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-next>] [day] [month] [year] [list]
Date:   Tue, 1 May 2018 17:02:19 -0700
From:   Song Liu <songliubraving@...com>
To:     <netdev@...r.kernel.org>
CC:     Song Liu <songliubraving@...com>, <kernel-team@...com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Peter Zijlstra <peterz@...radead.org>
Subject: [PATCH bpf-next 1/2] bpf: enable stackmap with build_id in nmi context

Currently, we cannot parse build_id in nmi context because of
up_read(&current->mm->mmap_sem), this makes stackmap with build_id
less useful. This patch enables parsing build_id in nmi by putting
the up_read() call in irq_work. To avoid memory allocation in nmi
context, we use per cpu variable for the irq_work. As a result, only
one irq_work per cpu is allowed. If the irq_work is in-use, we
fallback to only report ips.

Cc: Alexei Starovoitov <ast@...nel.org>
Cc: Daniel Borkmann <daniel@...earbox.net>
Cc: Peter Zijlstra <peterz@...radead.org>
Signed-off-by: Song Liu <songliubraving@...com>
---
 kernel/bpf/stackmap.c | 60 +++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 54 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 3ba102b..c33fec1 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -11,6 +11,7 @@
 #include <linux/perf_event.h>
 #include <linux/elf.h>
 #include <linux/pagemap.h>
+#include <linux/irq_work.h>
 #include "percpu_freelist.h"
 
 #define STACK_CREATE_FLAG_MASK					\
@@ -32,6 +33,23 @@ struct bpf_stack_map {
 	struct stack_map_bucket *buckets[];
 };
 
+/* irq_work to run up_read() for build_id lookup in nmi context */
+struct stack_map_irq_work {
+	struct irq_work work;
+	struct rw_semaphore *sem;
+};
+
+static void up_read_work(struct irq_work *entry)
+{
+	struct stack_map_irq_work *work = container_of(entry,
+			struct stack_map_irq_work, work);
+
+	up_read(work->sem);
+	work->sem = NULL;
+}
+
+DEFINE_PER_CPU(struct stack_map_irq_work, irq_work);
+
 static inline bool stack_map_use_build_id(struct bpf_map *map)
 {
 	return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -267,17 +285,27 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 {
 	int i;
 	struct vm_area_struct *vma;
+	bool in_nmi_ctx = in_nmi();
+	bool irq_work_busy = false;
+	struct stack_map_irq_work *work;
+
+	if (in_nmi_ctx) {
+		work = this_cpu_ptr(&irq_work);
+		if (work->sem)
+			/* cannot queue more up_read, fallback */
+			irq_work_busy = true;
+	}
 
 	/*
-	 * We cannot do up_read() in nmi context, so build_id lookup is
-	 * only supported for non-nmi events. If at some point, it is
-	 * possible to run find_vma() without taking the semaphore, we
-	 * would like to allow build_id lookup in nmi context.
+	 * We cannot do up_read() in nmi context. To do build_id lookup
+	 * in nmi context, we need to run up_read() in irq_work. We use
+	 * a percpu variable to do the irq_work. If the irq_work is
+	 * already used by another lookup, we fall back to report ips.
 	 *
 	 * Same fallback is used for kernel stack (!user) on a stackmap
 	 * with build_id.
 	 */
-	if (!user || !current || !current->mm || in_nmi() ||
+	if (!user || !current || !current->mm || irq_work_busy ||
 	    down_read_trylock(&current->mm->mmap_sem) == 0) {
 		/* cannot access current->mm, fall back to ips */
 		for (i = 0; i < trace_nr; i++) {
@@ -299,7 +327,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			- vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 	}
-	up_read(&current->mm->mmap_sem);
+
+	if (!in_nmi_ctx)
+		up_read(&current->mm->mmap_sem);
+	else {
+		work->sem = &current->mm->mmap_sem;
+		irq_work_queue(&work->work);
+	}
 }
 
 BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
@@ -575,3 +609,17 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 };
+
+static int __init stack_map_init(void)
+{
+	int cpu;
+	struct stack_map_irq_work *work;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&irq_work, cpu);
+		init_irq_work(&work->work, up_read_work);
+	}
+	pr_info("%s: done\n", __func__);
+	return 0;
+}
+subsys_initcall(stack_map_init);
-- 
2.9.5

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ