[PATCH v9 net-next 2/3] seccomp: convert seccomp to use extended BPF
use sk_convert_filter() to convert seccomp BPF into extended BPF
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 < 1000; i++)
syscall(199, 100);
'short filter' has 2 rules
'large filter' has 200 rules
'short filter' performance is slightly better on x86_64,i386,arm32
'large filter' is much faster on x86_64 and i386
and shows no difference on arm32
--x86_64-- short filter
old BPF: 2.7 sec
39.12% bench libc-2.15.so [.] syscall
8.10% bench [kernel.kallsyms] [k] sk_run_filter
6.31% bench [kernel.kallsyms] [k] system_call
5.59% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller
4.37% bench [kernel.kallsyms] [k] trace_hardirqs_off_caller
3.70% bench [kernel.kallsyms] [k] __secure_computing
3.67% bench [kernel.kallsyms] [k] lock_is_held
3.03% bench [kernel.kallsyms] [k] seccomp_bpf_load
new BPF: 2.58 sec
42.05% bench libc-2.15.so [.] syscall
6.91% bench [kernel.kallsyms] [k] system_call
6.25% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller
6.07% bench [kernel.kallsyms] [k] __secure_computing
5.08% bench [kernel.kallsyms] [k] sk_run_filter_ext
--arm32-- short filter
old BPF: 4.0 sec
39.92% bench [kernel.kallsyms] [k] vector_swi
16.60% bench [kernel.kallsyms] [k] sk_run_filter
14.66% bench libc-2.17.so [.] syscall
5.42% bench [kernel.kallsyms] [k] seccomp_bpf_load
5.10% bench [kernel.kallsyms] [k] __secure_computing
new BPF: 3.7 sec
35.93% bench [kernel.kallsyms] [k] vector_swi
21.89% bench libc-2.17.so [.] syscall
13.45% bench [kernel.kallsyms] [k] sk_run_filter_ext
6.25% bench [kernel.kallsyms] [k] __secure_computing
3.96% bench [kernel.kallsyms] [k] syscall_trace_exit
--x86_64-- large filter
old BPF: 8.6 seconds
73.38%bench [kernel.kallsyms] [k] sk_run_filter
10.70%bench libc-2.15.so [.] syscall
5.09%bench [kernel.kallsyms] [k] seccomp_bpf_load
1.97%bench [kernel.kallsyms] [k] system_call
ext BPF: 5.7 seconds
66.20%bench [kernel.kallsyms] [k] sk_run_filter_ext
16.75%bench libc-2.15.so [.] syscall
3.31%bench [kernel.kallsyms] [k] system_call
2.88%bench [kernel.kallsyms] [k] __secure_computing
--i386-- large filter
old BPF: 5.4 sec
ext BPF: 3.8 sec
--arm32-- large filter
old BPF: 13.5 sec
73.88% bench [kernel.kallsyms] [k] sk_run_filter
10.29% bench [kernel.kallsyms] [k] vector_swi
6.46% bench libc-2.17.so [.] syscall
2.94% bench [kernel.kallsyms] [k] seccomp_bpf_load
1.19% bench [kernel.kallsyms] [k] __secure_computing
0.87% bench [kernel.kallsyms] [k] sys_getuid
new BPF: 13.5 sec
76.08% bench [kernel.kallsyms] [k] sk_run_filter_ext
10.98% bench [kernel.kallsyms] [k] vector_swi
5.87% bench libc-2.17.so [.] syscall
1.77% bench [kernel.kallsyms] [k] __secure_computing
0.93% bench [kernel.kallsyms] [k] sys_getuid
BPF filters generated by seccomp are very branchy, so ext BPF
performance is better than old BPF.
Performance gains will be even higher when extended BPF JIT
is committed.
Signed-off-by: Alexei Starovoitov
Reviewed-by: Kees Cook
---
include/linux/seccomp.h |1 -
kernel/seccomp.c| 118 ++-
net/core/filter.c |5 --
3 files changed, 56 insertions(+), 68 deletions(-)
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd1840e..4054b0994071 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -76,7 +76,6 @@ static inline int seccomp_mode(struct seccomp *s)
#ifdef CONFIG_SECCOMP_FILTER
extern void put_seccomp_filter(struct task_struct *tsk);
extern void get_seccomp_filter(struct task_struct *tsk);
-extern u32 seccomp_bpf_load(int off);
#else /* CONFIG_SECCOMP_FILTER */
static inline void put_seccomp_filter(struct task_struct *tsk)
{
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a10048a32c..9bd265eaad05 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,31 @@ struct seccomp_filter {
atomic_t usage;
struct seccomp_filter *prev;
unsigned short len; /* Instruction count */
- struct sock_filter insns[];
+ struct sock_filter_ext insns[];
};
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long. If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
+/*
* Endianness is explicitly
[PATCH v9 net-next 2/3] seccomp: convert seccomp to use extended BPF
use sk_convert_filter() to convert seccomp BPF into extended BPF
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 1000; i++)
syscall(199, 100);
'short filter' has 2 rules
'large filter' has 200 rules
'short filter' performance is slightly better on x86_64,i386,arm32
'large filter' is much faster on x86_64 and i386
and shows no difference on arm32
--x86_64-- short filter
old BPF: 2.7 sec
39.12% bench libc-2.15.so [.] syscall
8.10% bench [kernel.kallsyms] [k] sk_run_filter
6.31% bench [kernel.kallsyms] [k] system_call
5.59% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller
4.37% bench [kernel.kallsyms] [k] trace_hardirqs_off_caller
3.70% bench [kernel.kallsyms] [k] __secure_computing
3.67% bench [kernel.kallsyms] [k] lock_is_held
3.03% bench [kernel.kallsyms] [k] seccomp_bpf_load
new BPF: 2.58 sec
42.05% bench libc-2.15.so [.] syscall
6.91% bench [kernel.kallsyms] [k] system_call
6.25% bench [kernel.kallsyms] [k] trace_hardirqs_on_caller
6.07% bench [kernel.kallsyms] [k] __secure_computing
5.08% bench [kernel.kallsyms] [k] sk_run_filter_ext
--arm32-- short filter
old BPF: 4.0 sec
39.92% bench [kernel.kallsyms] [k] vector_swi
16.60% bench [kernel.kallsyms] [k] sk_run_filter
14.66% bench libc-2.17.so [.] syscall
5.42% bench [kernel.kallsyms] [k] seccomp_bpf_load
5.10% bench [kernel.kallsyms] [k] __secure_computing
new BPF: 3.7 sec
35.93% bench [kernel.kallsyms] [k] vector_swi
21.89% bench libc-2.17.so [.] syscall
13.45% bench [kernel.kallsyms] [k] sk_run_filter_ext
6.25% bench [kernel.kallsyms] [k] __secure_computing
3.96% bench [kernel.kallsyms] [k] syscall_trace_exit
--x86_64-- large filter
old BPF: 8.6 seconds
73.38%bench [kernel.kallsyms] [k] sk_run_filter
10.70%bench libc-2.15.so [.] syscall
5.09%bench [kernel.kallsyms] [k] seccomp_bpf_load
1.97%bench [kernel.kallsyms] [k] system_call
ext BPF: 5.7 seconds
66.20%bench [kernel.kallsyms] [k] sk_run_filter_ext
16.75%bench libc-2.15.so [.] syscall
3.31%bench [kernel.kallsyms] [k] system_call
2.88%bench [kernel.kallsyms] [k] __secure_computing
--i386-- large filter
old BPF: 5.4 sec
ext BPF: 3.8 sec
--arm32-- large filter
old BPF: 13.5 sec
73.88% bench [kernel.kallsyms] [k] sk_run_filter
10.29% bench [kernel.kallsyms] [k] vector_swi
6.46% bench libc-2.17.so [.] syscall
2.94% bench [kernel.kallsyms] [k] seccomp_bpf_load
1.19% bench [kernel.kallsyms] [k] __secure_computing
0.87% bench [kernel.kallsyms] [k] sys_getuid
new BPF: 13.5 sec
76.08% bench [kernel.kallsyms] [k] sk_run_filter_ext
10.98% bench [kernel.kallsyms] [k] vector_swi
5.87% bench libc-2.17.so [.] syscall
1.77% bench [kernel.kallsyms] [k] __secure_computing
0.93% bench [kernel.kallsyms] [k] sys_getuid
BPF filters generated by seccomp are very branchy, so ext BPF
performance is better than old BPF.
Performance gains will be even higher when extended BPF JIT
is committed.
Signed-off-by: Alexei Starovoitov a...@plumgrid.com
Reviewed-by: Kees Cook keesc...@chromium.org
---
include/linux/seccomp.h |1 -
kernel/seccomp.c| 118 ++-
net/core/filter.c |5 --
3 files changed, 56 insertions(+), 68 deletions(-)
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd1840e..4054b0994071 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -76,7 +76,6 @@ static inline int seccomp_mode(struct seccomp *s)
#ifdef CONFIG_SECCOMP_FILTER
extern void put_seccomp_filter(struct task_struct *tsk);
extern void get_seccomp_filter(struct task_struct *tsk);
-extern u32 seccomp_bpf_load(int off);
#else /* CONFIG_SECCOMP_FILTER */
static inline void put_seccomp_filter(struct task_struct *tsk)
{
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a10048a32c..9bd265eaad05 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,31 @@ struct seccomp_filter {
atomic_t usage;
struct seccomp_filter *prev;
unsigned short len; /* Instruction count */
- struct sock_filter insns[];
+ struct sock_filter_ext insns[];
};
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 18) / sizeof(struct sock_filter))
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long. If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
