diff options
Diffstat (limited to 'net/core/skbuff.c')
| -rw-r--r-- | net/core/skbuff.c | 474 |
1 files changed, 259 insertions, 215 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e4ac97c8477..b6a19ca0f99e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -328,95 +328,37 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } -EXPORT_SYMBOL(build_skb); - -struct netdev_alloc_cache { - struct page_frag frag; - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_count every time we allocate a fragment. - */ - 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 struct page *__page_frag_refill(struct netdev_alloc_cache *nc, - gfp_t gfp_mask) -{ - 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); - } - - 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) +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) { - struct netdev_alloc_cache *nc = this_cpu_ptr(cache); - struct page *page = nc->frag.page; - unsigned int size; - int offset; - - if (unlikely(!page)) { -refill: - 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; - - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - 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; - } + struct sk_buff *skb = __build_skb(data, frag_size); - 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; + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; } - - nc->pagecnt_bias--; - nc->frag.offset = offset; - - return page_address(page) + offset; + return skb; } +EXPORT_SYMBOL(build_skb); + +static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); +static DEFINE_PER_CPU(struct page_frag_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); - data = __alloc_page_frag(&netdev_alloc_cache, fragsz, gfp_mask); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, fragsz, gfp_mask); local_irq_restore(flags); return data; } @@ -436,7 +378,9 @@ 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); + struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); + + return __alloc_page_frag(nc, fragsz, gfp_mask); } void *napi_alloc_frag(unsigned int fragsz) @@ -446,76 +390,70 @@ void *napi_alloc_frag(unsigned int fragsz) EXPORT_SYMBOL(napi_alloc_frag); /** - * __alloc_rx_skb - allocate an skbuff for rx + * __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 - * @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 + * 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. */ -static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask, - int flags) +struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, + gfp_t gfp_mask) { - struct sk_buff *skb = NULL; - unsigned int fragsz = SKB_DATA_ALIGN(length) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + struct page_frag_cache *nc; + unsigned long flags; + struct sk_buff *skb; + bool pfmemalloc; + void *data; - if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { - void *data; + len += NET_SKB_PAD; - if (sk_memalloc_socks()) - gfp_mask |= __GFP_MEMALLOC; + if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); + if (!skb) + goto skb_fail; + goto skb_success; + } - data = (flags & SKB_ALLOC_NAPI) ? - __napi_alloc_frag(fragsz, gfp_mask) : - __netdev_alloc_frag(fragsz, gfp_mask); + len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + len = SKB_DATA_ALIGN(len); - if (likely(data)) { - skb = build_skb(data, fragsz); - if (unlikely(!skb)) - put_page(virt_to_head_page(data)); - } - } else { - skb = __alloc_skb(length, gfp_mask, - SKB_ALLOC_RX, NUMA_NO_NODE); - } - return skb; -} + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; -/** - * __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; + local_irq_save(flags); - length += NET_SKB_PAD; - skb = __alloc_rx_skb(length, gfp_mask, 0); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = __alloc_page_frag(nc, len, gfp_mask); + pfmemalloc = nc->pfmemalloc; - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD); - skb->dev = dev; + local_irq_restore(flags); + + if (unlikely(!data)) + return NULL; + + skb = __build_skb(data, len); + if (unlikely(!skb)) { + skb_free_frag(data); + return NULL; } + /* use OR instead of assignment to avoid clearing of bits in mask */ + if (pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +skb_success: + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + +skb_fail: return skb; } EXPORT_SYMBOL(__netdev_alloc_skb); @@ -533,19 +471,49 @@ EXPORT_SYMBOL(__netdev_alloc_skb); * * %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 *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + gfp_t gfp_mask) { + struct page_frag_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; + void *data; - length += NET_SKB_PAD + NET_IP_ALIGN; - skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI); + len += NET_SKB_PAD + NET_IP_ALIGN; - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - skb->dev = napi->dev; + if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); + if (!skb) + goto skb_fail; + goto skb_success; } + len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + len = SKB_DATA_ALIGN(len); + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __alloc_page_frag(nc, len, gfp_mask); + if (unlikely(!data)) + return NULL; + + skb = __build_skb(data, len); + if (unlikely(!skb)) { + skb_free_frag(data); + return NULL; + } + + /* use OR instead of assignment to avoid clearing of bits in mask */ + if (nc->pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +skb_success: + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + skb->dev = napi->dev; + +skb_fail: return skb; } EXPORT_SYMBOL(__napi_alloc_skb); @@ -593,10 +561,12 @@ static void skb_clone_fraglist(struct sk_buff *skb) static void skb_free_head(struct sk_buff *skb) { + unsigned char *head = skb->head; + if (skb->head_frag) - put_page(virt_to_head_page(skb->head)); + skb_free_frag(head); else - kfree(skb->head); + kfree(head); } static void skb_release_data(struct sk_buff *skb) @@ -1900,15 +1870,39 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, return false; } +ssize_t skb_socket_splice(struct sock *sk, + struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) +{ + int ret; + + /* Drop the socket lock, otherwise we have reverse + * locking dependencies between sk_lock and i_mutex + * here as compared to sendfile(). We enter here + * with the socket lock held, and splice_to_pipe() will + * grab the pipe inode lock. For sendfile() emulation, + * we call into ->sendpage() with the i_mutex lock held + * and networking will grab the socket lock. + */ + release_sock(sk); + ret = splice_to_pipe(pipe, spd); + lock_sock(sk); + + return ret; +} + /* * Map data from the skb to a pipe. Should handle both the linear part, * the fragments, and the frag list. It does NOT handle frag lists within * the frag list, if such a thing exists. We'd probably need to recurse to * handle that cleanly. */ -int skb_splice_bits(struct sk_buff *skb, unsigned int offset, +int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, - unsigned int flags) + unsigned int flags, + ssize_t (*splice_cb)(struct sock *, + struct pipe_inode_info *, + struct splice_pipe_desc *)) { struct partial_page partial[MAX_SKB_FRAGS]; struct page *pages[MAX_SKB_FRAGS]; @@ -1921,7 +1915,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; - struct sock *sk = skb->sk; int ret = 0; /* @@ -1944,23 +1937,12 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, } done: - if (spd.nr_pages) { - /* - * Drop the socket lock, otherwise we have reverse - * locking dependencies between sk_lock and i_mutex - * here as compared to sendfile(). We enter here - * with the socket lock held, and splice_to_pipe() will - * grab the pipe inode lock. For sendfile() emulation, - * we call into ->sendpage() with the i_mutex lock held - * and networking will grab the socket lock. - */ - release_sock(sk); - ret = splice_to_pipe(pipe, &spd); - lock_sock(sk); - } + if (spd.nr_pages) + ret = splice_cb(sk, pipe, &spd); return ret; } +EXPORT_SYMBOL_GPL(skb_splice_bits); /** * skb_store_bits - store bits from kernel buffer to skb @@ -2865,7 +2847,6 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) * @from: search offset * @to: search limit * @config: textsearch configuration - * @state: uninitialized textsearch state variable * * Finds a pattern in the skb data according to the specified * textsearch configuration. Use textsearch_next() to retrieve @@ -2873,17 +2854,17 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) * to the first occurrence or UINT_MAX if no match was found. */ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, - unsigned int to, struct ts_config *config, - struct ts_state *state) + unsigned int to, struct ts_config *config) { + struct ts_state state; unsigned int ret; config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; - skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state)); + skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); - ret = textsearch_find(config, state); + ret = textsearch_find(config, &state); return (ret <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); @@ -2946,6 +2927,24 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, } EXPORT_SYMBOL(skb_append_datato_frags); +int skb_append_pagefrags(struct sk_buff *skb, struct page *page, + int offset, size_t size) +{ + int i = skb_shinfo(skb)->nr_frags; + + if (skb_can_coalesce(skb, i, page, offset)) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); + } else if (i < MAX_SKB_FRAGS) { + get_page(page); + skb_fill_page_desc(skb, i, page, offset, size); + } else { + return -EMSGSIZE; + } + + return 0; +} +EXPORT_SYMBOL_GPL(skb_append_pagefrags); + /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update @@ -3207,10 +3206,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); - struct sk_buff *nskb, *lp, *p = *head; unsigned int len = skb_gro_len(skb); + struct sk_buff *lp, *p = *head; unsigned int delta_truesize; - unsigned int headroom; if (unlikely(p->len + len >= 65536)) return -E2BIG; @@ -3277,48 +3275,6 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } - /* switch back to head shinfo */ - pinfo = skb_shinfo(p); - - if (pinfo->frag_list) - goto merge; - if (skb_gro_len(p) != pinfo->gso_size) - return -E2BIG; - - headroom = skb_headroom(p); - nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); - if (unlikely(!nskb)) - return -ENOMEM; - - __copy_skb_header(nskb, p); - nskb->mac_len = p->mac_len; - - skb_reserve(nskb, headroom); - __skb_put(nskb, skb_gro_offset(p)); - - skb_set_mac_header(nskb, skb_mac_header(p) - p->data); - skb_set_network_header(nskb, skb_network_offset(p)); - skb_set_transport_header(nskb, skb_transport_offset(p)); - - __skb_pull(p, skb_gro_offset(p)); - memcpy(skb_mac_header(nskb), skb_mac_header(p), - p->data - skb_mac_header(p)); - - skb_shinfo(nskb)->frag_list = p; - skb_shinfo(nskb)->gso_size = pinfo->gso_size; - pinfo->gso_size = 0; - __skb_header_release(p); - NAPI_GRO_CB(nskb)->last = p; - - nskb->data_len += p->len; - nskb->truesize += p->truesize; - nskb->len += p->len; - - *head = nskb; - nskb->next = p->next; - p->next = NULL; - - p = nskb; merge: delta_truesize = skb->truesize; @@ -3796,7 +3752,6 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) } EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); - /** * skb_partial_csum_set - set up and verify partial csum values for packet * @skb: the skb to set @@ -4057,6 +4012,93 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) } EXPORT_SYMBOL(skb_checksum_setup); +/** + * skb_checksum_maybe_trim - maybe trims the given skb + * @skb: the skb to check + * @transport_len: the data length beyond the network header + * + * Checks whether the given skb has data beyond the given transport length. + * If so, returns a cloned skb trimmed to this transport length. + * Otherwise returns the provided skb. Returns NULL in error cases + * (e.g. transport_len exceeds skb length or out-of-memory). + * + * Caller needs to set the skb transport header and release the returned skb. + * Provided skb is consumed. + */ +static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb, + unsigned int transport_len) +{ + struct sk_buff *skb_chk; + unsigned int len = skb_transport_offset(skb) + transport_len; + int ret; + + if (skb->len < len) { + kfree_skb(skb); + return NULL; + } else if (skb->len == len) { + return skb; + } + + skb_chk = skb_clone(skb, GFP_ATOMIC); + kfree_skb(skb); + + if (!skb_chk) + return NULL; + + ret = pskb_trim_rcsum(skb_chk, len); + if (ret) { + kfree_skb(skb_chk); + return NULL; + } + + return skb_chk; +} + +/** + * skb_checksum_trimmed - validate checksum of an skb + * @skb: the skb to check + * @transport_len: the data length beyond the network header + * @skb_chkf: checksum function to use + * + * Applies the given checksum function skb_chkf to the provided skb. + * Returns a checked and maybe trimmed skb. Returns NULL on error. + * + * If the skb has data beyond the given transport length, then a + * trimmed & cloned skb is checked and returned. + * + * Caller needs to set the skb transport header and release the returned skb. + * Provided skb is consumed. + */ +struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, + unsigned int transport_len, + __sum16(*skb_chkf)(struct sk_buff *skb)) +{ + struct sk_buff *skb_chk; + unsigned int offset = skb_transport_offset(skb); + __sum16 ret; + + skb_chk = skb_checksum_maybe_trim(skb, transport_len); + if (!skb_chk) + return NULL; + + if (!pskb_may_pull(skb_chk, offset)) { + kfree_skb(skb_chk); + return NULL; + } + + __skb_pull(skb_chk, offset); + ret = skb_chkf(skb_chk); + __skb_push(skb_chk, offset); + + if (ret) { + kfree_skb(skb_chk); + return NULL; + } + + return skb_chk; +} +EXPORT_SYMBOL(skb_checksum_trimmed); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", @@ -4169,19 +4211,21 @@ EXPORT_SYMBOL(skb_try_coalesce); */ void skb_scrub_packet(struct sk_buff *skb, bool xnet) { - if (xnet) - skb_orphan(skb); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - skb->mark = 0; skb_sender_cpu_clear(skb); - skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); + + if (!xnet) + return; + + skb_orphan(skb); + skb->mark = 0; } EXPORT_SYMBOL_GPL(skb_scrub_packet); @@ -4423,7 +4467,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, while (order) { if (npages >= 1 << order) { - page = alloc_pages(gfp_mask | + page = alloc_pages((gfp_mask & ~__GFP_WAIT) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, |