From 0a14842f5a3c0e88a1e59fac5c3025db39721f74 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 20 Apr 2011 09:27:32 +0000 Subject: net: filter: Just In Time compiler for x86-64 In order to speedup packet filtering, here is an implementation of a JIT compiler for x86_64 It is disabled by default, and must be enabled by the admin. echo 1 >/proc/sys/net/core/bpf_jit_enable It uses module_alloc() and module_free() to get memory in the 2GB text kernel range since we call helpers functions from the generated code. EAX : BPF A accumulator EBX : BPF X accumulator RDI : pointer to skb (first argument given to JIT function) RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) r9d : skb->len - skb->data_len (headlen) r8 : skb->data To get a trace of generated code, use : echo 2 >/proc/sys/net/core/bpf_jit_enable Example of generated code : # tcpdump -p -n -s 0 -i eth1 host 192.168.20.0/24 flen=18 proglen=147 pass=3 image=ffffffffa00b5000 JIT code: ffffffffa00b5000: 55 48 89 e5 48 83 ec 60 48 89 5d f8 44 8b 4f 60 JIT code: ffffffffa00b5010: 44 2b 4f 64 4c 8b 87 b8 00 00 00 be 0c 00 00 00 JIT code: ffffffffa00b5020: e8 24 7b f7 e0 3d 00 08 00 00 75 28 be 1a 00 00 JIT code: ffffffffa00b5030: 00 e8 fe 7a f7 e0 24 00 3d 00 14 a8 c0 74 49 be JIT code: ffffffffa00b5040: 1e 00 00 00 e8 eb 7a f7 e0 24 00 3d 00 14 a8 c0 JIT code: ffffffffa00b5050: 74 36 eb 3b 3d 06 08 00 00 74 07 3d 35 80 00 00 JIT code: ffffffffa00b5060: 75 2d be 1c 00 00 00 e8 c8 7a f7 e0 24 00 3d 00 JIT code: ffffffffa00b5070: 14 a8 c0 74 13 be 26 00 00 00 e8 b5 7a f7 e0 24 JIT code: ffffffffa00b5080: 00 3d 00 14 a8 c0 75 07 b8 ff ff 00 00 eb 02 31 JIT code: ffffffffa00b5090: c0 c9 c3 BPF program is 144 bytes long, so native program is almost same size ;) (000) ldh [12] (001) jeq #0x800 jt 2 jf 8 (002) ld [26] (003) and #0xffffff00 (004) jeq #0xc0a81400 jt 16 jf 5 (005) ld [30] (006) and #0xffffff00 (007) jeq #0xc0a81400 jt 16 jf 17 (008) jeq #0x806 jt 10 jf 9 (009) jeq #0x8035 jt 10 jf 17 (010) ld [28] (011) and #0xffffff00 (012) jeq #0xc0a81400 jt 16 jf 13 (013) ld [38] (014) and #0xffffff00 (015) jeq #0xc0a81400 jt 16 jf 17 (016) ret #65535 (017) ret #0 Signed-off-by: Eric Dumazet Cc: Arnaldo Carvalho de Melo Cc: Ben Hutchings Cc: Hagen Paul Pfeifer Signed-off-by: David S. Miller --- net/packet/af_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/packet/af_packet.c') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b5362e96022b..549527bca87a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,7 +538,7 @@ static inline unsigned int run_filter(const struct sk_buff *skb, rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) - res = sk_run_filter(skb, filter->insns); + res = SK_RUN_FILTER(filter, skb); rcu_read_unlock(); return res; -- cgit v1.2.3 From 71338aa7d050c86d8765cd36e46be514fb0ebbce Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Mon, 23 May 2011 12:17:35 +0000 Subject: net: convert %p usage to %pK The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". The supporting code for kptr_restrict and %pK are currently in the -mm tree. This patch converts users of %p in net/ to %pK. Cases of printing pointers to the syslog are not covered, since this would eliminate useful information for postmortem debugging and the reading of the syslog is already optionally protected by the dmesg_restrict sysctl. Signed-off-by: Dan Rosenberg Cc: James Morris Cc: Eric Dumazet Cc: Thomas Graf Cc: Eugene Teo Cc: Kees Cook Cc: Ingo Molnar Cc: David S. Miller Cc: Peter Zijlstra Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/atm/proc.c | 4 ++-- net/can/bcm.c | 6 +++--- net/ipv4/raw.c | 2 +- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/udp.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/tcp_ipv6.c | 6 +++--- net/ipv6/udp.c | 2 +- net/key/af_key.c | 2 +- net/netlink/af_netlink.c | 2 +- net/packet/af_packet.c | 2 +- net/phonet/socket.c | 2 +- net/sctp/proc.c | 4 ++-- net/unix/af_unix.c | 2 +- 14 files changed, 22 insertions(+), 22 deletions(-) (limited to 'net/packet/af_packet.c') diff --git a/net/atm/proc.c b/net/atm/proc.c index f85da0779e5e..be3afdefec58 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -191,7 +191,7 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc *vcc) { struct sock *sk = sk_atm(vcc); - seq_printf(seq, "%p ", vcc); + seq_printf(seq, "%pK ", vcc); if (!vcc->dev) seq_printf(seq, "Unassigned "); else @@ -218,7 +218,7 @@ static void svc_info(struct seq_file *seq, struct atm_vcc *vcc) { if (!vcc->dev) seq_printf(seq, sizeof(void *) == 4 ? - "N/A@%p%10s" : "N/A@%p%2s", vcc, ""); + "N/A@%pK%10s" : "N/A@%pK%2s", vcc, ""); else seq_printf(seq, "%3d %3d %5d ", vcc->dev->number, vcc->vpi, vcc->vci); diff --git a/net/can/bcm.c b/net/can/bcm.c index cced806098a9..184a6572b67e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -165,9 +165,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; - seq_printf(m, ">>> socket %p", sk->sk_socket); - seq_printf(m, " / sk %p", sk); - seq_printf(m, " / bo %p", bo); + seq_printf(m, ">>> socket %pK", sk->sk_socket); + seq_printf(m, " / sk %pK", sk); + seq_printf(m, " / bo %pK", bo); seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); seq_printf(m, " / bound %s", bcm_proc_getifname(ifname, bo->ifindex)); seq_printf(m, " <<<\n"); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 11e1780455f2..c9893d43242e 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -979,7 +979,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet->inet_num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", i, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3c8d9b6f1ea4..a7d6671e33b8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2371,7 +2371,7 @@ static void get_openreq4(struct sock *sk, struct request_sock *req, int ttd = req->expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n", i, ireq->loc_addr, ntohs(inet_sk(sk)->inet_sport), @@ -2426,7 +2426,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " - "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", + "%08X %5d %8d %lu %d %pK %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, rx_queue, @@ -2461,7 +2461,7 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw, srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw, len); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 599374f65c76..abca870d8ff6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2090,7 +2090,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ae64984f81aa..cc7313b8f7ea 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1240,7 +1240,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet_sk(sp)->inet_num; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 868366470b4a..d1fd28711ba5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2036,7 +2036,7 @@ static void get_openreq6(struct seq_file *seq, seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], @@ -2087,7 +2087,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %lu %lu %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, @@ -2129,7 +2129,7 @@ static void get_timewait6_sock(struct seq_file *seq, seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index fc0c42a88e54..41f8c9c08dba 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1391,7 +1391,7 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket srcp = ntohs(inet->inet_sport); seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n", bucket, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, diff --git a/net/key/af_key.c b/net/key/af_key.c index d62401c25684..8f92cf8116ea 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3656,7 +3656,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v) if (v == SEQ_START_TOKEN) seq_printf(f ,"sk RefCnt Rmem Wmem User Inode\n"); else - seq_printf(f ,"%p %-6d %-6u %-6u %-6u %-6lu\n", + seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, atomic_read(&s->sk_refcnt), sk_rmem_alloc_get(s), diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 5fe4f3b04ed3..6ef64adf7362 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1985,7 +1985,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-6d %08x %-8d %-8d %pK %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->pid, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 549527bca87a..925f715686a5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2706,7 +2706,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) const struct packet_sock *po = pkt_sk(s); seq_printf(seq, - "%p %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", + "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, atomic_read(&s->sk_refcnt), s->sk_type, diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 8c5bfcef92cb..ab07711cf2f4 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -607,7 +607,7 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v) struct pn_sock *pn = pn_sk(sk); seq_printf(seq, "%2d %04X:%04X:%02X %02X %08X:%08X %5d %lu " - "%d %p %d%n", + "%d %pK %d%n", sk->sk_protocol, pn->sobject, pn->dobject, pn->resource, sk->sk_state, sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 61aacfbbaa92..05a6ce214714 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -212,7 +212,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) sctp_for_each_hentry(epb, node, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; - seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, + seq_printf(seq, "%8pK %8pK %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk, sctp_sk(sk)->type, sk->sk_state, hash, epb->bind_addr.port, sock_i_uid(sk), sock_i_ino(sk)); @@ -316,7 +316,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc = sctp_assoc(epb); sk = epb->sk; seq_printf(seq, - "%8p %8p %-3d %-3d %-2d %-4d " + "%8pK %8pK %-3d %-3d %-2d %-4d " "%4d %8d %8d %7d %5lu %-5d %5d ", assoc, sk, sctp_sk(sk)->type, sk->sk_state, assoc->state, hash, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b1d75beb7e20..0722a25a3a33 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2254,7 +2254,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) struct unix_sock *u = unix_sk(s); unix_state_lock(s); - seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu", + seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu", s, atomic_read(&s->sk_refcnt), 0, -- cgit v1.2.3