[PATCH V2 1/3] seccomp: add generic code for jitted seccomp filters.

From: Nicolas Schichan
Date: Mon Mar 18 2013 - 10:51:13 EST


Architecture must select HAVE_SECCOMP_FILTER_JIT and implement
seccomp_jit_compile() and seccomp_jit_free() if they intend to support
jitted seccomp filters.

struct seccomp_filter has been moved to <linux/seccomp.h> to make its
content available to the jit compilation code.

In a way similar to the net BPF, the jit compilation code is expected
to updates struct seccomp_filter.bpf_func pointer to the generated
code.

Signed-off-by: Nicolas Schichan <nschichan@xxxxxxxxxx>
---
arch/Kconfig | 14 ++++++++++++++
include/linux/seccomp.h | 41 +++++++++++++++++++++++++++++++++++++++++
kernel/seccomp.c | 34 +++++-----------------------------
3 files changed, 60 insertions(+), 29 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 5a1779c..1284367 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -339,6 +339,10 @@ 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
@@ -349,6 +353,16 @@ 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
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd..a216ab7 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -6,6 +6,7 @@
#ifdef CONFIG_SECCOMP

#include <linux/thread_info.h>
+#include <linux/filter.h>
#include <asm/seccomp.h>

struct seccomp_filter;
@@ -47,6 +48,46 @@ static inline int seccomp_mode(struct seccomp *s)
return s->mode;
}

+/**
+ * struct seccomp_filter - container for seccomp BPF programs
+ *
+ * @usage: reference count to manage the object lifetime.
+ * get/put helpers should be used when accessing an instance
+ * outside of a lifetime-guarded section. In general, this
+ * is only needed for handling filters shared across tasks.
+ * @prev: points to a previously installed, or inherited, filter
+ * @len: the number of instructions in the program
+ * @bpc_func: points to either sk_run_filter or the code generated
+ * by the BPF JIT.
+ * @insns: the BPF program instructions to evaluate
+ *
+ * seccomp_filter objects are organized in a tree linked via the @prev
+ * pointer. For any task, it appears to be a singly-linked list starting
+ * with current->seccomp.filter, the most recently attached or inherited filter.
+ * However, multiple filters may share a @prev node, by way of fork(), which
+ * results in a unidirectional tree existing in memory. This is similar to
+ * how namespaces work.
+ *
+ * seccomp_filter objects should never be modified after being attached
+ * to a task_struct (other than @usage).
+ */
+struct seccomp_filter {
+ atomic_t usage;
+ struct seccomp_filter *prev;
+ unsigned short len; /* Instruction count */
+ unsigned int (*bpf_func)(const struct sk_buff *skb,
+ const struct sock_filter *filter);
+ struct sock_filter insns[];
+};
+
+#ifdef CONFIG_SECCOMP_FILTER_JIT
+extern void seccomp_jit_compile(struct seccomp_filter *fp);
+extern void seccomp_jit_free(struct seccomp_filter *fp);
+#else
+static inline void seccomp_jit_compile(struct seccomp_filter *fp) { }
+static inline void seccomp_jit_free(struct seccomp_filter *fp) { }
+#endif
+
#else /* CONFIG_SECCOMP */

#include <linux/errno.h>
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a1004..a1aadaa 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -30,34 +30,6 @@
#include <linux/tracehook.h>
#include <linux/uaccess.h>

-/**
- * struct seccomp_filter - container for seccomp BPF programs
- *
- * @usage: reference count to manage the object lifetime.
- * get/put helpers should be used when accessing an instance
- * outside of a lifetime-guarded section. In general, this
- * is only needed for handling filters shared across tasks.
- * @prev: points to a previously installed, or inherited, filter
- * @len: the number of instructions in the program
- * @insns: the BPF program instructions to evaluate
- *
- * seccomp_filter objects are organized in a tree linked via the @prev
- * pointer. For any task, it appears to be a singly-linked list starting
- * with current->seccomp.filter, the most recently attached or inherited filter.
- * However, multiple filters may share a @prev node, by way of fork(), which
- * results in a unidirectional tree existing in memory. This is similar to
- * how namespaces work.
- *
- * seccomp_filter objects should never be modified after being attached
- * to a task_struct (other than @usage).
- */
-struct seccomp_filter {
- atomic_t usage;
- struct seccomp_filter *prev;
- unsigned short len; /* Instruction count */
- struct sock_filter insns[];
-};
-
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))

@@ -213,7 +185,7 @@ 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(NULL, f->insns);
+ u32 cur_ret = f->bpf_func(NULL, f->insns);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
ret = cur_ret;
}
@@ -275,6 +247,9 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
if (ret)
goto fail;

+ filter->bpf_func = sk_run_filter;
+ seccomp_jit_compile(filter);
+
/*
* If there is an existing filter, make it the prev and don't drop its
* task reference.
@@ -332,6 +307,7 @@ void put_seccomp_filter(struct task_struct *tsk)
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
orig = orig->prev;
+ seccomp_jit_free(freeme);
kfree(freeme);
}
}
--
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/