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.
* __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 = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+ cache = (flags & SKB_ALLOC_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);
*/
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.
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;
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);
atomic_set(fclone_ref, 1);
child->fclone = SKB_FCLONE_UNAVAILABLE;
+ child->pfmemalloc = pfmemalloc;
}
out:
return 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);
-/**
- * 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)
+#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;
nc = &__get_cpu_var(netdev_alloc_cache);
if (unlikely(!nc->page)) {
refill:
- nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ 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 (likely(nc->page)) {
- if (nc->offset + fragsz > PAGE_SIZE) {
- put_page(nc->page);
- goto refill;
- }
- data = page_address(nc->page) + nc->offset;
- nc->offset += fragsz;
- get_page(nc->page);
+
+ 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);
/**
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)) {
- void *data = netdev_alloc_frag(fragsz);
+ 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);
if (likely(data)) {
skb = build_skb(data, fragsz);
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);
#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;
}
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
*
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;
}
/* 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
{
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 &&
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;
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
{
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;
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;
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];
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));
*/
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);
/*
* 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;
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
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;
projects / platform / adaptation / renesas_rcar / renesas_kernel.git / blobdiff