From 8ac6c7a54ed1b98d142dce24b11c6de6a1e239a5 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 22 Oct 2024 10:36:11 +0000
Subject: [PATCH] 修改4g拨号为QMI,需要在系统里后台执行quectel-CM
---
kernel/net/core/skbuff.c | 1367 ++++++++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 1,066 insertions(+), 301 deletions(-)
diff --git a/kernel/net/core/skbuff.c b/kernel/net/core/skbuff.c
index 6cca6a0..0c8b8ab 100644
--- a/kernel/net/core/skbuff.c
+++ b/kernel/net/core/skbuff.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Routines having to do with the 'struct sk_buff' memory handlers.
*
@@ -25,11 +26,6 @@
* disabled, or you better be *real* sure that the operation is atomic
* with respect to whatever list is being frobbed (e.g. via lock_sock()
* or via disabling bottom half handlers, etc).
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
/*
@@ -63,6 +59,7 @@
#include <linux/errqueue.h>
#include <linux/prefetch.h>
#include <linux/if_vlan.h>
+#include <linux/mpls.h>
#include <net/protocol.h>
#include <net/dst.h>
@@ -70,15 +67,24 @@
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
+#include <net/mpls.h>
+#include <net/mptcp.h>
#include <linux/uaccess.h>
#include <trace/events/skb.h>
#include <linux/highmem.h>
#include <linux/capability.h>
#include <linux/user_namespace.h>
+#include <linux/indirect_call_wrapper.h>
+#include <trace/hooks/net.h>
+
+#include "datagram.h"
struct kmem_cache *skbuff_head_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
+#ifdef CONFIG_SKB_EXTENSIONS
+static struct kmem_cache *skbuff_ext_cache __ro_after_init;
+#endif
int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
EXPORT_SYMBOL(sysctl_max_skb_frags);
@@ -97,7 +103,7 @@
static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr,
const char msg[])
{
- pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n",
+ pr_emerg("%s: text:%px len:%d put:%d head:%px data:%px tail:%#lx end:%#lx dev:%s\n",
msg, addr, skb->len, sz, skb->head, skb->data,
(unsigned long)skb->tail, (unsigned long)skb->end,
skb->dev ? skb->dev->name : "<NULL>");
@@ -244,6 +250,9 @@
fclones->skb2.fclone = SKB_FCLONE_CLONE;
}
+
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
out:
return skb;
nodata:
@@ -252,6 +261,35 @@
goto out;
}
EXPORT_SYMBOL(__alloc_skb);
+
+/* Caller must provide SKB that is memset cleared */
+static struct sk_buff *__build_skb_around(struct sk_buff *skb,
+ void *data, unsigned int frag_size)
+{
+ struct skb_shared_info *shinfo;
+ unsigned int size = frag_size ? : ksize(data);
+
+ size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ /* Assumes caller memset cleared SKB */
+ skb->truesize = SKB_TRUESIZE(size);
+ refcount_set(&skb->users, 1);
+ skb->head = data;
+ skb->data = data;
+ skb_reset_tail_pointer(skb);
+ skb->end = skb->tail + size;
+ skb->mac_header = (typeof(skb->mac_header))~0U;
+ skb->transport_header = (typeof(skb->transport_header))~0U;
+
+ /* make sure we initialize shinfo sequentially */
+ shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+ atomic_set(&shinfo->dataref, 1);
+
+ skb_set_kcov_handle(skb, kcov_common_handle());
+
+ return skb;
+}
/**
* __build_skb - build a network buffer
@@ -274,32 +312,15 @@
*/
struct sk_buff *__build_skb(void *data, unsigned int frag_size)
{
- struct skb_shared_info *shinfo;
struct sk_buff *skb;
- unsigned int size = frag_size ? : ksize(data);
skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
- if (!skb)
+ if (unlikely(!skb))
return NULL;
- size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
memset(skb, 0, offsetof(struct sk_buff, tail));
- skb->truesize = SKB_TRUESIZE(size);
- refcount_set(&skb->users, 1);
- skb->head = data;
- skb->data = data;
- skb_reset_tail_pointer(skb);
- skb->end = skb->tail + size;
- skb->mac_header = (typeof(skb->mac_header))~0U;
- skb->transport_header = (typeof(skb->transport_header))~0U;
- /* make sure we initialize shinfo sequentially */
- shinfo = skb_shinfo(skb);
- memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
- atomic_set(&shinfo->dataref, 1);
-
- return skb;
+ return __build_skb_around(skb, data, frag_size);
}
/* build_skb() is wrapper over __build_skb(), that specifically
@@ -320,6 +341,29 @@
}
EXPORT_SYMBOL(build_skb);
+/**
+ * build_skb_around - build a network buffer around provided skb
+ * @skb: sk_buff provide by caller, must be memset cleared
+ * @data: data buffer provided by caller
+ * @frag_size: size of data, or 0 if head was kmalloced
+ */
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+ void *data, unsigned int frag_size)
+{
+ if (unlikely(!skb))
+ return NULL;
+
+ skb = __build_skb_around(skb, data, frag_size);
+
+ if (skb && frag_size) {
+ skb->head_frag = 1;
+ if (page_is_pfmemalloc(virt_to_head_page(data)))
+ skb->pfmemalloc = 1;
+ }
+ return skb;
+}
+EXPORT_SYMBOL(build_skb_around);
+
#define NAPI_SKB_CACHE_SIZE 64
struct napi_alloc_cache {
@@ -330,34 +374,6 @@
static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
-
-static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
-{
- struct page_frag_cache *nc;
- unsigned long flags;
- void *data;
-
- local_irq_save(flags);
- nc = this_cpu_ptr(&netdev_alloc_cache);
- data = page_frag_alloc(nc, fragsz, gfp_mask);
- local_irq_restore(flags);
- return data;
-}
-
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
-{
- fragsz = SKB_DATA_ALIGN(fragsz);
-
- return __netdev_alloc_frag(fragsz, GFP_ATOMIC);
-}
-EXPORT_SYMBOL(netdev_alloc_frag);
static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
@@ -373,6 +389,31 @@
return __napi_alloc_frag(fragsz, GFP_ATOMIC);
}
EXPORT_SYMBOL(napi_alloc_frag);
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+ struct page_frag_cache *nc;
+ void *data;
+
+ fragsz = SKB_DATA_ALIGN(fragsz);
+ if (in_irq() || irqs_disabled()) {
+ nc = this_cpu_ptr(&netdev_alloc_cache);
+ data = page_frag_alloc(nc, fragsz, GFP_ATOMIC);
+ } else {
+ local_bh_disable();
+ data = __napi_alloc_frag(fragsz, GFP_ATOMIC);
+ local_bh_enable();
+ }
+ return data;
+}
+EXPORT_SYMBOL(netdev_alloc_frag);
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
@@ -391,7 +432,6 @@
gfp_t gfp_mask)
{
struct page_frag_cache *nc;
- unsigned long flags;
struct sk_buff *skb;
bool pfmemalloc;
void *data;
@@ -416,13 +456,17 @@
if (sk_memalloc_socks())
gfp_mask |= __GFP_MEMALLOC;
- local_irq_save(flags);
-
- nc = this_cpu_ptr(&netdev_alloc_cache);
- data = page_frag_alloc(nc, len, gfp_mask);
- pfmemalloc = nc->pfmemalloc;
-
- local_irq_restore(flags);
+ if (in_irq() || irqs_disabled()) {
+ nc = this_cpu_ptr(&netdev_alloc_cache);
+ data = page_frag_alloc(nc, len, gfp_mask);
+ pfmemalloc = nc->pfmemalloc;
+ } else {
+ local_bh_disable();
+ nc = this_cpu_ptr(&napi_alloc_cache.page);
+ data = page_frag_alloc(nc, len, gfp_mask);
+ pfmemalloc = nc->pfmemalloc;
+ local_bh_enable();
+ }
if (unlikely(!data))
return NULL;
@@ -433,7 +477,6 @@
return NULL;
}
- /* use OR instead of assignment to avoid clearing of bits in mask */
if (pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
@@ -498,7 +541,6 @@
return NULL;
}
- /* use OR instead of assignment to avoid clearing of bits in mask */
if (nc->page.pfmemalloc)
skb->pfmemalloc = 1;
skb->head_frag = 1;
@@ -619,7 +661,6 @@
void skb_release_head_state(struct sk_buff *skb)
{
skb_dst_drop(skb);
- secpath_reset(skb);
if (skb->destructor) {
WARN_ON(in_irq());
skb->destructor(skb);
@@ -627,9 +668,7 @@
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb_nfct(skb));
#endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
- nf_bridge_put(skb->nf_bridge);
-#endif
+ skb_ext_put(skb);
}
/* Free everything but the sk_buff shell. */
@@ -668,6 +707,7 @@
if (!skb_unref(skb))
return;
+ trace_android_vh_kfree_skb(skb);
trace_kfree_skb(skb, __builtin_return_address(0));
__kfree_skb(skb);
}
@@ -684,6 +724,101 @@
}
EXPORT_SYMBOL(kfree_skb_list);
+/* Dump skb information and contents.
+ *
+ * Must only be called from net_ratelimit()-ed paths.
+ *
+ * Dumps whole packets if full_pkt, only headers otherwise.
+ */
+void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
+{
+ struct skb_shared_info *sh = skb_shinfo(skb);
+ struct net_device *dev = skb->dev;
+ struct sock *sk = skb->sk;
+ struct sk_buff *list_skb;
+ bool has_mac, has_trans;
+ int headroom, tailroom;
+ int i, len, seg_len;
+
+ if (full_pkt)
+ len = skb->len;
+ else
+ len = min_t(int, skb->len, MAX_HEADER + 128);
+
+ headroom = skb_headroom(skb);
+ tailroom = skb_tailroom(skb);
+
+ has_mac = skb_mac_header_was_set(skb);
+ has_trans = skb_transport_header_was_set(skb);
+
+ printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n"
+ "mac=(%d,%d) net=(%d,%d) trans=%d\n"
+ "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n"
+ "csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n"
+ "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n",
+ level, skb->len, headroom, skb_headlen(skb), tailroom,
+ has_mac ? skb->mac_header : -1,
+ has_mac ? skb_mac_header_len(skb) : -1,
+ skb->network_header,
+ has_trans ? skb_network_header_len(skb) : -1,
+ has_trans ? skb->transport_header : -1,
+ sh->tx_flags, sh->nr_frags,
+ sh->gso_size, sh->gso_type, sh->gso_segs,
+ skb->csum, skb->ip_summed, skb->csum_complete_sw,
+ skb->csum_valid, skb->csum_level,
+ skb->hash, skb->sw_hash, skb->l4_hash,
+ ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
+
+ if (dev)
+ printk("%sdev name=%s feat=%pNF\n",
+ level, dev->name, &dev->features);
+ if (sk)
+ printk("%ssk family=%hu type=%u proto=%u\n",
+ level, sk->sk_family, sk->sk_type, sk->sk_protocol);
+
+ if (full_pkt && headroom)
+ print_hex_dump(level, "skb headroom: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb->head, headroom, false);
+
+ seg_len = min_t(int, skb_headlen(skb), len);
+ if (seg_len)
+ print_hex_dump(level, "skb linear: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb->data, seg_len, false);
+ len -= seg_len;
+
+ if (full_pkt && tailroom)
+ print_hex_dump(level, "skb tailroom: ", DUMP_PREFIX_OFFSET,
+ 16, 1, skb_tail_pointer(skb), tailroom, false);
+
+ for (i = 0; len && i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ u32 p_off, p_len, copied;
+ struct page *p;
+ u8 *vaddr;
+
+ skb_frag_foreach_page(frag, skb_frag_off(frag),
+ skb_frag_size(frag), p, p_off, p_len,
+ copied) {
+ seg_len = min_t(int, p_len, len);
+ vaddr = kmap_atomic(p);
+ print_hex_dump(level, "skb frag: ",
+ DUMP_PREFIX_OFFSET,
+ 16, 1, vaddr + p_off, seg_len, false);
+ kunmap_atomic(vaddr);
+ len -= seg_len;
+ if (!len)
+ break;
+ }
+ }
+
+ if (full_pkt && skb_has_frag_list(skb)) {
+ printk("skb fraglist:\n");
+ skb_walk_frags(skb, list_skb)
+ skb_dump(level, list_skb, true);
+ }
+}
+EXPORT_SYMBOL(skb_dump);
+
/**
* skb_tx_error - report an sk_buff xmit error
* @skb: buffer that triggered an error
@@ -697,6 +832,7 @@
}
EXPORT_SYMBOL(skb_tx_error);
+#ifdef CONFIG_TRACEPOINTS
/**
* consume_skb - free an skbuff
* @skb: buffer to free
@@ -714,6 +850,7 @@
__kfree_skb(skb);
}
EXPORT_SYMBOL(consume_skb);
+#endif
/**
* consume_stateless_skb - free an skbuff, assuming it is stateless
@@ -770,9 +907,6 @@
void napi_consume_skb(struct sk_buff *skb, int budget)
{
- if (unlikely(!skb))
- return;
-
/* Zero budget indicate non-NAPI context called us, like netpoll */
if (unlikely(!budget)) {
dev_consume_skb_any(skb);
@@ -809,9 +943,7 @@
new->dev = old->dev;
memcpy(new->cb, old->cb, sizeof(old->cb));
skb_dst_copy(new, old);
-#ifdef CONFIG_XFRM
- new->sp = secpath_get(old->sp);
-#endif
+ __skb_ext_copy(new, old);
__nf_copy(new, old, false);
/* Note : this field could be in headers_start/headers_end section
@@ -887,6 +1019,31 @@
return n;
#undef C
}
+
+/**
+ * alloc_skb_for_msg() - allocate sk_buff to wrap frag list forming a msg
+ * @first: first sk_buff of the msg
+ */
+struct sk_buff *alloc_skb_for_msg(struct sk_buff *first)
+{
+ struct sk_buff *n;
+
+ n = alloc_skb(0, GFP_ATOMIC);
+ if (!n)
+ return NULL;
+
+ n->len = first->len;
+ n->data_len = first->len;
+ n->truesize = first->truesize;
+
+ skb_shinfo(n)->frag_list = first;
+
+ __copy_skb_header(n, first);
+ n->destructor = NULL;
+
+ return n;
+}
+EXPORT_SYMBOL_GPL(alloc_skb_for_msg);
/**
* skb_morph - morph one skb into another
@@ -1012,7 +1169,11 @@
uarg->len++;
uarg->bytelen = bytelen;
atomic_set(&sk->sk_zckey, ++next);
- sock_zerocopy_get(uarg);
+
+ /* no extra ref when appending to datagram (MSG_MORE) */
+ if (sk->sk_type == SOCK_STREAM)
+ sock_zerocopy_get(uarg);
+
return uarg;
}
}
@@ -1102,7 +1263,7 @@
}
EXPORT_SYMBOL_GPL(sock_zerocopy_put);
-void sock_zerocopy_put_abort(struct ubuf_info *uarg)
+void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref)
{
if (uarg) {
struct sock *sk = skb_from_uarg(uarg)->sk;
@@ -1110,13 +1271,17 @@
atomic_dec(&sk->sk_zckey);
uarg->len--;
- sock_zerocopy_put(uarg);
+ if (have_uref)
+ sock_zerocopy_put(uarg);
}
}
EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort);
-extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
- struct iov_iter *from, size_t length);
+int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len)
+{
+ return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len);
+}
+EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram);
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
@@ -1144,7 +1309,7 @@
return err;
}
- skb_zcopy_set(skb, uarg);
+ skb_zcopy_set(skb, uarg, NULL);
return skb->len - orig_len;
}
EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream);
@@ -1164,7 +1329,7 @@
if (skb_copy_ubufs(nskb, GFP_ATOMIC))
return -EIO;
}
- skb_zcopy_set(nskb, skb_uarg(orig));
+ skb_zcopy_set(nskb, skb_uarg(orig), NULL);
}
return 0;
}
@@ -1220,7 +1385,7 @@
struct page *p;
u8 *vaddr;
- skb_frag_foreach_page(f, f->page_offset, skb_frag_size(f),
+ skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f),
p, p_off, p_len, copied) {
u32 copy, done = 0;
vaddr = kmap_atomic(p);
@@ -1510,11 +1675,10 @@
skb->head = data;
skb->head_frag = 0;
skb->data += off;
+
+ skb_set_end_offset(skb, size);
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->end = size;
off = nhead;
-#else
- skb->end = skb->head + size;
#endif
skb->tail += off;
skb_headers_offset_update(skb, nhead);
@@ -1561,6 +1725,38 @@
return skb2;
}
EXPORT_SYMBOL(skb_realloc_headroom);
+
+int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
+{
+ unsigned int saved_end_offset, saved_truesize;
+ struct skb_shared_info *shinfo;
+ int res;
+
+ saved_end_offset = skb_end_offset(skb);
+ saved_truesize = skb->truesize;
+
+ res = pskb_expand_head(skb, 0, 0, pri);
+ if (res)
+ return res;
+
+ skb->truesize = saved_truesize;
+
+ if (likely(skb_end_offset(skb) == saved_end_offset))
+ return 0;
+
+ shinfo = skb_shinfo(skb);
+
+ /* We are about to change back skb->end,
+ * we need to move skb_shinfo() to its new location.
+ */
+ memmove(skb->head + saved_end_offset,
+ shinfo,
+ offsetof(struct skb_shared_info, frags[shinfo->nr_frags]));
+
+ skb_set_end_offset(skb, saved_end_offset);
+
+ return 0;
+}
/**
* skb_copy_expand - copy and expand sk_buff
@@ -1944,8 +2140,6 @@
struct sk_buff *insp = NULL;
do {
- BUG_ON(!list);
-
if (list->len <= eat) {
/* Eaten as whole. */
eat -= list->len;
@@ -1953,6 +2147,9 @@
insp = list;
} else {
/* Eaten partially. */
+ if (skb_is_gso(skb) && !list->head_frag &&
+ skb_headlen(list))
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
if (skb_shared(list)) {
/* Sucks! We need to fork list. :-( */
@@ -1997,10 +2194,12 @@
skb_frag_unref(skb, i);
eat -= size;
} else {
- skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
+
+ *frag = skb_shinfo(skb)->frags[i];
if (eat) {
- skb_shinfo(skb)->frags[k].page_offset += eat;
- skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat);
+ skb_frag_off_add(frag, eat);
+ skb_frag_size_sub(frag, eat);
if (!i)
goto end;
eat = 0;
@@ -2072,7 +2271,7 @@
copy = len;
skb_frag_foreach_page(f,
- f->page_offset + offset - start,
+ skb_frag_off(f) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
memcpy(to + copied, vaddr + p_off, p_len);
@@ -2248,7 +2447,7 @@
const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
if (__splice_segment(skb_frag_page(f),
- f->page_offset, skb_frag_size(f),
+ skb_frag_off(f), skb_frag_size(f),
offset, len, spd, false, sk, pipe))
return true;
}
@@ -2338,20 +2537,20 @@
for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
- if (offset < frag->size)
+ if (offset < skb_frag_size(frag))
break;
- offset -= frag->size;
+ offset -= skb_frag_size(frag);
}
for (; len && fragidx < skb_shinfo(skb)->nr_frags; fragidx++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[fragidx];
- slen = min_t(size_t, len, frag->size - offset);
+ slen = min_t(size_t, len, skb_frag_size(frag) - offset);
while (slen) {
- ret = kernel_sendpage_locked(sk, frag->page.p,
- frag->page_offset + offset,
+ ret = kernel_sendpage_locked(sk, skb_frag_page(frag),
+ skb_frag_off(frag) + offset,
slen, MSG_DONTWAIT);
if (ret <= 0)
goto error;
@@ -2385,19 +2584,6 @@
return orig_len == len ? ret : orig_len - len;
}
EXPORT_SYMBOL_GPL(skb_send_sock_locked);
-
-/* Send skb data on a socket. */
-int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
-{
- int ret = 0;
-
- lock_sock(sk);
- ret = skb_send_sock_locked(sk, skb, offset, len);
- release_sock(sk);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(skb_send_sock);
/**
* skb_store_bits - store bits from kernel buffer to skb
@@ -2446,7 +2632,7 @@
copy = len;
skb_frag_foreach_page(frag,
- frag->page_offset + offset - start,
+ skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
memcpy(vaddr + p_off, from + copied, p_len);
@@ -2501,7 +2687,8 @@
if (copy > 0) {
if (copy > len)
copy = len;
- csum = ops->update(skb->data + offset, copy, csum);
+ csum = INDIRECT_CALL_1(ops->update, csum_partial_ext,
+ skb->data + offset, copy, csum);
if ((len -= copy) == 0)
return csum;
offset += copy;
@@ -2525,12 +2712,16 @@
copy = len;
skb_frag_foreach_page(frag,
- frag->page_offset + offset - start,
+ skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
- csum2 = ops->update(vaddr + p_off, p_len, 0);
+ csum2 = INDIRECT_CALL_1(ops->update,
+ csum_partial_ext,
+ vaddr + p_off, p_len, 0);
kunmap_atomic(vaddr);
- csum = ops->combine(csum, csum2, pos, p_len);
+ csum = INDIRECT_CALL_1(ops->combine,
+ csum_block_add_ext, csum,
+ csum2, pos, p_len);
pos += p_len;
}
@@ -2553,7 +2744,8 @@
copy = len;
csum2 = __skb_checksum(frag_iter, offset - start,
copy, 0, ops);
- csum = ops->combine(csum, csum2, pos, copy);
+ csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext,
+ csum, csum2, pos, copy);
if ((len -= copy) == 0)
return csum;
offset += copy;
@@ -2582,19 +2774,20 @@
/* Both of above in one bottle. */
__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
- u8 *to, int len, __wsum csum)
+ u8 *to, int len)
{
int start = skb_headlen(skb);
int i, copy = start - offset;
struct sk_buff *frag_iter;
int pos = 0;
+ __wsum csum = 0;
/* Copy header. */
if (copy > 0) {
if (copy > len)
copy = len;
csum = csum_partial_copy_nocheck(skb->data + offset, to,
- copy, csum);
+ copy);
if ((len -= copy) == 0)
return csum;
offset += copy;
@@ -2619,12 +2812,12 @@
copy = len;
skb_frag_foreach_page(frag,
- frag->page_offset + offset - start,
+ skb_frag_off(frag) + offset - start,
copy, p, p_off, p_len, copied) {
vaddr = kmap_atomic(p);
csum2 = csum_partial_copy_nocheck(vaddr + p_off,
to + copied,
- p_len, 0);
+ p_len);
kunmap_atomic(vaddr);
csum = csum_block_add(csum, csum2, pos);
pos += p_len;
@@ -2650,7 +2843,7 @@
copy = len;
csum2 = skb_copy_and_csum_bits(frag_iter,
offset - start,
- to, copy, 0);
+ to, copy);
csum = csum_block_add(csum, csum2, pos);
if ((len -= copy) == 0)
return csum;
@@ -2664,6 +2857,65 @@
return csum;
}
EXPORT_SYMBOL(skb_copy_and_csum_bits);
+
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
+{
+ __sum16 sum;
+
+ sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
+ /* See comments in __skb_checksum_complete(). */
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev, skb);
+ }
+ if (!skb_shared(skb))
+ skb->csum_valid = !sum;
+ return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete_head);
+
+/* This function assumes skb->csum already holds pseudo header's checksum,
+ * which has been changed from the hardware checksum, for example, by
+ * __skb_checksum_validate_complete(). And, the original skb->csum must
+ * have been validated unsuccessfully for CHECKSUM_COMPLETE case.
+ *
+ * It returns non-zero if the recomputed checksum is still invalid, otherwise
+ * zero. The new checksum is stored back into skb->csum unless the skb is
+ * shared.
+ */
+__sum16 __skb_checksum_complete(struct sk_buff *skb)
+{
+ __wsum csum;
+ __sum16 sum;
+
+ csum = skb_checksum(skb, 0, skb->len, 0);
+
+ sum = csum_fold(csum_add(skb->csum, csum));
+ /* This check is inverted, because we already knew the hardware
+ * checksum is invalid before calling this function. So, if the
+ * re-computed checksum is valid instead, then we have a mismatch
+ * between the original skb->csum and skb_checksum(). This means either
+ * the original hardware checksum is incorrect or we screw up skb->csum
+ * when moving skb->data around.
+ */
+ if (likely(!sum)) {
+ if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !skb->csum_complete_sw)
+ netdev_rx_csum_fault(skb->dev, skb);
+ }
+
+ if (!skb_shared(skb)) {
+ /* Save full packet checksum */
+ skb->csum = csum;
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum_complete_sw = 1;
+ skb->csum_valid = !sum;
+ }
+
+ return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete);
static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
{
@@ -2779,11 +3031,15 @@
skb_zerocopy_clone(to, from, GFP_ATOMIC);
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
+ int size;
+
if (!len)
break;
skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
- skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
- len -= skb_shinfo(to)->frags[j].size;
+ size = min_t(int, skb_frag_size(&skb_shinfo(to)->frags[j]),
+ len);
+ skb_frag_size_set(&skb_shinfo(to)->frags[j], size);
+ len -= size;
skb_frag_ref(to, j);
j++;
}
@@ -2810,7 +3066,7 @@
csum = 0;
if (csstart != skb->len)
csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
- skb->len - csstart, 0);
+ skb->len - csstart);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
long csstuff = csstart + skb->csum_offset;
@@ -2985,28 +3241,6 @@
}
EXPORT_SYMBOL(skb_append);
-/**
- * skb_insert - insert a buffer
- * @old: buffer to insert before
- * @newsk: buffer to insert
- * @list: list to use
- *
- * Place a packet before a given packet in a list. The list locks are
- * taken and this function is atomic with respect to other list locked
- * calls.
- *
- * A buffer cannot be placed on two lists at the same time.
- */
-void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&list->lock, flags);
- __skb_insert(newsk, old->prev, old, list);
- spin_unlock_irqrestore(&list->lock, flags);
-}
-EXPORT_SYMBOL(skb_insert);
-
static inline void skb_split_inside_header(struct sk_buff *skb,
struct sk_buff* skb1,
const u32 len, const int pos)
@@ -3056,7 +3290,7 @@
* 2. Split is accurately. We make this.
*/
skb_frag_ref(skb, i);
- skb_shinfo(skb1)->frags[0].page_offset += len - pos;
+ skb_frag_off_add(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos);
skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos);
skb_shinfo(skb)->nr_frags++;
@@ -3095,19 +3329,7 @@
*/
static int skb_prepare_for_shift(struct sk_buff *skb)
{
- int ret = 0;
-
- if (skb_cloned(skb)) {
- /* Save and restore truesize: pskb_expand_head() may reallocate
- * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we
- * cannot change truesize at this point.
- */
- unsigned int save_truesize = skb->truesize;
-
- ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- skb->truesize = save_truesize;
- }
- return ret;
+ return skb_unclone_keeptruesize(skb, GFP_ATOMIC);
}
/**
@@ -3131,7 +3353,7 @@
int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
{
int from, to, merge, todo;
- struct skb_frag_struct *fragfrom, *fragto;
+ skb_frag_t *fragfrom, *fragto;
BUG_ON(shiftlen > skb->len);
@@ -3150,7 +3372,7 @@
*/
if (!to ||
!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
- fragfrom->page_offset)) {
+ skb_frag_off(fragfrom))) {
merge = -1;
} else {
merge = to - 1;
@@ -3167,7 +3389,7 @@
skb_frag_size_add(fragto, shiftlen);
skb_frag_size_sub(fragfrom, shiftlen);
- fragfrom->page_offset += shiftlen;
+ skb_frag_off_add(fragfrom, shiftlen);
goto onlymerged;
}
@@ -3198,11 +3420,11 @@
} else {
__skb_frag_ref(fragfrom);
- fragto->page = fragfrom->page;
- fragto->page_offset = fragfrom->page_offset;
+ skb_frag_page_copy(fragto, fragfrom);
+ skb_frag_off_copy(fragto, fragfrom);
skb_frag_size_set(fragto, todo);
- fragfrom->page_offset += todo;
+ skb_frag_off_add(fragfrom, todo);
skb_frag_size_sub(fragfrom, todo);
todo = 0;
@@ -3327,7 +3549,7 @@
if (!st->frag_data)
st->frag_data = kmap_atomic(skb_frag_page(frag));
- *data = (u8 *) st->frag_data + frag->page_offset +
+ *data = (u8 *) st->frag_data + skb_frag_off(frag) +
(abs_offset - st->stepped_offset);
return block_limit - abs_offset;
@@ -3417,64 +3639,6 @@
}
EXPORT_SYMBOL(skb_find_text);
-/**
- * skb_append_datato_frags - append the user data to a skb
- * @sk: sock structure
- * @skb: skb structure to be appended with user data.
- * @getfrag: call back function to be used for getting the user data
- * @from: pointer to user message iov
- * @length: length of the iov message
- *
- * Description: This procedure append the user data in the fragment part
- * of the skb if any page alloc fails user this procedure returns -ENOMEM
- */
-int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb,
- int (*getfrag)(void *from, char *to, int offset,
- int len, int odd, struct sk_buff *skb),
- void *from, int length)
-{
- int frg_cnt = skb_shinfo(skb)->nr_frags;
- int copy;
- int offset = 0;
- int ret;
- struct page_frag *pfrag = ¤t->task_frag;
-
- do {
- /* Return error if we don't have space for new frag */
- if (frg_cnt >= MAX_SKB_FRAGS)
- return -EMSGSIZE;
-
- if (!sk_page_frag_refill(sk, pfrag))
- return -ENOMEM;
-
- /* copy the user data to page */
- copy = min_t(int, length, pfrag->size - pfrag->offset);
-
- ret = getfrag(from, page_address(pfrag->page) + pfrag->offset,
- offset, copy, 0, skb);
- if (ret < 0)
- return -EFAULT;
-
- /* copy was successful so update the size parameters */
- skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset,
- copy);
- frg_cnt++;
- pfrag->offset += copy;
- get_page(pfrag->page);
-
- skb->truesize += copy;
- refcount_add(copy, &sk->sk_wmem_alloc);
- skb->len += copy;
- skb->data_len += copy;
- offset += copy;
- length -= copy;
-
- } while (length > 0);
-
- return 0;
-}
-EXPORT_SYMBOL(skb_append_datato_frags);
-
int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
int offset, size_t size)
{
@@ -3521,11 +3685,126 @@
struct page *page;
page = virt_to_head_page(frag_skb->head);
- head_frag.page.p = page;
- head_frag.page_offset = frag_skb->data -
- (unsigned char *)page_address(page);
- head_frag.size = skb_headlen(frag_skb);
+ __skb_frag_set_page(&head_frag, page);
+ skb_frag_off_set(&head_frag, frag_skb->data -
+ (unsigned char *)page_address(page));
+ skb_frag_size_set(&head_frag, skb_headlen(frag_skb));
return head_frag;
+}
+
+struct sk_buff *skb_segment_list(struct sk_buff *skb,
+ netdev_features_t features,
+ unsigned int offset)
+{
+ struct sk_buff *list_skb = skb_shinfo(skb)->frag_list;
+ unsigned int tnl_hlen = skb_tnl_header_len(skb);
+ unsigned int delta_truesize = 0;
+ unsigned int delta_len = 0;
+ struct sk_buff *tail = NULL;
+ struct sk_buff *nskb, *tmp;
+ int len_diff, err;
+
+ skb_push(skb, -skb_network_offset(skb) + offset);
+
+ /* Ensure the head is writeable before touching the shared info */
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (err)
+ goto err_linearize;
+
+ skb_shinfo(skb)->frag_list = NULL;
+
+ while (list_skb) {
+ nskb = list_skb;
+ list_skb = list_skb->next;
+
+ err = 0;
+ delta_truesize += nskb->truesize;
+ if (skb_shared(nskb)) {
+ tmp = skb_clone(nskb, GFP_ATOMIC);
+ if (tmp) {
+ consume_skb(nskb);
+ nskb = tmp;
+ err = skb_unclone(nskb, GFP_ATOMIC);
+ } else {
+ err = -ENOMEM;
+ }
+ }
+
+ if (!tail)
+ skb->next = nskb;
+ else
+ tail->next = nskb;
+
+ if (unlikely(err)) {
+ nskb->next = list_skb;
+ goto err_linearize;
+ }
+
+ tail = nskb;
+
+ delta_len += nskb->len;
+
+ skb_push(nskb, -skb_network_offset(nskb) + offset);
+
+ skb_release_head_state(nskb);
+ len_diff = skb_network_header_len(nskb) - skb_network_header_len(skb);
+ __copy_skb_header(nskb, skb);
+
+ skb_headers_offset_update(nskb, skb_headroom(nskb) - skb_headroom(skb));
+ nskb->transport_header += len_diff;
+ skb_copy_from_linear_data_offset(skb, -tnl_hlen,
+ nskb->data - tnl_hlen,
+ offset + tnl_hlen);
+
+ if (skb_needs_linearize(nskb, features) &&
+ __skb_linearize(nskb))
+ goto err_linearize;
+ }
+
+ skb->truesize = skb->truesize - delta_truesize;
+ skb->data_len = skb->data_len - delta_len;
+ skb->len = skb->len - delta_len;
+
+ skb_gso_reset(skb);
+
+ skb->prev = tail;
+
+ if (skb_needs_linearize(skb, features) &&
+ __skb_linearize(skb))
+ goto err_linearize;
+
+ skb_get(skb);
+
+ return skb;
+
+err_linearize:
+ kfree_skb_list(skb->next);
+ skb->next = NULL;
+ return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL_GPL(skb_segment_list);
+
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
+{
+ if (unlikely(p->len + skb->len >= 65536))
+ return -E2BIG;
+
+ if (NAPI_GRO_CB(p)->last == p)
+ skb_shinfo(p)->frag_list = skb;
+ else
+ NAPI_GRO_CB(p)->last->next = skb;
+
+ skb_pull(skb, skb_gro_offset(skb));
+
+ NAPI_GRO_CB(p)->last = skb;
+ NAPI_GRO_CB(p)->count++;
+ p->data_len += skb->len;
+ p->truesize += skb->truesize;
+ p->len += skb->len;
+
+ NAPI_GRO_CB(skb)->same_flow = 1;
+
+ return 0;
}
/**
@@ -3543,44 +3822,44 @@
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
- skb_frag_t *frag = skb_shinfo(head_skb)->frags;
unsigned int mss = skb_shinfo(head_skb)->gso_size;
unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
- struct sk_buff *frag_skb = head_skb;
unsigned int offset = doffset;
unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int partial_segs = 0;
unsigned int headroom;
unsigned int len = head_skb->len;
+ struct sk_buff *frag_skb;
+ skb_frag_t *frag;
__be16 proto;
bool csum, sg;
- int nfrags = skb_shinfo(head_skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
- int pos;
- int dummy;
+ int nfrags, pos;
- if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) &&
- (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) {
- /* gso_size is untrusted, and we have a frag_list with a linear
- * non head_frag head.
- *
- * (we assume checking the first list_skb member suffices;
- * i.e if either of the list_skb members have non head_frag
- * head, then the first one has too).
- *
- * If head_skb's headlen does not fit requested gso_size, it
- * means that the frag_list members do NOT terminate on exact
- * gso_size boundaries. Hence we cannot perform skb_frag_t page
- * sharing. Therefore we must fallback to copying the frag_list
- * skbs; we do so by disabling SG.
- */
- if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb))
- features &= ~NETIF_F_SG;
+ if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
+ mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) {
+ struct sk_buff *check_skb;
+
+ for (check_skb = list_skb; check_skb; check_skb = check_skb->next) {
+ if (skb_headlen(check_skb) && !check_skb->head_frag) {
+ /* gso_size is untrusted, and we have a frag_list with
+ * a linear non head_frag item.
+ *
+ * If head_skb's headlen does not fit requested gso_size,
+ * it means that the frag_list members do NOT terminate
+ * on exact gso_size boundaries. Hence we cannot perform
+ * skb_frag_t page sharing. Therefore we must fallback to
+ * copying the frag_list skbs; we do so by disabling SG.
+ */
+ features &= ~NETIF_F_SG;
+ break;
+ }
+ }
}
__skb_push(head_skb, doffset);
- proto = skb_network_protocol(head_skb, &dummy);
+ proto = skb_network_protocol(head_skb, NULL);
if (unlikely(!proto))
return ERR_PTR(-EINVAL);
@@ -3633,6 +3912,13 @@
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
+ if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+ return ERR_PTR(-ENOMEM);
+
+ nfrags = skb_shinfo(head_skb)->nr_frags;
+ frag = skb_shinfo(head_skb)->frags;
+ frag_skb = head_skb;
+
do {
struct sk_buff *nskb;
skb_frag_t *nskb_frag;
@@ -3657,6 +3943,10 @@
(skb_headlen(list_skb) == len || sg)) {
BUG_ON(skb_headlen(list_skb) > len);
+ nskb = skb_clone(list_skb, GFP_ATOMIC);
+ if (unlikely(!nskb))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3675,11 +3965,7 @@
frag++;
}
- nskb = skb_clone(list_skb, GFP_ATOMIC);
list_skb = list_skb->next;
-
- if (unlikely(!nskb))
- goto err;
if (unlikely(pskb_trim(nskb, len))) {
kfree_skb(nskb);
@@ -3726,14 +4012,20 @@
goto perform_csum_check;
if (!sg) {
- if (!nskb->remcsum_offload)
- nskb->ip_summed = CHECKSUM_NONE;
- SKB_GSO_CB(nskb)->csum =
- skb_copy_and_csum_bits(head_skb, offset,
- skb_put(nskb, len),
- len, 0);
- SKB_GSO_CB(nskb)->csum_start =
- skb_headroom(nskb) + doffset;
+ if (!csum) {
+ if (!nskb->remcsum_offload)
+ nskb->ip_summed = CHECKSUM_NONE;
+ SKB_GSO_CB(nskb)->csum =
+ skb_copy_and_csum_bits(head_skb, offset,
+ skb_put(nskb,
+ len),
+ len);
+ SKB_GSO_CB(nskb)->csum_start =
+ skb_headroom(nskb) + doffset;
+ } else {
+ if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len))
+ goto err;
+ }
continue;
}
@@ -3745,12 +4037,16 @@
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
if (i >= nfrags) {
+ if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, list_skb,
+ GFP_ATOMIC))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3764,10 +4060,6 @@
i--;
frag--;
}
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb,
- GFP_ATOMIC))
- goto err;
list_skb = list_skb->next;
}
@@ -3786,7 +4078,7 @@
size = skb_frag_size(nskb_frag);
if (pos < offset) {
- nskb_frag->page_offset += offset - pos;
+ skb_frag_off_add(nskb_frag, offset - pos);
skb_frag_size_sub(nskb_frag, offset - pos);
}
@@ -3907,7 +4199,7 @@
*--frag = *--frag2;
} while (--i);
- frag->page_offset += offset;
+ skb_frag_off_add(frag, offset);
skb_frag_size_sub(frag, offset);
/* all fragments truesize : remove (head size + sk_buff) */
@@ -3936,8 +4228,8 @@
pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags;
- frag->page.p = page;
- frag->page_offset = first_offset;
+ __skb_frag_set_page(frag, page);
+ skb_frag_off_set(frag, first_offset);
skb_frag_size_set(frag, first_size);
memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
@@ -3953,7 +4245,7 @@
if (offset > headlen) {
unsigned int eat = offset - headlen;
- skbinfo->frags[0].page_offset += eat;
+ skb_frag_off_add(&skbinfo->frags[0], eat);
skb_frag_size_sub(&skbinfo->frags[0], eat);
skb->data_len -= eat;
skb->len -= eat;
@@ -3983,7 +4275,58 @@
NAPI_GRO_CB(skb)->same_flow = 1;
return 0;
}
-EXPORT_SYMBOL_GPL(skb_gro_receive);
+
+#ifdef CONFIG_SKB_EXTENSIONS
+#define SKB_EXT_ALIGN_VALUE 8
+#define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE)
+
+static const u8 skb_ext_type_len[] = {
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ [SKB_EXT_BRIDGE_NF] = SKB_EXT_CHUNKSIZEOF(struct nf_bridge_info),
+#endif
+#ifdef CONFIG_XFRM
+ [SKB_EXT_SEC_PATH] = SKB_EXT_CHUNKSIZEOF(struct sec_path),
+#endif
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext),
+#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
+#endif
+};
+
+static __always_inline unsigned int skb_ext_total_length(void)
+{
+ return SKB_EXT_CHUNKSIZEOF(struct skb_ext) +
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+ skb_ext_type_len[SKB_EXT_BRIDGE_NF] +
+#endif
+#ifdef CONFIG_XFRM
+ skb_ext_type_len[SKB_EXT_SEC_PATH] +
+#endif
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ skb_ext_type_len[TC_SKB_EXT] +
+#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ skb_ext_type_len[SKB_EXT_MPTCP] +
+#endif
+ 0;
+}
+
+static void skb_extensions_init(void)
+{
+ BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+ BUILD_BUG_ON(skb_ext_total_length() > 255);
+
+ skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
+ SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
+ 0,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+ NULL);
+}
+#else
+static void skb_extensions_init(void) {}
+#endif
void __init skb_init(void)
{
@@ -3999,6 +4342,7 @@
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
+ skb_extensions_init();
}
static int
@@ -4037,7 +4381,7 @@
if (copy > len)
copy = len;
sg_set_page(&sg[elt], skb_frag_page(frag), copy,
- frag->page_offset+offset-start);
+ skb_frag_off(frag) + offset - start);
elt++;
if (!(len -= copy))
return elt;
@@ -4154,7 +4498,7 @@
* at the moment even if they are anonymous).
*/
if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) &&
- __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL)
+ !__pskb_pull_tail(skb, __skb_pagelen(skb)))
return -ENOMEM;
/* Easy case. Most of packets will go this way. */
@@ -4258,7 +4602,7 @@
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned int)sk->sk_rcvbuf)
+ (unsigned int)READ_ONCE(sk->sk_rcvbuf))
return -ENOMEM;
skb_orphan(skb);
@@ -4377,7 +4721,7 @@
{
bool ret;
- if (likely(sysctl_tstamp_allow_data || tsonly))
+ if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
return true;
read_lock_bh(&sk->sk_callback_lock);
@@ -4433,13 +4777,18 @@
if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
sk->sk_protocol == IPPROTO_TCP &&
sk->sk_type == SOCK_STREAM) {
- skb = tcp_get_timestamping_opt_stats(sk);
+ skb = tcp_get_timestamping_opt_stats(sk, orig_skb);
opt_stats = true;
} else
#endif
skb = alloc_skb(0, GFP_ATOMIC);
} else {
skb = skb_clone(orig_skb, GFP_ATOMIC);
+
+ if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ return;
+ }
}
if (!skb)
return;
@@ -4550,9 +4899,9 @@
typeof(IPPROTO_IP) proto,
unsigned int off)
{
- switch (proto) {
- int err;
+ int err;
+ switch (proto) {
case IPPROTO_TCP:
err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
off + MAX_TCP_HDR_LEN);
@@ -4595,7 +4944,7 @@
if (err < 0)
goto out;
- if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+ if (ip_is_fragment(ip_hdr(skb)))
fragment = true;
off = ip_hdrlen(skb);
@@ -4962,13 +5311,13 @@
skb->skb_iif = 0;
skb->ignore_df = 0;
skb_dst_drop(skb);
- secpath_reset(skb);
- nf_reset(skb);
+ skb_ext_reset(skb);
+ nf_reset_ct(skb);
nf_reset_trace(skb);
#ifdef CONFIG_NET_SWITCHDEV
skb->offload_fwd_mark = 0;
- skb->offload_mr_fwd_mark = 0;
+ skb->offload_l3_fwd_mark = 0;
#endif
if (!xnet)
@@ -5060,6 +5409,8 @@
* - L2+L3+L4+payload size (e.g. sanity check before passing to driver)
*
* This is a helper to do that correctly considering GSO_BY_FRAGS.
+ *
+ * @skb: GSO skb
*
* @seg_len: The segmented length (from skb_gso_*_seglen). In the
* GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
@@ -5246,7 +5597,7 @@
int err;
if (likely(skb_vlan_tag_present(skb))) {
- skb->vlan_tci = 0;
+ __vlan_hwaccel_clear_tag(skb);
} else {
if (unlikely(!eth_type_vlan(skb->protocol)))
return 0;
@@ -5298,6 +5649,252 @@
return 0;
}
EXPORT_SYMBOL(skb_vlan_push);
+
+/**
+ * skb_eth_pop() - Drop the Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ *
+ * Drop the Ethernet header of @skb.
+ *
+ * Expects that skb->data points to the mac header and that no VLAN tags are
+ * present.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_pop(struct sk_buff *skb)
+{
+ if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
+ skb_network_offset(skb) < ETH_HLEN)
+ return -EPROTO;
+
+ skb_pull_rcsum(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ return 0;
+}
+EXPORT_SYMBOL(skb_eth_pop);
+
+/**
+ * skb_eth_push() - Add a new Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ * @dst: Destination MAC address of the new header
+ * @src: Source MAC address of the new header
+ *
+ * Prepend @skb with a new Ethernet header.
+ *
+ * Expects that skb->data points to the mac header, which must be empty.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+ const unsigned char *src)
+{
+ struct ethhdr *eth;
+ int err;
+
+ if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
+ return -EPROTO;
+
+ err = skb_cow_head(skb, sizeof(*eth));
+ if (err < 0)
+ return err;
+
+ skb_push(skb, sizeof(*eth));
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ eth = eth_hdr(skb);
+ ether_addr_copy(eth->h_dest, dst);
+ ether_addr_copy(eth->h_source, src);
+ eth->h_proto = skb->protocol;
+
+ skb_postpush_rcsum(skb, eth, sizeof(*eth));
+
+ return 0;
+}
+EXPORT_SYMBOL(skb_eth_push);
+
+/* Update the ethertype of hdr and the skb csum value if required. */
+static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
+ __be16 ethertype)
+{
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ __be16 diff[] = { ~hdr->h_proto, ethertype };
+
+ skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
+ }
+
+ hdr->h_proto = ethertype;
+}
+
+/**
+ * skb_mpls_push() - push a new MPLS header after mac_len bytes from start of
+ * the packet
+ *
+ * @skb: buffer
+ * @mpls_lse: MPLS label stack entry to push
+ * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ * @mac_len: length of the MAC header
+ * @ethernet: flag to indicate if the resulting packet after skb_mpls_push is
+ * ethernet
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+ int mac_len, bool ethernet)
+{
+ struct mpls_shim_hdr *lse;
+ int err;
+
+ if (unlikely(!eth_p_mpls(mpls_proto)))
+ return -EINVAL;
+
+ /* Networking stack does not allow simultaneous Tunnel and MPLS GSO. */
+ if (skb->encapsulation)
+ return -EINVAL;
+
+ err = skb_cow_head(skb, MPLS_HLEN);
+ if (unlikely(err))
+ return err;
+
+ if (!skb->inner_protocol) {
+ skb_set_inner_network_header(skb, skb_network_offset(skb));
+ skb_set_inner_protocol(skb, skb->protocol);
+ }
+
+ skb_push(skb, MPLS_HLEN);
+ memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+ mac_len);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, mac_len);
+ skb_reset_mac_len(skb);
+
+ lse = mpls_hdr(skb);
+ lse->label_stack_entry = mpls_lse;
+ skb_postpush_rcsum(skb, lse, MPLS_HLEN);
+
+ if (ethernet && mac_len >= ETH_HLEN)
+ skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto);
+ skb->protocol = mpls_proto;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_push);
+
+/**
+ * skb_mpls_pop() - pop the outermost MPLS header
+ *
+ * @skb: buffer
+ * @next_proto: ethertype of header after popped MPLS header
+ * @mac_len: length of the MAC header
+ * @ethernet: flag to indicate if the packet is ethernet
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len,
+ bool ethernet)
+{
+ int err;
+
+ if (unlikely(!eth_p_mpls(skb->protocol)))
+ return 0;
+
+ err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
+ if (unlikely(err))
+ return err;
+
+ skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
+ memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+ mac_len);
+
+ __skb_pull(skb, MPLS_HLEN);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, mac_len);
+
+ if (ethernet && mac_len >= ETH_HLEN) {
+ struct ethhdr *hdr;
+
+ /* use mpls_hdr() to get ethertype to account for VLANs. */
+ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
+ skb_mod_eth_type(skb, hdr, next_proto);
+ }
+ skb->protocol = next_proto;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_pop);
+
+/**
+ * skb_mpls_update_lse() - modify outermost MPLS header and update csum
+ *
+ * @skb: buffer
+ * @mpls_lse: new MPLS label stack entry to update to
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse)
+{
+ int err;
+
+ if (unlikely(!eth_p_mpls(skb->protocol)))
+ return -EINVAL;
+
+ err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+ if (unlikely(err))
+ return err;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ __be32 diff[] = { ~mpls_hdr(skb)->label_stack_entry, mpls_lse };
+
+ skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
+ }
+
+ mpls_hdr(skb)->label_stack_entry = mpls_lse;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(skb_mpls_update_lse);
+
+/**
+ * skb_mpls_dec_ttl() - decrement the TTL of the outermost MPLS header
+ *
+ * @skb: buffer
+ *
+ * Expects skb->data at mac header.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_mpls_dec_ttl(struct sk_buff *skb)
+{
+ u32 lse;
+ u8 ttl;
+
+ if (unlikely(!eth_p_mpls(skb->protocol)))
+ return -EINVAL;
+
+ if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+ return -ENOMEM;
+
+ lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry);
+ ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+ if (!--ttl)
+ return -EINVAL;
+
+ lse &= ~MPLS_LS_TTL_MASK;
+ lse |= ttl << MPLS_LS_TTL_SHIFT;
+
+ return skb_mpls_update_lse(skb, cpu_to_be32(lse));
+}
+EXPORT_SYMBOL_GPL(skb_mpls_dec_ttl);
/**
* alloc_skb_with_frags - allocate skb with page frags
@@ -5421,11 +6018,7 @@
skb->head = data;
skb->data = data;
skb->head_frag = 0;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->end = size;
-#else
- skb->end = skb->head + size;
-#endif
+ skb_set_end_offset(skb, size);
skb_set_tail_pointer(skb, skb_headlen(skb));
skb_headers_offset_update(skb, 0);
skb->cloned = 0;
@@ -5517,8 +6110,7 @@
size = SKB_WITH_OVERHEAD(ksize(data));
memcpy((struct skb_shared_info *)(data + size),
- skb_shinfo(skb), offsetof(struct skb_shared_info,
- frags[skb_shinfo(skb)->nr_frags]));
+ skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0]));
if (skb_orphan_frags(skb, gfp_mask)) {
kfree(data);
return -ENOMEM;
@@ -5539,7 +6131,7 @@
* where splitting is expensive.
* 2. Split is accurately. We make this.
*/
- shinfo->frags[0].page_offset += off - pos;
+ skb_frag_off_add(&shinfo->frags[0], off - pos);
skb_frag_size_sub(&shinfo->frags[0], off - pos);
}
skb_frag_ref(skb, i);
@@ -5564,11 +6156,7 @@
skb->head = data;
skb->head_frag = 0;
skb->data = data;
-#ifdef NET_SKBUFF_DATA_USES_OFFSET
- skb->end = size;
-#else
- skb->end = skb->head + size;
-#endif
+ skb_set_end_offset(skb, size);
skb_reset_tail_pointer(skb);
skb_headers_offset_update(skb, 0);
skb->cloned = 0;
@@ -5642,4 +6230,181 @@
*/
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
}
-EXPORT_SYMBOL_GPL(skb_condense);
+
+#ifdef CONFIG_SKB_EXTENSIONS
+static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
+{
+ return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
+}
+
+/**
+ * __skb_ext_alloc - allocate a new skb extensions storage
+ *
+ * @flags: See kmalloc().
+ *
+ * Returns the newly allocated pointer. The pointer can later attached to a
+ * skb via __skb_ext_set().
+ * Note: caller must handle the skb_ext as an opaque data.
+ */
+struct skb_ext *__skb_ext_alloc(gfp_t flags)
+{
+ struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, flags);
+
+ if (new) {
+ memset(new->offset, 0, sizeof(new->offset));
+ refcount_set(&new->refcnt, 1);
+ }
+
+ return new;
+}
+
+static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
+ unsigned int old_active)
+{
+ struct skb_ext *new;
+
+ if (refcount_read(&old->refcnt) == 1)
+ return old;
+
+ new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
+ if (!new)
+ return NULL;
+
+ memcpy(new, old, old->chunks * SKB_EXT_ALIGN_VALUE);
+ refcount_set(&new->refcnt, 1);
+
+#ifdef CONFIG_XFRM
+ if (old_active & (1 << SKB_EXT_SEC_PATH)) {
+ struct sec_path *sp = skb_ext_get_ptr(old, SKB_EXT_SEC_PATH);
+ unsigned int i;
+
+ for (i = 0; i < sp->len; i++)
+ xfrm_state_hold(sp->xvec[i]);
+ }
+#endif
+ __skb_ext_put(old);
+ return new;
+}
+
+/**
+ * __skb_ext_set - attach the specified extension storage to this skb
+ * @skb: buffer
+ * @id: extension id
+ * @ext: extension storage previously allocated via __skb_ext_alloc()
+ *
+ * Existing extensions, if any, are cleared.
+ *
+ * Returns the pointer to the extension.
+ */
+void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
+ struct skb_ext *ext)
+{
+ unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext);
+
+ skb_ext_put(skb);
+ newlen = newoff + skb_ext_type_len[id];
+ ext->chunks = newlen;
+ ext->offset[id] = newoff;
+ skb->extensions = ext;
+ skb->active_extensions = 1 << id;
+ return skb_ext_get_ptr(ext, id);
+}
+
+/**
+ * skb_ext_add - allocate space for given extension, COW if needed
+ * @skb: buffer
+ * @id: extension to allocate space for
+ *
+ * Allocates enough space for the given extension.
+ * If the extension is already present, a pointer to that extension
+ * is returned.
+ *
+ * If the skb was cloned, COW applies and the returned memory can be
+ * modified without changing the extension space of clones buffers.
+ *
+ * Returns pointer to the extension or NULL on allocation failure.
+ */
+void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
+{
+ struct skb_ext *new, *old = NULL;
+ unsigned int newlen, newoff;
+
+ if (skb->active_extensions) {
+ old = skb->extensions;
+
+ new = skb_ext_maybe_cow(old, skb->active_extensions);
+ if (!new)
+ return NULL;
+
+ if (__skb_ext_exist(new, id))
+ goto set_active;
+
+ newoff = new->chunks;
+ } else {
+ newoff = SKB_EXT_CHUNKSIZEOF(*new);
+
+ new = __skb_ext_alloc(GFP_ATOMIC);
+ if (!new)
+ return NULL;
+ }
+
+ newlen = newoff + skb_ext_type_len[id];
+ new->chunks = newlen;
+ new->offset[id] = newoff;
+set_active:
+ skb->extensions = new;
+ skb->active_extensions |= 1 << id;
+ return skb_ext_get_ptr(new, id);
+}
+EXPORT_SYMBOL(skb_ext_add);
+
+#ifdef CONFIG_XFRM
+static void skb_ext_put_sp(struct sec_path *sp)
+{
+ unsigned int i;
+
+ for (i = 0; i < sp->len; i++)
+ xfrm_state_put(sp->xvec[i]);
+}
+#endif
+
+void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id)
+{
+ struct skb_ext *ext = skb->extensions;
+
+ skb->active_extensions &= ~(1 << id);
+ if (skb->active_extensions == 0) {
+ skb->extensions = NULL;
+ __skb_ext_put(ext);
+#ifdef CONFIG_XFRM
+ } else if (id == SKB_EXT_SEC_PATH &&
+ refcount_read(&ext->refcnt) == 1) {
+ struct sec_path *sp = skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH);
+
+ skb_ext_put_sp(sp);
+ sp->len = 0;
+#endif
+ }
+}
+EXPORT_SYMBOL(__skb_ext_del);
+
+void __skb_ext_put(struct skb_ext *ext)
+{
+ /* If this is last clone, nothing can increment
+ * it after check passes. Avoids one atomic op.
+ */
+ if (refcount_read(&ext->refcnt) == 1)
+ goto free_now;
+
+ if (!refcount_dec_and_test(&ext->refcnt))
+ return;
+free_now:
+#ifdef CONFIG_XFRM
+ if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH))
+ skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH));
+#endif
+
+ kmem_cache_free(skbuff_ext_cache, ext);
+}
+EXPORT_SYMBOL(__skb_ext_put);
+#endif /* CONFIG_SKB_EXTENSIONS */
--
Gitblit v1.6.2