net: do not deplete pfmemalloc reserve

[linux-2.6-block.git] / net / core / skbuff.c

/*
 *	Routines having to do with the 'struct sk_buff' memory handlers.
 *
 *	Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>
 *			Florian La Roche <rzsfl@rz.uni-sb.de>
 *
 *	Fixes:
 *		Alan Cox	:	Fixed the worst of the load
 *					balancer bugs.
 *		Dave Platt	:	Interrupt stacking fix.
 *	Richard Kooijman	:	Timestamp fixes.
 *		Alan Cox	:	Changed buffer format.
 *		Alan Cox	:	destructor hook for AF_UNIX etc.
 *		Linus Torvalds	:	Better skb_clone.
 *		Alan Cox	:	Added skb_copy.
 *		Alan Cox	:	Added all the changed routines Linus
 *					only put in the headers
 *		Ray VanTassle	:	Fixed --skb->lock in free
 *		Alan Cox	:	skb_copy copy arp field
 *		Andi Kleen	:	slabified it.
 *		Robert Olsson	:	Removed skb_head_pool
 *
 *	NOTE:
 *		The __skb_ routines should be called with interrupts
 *	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.
 */

/*
 *	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>
#include <linux/kmemcheck.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
#endif
#include <linux/string.h>
#include <linux/skbuff.h>
#include <linux/splice.h>
#include <linux/cache.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/scatterlist.h>
#include <linux/errqueue.h>
#include <linux/prefetch.h>
#include <linux/if_vlan.h>

#include <net/protocol.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>

#include <asm/uaccess.h>
#include <trace/events/skb.h>
#include <linux/highmem.h>
#include <linux/capability.h>
#include <linux/user_namespace.h>

struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;

/**
 *	skb_panic - private function for out-of-line support
 *	@skb:	buffer
 *	@sz:	size
 *	@addr:	address
 *	@msg:	skb_over_panic or skb_under_panic
 *
 *	Out-of-line support for skb_put() and skb_push().
 *	Called via the wrapper skb_over_panic() or skb_under_panic().
 *	Keep out of line to prevent kernel bloat.
 *	__builtin_return_address is not used because it is not always reliable.
 */
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",
		 msg, addr, skb->len, sz, skb->head, skb->data,
		 (unsigned long)skb->tail, (unsigned long)skb->end,
		 skb->dev ? skb->dev->name : "<NULL>");
	BUG();
}

static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
	skb_panic(skb, sz, addr, __func__);
}

static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr)
{
	skb_panic(skb, sz, addr, __func__);
}

/*
 * 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)

static 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.
 *
 */

struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node)
{
	struct sk_buff *skb;

	/* Get the HEAD */
	skb = kmem_cache_alloc_node(skbuff_head_cache,
				    gfp_mask & ~__GFP_DMA, node);
	if (!skb)
		goto out;

	/*
	 * Only clear those fields we need to clear, not those that we will
	 * actually initialise below. Hence, don't put any more fields after
	 * the tail pointer in struct sk_buff!
	 */
	memset(skb, 0, offsetof(struct sk_buff, tail));
	skb->head = NULL;
	skb->truesize = sizeof(struct sk_buff);
	atomic_set(&skb->users, 1);

	skb->mac_header = (typeof(skb->mac_header))~0U;
out:
	return skb;
}

/**
 *	__alloc_skb	-	allocate a network buffer
 *	@size: size to allocate
 *	@gfp_mask: allocation mask
 *	@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 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 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;

	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);
	if (!skb)
		goto out;
	prefetchw(skb);

	/* We do our best to align skb_shared_info on a separate cache
	 * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives
	 * aligned memory blocks, unless SLUB/SLAB debug is enabled.
	 * Both skb->head and skb_shared_info are cache line aligned.
	 */
	size = SKB_DATA_ALIGN(size);
	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
	if (!data)
		goto nodata;
	/* kmalloc(size) might give us more room than requested.
	 * Put skb_shared_info exactly at the end of allocated zone,
	 * to allow max possible filling before reallocation.
	 */
	size = SKB_WITH_OVERHEAD(ksize(data));
	prefetchw(data + size);

	/*
	 * Only clear those fields we need to clear, not those that we will
	 * actually initialise below. Hence, don't put any more fields after
	 * the tail pointer in struct sk_buff!
	 */
	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;
	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);
	kmemcheck_annotate_variable(shinfo->destructor_arg);

	if (flags & SKB_ALLOC_FCLONE) {
		struct sk_buff_fclones *fclones;

		fclones = container_of(skb, struct sk_buff_fclones, skb1);

		kmemcheck_annotate_bitfield(&fclones->skb2, flags1);
		skb->fclone = SKB_FCLONE_ORIG;
		atomic_set(&fclones->fclone_ref, 1);

		fclones->skb2.fclone = SKB_FCLONE_CLONE;
		fclones->skb2.pfmemalloc = pfmemalloc;
	}
out:
	return skb;
nodata:
	kmem_cache_free(cache, skb);
	skb = NULL;
	goto out;
}
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() only if
 * @frag_size is 0, otherwise data should come from the page allocator.
 * The return is the new skb buffer.
 * On a failure the return is %NULL, and @data is not freed.
 * Notes :
 *  Before IO, driver allocates only data buffer where NIC put incoming frame
 *  Driver should add room at head (NET_SKB_PAD) and
 *  MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info))
 *  After IO, driver calls build_skb(), to allocate sk_buff and populate it
 *  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 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)
		return NULL;

	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));

	memset(skb, 0, offsetof(struct sk_buff, tail));
	skb->truesize = SKB_TRUESIZE(size);
	if (frag_size) {
		skb->head_frag = 1;
		if (virt_to_head_page(data)->pfmemalloc)
			skb->pfmemalloc = 1;
	}
	atomic_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);
	kmemcheck_annotate_variable(shinfo->destructor_arg);

	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 |
			    __GFP_NOMEMALLOC;
		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)
{
	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;
	}

	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;
	}

	nc->pagecnt_bias--;
	nc->frag.offset = offset;

	return page_address(page) + offset;
}

static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
	unsigned long flags;
	void *data;

	local_irq_save(flags);
	data = __alloc_page_frag(&netdev_alloc_cache, 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)
{
	return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
}
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);
}

void *napi_alloc_frag(unsigned int fragsz)
{
	return __napi_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
}
EXPORT_SYMBOL(napi_alloc_frag);

/**
 *	__alloc_rx_skb - allocate an skbuff for rx
 *	@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
 *	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 *skb = NULL;
	unsigned int fragsz = SKB_DATA_ALIGN(length) +
			      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 = (flags & SKB_ALLOC_NAPI) ?
			__napi_alloc_frag(fragsz, gfp_mask) :
			__netdev_alloc_frag(fragsz, gfp_mask);

		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;
}

/**
 *	__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;

	length += NET_SKB_PAD;
	skb = __alloc_rx_skb(length, gfp_mask, 0);

	if (likely(skb)) {
		skb_reserve(skb, NET_SKB_PAD);
		skb->dev = dev;
	}

	return skb;
}
EXPORT_SYMBOL(__netdev_alloc_skb);

/**
 *	__napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance
 *	@napi: napi instance this buffer was allocated for
 *	@length: length to allocate
 *	@gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages
 *
 *	Allocate a new sk_buff for use in NAPI receive.  This buffer will
 *	attempt to allocate the head from a special reserved region used
 *	only for NAPI Rx allocation.  By doing this we can save several
 *	CPU cycles by avoiding having to disable and re-enable IRQs.
 *
 *	%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 *skb;

	length += NET_SKB_PAD + NET_IP_ALIGN;
	skb = __alloc_rx_skb(length, gfp_mask, SKB_ALLOC_NAPI);

	if (likely(skb)) {
		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
		skb->dev = napi->dev;
	}

	return skb;
}
EXPORT_SYMBOL(__napi_alloc_skb);

void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
		     int size, unsigned int truesize)
{
	skb_fill_page_desc(skb, i, page, off, size);
	skb->len += size;
	skb->data_len += size;
	skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_add_rx_frag);

void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
			  unsigned int truesize)
{
	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];

	skb_frag_size_add(frag, size);
	skb->len += size;
	skb->data_len += size;
	skb->truesize += truesize;
}
EXPORT_SYMBOL(skb_coalesce_rx_frag);

static void skb_drop_list(struct sk_buff **listp)
{
	kfree_skb_list(*listp);
	*listp = NULL;
}

static inline void skb_drop_fraglist(struct sk_buff *skb)
{
	skb_drop_list(&skb_shinfo(skb)->frag_list);
}

static void skb_clone_fraglist(struct sk_buff *skb)
{
	struct sk_buff *list;

	skb_walk_frags(skb, list)
		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)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int i;

	if (skb->cloned &&
	    atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
			      &shinfo->dataref))
		return;

	for (i = 0; i < shinfo->nr_frags; i++)
		__skb_frag_unref(&shinfo->frags[i]);

	/*
	 * If skb buf is from userspace, we need to notify the caller
	 * the lower device DMA has done;
	 */
	if (shinfo->tx_flags & SKBTX_DEV_ZEROCOPY) {
		struct ubuf_info *uarg;

		uarg = shinfo->destructor_arg;
		if (uarg->callback)
			uarg->callback(uarg, true);
	}

	if (shinfo->frag_list)
		kfree_skb_list(shinfo->frag_list);

	skb_free_head(skb);
}

/*
 *	Free an skbuff by memory without cleaning the state.
 */
static void kfree_skbmem(struct sk_buff *skb)
{
	struct sk_buff_fclones *fclones;

	switch (skb->fclone) {
	case SKB_FCLONE_UNAVAILABLE:
		kmem_cache_free(skbuff_head_cache, skb);
		return;

	case SKB_FCLONE_ORIG:
		fclones = container_of(skb, struct sk_buff_fclones, skb1);

		/* We usually free the clone (TX completion) before original skb
		 * This test would have no chance to be true for the clone,
		 * while here, branch prediction will be good.
		 */
		if (atomic_read(&fclones->fclone_ref) == 1)
			goto fastpath;
		break;

	default: /* SKB_FCLONE_CLONE */
		fclones = container_of(skb, struct sk_buff_fclones, skb2);
		break;
	}
	if (!atomic_dec_and_test(&fclones->fclone_ref))
		return;
fastpath:
	kmem_cache_free(skbuff_fclone_cache, fclones);
}

static void skb_release_head_state(struct sk_buff *skb)
{
	skb_dst_drop(skb);
#ifdef CONFIG_XFRM
	secpath_put(skb->sp);
#endif
	if (skb->destructor) {
		WARN_ON(in_irq());
		skb->destructor(skb);
	}
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
	nf_conntrack_put(skb->nfct);
#endif
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	nf_bridge_put(skb->nf_bridge);
#endif
}

/* Free everything but the sk_buff shell. */
static void skb_release_all(struct sk_buff *skb)
{
	skb_release_head_state(skb);
	if (likely(skb->head))
		skb_release_data(skb);
}

/**
 *	__kfree_skb - private function
 *	@skb: buffer
 *
 *	Free an sk_buff. Release anything attached to the buffer.
 *	Clean the state. This is an internal helper function. Users should
 *	always call kfree_skb
 */

void __kfree_skb(struct sk_buff *skb)
{
	skb_release_all(skb);
	kfree_skbmem(skb);
}
EXPORT_SYMBOL(__kfree_skb);