3769229931
Michal Sekletar added in commit ea02f9411d ("net: introduce
SO_BPF_EXTENSIONS") a facility where user space can enquire
the BPF ancillary instruction set, which is imho a step into
the right direction for letting user space high-level to BPF
optimizers make an informed decision for possibly using these
extensions.
The original rationale was to return through a getsockopt(2)
a bitfield of which instructions are supported and which
are not, as of right now, we just return 0 to indicate a
base support for SKF_AD_PROTOCOL up to SKF_AD_PAY_OFFSET.
Limitations of this approach are that this API which we need
to maintain for a long time can only support a maximum of 32
extensions, and needs to be additionally maintained/updated
when each new extension that comes in.
I thought about this a bit more and what we can do here to
overcome this is to just return SKF_AD_MAX. Since we never
remove any extension since we cannot break user space and
always linearly increase SKF_AD_MAX on each newly added
extension, user space can make a decision on what extensions
are supported in the whole set of extensions and which aren't,
by just checking which of them from the whole set have an
offset < SKF_AD_MAX of the underlying kernel.
Since SKF_AD_MAX must be updated each time we add new ones,
we don't need to introduce an additional enum and got
maintenance for free. At some point in time when
SO_BPF_EXTENSIONS becomes ubiquitous for most kernels, then
an application can simply make use of this and easily be run
on newer or older underlying kernels without needing to be
recompiled, of course. Since that is for 3.14, it's not too
late to do this change.
Cc: Michal Sekletar <msekleta@redhat.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Michal Sekletar <msekleta@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
160 lines
3.6 KiB
C
160 lines
3.6 KiB
C
/*
|
|
* Linux Socket Filter Data Structures
|
|
*/
|
|
#ifndef __LINUX_FILTER_H__
|
|
#define __LINUX_FILTER_H__
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/compat.h>
|
|
#include <linux/workqueue.h>
|
|
#include <uapi/linux/filter.h>
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
/*
|
|
* A struct sock_filter is architecture independent.
|
|
*/
|
|
struct compat_sock_fprog {
|
|
u16 len;
|
|
compat_uptr_t filter; /* struct sock_filter * */
|
|
};
|
|
#endif
|
|
|
|
struct sk_buff;
|
|
struct sock;
|
|
|
|
struct sk_filter
|
|
{
|
|
atomic_t refcnt;
|
|
unsigned int len; /* Number of filter blocks */
|
|
struct rcu_head rcu;
|
|
unsigned int (*bpf_func)(const struct sk_buff *skb,
|
|
const struct sock_filter *filter);
|
|
union {
|
|
struct sock_filter insns[0];
|
|
struct work_struct work;
|
|
};
|
|
};
|
|
|
|
static inline unsigned int sk_filter_size(unsigned int proglen)
|
|
{
|
|
return max(sizeof(struct sk_filter),
|
|
offsetof(struct sk_filter, insns[proglen]));
|
|
}
|
|
|
|
extern int sk_filter(struct sock *sk, struct sk_buff *skb);
|
|
extern unsigned int sk_run_filter(const struct sk_buff *skb,
|
|
const struct sock_filter *filter);
|
|
extern int sk_unattached_filter_create(struct sk_filter **pfp,
|
|
struct sock_fprog *fprog);
|
|
extern void sk_unattached_filter_destroy(struct sk_filter *fp);
|
|
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
|
|
extern int sk_detach_filter(struct sock *sk);
|
|
extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
|
|
extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
|
|
extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
|
|
|
|
#ifdef CONFIG_BPF_JIT
|
|
#include <stdarg.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/printk.h>
|
|
|
|
extern void bpf_jit_compile(struct sk_filter *fp);
|
|
extern void bpf_jit_free(struct sk_filter *fp);
|
|
|
|
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
|
|
u32 pass, void *image)
|
|
{
|
|
pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
|
|
flen, proglen, pass, image);
|
|
if (image)
|
|
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
|
|
16, 1, image, proglen, false);
|
|
}
|
|
#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
|
|
#else
|
|
#include <linux/slab.h>
|
|
static inline void bpf_jit_compile(struct sk_filter *fp)
|
|
{
|
|
}
|
|
static inline void bpf_jit_free(struct sk_filter *fp)
|
|
{
|
|
kfree(fp);
|
|
}
|
|
#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
|
|
#endif
|
|
|
|
static inline int bpf_tell_extensions(void)
|
|
{
|
|
return SKF_AD_MAX;
|
|
}
|
|
|
|
enum {
|
|
BPF_S_RET_K = 1,
|
|
BPF_S_RET_A,
|
|
BPF_S_ALU_ADD_K,
|
|
BPF_S_ALU_ADD_X,
|
|
BPF_S_ALU_SUB_K,
|
|
BPF_S_ALU_SUB_X,
|
|
BPF_S_ALU_MUL_K,
|
|
BPF_S_ALU_MUL_X,
|
|
BPF_S_ALU_DIV_X,
|
|
BPF_S_ALU_MOD_K,
|
|
BPF_S_ALU_MOD_X,
|
|
BPF_S_ALU_AND_K,
|
|
BPF_S_ALU_AND_X,
|
|
BPF_S_ALU_OR_K,
|
|
BPF_S_ALU_OR_X,
|
|
BPF_S_ALU_XOR_K,
|
|
BPF_S_ALU_XOR_X,
|
|
BPF_S_ALU_LSH_K,
|
|
BPF_S_ALU_LSH_X,
|
|
BPF_S_ALU_RSH_K,
|
|
BPF_S_ALU_RSH_X,
|
|
BPF_S_ALU_NEG,
|
|
BPF_S_LD_W_ABS,
|
|
BPF_S_LD_H_ABS,
|
|
BPF_S_LD_B_ABS,
|
|
BPF_S_LD_W_LEN,
|
|
BPF_S_LD_W_IND,
|
|
BPF_S_LD_H_IND,
|
|
BPF_S_LD_B_IND,
|
|
BPF_S_LD_IMM,
|
|
BPF_S_LDX_W_LEN,
|
|
BPF_S_LDX_B_MSH,
|
|
BPF_S_LDX_IMM,
|
|
BPF_S_MISC_TAX,
|
|
BPF_S_MISC_TXA,
|
|
BPF_S_ALU_DIV_K,
|
|
BPF_S_LD_MEM,
|
|
BPF_S_LDX_MEM,
|
|
BPF_S_ST,
|
|
BPF_S_STX,
|
|
BPF_S_JMP_JA,
|
|
BPF_S_JMP_JEQ_K,
|
|
BPF_S_JMP_JEQ_X,
|
|
BPF_S_JMP_JGE_K,
|
|
BPF_S_JMP_JGE_X,
|
|
BPF_S_JMP_JGT_K,
|
|
BPF_S_JMP_JGT_X,
|
|
BPF_S_JMP_JSET_K,
|
|
BPF_S_JMP_JSET_X,
|
|
/* Ancillary data */
|
|
BPF_S_ANC_PROTOCOL,
|
|
BPF_S_ANC_PKTTYPE,
|
|
BPF_S_ANC_IFINDEX,
|
|
BPF_S_ANC_NLATTR,
|
|
BPF_S_ANC_NLATTR_NEST,
|
|
BPF_S_ANC_MARK,
|
|
BPF_S_ANC_QUEUE,
|
|
BPF_S_ANC_HATYPE,
|
|
BPF_S_ANC_RXHASH,
|
|
BPF_S_ANC_CPU,
|
|
BPF_S_ANC_ALU_XOR_X,
|
|
BPF_S_ANC_SECCOMP_LD_W,
|
|
BPF_S_ANC_VLAN_TAG,
|
|
BPF_S_ANC_VLAN_TAG_PRESENT,
|
|
BPF_S_ANC_PAY_OFFSET,
|
|
};
|
|
|
|
#endif /* __LINUX_FILTER_H__ */
|