From 71ac7f6255c560716c20da8ee2c964bbd96e941f Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Sun, 29 Sep 2013 08:39:21 -0700 Subject: apparmor: Use shash crypto API interface for profile hashes Use the shash interface, rather than the hash interface, when hashing AppArmor profiles. The shash interface does not use scatterlists and it is a better fit for what AppArmor needs. This fixes a kernel paging BUG when aa_calc_profile_hash() is passed a buffer from vmalloc(). The hash interface requires callers to handle vmalloc() buffers differently than what AppArmor was doing. Due to vmalloc() memory not being physically contiguous, each individual page behind the buffer must be assigned to a scatterlist with sg_set_page() and then the scatterlist passed to crypto_hash_update(). The shash interface does not have that limitation and allows vmalloc() and kmalloc() buffers to be handled in the same manner. BugLink: https://launchpad.net/bugs/1216294/ BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=62261 Signed-off-by: Tyler Hicks Acked-by: Seth Arnold Signed-off-by: John Johansen Signed-off-by: James Morris --- security/apparmor/crypto.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) (limited to 'security') diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c index d6222ba4e919..532471d0b3a0 100644 --- a/security/apparmor/crypto.c +++ b/security/apparmor/crypto.c @@ -15,14 +15,14 @@ * it should be. */ -#include +#include #include "include/apparmor.h" #include "include/crypto.h" static unsigned int apparmor_hash_size; -static struct crypto_hash *apparmor_tfm; +static struct crypto_shash *apparmor_tfm; unsigned int aa_hash_size(void) { @@ -32,35 +32,33 @@ unsigned int aa_hash_size(void) int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start, size_t len) { - struct scatterlist sg[2]; - struct hash_desc desc = { - .tfm = apparmor_tfm, - .flags = 0 - }; + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(apparmor_tfm)]; + } desc; int error = -ENOMEM; u32 le32_version = cpu_to_le32(version); if (!apparmor_tfm) return 0; - sg_init_table(sg, 2); - sg_set_buf(&sg[0], &le32_version, 4); - sg_set_buf(&sg[1], (u8 *) start, len); - profile->hash = kzalloc(apparmor_hash_size, GFP_KERNEL); if (!profile->hash) goto fail; - error = crypto_hash_init(&desc); + desc.shash.tfm = apparmor_tfm; + desc.shash.flags = 0; + + error = crypto_shash_init(&desc.shash); if (error) goto fail; - error = crypto_hash_update(&desc, &sg[0], 4); + error = crypto_shash_update(&desc.shash, (u8 *) &le32_version, 4); if (error) goto fail; - error = crypto_hash_update(&desc, &sg[1], len); + error = crypto_shash_update(&desc.shash, (u8 *) start, len); if (error) goto fail; - error = crypto_hash_final(&desc, profile->hash); + error = crypto_shash_final(&desc.shash, profile->hash); if (error) goto fail; @@ -75,19 +73,19 @@ fail: static int __init init_profile_hash(void) { - struct crypto_hash *tfm; + struct crypto_shash *tfm; if (!apparmor_initialized) return 0; - tfm = crypto_alloc_hash("sha1", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_shash("sha1", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) { int error = PTR_ERR(tfm); AA_ERROR("failed to setup profile sha1 hashing: %d\n", error); return error; } apparmor_tfm = tfm; - apparmor_hash_size = crypto_hash_digestsize(apparmor_tfm); + apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm); aa_info_message("AppArmor sha1 policy hashing enabled"); -- cgit v1.2.3 From 4cd4fc77032dca46fe7475d81461e29145db247a Mon Sep 17 00:00:00 2001 From: John Johansen Date: Sun, 29 Sep 2013 08:39:22 -0700 Subject: apparmor: fix suspicious RCU usage warning in policy.c/policy.h The recent 3.12 pull request for apparmor was missing a couple rcu _protected access modifiers. Resulting in the follow suspicious RCU usage [ 29.804534] [ INFO: suspicious RCU usage. ] [ 29.804539] 3.11.0+ #5 Not tainted [ 29.804541] ------------------------------- [ 29.804545] security/apparmor/include/policy.h:363 suspicious rcu_dereference_check() usage! [ 29.804548] [ 29.804548] other info that might help us debug this: [ 29.804548] [ 29.804553] [ 29.804553] rcu_scheduler_active = 1, debug_locks = 1 [ 29.804558] 2 locks held by apparmor_parser/1268: [ 29.804560] #0: (sb_writers#9){.+.+.+}, at: [] file_start_write+0x27/0x29 [ 29.804576] #1: (&ns->lock){+.+.+.}, at: [] aa_replace_profiles+0x166/0x57c [ 29.804589] [ 29.804589] stack backtrace: [ 29.804595] CPU: 0 PID: 1268 Comm: apparmor_parser Not tainted 3.11.0+ #5 [ 29.804599] Hardware name: ASUSTeK Computer Inc. UL50VT /UL50VT , BIOS 217 03/01/2010 [ 29.804602] 0000000000000000 ffff8800b95a1d90 ffffffff8144eb9b ffff8800b94db540 [ 29.804611] ffff8800b95a1dc0 ffffffff81087439 ffff880138cc3a18 ffff880138cc3a18 [ 29.804619] ffff8800b9464a90 ffff880138cc3a38 ffff8800b95a1df0 ffffffff811f5084 [ 29.804628] Call Trace: [ 29.804636] [] dump_stack+0x4e/0x82 [ 29.804642] [] lockdep_rcu_suspicious+0xfc/0x105 [ 29.804649] [] __aa_update_replacedby+0x53/0x7f [ 29.804655] [] __replace_profile+0x11f/0x1ed [ 29.804661] [] aa_replace_profiles+0x410/0x57c [ 29.804668] [] profile_replace+0x35/0x4c [ 29.804674] [] vfs_write+0xad/0x113 [ 29.804680] [] SyS_write+0x44/0x7a [ 29.804687] [] system_call_fastpath+0x16/0x1b [ 29.804691] [ 29.804694] =============================== [ 29.804697] [ INFO: suspicious RCU usage. ] [ 29.804700] 3.11.0+ #5 Not tainted [ 29.804703] ------------------------------- [ 29.804706] security/apparmor/policy.c:566 suspicious rcu_dereference_check() usage! [ 29.804709] [ 29.804709] other info that might help us debug this: [ 29.804709] [ 29.804714] [ 29.804714] rcu_scheduler_active = 1, debug_locks = 1 [ 29.804718] 2 locks held by apparmor_parser/1268: [ 29.804721] #0: (sb_writers#9){.+.+.+}, at: [] file_start_write+0x27/0x29 [ 29.804733] #1: (&ns->lock){+.+.+.}, at: [] aa_replace_profiles+0x166/0x57c [ 29.804744] [ 29.804744] stack backtrace: [ 29.804750] CPU: 0 PID: 1268 Comm: apparmor_parser Not tainted 3.11.0+ #5 [ 29.804753] Hardware name: ASUSTeK Computer Inc. UL50VT /UL50VT , BIOS 217 03/01/2010 [ 29.804756] 0000000000000000 ffff8800b95a1d80 ffffffff8144eb9b ffff8800b94db540 [ 29.804764] ffff8800b95a1db0 ffffffff81087439 ffff8800b95b02b0 0000000000000000 [ 29.804772] ffff8800b9efba08 ffff880138cc3a38 ffff8800b95a1dd0 ffffffff811f4f94 [ 29.804779] Call Trace: [ 29.804786] [] dump_stack+0x4e/0x82 [ 29.804791] [] lockdep_rcu_suspicious+0xfc/0x105 [ 29.804798] [] aa_free_replacedby_kref+0x4d/0x62 [ 29.804804] [] ? aa_put_namespace+0x17/0x17 [ 29.804810] [] kref_put+0x36/0x40 [ 29.804816] [] __replace_profile+0x13a/0x1ed [ 29.804822] [] aa_replace_profiles+0x410/0x57c [ 29.804829] [] profile_replace+0x35/0x4c [ 29.804835] [] vfs_write+0xad/0x113 [ 29.804840] [] SyS_write+0x44/0x7a [ 29.804847] [] system_call_fastpath+0x16/0x1b Reported-by: miles.lane@gmail.com CC: paulmck@linux.vnet.ibm.com Signed-off-by: John Johansen Signed-off-by: James Morris --- security/apparmor/include/policy.h | 4 +++- security/apparmor/policy.c | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'security') diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index f2d4b6348cbc..c28b0f20ab53 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -360,7 +360,9 @@ static inline void aa_put_replacedby(struct aa_replacedby *p) static inline void __aa_update_replacedby(struct aa_profile *orig, struct aa_profile *new) { - struct aa_profile *tmp = rcu_dereference(orig->replacedby->profile); + struct aa_profile *tmp; + tmp = rcu_dereference_protected(orig->replacedby->profile, + mutex_is_locked(&orig->ns->lock)); rcu_assign_pointer(orig->replacedby->profile, aa_get_profile(new)); orig->flags |= PFLAG_INVALID; aa_put_profile(tmp); diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 6172509fa2b7..345bec07a27d 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -563,7 +563,8 @@ void __init aa_free_root_ns(void) static void free_replacedby(struct aa_replacedby *r) { if (r) { - aa_put_profile(rcu_dereference(r->profile)); + /* r->profile will not be updated any more as r is dead */ + aa_put_profile(rcu_dereference_protected(r->profile, true)); kzfree(r); } } -- cgit v1.2.3 From 0bbf87d852d243680ed7074110ccc1dea003b61a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 28 Sep 2013 14:10:59 -0700 Subject: net ipv4: Convert ipv4.ip_local_port_range to be per netns v3 - Move sysctl_local_ports from a global variable into struct netns_ipv4. - Modify inet_get_local_port_range to take a struct net, and update all of the callers. - Move the initialization of sysctl_local_ports into sysctl_net_ipv4.c:ipv4_sysctl_init_net from inet_connection_sock.c v2: - Ensure indentation used tabs - Fixed ip.h so it applies cleanly to todays net-next v3: - Compile fixes of strange callers of inet_get_local_port_range. This patch now successfully passes an allmodconfig build. Removed manual inlining of inet_get_local_port_range in ipv4_local_port_range Originally-by: Samya Acked-by: Nicolas Dichtel Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- drivers/infiniband/core/cma.c | 2 +- drivers/net/vxlan.c | 2 +- include/net/ip.h | 6 +---- include/net/netns/ipv4.h | 6 +++++ net/ipv4/inet_connection_sock.c | 20 +++++----------- net/ipv4/inet_hashtables.c | 2 +- net/ipv4/ping.c | 4 ++-- net/ipv4/sysctl_net_ipv4.c | 52 +++++++++++++++++++++++++++-------------- net/ipv4/udp.c | 2 +- net/openvswitch/vport-vxlan.c | 2 +- net/sctp/socket.c | 2 +- security/selinux/hooks.c | 2 +- 12 files changed, 56 insertions(+), 46 deletions(-) (limited to 'security') diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index dab4b41f1715..a082fd9e7ebe 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2294,7 +2294,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) int low, high, remaining; unsigned int rover; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(&init_net, &low, &high); remaining = (high - low) + 1; rover = net_random() % remaining + low; retry: diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index d1292fe746bc..c376be7b528a 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2089,7 +2089,7 @@ static void vxlan_setup(struct net_device *dev) vxlan->age_timer.function = vxlan_cleanup; vxlan->age_timer.data = (unsigned long) vxlan; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(dev_net(dev), &low, &high); vxlan->port_min = low; vxlan->port_max = high; vxlan->dst_port = htons(vxlan_port); diff --git a/include/net/ip.h b/include/net/ip.h index 77b4f9b57c28..16078f422397 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -217,11 +217,7 @@ static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ]) } } -extern struct local_ports { - seqlock_t lock; - int range[2]; -} sysctl_local_ports; -void inet_get_local_port_range(int *low, int *high); +void inet_get_local_port_range(struct net *net, int *low, int *high); extern unsigned long *sysctl_local_reserved_ports; static inline int inet_is_reserved_local_port(int port) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index bf2ec2202c56..5dbd232e12ff 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -15,6 +15,10 @@ struct fib_rules_ops; struct hlist_head; struct fib_table; struct sock; +struct local_ports { + seqlock_t lock; + int range[2]; +}; struct netns_ipv4 { #ifdef CONFIG_SYSCTL @@ -62,6 +66,8 @@ struct netns_ipv4 { int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; + struct local_ports sysctl_local_ports; + int sysctl_tcp_ecn; kgid_t sysctl_ping_group_range[2]; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6acb541c9091..7ac7aa11130e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -29,27 +29,19 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; EXPORT_SYMBOL(inet_csk_timer_bug_msg); #endif -/* - * This struct holds the first and last local port number. - */ -struct local_ports sysctl_local_ports __read_mostly = { - .lock = __SEQLOCK_UNLOCKED(sysctl_local_ports.lock), - .range = { 32768, 61000 }, -}; - unsigned long *sysctl_local_reserved_ports; EXPORT_SYMBOL(sysctl_local_reserved_ports); -void inet_get_local_port_range(int *low, int *high) +void inet_get_local_port_range(struct net *net, int *low, int *high) { unsigned int seq; do { - seq = read_seqbegin(&sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); - *low = sysctl_local_ports.range[0]; - *high = sysctl_local_ports.range[1]; - } while (read_seqretry(&sysctl_local_ports.lock, seq)); + *low = net->ipv4.sysctl_local_ports.range[0]; + *high = net->ipv4.sysctl_local_ports.range[1]; + } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); } EXPORT_SYMBOL(inet_get_local_port_range); @@ -116,7 +108,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) int remaining, rover, low, high; again: - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; smallest_rover = rover = net_random() % remaining + low; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7bd8983dbfcf..2779037bd113 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -494,7 +494,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, u32 offset = hint + port_offset; struct inet_timewait_sock *tw = NULL; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; local_bh_disable(); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 706d108e128c..a62610443152 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -237,11 +237,11 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, unsigned int seq; do { - seq = read_seqbegin(&sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 540279f4c531..c08f096d46b5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -43,12 +43,12 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; /* Update system visible IP port range */ -static void set_local_port_range(int range[2]) +static void set_local_port_range(struct net *net, int range[2]) { - write_seqlock(&sysctl_local_ports.lock); - sysctl_local_ports.range[0] = range[0]; - sysctl_local_ports.range[1] = range[1]; - write_sequnlock(&sysctl_local_ports.lock); + write_seqlock(&net->ipv4.sysctl_local_ports.lock); + net->ipv4.sysctl_local_ports.range[0] = range[0]; + net->ipv4.sysctl_local_ports.range[1] = range[1]; + write_sequnlock(&net->ipv4.sysctl_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -56,6 +56,8 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = + container_of(table->data, struct net, ipv4.sysctl_local_ports.range); int ret; int range[2]; struct ctl_table tmp = { @@ -66,14 +68,15 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, .extra2 = &ip_local_port_range_max, }; - inet_get_local_port_range(range, range + 1); + inet_get_local_port_range(net, &range[0], &range[1]); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { if (range[1] < range[0]) ret = -EINVAL; else - set_local_port_range(range); + set_local_port_range(net, range); } return ret; @@ -83,23 +86,27 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high) { kgid_t *data = table->data; + struct net *net = + container_of(table->data, struct net, ipv4.sysctl_ping_group_range); unsigned int seq; do { - seq = read_seqbegin(&sysctl_local_ports.lock); + seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock); *low = data[0]; *high = data[1]; - } while (read_seqretry(&sysctl_local_ports.lock, seq)); + } while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq)); } /* Update system visible IP port range */ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high) { kgid_t *data = table->data; - write_seqlock(&sysctl_local_ports.lock); + struct net *net = + container_of(table->data, struct net, ipv4.sysctl_ping_group_range); + write_seqlock(&net->ipv4.sysctl_local_ports.lock); data[0] = low; data[1] = high; - write_sequnlock(&sysctl_local_ports.lock); + write_sequnlock(&net->ipv4.sysctl_local_ports.lock); } /* Validate changes from /proc interface. */ @@ -474,13 +481,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "ip_local_port_range", - .data = &sysctl_local_ports.range, - .maxlen = sizeof(sysctl_local_ports.range), - .mode = 0644, - .proc_handler = ipv4_local_port_range, - }, { .procname = "ip_local_reserved_ports", .data = NULL, /* initialized in sysctl_ipv4_init */ @@ -853,6 +853,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_local_port_range", + .maxlen = sizeof(init_net.ipv4.sysctl_local_ports.range), + .data = &init_net.ipv4.sysctl_local_ports.range, + .mode = 0644, + .proc_handler = ipv4_local_port_range, + }, { .procname = "tcp_mem", .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), @@ -888,6 +895,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_ping_group_range; table[7].data = &net->ipv4.sysctl_tcp_ecn; + table[8].data = + &net->ipv4.sysctl_local_ports.range; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) @@ -901,6 +910,13 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1); net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0); + /* + * Set defaults for local port range + */ + seqlock_init(&net->ipv4.sysctl_local_ports.lock); + net->ipv4.sysctl_local_ports.range[0] = 32768; + net->ipv4.sysctl_local_ports.range[1] = 61000; + tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 22462d947750..728ce9503a27 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -219,7 +219,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned short first, last; DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rand = net_random(); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index a481c03e2861..56e22b74cf96 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -173,7 +173,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) skb->local_df = 1; - inet_get_local_port_range(&port_min, &port_max); + inet_get_local_port_range(net, &port_min, &port_max); src_port = vxlan_src_port(port_min, port_max, skb); err = vxlan_xmit_skb(vxlan_port->vs, rt, skb, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 911b71b26b0e..72046b9729a8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5890,7 +5890,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) int low, high, remaining, index; unsigned int rover; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(sock_net(sk), &low, &high); remaining = (high - low) + 1; rover = net_random() % remaining + low; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a5091ec06aa6..568c7699abf1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3929,7 +3929,7 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in if (snum) { int low, high; - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(sock_net(sk), &low, &high); if (snum < max(PROT_SOCK, low) || snum > high) { err = sel_netport_sid(sk->sk_protocol, -- cgit v1.2.3 From 19e49834d22c2271ed1f4a03aaa4b74986447fb4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 4 Oct 2013 12:54:11 -0700 Subject: selinux: remove 'flags' parameter from inode_has_perm Every single user passes in '0'. I think we had non-zero users back in some stone age when selinux_inode_permission() was implemented in terms of inode_has_perm(), but that complicated case got split up into a totally separate code-path so that we could optimize the much simpler special cases. See commit 2e33405785d3 ("SELinux: delay initialization of audit data in selinux_inode_permission") for example. Signed-off-by: Linus Torvalds --- security/selinux/hooks.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index a5091ec06aa6..967823212d7d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1525,8 +1525,7 @@ static int task_has_system(struct task_struct *tsk, static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, - struct common_audit_data *adp, - unsigned flags) + struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; @@ -1539,7 +1538,7 @@ static int inode_has_perm(const struct cred *cred, sid = cred_sid(cred); isec = inode->i_security; - return avc_has_perm_flags(sid, isec->sid, isec->sclass, perms, adp, flags); + return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing @@ -1554,7 +1553,7 @@ static inline int dentry_has_perm(const struct cred *cred, ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; - return inode_has_perm(cred, inode, av, &ad, 0); + return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing @@ -1569,7 +1568,7 @@ static inline int path_has_perm(const struct cred *cred, ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; - return inode_has_perm(cred, inode, av, &ad, 0); + return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ @@ -1581,7 +1580,7 @@ static inline int file_path_has_perm(const struct cred *cred, ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; - return inode_has_perm(cred, file_inode(file), av, &ad, 0); + return inode_has_perm(cred, file_inode(file), av, &ad); } /* Check whether a task can use an open file descriptor to @@ -1617,7 +1616,7 @@ static int file_has_perm(const struct cred *cred, /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) - rc = inode_has_perm(cred, inode, av, &ad, 0); + rc = inode_has_perm(cred, inode, av, &ad); out: return rc; -- cgit v1.2.3 From cb4fbe5703be51f8a2dff4052b1901941ab99e12 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 4 Oct 2013 12:57:22 -0700 Subject: selinux: avc_has_perm_flags has no more users .. so get rid of it. The only indirect users were all the avc_has_perm() callers which just expanded to have a zero flags argument. Signed-off-by: Linus Torvalds --- security/selinux/avc.c | 9 +++------ security/selinux/include/avc.h | 14 +++----------- 2 files changed, 6 insertions(+), 17 deletions(-) (limited to 'security') diff --git a/security/selinux/avc.c b/security/selinux/avc.c index dad36a6ab45f..e720f72fcb87 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -746,7 +746,6 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @auditdata: auxiliary audit data - * @flags: VFS walk flags * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions @@ -756,17 +755,15 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, * permissions are granted, -%EACCES if any permissions are denied, or * another -errno upon other errors. */ -int avc_has_perm_flags(u32 ssid, u32 tsid, u16 tclass, - u32 requested, struct common_audit_data *auditdata, - unsigned flags) +int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, + u32 requested, struct common_audit_data *auditdata) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd); - rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata, - flags); + rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata, 0); if (rc2) return rc2; return rc; diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index 92d0ab561db8..e30657b59cb3 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -147,17 +147,9 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid, unsigned flags, struct av_decision *avd); -int avc_has_perm_flags(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - struct common_audit_data *auditdata, - unsigned); - -static inline int avc_has_perm(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - struct common_audit_data *auditdata) -{ - return avc_has_perm_flags(ssid, tsid, tclass, requested, auditdata, 0); -} +int avc_has_perm(u32 ssid, u32 tsid, + u16 tclass, u32 requested, + struct common_audit_data *auditdata); u32 avc_policy_seqno(void); -- cgit v1.2.3 From ab3540626435c01e08fe58ce544311a78430f112 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 4 Oct 2013 14:05:38 -0700 Subject: selinux: remove 'flags' parameter from avc_audit() Now avc_audit() has no more users with that parameter. Remove it. Signed-off-by: Linus Torvalds --- security/selinux/avc.c | 2 +- security/selinux/hooks.c | 2 +- security/selinux/include/avc.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'security') diff --git a/security/selinux/avc.c b/security/selinux/avc.c index e720f72fcb87..fc3e6628a864 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -763,7 +763,7 @@ int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0, &avd); - rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata, 0); + rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc, auditdata); if (rc2) return rc2; return rc; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 967823212d7d..5b5231068516 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1502,7 +1502,7 @@ static int cred_has_capability(const struct cred *cred, rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); if (audit == SECURITY_CAP_AUDIT) { - int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad, 0); + int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index e30657b59cb3..f53ee3c58d0f 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -130,7 +130,7 @@ static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, int result, - struct common_audit_data *a, unsigned flags) + struct common_audit_data *a) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); @@ -138,7 +138,7 @@ static inline int avc_audit(u32 ssid, u32 tsid, return 0; return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied, - a, flags); + a, 0); } #define AVC_STRICT 1 /* Ignore permissive mode. */ -- cgit v1.2.3 From efe4208f47f907b86f528788da711e8ab9dea44d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 3 Oct 2013 15:42:29 -0700 Subject: ipv6: make lookups simpler and faster TCP listener refactoring, part 4 : To speed up inet lookups, we moved IPv4 addresses from inet to struct sock_common Now is time to do the same for IPv6, because it permits us to have fast lookups for all kind of sockets, including upcoming SYN_RECV. Getting IPv6 addresses in TCP lookups currently requires two extra cache lines, plus a dereference (and memory stall). inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6 This patch is way bigger than its IPv4 counter part, because for IPv4, we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6, it's not doable easily. inet6_sk(sk)->daddr becomes sk->sk_v6_daddr inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr at the same offset. We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic macro. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 46 +++----------------- include/net/inet6_hashtables.h | 5 +-- include/net/inet_timewait_sock.h | 4 +- include/net/ip.h | 2 +- include/net/ip6_checksum.h | 2 +- include/net/sock.h | 9 ++++ net/dccp/ipv6.c | 24 +++++------ net/dccp/ipv6.h | 1 - net/dccp/minisocks.c | 7 +--- net/ipv4/inet_diag.c | 35 +++++++--------- net/ipv4/ping.c | 15 ++++--- net/ipv4/tcp_metrics.c | 10 ++--- net/ipv4/tcp_minisocks.c | 7 +--- net/ipv4/tcp_probe.c | 29 +++++-------- net/ipv4/tcp_timer.c | 3 +- net/ipv6/af_inet6.c | 10 ++--- net/ipv6/datagram.c | 25 ++++++----- net/ipv6/inet6_connection_sock.c | 7 ++-- net/ipv6/inet6_hashtables.c | 58 +++++++++----------------- net/ipv6/ipv6_sockglue.c | 7 ++-- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 4 +- net/ipv6/ping.c | 2 +- net/ipv6/raw.c | 17 ++++---- net/ipv6/tcp_ipv6.c | 44 ++++++++++--------- net/ipv6/udp.c | 48 ++++++++++----------- net/l2tp/l2tp_core.c | 10 ++--- net/l2tp/l2tp_debugfs.c | 5 ++- net/l2tp/l2tp_ip6.c | 16 +++---- net/l2tp/l2tp_netlink.c | 4 +- net/l2tp/l2tp_ppp.c | 12 +++--- net/netfilter/xt_TPROXY.c | 2 +- net/netfilter/xt_socket.c | 2 +- net/sctp/ipv6.c | 22 +++++----- net/sunrpc/svcsock.c | 2 +- security/lsm_audit.c | 5 +-- 35 files changed, 213 insertions(+), 288 deletions(-) (limited to 'security') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index b7f1f3bb346d..35f6c1b562c4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -141,8 +141,6 @@ struct ipv6_fl_socklist; */ struct ipv6_pinfo { struct in6_addr saddr; - struct in6_addr rcv_saddr; - struct in6_addr daddr; struct in6_pktinfo sticky_pktinfo; const struct in6_addr *daddr_cache; #ifdef CONFIG_IPV6_SUBTREES @@ -256,22 +254,10 @@ struct tcp6_sock { extern int inet6_sk_rebuild_header(struct sock *sk); -struct inet6_timewait_sock { - struct in6_addr tw_v6_daddr; - struct in6_addr tw_v6_rcv_saddr; -}; - struct tcp6_timewait_sock { struct tcp_timewait_sock tcp6tw_tcp; - struct inet6_timewait_sock tcp6tw_inet6; }; -static inline struct inet6_timewait_sock *inet6_twsk(const struct sock *sk) -{ - return (struct inet6_timewait_sock *)(((u8 *)sk) + - inet_twsk(sk)->tw_ipv6_offset); -} - #if IS_ENABLED(CONFIG_IPV6) static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { @@ -321,21 +307,11 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to, #define __ipv6_only_sock(sk) (inet6_sk(sk)->ipv6only) #define ipv6_only_sock(sk) ((sk)->sk_family == PF_INET6 && __ipv6_only_sock(sk)) -static inline u16 inet6_tw_offset(const struct proto *prot) -{ - return prot->twsk_prot->twsk_obj_size - - sizeof(struct inet6_timewait_sock); -} - -static inline struct in6_addr *__inet6_rcv_saddr(const struct sock *sk) +static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { - return likely(sk->sk_state != TCP_TIME_WAIT) ? - &inet6_sk(sk)->rcv_saddr : &inet6_twsk(sk)->tw_v6_rcv_saddr; -} - -static inline struct in6_addr *inet6_rcv_saddr(const struct sock *sk) -{ - return sk->sk_family == AF_INET6 ? __inet6_rcv_saddr(sk) : NULL; + if (sk->sk_family == AF_INET6) + return &sk->sk_v6_rcv_saddr; + return NULL; } static inline int inet_v6_ipv6only(const struct sock *sk) @@ -363,7 +339,6 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return NULL; } -#define __inet6_rcv_saddr(__sk) NULL #define inet6_rcv_saddr(__sk) NULL #define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 @@ -372,19 +347,10 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ - ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ + ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ + ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ (!(__sk)->sk_bound_dev_if || \ ((__sk)->sk_bound_dev_if == (__dif))) && \ net_eq(sock_net(__sk), (__net))) -#define INET6_TW_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr)) && \ - ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_rcv_saddr, (__daddr)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif))) && \ - net_eq(sock_net(__sk), (__net))) - #endif /* _IPV6_H */ diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index f52fa88feb64..a105d1a2fc00 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -43,9 +43,8 @@ static inline unsigned int inet6_ehashfn(struct net *net, static inline int inet6_sk_ehashfn(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - const struct in6_addr *laddr = &np->rcv_saddr; - const struct in6_addr *faddr = &np->daddr; + const struct in6_addr *laddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *faddr = &sk->sk_v6_daddr; const __u16 lport = inet->inet_num; const __be16 fport = inet->inet_dport; struct net *net = sock_net(sk); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index de9e3ab7d43d..b647c6270eb7 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -116,7 +116,9 @@ struct inet_timewait_sock { #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net #define tw_daddr __tw_common.skc_daddr +#define tw_v6_daddr __tw_common.skc_v6_daddr #define tw_rcv_saddr __tw_common.skc_rcv_saddr +#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr #define tw_dport __tw_common.skc_dport #define tw_num __tw_common.skc_num @@ -133,7 +135,7 @@ struct inet_timewait_sock { tw_transparent : 1, tw_pad : 6, /* 6 bits hole */ tw_tos : 8, - tw_ipv6_offset : 16; + tw_pad2 : 16 /* 16 bits hole */ kmemcheck_bitfield_end(flags); u32 tw_ttd; struct inet_bind_bucket *tw_tb; diff --git a/include/net/ip.h b/include/net/ip.h index b39ebe5339ac..217bc5bfc6c6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -374,7 +374,7 @@ static __inline__ void inet_reset_saddr(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); memset(&np->saddr, 0, sizeof(np->saddr)); - memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr)); + memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); } #endif } diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 7686e3f5033d..1944406949ba 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -70,7 +70,7 @@ static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); - __tcp_v6_send_check(skb, &np->saddr, &np->daddr); + __tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr); } int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto); diff --git a/include/net/sock.h b/include/net/sock.h index 3f3e48c4704d..7e50df5c71d4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -191,6 +191,12 @@ struct sock_common { #ifdef CONFIG_NET_NS struct net *skc_net; #endif + +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr skc_v6_daddr; + struct in6_addr skc_v6_rcv_saddr; +#endif + /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() @@ -314,6 +320,9 @@ struct sock { #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr + socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; /* diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6cf9f7782ad4..7f075b83128a 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -67,7 +67,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); + dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr); } static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) @@ -467,11 +467,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - newnp->rcv_saddr = newnp->saddr; + newsk->sk_v6_rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; @@ -538,9 +538,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->daddr = ireq6->rmt_addr; + newsk->sk_v6_daddr = ireq6->rmt_addr; newnp->saddr = ireq6->loc_addr; - newnp->rcv_saddr = ireq6->loc_addr; + newsk->sk_v6_rcv_saddr = ireq6->loc_addr; newsk->sk_bound_dev_if = ireq6->iif; /* Now IPv6 options... @@ -885,7 +885,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - np->daddr = usin->sin6_addr; + sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -915,16 +915,16 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto failure; } ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_DCCP; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = usin->sin6_port; @@ -941,7 +941,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - np->rcv_saddr = *saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ @@ -963,7 +963,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto late_failure; dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); err = dccp_connect(sk); diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h index 6eef81fdbe56..6604fc3fe953 100644 --- a/net/dccp/ipv6.h +++ b/net/dccp/ipv6.h @@ -30,7 +30,6 @@ struct dccp6_request_sock { struct dccp6_timewait_sock { struct inet_timewait_sock inet; - struct inet6_timewait_sock tw6; }; #endif /* _DCCP_IPV6_H */ diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 662071b249cc..32e80d96d4c0 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -56,12 +56,9 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_timewait_sock *tw6; - tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); - tw6 = inet6_twsk((struct sock *)tw); - tw6->tw_v6_daddr = np->daddr; - tw6->tw_v6_rcv_saddr = np->rcv_saddr; + tw->tw_v6_daddr = sk->sk_v6_daddr; + tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_ipv6only = np->ipv6only; } #endif diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8e1e40653357..ecc179d676e4 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -121,13 +121,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, #if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); - *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr; - *(struct in6_addr *)r->id.idiag_dst = np->daddr; + *(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr; if (ext & (1 << (INET_DIAG_TCLASS - 1))) - if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0) + if (nla_put_u8(skb, INET_DIAG_TCLASS, + inet6_sk(sk)->tclass) < 0) goto errout; } #endif @@ -255,11 +255,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_inode = 0; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { - const struct inet6_timewait_sock *tw6 = - inet6_twsk((struct sock *)tw); - - *(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr; - *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr; + *(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr; } #endif @@ -273,10 +270,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill((struct inet_timewait_sock *)sk, - skb, r, portid, seq, nlmsg_flags, - unlh); - return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh); + return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, seq, + nlmsg_flags, unlh); + + return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, + nlmsg_flags, unlh); } int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, @@ -489,10 +487,9 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) if (entry.family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - entry.saddr = np->rcv_saddr.s6_addr32; - entry.daddr = np->daddr.s6_addr32; + entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32; + entry.daddr = sk->sk_v6_daddr.s6_addr32; } else #endif { @@ -649,10 +646,8 @@ static int inet_twsk_diag_dump(struct sock *sk, entry.family = tw->tw_family; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { - struct inet6_timewait_sock *tw6 = - inet6_twsk((struct sock *)tw); - entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32; - entry.daddr = tw6->tw_v6_daddr.s6_addr32; + entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32; + entry.daddr = tw->tw_v6_daddr.s6_addr32; } else #endif { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a62610443152..ccefc07beacd 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -202,15 +202,14 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6) && sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, (int) isk->inet_num, - &inet6_sk(sk)->rcv_saddr, + &sk->sk_v6_rcv_saddr, sk->sk_bound_dev_if); - if (!ipv6_addr_any(&np->rcv_saddr) && - !ipv6_addr_equal(&np->rcv_saddr, + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, &ipv6_hdr(skb)->daddr)) continue; #endif @@ -362,7 +361,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) } else if (saddr->sa_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; struct ipv6_pinfo *np = inet6_sk(sk); - np->rcv_saddr = np->saddr = addr->sin6_addr; + sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr; #endif } } @@ -376,7 +375,7 @@ static void ping_clear_saddr(struct sock *sk, int dif) #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr)); + memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr)); memset(&np->saddr, 0, sizeof(np->saddr)); #endif } @@ -418,7 +417,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = 0; if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) || (sk->sk_family == AF_INET6 && - !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr))) + !ipv6_addr_any(&sk->sk_v6_rcv_saddr))) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) @@ -429,7 +428,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) - memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr)); + memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); #endif sk_dst_reset(sk); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 52f3c6b971d2..27535fd5ea10 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -240,7 +240,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw) { - struct inet6_timewait_sock *tw6; struct tcp_metrics_block *tm; struct inetpeer_addr addr; unsigned int hash; @@ -253,9 +252,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock hash = (__force unsigned int) addr.addr.a4; break; case AF_INET6: - tw6 = inet6_twsk((struct sock *)tw); - *(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr; - hash = ipv6_addr_hash(&tw6->tw_v6_daddr); + *(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr; + hash = ipv6_addr_hash(&tw->tw_v6_daddr); break; default: return NULL; @@ -289,8 +287,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, hash = (__force unsigned int) addr.addr.a4; break; case AF_INET6: - *(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr; - hash = ipv6_addr_hash(&inet6_sk(sk)->daddr); + *(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr; + hash = ipv6_addr_hash(&sk->sk_v6_daddr); break; default: return NULL; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 58a3e69aef64..97b684159861 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -293,12 +293,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_timewait_sock *tw6; - tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); - tw6 = inet6_twsk((struct sock *)tw); - tw6->tw_v6_daddr = np->daddr; - tw6->tw_v6_rcv_saddr = np->rcv_saddr; + tw->tw_v6_daddr = sk->sk_v6_daddr; + tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_ipv6only = np->ipv6only; } diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 611beab38a00..8b97d71e193b 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -101,22 +101,6 @@ static inline int tcp_probe_avail(void) si4.sin_addr.s_addr = inet->inet_##mem##addr; \ } while (0) \ -#if IS_ENABLED(CONFIG_IPV6) -#define tcp_probe_copy_fl_to_si6(inet, si6, mem) \ - do { \ - struct ipv6_pinfo *pi6 = inet->pinet6; \ - si6.sin6_family = AF_INET6; \ - si6.sin6_port = inet->inet_##mem##port; \ - si6.sin6_addr = pi6->mem##addr; \ - si6.sin6_flowinfo = 0; /* No need here. */ \ - si6.sin6_scope_id = 0; /* No need here. */ \ - } while (0) -#else -#define tcp_probe_copy_fl_to_si6(fl, si6, mem) \ - do { \ - memset(&si6, 0, sizeof(si6)); \ - } while (0) -#endif /* * Hook inserted to be called before each receive packet. @@ -147,8 +131,17 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d); break; case AF_INET6: - tcp_probe_copy_fl_to_si6(inet, p->src.v6, s); - tcp_probe_copy_fl_to_si6(inet, p->dst.v6, d); + memset(&p->src.v6, 0, sizeof(p->src.v6)); + memset(&p->dst.v6, 0, sizeof(p->dst.v6)); +#if IS_ENABLED(CONFIG_IPV6) + p->src.v6.sin6_family = AF_INET6; + p->src.v6.sin6_port = inet->inet_sport; + p->src.v6.sin6_addr = inet6_sk(sk)->saddr; + + p->dst.v6.sin6_family = AF_INET6; + p->dst.v6.sin6_port = inet->inet_dport; + p->dst.v6.sin6_addr = sk->sk_v6_daddr; +#endif break; default: BUG(); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4b85e6f636c9..af07b5b23ebf 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -374,9 +374,8 @@ void tcp_retransmit_timer(struct sock *sk) } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &np->daddr, + &sk->sk_v6_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 4966b124dc2e..a2cb07cd3850 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -364,7 +364,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = v4addr; inet->inet_saddr = v4addr; - np->rcv_saddr = addr->sin6_addr; + sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; @@ -461,14 +461,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, peer == 1) return -ENOTCONN; sin->sin6_port = inet->inet_dport; - sin->sin6_addr = np->daddr; + sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; } else { - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else - sin->sin6_addr = np->rcv_saddr; + sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; } @@ -655,7 +655,7 @@ int inet6_sk_rebuild_header(struct sock *sk) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; fl6.flowi6_oif = sk->sk_bound_dev_if; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 48b6bd2a9a14..a454b0ff57c7 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -107,16 +107,16 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); if (ipv6_addr_any(&np->saddr) || ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr) || - ipv6_mapped_addr_any(&np->rcv_saddr)) { + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || + ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &np->rcv_saddr); + &sk->sk_v6_rcv_saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } @@ -145,7 +145,7 @@ ipv4_connected: } } - np->daddr = *daddr; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6.flowlabel; inet->inet_dport = usin->sin6_port; @@ -156,7 +156,7 @@ ipv4_connected: */ fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -183,16 +183,16 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) np->saddr = fl6.saddr; - if (ipv6_addr_any(&np->rcv_saddr)) { - np->rcv_saddr = fl6.saddr; + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + sk->sk_v6_rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : @@ -883,11 +883,10 @@ EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int bucket) { - struct ipv6_pinfo *np = inet6_sk(sp); const struct in6_addr *dest, *src; - dest = &np->daddr; - src = &np->rcv_saddr; + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n", diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index e4311cbc8b4e..b7400b480e74 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -165,11 +165,10 @@ EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add); void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) { - struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; sin6->sin6_family = AF_INET6; - sin6->sin6_addr = np->daddr; + sin6->sin6_addr = sk->sk_v6_daddr; sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; @@ -203,7 +202,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; - fl6->daddr = np->daddr; + fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6->flowlabel); @@ -245,7 +244,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); rcu_read_unlock(); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 46440777e1c5..842d833dfc18 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -89,30 +89,16 @@ begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; - if (sk->sk_state == TCP_TIME_WAIT) { - if (!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif)) - continue; - } else { - if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) - continue; - } + if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) + continue; if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) goto out; - if (sk->sk_state == TCP_TIME_WAIT) { - if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, - ports, dif))) { - sock_gen_put(sk); - goto begin; - } - } else { - if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, - ports, dif))) { - sock_put(sk); - goto begin; - } - goto found; + if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { + sock_gen_put(sk); + goto begin; } + goto found; } if (get_nulls_value(node) != slot) goto begin; @@ -133,11 +119,10 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { - const struct ipv6_pinfo *np = inet6_sk(sk); score = 1; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score++; } @@ -229,9 +214,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - const struct in6_addr *daddr = &np->rcv_saddr; - const struct in6_addr *saddr = &np->daddr; + const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; + const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); @@ -250,23 +234,19 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, if (sk2->sk_hash != hash) continue; - if (sk2->sk_state == TCP_TIME_WAIT) { - if (likely(INET6_TW_MATCH(sk2, net, saddr, daddr, - ports, dif))) { + if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) { + if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) - goto unique; - else - goto not_unique; + break; } - } - if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) goto not_unique; + } } -unique: /* Must record num and sport now. Otherwise we will see - * in hash table socket with a funny identity. */ + * in hash table socket with a funny identity. + */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; @@ -299,9 +279,9 @@ not_unique: static inline u32 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - const struct ipv6_pinfo *np = inet6_sk(sk); - return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, - np->daddr.s6_addr32, + + return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d1e2e8ef29c5..4919a8e6063e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -174,7 +174,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, } if (ipv6_only_sock(sk) || - !ipv6_addr_v4mapped(&np->daddr)) { + !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { retv = -EADDRNOTAVAIL; break; } @@ -1011,7 +1011,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -1026,7 +1026,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : + np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index d6e4dd8b58df..54b75ead5a69 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -297,9 +297,9 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; struct nf_conn *ct; - tuple.src.u3.in6 = inet6->rcv_saddr; + tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; tuple.src.u.tcp.port = inet->inet_sport; - tuple.dst.u3.in6 = inet6->daddr; + tuple.dst.u3.in6 = sk->sk_v6_daddr; tuple.dst.u.tcp.port = inet->inet_dport; tuple.dst.protonum = sk->sk_protocol; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 18f19df4189f..8815e31a87fe 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -116,7 +116,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; } if (!iif) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a4ed2416399e..3c00842b0079 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -77,20 +77,19 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { - struct ipv6_pinfo *np = inet6_sk(sk); if (!net_eq(sock_net(sk), net)) continue; - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) @@ -302,7 +301,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; - np->rcv_saddr = addr->sin6_addr; + sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; @@ -804,8 +803,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && @@ -816,7 +815,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, return -EDESTADDRREQ; proto = inet->inet_num; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 528e61afaf5e..541dfc40c7b3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -192,13 +192,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (tp->rx_opt.ts_recent_stamp && - !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) { + !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; tp->write_seq = 0; } - np->daddr = usin->sin6_addr; + sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -237,17 +237,17 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } else { ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, - &np->rcv_saddr); + &sk->sk_v6_rcv_saddr); } return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - fl6.daddr = np->daddr; + fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -266,7 +266,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - np->rcv_saddr = *saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ @@ -279,7 +279,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, rt = (struct rt6_info *) dst; if (tcp_death_row.sysctl_tw_recycle && !tp->rx_opt.ts_recent_stamp && - ipv6_addr_equal(&rt->rt6i_dst.addr, &np->daddr)) + ipv6_addr_equal(&rt->rt6i_dst.addr, &sk->sk_v6_daddr)) tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; @@ -298,7 +298,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); @@ -515,7 +515,7 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v6_md5_do_lookup(sk, &inet6_sk(addr_sk)->daddr); + return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, @@ -621,7 +621,7 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, if (sk) { saddr = &inet6_sk(sk)->saddr; - daddr = &inet6_sk(sk)->daddr; + daddr = &sk->sk_v6_daddr; } else if (req) { saddr = &inet6_rsk(req)->loc_addr; daddr = &inet6_rsk(req)->rmt_addr; @@ -1116,11 +1116,11 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - newnp->rcv_saddr = newnp->saddr; + newsk->sk_v6_rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1185,9 +1185,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->daddr = treq->rmt_addr; + newsk->sk_v6_daddr = treq->rmt_addr; newnp->saddr = treq->loc_addr; - newnp->rcv_saddr = treq->loc_addr; + newsk->sk_v6_rcv_saddr = treq->loc_addr; newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... @@ -1244,13 +1244,13 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v6_md5_do_lookup(sk, &newnp->daddr)) != NULL) { + if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, AF_INET6, key->key, key->keylen, sk_gfp_atomic(sk, GFP_ATOMIC)); } @@ -1758,10 +1758,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - const struct ipv6_pinfo *np = inet6_sk(sp); - dest = &np->daddr; - src = &np->rcv_saddr; + dest = &sp->sk_v6_daddr; + src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); @@ -1810,11 +1809,10 @@ static void get_timewait6_sock(struct seq_file *seq, { const struct in6_addr *dest, *src; __u16 destp, srcp; - const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); s32 delta = tw->tw_ttd - inet_tw_time_stamp(); - dest = &tw6->tw_v6_daddr; - src = &tw6->tw_v6_rcv_saddr; + dest = &tw->tw_v6_daddr; + src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 37532478e3ba..b496de19a341 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -55,11 +55,10 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { - const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); - int addr_type = ipv6_addr_type(sk_rcv_saddr6); + int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ @@ -77,7 +76,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 1; if (sk2_rcv_saddr6 && - ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6)) + ipv6_addr_equal(&sk->sk_v6_rcv_saddr, sk2_rcv_saddr6)) return 1; return 0; @@ -105,7 +104,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) unsigned int hash2_nulladdr = udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); unsigned int hash2_partial = - udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; @@ -115,7 +114,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) static void udp_v6_rehash(struct sock *sk) { u16 new_hash = udp6_portaddr_hash(sock_net(sk), - &inet6_sk(sk)->rcv_saddr, + &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); @@ -131,7 +130,6 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); score = 0; @@ -140,13 +138,13 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score++; } - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score++; } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } @@ -169,10 +167,9 @@ static inline int compute_score2(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); - if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; score = 0; if (inet->inet_dport) { @@ -180,8 +177,8 @@ static inline int compute_score2(struct sock *sk, struct net *net, return -1; score++; } - if (!ipv6_addr_any(&np->daddr)) { - if (!ipv6_addr_equal(&np->daddr, saddr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr)) return -1; score++; } @@ -549,7 +546,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; - if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) { + if (!ipv6_addr_any(&sk->sk_v6_daddr)) { sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); } @@ -690,20 +687,19 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (udp_sk(s)->udp_port_hash == num && s->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(s); if (inet->inet_dport) { if (inet->inet_dport != rmt_port) continue; } - if (!ipv6_addr_any(&np->daddr) && - !ipv6_addr_equal(&np->daddr, rmt_addr)) + if (!ipv6_addr_any(&sk->sk_v6_daddr) && + !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif) continue; - if (!ipv6_addr_any(&np->rcv_saddr)) { - if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr)) + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { + if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) continue; } if (!inet6_mc_check(s, loc_addr, rmt_addr)) @@ -1063,7 +1059,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, } else if (!up->pending) { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; } else daddr = NULL; @@ -1133,8 +1129,8 @@ do_udp_sendmsg: * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && @@ -1145,7 +1141,7 @@ do_udp_sendmsg: return -EDESTADDRREQ; fl6.fl6_dport = inet->inet_dport; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; connected = 1; } @@ -1261,8 +1257,8 @@ do_append_data: if (dst) { if (connected) { ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &np->daddr) ? - &np->daddr : NULL, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6.saddr, &np->saddr) ? &np->saddr : diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index b076e8309bc2..9af77d9c0ec9 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1181,7 +1181,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) { __wsum csum = skb_checksum(skb, 0, udp_len, 0); skb->ip_summed = CHECKSUM_UNNECESSARY; - uh->check = csum_ipv6_magic(&np->saddr, &np->daddr, udp_len, + uh->check = csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; @@ -1189,7 +1189,7 @@ static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); - uh->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, + uh->check = ~csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len, IPPROTO_UDP, 0); } } @@ -1713,13 +1713,13 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 struct ipv6_pinfo *np = inet6_sk(sk); if (ipv6_addr_v4mapped(&np->saddr) && - ipv6_addr_v4mapped(&np->daddr)) { + ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { struct inet_sock *inet = inet_sk(sk); tunnel->v4mapped = true; inet->inet_saddr = np->saddr.s6_addr32[3]; - inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3]; - inet->inet_daddr = np->daddr.s6_addr32[3]; + inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3]; + inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3]; } else { tunnel->v4mapped = false; } diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 072d7202e182..2d6760a2ae34 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -127,9 +127,10 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) #if IS_ENABLED(CONFIG_IPV6) if (tunnel->sock->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(tunnel->sock); + const struct ipv6_pinfo *np = inet6_sk(tunnel->sock); + seq_printf(m, " from %pI6c to %pI6c\n", - &np->saddr, &np->daddr); + &np->saddr, &tunnel->sock->sk_v6_daddr); } else #endif seq_printf(m, " from %pI4 to %pI4\n", diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index b8a6039314e8..cfd65304be60 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -63,7 +63,7 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, struct sock *sk; sk_for_each_bound(sk, &l2tp_ip6_bind_table) { - struct in6_addr *addr = inet6_rcv_saddr(sk); + const struct in6_addr *addr = inet6_rcv_saddr(sk); struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); if (l2tp == NULL) @@ -331,7 +331,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) rcu_read_unlock(); inet->inet_rcv_saddr = inet->inet_saddr = v4addr; - np->rcv_saddr = addr->l2tp_addr; + sk->sk_v6_rcv_saddr = addr->l2tp_addr; np->saddr = addr->l2tp_addr; l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; @@ -421,14 +421,14 @@ static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, if (!lsk->peer_conn_id) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; - lsa->l2tp_addr = np->daddr; + lsa->l2tp_addr = sk->sk_v6_daddr; if (np->sndflow) lsa->l2tp_flowinfo = np->flow_label; } else { - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) lsa->l2tp_addr = np->saddr; else - lsa->l2tp_addr = np->rcv_saddr; + lsa->l2tp_addr = sk->sk_v6_rcv_saddr; lsa->l2tp_conn_id = lsk->conn_id; } @@ -537,8 +537,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && - ipv6_addr_equal(daddr, &np->daddr)) - daddr = &np->daddr; + ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) + daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && lsa->l2tp_scope_id && @@ -548,7 +548,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = &np->daddr; + daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 0825ff26e113..be446d517bc9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -306,8 +306,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (np) { if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr), &np->saddr) || - nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(np->daddr), - &np->daddr)) + nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(sk->sk_v6_daddr), + &sk->sk_v6_daddr)) goto nla_put_failure; } else #endif diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ebee2ded9e9..f0a7adaef2ea 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -906,8 +906,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, #if IS_ENABLED(CONFIG_IPV6) } else if ((tunnel->version == 2) && (tunnel->sock->sk_family == AF_INET6)) { - struct ipv6_pinfo *np = inet6_sk(tunnel->sock); struct sockaddr_pppol2tpin6 sp; + len = sizeof(sp); memset(&sp, 0, len); sp.sa_family = AF_PPPOX; @@ -920,13 +920,13 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, sp.pppol2tp.d_session = session->peer_session_id; sp.pppol2tp.addr.sin6_family = AF_INET6; sp.pppol2tp.addr.sin6_port = inet->inet_dport; - memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr, - sizeof(np->daddr)); + memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr, + sizeof(tunnel->sock->sk_v6_daddr)); memcpy(uaddr, &sp, len); } else if ((tunnel->version == 3) && (tunnel->sock->sk_family == AF_INET6)) { - struct ipv6_pinfo *np = inet6_sk(tunnel->sock); struct sockaddr_pppol2tpv3in6 sp; + len = sizeof(sp); memset(&sp, 0, len); sp.sa_family = AF_PPPOX; @@ -939,8 +939,8 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, sp.pppol2tp.d_session = session->peer_session_id; sp.pppol2tp.addr.sin6_family = AF_INET6; sp.pppol2tp.addr.sin6_port = inet->inet_dport; - memcpy(&sp.pppol2tp.addr.sin6_addr, &np->daddr, - sizeof(np->daddr)); + memcpy(&sp.pppol2tp.addr.sin6_addr, &tunnel->sock->sk_v6_daddr, + sizeof(tunnel->sock->sk_v6_daddr)); memcpy(uaddr, &sp, len); #endif } else if (tunnel->version == 3) { diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 5d8a3a3cd5a7..ef8a926752a9 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -200,7 +200,7 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, in->ifindex); if (sk) { int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr); + int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr); /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 06df2b9110f5..3dd0e374bc2b 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -370,7 +370,7 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par) */ wildcard = (!(info->flags & XT_SOCKET_NOWILDCARD) && sk->sk_state != TCP_TIME_WAIT && - ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)); + ipv6_addr_any(&sk->sk_v6_rcv_saddr)); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e7b2d4fe2b6a..f6334aa19151 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -426,20 +426,20 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = 0; - addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr; + addr->v6.sin6_addr = sk->sk_v6_rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) { - inet6_sk(sk)->rcv_saddr.s6_addr32[0] = 0; - inet6_sk(sk)->rcv_saddr.s6_addr32[1] = 0; - inet6_sk(sk)->rcv_saddr.s6_addr32[2] = htonl(0x0000ffff); - inet6_sk(sk)->rcv_saddr.s6_addr32[3] = + sk->sk_v6_rcv_saddr.s6_addr32[0] = 0; + sk->sk_v6_rcv_saddr.s6_addr32[1] = 0; + sk->sk_v6_rcv_saddr.s6_addr32[2] = htonl(0x0000ffff); + sk->sk_v6_rcv_saddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { - inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr; + sk->sk_v6_rcv_saddr = addr->v6.sin6_addr; } } @@ -447,12 +447,12 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { if (addr->sa.sa_family == AF_INET && sctp_sk(sk)->v4mapped) { - inet6_sk(sk)->daddr.s6_addr32[0] = 0; - inet6_sk(sk)->daddr.s6_addr32[1] = 0; - inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff); - inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; + sk->sk_v6_daddr.s6_addr32[0] = 0; + sk->sk_v6_daddr.s6_addr32[1] = 0; + sk->sk_v6_daddr.s6_addr32[2] = htonl(0x0000ffff); + sk->sk_v6_daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { - inet6_sk(sk)->daddr = addr->v6.sin6_addr; + sk->sk_v6_daddr = addr->v6.sin6_addr; } } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 9c9caaa5e0d3..0045c7cf1e9e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -294,7 +294,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) case PF_INET6: len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n", proto_name, - &inet6_sk(sk)->rcv_saddr, + &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); break; default: diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 8d8d97dbb389..80554fcf9fcc 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -304,12 +304,11 @@ static void dump_common_audit_data(struct audit_buffer *ab, } case AF_INET6: { struct inet_sock *inet = inet_sk(sk); - struct ipv6_pinfo *inet6 = inet6_sk(sk); - print_ipv6_addr(ab, &inet6->rcv_saddr, + print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr, inet->inet_sport, "laddr", "lport"); - print_ipv6_addr(ab, &inet6->daddr, + print_ipv6_addr(ab, &sk->sk_v6_daddr, inet->inet_dport, "faddr", "fport"); break; -- cgit v1.2.3 From c2bb06db59eaf92eb5ca9c6faed590597c6ceccb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Oct 2013 03:05:48 -0700 Subject: net: fix build errors if ipv6 is disabled CONFIG_IPV6=n is still a valid choice ;) It appears we can remove dead code. Reported-by: Wu Fengguang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_checksum.h | 2 ++ net/ipv4/ping.c | 8 +++++--- net/ipv4/tcp_metrics.c | 4 ++++ net/sunrpc/svcsock.c | 2 ++ security/lsm_audit.c | 2 ++ 5 files changed, 15 insertions(+), 3 deletions(-) (limited to 'security') diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 1944406949ba..9e3c540c1b11 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -66,12 +66,14 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb, } } +#if IS_ENABLED(CONFIG_IPV6) static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); __tcp_v6_send_check(skb, &np->saddr, &sk->sk_v6_daddr); } +#endif int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto); #endif diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index ccefc07beacd..9afbdb19f4a2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -415,10 +415,12 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) (int)sk->sk_bound_dev_if); err = 0; - if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) || - (sk->sk_family == AF_INET6 && - !ipv6_addr_any(&sk->sk_v6_rcv_saddr))) + if (sk->sk_family == AF_INET && isk->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + sk->sk_userlocks |= SOCK_BINDADDR_LOCK; +#endif if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 27535fd5ea10..8fcc2cb9dba4 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -251,10 +251,12 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock addr.addr.a4 = tw->tw_daddr; hash = (__force unsigned int) addr.addr.a4; break; +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: *(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr; hash = ipv6_addr_hash(&tw->tw_v6_daddr); break; +#endif default: return NULL; } @@ -286,10 +288,12 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, addr.addr.a4 = inet_sk(sk)->inet_daddr; hash = (__force unsigned int) addr.addr.a4; break; +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: *(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr; hash = ipv6_addr_hash(&sk->sk_v6_daddr); break; +#endif default: return NULL; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 0045c7cf1e9e..b6e59f0a9475 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -291,12 +291,14 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) &inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); break; +#if IS_ENABLED(CONFIG_IPV6) case PF_INET6: len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n", proto_name, &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); break; +#endif default: len = snprintf(buf, remaining, "*unknown-%d*\n", sk->sk_family); diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 80554fcf9fcc..234bc2ab450c 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -302,6 +302,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, "faddr", "fport"); break; } +#if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct inet_sock *inet = inet_sk(sk); @@ -313,6 +314,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, "faddr", "fport"); break; } +#endif case AF_UNIX: u = unix_sk(sk); if (u->path.dentry) { -- cgit v1.2.3 From 795aa6ef6a1aba99050735eadd0c2341b789b53b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Oct 2013 09:21:55 +0200 Subject: netfilter: pass hook ops to hookfn Pass the hook ops to the hookfn to allow for generic hook functions. This change is required by nf_tables. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 3 +- net/bridge/br_netfilter.c | 22 +++++++++----- net/bridge/netfilter/ebtable_filter.c | 16 ++++++---- net/bridge/netfilter/ebtable_nat.c | 16 ++++++---- net/decnet/netfilter/dn_rtmsg.c | 2 +- net/ipv4/netfilter/arptable_filter.c | 5 +-- net/ipv4/netfilter/ipt_CLUSTERIP.c | 2 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 2 +- net/ipv4/netfilter/iptable_filter.c | 7 +++-- net/ipv4/netfilter/iptable_mangle.c | 10 +++--- net/ipv4/netfilter/iptable_nat.c | 26 ++++++++-------- net/ipv4/netfilter/iptable_raw.c | 6 ++-- net/ipv4/netfilter/iptable_security.c | 7 +++-- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 12 ++++---- net/ipv4/netfilter/nf_defrag_ipv4.c | 6 ++-- net/ipv6/netfilter/ip6t_SYNPROXY.c | 2 +- net/ipv6/netfilter/ip6table_filter.c | 5 +-- net/ipv6/netfilter/ip6table_mangle.c | 10 +++--- net/ipv6/netfilter/ip6table_nat.c | 27 +++++++++-------- net/ipv6/netfilter/ip6table_raw.c | 5 +-- net/ipv6/netfilter/ip6table_security.c | 5 +-- net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 14 +++++---- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 6 ++-- net/netfilter/core.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 42 +++++++++++++------------- security/selinux/hooks.c | 10 +++--- 26 files changed, 148 insertions(+), 122 deletions(-) (limited to 'security') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 61223c52414f..fef7e67f7101 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -42,7 +42,8 @@ int netfilter_init(void); struct sk_buff; -typedef unsigned int nf_hookfn(unsigned int hooknum, +struct nf_hook_ops; +typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index f87736270eaa..878f008afefa 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -619,7 +619,7 @@ bad: /* Replicate the checks that IPv6 does on packet reception and pass the packet * to ip6tables, which doesn't support NAT, so things are fairly simple. */ -static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, +static unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -669,7 +669,8 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ -static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -691,7 +692,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(hook, skb, in, out, okfn); + return br_nf_pre_routing_ipv6(ops, skb, in, out, okfn); } if (!brnf_call_iptables && !br->nf_call_iptables) @@ -727,7 +728,8 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, * took place when the packet entered the bridge), but we * register an IPv4 PRE_ROUTING 'sabotage' hook that will * prevent this from happening. */ -static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -765,7 +767,8 @@ static int br_nf_forward_finish(struct sk_buff *skb) * but we are still able to filter on the 'real' indev/outdev * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ -static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -818,7 +821,8 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, return NF_STOLEN; } -static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -878,7 +882,8 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) #endif /* PF_BRIDGE/POST_ROUTING ********************************************/ -static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, +static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -923,7 +928,8 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ -static unsigned int ip_sabotage_in(unsigned int hook, struct sk_buff *skb, +static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, + struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 94b2b700cff8..bb2da7b706e7 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -60,17 +60,21 @@ static const struct ebt_table frame_filter = }; static unsigned int -ebt_in_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(in)->xt.frame_filter); } static unsigned int -ebt_out_hook(unsigned int hook, struct sk_buff *skb, const struct net_device *in, - const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_filter); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(out)->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 322555acdd40..bd238f1f105b 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -60,17 +60,21 @@ static struct ebt_table frame_nat = }; static unsigned int -ebt_nat_in(unsigned int hook, struct sk_buff *skb, const struct net_device *in - , const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(in)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(in)->xt.frame_nat); } static unsigned int -ebt_nat_out(unsigned int hook, struct sk_buff *skb, const struct net_device *in - , const struct net_device *out, int (*okfn)(struct sk_buff *)) +ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, + const struct net_device *in, const struct net_device *out, + int (*okfn)(struct sk_buff *)) { - return ebt_do_table(hook, skb, in, out, dev_net(out)->xt.frame_nat); + return ebt_do_table(ops->hooknum, skb, in, out, + dev_net(out)->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 2a7efe388344..e83015cecfa7 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -87,7 +87,7 @@ static void dnrmg_send_peer(struct sk_buff *skb) } -static unsigned int dnrmg_hook(unsigned int hook, +static unsigned int dnrmg_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index a865f6f94013..802ddecb30b8 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -27,13 +27,14 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c */ static unsigned int -arptable_filter_hook(unsigned int hook, struct sk_buff *skb, +arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return arpt_do_table(skb, hook, in, out, net->ipv4.arptable_filter); + return arpt_do_table(skb, ops->hooknum, in, out, + net->ipv4.arptable_filter); } static struct nf_hook_ops *arpfilter_ops __read_mostly; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 0b732efd32e2..a2e2b61cd7da 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -483,7 +483,7 @@ static void arp_print(struct arp_payload *payload) #endif static unsigned int -arp_mangle(unsigned int hook, +arp_mangle(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index b6346bf2fde3..01cffeaa0085 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -297,7 +297,7 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv4_synproxy_hook(unsigned int hooknum, +static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 50af5b45c050..e08a74a243a8 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -33,20 +33,21 @@ static const struct xt_table packet_filter = { }; static unsigned int -iptable_filter_hook(unsigned int hook, struct sk_buff *skb, +iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net; - if (hook == NF_INET_LOCAL_OUT && + if (ops->hooknum == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_filter); + return ipt_do_table(skb, ops->hooknum, in, out, + net->ipv4.iptable_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 0d8cd82e0fad..6a5079c34bb3 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -79,19 +79,19 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) /* The work comes in here from netfilter.c. */ static unsigned int -iptable_mangle_hook(unsigned int hook, +iptable_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) + if (ops->hooknum == NF_INET_LOCAL_OUT) return ipt_mangle_out(skb, out); - if (hook == NF_INET_POST_ROUTING) - return ipt_do_table(skb, hook, in, out, + if (ops->hooknum == NF_INET_POST_ROUTING) + return ipt_do_table(skb, ops->hooknum, in, out, dev_net(out)->ipv4.iptable_mangle); /* PREROUTING/INPUT/FORWARD: */ - return ipt_do_table(skb, hook, in, out, + return ipt_do_table(skb, ops->hooknum, in, out, dev_net(in)->ipv4.iptable_mangle); } diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 683bfaffed65..ee2886126e3d 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -61,7 +61,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, } static unsigned int -nf_nat_ipv4_fn(unsigned int hooknum, +nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -71,7 +71,7 @@ nf_nat_ipv4_fn(unsigned int hooknum, enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; /* maniptype == SRC for postrouting. */ - enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); /* We never see fragments: conntrack defrags on pre-routing * and local-out, and nf_nat_out protects post-routing. @@ -108,7 +108,7 @@ nf_nat_ipv4_fn(unsigned int hooknum, case IP_CT_RELATED_REPLY: if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - hooknum)) + ops->hooknum)) return NF_DROP; else return NF_ACCEPT; @@ -121,14 +121,14 @@ nf_nat_ipv4_fn(unsigned int hooknum, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = nf_nat_rule_find(skb, hooknum, in, out, ct); + ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } break; @@ -137,11 +137,11 @@ nf_nat_ipv4_fn(unsigned int hooknum, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } - return nf_nat_packet(ct, ctinfo, hooknum, skb); + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); @@ -149,7 +149,7 @@ oif_changed: } static unsigned int -nf_nat_ipv4_in(unsigned int hooknum, +nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -158,7 +158,7 @@ nf_nat_ipv4_in(unsigned int hooknum, unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; - ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); @@ -167,7 +167,7 @@ nf_nat_ipv4_in(unsigned int hooknum, } static unsigned int -nf_nat_ipv4_out(unsigned int hooknum, +nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -185,7 +185,7 @@ nf_nat_ipv4_out(unsigned int hooknum, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && @@ -207,7 +207,7 @@ nf_nat_ipv4_out(unsigned int hooknum, } static unsigned int -nf_nat_ipv4_local_fn(unsigned int hooknum, +nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -223,7 +223,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv4_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 1f82aea11df6..b2f7e8f98316 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -20,20 +20,20 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -iptable_raw_hook(unsigned int hook, struct sk_buff *skb, +iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net; - if (hook == NF_INET_LOCAL_OUT && + if (ops->hooknum == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_raw); + return ipt_do_table(skb, ops->hooknum, in, out, net->ipv4.iptable_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index f867a8d38bf7..c86647ed2078 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -37,21 +37,22 @@ static const struct xt_table security_table = { }; static unsigned int -iptable_security_hook(unsigned int hook, struct sk_buff *skb, +iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net; - if (hook == NF_INET_LOCAL_OUT && + if (ops->hooknum == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* Somebody is playing with raw sockets. */ return NF_ACCEPT; net = dev_net((in != NULL) ? in : out); - return ipt_do_table(skb, hook, in, out, net->ipv4.iptable_security); + return ipt_do_table(skb, ops->hooknum, in, out, + net->ipv4.iptable_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 86f5b34a4ed1..ecd8bec411c9 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv4_helper(unsigned int hooknum, +static unsigned int ipv4_helper(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -121,7 +121,7 @@ static unsigned int ipv4_helper(unsigned int hooknum, ct, ctinfo); } -static unsigned int ipv4_confirm(unsigned int hooknum, +static unsigned int ipv4_confirm(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -147,16 +147,16 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int ipv4_conntrack_in(unsigned int hooknum, +static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return nf_conntrack_in(dev_net(in), PF_INET, hooknum, skb); + return nf_conntrack_in(dev_net(in), PF_INET, ops->hooknum, skb); } -static unsigned int ipv4_conntrack_local(unsigned int hooknum, +static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -166,7 +166,7 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum, if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - return nf_conntrack_in(dev_net(out), PF_INET, hooknum, skb); + return nf_conntrack_in(dev_net(out), PF_INET, ops->hooknum, skb); } /* Connection tracking may drop packets, but never alters them, so diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 742815518b0f..12e13bd82b5b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -60,7 +60,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, return IP_DEFRAG_CONNTRACK_OUT + zone; } -static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, +static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -83,7 +83,9 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif /* Gather fragments. */ if (ip_is_fragment(ip_hdr(skb))) { - enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); + enum ip_defrag_users user = + nf_ct_defrag_user(ops->hooknum, skb); + if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 2748b042da72..bf9f612c1bc2 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -312,7 +312,7 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv6_synproxy_hook(unsigned int hooknum, +static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 29b44b14c5ea..ca7f6c128086 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -32,13 +32,14 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_filter_hook(unsigned int hook, struct sk_buff *skb, +ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index c705907ae6ab..307bbb782d14 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -76,17 +76,17 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb, +ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - if (hook == NF_INET_LOCAL_OUT) + if (ops->hooknum == NF_INET_LOCAL_OUT) return ip6t_mangle_out(skb, out); - if (hook == NF_INET_POST_ROUTING) - return ip6t_do_table(skb, hook, in, out, + if (ops->hooknum == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, ops->hooknum, in, out, dev_net(out)->ipv6.ip6table_mangle); /* INPUT/FORWARD */ - return ip6t_do_table(skb, hook, in, out, + return ip6t_do_table(skb, ops->hooknum, in, out, dev_net(in)->ipv6.ip6table_mangle); } diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 9b076d2d3a7b..84c7f33d0cf8 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -63,7 +63,7 @@ static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, } static unsigned int -nf_nat_ipv6_fn(unsigned int hooknum, +nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -72,7 +72,7 @@ nf_nat_ipv6_fn(unsigned int hooknum, struct nf_conn *ct; enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); __be16 frag_off; int hdrlen; u8 nexthdr; @@ -111,7 +111,8 @@ nf_nat_ipv6_fn(unsigned int hooknum, if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - hooknum, hdrlen)) + ops->hooknum, + hdrlen)) return NF_DROP; else return NF_ACCEPT; @@ -124,14 +125,14 @@ nf_nat_ipv6_fn(unsigned int hooknum, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = nf_nat_rule_find(skb, hooknum, in, out, ct); + ret = nf_nat_rule_find(skb, ops->hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } break; @@ -140,11 +141,11 @@ nf_nat_ipv6_fn(unsigned int hooknum, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, out)) goto oif_changed; } - return nf_nat_packet(ct, ctinfo, hooknum, skb); + return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); @@ -152,7 +153,7 @@ oif_changed: } static unsigned int -nf_nat_ipv6_in(unsigned int hooknum, +nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -161,7 +162,7 @@ nf_nat_ipv6_in(unsigned int hooknum, unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); @@ -170,7 +171,7 @@ nf_nat_ipv6_in(unsigned int hooknum, } static unsigned int -nf_nat_ipv6_out(unsigned int hooknum, +nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -187,7 +188,7 @@ nf_nat_ipv6_out(unsigned int hooknum, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -209,7 +210,7 @@ nf_nat_ipv6_out(unsigned int hooknum, } static unsigned int -nf_nat_ipv6_local_fn(unsigned int hooknum, +nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -224,7 +225,7 @@ nf_nat_ipv6_local_fn(unsigned int hooknum, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn); + ret = nf_nat_ipv6_fn(ops, skb, in, out, okfn); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 9a626d86720f..5274740acecc 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -19,13 +19,14 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_raw_hook(unsigned int hook, struct sk_buff *skb, +ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index ce88d1d7e525..ab3b0219ecfa 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -36,14 +36,15 @@ static const struct xt_table security_table = { }; static unsigned int -ip6table_security_hook(unsigned int hook, struct sk_buff *skb, +ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { const struct net *net = dev_net((in != NULL) ? in : out); - return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security); + return ip6t_do_table(skb, ops->hooknum, in, out, + net->ipv6.ip6table_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 54b75ead5a69..486545eb42ce 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -95,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_helper(unsigned int hooknum, +static unsigned int ipv6_helper(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -133,7 +133,7 @@ static unsigned int ipv6_helper(unsigned int hooknum, return helper->help(skb, protoff, ct, ctinfo); } -static unsigned int ipv6_confirm(unsigned int hooknum, +static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -219,16 +219,17 @@ static unsigned int __ipv6_conntrack_in(struct net *net, return nf_conntrack_in(net, PF_INET6, hooknum, skb); } -static unsigned int ipv6_conntrack_in(unsigned int hooknum, +static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn); + return __ipv6_conntrack_in(dev_net(in), ops->hooknum, skb, in, out, + okfn); } -static unsigned int ipv6_conntrack_local(unsigned int hooknum, +static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -239,7 +240,8 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn); + return __ipv6_conntrack_in(dev_net(out), ops->hooknum, skb, in, out, + okfn); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index aacd121fe8c5..ec483aa3f60f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -52,7 +52,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, } -static unsigned int ipv6_defrag(unsigned int hooknum, +static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -66,7 +66,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb)); + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; @@ -75,7 +75,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum, if (reasm == skb) return NF_ACCEPT; - nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in, + nf_ct_frag6_output(ops->hooknum, reasm, (struct net_device *)in, (struct net_device *)out, okfn); return NF_STOLEN; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 593b16ea45e0..1fbab0cdd302 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -146,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head, /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn); + verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 74fd00c27210..34fda62f40f6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1239,11 +1239,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb, +ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_out(hooknum, skb, AF_INET); + return ip_vs_out(ops->hooknum, skb, AF_INET); } /* @@ -1251,11 +1251,11 @@ ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb, +ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_out(hooknum, skb, AF_INET); + return ip_vs_out(ops->hooknum, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 @@ -1266,11 +1266,11 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_out(hooknum, skb, AF_INET6); + return ip_vs_out(ops->hooknum, skb, AF_INET6); } /* @@ -1278,11 +1278,11 @@ ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_out(hooknum, skb, AF_INET6); + return ip_vs_out(ops->hooknum, skb, AF_INET6); } #endif @@ -1733,12 +1733,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb, +ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_in(hooknum, skb, AF_INET); + return ip_vs_in(ops->hooknum, skb, AF_INET); } /* @@ -1746,11 +1746,11 @@ ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, +ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_in(hooknum, skb, AF_INET); + return ip_vs_in(ops->hooknum, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 @@ -1760,7 +1760,7 @@ ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb, * Copy info from first fragment, to the rest of them. */ static unsigned int -ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_preroute_frag6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) @@ -1792,12 +1792,12 @@ ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb, * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_in(hooknum, skb, AF_INET6); + return ip_vs_in(ops->hooknum, skb, AF_INET6); } /* @@ -1805,11 +1805,11 @@ ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { - return ip_vs_in(hooknum, skb, AF_INET6); + return ip_vs_in(ops->hooknum, skb, AF_INET6); } #endif @@ -1825,7 +1825,7 @@ ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb, * and send them to ip_vs_in_icmp. */ static unsigned int -ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, +ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { @@ -1842,12 +1842,12 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp(skb, &r, hooknum); + return ip_vs_in_icmp(skb, &r, ops->hooknum); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int -ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, +ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, int (*okfn)(struct sk_buff *)) { @@ -1866,7 +1866,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr); + return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr); } #endif diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 568c7699abf1..3f224d7795f5 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4668,7 +4668,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, int ifindex, return NF_ACCEPT; } -static unsigned int selinux_ipv4_forward(unsigned int hooknum, +static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -4678,7 +4678,7 @@ static unsigned int selinux_ipv4_forward(unsigned int hooknum, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_forward(unsigned int hooknum, +static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -4710,7 +4710,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_output(unsigned int hooknum, +static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -4837,7 +4837,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, return NF_ACCEPT; } -static unsigned int selinux_ipv4_postroute(unsigned int hooknum, +static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -4847,7 +4847,7 @@ static unsigned int selinux_ipv4_postroute(unsigned int hooknum, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_postroute(unsigned int hooknum, +static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct net_device *in, const struct net_device *out, -- cgit v1.2.3 From 5cb3e91ebd0405519795f243adbfc4ed2a6fe53f Mon Sep 17 00:00:00 2001 From: John Johansen Date: Mon, 14 Oct 2013 11:44:34 -0700 Subject: apparmor: fix memleak of the profile hash BugLink: http://bugs.launchpad.net/bugs/1235523 This fixes the following kmemleak trace: unreferenced object 0xffff8801e8c35680 (size 32): comm "apparmor_parser", pid 691, jiffies 4294895667 (age 13230.876s) hex dump (first 32 bytes): e0 d3 4e b5 ac 6d f4 ed 3f cb ee 48 1c fd 40 cf ..N..m..?..H..@. 5b cc e9 93 00 00 00 00 00 00 00 00 00 00 00 00 [............... backtrace: [] kmemleak_alloc+0x4e/0xb0 [] __kmalloc+0x103/0x290 [] aa_calc_profile_hash+0x6c/0x150 [] aa_unpack+0x39d/0xd50 [] aa_replace_profiles+0x3d/0xd80 [] profile_replace+0x37/0x50 [] vfs_write+0xbd/0x1e0 [] SyS_write+0x4c/0xa0 [] system_call_fastpath+0x1a/0x1f [] 0xffffffffffffffff Signed-off-by: John Johansen Signed-off-by: James Morris --- security/apparmor/policy.c | 1 + 1 file changed, 1 insertion(+) (limited to 'security') diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 345bec07a27d..705c2879d3a9 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -610,6 +610,7 @@ void aa_free_profile(struct aa_profile *profile) aa_put_dfa(profile->policy.dfa); aa_put_replacedby(profile->replacedby); + kzfree(profile->hash); kzfree(profile); } -- cgit v1.2.3 From ed2c7da3a40c58410508fe24e12d03e508d7ec01 Mon Sep 17 00:00:00 2001 From: John Johansen Date: Mon, 14 Oct 2013 11:46:27 -0700 Subject: apparmor: fix bad lock balance when introspecting policy BugLink: http://bugs.launchpad.net/bugs/1235977 The profile introspection seq file has a locking bug when policy is viewed from a virtual root (task in a policy namespace), introspection from the real root is not affected. The test for root while (parent) { is correct for the real root, but incorrect for tasks in a policy namespace. This allows the task to walk backup the policy tree past its virtual root causing it to be unlocked before the virtual root should be in the p_stop fn. This results in the following lockdep back trace: [ 78.479744] [ BUG: bad unlock balance detected! ] [ 78.479792] 3.11.0-11-generic #17 Not tainted [ 78.479838] ------------------------------------- [ 78.479885] grep/2223 is trying to release lock (&ns->lock) at: [ 78.479952] [] mutex_unlock+0xe/0x10 [ 78.480002] but there are no more locks to release! [ 78.480037] [ 78.480037] other info that might help us debug this: [ 78.480037] 1 lock held by grep/2223: [ 78.480037] #0: (&p->lock){+.+.+.}, at: [] seq_read+0x3d/0x3d0 [ 78.480037] [ 78.480037] stack backtrace: [ 78.480037] CPU: 0 PID: 2223 Comm: grep Not tainted 3.11.0-11-generic #17 [ 78.480037] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 78.480037] ffffffff817bf3be ffff880007763d60 ffffffff817b97ef ffff8800189d2190 [ 78.480037] ffff880007763d88 ffffffff810e1c6e ffff88001f044730 ffff8800189d2190 [ 78.480037] ffffffff817bf3be ffff880007763e00 ffffffff810e5bd6 0000000724fe56b7 [ 78.480037] Call Trace: [ 78.480037] [] ? mutex_unlock+0xe/0x10 [ 78.480037] [] dump_stack+0x54/0x74 [ 78.480037] [] print_unlock_imbalance_bug+0xee/0x100 [ 78.480037] [] ? mutex_unlock+0xe/0x10 [ 78.480037] [] lock_release_non_nested+0x226/0x300 [ 78.480037] [] ? __mutex_unlock_slowpath+0xce/0x180 [ 78.480037] [] ? mutex_unlock+0xe/0x10 [ 78.480037] [] lock_release+0xac/0x310 [ 78.480037] [] __mutex_unlock_slowpath+0x83/0x180 [ 78.480037] [] mutex_unlock+0xe/0x10 [ 78.480037] [] p_stop+0x51/0x90 [ 78.480037] [] seq_read+0x288/0x3d0 [ 78.480037] [] vfs_read+0x9e/0x170 [ 78.480037] [] SyS_read+0x4c/0xa0 [ 78.480037] [] system_call_fastpath+0x1a/0x1f Signed-off-by: John Johansen Signed-off-by: James Morris --- security/apparmor/apparmorfs.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'security') diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 95c2b2689a03..7db9954f1af2 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -580,15 +580,13 @@ static struct aa_namespace *__next_namespace(struct aa_namespace *root, /* check if the next ns is a sibling, parent, gp, .. */ parent = ns->parent; - while (parent) { + while (ns != root) { mutex_unlock(&ns->lock); next = list_entry_next(ns, base.list); if (!list_entry_is_head(next, &parent->sub_ns, base.list)) { mutex_lock(&next->lock); return next; } - if (parent == root) - return NULL; ns = parent; parent = parent->parent; } -- cgit v1.2.3 From 73ba353471e0b692f398f3d63018b7f46ccf1d3e Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Wed, 23 Oct 2013 01:34:00 +0200 Subject: device_cgroup: remove can_attach It is really only wanting to duplicate a check which is already done by the cgroup subsystem. With this patch, user jdoe still cannot move pid 1 into a devices cgroup he owns, but now he can move his own other tasks into devices cgroups. Signed-off-by: Serge Hallyn Signed-off-by: Tejun Heo Cc: Aristeu Rozanski --- security/device_cgroup.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'security') diff --git a/security/device_cgroup.c b/security/device_cgroup.c index c123628d3f84..7c2a0a71049e 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -63,16 +63,6 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) struct cgroup_subsys devices_subsys; -static int devcgroup_can_attach(struct cgroup_subsys_state *new_css, - struct cgroup_taskset *set) -{ - struct task_struct *task = cgroup_taskset_first(set); - - if (current != task && !capable(CAP_SYS_ADMIN)) - return -EPERM; - return 0; -} - /* * called under devcgroup_mutex */ @@ -697,7 +687,6 @@ static struct cftype dev_cgroup_files[] = { struct cgroup_subsys devices_subsys = { .name = "devices", - .can_attach = devcgroup_can_attach, .css_alloc = devcgroup_css_alloc, .css_free = devcgroup_css_free, .css_online = devcgroup_online, -- cgit v1.2.3 From b805b198dc74b73aabb6969a3db734c71c05c88c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 24 May 2013 12:09:50 -0400 Subject: selinux: apply selinux checks on new audit message types We use the read check to get the feature set (like AUDIT_GET) and the write check to set the features (like AUDIT_SET). Signed-off-by: Eric Paris Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- security/selinux/nlmsgtab.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'security') diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 855e464e92ef..332ac8a80cf5 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -116,6 +116,8 @@ static struct nlmsg_perm nlmsg_audit_perms[] = { AUDIT_MAKE_EQUIV, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_TTY_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ }, { AUDIT_TTY_SET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT }, + { AUDIT_GET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_READ }, + { AUDIT_SET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, }; -- cgit v1.2.3 From a20b62bdf7a1ed1a334eff3c4cafa97f5826006b Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 1 Oct 2013 21:14:54 -0400 Subject: audit: suppress stock memalloc failure warnings since already managed Supress the stock memory allocation failure warnings for audit buffers since audit alreay takes care of memory allocation failure warnings, including rate-limiting, in audit_log_start(). Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- security/lsm_audit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'security') diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 8d8d97dbb389..b0f249d1a1ef 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -396,7 +396,8 @@ void common_lsm_audit(struct common_audit_data *a, if (a == NULL) return; /* we use GFP_ATOMIC so we won't sleep */ - ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_AVC); + ab = audit_log_start(current->audit_context, GFP_ATOMIC | __GFP_NOWARN, + AUDIT_AVC); if (ab == NULL) return; -- cgit v1.2.3 From fbf8c53f1a2ac7610ed124043600dc074992e71b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 6 Nov 2013 14:01:51 +0000 Subject: KEYS: Fix UID check in keyctl_get_persistent() If the UID is specified by userspace when calling the KEYCTL_GET_PERSISTENT function and the process does not have the CAP_SETUID capability, then the function will return -EPERM if the current process's uid, suid, euid and fsuid all match the requested UID. This is incorrect. Fix it such that when a non-privileged caller requests a persistent keyring by a specific UID they can only request their own (ie. the specified UID matches either then process's UID or the process's EUID). This can be tested by logging in as the user and doing: keyctl get_persistent @p keyctl get_persistent @p `id -u` keyctl get_persistent @p 0 The first two should successfully print the same key ID. The third should do the same if called by UID 0 or indicate Operation Not Permitted otherwise. Signed-off-by: David Howells Acked-by: Stephen Gallagher --- security/keys/persistent.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'security') diff --git a/security/keys/persistent.c b/security/keys/persistent.c index 82f4957a7acf..0ad3ee283781 100644 --- a/security/keys/persistent.c +++ b/security/keys/persistent.c @@ -144,10 +144,8 @@ long keyctl_get_persistent(uid_t _uid, key_serial_t destid) /* You can only see your own persistent cache if you're not * sufficiently privileged. */ - if (uid_eq(uid, current_uid()) && - uid_eq(uid, current_suid()) && - uid_eq(uid, current_euid()) && - uid_eq(uid, current_fsuid()) && + if (!uid_eq(uid, current_uid()) && + !uid_eq(uid, current_euid()) && !ns_capable(ns, CAP_SETUID)) return -EPERM; } -- cgit v1.2.3 From 97826c821ec6724fc359d9b7840dc10af914c641 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 13 Nov 2013 16:51:06 +0000 Subject: KEYS: Fix error handling in big_key instantiation In the big_key_instantiate() function we return 0 if kernel_write() returns us an error rather than returning an error. This can potentially lead to dentry_open() giving a BUG when called from big_key_read() with an unset tmpfile path. ------------[ cut here ]------------ kernel BUG at fs/open.c:798! ... RIP: 0010:[] dentry_open+0xd1/0xe0 ... Call Trace: [] big_key_read+0x55/0x100 [] keyctl_read_key+0xb4/0xe0 [] SyS_keyctl+0xf8/0x1d0 [] system_call_fastpath+0x16/0x1b Signed-off-by: David Howells Reviewed-by: Stephen Gallagher --- security/keys/big_key.c | 1 + 1 file changed, 1 insertion(+) (limited to 'security') diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 2cf5e62d67af..7f44c3207a9b 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -78,6 +78,7 @@ int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep) written = kernel_write(file, prep->data, prep->datalen, 0); if (written != datalen) { + ret = written; if (written >= 0) ret = -ENOMEM; goto err_fput; -- cgit v1.2.3 From 62fe318256befbd1b4a6765e71d9c997f768fe79 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 14 Nov 2013 13:02:31 +0000 Subject: KEYS: Fix keyring content gc scanner Key pointers stored in the keyring are marked in bit 1 to indicate if they point to a keyring. We need to strip off this bit before using the pointer when iterating over the keyring for the purpose of looking for links to garbage collect. This means that expirable keyrings aren't correctly expiring because the checker is seeing their key pointer with 2 added to it. Since the fix for this involves knowing about the internals of the keyring, key_gc_keyring() is moved to keyring.c and merged into keyring_gc(). This can be tested by: echo 2 >/proc/sys/kernel/keys/gc_delay keyctl timeout `keyctl add keyring qwerty "" @s` 2 cat /proc/keys sleep 5; cat /proc/keys which should see a keyring called "qwerty" appear in the session keyring and then disappear after it expires, and: echo 2 >/proc/sys/kernel/keys/gc_delay a=`keyctl get_persistent @s` b=`keyctl add keyring 0 "" $a` keyctl add user a a $b keyctl timeout $b 2 cat /proc/keys sleep 5; cat /proc/keys which should see a keyring called "0" with a key called "a" in it appear in the user's persistent keyring (which will be attached to the session keyring) and then both the "0" keyring and the "a" key should disappear when the "0" keyring expires. Signed-off-by: David Howells Acked-by: Simo Sorce --- security/keys/gc.c | 42 +----------------------------------------- security/keys/keyring.c | 45 +++++++++++++++++++++++++++++++++++---------- 2 files changed, 36 insertions(+), 51 deletions(-) (limited to 'security') diff --git a/security/keys/gc.c b/security/keys/gc.c index cce621c33dce..d3222b6d7d59 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -130,46 +130,6 @@ void key_gc_keytype(struct key_type *ktype) kleave(""); } -static int key_gc_keyring_func(const void *object, void *iterator_data) -{ - const struct key *key = object; - time_t *limit = iterator_data; - return key_is_dead(key, *limit); -} - -/* - * Garbage collect pointers from a keyring. - * - * Not called with any locks held. The keyring's key struct will not be - * deallocated under us as only our caller may deallocate it. - */ -static void key_gc_keyring(struct key *keyring, time_t limit) -{ - int result; - - kenter("%x{%s}", keyring->serial, keyring->description ?: ""); - - if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED))) - goto dont_gc; - - /* scan the keyring looking for dead keys */ - rcu_read_lock(); - result = assoc_array_iterate(&keyring->keys, - key_gc_keyring_func, &limit); - rcu_read_unlock(); - if (result == true) - goto do_gc; - -dont_gc: - kleave(" [no gc]"); - return; - -do_gc: - keyring_gc(keyring, limit); - kleave(" [gc]"); -} - /* * Garbage collect a list of unreferenced, detached keys */ @@ -388,7 +348,7 @@ found_unreferenced_key: */ found_keyring: spin_unlock(&key_serial_lock); - key_gc_keyring(key, limit); + keyring_gc(key, limit); goto maybe_resched; /* We found a dead key that is still referenced. Reset its type and diff --git a/security/keys/keyring.c b/security/keys/keyring.c index d80311e571c3..69f0cb7bab7e 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -1304,7 +1304,7 @@ static void keyring_revoke(struct key *keyring) } } -static bool gc_iterator(void *object, void *iterator_data) +static bool keyring_gc_select_iterator(void *object, void *iterator_data) { struct key *key = keyring_ptr_to_key(object); time_t *limit = iterator_data; @@ -1315,22 +1315,47 @@ static bool gc_iterator(void *object, void *iterator_data) return true; } +static int keyring_gc_check_iterator(const void *object, void *iterator_data) +{ + const struct key *key = keyring_ptr_to_key(object); + time_t *limit = iterator_data; + + key_check(key); + return key_is_dead(key, *limit); +} + /* - * Collect garbage from the contents of a keyring, replacing the old list with - * a new one with the pointers all shuffled down. + * Garbage collect pointers from a keyring. * - * Dead keys are classed as oned that are flagged as being dead or are revoked, - * expired or negative keys that were revoked or expired before the specified - * limit. + * Not called with any locks held. The keyring's key struct will not be + * deallocated under us as only our caller may deallocate it. */ void keyring_gc(struct key *keyring, time_t limit) { - kenter("{%x,%s}", key_serial(keyring), keyring->description); + int result; + + kenter("%x{%s}", keyring->serial, keyring->description ?: ""); + if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED))) + goto dont_gc; + + /* scan the keyring looking for dead keys */ + rcu_read_lock(); + result = assoc_array_iterate(&keyring->keys, + keyring_gc_check_iterator, &limit); + rcu_read_unlock(); + if (result == true) + goto do_gc; + +dont_gc: + kleave(" [no gc]"); + return; + +do_gc: down_write(&keyring->sem); assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops, - gc_iterator, &limit); + keyring_gc_select_iterator, &limit); up_write(&keyring->sem); - - kleave(""); + kleave(" [gc]"); } -- cgit v1.2.3 From 34ef7bd3823bf4401bf8f1f855e1bc77b82b1a43 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 23 Nov 2013 16:36:35 -0800 Subject: Revert "ima: define '_ima' as a builtin 'trusted' keyring" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 217091dd7a7a1bdac027ddb7c5a25f6ac0b8e241, which caused the following build error: security/integrity/digsig.c:70:5: error: redefinition of ‘integrity_init_keyring’ security/integrity/integrity.h:149:12: note: previous definition of ‘integrity_init_keyring’ w security/integrity/integrity.h:149:12: warning: ‘integrity_init_keyring’ defined but not used reported by Krzysztof Kolasa. Mimi says: "I made the classic mistake of requesting this patch to be upstreamed at the last second, rather than waiting until the next open window. At this point, the best course would probably be to revert the two commits and fix them for the next open window" Reported-by: Krzysztof Kolasa Acked-by: Mimi Zohar Signed-off-by: Linus Torvalds --- security/integrity/digsig.c | 30 +----------------------------- security/integrity/ima/Kconfig | 8 -------- security/integrity/ima/ima_appraise.c | 11 ----------- security/integrity/integrity.h | 7 ------- 4 files changed, 1 insertion(+), 55 deletions(-) (limited to 'security') diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 77ca965ab684..b4af4ebc5be2 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -13,9 +13,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include #include -#include #include #include @@ -23,19 +21,11 @@ static struct key *keyring[INTEGRITY_KEYRING_MAX]; -#ifdef CONFIG_IMA_TRUSTED_KEYRING -static const char *keyring_name[INTEGRITY_KEYRING_MAX] = { - ".evm", - ".module", - ".ima", -}; -#else static const char *keyring_name[INTEGRITY_KEYRING_MAX] = { "_evm", "_module", "_ima", }; -#endif int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, const char *digest, int digestlen) @@ -45,7 +35,7 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, if (!keyring[id]) { keyring[id] = - request_key(&key_type_keyring, keyring_name[id], NULL); + request_key(&key_type_keyring, keyring_name[id], NULL); if (IS_ERR(keyring[id])) { int err = PTR_ERR(keyring[id]); pr_err("no %s keyring: %d\n", keyring_name[id], err); @@ -66,21 +56,3 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, return -EOPNOTSUPP; } - -int integrity_init_keyring(const unsigned int id) -{ - const struct cred *cred = current_cred(); - const struct user_struct *user = cred->user; - - keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), - KGIDT_INIT(0), cred, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA, user->uid_keyring); - if (!IS_ERR(keyring[id])) - set_bit(KEY_FLAG_TRUSTED_ONLY, &keyring[id]->flags); - else - pr_info("Can't allocate %s keyring (%ld)\n", - keyring_name[id], PTR_ERR(keyring[id])); - return 0; -} diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index dad8d4ca2437..81a27971d884 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -123,11 +123,3 @@ config IMA_APPRAISE For more information on integrity appraisal refer to: If unsure, say N. - -config IMA_TRUSTED_KEYRING - bool "Require all keys on the _ima keyring be signed" - depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING - default y - help - This option requires that all keys added to the _ima - keyring be signed by a key on the system trusted keyring. diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 46353ee517f6..734e9468aca0 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -381,14 +381,3 @@ int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name) } return result; } - -#ifdef CONFIG_IMA_TRUSTED_KEYRING -static int __init init_ima_keyring(void) -{ - int ret; - - ret = integrity_init_keyring(INTEGRITY_KEYRING_IMA); - return 0; -} -late_initcall(init_ima_keyring); -#endif diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index b9e7c133734a..2fb5e53e927f 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -137,19 +137,12 @@ static inline int integrity_digsig_verify(const unsigned int id, #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS int asymmetric_verify(struct key *keyring, const char *sig, int siglen, const char *data, int datalen); - -int integrity_init_keyring(const unsigned int id); #else static inline int asymmetric_verify(struct key *keyring, const char *sig, int siglen, const char *data, int datalen) { return -EOPNOTSUPP; } - -static int integrity_init_keyring(const unsigned int id) -{ - return 0; -} #endif #ifdef CONFIG_INTEGRITY_AUDIT -- cgit v1.2.3 From b6f8f16f41d92861621b043389ef49de1c52d613 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 8 Nov 2013 19:21:39 +0100 Subject: ima: do not include field length in template digest calc for ima template To maintain compatibility with userspace tools, the field length must not be included in the template digest calculation for the 'ima' template. Fixes commit: a71dc65 ima: switch to new template management mechanism Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- security/integrity/ima/ima.h | 3 ++- security/integrity/ima/ima_api.c | 1 + security/integrity/ima/ima_crypto.c | 17 ++++++++++++----- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'security') diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index bf03c6a16cc8..a21cf706d213 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -97,7 +97,8 @@ int ima_add_template_entry(struct ima_template_entry *entry, int violation, const char *op, struct inode *inode, const unsigned char *filename); int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash); -int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields, +int ima_calc_field_array_hash(struct ima_field_data *field_data, + struct ima_template_desc *desc, int num_fields, struct ima_digest_data *hash); int __init ima_calc_boot_aggregate(struct ima_digest_data *hash); void ima_add_violation(struct file *file, const unsigned char *filename, diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 0e7540863fc2..80374842fe0b 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -94,6 +94,7 @@ int ima_store_template(struct ima_template_entry *entry, /* this function uses default algo */ hash.hdr.algo = HASH_ALGO_SHA1; result = ima_calc_field_array_hash(&entry->template_data[0], + entry->template_desc, num_fields, &hash.hdr); if (result < 0) { integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 676e0292dfec..fdf60def52e9 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -140,6 +140,7 @@ int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash) * Calculate the hash of template data */ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data, + struct ima_template_desc *td, int num_fields, struct ima_digest_data *hash, struct crypto_shash *tfm) @@ -160,9 +161,13 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data, return rc; for (i = 0; i < num_fields; i++) { - rc = crypto_shash_update(&desc.shash, - (const u8 *) &field_data[i].len, - sizeof(field_data[i].len)); + if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) { + rc = crypto_shash_update(&desc.shash, + (const u8 *) &field_data[i].len, + sizeof(field_data[i].len)); + if (rc) + break; + } rc = crypto_shash_update(&desc.shash, field_data[i].data, field_data[i].len); if (rc) @@ -175,7 +180,8 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data, return rc; } -int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields, +int ima_calc_field_array_hash(struct ima_field_data *field_data, + struct ima_template_desc *desc, int num_fields, struct ima_digest_data *hash) { struct crypto_shash *tfm; @@ -185,7 +191,8 @@ int ima_calc_field_array_hash(struct ima_field_data *field_data, int num_fields, if (IS_ERR(tfm)) return PTR_ERR(tfm); - rc = ima_calc_field_array_hash_tfm(field_data, num_fields, hash, tfm); + rc = ima_calc_field_array_hash_tfm(field_data, desc, num_fields, + hash, tfm); ima_free_tfm(tfm); -- cgit v1.2.3 From 3e8e5503a33577d89bdb7469b851b11f507bbed6 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Fri, 8 Nov 2013 19:21:40 +0100 Subject: ima: do not send field length to userspace for digest of ima template This patch defines a new value for the 'ima_show_type' enumerator (IMA_SHOW_BINARY_NO_FIELD_LEN) to prevent that the field length is transmitted through the 'binary_runtime_measurements' interface for the digest field of the 'ima' template. Fixes commit: 3ce1217 ima: define template fields library and new helpers Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- security/integrity/ima/ima.h | 3 ++- security/integrity/ima/ima_fs.c | 14 +++++++++++--- security/integrity/ima/ima_template_lib.c | 6 +++++- 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'security') diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index a21cf706d213..9636e17c9f5d 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -26,7 +26,8 @@ #include "../integrity.h" -enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_ASCII }; +enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN, + IMA_SHOW_ASCII }; enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 }; /* digest size for IMA, fits SHA1 or MD5 */ diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index d47a7c86a21d..db01125926bd 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -120,6 +120,7 @@ static int ima_measurements_show(struct seq_file *m, void *v) struct ima_template_entry *e; int namelen; u32 pcr = CONFIG_IMA_MEASURE_PCR_IDX; + bool is_ima_template = false; int i; /* get entry */ @@ -145,14 +146,21 @@ static int ima_measurements_show(struct seq_file *m, void *v) ima_putc(m, e->template_desc->name, namelen); /* 5th: template length (except for 'ima' template) */ - if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) + if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) + is_ima_template = true; + + if (!is_ima_template) ima_putc(m, &e->template_data_len, sizeof(e->template_data_len)); /* 6th: template specific data */ for (i = 0; i < e->template_desc->num_fields; i++) { - e->template_desc->fields[i]->field_show(m, IMA_SHOW_BINARY, - &e->template_data[i]); + enum ima_show_type show = IMA_SHOW_BINARY; + struct ima_template_field *field = e->template_desc->fields[i]; + + if (is_ima_template && strcmp(field->field_id, "d") == 0) + show = IMA_SHOW_BINARY_NO_FIELD_LEN; + field->field_show(m, show, &e->template_data[i]); } return 0; } diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c index 6d66ad6ed265..c38adcc910fb 100644 --- a/security/integrity/ima/ima_template_lib.c +++ b/security/integrity/ima/ima_template_lib.c @@ -109,9 +109,12 @@ static void ima_show_template_data_binary(struct seq_file *m, enum data_formats datafmt, struct ima_field_data *field_data) { - ima_putc(m, &field_data->len, sizeof(u32)); + if (show != IMA_SHOW_BINARY_NO_FIELD_LEN) + ima_putc(m, &field_data->len, sizeof(u32)); + if (!field_data->len) return; + ima_putc(m, field_data->data, field_data->len); } @@ -125,6 +128,7 @@ static void ima_show_template_field_data(struct seq_file *m, ima_show_template_data_ascii(m, show, datafmt, field_data); break; case IMA_SHOW_BINARY: + case IMA_SHOW_BINARY_NO_FIELD_LEN: ima_show_template_data_binary(m, show, datafmt, field_data); break; default: -- cgit v1.2.3 From dbc335d2dc3c437649eb6b39f4e9aee2a13eb0af Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 25 Nov 2013 20:18:52 +0100 Subject: ima: make a copy of template_fmt in template_desc_init_fields() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch makes a copy of the 'template_fmt' function argument so that the latter will not be modified by strsep(), which does the splitting by replacing the given separator with '\0'.  IMA: No TPM chip found, activating TPM-bypass!  Unable to handle kernel pointer dereference at virtual kernel address 0000000000842000  Oops: 0004 [#1] SMP  Modules linked in:  CPU: 3 PID: 1 Comm: swapper/0 Not tainted 3.12.0-rc2-00098-g3ce1217d6cd5 #17  task: 000000003ffa0000 ti: 000000003ff84000 task.ti: 000000003ff84000  Krnl PSW : 0704e00180000000 000000000044bf88 (strsep+0x7c/0xa0)             R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 EA:3  Krnl GPRS: 000000000000007c 000000000000007c 000000003ff87d90 0000000000821fd8             0000000000000000 000000000000007c 0000000000aa37e0 0000000000aa9008             0000000000000051 0000000000a114d8 0000000100000002 0000000000842bde             0000000000842bdf 00000000006f97f0 000000000040062c 000000003ff87cf0  Krnl Code: 000000000044bf7c: a7f4000a           brc     15,44bf90             000000000044bf80: b90200cc           ltgr    %r12,%r12            #000000000044bf84: a7840006           brc     8,44bf90            >000000000044bf88: 9200c000           mvi     0(%r12),0             000000000044bf8c: 41c0c001           la      %r12,1(%r12)             000000000044bf90: e3c020000024       stg     %r12,0(%r2)             000000000044bf96: b904002b           lgr     %r2,%r11             000000000044bf9a: ebbcf0700004       lmg     %r11,%r12,112(%r15)  Call Trace:  ([<00000000004005fe>] ima_init_template+0xa2/0x1bc)   [<0000000000a7c896>] ima_init+0x7a/0xa8   [<0000000000a7c938>] init_ima+0x24/0x40   [<00000000001000e8>] do_one_initcall+0x68/0x128   [<0000000000a4eb56>] kernel_init_freeable+0x20a/0x2b4   [<00000000006a1ff4>] kernel_init+0x30/0x178   [<00000000006b69fe>] kernel_thread_starter+0x6/0xc   [<00000000006b69f8>] kernel_thread_starter+0x0/0xc  Last Breaking-Event-Address:   [<000000000044bf42>] strsep+0x36/0xa0 Fixes commit: adf53a7 ima: new templates management mechanism Changelog v1: - make template_fmt 'const char *' (reported-by James Morris) - fix kstrdup memory leak (reported-by James Morris) Reported-by: Heiko Carstens Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar Tested-by: Heiko Carstens --- security/integrity/ima/ima_template.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'security') diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index 4e5da990630b..913e1927f916 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -90,7 +90,7 @@ static struct ima_template_field *lookup_template_field(const char *field_id) return NULL; } -static int template_fmt_size(char *template_fmt) +static int template_fmt_size(const char *template_fmt) { char c; int template_fmt_len = strlen(template_fmt); @@ -106,23 +106,28 @@ static int template_fmt_size(char *template_fmt) return j + 1; } -static int template_desc_init_fields(char *template_fmt, +static int template_desc_init_fields(const char *template_fmt, struct ima_template_field ***fields, int *num_fields) { - char *c, *template_fmt_ptr = template_fmt; + char *c, *template_fmt_copy; int template_num_fields = template_fmt_size(template_fmt); int i, result = 0; if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX) return -EINVAL; + /* copying is needed as strsep() modifies the original buffer */ + template_fmt_copy = kstrdup(template_fmt, GFP_KERNEL); + if (template_fmt_copy == NULL) + return -ENOMEM; + *fields = kzalloc(template_num_fields * sizeof(*fields), GFP_KERNEL); if (*fields == NULL) { result = -ENOMEM; goto out; } - for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL && + for (i = 0; (c = strsep(&template_fmt_copy, "|")) != NULL && i < template_num_fields; i++) { struct ima_template_field *f = lookup_template_field(c); @@ -133,10 +138,12 @@ static int template_desc_init_fields(char *template_fmt, (*fields)[i] = f; } *num_fields = i; - return 0; out: - kfree(*fields); - *fields = NULL; + if (result < 0) { + kfree(*fields); + *fields = NULL; + } + kfree(template_fmt_copy); return result; } -- cgit v1.2.3 From af91706d5ddecb4a9858cca9e90d463037cfd498 Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 27 Nov 2013 14:40:41 +0100 Subject: ima: store address of template_fmt_copy in a pointer before calling strsep This patch stores the address of the 'template_fmt_copy' variable in a new variable, called 'template_fmt_ptr', so that the latter is passed as an argument of strsep() instead of the former. This modification is needed in order to correctly free the memory area referenced by 'template_fmt_copy' (strsep() modifies the pointer of the passed string). Signed-off-by: Roberto Sassu Reported-by: Sebastian Ott Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- security/integrity/ima/ima_template.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'security') diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index 913e1927f916..635695f6a185 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -110,7 +110,7 @@ static int template_desc_init_fields(const char *template_fmt, struct ima_template_field ***fields, int *num_fields) { - char *c, *template_fmt_copy; + char *c, *template_fmt_copy, *template_fmt_ptr; int template_num_fields = template_fmt_size(template_fmt); int i, result = 0; @@ -127,7 +127,9 @@ static int template_desc_init_fields(const char *template_fmt, result = -ENOMEM; goto out; } - for (i = 0; (c = strsep(&template_fmt_copy, "|")) != NULL && + + template_fmt_ptr = template_fmt_copy; + for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL && i < template_num_fields; i++) { struct ima_template_field *f = lookup_template_field(c); -- cgit v1.2.3 From 2480f57fb3023eb047c5f2d6dfefef41ab9b893c Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:18 +0000 Subject: KEYS: Pre-clear struct key on allocation The second word of key->payload does not get initialised in key_alloc(), but the big_key type is relying on it having been cleared. The problem comes when big_key fails to instantiate a large key and doesn't then set the payload. The big_key_destroy() op is called from the garbage collector and this assumes that the dentry pointer stored in the second word will be NULL if instantiation did not complete. Therefore just pre-clear the entire struct key on allocation rather than trying to be clever and only initialising to 0 only those bits that aren't otherwise initialised. The lack of initialisation can lead to a bug report like the following if big_key failed to initialise its file: general protection fault: 0000 [#1] SMP Modules linked in: ... CPU: 0 PID: 51 Comm: kworker/0:1 Not tainted 3.10.0-53.el7.x86_64 #1 Hardware name: Dell Inc. PowerEdge 1955/0HC513, BIOS 1.4.4 12/09/2008 Workqueue: events key_garbage_collector task: ffff8801294f5680 ti: ffff8801296e2000 task.ti: ffff8801296e2000 RIP: 0010:[] dput+0x21/0x2d0 ... Call Trace: [] path_put+0x16/0x30 [] big_key_destroy+0x44/0x60 [] key_gc_unused_keys.constprop.2+0x5b/0xe0 [] key_garbage_collector+0x1df/0x3c0 [] process_one_work+0x17b/0x460 [] worker_thread+0x11b/0x400 [] ? rescuer_thread+0x3e0/0x3e0 [] kthread+0xc0/0xd0 [] ? kthread_create_on_node+0x110/0x110 [] ret_from_fork+0x7c/0xb0 [] ? kthread_create_on_node+0x110/0x110 Reported-by: Patrik Kis Signed-off-by: David Howells Reviewed-by: Stephen Gallagher --- security/keys/key.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'security') diff --git a/security/keys/key.c b/security/keys/key.c index 55d110f0aced..6e21c11e48bc 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -272,7 +272,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, } /* allocate and initialise the key and its description */ - key = kmem_cache_alloc(key_jar, GFP_KERNEL); + key = kmem_cache_zalloc(key_jar, GFP_KERNEL); if (!key) goto no_memory_2; @@ -293,18 +293,12 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->uid = uid; key->gid = gid; key->perm = perm; - key->flags = 0; - key->expiry = 0; - key->payload.data = NULL; - key->security = NULL; if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_TRUSTED) key->flags |= 1 << KEY_FLAG_TRUSTED; - memset(&key->type_data, 0, sizeof(key->type_data)); - #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; #endif -- cgit v1.2.3 From d54e58b7f01552b0eb7d445f4b58de4499ad5ea6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:18 +0000 Subject: KEYS: Fix the keyring hash function The keyring hash function (used by the associative array) is supposed to clear the bottommost nibble of the index key (where the hash value resides) for keyrings and make sure it is non-zero for non-keyrings. This is done to make keyrings cluster together on one branch of the tree separately to other keys. Unfortunately, the wrong mask is used, so only the bottom two bits are examined and cleared and not the whole bottom nibble. This means that keys and keyrings can still be successfully searched for under most circumstances as the hash is consistent in its miscalculation, but if a keyring's associative array bottom node gets filled up then approx 75% of the keyrings will not be put into the 0 branch. The consequence of this is that a key in a keyring linked to by another keyring, ie. keyring A -> keyring B -> key may not be found if the search starts at keyring A and then descends into keyring B because search_nested_keyrings() only searches up the 0 branch (as it "knows" all keyrings must be there and not elsewhere in the tree). The fix is to use the right mask. This can be tested with: r=`keyctl newring sandbox @s` for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done for ((i=0; i<=16; i++)); do keyctl add user a$i a %:ring$i; done for ((i=0; i<=16; i++)); do keyctl search $r user a$i; done This creates a sandbox keyring, then creates 17 keyrings therein (labelled ring0..ring16). This causes the root node of the sandbox's associative array to overflow and for the tree to have extra nodes inserted. Each keyring then is given a user key (labelled aN for ringN) for us to search for. We then search for the user keys we added, starting from the sandbox. If working correctly, it should return the same ordered list of key IDs as for...keyctl add... did. Without this patch, it reports ENOKEY "Required key not available" for some of the keys. Just which keys get this depends as the kernel pointer to the key type forms part of the hash function. Reported-by: Nalin Dahyabhai Signed-off-by: David Howells Tested-by: Stephen Gallagher --- security/keys/keyring.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'security') diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 69f0cb7bab7e..0adbc77a59b9 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -160,7 +160,7 @@ static u64 mult_64x32_and_fold(u64 x, u32 y) static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key) { const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP; - const unsigned long level_mask = ASSOC_ARRAY_LEVEL_STEP_MASK; + const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK; const char *description = index_key->description; unsigned long hash, type; u32 piece; @@ -194,10 +194,10 @@ static unsigned long hash_key_type_and_desc(const struct keyring_index_key *inde * ordinary keys by making sure the lowest level segment in the hash is * zero for keyrings and non-zero otherwise. */ - if (index_key->type != &key_type_keyring && (hash & level_mask) == 0) + if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0) return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1; - if (index_key->type == &key_type_keyring && (hash & level_mask) != 0) - return (hash + (hash << level_shift)) & ~level_mask; + if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0) + return (hash + (hash << level_shift)) & ~fan_mask; return hash; } -- cgit v1.2.3 From 23fd78d76415729b338ff1802a0066b4a62f7fb8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:18 +0000 Subject: KEYS: Fix multiple key add into associative array If sufficient keys (or keyrings) are added into a keyring such that a node in the associative array's tree overflows (each node has a capacity N, currently 16) and such that all N+1 keys have the same index key segment for that level of the tree (the level'th nibble of the index key), then assoc_array_insert() calls ops->diff_objects() to indicate at which bit position the two index keys vary. However, __key_link_begin() passes a NULL object to assoc_array_insert() with the intention of supplying the correct pointer later before we commit the change. This means that keyring_diff_objects() is given a NULL pointer as one of its arguments which it does not expect. This results in an oops like the attached. With the previous patch to fix the keyring hash function, this can be forced much more easily by creating a keyring and only adding keyrings to it. Add any other sort of key and a different insertion path is taken - all 16+1 objects must want to cluster in the same node slot. This can be tested by: r=`keyctl newring sandbox @s` for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done This should work fine, but oopses when the 17th keyring is added. Since ops->diff_objects() is always called with the first pointer pointing to the object to be inserted (ie. the NULL pointer), we can fix the problem by changing the to-be-inserted object pointer to point to the index key passed into assoc_array_insert() instead. Whilst we're at it, we also switch the arguments so that they are the same as for ->compare_object(). BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 IP: [] hash_key_type_and_desc+0x18/0xb0 ... RIP: 0010:[] hash_key_type_and_desc+0x18/0xb0 ... Call Trace: [] keyring_diff_objects+0x21/0xd2 [] assoc_array_insert+0x3b6/0x908 [] __key_link_begin+0x78/0xe5 [] key_create_or_update+0x17d/0x36a [] SyS_add_key+0x123/0x183 [] tracesys+0xdd/0xe2 Signed-off-by: David Howells Tested-by: Stephen Gallagher --- Documentation/assoc_array.txt | 6 +++--- include/linux/assoc_array.h | 6 +++--- lib/assoc_array.c | 4 ++-- security/keys/keyring.c | 7 +++---- 4 files changed, 11 insertions(+), 12 deletions(-) (limited to 'security') diff --git a/Documentation/assoc_array.txt b/Documentation/assoc_array.txt index f4faec0f66e4..2f2c6cdd73c0 100644 --- a/Documentation/assoc_array.txt +++ b/Documentation/assoc_array.txt @@ -164,10 +164,10 @@ This points to a number of methods, all of which need to be provided: (4) Diff the index keys of two objects. - int (*diff_objects)(const void *a, const void *b); + int (*diff_objects)(const void *object, const void *index_key); - Return the bit position at which the index keys of two objects differ or - -1 if they are the same. + Return the bit position at which the index key of the specified object + differs from the given index key or -1 if they are the same. (5) Free an object. diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h index 9a193b84238a..a89df3be1686 100644 --- a/include/linux/assoc_array.h +++ b/include/linux/assoc_array.h @@ -41,10 +41,10 @@ struct assoc_array_ops { /* Is this the object we're looking for? */ bool (*compare_object)(const void *object, const void *index_key); - /* How different are two objects, to a bit position in their keys? (or - * -1 if they're the same) + /* How different is an object from an index key, to a bit position in + * their keys? (or -1 if they're the same) */ - int (*diff_objects)(const void *a, const void *b); + int (*diff_objects)(const void *object, const void *index_key); /* Method to free an object. */ void (*free_object)(void *object); diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 17edeaf19180..1b6a44f1ec3e 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -759,8 +759,8 @@ all_leaves_cluster_together: pr_devel("all leaves cluster together\n"); diff = INT_MAX; for (i = 0; i < ASSOC_ARRAY_FAN_OUT; i++) { - int x = ops->diff_objects(assoc_array_ptr_to_leaf(edit->leaf), - assoc_array_ptr_to_leaf(node->slots[i])); + int x = ops->diff_objects(assoc_array_ptr_to_leaf(node->slots[i]), + index_key); if (x < diff) { BUG_ON(x < 0); diff = x; diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 0adbc77a59b9..3dd8445cd489 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -279,12 +279,11 @@ static bool keyring_compare_object(const void *object, const void *data) * Compare the index keys of a pair of objects and determine the bit position * at which they differ - if they differ. */ -static int keyring_diff_objects(const void *_a, const void *_b) +static int keyring_diff_objects(const void *object, const void *data) { - const struct key *key_a = keyring_ptr_to_key(_a); - const struct key *key_b = keyring_ptr_to_key(_b); + const struct key *key_a = keyring_ptr_to_key(object); const struct keyring_index_key *a = &key_a->index_key; - const struct keyring_index_key *b = &key_b->index_key; + const struct keyring_index_key *b = data; unsigned long seg_a, seg_b; int level, i; -- cgit v1.2.3 From 9c5e45df215b4788f7a41c983ce862d08a083c2d Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:19 +0000 Subject: KEYS: Fix searching of nested keyrings If a keyring contains more than 16 keyrings (the capacity of a single node in the associative array) then those keyrings are split over multiple nodes arranged as a tree. If search_nested_keyrings() is called to search the keyring then it will attempt to manually walk over just the 0 branch of the associative array tree where all the keyring links are stored. This works provided the key is found before the algorithm steps from one node containing keyrings to a child node or if there are sufficiently few keyring links that the keyrings are all in one node. However, if the algorithm does need to step from a node to a child node, it doesn't change the node pointer unless a shortcut also gets transited. This means that the algorithm will keep scanning the same node over and over again without terminating and without returning. To fix this, move the internal-pointer-to-node translation from inside the shortcut transit handler so that it applies it to node arrival as well. This can be tested by: r=`keyctl newring sandbox @s` for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done for ((i=0; i<=16; i++)); do keyctl add user a$i a %:ring$i; done for ((i=0; i<=16; i++)); do keyctl search $r user a$i; done for ((i=17; i<=20; i++)); do keyctl search $r user a$i; done The searches should all complete successfully (or with an error for 17-20), but instead one or more of them will hang. Signed-off-by: David Howells Tested-by: Stephen Gallagher --- security/keys/keyring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'security') diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 3dd8445cd489..d46cbc5e335e 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -690,8 +690,8 @@ descend_to_node: smp_read_barrier_depends(); ptr = ACCESS_ONCE(shortcut->next_node); BUG_ON(!assoc_array_ptr_is_node(ptr)); - node = assoc_array_ptr_to_node(ptr); } + node = assoc_array_ptr_to_node(ptr); begin_node: kdebug("begin_node"); -- cgit v1.2.3 From c7277090927a5e71871e799a355ed2940f6c8fc6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 2 Dec 2013 11:24:19 +0000 Subject: security: shmem: implement kernel private shmem inodes We have a problem where the big_key key storage implementation uses a shmem backed inode to hold the key contents. Because of this detail of implementation LSM checks are being done between processes trying to read the keys and the tmpfs backed inode. The LSM checks are already being handled on the key interface level and should not be enforced at the inode level (since the inode is an implementation detail, not a part of the security model) This patch implements a new function shmem_kernel_file_setup() which returns the equivalent to shmem_file_setup() only the underlying inode has S_PRIVATE set. This means that all LSM checks for the inode in question are skipped. It should only be used for kernel internal operations where the inode is not exposed to userspace without proper LSM checking. It is possible that some other users of shmem_file_setup() should use the new interface, but this has not been explored. Reproducing this bug is a little bit difficult. The steps I used on Fedora are: (1) Turn off selinux enforcing: setenforce 0 (2) Create a huge key k=`dd if=/dev/zero bs=8192 count=1 | keyctl padd big_key test-key @s` (3) Access the key in another context: runcon system_u:system_r:httpd_t:s0-s0:c0.c1023 keyctl print $k >/dev/null (4) Examine the audit logs: ausearch -m AVC -i --subject httpd_t | audit2allow If the last command's output includes a line that looks like: allow httpd_t user_tmpfs_t:file { open read }; There was an inode check between httpd and the tmpfs filesystem. With this patch no such denial will be seen. (NOTE! you should clear your audit log if you have tested for this previously) (Please return you box to enforcing) Signed-off-by: Eric Paris Signed-off-by: David Howells cc: Hugh Dickins cc: linux-mm@kvack.org --- include/linux/shmem_fs.h | 2 ++ mm/shmem.c | 36 +++++++++++++++++++++++++++++------- security/keys/big_key.c | 2 +- 3 files changed, 32 insertions(+), 8 deletions(-) (limited to 'security') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 30aa0dc60d75..9d55438bc4ad 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -47,6 +47,8 @@ extern int shmem_init(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); +extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, + unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern void shmem_unlock_mapping(struct address_space *mapping); diff --git a/mm/shmem.c b/mm/shmem.c index 8297623fcaed..902a14842b74 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2918,13 +2918,8 @@ static struct dentry_operations anon_ops = { .d_dname = simple_dname }; -/** - * shmem_file_setup - get an unlinked file living in tmpfs - * @name: name for dentry (to be seen in /proc//maps - * @size: size to be set for the file - * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size - */ -struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +static struct file *__shmem_file_setup(const char *name, loff_t size, + unsigned long flags, unsigned int i_flags) { struct file *res; struct inode *inode; @@ -2957,6 +2952,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags if (!inode) goto put_dentry; + inode->i_flags |= i_flags; d_instantiate(path.dentry, inode); inode->i_size = size; clear_nlink(inode); /* It is unlinked */ @@ -2977,6 +2973,32 @@ put_memory: shmem_unacct_size(flags, size); return res; } + +/** + * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be + * kernel internal. There will be NO LSM permission checks against the + * underlying inode. So users of this interface must do LSM checks at a + * higher layer. The one user is the big_key implementation. LSM checks + * are provided at the key level rather than the inode level. + * @name: name for dentry (to be seen in /proc//maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, S_PRIVATE); +} + +/** + * shmem_file_setup - get an unlinked file living in tmpfs + * @name: name for dentry (to be seen in /proc//maps + * @size: size to be set for the file + * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size + */ +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) +{ + return __shmem_file_setup(name, size, flags, 0); +} EXPORT_SYMBOL_GPL(shmem_file_setup); /** diff --git a/security/keys/big_key.c b/security/keys/big_key.c index 7f44c3207a9b..8137b27d641d 100644 --- a/security/keys/big_key.c +++ b/security/keys/big_key.c @@ -70,7 +70,7 @@ int big_key_instantiate(struct key *key, struct key_preparsed_payload *prep) * * TODO: Encrypt the stored data with a temporary key. */ - file = shmem_file_setup("", datalen, 0); + file = shmem_kernel_file_setup("", datalen, 0); if (IS_ERR(file)) { ret = PTR_ERR(file); goto err_quota; -- cgit v1.2.3 From 09ae6345721afbb7cf3e0920209b140cbe7bff0d Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Mon, 2 Dec 2013 00:05:20 +0100 Subject: ima: Do not free 'entry' before it is initialized 7bc5f447ce9d0 (ima: define new function ima_alloc_init_template() to API) moved the initialization of 'entry' in ima_add_boot_aggregate() a bit more below, after the if (ima_used_chip). So, 'entry' is not initialized while being inside this if-block. So, we should not attempt to free it. Found by Coverity (CID: 1131971) Fixes: 7bc5f447ce9d0 (ima: define new function ima_alloc_init_template() to API) Signed-off-by: Christoph Paasch Signed-off-by: Mimi Zohar --- security/integrity/ima/ima_init.c | 1 - 1 file changed, 1 deletion(-) (limited to 'security') diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c index 15f34bd40abe..76b8e2c4fd38 100644 --- a/security/integrity/ima/ima_init.c +++ b/security/integrity/ima/ima_init.c @@ -63,7 +63,6 @@ static void __init ima_add_boot_aggregate(void) result = ima_calc_boot_aggregate(&hash.hdr); if (result < 0) { audit_cause = "hashing_error"; - kfree(entry); goto err_out; } } -- cgit v1.2.3 From a7ed7c60e14df5b986f93549717235b882643e7e Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Mon, 2 Dec 2013 19:40:34 +0100 Subject: ima: properly free ima_template_entry structures The new templates management mechanism records information associated to an event into an array of 'ima_field_data' structures and makes it available through the 'template_data' field of the 'ima_template_entry' structure (the element of the measurements list created by IMA). Since 'ima_field_data' contains dynamically allocated data (which length varies depending on the data associated to a selected template field), it is not enough to just free the memory reserved for a 'ima_template_entry' structure if something goes wrong. This patch creates the new function ima_free_template_entry() which walks the array of 'ima_field_data' structures, frees the memory referenced by the 'data' pointer and finally the space reserved for the 'ima_template_entry' structure. Further, it replaces existing kfree() that have a pointer to an 'ima_template_entry' structure as argument with calls to the new function. Fixes: a71dc65: ima: switch to new template management mechanism Signed-off-by: Roberto Sassu Signed-off-by: Mimi Zohar --- security/integrity/ima/ima.h | 1 + security/integrity/ima/ima_api.c | 21 +++++++++++++++++---- security/integrity/ima/ima_init.c | 2 +- 3 files changed, 19 insertions(+), 5 deletions(-) (limited to 'security') diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 9636e17c9f5d..0356e1d437ca 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -148,6 +148,7 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint, int xattr_len, struct ima_template_entry **entry); int ima_store_template(struct ima_template_entry *entry, int violation, struct inode *inode, const unsigned char *filename); +void ima_free_template_entry(struct ima_template_entry *entry); const char *ima_d_path(struct path *path, char **pathbuf); /* rbtree tree calls to lookup, insert, delete diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 80374842fe0b..c38bbce8c6a6 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -21,6 +21,19 @@ #include #include "ima.h" +/* + * ima_free_template_entry - free an existing template entry + */ +void ima_free_template_entry(struct ima_template_entry *entry) +{ + int i; + + for (i = 0; i < entry->template_desc->num_fields; i++) + kfree(entry->template_data[i].data); + + kfree(entry); +} + /* * ima_alloc_init_template - create and initialize a new template entry */ @@ -37,6 +50,7 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint, if (!*entry) return -ENOMEM; + (*entry)->template_desc = template_desc; for (i = 0; i < template_desc->num_fields; i++) { struct ima_template_field *field = template_desc->fields[i]; u32 len; @@ -51,10 +65,9 @@ int ima_alloc_init_template(struct integrity_iint_cache *iint, (*entry)->template_data_len += sizeof(len); (*entry)->template_data_len += len; } - (*entry)->template_desc = template_desc; return 0; out: - kfree(*entry); + ima_free_template_entry(*entry); *entry = NULL; return result; } @@ -134,7 +147,7 @@ void ima_add_violation(struct file *file, const unsigned char *filename, } result = ima_store_template(entry, violation, inode, filename); if (result < 0) - kfree(entry); + ima_free_template_entry(entry); err_out: integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename, op, cause, result, 0); @@ -269,7 +282,7 @@ void ima_store_measurement(struct integrity_iint_cache *iint, if (!result || result == -EEXIST) iint->flags |= IMA_MEASURED; if (result < 0) - kfree(entry); + ima_free_template_entry(entry); } void ima_audit_measurement(struct integrity_iint_cache *iint, diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c index 76b8e2c4fd38..37122768554a 100644 --- a/security/integrity/ima/ima_init.c +++ b/security/integrity/ima/ima_init.c @@ -75,7 +75,7 @@ static void __init ima_add_boot_aggregate(void) result = ima_store_template(entry, violation, NULL, boot_aggregate_name); if (result < 0) - kfree(entry); + ima_free_template_entry(entry); return; err_out: integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, boot_aggregate_name, op, -- cgit v1.2.3 From 0af901643fe3f1f8d44e41115d36609ee4bda2bf Mon Sep 17 00:00:00 2001 From: "Geyslan G. Bem" Date: Wed, 4 Dec 2013 16:10:24 -0500 Subject: selinux: fix possible memory leak Free 'ctx_str' when necessary. Signed-off-by: Geyslan G. Bem Signed-off-by: Paul Moore --- security/selinux/xfrm.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'security') diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index a91d205ec0c6..cf79a4564e38 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -327,19 +327,22 @@ int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x, return rc; ctx = kmalloc(sizeof(*ctx) + str_len, GFP_ATOMIC); - if (!ctx) - return -ENOMEM; + if (!ctx) { + rc = -ENOMEM; + goto out; + } ctx->ctx_doi = XFRM_SC_DOI_LSM; ctx->ctx_alg = XFRM_SC_ALG_SELINUX; ctx->ctx_sid = secid; ctx->ctx_len = str_len; memcpy(ctx->ctx_str, ctx_str, str_len); - kfree(ctx_str); x->security = ctx; atomic_inc(&selinux_xfrm_refcount); - return 0; +out: + kfree(ctx_str); + return rc; } /* -- cgit v1.2.3 From 47180068276a04ed31d24fe04c673138208b07a9 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 4 Dec 2013 16:10:45 -0500 Subject: selinux: handle TCP SYN-ACK packets correctly in selinux_ip_output() In selinux_ip_output() we always label packets based on the parent socket. While this approach works in almost all cases, it doesn't work in the case of TCP SYN-ACK packets when the correct label is not the label of the parent socket, but rather the label of the larval socket represented by the request_sock struct. Unfortunately, since the request_sock isn't queued on the parent socket until *after* the SYN-ACK packet is sent, we can't lookup the request_sock to determine the correct label for the packet; at this point in time the best we can do is simply pass/NF_ACCEPT the packet. It must be said that simply passing the packet without any explicit labeling action, while far from ideal, is not terrible as the SYN-ACK packet will inherit any IP option based labeling from the initial connection request so the label *should* be correct and all our access controls remain in place so we shouldn't have to worry about information leaks. Reported-by: Janak Desai Tested-by: Janak Desai Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 777ee98273d1..877bab748c87 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -53,6 +53,7 @@ #include /* for local_port_range[] */ #include #include /* struct or_callable used in sock_rcv_skb */ +#include #include #include #include @@ -4731,6 +4732,7 @@ static unsigned int selinux_ipv6_forward(unsigned int hooknum, static unsigned int selinux_ip_output(struct sk_buff *skb, u16 family) { + struct sock *sk; u32 sid; if (!netlbl_enabled()) @@ -4739,8 +4741,27 @@ static unsigned int selinux_ip_output(struct sk_buff *skb, /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ - if (skb->sk) { - struct sk_security_struct *sksec = skb->sk->sk_security; + sk = skb->sk; + if (sk) { + struct sk_security_struct *sksec; + + if (sk->sk_state == TCP_LISTEN) + /* if the socket is the listening state then this + * packet is a SYN-ACK packet which means it needs to + * be labeled based on the connection/request_sock and + * not the parent socket. unfortunately, we can't + * lookup the request_sock yet as it isn't queued on + * the parent socket until after the SYN-ACK is sent. + * the "solution" is to simply pass the packet as-is + * as any IP option based labeling should be copied + * from the initial connection request (in the IP + * layer). it is far from ideal, but until we get a + * security label in the packet itself this is the + * best we can do. */ + return NF_ACCEPT; + + /* standard practice, label using the parent socket */ + sksec = sk->sk_security; sid = sksec->sid; } else sid = SECINITSID_KERNEL; -- cgit v1.2.3 From 446b802437f285de68ffb8d6fac3c44c3cab5b04 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 4 Dec 2013 16:10:51 -0500 Subject: selinux: handle TCP SYN-ACK packets correctly in selinux_ip_postroute() In selinux_ip_postroute() we perform access checks based on the packet's security label. For locally generated traffic we get the packet's security label from the associated socket; this works in all cases except for TCP SYN-ACK packets. In the case of SYN-ACK packet's the correct security label is stored in the connection's request_sock, not the server's socket. Unfortunately, at the point in time when selinux_ip_postroute() is called we can't query the request_sock directly, we need to recreate the label using the same logic that originally labeled the associated request_sock. See the inline comments for more explanation. Reported-by: Janak Desai Tested-by: Janak Desai Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 68 +++++++++++++++++++++++++++++++++++++----------- 1 file changed, 53 insertions(+), 15 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 877bab748c87..cc076a9b0344 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3847,6 +3847,30 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) return 0; } +/** + * selinux_conn_sid - Determine the child socket label for a connection + * @sk_sid: the parent socket's SID + * @skb_sid: the packet's SID + * @conn_sid: the resulting connection SID + * + * If @skb_sid is valid then the user:role:type information from @sk_sid is + * combined with the MLS information from @skb_sid in order to create + * @conn_sid. If @skb_sid is not valid then then @conn_sid is simply a copy + * of @sk_sid. Returns zero on success, negative values on failure. + * + */ +static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) +{ + int err = 0; + + if (skb_sid != SECSID_NULL) + err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid); + else + *conn_sid = sk_sid; + + return err; +} + /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, @@ -4453,7 +4477,7 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct sk_security_struct *sksec = sk->sk_security; int err; u16 family = sk->sk_family; - u32 newsid; + u32 connsid; u32 peersid; /* handle mapped IPv4 packets arriving via IPv6 sockets */ @@ -4463,16 +4487,11 @@ static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb, err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; - if (peersid == SECSID_NULL) { - req->secid = sksec->sid; - req->peer_secid = SECSID_NULL; - } else { - err = security_sid_mls_copy(sksec->sid, peersid, &newsid); - if (err) - return err; - req->secid = newsid; - req->peer_secid = peersid; - } + err = selinux_conn_sid(sksec->sid, peersid, &connsid); + if (err) + return err; + req->secid = connsid; + req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } @@ -4846,12 +4865,12 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, if (!secmark_active && !peerlbl_active) return NF_ACCEPT; - /* if the packet is being forwarded then get the peer label from the - * packet itself; otherwise check to see if it is from a local - * application or the kernel, if from an application get the peer label - * from the sending socket, otherwise use the kernel's sid */ sk = skb->sk; if (sk == NULL) { + /* Without an associated socket the packet is either coming + * from the kernel or it is being forwarded; check the packet + * to determine which and if the packet is being forwarded + * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) @@ -4860,7 +4879,26 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } + } else if (sk->sk_state == TCP_LISTEN) { + /* Locally generated packet but the associated socket is in the + * listening state which means this is a SYN-ACK packet. In + * this particular case the correct security label is assigned + * to the connection/request_sock but unfortunately we can't + * query the request_sock as it isn't queued on the parent + * socket until after the SYN-ACK packet is sent; the only + * viable choice is to regenerate the label like we do in + * selinux_inet_conn_request(). See also selinux_ip_output() + * for similar problems. */ + u32 skb_sid; + struct sk_security_struct *sksec = sk->sk_security; + if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) + return NF_DROP; + if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) + return NF_DROP; + secmark_perm = PACKET__SEND; } else { + /* Locally generated packet, fetch the security label from the + * associated socket. */ struct sk_security_struct *sksec = sk->sk_security; peer_sid = sksec->sid; secmark_perm = PACKET__SEND; -- cgit v1.2.3 From 817eff718dca4e54d5721211ddde0914428fbb7c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 10 Dec 2013 14:57:54 -0500 Subject: selinux: look for IPsec labels on both inbound and outbound packets Previously selinux_skb_peerlbl_sid() would only check for labeled IPsec security labels on inbound packets, this patch enables it to check both inbound and outbound traffic for labeled IPsec security labels. Reported-by: Janak Desai Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 2 +- security/selinux/include/xfrm.h | 8 ++++--- security/selinux/xfrm.c | 51 +++++++++++++++++++++++++++++++++-------- 3 files changed, 47 insertions(+), 14 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index cc076a9b0344..8b2812312ae4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3829,7 +3829,7 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) u32 nlbl_sid; u32 nlbl_type; - err = selinux_skb_xfrm_sid(skb, &xfrm_sid); + err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 0dec76c64cf5..48c3cc94c168 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -39,6 +39,7 @@ int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb, int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb, struct common_audit_data *ad, u8 proto); int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall); +int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid); static inline void selinux_xfrm_notify_policyload(void) { @@ -79,11 +80,12 @@ static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, static inline void selinux_xfrm_notify_policyload(void) { } -#endif -static inline int selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid) +static inline int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid) { - return selinux_xfrm_decode_session(skb, sid, 0); + *sid = SECSID_NULL; + return 0; } +#endif #endif /* _SELINUX_XFRM_H_ */ diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index cf79a4564e38..0462cb3ff0a7 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -209,19 +209,26 @@ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, NULL) ? 0 : 1); } -/* - * LSM hook implementation that checks and/or returns the xfrm sid for the - * incoming packet. - */ -int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall) +static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb) { - u32 sid_session = SECSID_NULL; - struct sec_path *sp; + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x; - if (skb == NULL) - goto out; + if (dst == NULL) + return SECSID_NULL; + x = dst->xfrm; + if (x == NULL || !selinux_authorizable_xfrm(x)) + return SECSID_NULL; + + return x->security->ctx_sid; +} + +static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb, + u32 *sid, int ckall) +{ + u32 sid_session = SECSID_NULL; + struct sec_path *sp = skb->sp; - sp = skb->sp; if (sp) { int i; @@ -247,6 +254,30 @@ out: return 0; } +/* + * LSM hook implementation that checks and/or returns the xfrm sid for the + * incoming packet. + */ +int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall) +{ + if (skb == NULL) { + *sid = SECSID_NULL; + return 0; + } + return selinux_xfrm_skb_sid_ingress(skb, sid, ckall); +} + +int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid) +{ + int rc; + + rc = selinux_xfrm_skb_sid_ingress(skb, sid, 0); + if (rc == 0 && *sid == SECSID_NULL) + *sid = selinux_xfrm_skb_sid_egress(skb); + + return rc; +} + /* * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy. */ -- cgit v1.2.3 From c0828e50485932b7e019df377a6b0a8d1ebd3080 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 10 Dec 2013 14:58:01 -0500 Subject: selinux: process labeled IPsec TCP SYN-ACK packets properly in selinux_ip_postroute() Due to difficulty in arriving at the proper security label for TCP SYN-ACK packets in selinux_ip_postroute(), we need to check packets while/before they are undergoing XFRM transforms instead of waiting until afterwards so that we can determine the correct security label. Reported-by: Janak Desai Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 42 +++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 8b2812312ae4..6db2e589a1f3 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4850,22 +4850,31 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, * as fast and as clean as possible. */ if (!selinux_policycap_netpeer) return selinux_ip_postroute_compat(skb, ifindex, family); + + secmark_active = selinux_secmark_enabled(); + peerlbl_active = selinux_peerlbl_enabled(); + if (!secmark_active && !peerlbl_active) + return NF_ACCEPT; + + sk = skb->sk; + #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst - * is NULL, in this case go ahead and apply access control. */ - if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL) + * is NULL, in this case go ahead and apply access control. + * NOTE: if this is a local socket (skb->sk != NULL) that is in the + * TCP listening state we cannot wait until the XFRM processing + * is done as we will miss out on the SA label if we do; + * unfortunately, this means more work, but it is only once per + * connection. */ + if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && + !(sk != NULL && sk->sk_state == TCP_LISTEN)) return NF_ACCEPT; #endif - secmark_active = selinux_secmark_enabled(); - peerlbl_active = selinux_peerlbl_enabled(); - if (!secmark_active && !peerlbl_active) - return NF_ACCEPT; - sk = skb->sk; if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet @@ -4893,6 +4902,25 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, int ifindex, struct sk_security_struct *sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; + /* At this point, if the returned skb peerlbl is SECSID_NULL + * and the packet has been through at least one XFRM + * transformation then we must be dealing with the "final" + * form of labeled IPsec packet; since we've already applied + * all of our access controls on this packet we can safely + * pass the packet. */ + if (skb_sid == SECSID_NULL) { + switch (family) { + case PF_INET: + if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) + return NF_ACCEPT; + break; + case PF_INET6: + if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) + return NF_ACCEPT; + default: + return NF_DROP_ERR(-ECONNREFUSED); + } + } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; -- cgit v1.2.3 From 29b1deb2a48a9dd02b93597aa4c055a24c0e989f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Dec 2013 11:17:45 -0800 Subject: Revert "selinux: consider filesystem subtype in policies" This reverts commit 102aefdda4d8275ce7d7100bc16c88c74272b260. Tom London reports that it causes sync() to hang on Fedora rawhide: https://bugzilla.redhat.com/show_bug.cgi?id=1033965 and Josh Boyer bisected it down to this commit. Reverting the commit in the rawhide kernel fixes the problem. Eric Paris root-caused it to incorrect subtype matching in that commit breaking fuse, and has a tentative patch, but by now we're better off retrying this in 3.14 rather than playing with it any more. Reported-by: Tom London Bisected-by: Josh Boyer Acked-by: Eric Paris Cc: James Morris Cc: Anand Avati Cc: Paul Moore Signed-off-by: Linus Torvalds --- security/selinux/hooks.c | 40 ++++++++++++++++++---------------------- security/selinux/ss/services.c | 42 ++++-------------------------------------- 2 files changed, 22 insertions(+), 60 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 794c3ca49eac..98b1caa1c1d3 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -95,10 +95,6 @@ #include "audit.h" #include "avc_ss.h" -#define SB_TYPE_FMT "%s%s%s" -#define SB_SUBTYPE(sb) (sb->s_subtype && sb->s_subtype[0]) -#define SB_TYPE_ARGS(sb) sb->s_type->name, SB_SUBTYPE(sb) ? "." : "", SB_SUBTYPE(sb) ? sb->s_subtype : "" - extern struct security_operations *security_ops; /* SECMARK reference count */ @@ -413,8 +409,8 @@ static int sb_finish_set_opts(struct super_block *sb) the first boot of the SELinux kernel before we have assigned xattr values to the filesystem. */ if (!root_inode->i_op->getxattr) { - printk(KERN_WARNING "SELinux: (dev %s, type "SB_TYPE_FMT") has no " - "xattr support\n", sb->s_id, SB_TYPE_ARGS(sb)); + printk(KERN_WARNING "SELinux: (dev %s, type %s) has no " + "xattr support\n", sb->s_id, sb->s_type->name); rc = -EOPNOTSUPP; goto out; } @@ -422,22 +418,22 @@ static int sb_finish_set_opts(struct super_block *sb) if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) printk(KERN_WARNING "SELinux: (dev %s, type " - SB_TYPE_FMT") has no security xattr handler\n", - sb->s_id, SB_TYPE_ARGS(sb)); + "%s) has no security xattr handler\n", + sb->s_id, sb->s_type->name); else printk(KERN_WARNING "SELinux: (dev %s, type " - SB_TYPE_FMT") getxattr errno %d\n", sb->s_id, - SB_TYPE_ARGS(sb), -rc); + "%s) getxattr errno %d\n", sb->s_id, + sb->s_type->name, -rc); goto out; } } if (sbsec->behavior > ARRAY_SIZE(labeling_behaviors)) - printk(KERN_ERR "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), unknown behavior\n", - sb->s_id, SB_TYPE_ARGS(sb)); + printk(KERN_ERR "SELinux: initialized (dev %s, type %s), unknown behavior\n", + sb->s_id, sb->s_type->name); else - printk(KERN_DEBUG "SELinux: initialized (dev %s, type "SB_TYPE_FMT"), %s\n", - sb->s_id, SB_TYPE_ARGS(sb), + printk(KERN_DEBUG "SELinux: initialized (dev %s, type %s), %s\n", + sb->s_id, sb->s_type->name, labeling_behaviors[sbsec->behavior-1]); sbsec->flags |= SE_SBINITIALIZED; @@ -600,6 +596,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, const struct cred *cred = current_cred(); int rc = 0, i; struct superblock_security_struct *sbsec = sb->s_security; + const char *name = sb->s_type->name; struct inode *inode = sbsec->sb->s_root->d_inode; struct inode_security_struct *root_isec = inode->i_security; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; @@ -658,8 +655,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, strlen(mount_options[i]), &sid); if (rc) { printk(KERN_WARNING "SELinux: security_context_to_sid" - "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n", - mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc); + "(%s) failed for (dev %s, type %s) errno=%d\n", + mount_options[i], sb->s_id, name, rc); goto out; } switch (flags[i]) { @@ -806,8 +803,7 @@ out: out_double_mount: rc = -EINVAL; printk(KERN_WARNING "SELinux: mount invalid. Same superblock, different " - "security settings for (dev %s, type "SB_TYPE_FMT")\n", sb->s_id, - SB_TYPE_ARGS(sb)); + "security settings for (dev %s, type %s)\n", sb->s_id, name); goto out; } @@ -2480,8 +2476,8 @@ static int selinux_sb_remount(struct super_block *sb, void *data) rc = security_context_to_sid(mount_options[i], len, &sid); if (rc) { printk(KERN_WARNING "SELinux: security_context_to_sid" - "(%s) failed for (dev %s, type "SB_TYPE_FMT") errno=%d\n", - mount_options[i], sb->s_id, SB_TYPE_ARGS(sb), rc); + "(%s) failed for (dev %s, type %s) errno=%d\n", + mount_options[i], sb->s_id, sb->s_type->name, rc); goto out_free_opts; } rc = -EINVAL; @@ -2519,8 +2515,8 @@ out_free_secdata: return rc; out_bad_option: printk(KERN_WARNING "SELinux: unable to change security options " - "during remount (dev %s, type "SB_TYPE_FMT")\n", sb->s_id, - SB_TYPE_ARGS(sb)); + "during remount (dev %s, type=%s)\n", sb->s_id, + sb->s_type->name); goto out_free_opts; } diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index ee470a0b5c27..d106733ad987 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2334,50 +2334,16 @@ int security_fs_use(struct super_block *sb) struct ocontext *c; struct superblock_security_struct *sbsec = sb->s_security; const char *fstype = sb->s_type->name; - const char *subtype = (sb->s_subtype && sb->s_subtype[0]) ? sb->s_subtype : NULL; - struct ocontext *base = NULL; read_lock(&policy_rwlock); - for (c = policydb.ocontexts[OCON_FSUSE]; c; c = c->next) { - char *sub; - int baselen; - - baselen = strlen(fstype); - - /* if base does not match, this is not the one */ - if (strncmp(fstype, c->u.name, baselen)) - continue; - - /* if there is no subtype, this is the one! */ - if (!subtype) - break; - - /* skip past the base in this entry */ - sub = c->u.name + baselen; - - /* entry is only a base. save it. keep looking for subtype */ - if (sub[0] == '\0') { - base = c; - continue; - } - - /* entry is not followed by a subtype, so it is not a match */ - if (sub[0] != '.') - continue; - - /* whew, we found a subtype of this fstype */ - sub++; /* move past '.' */ - - /* exact match of fstype AND subtype */ - if (!strcmp(subtype, sub)) + c = policydb.ocontexts[OCON_FSUSE]; + while (c) { + if (strcmp(fstype, c->u.name) == 0) break; + c = c->next; } - /* in case we had found an fstype match but no subtype match */ - if (!c) - c = base; - if (c) { sbsec->behavior = c->v.behavior; if (!c->sid[0]) { -- cgit v1.2.3 From 46d01d63221c3508421dd72ff9c879f61053cffc Mon Sep 17 00:00:00 2001 From: Chad Hanson Date: Mon, 23 Dec 2013 17:45:01 -0500 Subject: selinux: fix broken peer recv check Fix a broken networking check. Return an error if peer recv fails. If secmark is active and the packet recv succeeds the peer recv error is ignored. Signed-off-by: Chad Hanson Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 419491d8e7d2..5db26468b5c3 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4334,8 +4334,10 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); - if (err) + if (err) { selinux_netlbl_err(skb, err, 0); + return err; + } } if (secmark_active) { -- cgit v1.2.3 From c0c1439541f5305b57a83d599af32b74182933fe Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 23 Dec 2013 17:45:01 -0500 Subject: selinux: selinux_setprocattr()->ptrace_parent() needs rcu_read_lock() selinux_setprocattr() does ptrace_parent(p) under task_lock(p), but task_struct->alloc_lock doesn't pin ->parent or ->ptrace, this looks confusing and triggers the "suspicious RCU usage" warning because ptrace_parent() does rcu_dereference_check(). And in theory this is wrong, spin_lock()->preempt_disable() doesn't necessarily imply rcu_read_lock() we need to access the ->parent. Reported-by: Evan McNabb Signed-off-by: Oleg Nesterov Cc: stable@vger.kernel.org Signed-off-by: Paul Moore --- security/selinux/hooks.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'security') diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 5db26468b5c3..6625699f497c 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5588,11 +5588,11 @@ static int selinux_setprocattr(struct task_struct *p, /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = 0; - task_lock(p); + rcu_read_lock(); tracer = ptrace_parent(p); if (tracer) ptsid = task_sid(tracer); - task_unlock(p); + rcu_read_unlock(); if (tracer) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, -- cgit v1.2.3