diff options
Diffstat (limited to 'net/core/skbuff.c')
| -rw-r--r-- | net/core/skbuff.c | 604 |
1 files changed, 419 insertions, 185 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e59840010d45..fe00d1208167 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -36,6 +36,8 @@ * The functions in this file will not compile correctly with gcc 2.4.x */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -67,10 +69,9 @@ #include <asm/uaccess.h> #include <trace/events/skb.h> +#include <linux/highmem.h> -#include "kmap_skb.h" - -static struct kmem_cache *skbuff_head_cache __read_mostly; +struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; static void sock_pipe_buf_release(struct pipe_inode_info *pipe, @@ -119,11 +120,10 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { */ static void skb_over_panic(struct sk_buff *skb, int sz, void *here) { - printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + __func__, here, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); BUG(); } @@ -138,14 +138,50 @@ static void skb_over_panic(struct sk_buff *skb, int sz, void *here) static void skb_under_panic(struct sk_buff *skb, int sz, void *here) { - printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + __func__, here, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); BUG(); } + +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free + */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) +void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, + bool *pfmemalloc) +{ + void *obj; + bool ret_pfmemalloc = false; + + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; +} + /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the * [BEEP] leaks. @@ -156,26 +192,33 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone, int node) + int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; + + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; - cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); @@ -190,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_node_track_caller(size, gfp_mask, node); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; /* kmalloc(size) might give us more room than requested. @@ -208,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, memset(skb, 0, offsetof(struct sk_buff, tail)); /* Account for allocated memory : skb + skb->head */ skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -223,7 +267,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(&shinfo->dataref, 1); kmemcheck_annotate_variable(shinfo->destructor_arg); - if (fclone) { + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); @@ -233,6 +277,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; @@ -246,6 +291,7 @@ EXPORT_SYMBOL(__alloc_skb); /** * build_skb - build a network buffer * @data: data buffer provided by caller + * @frag_size: size of fragment, 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() @@ -259,20 +305,21 @@ 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) +struct sk_buff *build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; - unsigned int size; + unsigned int size = frag_size ? : ksize(data); skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); if (!skb) return NULL; - size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); 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; @@ -292,6 +339,63 @@ struct sk_buff *build_skb(void *data) } EXPORT_SYMBOL(build_skb); +struct netdev_alloc_cache { + struct page *page; + unsigned int offset; + unsigned int pagecnt_bias; +}; +static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); + +#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES) + +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) +{ + struct netdev_alloc_cache *nc; + void *data = NULL; + unsigned long flags; + + local_irq_save(flags); + nc = &__get_cpu_var(netdev_alloc_cache); + if (unlikely(!nc->page)) { +refill: + nc->page = alloc_page(gfp_mask); + if (unlikely(!nc->page)) + goto end; +recycle: + atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS); + nc->pagecnt_bias = NETDEV_PAGECNT_BIAS; + nc->offset = 0; + } + + if (nc->offset + fragsz > PAGE_SIZE) { + /* avoid unnecessary locked operations if possible */ + if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) || + atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count)) + goto recycle; + goto refill; + } + + data = page_address(nc->page) + nc->offset; + nc->offset += fragsz; + nc->pagecnt_bias--; +end: + 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) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} +EXPORT_SYMBOL(netdev_alloc_frag); + /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on @@ -306,11 +410,29 @@ EXPORT_SYMBOL(build_skb); * %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) + unsigned int length, gfp_t gfp_mask) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + if (likely(data)) { + skb = build_skb(data, fragsz); + if (unlikely(!skb)) + put_page(virt_to_head_page(data)); + } + } else { + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); + } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -329,28 +451,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, } EXPORT_SYMBOL(skb_add_rx_frag); -/** - * dev_alloc_skb - allocate an skbuff for receiving - * @length: length to allocate - * - * Allocate a new &sk_buff and assign it a usage count of one. The - * buffer has unspecified 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. Although this function - * allocates memory it can be called from an interrupt. - */ -struct sk_buff *dev_alloc_skb(unsigned int length) -{ - /* - * There is more code here than it seems: - * __dev_alloc_skb is an inline - */ - return __dev_alloc_skb(length, GFP_ATOMIC); -} -EXPORT_SYMBOL(dev_alloc_skb); - static void skb_drop_list(struct sk_buff **listp) { struct sk_buff *list = *listp; @@ -377,6 +477,14 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static void skb_free_head(struct sk_buff *skb) +{ + if (skb->head_frag) + put_page(virt_to_head_page(skb->head)); + else + kfree(skb->head); +} + static void skb_release_data(struct sk_buff *skb) { if (!skb->cloned || @@ -403,7 +511,7 @@ static void skb_release_data(struct sk_buff *skb) if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); - kfree(skb->head); + skb_free_head(skb); } } @@ -605,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #if IS_ENABLED(CONFIG_IP_VS) new->ipvs_property = old->ipvs_property; #endif + new->pfmemalloc = old->pfmemalloc; new->protocol = old->protocol; new->mark = old->mark; new->skb_iif = old->skb_iif; @@ -645,6 +754,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(tail); C(end); C(head); + C(head_frag); C(data); C(truesize); atomic_set(&n->users, 1); @@ -673,7 +783,8 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); -/* skb_copy_ubufs - copy userspace skb frags buffers to kernel +/** + * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify * @gfp_mask: allocation priority * @@ -698,7 +809,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) u8 *vaddr; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - page = alloc_page(GFP_ATOMIC); + page = alloc_page(gfp_mask); if (!page) { while (head) { struct page *next = (struct page *)head->private; @@ -707,31 +818,31 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) } return -ENOMEM; } - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(page_address(page), vaddr + f->page_offset, skb_frag_size(f)); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); page->private = (unsigned long)head; head = page; } /* skb frags release userspace buffers */ - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + for (i = 0; i < num_frags; i++) skb_frag_unref(skb, i); uarg->callback(uarg); /* skb frags point to kernel buffers */ - for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) { - __skb_fill_page_desc(skb, i-1, head, 0, - skb_shinfo(skb)->frags[i - 1].size); + for (i = num_frags - 1; i >= 0; i--) { + __skb_fill_page_desc(skb, i, head, 0, + skb_shinfo(skb)->frags[i].size); head = (struct page *)head->private; } skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; return 0; } - +EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff @@ -751,10 +862,8 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) - return NULL; - } + if (skb_orphan_frags(skb, gfp_mask)) + return NULL; n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && @@ -763,6 +872,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; @@ -799,6 +911,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) +{ + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; +} + /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy @@ -819,8 +938,9 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); - unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len; - struct sk_buff *n = alloc_skb(size, gfp_mask); + unsigned int size = skb_end_offset(skb) + skb->data_len; + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -855,7 +975,8 @@ EXPORT_SYMBOL(skb_copy); struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { unsigned int size = skb_headlen(skb) + headroom; - struct sk_buff *n = alloc_skb(size, gfp_mask); + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) goto out; @@ -874,12 +995,10 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) if (skb_shinfo(skb)->nr_frags) { int i; - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) { - kfree_skb(n); - n = NULL; - goto out; - } + if (skb_orphan_frags(skb, gfp_mask)) { + kfree_skb(n); + n = NULL; + goto out; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; @@ -920,9 +1039,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; - int size = nhead + (skb_end_pointer(skb) - skb->head) + ntail; + int size = nhead + skb_end_offset(skb) + ntail; long off; - bool fastpath; BUG_ON(nhead < 0); @@ -931,29 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - /* Check if we can avoid taking references on fragments if we own - * the last reference on skb->head. (see skb_release_data()) - */ - if (!skb->cloned) - fastpath = true; - else { - int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; - fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; - } - - if (fastpath && - size + sizeof(struct skb_shared_info) <= ksize(skb->head)) { - memmove(skb->head + size, skb_shinfo(skb), - offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); - memmove(skb->head + nhead, skb->head, - skb_tail_pointer(skb) - skb->head); - off = nhead; - goto adjust_others; - } - - data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(ksize(data)); @@ -967,14 +1066,15 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - if (fastpath) { - kfree(skb->head); - } else { + /* + * if shinfo is shared we must drop the old head gracefully, but if it + * is not we can just drop the old head and let the existing refcount + * be since all we did is relocate the values + */ + if (skb_cloned(skb)) { /* copy this zero copy skb frags */ - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, gfp_mask)) - goto nofrags; - } + if (skb_orphan_frags(skb, gfp_mask)) + goto nofrags; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_frag_ref(skb, i); @@ -982,11 +1082,13 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_clone_fraglist(skb); skb_release_data(skb); + } else { + skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; -adjust_others: + skb->head_frag = 0; skb->data += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; @@ -1062,8 +1164,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; int off; @@ -1275,7 +1378,7 @@ drop_pages: return -ENOMEM; nfrag->next = frag->next; - kfree_skb(frag); + consume_skb(frag); frag = nfrag; *fragp = frag; } @@ -1487,21 +1590,22 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(to, - vaddr + skb_shinfo(skb)->frags[i].page_offset+ - offset - start, copy); - kunmap_skb_frag(vaddr); + vaddr + f->page_offset + offset - start, + copy); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1547,9 +1651,9 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) put_page(spd->pages[i]); } -static inline struct page *linear_to_page(struct page *page, unsigned int *len, - unsigned int *offset, - struct sk_buff *skb, struct sock *sk) +static struct page *linear_to_page(struct page *page, unsigned int *len, + unsigned int *offset, + struct sk_buff *skb, struct sock *sk) { struct page *p = sk->sk_sndmsg_page; unsigned int off; @@ -1565,6 +1669,9 @@ new_page: } else { unsigned int mlen; + /* If we are the only user of the page, we can reset offset */ + if (page_count(p) == 1) + sk->sk_sndmsg_off = 0; off = sk->sk_sndmsg_off; mlen = PAGE_SIZE - off; if (mlen < 64 && mlen < *len) { @@ -1578,36 +1685,48 @@ new_page: memcpy(page_address(p) + off, page_address(page) + *offset, *len); sk->sk_sndmsg_off += *len; *offset = off; - get_page(p); return p; } +static bool spd_can_coalesce(const struct splice_pipe_desc *spd, + struct page *page, + unsigned int offset) +{ + return spd->nr_pages && + spd->pages[spd->nr_pages - 1] == page && + (spd->partial[spd->nr_pages - 1].offset + + spd->partial[spd->nr_pages - 1].len == offset); +} + /* * Fill page/offset/length into spd, if it can hold more pages. */ -static inline int spd_fill_page(struct splice_pipe_desc *spd, - struct pipe_inode_info *pipe, struct page *page, - unsigned int *len, unsigned int offset, - struct sk_buff *skb, int linear, - struct sock *sk) +static bool spd_fill_page(struct splice_pipe_desc *spd, + struct pipe_inode_info *pipe, struct page *page, + unsigned int *len, unsigned int offset, + struct sk_buff *skb, bool linear, + struct sock *sk) { - if (unlikely(spd->nr_pages == pipe->buffers)) - return 1; + if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) + return true; if (linear) { page = linear_to_page(page, len, &offset, skb, sk); if (!page) - return 1; - } else - get_page(page); - + return true; + } + if (spd_can_coalesce(spd, page, offset)) { + spd->partial[spd->nr_pages - 1].len += *len; + return false; + } + get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; - return 0; + return false; } static inline void __segment_seek(struct page **page, unsigned int *poff, @@ -1624,20 +1743,20 @@ static inline void __segment_seek(struct page **page, unsigned int *poff, *plen -= off; } -static inline int __splice_segment(struct page *page, unsigned int poff, - unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd, int linear, - struct sock *sk, - struct pipe_inode_info *pipe) +static bool __splice_segment(struct page *page, unsigned int poff, + unsigned int plen, unsigned int *off, + unsigned int *len, struct sk_buff *skb, + struct splice_pipe_desc *spd, bool linear, + struct sock *sk, + struct pipe_inode_info *pipe) { if (!*len) - return 1; + return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; - return 0; + return false; } /* ignore any bits we already processed */ @@ -1653,34 +1772,38 @@ static inline int __splice_segment(struct page *page, unsigned int poff, flen = min_t(unsigned int, flen, PAGE_SIZE - poff); if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) - return 1; + return true; __segment_seek(&page, &poff, &plen, flen); *len -= flen; } while (*len && plen); - return 0; + return false; } /* - * Map linear and fragment data from the skb to spd. It reports failure if the + * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ -static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, - unsigned int *offset, unsigned int *len, - struct splice_pipe_desc *spd, struct sock *sk) +static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, + unsigned int *offset, unsigned int *len, + struct splice_pipe_desc *spd, struct sock *sk) { int seg; - /* - * map the linear part + /* map the linear part : + * If skb->head_frag is set, this 'linear' part is backed by a + * fragment, and if the head is not shared with any clones then + * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, 1, sk, pipe)) - return 1; + offset, len, skb, spd, + skb_head_is_locked(skb), + sk, pipe)) + return true; /* * then map the fragments @@ -1690,11 +1813,11 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, 0, sk, pipe)) - return 1; + offset, len, skb, spd, false, sk, pipe)) + return true; } - return 0; + return false; } /* @@ -1707,11 +1830,12 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[MAX_SKB_FRAGS]; + struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, @@ -1720,9 +1844,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct sock *sk = skb->sk; int ret = 0; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - /* * __skb_splice_bits() only fails if the output has no room left, * so no point in going over the frag_list for the error case. @@ -1758,7 +1879,6 @@ done: lock_sock(sk); } - splice_shrink_spd(pipe, &spd); return ret; } @@ -1806,10 +1926,10 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); memcpy(vaddr + frag->page_offset + offset - start, from, copy); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1869,21 +1989,21 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial(vaddr + frag->page_offset + offset - start, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -1955,12 +2075,12 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial_copy_nocheck(vaddr + frag->page_offset + offset - start, to, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -2480,7 +2600,7 @@ next_skb: if (abs_offset < block_limit) { if (!st->frag_data) - st->frag_data = kmap_skb_frag(frag); + st->frag_data = kmap_atomic(skb_frag_page(frag)); *data = (u8 *) st->frag_data + frag->page_offset + (abs_offset - st->stepped_offset); @@ -2489,7 +2609,7 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } @@ -2498,7 +2618,7 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } @@ -2526,7 +2646,7 @@ EXPORT_SYMBOL(skb_seq_read); void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); @@ -2574,7 +2694,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, EXPORT_SYMBOL(skb_find_text); /** - * skb_append_datato_frags: - append the user data to a skb + * skb_append_datato_frags - append the user data to a skb * @sk: sock structure * @skb: skb structure to be appened with user data. * @getfrag: call back function to be used for getting the user data @@ -2718,19 +2838,19 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) if (unlikely(!nskb)) goto err; - hsize = skb_end_pointer(nskb) - nskb->head; + hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } - nskb->truesize += skb_end_pointer(nskb) - nskb->head - - hsize; + nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { - nskb = alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC); + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (unlikely(!nskb)) goto err; @@ -2843,6 +2963,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) unsigned int len = skb_gro_len(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); + unsigned int delta_truesize; if (p->len + len >= 65536) return -E2BIG; @@ -2872,11 +2993,41 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) frag->page_offset += offset; skb_frag_size_sub(frag, offset); + /* all fragments truesize : remove (head size + sk_buff) */ + delta_truesize = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + skb->truesize -= skb->data_len; skb->len -= skb->data_len; skb->data_len = 0; - NAPI_GRO_CB(skb)->free = 1; + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + return -E2BIG; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + frag->page.p = page; + frag->page_offset = first_offset; + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; @@ -2918,7 +3069,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: - p->truesize += skb->truesize - len; + delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; @@ -2938,7 +3089,7 @@ merge: done: NAPI_GRO_CB(p)->count++; p->data_len += len; - p->truesize += len; + p->truesize += delta_truesize; p->len += len; NAPI_GRO_CB(skb)->same_flow = 1; @@ -3166,7 +3317,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) int len = skb->len; if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) + (unsigned int)sk->sk_rcvbuf) return -ENOMEM; skb_orphan(skb); @@ -3260,10 +3411,8 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { if (unlikely(start > skb_headlen(skb)) || unlikely((int)start + off > skb_headlen(skb) - 2)) { - if (net_ratelimit()) - printk(KERN_WARNING - "bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", + start, off, skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; @@ -3275,8 +3424,93 @@ EXPORT_SYMBOL_GPL(skb_partial_csum_set); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { - if (net_ratelimit()) - pr_warning("%s: received packets cannot be forwarded" - " while LRO is enabled\n", skb->dev->name); + net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", + skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); + +void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) +{ + if (head_stolen) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); +} +EXPORT_SYMBOL(kfree_skb_partial); + +/** + * skb_try_coalesce - try to merge skb to prior one + * @to: prior buffer + * @from: buffer to add + * @fragstolen: pointer to boolean + * @delta_truesize: how much more was allocated than was requested + */ +bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, + bool *fragstolen, int *delta_truesize) +{ + int i, delta, len = from->len; + + *fragstolen = false; + + if (skb_cloned(to)) + return false; + + if (len <= skb_tailroom(to)) { + BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); + *delta_truesize = 0; + return true; + } + + if (skb_has_frag_list(to) || skb_has_frag_list(from)) + return false; + + if (skb_headlen(from) != 0) { + struct page *page; + unsigned int offset; + + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + return false; + + if (skb_head_is_locked(from)) + return false; + + delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + + skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + page, offset, skb_headlen(from)); + *fragstolen = true; + } else { + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + return false; + + delta = from->truesize - + SKB_TRUESIZE(skb_end_pointer(from) - from->head); + } + + WARN_ON_ONCE(delta < len); + + memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, + skb_shinfo(from)->frags, + skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); + skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + + if (!skb_cloned(from)) + skb_shinfo(from)->nr_frags = 0; + + /* if the skb is cloned this does nothing since we set nr_frags to 0 */ + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) + skb_frag_ref(from, i); + + to->truesize += delta; + to->len += len; + to->data_len += len; + + *delta_truesize = delta; + return true; +} +EXPORT_SYMBOL(skb_try_coalesce); |