From 3a101b8de0d39403b2c7e5c23fd0b005668acf48 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 22 Apr 2014 21:31:56 -0400 Subject: audit: add netlink audit protocol bind to check capabilities on multicast join Register a netlink per-protocol bind fuction for audit to check userspace process capabilities before allowing a multicast group connection. Signed-off-by: Richard Guy Briggs Signed-off-by: David S. Miller --- kernel/audit.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 7c2893602d06..223cb746f141 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1076,10 +1076,20 @@ static void audit_receive(struct sk_buff *skb) mutex_unlock(&audit_cmd_mutex); } +/* Run custom bind function on netlink socket group connect or bind requests. */ +static int audit_bind(int group) +{ + if (!capable(CAP_AUDIT_READ)) + return -EPERM; + + return 0; +} + static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, + .bind = audit_bind, }; struct audit_net *aunet = net_generic(net, audit_net_id); -- cgit v1.2.3 From 451f921639fea4600dfb9ab2889332bdcc7b48d3 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 22 Apr 2014 21:31:57 -0400 Subject: audit: add netlink multicast group for log read Add a netlink multicast socket with one group to kaudit for "best-effort" delivery to read-only userspace clients such as systemd, in addition to the existing bidirectional unicast auditd userspace client. Currently, auditd is intended to use the CAP_AUDIT_CONTROL and CAP_AUDIT_WRITE capabilities, but actually uses CAP_NET_ADMIN. The CAP_AUDIT_READ capability is added for use by read-only AUDIT_NLGRP_READLOG netlink multicast group clients to the kaudit subsystem. This will safely give access to services such as systemd to consume audit logs while ensuring write access remains restricted for integrity. Signed-off-by: Richard Guy Briggs Signed-off-by: David S. Miller --- kernel/audit.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 47 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 223cb746f141..d272cc11dff4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -423,6 +423,35 @@ static void kauditd_send_skb(struct sk_buff *skb) consume_skb(skb); } +/* + * kauditd_send_multicast_skb - send the skb to multicast userspace listeners + * + * This function doesn't consume an skb as might be expected since it has to + * copy it anyways. + */ +static void kauditd_send_multicast_skb(struct sk_buff *skb) +{ + struct sk_buff *copy; + struct audit_net *aunet = net_generic(&init_net, audit_net_id); + struct sock *sock = aunet->nlsk; + + /* + * The seemingly wasteful skb_copy() rather than bumping the refcount + * using skb_get() is necessary because non-standard mods are made to + * the skb by the original kaudit unicast socket send routine. The + * existing auditd daemon assumes this breakage. Fixing this would + * require co-ordinating a change in the established protocol between + * the kaudit kernel subsystem and the auditd userspace code. There is + * no reason for new multicast clients to continue with this + * non-compliance. + */ + copy = skb_copy(skb, GFP_KERNEL); + if (!copy) + return; + + nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); +} + /* * flush_hold_queue - empty the hold queue if auditd appears * @@ -1090,6 +1119,8 @@ static int __net_init audit_net_init(struct net *net) struct netlink_kernel_cfg cfg = { .input = audit_receive, .bind = audit_bind, + .flags = NL_CFG_F_NONROOT_RECV, + .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); @@ -1911,10 +1942,10 @@ out: * audit_log_end - end one audit record * @ab: the audit_buffer * - * The netlink_* functions cannot be called inside an irq context, so - * the audit buffer is placed on a queue and a tasklet is scheduled to - * remove them from the queue outside the irq context. May be called in - * any context. + * netlink_unicast() cannot be called inside an irq context because it blocks + * (last arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed + * on a queue and a tasklet is scheduled to remove them from the queue outside + * the irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { @@ -1924,6 +1955,18 @@ void audit_log_end(struct audit_buffer *ab) audit_log_lost("rate limit exceeded"); } else { struct nlmsghdr *nlh = nlmsg_hdr(ab->skb); + + kauditd_send_multicast_skb(ab->skb); + + /* + * The original kaudit unicast socket sends up messages with + * nlmsg_len set to the payload length rather than the entire + * message length. This breaks the standard set by netlink. + * The existing auditd daemon assumes this breakage. Fixing + * this would require co-ordinating a change in the established + * protocol between the kaudit kernel subsystem and the auditd + * userspace code. + */ nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN; if (audit_pid) { -- cgit v1.2.3 From 7f74ecd788a8b2a122d4d8bdc4d517cc60b8b638 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 22 Apr 2014 21:31:58 -0400 Subject: audit: send multicast messages only if there are listeners Test first to see if there are any userspace multicast listeners bound to the socket before starting the multicast send work. Signed-off-by: Richard Guy Briggs Signed-off-by: David S. Miller --- kernel/audit.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index d272cc11dff4..33531d72e4a2 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -435,6 +435,9 @@ static void kauditd_send_multicast_skb(struct sk_buff *skb) struct audit_net *aunet = net_generic(&init_net, audit_net_id); struct sock *sock = aunet->nlsk; + if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) + return; + /* * The seemingly wasteful skb_copy() rather than bumping the refcount * using skb_get() is necessary because non-standard mods are made to -- cgit v1.2.3 From 122ff243f5f104194750ecbc76d5946dd1eec934 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 12 May 2014 16:04:53 -0700 Subject: ipv4: make ip_local_reserved_ports per netns ip_local_port_range is already per netns, so should ip_local_reserved_ports be. And since it is none by default we don't actually need it when we don't enable CONFIG_SYSCTL. By the way, rename inet_is_reserved_local_port() to inet_is_local_reserved_port() Cc: "David S. Miller" Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- kernel/sysctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 74f5b580fe34..e36ae4b15726 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2501,11 +2501,11 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, bool first = 1; size_t left = *lenp; unsigned long bitmap_len = table->maxlen; - unsigned long *bitmap = (unsigned long *) table->data; + unsigned long *bitmap = *(unsigned long **) table->data; unsigned long *tmp_bitmap = NULL; char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c; - if (!bitmap_len || !left || (*ppos && !write)) { + if (!bitmap || !bitmap_len || !left || (*ppos && !write)) { *lenp = 0; return 0; } -- cgit v1.2.3 From 8f577cadf7181243d336be9aba40c1bcc02c4c54 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 13 May 2014 19:50:47 -0700 Subject: seccomp: JIT compile seccomp filter Take advantage of internal BPF JIT 05-sim-long_jumps.c of libseccomp was used as micro-benchmark: seccomp_rule_add_exact(ctx,... seccomp_rule_add_exact(ctx,... rc = seccomp_load(ctx); for (i = 0; i < 10000000; i++) syscall(...); $ sudo sysctl net.core.bpf_jit_enable=1 $ time ./bench real 0m2.769s user 0m1.136s sys 0m1.624s $ sudo sysctl net.core.bpf_jit_enable=0 $ time ./bench real 0m5.825s user 0m1.268s sys 0m4.548s Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/seccomp.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index b35c21503a36..7e02d624cc50 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -54,8 +54,7 @@ struct seccomp_filter { atomic_t usage; struct seccomp_filter *prev; - unsigned short len; /* Instruction count */ - struct sock_filter_int insnsi[]; + struct sk_filter *prog; }; /* Limit any path through the tree to 256KB worth of instructions. */ @@ -189,7 +188,8 @@ static u32 seccomp_run_filters(int syscall) * value always takes priority (ignoring the DATA). */ for (f = current->seccomp.filter; f; f = f->prev) { - u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi); + u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd); + if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; } @@ -215,7 +215,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) return -EINVAL; for (filter = current->seccomp.filter; filter; filter = filter->prev) - total_insns += filter->len + 4; /* include a 4 instr penalty */ + total_insns += filter->prog->len + 4; /* include a 4 instr penalty */ if (total_insns > MAX_INSNS_PER_PATH) return -ENOMEM; @@ -256,19 +256,27 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) /* Allocate a new seccomp_filter */ ret = -ENOMEM; - filter = kzalloc(sizeof(struct seccomp_filter) + - sizeof(struct sock_filter_int) * new_len, + filter = kzalloc(sizeof(struct seccomp_filter), GFP_KERNEL|__GFP_NOWARN); if (!filter) goto free_prog; - ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len); - if (ret) + filter->prog = kzalloc(sk_filter_size(new_len), + GFP_KERNEL|__GFP_NOWARN); + if (!filter->prog) goto free_filter; + + ret = sk_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); + if (ret) + goto free_filter_prog; kfree(fp); atomic_set(&filter->usage, 1); - filter->len = new_len; + filter->prog->len = new_len; + filter->prog->bpf_func = (void *)sk_run_filter_int_seccomp; + + /* JIT internal BPF into native HW instructions */ + bpf_int_jit_compile(filter->prog); /* * If there is an existing filter, make it the prev and don't drop its @@ -278,6 +286,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) current->seccomp.filter = filter; return 0; +free_filter_prog: + kfree(filter->prog); free_filter: kfree(filter); free_prog: @@ -330,6 +340,7 @@ void put_seccomp_filter(struct task_struct *tsk) while (orig && atomic_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; orig = orig->prev; + bpf_jit_free(freeme->prog); kfree(freeme); } } -- cgit v1.2.3 From 5fe821a9dee241fa450703ab7015d970ee0cfb8d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 19 May 2014 14:56:14 -0700 Subject: net: filter: cleanup invocation of internal BPF Kernel API for classic BPF socket filters is: sk_unattached_filter_create() - validate classic BPF, convert, JIT SK_RUN_FILTER() - run it sk_unattached_filter_destroy() - destroy socket filter Cleanup internal BPF kernel API as following: sk_filter_select_runtime() - final step of internal BPF creation. Try to JIT internal BPF program, if JIT is not available select interpreter SK_RUN_FILTER() - run it sk_filter_free() - free internal BPF program Disallow direct calls to BPF interpreter. Execution of the BPF program should be done with SK_RUN_FILTER() macro. Example of internal BPF create, run, destroy: struct sk_filter *fp; fp = kzalloc(sk_filter_size(prog_len), GFP_KERNEL); memcpy(fp->insni, prog, prog_len * sizeof(fp->insni[0])); fp->len = prog_len; sk_filter_select_runtime(fp); SK_RUN_FILTER(fp, ctx); sk_filter_free(fp); Sockets, seccomp, testsuite, tracing are using different ways to populate sk_filter, so first steps of program creation are not common. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/seccomp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 7e02d624cc50..1036b6f2fded 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -273,10 +273,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) atomic_set(&filter->usage, 1); filter->prog->len = new_len; - filter->prog->bpf_func = (void *)sk_run_filter_int_seccomp; - /* JIT internal BPF into native HW instructions */ - bpf_int_jit_compile(filter->prog); + sk_filter_select_runtime(filter->prog); /* * If there is an existing filter, make it the prev and don't drop its @@ -340,7 +338,7 @@ void put_seccomp_filter(struct task_struct *tsk) while (orig && atomic_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; orig = orig->prev; - bpf_jit_free(freeme->prog); + sk_filter_free(freeme->prog); kfree(freeme); } } -- cgit v1.2.3 From 3480593131e0b781287dae0139bf7ccee7cba7ff Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 May 2014 10:22:50 +0200 Subject: net: filter: get rid of BPF_S_* enum This patch finally allows us to get rid of the BPF_S_* enum. Currently, the code performs unnecessary encode and decode workarounds in seccomp and filter migration itself when a filter is being attached in order to overcome BPF_S_* encoding which is not used anymore by the new interpreter resp. JIT compilers. Keeping it around would mean that also in future we would need to extend and maintain this enum and related encoders/decoders. We can get rid of all that and save us these operations during filter attaching. Naturally, also JIT compilers need to be updated by this. Before JIT conversion is being done, each compiler checks if A is being loaded at startup to obtain information if it needs to emit instructions to clear A first. Since BPF extensions are a subset of BPF_LD | BPF_{W,H,B} | BPF_ABS variants, case statements for extensions can be removed at that point. To ease and minimalize code changes in the classic JITs, we have introduced bpf_anc_helper(). Tested with test_bpf on x86_64 (JIT, int), s390x (JIT, int), arm (JIT, int), i368 (int), ppc64 (JIT, int); for sparc we unfortunately didn't have access, but changes are analogous to the rest. Joint work with Alexei Starovoitov. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Benjamin Herrenschmidt Cc: Martin Schwidefsky Cc: Mircea Gherzan Cc: Kees Cook Acked-by: Chema Gonzalez Signed-off-by: David S. Miller --- kernel/seccomp.c | 83 ++++++++++++++++++++++++++++---------------------------- 1 file changed, 41 insertions(+), 42 deletions(-) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 1036b6f2fded..44e69483b383 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -103,60 +103,59 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) u32 k = ftest->k; switch (code) { - case BPF_S_LD_W_ABS: + case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; - case BPF_S_LD_W_LEN: + case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; - case BPF_S_LDX_W_LEN: + case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ - case BPF_S_RET_K: - case BPF_S_RET_A: - case BPF_S_ALU_ADD_K: - case BPF_S_ALU_ADD_X: - case BPF_S_ALU_SUB_K: - case BPF_S_ALU_SUB_X: - case BPF_S_ALU_MUL_K: - case BPF_S_ALU_MUL_X: - case BPF_S_ALU_DIV_X: - case BPF_S_ALU_AND_K: - case BPF_S_ALU_AND_X: - case BPF_S_ALU_OR_K: - case BPF_S_ALU_OR_X: - case BPF_S_ALU_XOR_K: - case BPF_S_ALU_XOR_X: - case BPF_S_ALU_LSH_K: - case BPF_S_ALU_LSH_X: - case BPF_S_ALU_RSH_K: - case BPF_S_ALU_RSH_X: - case BPF_S_ALU_NEG: - case BPF_S_LD_IMM: - case BPF_S_LDX_IMM: - case BPF_S_MISC_TAX: - case BPF_S_MISC_TXA: - case BPF_S_ALU_DIV_K: - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: - case BPF_S_ST: - case BPF_S_STX: - case BPF_S_JMP_JA: - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_K: - case BPF_S_JMP_JSET_X: - sk_decode_filter(ftest, ftest); + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + case BPF_MISC | BPF_TAX: + case BPF_MISC | BPF_TXA: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; -- cgit v1.2.3