mirror of
https://github.com/torvalds/linux.git
synced 2024-12-21 10:31:54 +00:00
891584f48a
Before commitd4289fcc9b
("net: IP6 defrag: use rbtrees for IPv6 defrag"), a netperf UDP_STREAM test[0] using big IPv6 datagrams (thus generating many fragments) and running over an IPsec tunnel, reported more than 6Gbps throughput. After that patch, the same test gets only 9Mbps when receiving on a be2net nic (driver can make a big difference here, for example, ixgbe doesn't seem to be affected). By reusing the IPv4 defragmentation code, IPv6 lost fragment coalescing (IPv4 fragment coalescing was dropped by commit14fe22e334
("Revert "ipv4: use skb coalescing in defragmentation"")). Without fragment coalescing, be2net runs out of Rx ring entries and starts to drop frames (ethtool reports rx_drops_no_frags errors). Since the netperf traffic is only composed of UDP fragments, any lost packet prevents reassembly of the full datagram. Therefore, fragments which have no possibility to ever get reassembled pile up in the reassembly queue, until the memory accounting exeeds the threshold. At that point no fragment is accepted anymore, which effectively discards all netperf traffic. When reassembly timeout expires, some stale fragments are removed from the reassembly queue, so a few packets can be received, reassembled and delivered to the netperf receiver. But the nic still drops frames and soon the reassembly queue gets filled again with stale fragments. These long time frames where no datagram can be received explain why the performance drop is so significant. Re-introducing fragment coalescing is enough to get the initial performances again (6.6Gbps with be2net): driver doesn't drop frames anymore (no more rx_drops_no_frags errors) and the reassembly engine works at full speed. This patch is quite conservative and only coalesces skbs for local IPv4 and IPv6 delivery (in order to avoid changing skb geometry when forwarding). Coalescing could be extended in the future if need be, as more scenarios would probably benefit from it. [0]: Test configuration Sender: ip xfrm policy flush ip xfrm state flush ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1 ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir in tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1 ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir out tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow netserver -D -L fc00:2::1 Receiver: ip xfrm policy flush ip xfrm state flush ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1 ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir in tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1 ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir out tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow netperf -H fc00:2::1 -f k -P 0 -L fc00:1::1 -l 60 -t UDP_STREAM -I 99,5 -i 5,5 -T5,5 -6 Signed-off-by: Guillaume Nault <gnault@redhat.com> Acked-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
178 lines
4.7 KiB
C
178 lines
4.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __NET_FRAG_H__
|
|
#define __NET_FRAG_H__
|
|
|
|
#include <linux/rhashtable-types.h>
|
|
#include <linux/completion.h>
|
|
|
|
/* Per netns frag queues directory */
|
|
struct fqdir {
|
|
/* sysctls */
|
|
long high_thresh;
|
|
long low_thresh;
|
|
int timeout;
|
|
int max_dist;
|
|
struct inet_frags *f;
|
|
struct net *net;
|
|
bool dead;
|
|
|
|
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
|
|
|
|
/* Keep atomic mem on separate cachelines in structs that include it */
|
|
atomic_long_t mem ____cacheline_aligned_in_smp;
|
|
struct work_struct destroy_work;
|
|
};
|
|
|
|
/**
|
|
* fragment queue flags
|
|
*
|
|
* @INET_FRAG_FIRST_IN: first fragment has arrived
|
|
* @INET_FRAG_LAST_IN: final fragment has arrived
|
|
* @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
|
|
* @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable
|
|
*/
|
|
enum {
|
|
INET_FRAG_FIRST_IN = BIT(0),
|
|
INET_FRAG_LAST_IN = BIT(1),
|
|
INET_FRAG_COMPLETE = BIT(2),
|
|
INET_FRAG_HASH_DEAD = BIT(3),
|
|
};
|
|
|
|
struct frag_v4_compare_key {
|
|
__be32 saddr;
|
|
__be32 daddr;
|
|
u32 user;
|
|
u32 vif;
|
|
__be16 id;
|
|
u16 protocol;
|
|
};
|
|
|
|
struct frag_v6_compare_key {
|
|
struct in6_addr saddr;
|
|
struct in6_addr daddr;
|
|
u32 user;
|
|
__be32 id;
|
|
u32 iif;
|
|
};
|
|
|
|
/**
|
|
* struct inet_frag_queue - fragment queue
|
|
*
|
|
* @node: rhash node
|
|
* @key: keys identifying this frag.
|
|
* @timer: queue expiration timer
|
|
* @lock: spinlock protecting this frag
|
|
* @refcnt: reference count of the queue
|
|
* @rb_fragments: received fragments rb-tree root
|
|
* @fragments_tail: received fragments tail
|
|
* @last_run_head: the head of the last "run". see ip_fragment.c
|
|
* @stamp: timestamp of the last received fragment
|
|
* @len: total length of the original datagram
|
|
* @meat: length of received fragments so far
|
|
* @flags: fragment queue flags
|
|
* @max_size: maximum received fragment size
|
|
* @fqdir: pointer to struct fqdir
|
|
* @rcu: rcu head for freeing deferall
|
|
*/
|
|
struct inet_frag_queue {
|
|
struct rhash_head node;
|
|
union {
|
|
struct frag_v4_compare_key v4;
|
|
struct frag_v6_compare_key v6;
|
|
} key;
|
|
struct timer_list timer;
|
|
spinlock_t lock;
|
|
refcount_t refcnt;
|
|
struct rb_root rb_fragments;
|
|
struct sk_buff *fragments_tail;
|
|
struct sk_buff *last_run_head;
|
|
ktime_t stamp;
|
|
int len;
|
|
int meat;
|
|
__u8 flags;
|
|
u16 max_size;
|
|
struct fqdir *fqdir;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
struct inet_frags {
|
|
unsigned int qsize;
|
|
|
|
void (*constructor)(struct inet_frag_queue *q,
|
|
const void *arg);
|
|
void (*destructor)(struct inet_frag_queue *);
|
|
void (*frag_expire)(struct timer_list *t);
|
|
struct kmem_cache *frags_cachep;
|
|
const char *frags_cache_name;
|
|
struct rhashtable_params rhash_params;
|
|
refcount_t refcnt;
|
|
struct completion completion;
|
|
};
|
|
|
|
int inet_frags_init(struct inet_frags *);
|
|
void inet_frags_fini(struct inet_frags *);
|
|
|
|
int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net);
|
|
|
|
static inline void fqdir_pre_exit(struct fqdir *fqdir)
|
|
{
|
|
fqdir->high_thresh = 0; /* prevent creation of new frags */
|
|
fqdir->dead = true;
|
|
}
|
|
void fqdir_exit(struct fqdir *fqdir);
|
|
|
|
void inet_frag_kill(struct inet_frag_queue *q);
|
|
void inet_frag_destroy(struct inet_frag_queue *q);
|
|
struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
|
|
|
|
/* Free all skbs in the queue; return the sum of their truesizes. */
|
|
unsigned int inet_frag_rbtree_purge(struct rb_root *root);
|
|
|
|
static inline void inet_frag_put(struct inet_frag_queue *q)
|
|
{
|
|
if (refcount_dec_and_test(&q->refcnt))
|
|
inet_frag_destroy(q);
|
|
}
|
|
|
|
/* Memory Tracking Functions. */
|
|
|
|
static inline long frag_mem_limit(const struct fqdir *fqdir)
|
|
{
|
|
return atomic_long_read(&fqdir->mem);
|
|
}
|
|
|
|
static inline void sub_frag_mem_limit(struct fqdir *fqdir, long val)
|
|
{
|
|
atomic_long_sub(val, &fqdir->mem);
|
|
}
|
|
|
|
static inline void add_frag_mem_limit(struct fqdir *fqdir, long val)
|
|
{
|
|
atomic_long_add(val, &fqdir->mem);
|
|
}
|
|
|
|
/* RFC 3168 support :
|
|
* We want to check ECN values of all fragments, do detect invalid combinations.
|
|
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
|
|
*/
|
|
#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */
|
|
#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */
|
|
#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */
|
|
#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */
|
|
|
|
extern const u8 ip_frag_ecn_table[16];
|
|
|
|
/* Return values of inet_frag_queue_insert() */
|
|
#define IPFRAG_OK 0
|
|
#define IPFRAG_DUP 1
|
|
#define IPFRAG_OVERLAP 2
|
|
int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
|
|
int offset, int end);
|
|
void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
|
|
struct sk_buff *parent);
|
|
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
|
|
void *reasm_data, bool try_coalesce);
|
|
struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q);
|
|
|
|
#endif
|