summaryrefslogtreecommitdiffstats
path: root/net/core/skbuff.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/skbuff.c')
-rw-r--r--net/core/skbuff.c212
1 files changed, 141 insertions, 71 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 368f65c15e4f..cdc28598f4ef 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -145,6 +145,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
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.
@@ -155,8 +192,10 @@ 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
@@ -167,14 +206,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
* %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);
@@ -189,7 +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.
@@ -207,6 +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;
@@ -222,7 +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);
@@ -232,6 +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;
@@ -294,55 +340,74 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
EXPORT_SYMBOL(build_skb);
struct netdev_alloc_cache {
- struct page *page;
- unsigned int offset;
- unsigned int pagecnt_bias;
+ 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);
-#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
+#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768)
+#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER)
+#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE
-/**
- * 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)
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
struct netdev_alloc_cache *nc;
void *data = NULL;
+ int order;
unsigned long flags;
local_irq_save(flags);
nc = &__get_cpu_var(netdev_alloc_cache);
- if (unlikely(!nc->page)) {
+ if (unlikely(!nc->frag.page)) {
refill:
- nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
- if (unlikely(!nc->page))
- goto end;
+ for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
+ gfp_t gfp = gfp_mask;
+
+ if (order)
+ gfp |= __GFP_COMP | __GFP_NOWARN;
+ nc->frag.page = alloc_pages(gfp, order);
+ if (likely(nc->frag.page))
+ break;
+ if (--order < 0)
+ goto end;
+ }
+ nc->frag.size = PAGE_SIZE << order;
recycle:
- atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS);
- nc->pagecnt_bias = NETDEV_PAGECNT_BIAS;
- nc->offset = 0;
+ atomic_set(&nc->frag.page->_count, NETDEV_PAGECNT_MAX_BIAS);
+ nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
+ nc->frag.offset = 0;
}
- if (nc->offset + fragsz > PAGE_SIZE) {
+ if (nc->frag.offset + fragsz > nc->frag.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))
+ if ((atomic_read(&nc->frag.page->_count) == nc->pagecnt_bias) ||
+ atomic_sub_and_test(nc->pagecnt_bias, &nc->frag.page->_count))
goto recycle;
goto refill;
}
- data = page_address(nc->page) + nc->offset;
- nc->offset += fragsz;
+ data = page_address(nc->frag.page) + nc->frag.offset;
+ nc->frag.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);
/**
@@ -366,7 +431,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
- void *data = netdev_alloc_frag(fragsz);
+ void *data;
+
+ if (sk_memalloc_socks())
+ gfp_mask |= __GFP_MEMALLOC;
+
+ data = __netdev_alloc_frag(fragsz, gfp_mask);
if (likely(data)) {
skb = build_skb(data, fragsz);
@@ -374,7 +444,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
put_page(virt_to_head_page(data));
}
} else {
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+ SKB_ALLOC_RX, NUMA_NO_NODE);
}
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
@@ -656,6 +727,7 @@ 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;
@@ -814,6 +886,9 @@ 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;
@@ -850,6 +925,13 @@ 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
@@ -871,7 +953,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
unsigned int size = skb_end_offset(skb) + skb->data_len;
- 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)
return NULL;
@@ -906,7 +989,8 @@ 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;
@@ -979,8 +1063,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
size = SKB_DATA_ALIGN(size);
- 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));
@@ -1092,8 +1178,9 @@ 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;
@@ -1582,38 +1669,19 @@ 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;
+ struct page_frag *pfrag = sk_page_frag(sk);
- if (!p) {
-new_page:
- p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0);
- if (!p)
- return NULL;
-
- off = sk->sk_sndmsg_off = 0;
- /* hold one ref to this page until it's full */
- } 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) {
- put_page(p);
- goto new_page;
- }
+ if (!sk_page_frag_refill(sk, pfrag))
+ return NULL;
- *len = min_t(unsigned int, *len, mlen);
- }
+ *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset);
- memcpy(page_address(p) + off, page_address(page) + *offset, *len);
- sk->sk_sndmsg_off += *len;
- *offset = off;
+ memcpy(page_address(pfrag->page) + pfrag->offset,
+ page_address(page) + *offset, *len);
+ *offset = pfrag->offset;
+ pfrag->offset += *len;
- return p;
+ return pfrag->page;
}
static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
@@ -2775,8 +2843,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
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;
@@ -3414,8 +3483,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
return false;
- delta = from->truesize -
- SKB_TRUESIZE(skb_end_pointer(from) - from->head);
+ delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from));
}
WARN_ON_ONCE(delta < len);
@@ -3428,7 +3496,9 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
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 */
+ /* if the skb is not 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);
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-06 21:15:47 +0000