From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: [PATCH v3 13/30] inet: frags: break the 2GB limit for frags storage Date: Thu, 13 Sep 2018 07:58:45 -0700 Message-ID: <20180913145902.17531-14-sthemmin@microsoft.com> References: <20180913145902.17531-1-sthemmin@microsoft.com> Cc: netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com To: davem@davemloft.net, gregkh@linuxfoundation.org Return-path: Received: from mail-pg1-f194.google.com ([209.85.215.194]:41051 "EHLO mail-pg1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728348AbeIMUJU (ORCPT ); Thu, 13 Sep 2018 16:09:20 -0400 Received: by mail-pg1-f194.google.com with SMTP id s15-v6so2871355pgv.8 for ; Thu, 13 Sep 2018 07:59:28 -0700 (PDT) In-Reply-To: <20180913145902.17531-1-sthemmin@microsoft.com> Sender: netdev-owner@vger.kernel.org List-ID: From: Eric Dumazet Some users are willing to provision huge amounts of memory to be able to perform reassembly reasonnably well under pressure. Current memory tracking is using one atomic_t and integers. Switch to atomic_long_t so that 64bit arches can use more than 2GB, without any cost for 32bit arches. Note that this patch avoids an overflow error, if high_thresh was set to ~2GB, since this test in inet_frag_alloc() was never true : if (... || frag_mem_limit(nf) > nf->high_thresh) Tested: $ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh $ grep FRAG /proc/net/sockstat FRAG: inuse 14705885 memory 16000002880 $ nstat -n ; sleep 1 ; nstat | grep Reas IpReasmReqds 3317150 0.0 IpReasmFails 3317112 0.0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller (cherry picked from commit 3e67f106f619dcfaf6f4e2039599bdb69848c714) --- Documentation/networking/ip-sysctl.txt | 4 ++-- include/net/inet_frag.h | 20 ++++++++++---------- net/ieee802154/6lowpan/reassembly.c | 10 +++++----- net/ipv4/ip_fragment.c | 10 +++++----- net/ipv4/proc.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++----- net/ipv6/proc.c | 2 +- net/ipv6/reassembly.c | 6 +++--- 8 files changed, 32 insertions(+), 32 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index f23582a3c661..a054b5ad410a 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -133,10 +133,10 @@ min_adv_mss - INTEGER IP Fragmentation: -ipfrag_high_thresh - INTEGER +ipfrag_high_thresh - LONG INTEGER Maximum memory used to reassemble IP fragments. -ipfrag_low_thresh - INTEGER +ipfrag_low_thresh - LONG INTEGER (Obsolete since linux-4.17) Maximum memory used to reassemble IP fragments before the kernel begins to remove incomplete fragment queues to free up resources. diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 95e353e3305b..a52e7273e7a5 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -8,11 +8,11 @@ struct netns_frags { struct rhashtable rhashtable ____cacheline_aligned_in_smp; /* Keep atomic mem on separate cachelines in structs that include it */ - atomic_t mem ____cacheline_aligned_in_smp; + atomic_long_t mem ____cacheline_aligned_in_smp; /* sysctls */ + long high_thresh; + long low_thresh; int timeout; - int high_thresh; - int low_thresh; int max_dist; struct inet_frags *f; }; @@ -102,7 +102,7 @@ void inet_frags_fini(struct inet_frags *); static inline int inet_frags_init_net(struct netns_frags *nf) { - atomic_set(&nf->mem, 0); + atomic_long_set(&nf->mem, 0); return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params); } void inet_frags_exit_net(struct netns_frags *nf); @@ -119,19 +119,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q) /* Memory Tracking Functions. */ -static inline int frag_mem_limit(struct netns_frags *nf) +static inline long frag_mem_limit(const struct netns_frags *nf) { - return atomic_read(&nf->mem); + return atomic_long_read(&nf->mem); } -static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) +static inline void sub_frag_mem_limit(struct netns_frags *nf, long val) { - atomic_sub(i, &nf->mem); + atomic_long_sub(val, &nf->mem); } -static inline void add_frag_mem_limit(struct netns_frags *nf, int i) +static inline void add_frag_mem_limit(struct netns_frags *nf, long val) { - atomic_add(i, &nf->mem); + atomic_long_add(val, &nf->mem); } /* RFC 3168 support : diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 1aec71a3f904..44f148a6bb57 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -411,23 +411,23 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) } #ifdef CONFIG_SYSCTL -static int zero; +static long zero; static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .data = &init_net.ieee802154_lowpan.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ieee802154_lowpan.frags.low_thresh }, { .procname = "6lowpanfrag_low_thresh", .data = &init_net.ieee802154_lowpan.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 38cbf56bb48e..dc3ed0ac4c58 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -683,23 +683,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL -static int zero; +static long zero; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .data = &init_net.ipv4.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ipv4.frags.low_thresh }, { .procname = "ipfrag_low_thresh", .data = &init_net.ipv4.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.ipv4.frags.high_thresh }, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 01a337c3a36b..8fbd5633e544 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -71,7 +71,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(net, &raw_prot)); - seq_printf(seq, "FRAG: inuse %u memory %u\n", + seq_printf(seq, "FRAG: inuse %u memory %lu\n", atomic_read(&net->ipv4.frags.rhashtable.nelems), frag_mem_limit(&net->ipv4.frags)); return 0; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 54ce1d2a9a9d..6613f81e553a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb static struct inet_frags nf_frags; #ifdef CONFIG_SYSCTL -static int zero; +static long zero; static struct ctl_table nf_ct_frag6_sysctl_table[] = { { @@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_low_thresh", .data = &init_net.nf_frag.frags.low_thresh, - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.nf_frag.frags.high_thresh }, { .procname = "nf_conntrack_frag6_high_thresh", .data = &init_net.nf_frag.frags.high_thresh, - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.nf_frag.frags.low_thresh }, { } diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 5704ec3d3178..dc04c024986c 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(net, &rawv6_prot)); - seq_printf(seq, "FRAG6: inuse %u memory %u\n", + seq_printf(seq, "FRAG6: inuse %u memory %lu\n", atomic_read(&net->ipv6.frags.rhashtable.nelems), frag_mem_limit(&net->ipv6.frags)); return 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2a77fda5e3bc..905a8aee2671 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -552,15 +552,15 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { { .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ipv6.frags.low_thresh }, { .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero, -- 2.18.0