netdev - [patch V2 09/20] bpf: Use bpf_prog_run_pin_on

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 20 Feb 2020 21:45:26 +0100
From:   Thomas Gleixner <tglx@...utronix.de>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     David Miller <davem@...emloft.net>, bpf@...r.kernel.org,
        netdev@...r.kernel.org, Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Sebastian Sewior <bigeasy@...utronix.de>,
        Peter Zijlstra <peterz@...radead.org>,
        Clark Williams <williams@...hat.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Ingo Molnar <mingo@...nel.org>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Vinicius Costa Gomes <vinicius.gomes@...el.com>,
        Jakub Kicinski <kuba@...nel.org>
Subject: [patch V2 09/20] bpf: Use bpf_prog_run_pin_on_cpu() at simple call sites.

From: David Miller <davem@...emloft.net>

All of these cases are strictly of the form:

	preempt_disable();
	BPF_PROG_RUN(...);
	preempt_enable();

Replace this with bpf_prog_run_pin_on_cpu() which wraps BPF_PROG_RUN()
with:

	migrate_disable();
	BPF_PROG_RUN(...);
	migrate_enable();

On non RT enabled kernels this maps to preempt_disable/enable() and on RT
enabled kernels this solely prevents migration, which is sufficient as
there is no requirement to prevent reentrancy to any BPF program from a
preempting task. The only requirement is that the program stays on the same
CPU.

The seccomp loop does not need protection over the loop. It only needs
protection per BPF filter program

Therefore, this is a trivially correct transformation.

[ tglx: Converted to bpf_prog_run_pin_on_cpu() ]

Signed-off-by: David S. Miller <davem@...emloft.net>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
V2: No change. Amended changelog vs. seccomp
---
 include/linux/filter.h    |    4 +---
 kernel/seccomp.c          |    4 +---
 net/core/flow_dissector.c |    4 +---
 net/core/skmsg.c          |    8 ++------
 net/kcm/kcmsock.c         |    4 +---
 5 files changed, 6 insertions(+), 18 deletions(-)

--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -717,9 +717,7 @@ static inline u32 bpf_prog_run_clear_cb(
 	if (unlikely(prog->cb_access))
 		memset(cb_data, 0, BPF_SKB_CB_LEN);
 
-	preempt_disable();
-	res = BPF_PROG_RUN(prog, skb);
-	preempt_enable();
+	res = bpf_prog_run_pin_on_cpu(prog, skb);
 	return res;
 }
 
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -268,16 +268,14 @@ static u32 seccomp_run_filters(const str
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
-	preempt_disable();
 	for (; f; f = f->prev) {
-		u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
+		u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd);
 
 		if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
 			ret = cur_ret;
 			*match = f;
 		}
 	}
-	preempt_enable();
 	return ret;
 }
 #endif /* CONFIG_SECCOMP_FILTER */
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -920,9 +920,7 @@ bool bpf_flow_dissect(struct bpf_prog *p
 		     (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP);
 	flow_keys->flags = flags;
 
-	preempt_disable();
-	result = BPF_PROG_RUN(prog, ctx);
-	preempt_enable();
+	result = bpf_prog_run_pin_on_cpu(prog, ctx);
 
 	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -628,7 +628,6 @@ int sk_psock_msg_verdict(struct sock *sk
 	struct bpf_prog *prog;
 	int ret;
 
-	preempt_disable();
 	rcu_read_lock();
 	prog = READ_ONCE(psock->progs.msg_parser);
 	if (unlikely(!prog)) {
@@ -638,7 +637,7 @@ int sk_psock_msg_verdict(struct sock *sk
 
 	sk_msg_compute_data_pointers(msg);
 	msg->sk = sk;
-	ret = BPF_PROG_RUN(prog, msg);
+	ret = bpf_prog_run_pin_on_cpu(prog, msg);
 	ret = sk_psock_map_verd(ret, msg->sk_redir);
 	psock->apply_bytes = msg->apply_bytes;
 	if (ret == __SK_REDIRECT) {
@@ -653,7 +652,6 @@ int sk_psock_msg_verdict(struct sock *sk
 	}
 out:
 	rcu_read_unlock();
-	preempt_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
@@ -665,9 +663,7 @@ static int sk_psock_bpf_run(struct sk_ps
 
 	skb->sk = psock->sk;
 	bpf_compute_data_end_sk_skb(skb);
-	preempt_disable();
-	ret = BPF_PROG_RUN(prog, skb);
-	preempt_enable();
+	ret = bpf_prog_run_pin_on_cpu(prog, skb);
 	/* strparser clones the skb before handing it to a upper layer,
 	 * meaning skb_orphan has been called. We NULL sk on the way out
 	 * to ensure we don't trigger a BUG_ON() in skb/sk operations
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -380,9 +380,7 @@ static int kcm_parse_func_strparser(stru
 	struct bpf_prog *prog = psock->bpf_prog;
 	int res;
 
-	preempt_disable();
-	res = BPF_PROG_RUN(prog, skb);
-	preempt_enable();
+	res = bpf_prog_run_pin_on_cpu(prog, skb);
 	return res;
 }