
offset += copy;
- to += copy;
pos += copy;
}
start = end;
@@ -722,7 +601,6 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
if ((len -= copy) == 0)
return 0;
offset += copy;
- to += copy;
pos += copy;
}
start = end;
@@ -775,20 +653,19 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
EXPORT_SYMBOL(__skb_checksum_complete);
/**
- * skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec.
+ * skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec.
* @skb: skbuff
* @hlen: hardware length
- * @iov: io vector
+ * @msg: destination
*
* Caller _must_ check that skb will fit to this iovec.
*
* Returns: 0 - success.
* -EINVAL - checksum failure.
- * -EFAULT - fault during copy. Beware, in this case iovec
- * can be modified!
+ * -EFAULT - fault during copy.
*/
-int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
- int hlen, struct iovec *iov)
+int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
+ int hlen, struct msghdr *msg)
{
__wsum csum;
int chunk = skb->len - hlen;
@@ -796,28 +673,20 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
if (!chunk)
return 0;
- /* Skip filled elements.
- * Pretty silly, look at memcpy_toiovec, though 8)
- */
- while (!iov->iov_len)
- iov++;
-
- if (iov->iov_len < chunk) {
+ if (iov_iter_count(&msg->msg_iter) < chunk) {
if (__skb_checksum_complete(skb))
goto csum_error;
- if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
+ if (skb_copy_datagram_msg(skb, hlen, msg, chunk))
goto fault;
} else {
csum = csum_partial(skb->data, hlen, skb->csum);
- if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
+ if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter,
chunk, &csum))
goto fault;
if (csum_fold(csum))
goto csum_error;
if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
netdev_rx_csum_fault(skb->dev);
- iov->iov_len -= chunk;
- iov->iov_base += chunk;
}
return 0;
csum_error:
@@ -825,7 +694,7 @@ csum_error:
fault:
return -EFAULT;
}
-EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
+EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg);
/**
* datagram_poll - generic datagram poll
diff --git a/net/core/dev.c b/net/core/dev.c
index 3acff0974560..f411c28d0a66 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -118,6 +118,7 @@
#include <linux/if_vlan.h>
#include <linux/ip.h>
#include <net/ip.h>
+#include <net/mpls.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
@@ -133,6 +134,7 @@
#include <linux/vmalloc.h>
#include <linux/if_macvlan.h>
#include <linux/errqueue.h>
+#include <linux/hrtimer.h>
#include "net-sysfs.h"
@@ -1435,22 +1437,17 @@ EXPORT_SYMBOL(dev_close);
*/
void dev_disable_lro(struct net_device *dev)
{
- /*
- * If we're trying to disable lro on a vlan device
- * use the underlying physical device instead
- */
- if (is_vlan_dev(dev))
- dev = vlan_dev_real_dev(dev);
-
- /* the same for macvlan devices */
- if (netif_is_macvlan(dev))
- dev = macvlan_dev_real_dev(dev);
+ struct net_device *lower_dev;
+ struct list_head *iter;
dev->wanted_features &= ~NETIF_F_LRO;
netdev_update_features(dev);
if (unlikely(dev->features & NETIF_F_LRO))
netdev_WARN(dev, "failed to disable LRO!\n");
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter)
+ dev_disable_lro(lower_dev);
}
EXPORT_SYMBOL(dev_disable_lro);
@@ -2530,7 +2527,7 @@ static netdev_features_t net_mpls_features(struct sk_buff *skb,
netdev_features_t features,
__be16 type)
{
- if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+ if (eth_p_mpls(type))
features &= skb->dev->mpls_features;
return features;
@@ -2647,12 +2644,8 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
netdev_features_t features)
{
if (vlan_tx_tag_present(skb) &&
- !vlan_hw_offload_capable(features, skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto,
- vlan_tx_tag_get(skb));
- if (skb)
- skb->vlan_tci = 0;
- }
+ !vlan_hw_offload_capable(features, skb->vlan_proto))
+ skb = __vlan_hwaccel_push_inside(skb);
return skb;
}
@@ -3304,7 +3297,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
rps_lock(sd);
qlen = skb_queue_len(&sd->input_pkt_queue);
if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
- if (skb_queue_len(&sd->input_pkt_queue)) {
+ if (qlen) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
input_queue_tail_incr_save(sd, qtail);
@@ -4179,7 +4172,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
struct sk_buff *skb = napi->skb;
if (!skb) {
- skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+ skb = napi_alloc_skb(napi, GRO_MAX_HEAD);
napi->skb = skb;
}
return skb;
@@ -4316,20 +4309,28 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
local_irq_enable();
}
+static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+ return sd->rps_ipi_list != NULL;
+#else
+ return false;
+#endif
+}
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
-#ifdef CONFIG_RPS
/* Check if we have pending ipi, its better to send them now,
* not waiting net_rx_action() end.
*/
- if (sd->rps_ipi_list) {
+ if (sd_has_rps_ipi_waiting(sd)) {
local_irq_disable();
net_rps_action_and_irq_enable(sd);
}
-#endif
+
napi->weight = weight_p;
local_irq_disable();
while (1) {
@@ -4356,7 +4357,6 @@ static int process_backlog(struct napi_struct *napi, int quota)
* We can use a plain write instead of clear_bit(),
* and we dont need an smp_mb() memory barrier.
*/
- list_del(&napi->poll_list);
napi->state = 0;
rps_unlock(sd);
@@ -4376,7 +4376,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
* __napi_schedule - schedule for receive
* @n: entry to schedule
*
- * The entry's receive function will be scheduled to run
+ * The entry's receive function will be scheduled to run.
+ * Consider using __napi_schedule_irqoff() if hard irqs are masked.
*/
void __napi_schedule(struct napi_struct *n)
{
@@ -4388,18 +4389,29 @@ void __napi_schedule(struct napi_struct *n)
}
EXPORT_SYMBOL(__napi_schedule);
+/**
+ * __napi_schedule_irqoff - schedule for receive
+ * @n: entry to schedule
+ *
+ * Variant of __napi_schedule() assuming hard irqs are masked
+ */
+void __napi_schedule_irqoff(struct napi_struct *n)
+{
+ ____napi_schedule(this_cpu_ptr(&softnet_data), n);
+}
+EXPORT_SYMBOL(__napi_schedule_irqoff);
+
void __napi_complete(struct napi_struct *n)
{
BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
- BUG_ON(n->gro_list);
- list_del(&n->poll_list);
+ list_del_init(&n->poll_list);
smp_mb__before_atomic();
clear_bit(NAPI_STATE_SCHED, &n->state);
}
EXPORT_SYMBOL(__napi_complete);
-void napi_complete(struct napi_struct *n)
+void napi_complete_done(struct napi_struct *n, int work_done)
{
unsigned long flags;
@@ -4410,12 +4422,28 @@ void napi_complete(struct napi_struct *n)
if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
return;
- napi_gro_flush(n, false);
- local_irq_save(flags);
- __napi_complete(n);
- local_irq_restore(flags);
+ if (n->gro_list) {
+ unsigned long timeout = 0;
+
+ if (work_done)
+ timeout = n->dev->gro_flush_timeout;
+
+ if (timeout)
+ hrtimer_start(&n->timer, ns_to_ktime(timeout),
+ HRTIMER_MODE_REL_PINNED);
+ else
+ napi_gro_flush(n, false);
+ }
+ if (likely(list_empty(&n->poll_list))) {
+ WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
+ } else {
+ /* If n->poll_list is not empty, we need to mask irqs */
+ local_irq_save(flags);
+ __napi_complete(n);
+ local_irq_restore(flags);
+ }
}
-EXPORT_SYMBOL(napi_complete);
+EXPORT_SYMBOL(napi_complete_done);
/* must be called under rcu_read_lock(), as we dont take a reference */
struct napi_struct *napi_by_id(unsigned int napi_id)
@@ -4469,10 +4497,23 @@ void napi_hash_del(struct napi_struct *napi)
}
EXPORT_SYMBOL_GPL(napi_hash_del);
+static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
+{
+ struct napi_struct *napi;
+
+ napi = container_of(timer, struct napi_struct, timer);
+ if (napi->gro_list)
+ napi_schedule(napi);
+
+ return HRTIMER_NORESTART;
+}
+
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
INIT_LIST_HEAD(&napi->poll_list);
+ hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+ napi->timer.function = napi_watchdog;
napi->gro_count = 0;
napi->gro_list = NULL;
napi->skb = NULL;
@@ -4491,6 +4532,20 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
}
EXPORT_SYMBOL(netif_napi_add);
+void napi_disable(struct napi_struct *n)
+{
+ might_sleep();
+ set_bit(NAPI_STATE_DISABLE, &n->state);
+
+ while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
+ msleep(1);
+
+ hrtimer_cancel(&n->timer);
+
+ clear_bit(NAPI_STATE_DISABLE, &n->state);
+}
+EXPORT_SYMBOL(napi_disable);
+
void netif_napi_del(struct napi_struct *napi)
{
list_del_init(&napi->dev_list);
@@ -4507,29 +4562,28 @@ static void net_rx_action(struct softirq_action *h)
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
+ LIST_HEAD(list);
+ LIST_HEAD(repoll);
void *have;
local_irq_disable();
+ list_splice_init(&sd->poll_list, &list);
+ local_irq_enable();
- while (!list_empty(&sd->poll_list)) {
+ while (!list_empty(&list)) {
struct napi_struct *n;
int work, weight;
- /* If softirq window is exhuasted then punt.
+ /* If softirq window is exhausted then punt.
* Allow this to run for 2 jiffies since which will allow
* an average latency of 1.5/HZ.
*/
if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit)))
goto softnet_break;
- local_irq_enable();
- /* Even though interrupts have been re-enabled, this
- * access is safe because interrupts can only add new
- * entries to the tail of this list, and only ->poll()
- * calls can remove this head entry from the list.
- */
- n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
+ n = list_first_entry(&list, struct napi_struct, poll_list);
+ list_del_init(&n->poll_list);
have = netpoll_poll_lock(n);
@@ -4551,8 +4605,6 @@ static void net_rx_action(struct softirq_action *h)
budget -= work;
- local_irq_disable();
-
/* Drivers must not modify the NAPI state if they
* consume the entire weight. In such cases this code
* still "owns" the NAPI instance and therefore can
@@ -4560,32 +4612,40 @@ static void net_rx_action(struct softirq_action *h)
*/
if (unlikely(work == weight)) {
if (unlikely(napi_disable_pending(n))) {
- local_irq_enable();
napi_complete(n);
- local_irq_disable();
} else {
if (n->gro_list) {
/* flush too old packets
* If HZ < 1000, flush all packets.
*/
- local_irq_enable();
napi_gro_flush(n, HZ >= 1000);
- local_irq_disable();
}
- list_move_tail(&n->poll_list, &sd->poll_list);
+ list_add_tail(&n->poll_list, &repoll);
}
}
netpoll_poll_unlock(have);
}
+
+ if (!sd_has_rps_ipi_waiting(sd) &&
+ list_empty(&list) &&
+ list_empty(&repoll))
+ return;
out:
+ local_irq_disable();
+
+ list_splice_tail_init(&sd->poll_list, &list);
+ list_splice_tail(&repoll, &list);
+ list_splice(&list, &sd->poll_list);
+ if (!list_empty(&sd->poll_list))
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+
net_rps_action_and_irq_enable(sd);
return;
softnet_break:
sd->time_squeeze++;
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
@@ -5786,7 +5846,7 @@ EXPORT_SYMBOL(dev_change_carrier);
* Get device physical port ID
*/
int dev_get_phys_port_id(struct net_device *dev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -5865,6 +5925,8 @@ static void rollback_registered_many(struct list_head *head)
synchronize_net();
list_for_each_entry(dev, head, unreg_list) {
+ struct sk_buff *skb = NULL;
+
/* Shutdown queueing discipline. */
dev_shutdown(dev);
@@ -5874,6 +5936,11 @@ static void rollback_registered_many(struct list_head *head)
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ if (!dev->rtnl_link_ops ||
+ dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+ skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U,
+ GFP_KERNEL);
+
/*
* Flush the unicast and multicast chains
*/
@@ -5883,9 +5950,8 @@ static void rollback_registered_many(struct list_head *head)
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
- if (!dev->rtnl_link_ops ||
- dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
- rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+ if (skb)
+ rtmsg_ifinfo_send(skb, dev, GFP_KERNEL);
/* Notifier chain MUST detach us all upper devices. */
WARN_ON(netdev_has_any_upper_dev(dev));
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index b6b230600b97..c0548d268e1a 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -278,8 +278,8 @@ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
EXPORT_SYMBOL(__hw_addr_sync_dev);
/**
- * __hw_addr_unsync_dev - Remove synchonized addresses from device
- * @list: address list to remove syncronized addresses from
+ * __hw_addr_unsync_dev - Remove synchronized addresses from device
+ * @list: address list to remove synchronized addresses from
* @dev: device to sync
* @unsync: function to call if address should be removed
*
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 72e899a3efda..b94b1d293506 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -142,10 +142,12 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm
case SIOCGIFHWADDR:
if (!dev->addr_len)
- memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ memset(ifr->ifr_hwaddr.sa_data, 0,
+ sizeof(ifr->ifr_hwaddr.sa_data));
else
memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ min(sizeof(ifr->ifr_hwaddr.sa_data),
+ (size_t)dev->addr_len));
ifr->ifr_hwaddr.sa_family = dev->type;
return 0;
@@ -265,7 +267,8 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
if (ifr->ifr_hwaddr.sa_family != dev->type)
return -EINVAL;
memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ min(sizeof(ifr->ifr_hwaddr.sa_data),
+ (size_t)dev->addr_len));
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return 0;
diff --git a/net/core/dst.c b/net/core/dst.c
index a028409ee438..e956ce6d1378 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -327,30 +327,6 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
}
EXPORT_SYMBOL(__dst_destroy_metrics_generic);
-/**
- * __skb_dst_set_noref - sets skb dst, without a reference
- * @skb: buffer
- * @dst: dst entry
- * @force: if force is set, use noref version even for DST_NOCACHE entries
- *
- * Sets skb dst, assuming a reference was not taken on dst
- * skb_dst_drop() should not dst_release() this dst
- */
-void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
-{
- WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
- /* If dst not in cache, we must take a reference, because
- * dst_release() will destroy dst as soon as its refcount becomes zero
- */
- if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
- dst_hold(dst);
- skb_dst_set(skb, dst);
- } else {
- skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
- }
-}
-EXPORT_SYMBOL(__skb_dst_set_noref);
-
/* Dirty hack. We did it in 2.2 (in __dst_free),
* we have _very_ good reasons not to repeat
* this mistake in 2.3, but we have no choice
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 06dfb293e5aa..550892cd6b3f 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include <linux/sched.h>
+#include <linux/net.h>
/*
* Some useful ethtool_ops methods that're device independent.
@@ -84,7 +85,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation",
[NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation",
[NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation",
- [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation",
[NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc",
[NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp",
@@ -100,6 +100,12 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
[NETIF_F_BUSY_POLL_BIT] = "busy-poll",
};
+static const char
+rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
+ [ETH_RSS_HASH_TOP_BIT] = "toeplitz",
+ [ETH_RSS_HASH_XOR_BIT] = "xor",
+};
+
static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
{
struct ethtool_gfeatures cmd = {
@@ -185,6 +191,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
if (sset == ETH_SS_FEATURES)
return ARRAY_SIZE(netdev_features_strings);
+ if (sset == ETH_SS_RSS_HASH_FUNCS)
+ return ARRAY_SIZE(rss_hash_func_strings);
+
if (ops->get_sset_count && ops->get_strings)
return ops->get_sset_count(dev, sset);
else
@@ -199,6 +208,9 @@ static void __ethtool_get_strings(struct net_device *dev,
if (stringset == ETH_SS_FEATURES)
memcpy(data, netdev_features_strings,
sizeof(netdev_features_strings));
+ else if (stringset == ETH_SS_RSS_HASH_FUNCS)
+ memcpy(data, rss_hash_func_strings,
+ sizeof(rss_hash_func_strings));
else
/* ops->get_strings is valid because checked earlier */
ops->get_strings(dev, stringset, data);
@@ -574,6 +586,16 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
return 0;
}
+u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+
+void netdev_rss_key_fill(void *buffer, size_t len)
+{
+ BUG_ON(len > sizeof(netdev_rss_key));
+ net_get_random_once(netdev_rss_key, sizeof(netdev_rss_key));
+ memcpy(buffer, netdev_rss_key, len);
+}
+EXPORT_SYMBOL(netdev_rss_key_fill);
+
static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
void __user *useraddr)
{
@@ -608,7 +630,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
if (!indir)
return -ENOMEM;
- ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
+ ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL);
if (ret)
goto out;
@@ -669,7 +691,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
goto out;
}
- ret = ops->set_rxfh(dev, indir, NULL);
+ ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE);
out:
kfree(indir);
@@ -687,12 +709,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
u32 total_size;
u32 indir_bytes;
u32 *indir = NULL;
+ u8 dev_hfunc = 0;
u8 *hkey = NULL;
u8 *rss_config;
- if (!(dev->ethtool_ops->get_rxfh_indir_size ||
- dev->ethtool_ops->get_rxfh_key_size) ||
- !dev->ethtool_ops->get_rxfh)
+ if (!ops->get_rxfh)
return -EOPNOTSUPP;
if (ops->get_rxfh_indir_size)
@@ -700,16 +721,14 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
if (ops->get_rxfh_key_size)
dev_key_size = ops->get_rxfh_key_size(dev);
- if ((dev_key_size + dev_indir_size) == 0)
- return -EOPNOTSUPP;
-
if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
return -EFAULT;
user_indir_size = rxfh.indir_size;
user_key_size = rxfh.key_size;
/* Check that reserved fields are 0 for now */
- if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+ if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+ rxfh.rsvd8[2] || rxfh.rsvd32)
return -EINVAL;
rxfh.indir_size = dev_indir_size;
@@ -717,13 +736,6 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
return -EFAULT;
- /* If the user buffer size is 0, this is just a query for the
- * device table size and key size. Otherwise, if the User size is
- * not equal to device table size or key size it's an error.
- */
- if (!user_indir_size && !user_key_size)
- return 0;
-
if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
(user_key_size && (user_key_size != dev_key_size)))
return -EINVAL;
@@ -740,14 +752,19 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
if (user_key_size)
hkey = rss_config + indir_bytes;
- ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey);
- if (!ret) {
- if (copy_to_user(useraddr +
- offsetof(struct ethtool_rxfh, rss_config[0]),
- rss_config, total_size))
- ret = -EFAULT;
- }
+ ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc);
+ if (ret)
+ goto out;
+ if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc),
+ &dev_hfunc, sizeof(rxfh.hfunc))) {
+ ret = -EFAULT;
+ } else if (copy_to_user(useraddr +
+ offsetof(struct ethtool_rxfh, rss_config[0]),
+ rss_config, total_size)) {
+ ret = -EFAULT;
+ }
+out:
kfree(rss_config);
return ret;
@@ -766,33 +783,31 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
u8 *rss_config;
u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
- if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
- !ops->get_rxnfc || !ops->set_rxfh)
+ if (!ops->get_rxnfc || !ops->set_rxfh)
return -EOPNOTSUPP;
if (ops->get_rxfh_indir_size)
dev_indir_size = ops->get_rxfh_indir_size(dev);
if (ops->get_rxfh_key_size)
dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
- if ((dev_key_size + dev_indir_size) == 0)
- return -EOPNOTSUPP;
if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
return -EFAULT;
/* Check that reserved fields are 0 for now */
- if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+ if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
+ rxfh.rsvd8[2] || rxfh.rsvd32)
return -EINVAL;
- /* If either indir or hash key is valid, proceed further.
- * It is not valid to request that both be unchanged.
+ /* If either indir, hash key or function is valid, proceed further.
+ * Must request at least one change: indir size, hash key or function.
*/
if ((rxfh.indir_size &&
rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
rxfh.indir_size != dev_indir_size) ||
(rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
(rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
- rxfh.key_size == 0))
+ rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE))
return -EINVAL;
if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
@@ -835,7 +850,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
}
}
- ret = ops->set_rxfh(dev, indir, hkey);
+ ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc);
out:
kfree(rss_config);
diff --git a/net/core/filter.c b/net/core/filter.c
index 647b12265e18..ec9baea10c16 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -44,6 +44,7 @@
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
+#include <linux/bpf.h>
/**
* sk_filter - run a packet through a socket filter
@@ -813,8 +814,12 @@ static void bpf_release_orig_filter(struct bpf_prog *fp)
static void __bpf_prog_release(struct bpf_prog *prog)
{
- bpf_release_orig_filter(prog);
- bpf_prog_free(prog);
+ if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
+ bpf_prog_put(prog);
+ } else {
+ bpf_release_orig_filter(prog);
+ bpf_prog_free(prog);
+ }
}
static void __sk_filter_release(struct sk_filter *fp)
@@ -1088,6 +1093,94 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
+#ifdef CONFIG_BPF_SYSCALL
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+ struct sk_filter *fp, *old_fp;
+ struct bpf_prog *prog;
+
+ if (sock_flag(sk, SOCK_FILTER_LOCKED))
+ return -EPERM;
+
+ prog = bpf_prog_get(ufd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ /* valid fd, but invalid program type */
+ bpf_prog_put(prog);
+ return -EINVAL;
+ }
+
+ fp = kmalloc(sizeof(*fp), GFP_KERNEL);
+ if (!fp) {
+ bpf_prog_put(prog);
+ return -ENOMEM;
+ }
+ fp->prog = prog;
+
+ atomic_set(&fp->refcnt, 0);
+
+ if (!sk_filter_charge(sk, fp)) {
+ __sk_filter_release(fp);
+ return -ENOMEM;
+ }
+
+ old_fp = rcu_dereference_protected(sk->sk_filter,
+ sock_owned_by_user(sk));
+ rcu_assign_pointer(sk->sk_filter, fp);
+
+ if (old_fp)
+ sk_filter_uncharge(sk, old_fp);
+
+ return 0;
+}
+
+/* allow socket filters to call
+ * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
+ */
+static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_map_lookup_elem:
+ return &bpf_map_lookup_elem_proto;
+ case BPF_FUNC_map_update_elem:
+ return &bpf_map_update_elem_proto;
+ case BPF_FUNC_map_delete_elem:
+ return &bpf_map_delete_elem_proto;
+ default:
+ return NULL;
+ }
+}
+
+static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ /* skb fields cannot be accessed yet */
+ return false;
+}
+
+static struct bpf_verifier_ops sock_filter_ops = {
+ .get_func_proto = sock_filter_func_proto,
+ .is_valid_access = sock_filter_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl = {
+ .ops = &sock_filter_ops,
+ .type = BPF_PROG_TYPE_SOCKET_FILTER,
+};
+
+static int __init register_sock_filter_ops(void)
+{
+ bpf_register_prog_type(&tl);
+ return 0;
+}
+late_initcall(register_sock_filter_ops);
+#else
+int sk_attach_bpf(u32 ufd, struct sock *sk)
+{
+ return -EOPNOTSUPP;
+}
+#endif
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/iovec.c b/net/core/iovec.c
index e1ec45ab1e63..dcbe98b3726a 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -28,53 +28,6 @@
#include <net/sock.h>
/*
- * Verify iovec. The caller must ensure that the iovec is big enough
- * to hold the message iovec.
- *
- * Save time not doing access_ok. copy_*_user will make this work
- * in any case.
- */
-
-int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode)
-{
- int size, ct, err;
-
- if (m->msg_name && m->msg_namelen) {
- if (mode == VERIFY_READ) {
- void __user *namep;
- namep = (void __user __force *) m->msg_name;
- err = move_addr_to_kernel(namep, m->msg_namelen,
- address);
- if (err < 0)
- return err;
- }
- m->msg_name = address;
- } else {
- m->msg_name = NULL;
- m->msg_namelen = 0;
- }
-
- size = m->msg_iovlen * sizeof(struct iovec);
- if (copy_from_user(iov, (void __user __force *) m->msg_iov, size))
- return -EFAULT;
-
- m->msg_iov = iov;
- err = 0;
-
- for (ct = 0; ct < m->msg_iovlen; ct++) {
- size_t len = iov[ct].iov_len;
-
- if (len > INT_MAX - err) {
- len = INT_MAX - err;
- iov[ct].iov_len = len;
- }
- err += len;
- }
-
- return err;
-}
-
-/*
* And now for the all-in-one: copy and checksum from a user iovec
* directly to a datagram
* Calls to csum_partial but the last must be in 32 bit chunks
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index bd0767e6b2b3..49a9e3e06c08 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -21,7 +21,7 @@
#include <linux/spinlock.h>
#include <linux/workqueue.h>
#include <linux/bitops.h>
-#include <asm/types.h>
+#include <linux/types.h>
enum lw_bits {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index ef31fef25e5a..8e38f17288d3 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -56,7 +56,6 @@ static void __neigh_notify(struct neighbour *n, int type, int flags);
static void neigh_update_notify(struct neighbour *neigh);
static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
-static struct neigh_table *neigh_tables;
#ifdef CONFIG_PROC_FS
static const struct file_operations neigh_stat_seq_fops;
#endif
@@ -87,13 +86,8 @@ static const struct file_operations neigh_stat_seq_fops;
the most complicated procedure, which we allow is dev->hard_header.
It is supposed, that dev->hard_header is simplistic and does
not make callbacks to neighbour tables.
-
- The last lock is neigh_tbl_lock. It is pure SMP lock, protecting
- list of neighbour tables. This list is used only in process context,
*/
-static DEFINE_RWLOCK(neigh_tbl_lock);
-
static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
{
kfree_skb(skb);
@@ -773,7 +767,7 @@ static void neigh_periodic_work(struct work_struct *work)
if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
struct neigh_parms *p;
tbl->last_rand = jiffies;
- for (p = &tbl->parms; p; p = p->next)
+ list_for_each_entry(p, &tbl->parms_list, list)
p->reachable_time =
neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
}
@@ -1446,7 +1440,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
{
struct neigh_parms *p;
- for (p = &tbl->parms; p; p = p->next) {
+ list_for_each_entry(p, &tbl->parms_list, list) {
if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) ||
(!p->dev && !ifindex && net_eq(net, &init_net)))
return p;
@@ -1481,8 +1475,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
}
write_lock_bh(&tbl->lock);
- p->next = tbl->parms.next;
- tbl->parms.next = p;
+ list_add(&p->list, &tbl->parms.list);
write_unlock_bh(&tbl->lock);
neigh_parms_data_state_cleanall(p);
@@ -1501,24 +1494,15 @@ static void neigh_rcu_free_parms(struct rcu_head *head)
void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
{
- struct neigh_parms **p;
-
if (!parms || parms == &tbl->parms)
return;
write_lock_bh(&tbl->lock);
- for (p = &tbl->parms.next; *p; p = &(*p)->next) {
- if (*p == parms) {
- *p = parms->next;
- parms->dead = 1;
- write_unlock_bh(&tbl->lock);
- if (parms->dev)
- dev_put(parms->dev);
- call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
- return;
- }
- }
+ list_del(&parms->list);
+ parms->dead = 1;
write_unlock_bh(&tbl->lock);
- neigh_dbg(1, "%s: not found\n", __func__);
+ if (parms->dev)
+ dev_put(parms->dev);
+ call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
}
EXPORT_SYMBOL(neigh_parms_release);
@@ -1530,11 +1514,15 @@ static void neigh_parms_destroy(struct neigh_parms *parms)
static struct lock_class_key neigh_table_proxy_queue_class;
-static void neigh_table_init_no_netlink(struct neigh_table *tbl)
+static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly;
+
+void neigh_table_init(int index, struct neigh_table *tbl)
{
unsigned long now = jiffies;
unsigned long phsize;
+ INIT_LIST_HEAD(&tbl->parms_list);
+ list_add(&tbl->parms.list, &tbl->parms_list);
write_pnet(&tbl->parms.net, &init_net);
atomic_set(&tbl->parms.refcnt, 1);
tbl->parms.reachable_time =
@@ -1574,34 +1562,14 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
tbl->last_flush = now;
tbl->last_rand = now + tbl->parms.reachable_time * 20;
-}
-
-void neigh_table_init(struct neigh_table *tbl)
-{
- struct neigh_table *tmp;
-
- neigh_table_init_no_netlink(tbl);
- write_lock(&neigh_tbl_lock);
- for (tmp = neigh_tables; tmp; tmp = tmp->next) {
- if (tmp->family == tbl->family)
- break;
- }
- tbl->next = neigh_tables;
- neigh_tables = tbl;
- write_unlock(&neigh_tbl_lock);
- if (unlikely(tmp)) {
- pr_err("Registering multiple tables for family %d\n",
- tbl->family);
- dump_stack();
- }
+ neigh_tables[index] = tbl;
}
EXPORT_SYMBOL(neigh_table_init);
-int neigh_table_clear(struct neigh_table *tbl)
+int neigh_table_clear(int index, struct neigh_table *tbl)
{
- struct neigh_table **tp;
-
+ neigh_tables[index] = NULL;
/* It is not clean... Fix it to unload IPv6 module safely */
cancel_delayed_work_sync(&tbl->gc_work);
del_timer_sync(&tbl->proxy_timer);
@@ -1609,14 +1577,6 @@ int neigh_table_clear(struct neigh_table *tbl)
neigh_ifdown(tbl, NULL);
if (atomic_read(&tbl->entries))
pr_crit("neighbour leakage\n");
- write_lock(&neigh_tbl_lock);
- for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
- if (*tp == tbl) {
- *tp = tbl->next;
- break;
- }
- }
- write_unlock(&neigh_tbl_lock);
call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu,
neigh_hash_free_rcu);
@@ -1634,12 +1594,32 @@ int neigh_table_clear(struct neigh_table *tbl)
}
EXPORT_SYMBOL(neigh_table_clear);
+static struct neigh_table *neigh_find_table(int family)
+{
+ struct neigh_table *tbl = NULL;
+
+ switch (family) {
+ case AF_INET:
+ tbl = neigh_tables[NEIGH_ARP_TABLE];
+ break;
+ case AF_INET6:
+ tbl = neigh_tables[NEIGH_ND_TABLE];
+ break;
+ case AF_DECnet:
+ tbl = neigh_tables[NEIGH_DN_TABLE];
+ break;
+ }
+
+ return tbl;
+}
+
static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
struct nlattr *dst_attr;
struct neigh_table *tbl;
+ struct neighbour *neigh;
struct net_device *dev = NULL;
int err = -EINVAL;
@@ -1660,39 +1640,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh)
}
}
- read_lock(&neigh_tbl_lock);
- for (tbl = neigh_tables; tbl; tbl = tbl->next) {
- struct neighbour *neigh;
+ tbl = neigh_find_table(ndm->ndm_family);
+ if (tbl == NULL)
+ return -EAFNOSUPPORT;
- if (tbl->family != ndm->ndm_family)
- continue;
- read_unlock(&neigh_tbl_lock);
-
- if (nla_len(dst_attr) < tbl->key_len)
- goto out;
-
- if (ndm->ndm_flags & NTF_PROXY) {
- err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
- goto out;
- }
+ if (nla_len(dst_attr) < tbl->key_len)
+ goto out;
- if (dev == NULL)
- goto out;
+ if (ndm->ndm_flags & NTF_PROXY) {
+ err = pneigh_delete(tbl, net, nla_data(dst_attr), dev);
+ goto out;
+ }
- neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
- if (neigh == NULL) {
- err = -ENOENT;
- goto out;
- }
+ if (dev == NULL)
+ goto out;
- err = neigh_update(neigh, NULL, NUD_FAILED,
- NEIGH_UPDATE_F_OVERRIDE |
- NEIGH_UPDATE_F_ADMIN);
- neigh_release(neigh);
+ neigh = neigh_lookup(tbl, nla_data(dst_attr), dev);
+ if (neigh == NULL) {
+ err = -ENOENT;
goto out;
}
- read_unlock(&neigh_tbl_lock);
- err = -EAFNOSUPPORT;
+
+ err = neigh_update(neigh, NULL, NUD_FAILED,
+ NEIGH_UPDATE_F_OVERRIDE |
+ NEIGH_UPDATE_F_ADMIN);
+ neigh_release(neigh);
out:
return err;
@@ -1700,11 +1672,14 @@ out:
static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
+ int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
struct neigh_table *tbl;
struct net_device *dev = NULL;
+ struct neighbour *neigh;
+ void *dst, *lladdr;
int err;
ASSERT_RTNL();
@@ -1728,70 +1703,60 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh)
goto out;
}
- read_lock(&neigh_tbl_lock);
- for (tbl = neigh_tables; tbl; tbl = tbl->next) {
- int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE;
- struct neighbour *neigh;
- void *dst, *lladdr;
+ tbl = neigh_find_table(ndm->ndm_family);
+ if (tbl == NULL)
+ return -EAFNOSUPPORT;
- if (tbl->family != ndm->ndm_family)
- continue;
- read_unlock(&neigh_tbl_lock);
+ if (nla_len(tb[NDA_DST]) < tbl->key_len)
+ goto out;
+ dst = nla_data(tb[NDA_DST]);
+ lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
- if (nla_len(tb[NDA_DST]) < tbl->key_len)
- goto out;
- dst = nla_data(tb[NDA_DST]);
- lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL;
+ if (ndm->ndm_flags & NTF_PROXY) {
+ struct pneigh_entry *pn;
- if (ndm->ndm_flags & NTF_PROXY) {
- struct pneigh_entry *pn;
+ err = -ENOBUFS;
+ pn = pneigh_lookup(tbl, net, dst, dev, 1);
+ if (pn) {
+ pn->flags = ndm->ndm_flags;
+ err = 0;
+ }
+ goto out;
+ }
- err = -ENOBUFS;
- pn = pneigh_lookup(tbl, net, dst, dev, 1);
- if (pn) {
- pn->flags = ndm->ndm_flags;
- err = 0;
- }
+ if (dev == NULL)
+ goto out;
+
+ neigh = neigh_lookup(tbl, dst, dev);
+ if (neigh == NULL) {
+ if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
+ err = -ENOENT;
goto out;
}
- if (dev == NULL)
+ neigh = __neigh_lookup_errno(tbl, dst, dev);
+ if (IS_ERR(neigh)) {
+ err = PTR_ERR(neigh);
+ goto out;
+ }
+ } else {
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ err = -EEXIST;
+ neigh_release(neigh);
goto out;
-
- neigh = neigh_lookup(tbl, dst, dev);
- if (neigh == NULL) {
- if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
- err = -ENOENT;
- goto out;
- }
-
- neigh = __neigh_lookup_errno(tbl, dst, dev);
- if (IS_ERR(neigh)) {
- err = PTR_ERR(neigh);
- goto out;
- }
- } else {
- if (nlh->nlmsg_flags & NLM_F_EXCL) {
- err = -EEXIST;
- neigh_release(neigh);
- goto out;
- }
-
- if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
- flags &= ~NEIGH_UPDATE_F_OVERRIDE;
}
- if (ndm->ndm_flags & NTF_USE) {
- neigh_event_send(neigh, NULL);
- err = 0;
- } else
- err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
- neigh_release(neigh);
- goto out;
+ if (!(nlh->nlmsg_flags & NLM_F_REPLACE))
+ flags &= ~NEIGH_UPDATE_F_OVERRIDE;
}
- read_unlock(&neigh_tbl_lock);
- err = -EAFNOSUPPORT;
+ if (ndm->ndm_flags & NTF_USE) {
+ neigh_event_send(neigh, NULL);
+ err = 0;
+ } else
+ err = neigh_update(neigh, lladdr, ndm->ndm_state, flags);
+ neigh_release(neigh);
+
out:
return err;
}
@@ -1990,7 +1955,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
struct neigh_table *tbl;
struct ndtmsg *ndtmsg;
struct nlattr *tb[NDTA_MAX+1];
- int err;
+ bool found = false;
+ int err, tidx;
err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
nl_neightbl_policy);
@@ -2003,19 +1969,21 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
}
ndtmsg = nlmsg_data(nlh);
- read_lock(&neigh_tbl_lock);
- for (tbl = neigh_tables; tbl; tbl = tbl->next) {
+
+ for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
+ tbl = neigh_tables[tidx];
+ if (!tbl)
+ continue;
if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
continue;
-
- if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
+ if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) {
+ found = true;
break;
+ }
}
- if (tbl == NULL) {
- err = -ENOENT;
- goto errout_locked;
- }
+ if (!found)
+ return -ENOENT;
/*
* We acquire tbl->lock to be nice to the periodic timers and
@@ -2126,8 +2094,6 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
errout_tbl_lock:
write_unlock_bh(&tbl->lock);
-errout_locked:
- read_unlock(&neigh_tbl_lock);
errout:
return err;
}
@@ -2142,10 +2108,13 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
- read_lock(&neigh_tbl_lock);
- for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
+ for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
struct neigh_parms *p;
+ tbl = neigh_tables[tidx];
+ if (!tbl)
+ continue;
+
if (tidx < tbl_skip || (family && tbl->family != family))
continue;
@@ -2154,7 +2123,9 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
NLM_F_MULTI) <= 0)
break;
- for (nidx = 0, p = tbl->parms.next; p; p = p->next) {
+ nidx = 0;
+ p = list_next_entry(&tbl->parms, list);
+ list_for_each_entry_from(p, &tbl->parms_list, list) {
if (!net_eq(neigh_parms_net(p), net))
continue;
@@ -2174,7 +2145,6 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
neigh_skip = 0;
}
out:
- read_unlock(&neigh_tbl_lock);
cb->args[0] = tidx;
cb->args[1] = nidx;
@@ -2357,7 +2327,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
int proxy = 0;
int err;
- read_lock(&neigh_tbl_lock);
family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
/* check for full ndmsg structure presence, family member is
@@ -2369,8 +2338,11 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
s_t = cb->args[0];
- for (tbl = neigh_tables, t = 0; tbl;
- tbl = tbl->next, t++) {
+ for (t = 0; t < NEIGH_NR_TABLES; t++) {
+ tbl = neigh_tables[t];
+
+ if (!tbl)
+ continue;
if (t < s_t || (family && tbl->family != family))
continue;
if (t > s_t)
@@ -2383,7 +2355,6 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
if (err < 0)
break;
}
- read_unlock(&neigh_tbl_lock);
cb->args[0] = t;
return skb->len;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9dd06699b09c..999341244434 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -12,6 +12,7 @@
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <net/switchdev.h>
#include <linux/if_arp.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
@@ -325,6 +326,23 @@ static ssize_t tx_queue_len_store(struct device *dev,
}
NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong);
+static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
+{
+ dev->gro_flush_timeout = val;
+ return 0;
+}
+
+static ssize_t gro_flush_timeout_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ return netdev_store(dev, attr, buf, len, change_gro_flush_timeout);
+}
+NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong);
+
static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
@@ -387,7 +405,7 @@ static ssize_t phys_port_id_show(struct device *dev,
return restart_syscall();
if (dev_isalive(netdev)) {
- struct netdev_phys_port_id ppid;
+ struct netdev_phys_item_id ppid;
ret = dev_get_phys_port_id(netdev, &ppid);
if (!ret)
@@ -399,6 +417,28 @@ static ssize_t phys_port_id_show(struct device *dev,
}
static DEVICE_ATTR_RO(phys_port_id);
+static ssize_t phys_switch_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ ssize_t ret = -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (dev_isalive(netdev)) {
+ struct netdev_phys_item_id ppid;
+
+ ret = netdev_switch_parent_id_get(netdev, &ppid);
+ if (!ret)
+ ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
+ }
+ rtnl_unlock();
+
+ return ret;
+}
+static DEVICE_ATTR_RO(phys_switch_id);
+
static struct attribute *net_class_attrs[] = {
&dev_attr_netdev_group.attr,
&dev_attr_type.attr,
@@ -422,7 +462,9 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_mtu.attr,
&dev_attr_flags.attr,
&dev_attr_tx_queue_len.attr,
+ &dev_attr_gro_flush_timeout.attr,
&dev_attr_phys_port_id.attr,
+ &dev_attr_phys_switch_id.attr,
NULL,
};
ATTRIBUTE_GROUPS(net_class);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e6645b4f330a..e0ad5d16c9c5 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -79,8 +79,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
if (vlan_tx_tag_present(skb) &&
!vlan_hw_offload_capable(features, skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto,
- vlan_tx_tag_get(skb));
+ skb = __vlan_hwaccel_push_inside(skb);
if (unlikely(!skb)) {
/* This is actually a packet drop, but we
* don't want the code that calls this
@@ -88,7 +87,6 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
*/
goto out;
}
- skb->vlan_tci = 0;
}
status = netdev_start_xmit(skb, dev, txq, false);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 443256bdcddc..da934fc3faa8 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3728,8 +3728,7 @@ static int pktgen_remove_device(struct pktgen_thread *t,
/* Remove proc before if_list entry, because add_device uses
* list to determine if interface already exist, avoid race
* with proc_create_data() */
- if (pkt_dev->entry)
- proc_remove(pkt_dev->entry);
+ proc_remove(pkt_dev->entry);
/* And update the thread if_list */
_rem_dev_from_if_list(t, pkt_dev);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 88e8de3b59b0..d06107d36ec8 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -36,6 +36,7 @@
#include <linux/mutex.h>
#include <linux/if_addr.h>
#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
#include <linux/pci.h>
#include <linux/etherdevice.h>
@@ -43,6 +44,7 @@
#include <linux/inet.h>
#include <linux/netdevice.h>
+#include <net/switchdev.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
@@ -868,7 +870,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
- + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -952,7 +955,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
- struct netdev_phys_port_id ppid;
+ struct netdev_phys_item_id ppid;
err = dev_get_phys_port_id(dev, &ppid);
if (err) {
@@ -967,6 +970,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
return 0;
}
+static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+ int err;
+ struct netdev_phys_item_id psid;
+
+ err = netdev_switch_parent_id_get(dev, &psid);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask)
@@ -1039,6 +1060,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (rtnl_phys_port_id_fill(skb, dev))
goto nla_put_failure;
+ if (rtnl_phys_switch_id_fill(skb, dev))
+ goto nla_put_failure;
+
attr = nla_reserve(skb, IFLA_STATS,
sizeof(struct rtnl_link_stats));
if (attr == NULL)
@@ -1196,8 +1220,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_PROMISCUITY] = { .type = NLA_U32 },
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
- [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+ [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
+ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2221,8 +2246,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
- gfp_t flags)
+struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
+ unsigned int change, gfp_t flags)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -2240,11 +2265,28 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
kfree_skb(skb);
goto errout;
}
- rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
- return;
+ return skb;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+ return NULL;
+}
+
+void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags)
+{
+ struct net *net = dev_net(dev);
+
+ rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags);
+}
+
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change,
+ gfp_t flags)
+{
+ struct sk_buff *skb;
+
+ skb = rtmsg_ifinfo_build_skb(type, dev, change, flags);
+ if (skb)
+ rtmsg_ifinfo_send(skb, dev, flags);
}
EXPORT_SYMBOL(rtmsg_ifinfo);
@@ -2313,7 +2355,7 @@ errout:
int ndo_dflt_fdb_add(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
- const unsigned char *addr,
+ const unsigned char *addr, u16 vid,
u16 flags)
{
int err = -EINVAL;
@@ -2339,6 +2381,28 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm,
}
EXPORT_SYMBOL(ndo_dflt_fdb_add);
+static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid)
+{
+ u16 vid = 0;
+
+ if (vlan_attr) {
+ if (nla_len(vlan_attr) != sizeof(u16)) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n");
+ return -EINVAL;
+ }
+
+ vid = nla_get_u16(vlan_attr);
+
+ if (!vid || vid >= VLAN_VID_MASK) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n",
+ vid);
+ return -EINVAL;
+ }
+ }
+ *p_vid = vid;
+ return 0;
+}
+
static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
@@ -2346,6 +2410,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
struct nlattr *tb[NDA_MAX+1];
struct net_device *dev;
u8 *addr;
+ u16 vid;
int err;
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2371,6 +2436,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
addr = nla_data(tb[NDA_LLADDR]);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ if (err)
+ return err;
+
err = -EOPNOTSUPP;
/* Support fdb on master device the net/bridge default case */
@@ -2379,7 +2448,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
const struct net_device_ops *ops = br_dev->netdev_ops;
- err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags);
+ err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid,
+ nlh->nlmsg_flags);
if (err)
goto out;
else
@@ -2390,9 +2460,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
if ((ndm->ndm_flags & NTF_SELF)) {
if (dev->netdev_ops->ndo_fdb_add)
err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr,
+ vid,
nlh->nlmsg_flags);
else
- err = ndo_dflt_fdb_add(ndm, tb, dev, addr,
+ err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid,
nlh->nlmsg_flags);
if (!err) {
@@ -2410,7 +2481,7 @@ out:
int ndo_dflt_fdb_del(struct ndmsg *ndm,
struct nlattr *tb[],
struct net_device *dev,
- const unsigned char *addr)
+ const unsigned char *addr, u16 vid)
{
int err = -EINVAL;
@@ -2439,6 +2510,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
struct net_device *dev;
int err = -EINVAL;
__u8 *addr;
+ u16 vid;
if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
@@ -2466,6 +2538,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
addr = nla_data(tb[NDA_LLADDR]);
+ err = fdb_vid_parse(tb[NDA_VLAN], &vid);
+ if (err)
+ return err;
+
err = -EOPNOTSUPP;
/* Support fdb on master device the net/bridge default case */
@@ -2475,7 +2551,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
const struct net_device_ops *ops = br_dev->netdev_ops;
if (ops->ndo_fdb_del)
- err = ops->ndo_fdb_del(ndm, tb, dev, addr);
+ err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
if (err)
goto out;
@@ -2486,9 +2562,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh)
/* Embedded bridge, macvlan, and any other device support */
if (ndm->ndm_flags & NTF_SELF) {
if (dev->netdev_ops->ndo_fdb_del)
- err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr);
+ err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
+ vid);
else
- err = ndo_dflt_fdb_del(ndm, tb, dev, addr);
+ err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
if (!err) {
rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
@@ -2628,12 +2705,22 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
+static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask,
+ unsigned int attrnum, unsigned int flag)
+{
+ if (mask & flag)
+ return nla_put_u8(skb, attrnum, !!(flags & flag));
+ return 0;
+}
+
int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
- struct net_device *dev, u16 mode)
+ struct net_device *dev, u16 mode,
+ u32 flags, u32 mask)
{
struct nlmsghdr *nlh;
struct ifinfomsg *ifm;
struct nlattr *br_afspec;
+ struct nlattr *protinfo;
u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
@@ -2665,13 +2752,46 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
if (!br_afspec)
goto nla_put_failure;
- if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) ||
- nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+ if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF)) {
nla_nest_cancel(skb, br_afspec);
goto nla_put_failure;
}
+
+ if (mode != BRIDGE_MODE_UNDEF) {
+ if (nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) {
+ nla_nest_cancel(skb, br_afspec);
+ goto nla_put_failure;
+ }
+ }
nla_nest_end(skb, br_afspec);
+ protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+ if (!protinfo)
+ goto nla_put_failure;
+
+ if (brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_GUARD, BR_BPDU_GUARD) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_FAST_LEAVE,
+ BR_MULTICAST_FAST_LEAVE) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_LEARNING, BR_LEARNING) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) ||
+ brport_nla_put_flag(skb, flags, mask,
+ IFLA_BRPORT_PROXYARP, BR_PROXYARP)) {
+ nla_nest_cancel(skb, protinfo);
+ goto nla_put_failure;
+ }
+
+ nla_nest_end(skb, protinfo);
+
return nlmsg_end(skb, nlh);
nla_put_failure:
nlmsg_cancel(skb, nlh);
diff --git a/net/core/scm.c b/net/core/scm.c
index b442e7e25e60..3b6899b7d810 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -129,8 +129,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
struct cmsghdr *cmsg;
int err;
- for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg))
- {
+ for_each_cmsghdr(cmsg, msg) {
err = -EINVAL;
/* Verify that cmsg_len is at least sizeof(struct cmsghdr) */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 32e31c299631..ae13ef6b3ea7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -265,7 +265,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->fclone = SKB_FCLONE_ORIG;
atomic_set(&fclones->fclone_ref, 1);
- fclones->skb2.fclone = SKB_FCLONE_FREE;
+ fclones->skb2.fclone = SKB_FCLONE_CLONE;
fclones->skb2.pfmemalloc = pfmemalloc;
}
out:
@@ -336,59 +336,85 @@ struct netdev_alloc_cache {
unsigned int pagecnt_bias;
};
static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
+static DEFINE_PER_CPU(struct netdev_alloc_cache, napi_alloc_cache);
-static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
+ gfp_t gfp_mask)
{
- struct netdev_alloc_cache *nc;
- void *data = NULL;
- int order;
- unsigned long flags;
+ const unsigned int order = NETDEV_FRAG_PAGE_MAX_ORDER;
+ struct page *page = NULL;
+ gfp_t gfp = gfp_mask;
+
+ if (order) {
+ gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+ page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+ nc->frag.size = PAGE_SIZE << (page ? order : 0);
+ }
- local_irq_save(flags);
- nc = this_cpu_ptr(&netdev_alloc_cache);
- if (unlikely(!nc->frag.page)) {
+ if (unlikely(!page))
+ page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+ nc->frag.page = page;
+
+ return page;
+}
+
+static void *__alloc_page_frag(struct netdev_alloc_cache __percpu *cache,
+ unsigned int fragsz, gfp_t gfp_mask)
+{
+ struct netdev_alloc_cache *nc = this_cpu_ptr(cache);
+ struct page *page = nc->frag.page;
+ unsigned int size;
+ int offset;
+
+ if (unlikely(!page)) {
refill:
- for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
- gfp_t gfp = gfp_mask;
+ page = __page_frag_refill(nc, gfp_mask);
+ if (!page)
+ return NULL;
+
+ /* if size can vary use frag.size else just use PAGE_SIZE */
+ size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
- if (order)
- gfp |= __GFP_COMP | __GFP_NOWARN;
- nc->frag.page = alloc_pages(gfp, order);
- if (likely(nc->frag.page))
- break;
- if (--order < 0)
- goto end;
- }
- nc->frag.size = PAGE_SIZE << order;
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
- atomic_add(NETDEV_PAGECNT_MAX_BIAS - 1,
- &nc->frag.page->_count);
- nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
- nc->frag.offset = 0;
+ atomic_add(size - 1, &page->_count);
+
+ /* reset page count bias and offset to start of new frag */
+ nc->pagecnt_bias = size;
+ nc->frag.offset = size;
}
- if (nc->frag.offset + fragsz > nc->frag.size) {
- if (atomic_read(&nc->frag.page->_count) != nc->pagecnt_bias) {
- if (!atomic_sub_and_test(nc->pagecnt_bias,
- &nc->frag.page->_count))
- goto refill;
- /* OK, page count is 0, we can safely set it */
- atomic_set(&nc->frag.page->_count,
- NETDEV_PAGECNT_MAX_BIAS);
- } else {
- atomic_add(NETDEV_PAGECNT_MAX_BIAS - nc->pagecnt_bias,
- &nc->frag.page->_count);
- }
- nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
- nc->frag.offset = 0;
+ offset = nc->frag.offset - fragsz;
+ if (unlikely(offset < 0)) {
+ if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
+ goto refill;
+
+ /* if size can vary use frag.size else just use PAGE_SIZE */
+ size = NETDEV_FRAG_PAGE_MAX_ORDER ? nc->frag.size : PAGE_SIZE;
+
+ /* OK, page count is 0, we can safely set it */
+ atomic_set(&page->_count, size);
+
+ /* reset page count bias and offset to start of new frag */
+ nc->pagecnt_bias = size;
+ offset = size - fragsz;
}
- data = page_address(nc->frag.page) + nc->frag.offset;
- nc->frag.offset += fragsz;
nc->pagecnt_bias--;
-end:
+ nc->frag.offset = offset;
+
+ return page_address(page) + offset;
+}
+
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+ unsigned long flags;
+ void *data;
+
+ local_irq_save(flags);
+ data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask);
local_irq_restore(flags);
return data;
}
@@ -406,11 +432,25 @@ void *netdev_alloc_frag(unsigned int fragsz)
}
EXPORT_SYMBOL(netdev_alloc_frag);
+static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+{
+ return __alloc_page_frag(&napi_alloc_cache, fragsz, gfp_mask);
+}
+
+void *napi_alloc_frag(unsigned int fragsz)
+{
+ return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
+EXPORT_SYMBOL(napi_alloc_frag);
+
/**
- * __netdev_alloc_skb - allocate an skbuff for rx on a specific device
- * @dev: network device to receive on
+ * __alloc_rx_skb - allocate an skbuff for rx
* @length: length to allocate
* @gfp_mask: get_free_pages mask, passed to alloc_skb
+ * @flags: If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ * allocations in case we have to fallback to __alloc_skb()
+ * If SKB_ALLOC_NAPI is set, page fragment will be allocated
+ * from napi_cache instead of netdev_cache.
*
* Allocate a new &sk_buff and assign it a usage count of one. The
* buffer has unspecified headroom built in. Users should allocate
@@ -419,11 +459,11 @@ EXPORT_SYMBOL(netdev_alloc_frag);
*
* %NULL is returned if there is no free memory.
*/
-struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
- unsigned int length, gfp_t gfp_mask)
+static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask,
+ int flags)
{
struct sk_buff *skb = NULL;
- unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) +
+ unsigned int fragsz = SKB_DATA_ALIGN(length) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
@@ -432,7 +472,9 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
- data = __netdev_alloc_frag(fragsz, gfp_mask);
+ data = (flags & SKB_ALLOC_NAPI) ?
+ __napi_alloc_frag(fragsz, gfp_mask) :
+ __netdev_alloc_frag(fragsz, gfp_mask);
if (likely(data)) {
skb = build_skb(data, fragsz);
@@ -440,17 +482,72 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
put_page(virt_to_head_page(data));
}
} else {
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+ skb = __alloc_skb(length, gfp_mask,
SKB_ALLOC_RX, NUMA_NO_NODE);
}
+ return skb;
+}
+
+/**
+ * __netdev_alloc_skb - allocate an skbuff for rx on a specific device
+ * @dev: network device to receive on
+ * @length: length to allocate
+ * @gfp_mask: get_free_pages mask, passed to alloc_skb
+ *
+ * Allocate a new &sk_buff and assign it a usage count of one. The
+ * buffer has NET_SKB_PAD headroom built in. Users should allocate
+ * the headroom they think they need without accounting for the
+ * built in space. The built in space is used for optimisations.
+ *
+ * %NULL is returned if there is no free memory.
+ */
+struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
+ unsigned int length, gfp_t gfp_mask)
+{
+ struct sk_buff *skb;
+
+ length += NET_SKB_PAD;
+ skb = __alloc_rx_skb(length, gfp_mask, 0);
+
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
}
+
return skb;
}
EXPORT_SYMBOL(__netdev_alloc_skb);
+/**
+ * __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
+ * @napi: napi instance this buffer was allocated for
+ * @length: length to allocate
+ * @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
+ *
+ * Allocate a new sk_buff for use in NAPI receive. This buffer will
+ * attempt to allocate the head from a special reserved region used
+ * only for NAPI Rx allocation. By doing this we can save several
+ * CPU cycles by avoiding having to disable and re-enable IRQs.
+ *
+ * %NULL is returned if there is no free memory.
+ */
+struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
+ unsigned int length, gfp_t gfp_mask)
+{
+ struct sk_buff *skb;
+
+ length += NET_SKB_PAD + NET_IP_ALIGN;
+ skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI);
+
+ if (likely(skb)) {
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
+ skb->dev = napi->dev;
+ }
+
+ return skb;
+}
+EXPORT_SYMBOL(__napi_alloc_skb);
+
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size, unsigned int truesize)
{
@@ -541,26 +638,27 @@ static void kfree_skbmem(struct sk_buff *skb)
switch (skb->fclone) {
case SKB_FCLONE_UNAVAILABLE:
kmem_cache_free(skbuff_head_cache, skb);
- break;
+ return;
case SKB_FCLONE_ORIG:
fclones = container_of(skb, struct sk_buff_fclones, skb1);
- if (atomic_dec_and_test(&fclones->fclone_ref))
- kmem_cache_free(skbuff_fclone_cache, fclones);
- break;
- case SKB_FCLONE_CLONE:
- fclones = container_of(skb, struct sk_buff_fclones, skb2);
-
- /* The clone portion is available for
- * fast-cloning again.
+ /* We usually free the clone (TX completion) before original skb
+ * This test would have no chance to be true for the clone,
+ * while here, branch prediction will be good.
*/
- skb->fclone = SKB_FCLONE_FREE;
+ if (atomic_read(&fclones->fclone_ref) == 1)
+ goto fastpath;
+ break;
- if (atomic_dec_and_test(&fclones->fclone_ref))
- kmem_cache_free(skbuff_fclone_cache, fclones);
+ default: /* SKB_FCLONE_CLONE */
+ fclones = container_of(skb, struct sk_buff_fclones, skb2);
break;
}
+ if (!atomic_dec_and_test(&fclones->fclone_ref))
+ return;
+fastpath:
+ kmem_cache_free(skbuff_fclone_cache, fclones);
}
static void skb_release_head_state(struct sk_buff *skb)
@@ -872,15 +970,15 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
struct sk_buff_fclones *fclones = container_of(skb,
struct sk_buff_fclones,
skb1);
- struct sk_buff *n = &fclones->skb2;
+ struct sk_buff *n;
if (skb_orphan_frags(skb, gfp_mask))
return NULL;
if (skb->fclone == SKB_FCLONE_ORIG &&
- n->fclone == SKB_FCLONE_FREE) {
- n->fclone = SKB_FCLONE_CLONE;
- atomic_inc(&fclones->fclone_ref);
+ atomic_read(&fclones->fclone_ref) == 1) {
+ n = &fclones->skb2;
+ atomic_set(&fclones->fclone_ref, 2);
} else {
if (skb_pfmemalloc(skb))
gfp_mask |= __GFP_MEMALLOC;
@@ -3002,7 +3100,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
if (nskb->len == len + doffset)
goto perform_csum_check;
- if (!sg) {
+ if (!sg && !nskb->remcsum_offload) {
nskb->ip_summed = CHECKSUM_NONE;
nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
skb_put(nskb, len),
@@ -3074,7 +3172,7 @@ skip_fraglist:
nskb->truesize += nskb->data_len;
perform_csum_check:
- if (!csum) {
+ if (!csum && !nskb->remcsum_offload) {
nskb->csum = skb_checksum(nskb, doffset,
nskb->len - doffset, 0);
nskb->ip_summed = CHECKSUM_NONE;
@@ -3088,6 +3186,16 @@ perform_csum_check:
* (see validate_xmit_skb_list() for example)
*/
segs->prev = tail;
+
+ /* Following permits correct backpressure, for protocols
+ * using skb_set_owner_w().
+ * Idea is to tranfert ownership from head_skb to last segment.
+ */
+ if (head_skb->destructor == sock_wfree) {
+ swap(tail->truesize, head_skb->truesize);
+ swap(tail->destructor, head_skb->destructor);
+ swap(tail->sk, head_skb->sk);
+ }
return segs;
err:
@@ -4130,6 +4238,113 @@ err_free:
}
EXPORT_SYMBOL(skb_vlan_untag);
+int skb_ensure_writable(struct sk_buff *skb, int write_len)
+{
+ if (!pskb_may_pull(skb, write_len))
+ return -ENOMEM;
+
+ if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+ return 0;
+
+ return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable);
+
+/* remove VLAN header from packet and update csum accordingly. */
+static int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci)
+{
+ struct vlan_hdr *vhdr;
+ unsigned int offset = skb->data - skb_mac_header(skb);
+ int err;
+
+ __skb_push(skb, offset);
+ err = skb_ensure_writable(skb, VLAN_ETH_HLEN);
+ if (unlikely(err))
+ goto pull;
+
+ skb_postpull_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
+
+ vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+ *vlan_tci = ntohs(vhdr->h_vlan_TCI);
+
+ memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+ __skb_pull(skb, VLAN_HLEN);
+
+ vlan_set_encap_proto(skb, vhdr);
+ skb->mac_header += VLAN_HLEN;
+
+ if (skb_network_offset(skb) < ETH_HLEN)
+ skb_set_network_header(skb, ETH_HLEN);
+
+ skb_reset_mac_len(skb);
+pull:
+ __skb_pull(skb, offset);
+
+ return err;
+}
+
+int skb_vlan_pop(struct sk_buff *skb)
+{
+ u16 vlan_tci;
+ __be16 vlan_proto;
+ int err;
+
+ if (likely(vlan_tx_tag_present(skb))) {
+ skb->vlan_tci = 0;
+ } else {
+ if (unlikely((skb->protocol != htons(ETH_P_8021Q) &&
+ skb->protocol != htons(ETH_P_8021AD)) ||
+ skb->len < VLAN_ETH_HLEN))
+ return 0;
+
+ err = __skb_vlan_pop(skb, &vlan_tci);
+ if (err)
+ return err;
+ }
+ /* move next vlan tag to hw accel tag */
+ if (likely((skb->protocol != htons(ETH_P_8021Q) &&
+ skb->protocol != htons(ETH_P_8021AD)) ||
+ skb->len < VLAN_ETH_HLEN))
+ return 0;
+
+ vlan_proto = skb->protocol;
+ err = __skb_vlan_pop(skb, &vlan_tci);
+ if (unlikely(err))
+ return err;
+
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+ return 0;
+}
+EXPORT_SYMBOL(skb_vlan_pop);
+
+int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
+{
+ if (vlan_tx_tag_present(skb)) {
+ unsigned int offset = skb->data - skb_mac_header(skb);
+ int err;
+
+ /* __vlan_insert_tag expect skb->data pointing to mac header.
+ * So change skb->data before calling it and change back to
+ * original position later
+ */
+ __skb_push(skb, offset);
+ err = __vlan_insert_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
+ if (err)
+ return err;
+ skb->protocol = skb->vlan_proto;
+ skb->mac_len += VLAN_HLEN;
+ __skb_pull(skb, offset);
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_add(skb->csum, csum_partial(skb->data
+ + (2 * ETH_ALEN), VLAN_HLEN, 0));
+ }
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci);
+ return 0;
+}
+EXPORT_SYMBOL(skb_vlan_push);
+
/**
* alloc_skb_with_frags - allocate skb with page frags
*
diff --git a/net/core/sock.c b/net/core/sock.c
index 15e0c67b1069..9a56b2000c3f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -888,6 +888,19 @@ set_rcvbuf:
}
break;
+ case SO_ATTACH_BPF:
+ ret = -EINVAL;
+ if (optlen == sizeof(u32)) {
+ u32 ufd;
+
+ ret = -EFAULT;
+ if (copy_from_user(&ufd, optval, sizeof(ufd)))
+ break;
+
+ ret = sk_attach_bpf(ufd, sk);
+ }
+ break;
+
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
@@ -1213,6 +1226,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_max_pacing_rate;
break;
+ case SO_INCOMING_CPU:
+ v.val = sk->sk_incoming_cpu;
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -1517,6 +1534,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
newsk->sk_err = 0;
newsk->sk_priority = 0;
+ newsk->sk_incoming_cpu = raw_smp_processor_id();
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -2457,7 +2475,7 @@ int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto out_free_skb;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cf9cd13509a7..31baba2a71ce 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -26,6 +26,8 @@ static int zero = 0;
static int one = 1;
static int ushort_max = USHRT_MAX;
+static int net_msg_warn; /* Unused, but still a sysctl */
+
#ifdef CONFIG_RPS
static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -215,6 +217,18 @@ static int set_default_qdisc(struct ctl_table *table, int write,
}
#endif
+static int proc_do_rss_key(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table fake_table;
+ char buf[NETDEV_RSS_KEY_LEN * 3];
+
+ snprintf(buf, sizeof(buf), "%*phC", NETDEV_RSS_KEY_LEN, netdev_rss_key);
+ fake_table.data = buf;
+ fake_table.maxlen = sizeof(buf);
+ return proc_dostring(&fake_table, write, buffer, lenp, ppos);
+}
+
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
@@ -263,6 +277,13 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "netdev_rss_key",
+ .data = &netdev_rss_key,
+ .maxlen = sizeof(int),
+ .mode = 0444,
+ .proc_handler = proc_do_rss_key,
+ },
#ifdef CONFIG_BPF_JIT
{
.procname = "bpf_jit_enable",
diff --git a/net/core/utils.c b/net/core/utils.c
index efc76dd9dcd1..7b803884c162 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -33,9 +33,6 @@
#include <asm/byteorder.h>
#include <asm/uaccess.h>
-int net_msg_warn __read_mostly = 1;
-EXPORT_SYMBOL(net_msg_warn);
-
DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10);
/*
* All net warning printk()s should be guarded by this function.
generated by cgit (git 2.34.1) at 2024-06-19 01:59:43 +0000