diff options
author | Nicolas Schichan <nschichan@freebox.fr> | 2013-05-10 09:58:01 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2013-05-10 12:59:01 +1000 |
commit | ca01d7dc4d427cc791f3f77f4a06c1623475d293 (patch) | |
tree | 01d52cb8615b3c3130c572c8ee424055850c469b /arch | |
parent | e4390676c9078024fef2bb54724c0d95b206f795 (diff) |
seccomp: add generic code for jitted seccomp filters.
This patchset adds support for jitted seccomp BPF filters, with the
required modifications to make it work on the ARM architecture.
- The first patch in the serie adds the required boiler plate in the
core kernel seccomp code to invoke the JIT compilation/free code.
- The second patch reworks the ARM BPF JIT code to make the generation
process less dependent on struct sk_filter.
- The last patch actually implements the ARM part in the BPF jit code.
Some benchmarks, on a 1.6Ghz 88f6282 CPU:
Each system call is tested in two way (fast/slow):
- on the fast version, the tested system call is accepted immediately
after checking the architecture (5 BPF instructions).
- on the slow version, the tested system call is accepted after
previously checking for 85 syscall (90 instructions, including the
architecture check).
The tested syscall is invoked in a loop 1000000 time, the reported
time is the time spent in the loop in seconds.
Without Seccomp JIT:
Syscall Time-Fast Time-Slow
--------------- ---------- ----------
gettimeofday 0.389 1.633
getpid 0.406 1.688
getresuid 1.003 2.266
getcwd 1.342 2.128
With Seccomp JIT:
Syscall Time-Fast Time-Slow
--------------- ----------- ---------
gettimeofday 0.348 0.428
getpid 0.365 0.480
getresuid 0.981 1.060
getcwd 1.237 1.294
For reference, the same code without any seccomp filter:
Syscall Time
--------------- -----
gettimeofday 0.119
getpid 0.137
getresuid 0.747
getcwd 1.021
The activation of the BPF JIT for seccomp is still controled with the
/proc/sys/net/core/bpf_jit_enable sysctl knob.
This patch:
Architecture must select HAVE_SECCOMP_FILTER_JIT and implement
seccomp_jit_compile() and seccomp_jit_free() if they intend to support
jitted seccomp filters.
Accessors to struct seccomp_filter fields are provided in
<linux/seccomp.h> to be used by the JIT code. With this, the 'struct
seccomp_filter' structure can stay opaque when outside kernel/seccomp.c.
In a way similar to the net BPF, the jit compilation code is expected to
updates struct seccomp_filter.bpf_func pointer (using the correct
accessor) to the generated code.
Signed-off-by: Nicolas Schichan <nschichan@freebox.fr>
Cc: Will Drewry <wad@chromium.org>
Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Nicolas Schichan <nschichan@freebox.fr>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Daniel Borkmann <daniel.borkmann@tik.ee.ethz.ch>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'arch')
-rw-r--r-- | arch/Kconfig | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 8d2ae24b9f4a..651a9e747ceb 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -332,6 +332,10 @@ config HAVE_ARCH_SECCOMP_FILTER - secure_computing return value is checked and a return value of -1 results in the system call being skipped immediately. +# Used by archs to tell that they support SECCOMP_FILTER_JIT +config HAVE_SECCOMP_FILTER_JIT + bool + config SECCOMP_FILTER def_bool y depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET @@ -342,6 +346,16 @@ config SECCOMP_FILTER See Documentation/prctl/seccomp_filter.txt for details. +config SECCOMP_FILTER_JIT + bool "enable Seccomp filter Just In Time compiler" + depends on HAVE_SECCOMP_FILTER_JIT && BPF_JIT && SECCOMP_FILTER + help + Seccomp syscall filtering capabilities are normally handled + by an interpreter. This option allows kernel to generate a native + code when filter is loaded in memory. This should speedup + syscall filtering. Note : Admin should enable this feature + changing /proc/sys/net/core/bpf_jit_enable + config HAVE_CONTEXT_TRACKING bool help |