openvswitch: fixed kernel crash

Signed-off-by: Dragos Motrea <Dragos.Motrea@enea.com>
Signed-off-by: Adrian Dudau <adrian.dudau@enea.com>

2 files changed, 242 insertions, 0 deletions

diff --git a/recipes-kernel/linux/linux-cavium/0001-openvswitch-fixed-kernel-crash.patch b/recipes-kernel/linux/linux-cavium/0001-openvswitch-fixed-kernel-crash.patch
new file mode 100644
index 0000000..ba631ea
--- /dev/null
+++ b/recipes-kernel/linux/linux-cavium/0001-openvswitch-fixed-kernel-crash.patch
@@ -0,0 +1,241 @@
+From 65693212754e9f97d29504219327ce4807780c48 Mon Sep 17 00:00:00 2001
+From: Dragos Motrea <Dragos.Motrea@enea.com>
+Date: Tue, 24 Oct 2017 13:10:10 +0200
+Subject: [meta-enea-bsp-arm][cavium-4.9][LXCR-8050][PATCHv1 1/1] openvswitch:
+ fixed kernel crash
+
+Inserting the openvswitch.ko is causing a kernel crash in 
+__percpu_counter_sum function. Applying this patch will replace the percpu
+counter API with the atomic operations for fragmentation mem accounting.
+The atomic operations should be used on architecture with many CPUs.
+
+The revert is made in kernel upstream by the commit:
+fb452a1aa3fd4034d7999e309c5466ff2d7005aa
+
+Upstream-Status: Backport
+
+Signed-off-by: Dragos Motrea <Dragos.Motrea@enea.com>
+---
+ include/net/inet_frag.h                 | 40 ++++++++-------------------------
+ net/ieee802154/6lowpan/reassembly.c     | 12 +++-------
+ net/ipv4/inet_fragment.c                |  4 +---
+ net/ipv4/ip_fragment.c                  | 15 ++++---------
+ net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++-------
+ net/ipv6/reassembly.c                   | 12 +++-------
+ 6 files changed, 23 insertions(+), 72 deletions(-)
+
+diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
+index 909972a..38beec0 100644
+--- a/include/net/inet_frag.h
++++ b/include/net/inet_frag.h
+@@ -1,14 +1,9 @@
+ #ifndef __NET_FRAG_H__
+ #define __NET_FRAG_H__
+ 
+-#include <linux/percpu_counter.h>
+-
+ struct netns_frags {
+-       /* The percpu_counter "mem" need to be cacheline aligned.
+-        *  mem.count must not share cacheline with other writers
+-        */
+-       struct percpu_counter   mem ____cacheline_aligned_in_smp;
+-
++       /* Keep atomic mem on separate cachelines in structs that include it */
++       atomic_t                mem ____cacheline_aligned_in_smp;
+        /* sysctls */
+        int                     timeout;
+        int                     high_thresh;
+@@ -108,13 +103,9 @@ struct inet_frags {
+ int inet_frags_init(struct inet_frags *);
+ void inet_frags_fini(struct inet_frags *);
+ 
+-static inline int inet_frags_init_net(struct netns_frags *nf)
+-{
+-       return percpu_counter_init(&nf->mem, 0, GFP_KERNEL);
+-}
+-static inline void inet_frags_uninit_net(struct netns_frags *nf)
++static inline void inet_frags_init_net(struct netns_frags *nf)
+ {
+-       percpu_counter_destroy(&nf->mem);
++       atomic_set(&nf->mem, 0);
+ }
+ 
+ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
+@@ -140,37 +131,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q)
+ 
+ /* Memory Tracking Functions. */
+ 
+-/* The default percpu_counter batch size is not big enough to scale to
+- * fragmentation mem acct sizes.
+- * The mem size of a 64K fragment is approx:
+- *  (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes
+- */
+-static unsigned int frag_percpu_counter_batch = 130000;
+-
+ static inline int frag_mem_limit(struct netns_frags *nf)
+ {
+-       return percpu_counter_read(&nf->mem);
++       return atomic_read(&nf->mem);
+ }
+ 
+ static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+ {
+-       __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
++       atomic_sub(i, &nf->mem);
+ }
+ 
+ static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+ {
+-       __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
++       atomic_add(i, &nf->mem);
+ }
+ 
+-static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
++static inline int sum_frag_mem_limit(struct netns_frags *nf)
+ {
+-       unsigned int res;
+-
+-       local_bh_disable();
+-       res = percpu_counter_sum_positive(&nf->mem);
+-       local_bh_enable();
+-
+-       return res;
++       return atomic_read(&nf->mem);
+ }
+ 
+ /* RFC 3168 support :
+diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
+index 30d875d..fb28a06 100644
+--- a/net/ieee802154/6lowpan/reassembly.c
++++ b/net/ieee802154/6lowpan/reassembly.c
+@@ -580,21 +580,15 @@ static int __net_init lowpan_frags_init_net(struct net *net)
+ {
+        struct netns_ieee802154_lowpan *ieee802154_lowpan =
+                net_ieee802154_lowpan(net);
+-       int res;
+ 
+        ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+        ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+        ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+ 
+-       res = inet_frags_init_net(&ieee802154_lowpan->frags);
+-       if (res)
+-               return res;
+-       res = lowpan_frags_ns_sysctl_register(net);
+-       if (res)
+-               inet_frags_uninit_net(&ieee802154_lowpan->frags);
+-       return res;
+-}
++        inet_frags_init_net(&ieee802154_lowpan->frags);
+ 
++        return lowpan_frags_ns_sysctl_register(net);
++}
+ static void __net_exit lowpan_frags_exit_net(struct net *net)
+ {
+        struct netns_ieee802154_lowpan *ieee802154_lowpan =
+diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
+index b5e9317..631c0d0 100644
+--- a/net/ipv4/inet_fragment.c
++++ b/net/ipv4/inet_fragment.c
+@@ -234,10 +234,8 @@ evict_again:
+        cond_resched();
+ 
+        if (read_seqretry(&f->rnd_seqlock, seq) ||
+-           percpu_counter_sum(&nf->mem))
++           sum_frag_mem_limit(nf))
+                goto evict_again;
+-
+-       percpu_counter_destroy(&nf->mem);
+ }
+ EXPORT_SYMBOL(inet_frags_exit_net);
+ 
+diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
+index bbe7f72..0f0d89e 100644
+--- a/net/ipv4/ip_fragment.c
++++ b/net/ipv4/ip_fragment.c
+@@ -835,8 +835,6 @@ static void __init ip4_frags_ctl_register(void)
+ 
+ static int __net_init ipv4_frags_init_net(struct net *net)
+ {
+-       int res;
+-
+        /* Fragment cache limits.
+         *
+         * The fragment memory accounting code, (tries to) account for
+@@ -861,16 +859,11 @@ static int __net_init ipv4_frags_init_net(struct net *net)
+        net->ipv4.frags.timeout = IP_FRAG_TIME;
+ 
+        net->ipv4.frags.max_dist = 64;
+-
+-       res = inet_frags_init_net(&net->ipv4.frags);
+-       if (res)
+-               return res;
+-       res = ip4_frags_ns_ctl_register(net);
+-       if (res)
+-               inet_frags_uninit_net(&net->ipv4.frags);
+-       return res;
++        
++        inet_frags_init_net(&net->ipv4.frags);
++      
++        return ip4_frags_ns_ctl_register(net);
+ }
+-
+ static void __net_exit ipv4_frags_exit_net(struct net *net)
+ {
+        ip4_frags_ns_ctl_unregister(net);
+diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
+index 9948b5c..8734e2c 100644
+--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
++++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
+@@ -621,18 +621,12 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
+ 
+ static int nf_ct_net_init(struct net *net)
+ {
+-       int res;
+-
+        net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+        net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+        net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+-       res = inet_frags_init_net(&net->nf_frag.frags);
+-       if (res)
+-               return res;
+-       res = nf_ct_frag6_sysctl_register(net);
+-       if (res)
+-               inet_frags_uninit_net(&net->nf_frag.frags);
+-       return res;
++       
++        inet_frags_init_net(&net->nf_frag.frags);
++        return nf_ct_frag6_sysctl_register(net);
+ }
+ 
+ static void nf_ct_net_exit(struct net *net)
+diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
+index 3815e85..fe67cf4 100644
+--- a/net/ipv6/reassembly.c
++++ b/net/ipv6/reassembly.c
+@@ -709,19 +709,13 @@ static void ip6_frags_sysctl_unregister(void)
+ 
+ static int __net_init ipv6_frags_init_net(struct net *net)
+ {
+-       int res;
+-
+        net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+        net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+        net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;
+ 
+-       res = inet_frags_init_net(&net->ipv6.frags);
+-       if (res)
+-               return res;
+-       res = ip6_frags_ns_sysctl_register(net);
+-       if (res)
+-               inet_frags_uninit_net(&net->ipv6.frags);
+-       return res;
++       inet_frags_init_net(&net->ipv6.frags);
++
++        return ip6_frags_ns_sysctl_register(net);
+ }
+ 
+ static void __net_exit ipv6_frags_exit_net(struct net *net)
+-- 
+2.7.4
+
diff --git a/recipes-kernel/linux/linux-cavium_4.9.inc b/recipes-kernel/linux/linux-cavium_4.9.inc
index 0089d62..1c504fe 100644
--- a/recipes-kernel/linux/linux-cavium_4.9.inc
+++ b/recipes-kernel/linux/linux-cavium_4.9.inc
@@ -38,6 +38,7 @@ SRC_URI = "git://git@git.enea.com/linux/linux-cavium.git;protocol=ssh;name=machi
            file://CVE-2017-8069.patch \
            file://CVE-2017-8831.patch \
            file://CVE-2017-1000364.patch \
+           file://0001-openvswitch-fixed-kernel-crash.patch \
            "
 
 LINUX_KERNEL_TYPE = "tiny"