diff options
author | Vishwanath Pai <vpai@akamai.com> | 2016-09-22 12:43:44 -0400 |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2016-09-25 14:54:06 +0200 |
commit | 11d5f15723c9f39d7c131d0149d024c17dbef676 (patch) | |
tree | 25daeeeaca4387aff480c28548039adb60c21d8f /net/netfilter | |
parent | 0dc60a4546fefc6dc9f54abf60beeeb3501726fa (diff) |
netfilter: xt_hashlimit: Create revision 2 to support higher pps rates
Create a new revision for the hashlimit iptables extension module. Rev 2
will support higher pps of upto 1 million, Version 1 supports only 10k.
To support this we have to increase the size of the variables avg and
burst in hashlimit_cfg to 64-bit. Create two new structs hashlimit_cfg2
and xt_hashlimit_mtinfo2 and also create newer versions of all the
functions for match, checkentry and destroy.
Some of the functions like hashlimit_mt, hashlimit_mt_check etc are very
similar in both rev1 and rev2 with only minor changes, so I have split
those functions and moved all the common code to a *_common function.
Signed-off-by: Vishwanath Pai <vpai@akamai.com>
Signed-off-by: Joshua Hunt <johunt@akamai.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/xt_hashlimit.c | 330 |
1 files changed, 262 insertions, 68 deletions
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index e93d9e0a3f35..44a095ecc7b7 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -57,6 +57,7 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net) /* need to declare this at the top */ static const struct file_operations dl_file_ops_v1; +static const struct file_operations dl_file_ops; /* hash table crap */ struct dsthash_dst { @@ -86,8 +87,8 @@ struct dsthash_ent { unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ - u_int32_t credit; - u_int32_t credit_cap, cost; + u_int64_t credit; + u_int64_t credit_cap, cost; } rateinfo; struct rcu_head rcu; }; @@ -98,7 +99,7 @@ struct xt_hashlimit_htable { u_int8_t family; bool rnd_initialized; - struct hashlimit_cfg1 cfg; /* config */ + struct hashlimit_cfg2 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ @@ -114,6 +115,30 @@ struct xt_hashlimit_htable { struct hlist_head hash[0]; /* hashtable itself */ }; +static int +cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) +{ + if (revision == 1) { + struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; + + to->mode = cfg->mode; + to->avg = cfg->avg; + to->burst = cfg->burst; + to->size = cfg->size; + to->max = cfg->max; + to->gc_interval = cfg->gc_interval; + to->expire = cfg->expire; + to->srcmask = cfg->srcmask; + to->dstmask = cfg->dstmask; + } else if (revision == 2) { + memcpy(to, from, sizeof(struct hashlimit_cfg2)); + } else { + return -EINVAL; + } + + return 0; +} + static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; @@ -215,16 +240,18 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(struct work_struct *work); -static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, - u_int8_t family) +static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, + const char *name, u_int8_t family, + struct xt_hashlimit_htable **out_hinfo, + int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; - unsigned int size; - unsigned int i; + unsigned int size, i; + int ret; - if (minfo->cfg.size) { - size = minfo->cfg.size; + if (cfg->size) { + size = cfg->size; } else { size = (totalram_pages << PAGE_SHIFT) / 16384 / sizeof(struct list_head); @@ -238,10 +265,14 @@ static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, sizeof(struct list_head) * size); if (hinfo == NULL) return -ENOMEM; - minfo->hinfo = hinfo; + *out_hinfo = hinfo; /* copy match config into hashtable config */ - memcpy(&hinfo->cfg, &minfo->cfg, sizeof(hinfo->cfg)); + ret = cfg_copy(&hinfo->cfg, (void *)cfg, 2); + + if (ret) + return ret; + hinfo->cfg.size = size; if (hinfo->cfg.max == 0) hinfo->cfg.max = 8 * hinfo->cfg.size; @@ -255,17 +286,18 @@ static int htable_create_v1(struct net *net, struct xt_hashlimit_mtinfo1 *minfo, hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; - hinfo->name = kstrdup(minfo->name, GFP_KERNEL); + hinfo->name = kstrdup(name, GFP_KERNEL); if (!hinfo->name) { vfree(hinfo); return -ENOMEM; } spin_lock_init(&hinfo->lock); - hinfo->pde = proc_create_data(minfo->name, 0, + hinfo->pde = proc_create_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, - &dl_file_ops_v1, hinfo); + (revision == 1) ? &dl_file_ops_v1 : &dl_file_ops, + hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); @@ -399,6 +431,7 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie. */ #define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24)) +#define MAX_CPJ (0xFFFFFFFFFFFFFFFF / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a @@ -408,8 +441,11 @@ static void htable_put(struct xt_hashlimit_htable *hinfo) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) +#define _POW2_BELOW64(x) (_POW2_BELOW32(x)|_POW2_BELOW32((x)>>32)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) +#define POW2_BELOW64(x) ((_POW2_BELOW64(x)>>1) + 1) +#define CREDITS_PER_JIFFY POW2_BELOW64(MAX_CPJ) #define CREDITS_PER_JIFFY_v1 POW2_BELOW32(MAX_CPJ_v1) /* in byte mode, the lowest possible rate is one packet/second. @@ -425,15 +461,24 @@ static u32 xt_hashlimit_len_to_chunks(u32 len) } /* Precision saver. */ -static u32 user2credits(u32 user) +static u64 user2credits(u64 user, int revision) { - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) - /* Divide first. */ - return (user / XT_HASHLIMIT_SCALE) *\ - HZ * CREDITS_PER_JIFFY_v1; + if (revision == 1) { + /* If multiplying would overflow... */ + if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY_v1)) + /* Divide first. */ + return (user / XT_HASHLIMIT_SCALE) *\ + HZ * CREDITS_PER_JIFFY_v1; + + return (user * HZ * CREDITS_PER_JIFFY_v1) \ + / XT_HASHLIMIT_SCALE; + } else { + if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) + return (user / XT_HASHLIMIT_SCALE_v2) *\ + HZ * CREDITS_PER_JIFFY; - return (user * HZ * CREDITS_PER_JIFFY_v1) / XT_HASHLIMIT_SCALE; + return (user * HZ * CREDITS_PER_JIFFY) / XT_HASHLIMIT_SCALE_v2; + } } static u32 user2credits_byte(u32 user) @@ -443,10 +488,11 @@ static u32 user2credits_byte(u32 user) return (u32) (us >> 32); } -static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) +static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, + u32 mode, int revision) { unsigned long delta = now - dh->rateinfo.prev; - u32 cap; + u64 cap, cpj; if (delta == 0) return; @@ -454,7 +500,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { - u32 tmp = dh->rateinfo.credit; + u64 tmp = dh->rateinfo.credit; dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; cap = CREDITS_PER_JIFFY_BYTES * HZ; if (tmp >= dh->rateinfo.credit) {/* overflow */ @@ -462,7 +508,9 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) return; } } else { - dh->rateinfo.credit += delta * CREDITS_PER_JIFFY_v1; + cpj = (revision == 1) ? + CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; + dh->rateinfo.credit += delta * cpj; cap = dh->rateinfo.credit_cap; } if (dh->rateinfo.credit > cap) @@ -470,7 +518,7 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode) } static void rateinfo_init(struct dsthash_ent *dh, - struct xt_hashlimit_htable *hinfo) + struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { @@ -479,8 +527,8 @@ static void rateinfo_init(struct dsthash_ent *dh, dh->rateinfo.credit_cap = hinfo->cfg.burst; } else { dh->rateinfo.credit = user2credits(hinfo->cfg.avg * - hinfo->cfg.burst); - dh->rateinfo.cost = user2credits(hinfo->cfg.avg); + hinfo->cfg.burst, revision); + dh->rateinfo.cost = user2credits(hinfo->cfg.avg, revision); dh->rateinfo.credit_cap = dh->rateinfo.credit; } } @@ -604,15 +652,15 @@ static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) } static bool -hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, + struct xt_hashlimit_htable *hinfo, + const struct hashlimit_cfg2 *cfg, int revision) { - const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; - struct xt_hashlimit_htable *hinfo = info->hinfo; unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; bool race = false; - u32 cost; + u64 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; @@ -627,18 +675,18 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) } else if (race) { /* Already got an entry, update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } else { dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); + rateinfo_init(dh, hinfo, revision); } } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_recalc(dh, now, hinfo->cfg.mode); + rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } - if (info->cfg.mode & XT_HASHLIMIT_BYTES) + if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else cost = dh->rateinfo.cost; @@ -648,70 +696,126 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); rcu_read_unlock_bh(); - return !(info->cfg.mode & XT_HASHLIMIT_INVERT); + return !(cfg->mode & XT_HASHLIMIT_INVERT); } spin_unlock(&dh->lock); rcu_read_unlock_bh(); /* default match is underlimit - so over the limit, we need to invert */ - return info->cfg.mode & XT_HASHLIMIT_INVERT; + return cfg->mode & XT_HASHLIMIT_INVERT; hotdrop: par->hotdrop = true; return false; } -static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) +static bool +hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_common(skb, par, hinfo, &cfg, 1); +} + +static bool +hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; + + return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 2); +} + +static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, + struct xt_hashlimit_htable **hinfo, + struct hashlimit_cfg2 *cfg, + const char *name, int revision) { struct net *net = par->net; - struct xt_hashlimit_mtinfo1 *info = par->matchinfo; int ret; - if (info->cfg.gc_interval == 0 || info->cfg.expire == 0) - return -EINVAL; - if (info->name[sizeof(info->name)-1] != '\0') + if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; if (par->family == NFPROTO_IPV4) { - if (info->cfg.srcmask > 32 || info->cfg.dstmask > 32) + if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; } else { - if (info->cfg.srcmask > 128 || info->cfg.dstmask > 128) + if (cfg->srcmask > 128 || cfg->dstmask > 128) return -EINVAL; } - if (info->cfg.mode & ~XT_HASHLIMIT_ALL) { + if (cfg->mode & ~XT_HASHLIMIT_ALL) { pr_info("Unknown mode mask %X, kernel too old?\n", - info->cfg.mode); + cfg->mode); return -EINVAL; } /* Check for overflow. */ - if (info->cfg.mode & XT_HASHLIMIT_BYTES) { - if (user2credits_byte(info->cfg.avg) == 0) { - pr_info("overflow, rate too high: %u\n", info->cfg.avg); + if (cfg->mode & XT_HASHLIMIT_BYTES) { + if (user2credits_byte(cfg->avg) == 0) { + pr_info("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; } - } else if (info->cfg.burst == 0 || - user2credits(info->cfg.avg * info->cfg.burst) < - user2credits(info->cfg.avg)) { - pr_info("overflow, try lower: %u/%u\n", - info->cfg.avg, info->cfg.burst); + } else if (cfg->burst == 0 || + user2credits(cfg->avg * cfg->burst, revision) < + user2credits(cfg->avg, revision)) { + pr_info("overflow, try lower: %llu/%llu\n", + cfg->avg, cfg->burst); return -ERANGE; } mutex_lock(&hashlimit_mutex); - info->hinfo = htable_find_get(net, info->name, par->family); - if (info->hinfo == NULL) { - ret = htable_create_v1(net, info, par->family); + *hinfo = htable_find_get(net, name, par->family); + if (*hinfo == NULL) { + ret = htable_create(net, cfg, name, par->family, + hinfo, revision); if (ret < 0) { mutex_unlock(&hashlimit_mutex); return ret; } } mutex_unlock(&hashlimit_mutex); + return 0; } +static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo1 *info = par->matchinfo; + struct hashlimit_cfg2 cfg = {}; + int ret; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 1); + + if (ret) + return ret; + + return hashlimit_mt_check_common(par, &info->hinfo, + &cfg, info->name, 1); +} + +static int hashlimit_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, + info->name, 2); +} + static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; @@ -719,6 +823,13 @@ static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) htable_put(info->hinfo); } +static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + htable_put(info->hinfo); +} + static struct xt_match hashlimit_mt_reg[] __read_mostly = { { .name = "hashlimit", @@ -730,6 +841,16 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV4, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .checkentry = hashlimit_mt_check, + .destroy = hashlimit_mt_destroy, + .me = THIS_MODULE, + }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "hashlimit", @@ -741,6 +862,16 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, + { + .name = "hashlimit", + .revision = 2, + .family = NFPROTO_IPV6, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo2), + .checkentry = hashlimit_mt_check, + .destroy = hashlimit_mt_destroy, + .me = THIS_MODULE, + }, #endif }; @@ -787,18 +918,12 @@ static void dl_seq_stop(struct seq_file *s, void *v) spin_unlock_bh(&htable->lock); } -static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, - struct seq_file *s) +static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) { - const struct xt_hashlimit_htable *ht = s->private; - - spin_lock(&ent->lock); - /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies, ht->cfg.mode); - switch (family) { case NFPROTO_IPV4: - seq_printf(s, "%ld %pI4:%u->%pI4:%u %u %u %u\n", + seq_printf(s, "%ld %pI4:%u->%pI4:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip.src, ntohs(ent->dst.src_port), @@ -809,7 +934,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: - seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n", + seq_printf(s, "%ld %pI6:%u->%pI6:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip6.src, ntohs(ent->dst.src_port), @@ -822,6 +947,34 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, default: BUG(); } +} + +static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 1); + + dl_seq_print(ent, family, s); + + spin_unlock(&ent->lock); + return seq_has_overflowed(s); +} + +static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + + dl_seq_print(ent, family, s); + spin_unlock(&ent->lock); return seq_has_overflowed(s); } @@ -840,6 +993,20 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) return 0; } +static int dl_seq_show(struct seq_file *s, void *v) +{ + struct xt_hashlimit_htable *htable = s->private; + unsigned int *bucket = (unsigned int *)v; + struct dsthash_ent *ent; + + if (!hlist_empty(&htable->hash[*bucket])) { + hlist_for_each_entry(ent, &htable->hash[*bucket], node) + if (dl_seq_real_show(ent, htable->family, s)) + return -1; + } + return 0; +} + static const struct seq_operations dl_seq_ops_v1 = { .start = dl_seq_start, .next = dl_seq_next, @@ -847,6 +1014,13 @@ static const struct seq_operations dl_seq_ops_v1 = { .show = dl_seq_show_v1 }; +static const struct seq_operations dl_seq_ops = { + .start = dl_seq_start, + .next = dl_seq_next, + .stop = dl_seq_stop, + .show = dl_seq_show +}; + static int dl_proc_open_v1(struct inode *inode, struct file *file) { int ret = seq_open(file, &dl_seq_ops_v1); @@ -858,6 +1032,18 @@ static int dl_proc_open_v1(struct inode *inode, struct file *file) return ret; } +static int dl_proc_open(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &dl_seq_ops); + + if (!ret) { + struct seq_file *sf = file->private_data; + + sf->private = PDE_DATA(inode); + } + return ret; +} + static const struct file_operations dl_file_ops_v1 = { .owner = THIS_MODULE, .open = dl_proc_open_v1, @@ -866,6 +1052,14 @@ static const struct file_operations dl_file_ops_v1 = { .release = seq_release }; +static const struct file_operations dl_file_ops = { + .owner = THIS_MODULE, + .open = dl_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + static int __net_init hashlimit_proc_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); |