Commit 0d01da6a authored by Stanislav Fomichev's avatar Stanislav Fomichev Committed by Alexei Starovoitov

bpf: implement getsockopt and setsockopt hooks

Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.

BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before
passing them down to the kernel or bypass kernel completely.
BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that
kernel returns.
Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure.

The buffer memory is pre-allocated (because I don't think there is
a precedent for working with __user memory from bpf). This might be
slow to do for each {s,g}etsockopt call, that's why I've added
__cgroup_bpf_prog_array_is_empty that exits early if there is nothing
attached to a cgroup. Note, however, that there is a race between
__cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup
program layout might have changed; this should not be a problem
because in general there is a race between multiple calls to
{s,g}etsocktop and user adding/removing bpf progs from a cgroup.

The return code of the BPF program is handled as follows:
* 0: EPERM
* 1: success, continue with next BPF program in the cgroup chain

v9:
* allow overwriting setsockopt arguments (Alexei Starovoitov):
  * use set_fs (same as kernel_setsockopt)
  * buffer is always kzalloc'd (no small on-stack buffer)

v8:
* use s32 for optlen (Andrii Nakryiko)

v7:
* return only 0 or 1 (Alexei Starovoitov)
* always run all progs (Alexei Starovoitov)
* use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov)
  (decided to use optval=-1 instead, optval=0 might be a valid input)
* call getsockopt hook after kernel handlers (Alexei Starovoitov)

v6:
* rework cgroup chaining; stop as soon as bpf program returns
  0 or 2; see patch with the documentation for the details
* drop Andrii's and Martin's Acked-by (not sure they are comfortable
  with the new state of things)

v5:
* skip copy_to_user() and put_user() when ret == 0 (Martin Lau)

v4:
* don't export bpf_sk_fullsock helper (Martin Lau)
* size != sizeof(__u64) for uapi pointers (Martin Lau)
* offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau)

v3:
* typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko)
* reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii
  Nakryiko)
* use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau)
* use BPF_FIELD_SIZEOF() for consistency (Martin Lau)
* new CG_SOCKOPT_ACCESS macro to wrap repeated parts

v2:
* moved bpf_sockopt_kern fields around to remove a hole (Martin Lau)
* aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau)
* bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau)
* added [0,2] return code check to verifier (Martin Lau)
* dropped unused buf[64] from the stack (Martin Lau)
* use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau)
* dropped bpf_target_off from ctx rewrites (Martin Lau)
* use return code for kernel bypass (Martin Lau & Andrii Nakryiko)

Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Martin Lau <kafai@fb.com>
Signed-off-by: default avatarStanislav Fomichev <sdf@google.com>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
parent 3b1c667e
...@@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, ...@@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
loff_t *ppos, void **new_buf, loff_t *ppos, void **new_buf,
enum bpf_attach_type type); enum bpf_attach_type type);
int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
int *optname, char __user *optval,
int *optlen, char **kernel_optval);
int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
int optname, char __user *optval,
int __user *optlen, int max_optlen,
int retval);
static inline enum bpf_cgroup_storage_type cgroup_storage_type( static inline enum bpf_cgroup_storage_type cgroup_storage_type(
struct bpf_map *map) struct bpf_map *map)
{ {
...@@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ...@@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
__ret; \ __ret; \
}) })
#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
kernel_optval) \
({ \
int __ret = 0; \
if (cgroup_bpf_enabled) \
__ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \
optname, optval, \
optlen, \
kernel_optval); \
__ret; \
})
#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \
({ \
int __ret = 0; \
if (cgroup_bpf_enabled) \
get_user(__ret, optlen); \
__ret; \
})
#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \
max_optlen, retval) \
({ \
int __ret = retval; \
if (cgroup_bpf_enabled) \
__ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \
optname, optval, \
optlen, max_optlen, \
retval); \
__ret; \
})
int cgroup_bpf_prog_attach(const union bpf_attr *attr, int cgroup_bpf_prog_attach(const union bpf_attr *attr,
enum bpf_prog_type ptype, struct bpf_prog *prog); enum bpf_prog_type ptype, struct bpf_prog *prog);
int cgroup_bpf_prog_detach(const union bpf_attr *attr, int cgroup_bpf_prog_detach(const union bpf_attr *attr,
...@@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, ...@@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
optlen, max_optlen, retval) ({ retval; })
#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
kernel_optval) ({ 0; })
#define for_each_cgroup_storage_type(stype) for (; false; ) #define for_each_cgroup_storage_type(stype) for (; false; )
......
...@@ -518,6 +518,7 @@ struct bpf_prog_array { ...@@ -518,6 +518,7 @@ struct bpf_prog_array {
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
void bpf_prog_array_free(struct bpf_prog_array *progs); void bpf_prog_array_free(struct bpf_prog_array *progs);
int bpf_prog_array_length(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs);
bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
__u32 __user *prog_ids, u32 cnt); __u32 __user *prog_ids, u32 cnt);
...@@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto; ...@@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto;
extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto;
extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_strtoul_proto;
extern const struct bpf_func_proto bpf_tcp_sock_proto;
/* Shared helpers among cBPF and eBPF. */ /* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void); void bpf_user_rnd_init_once(void);
......
...@@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) ...@@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
#ifdef CONFIG_CGROUP_BPF #ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
#endif #endif
#ifdef CONFIG_BPF_LIRC_MODE2 #ifdef CONFIG_BPF_LIRC_MODE2
BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
......
...@@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern { ...@@ -1199,4 +1199,14 @@ struct bpf_sysctl_kern {
u64 tmp_reg; u64 tmp_reg;
}; };
struct bpf_sockopt_kern {
struct sock *sk;
u8 *optval;
u8 *optval_end;
s32 level;
s32 optname;
s32 optlen;
s32 retval;
};
#endif /* __LINUX_FILTER_H__ */ #endif /* __LINUX_FILTER_H__ */
...@@ -170,6 +170,7 @@ enum bpf_prog_type { ...@@ -170,6 +170,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_FLOW_DISSECTOR,
BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_CGROUP_SYSCTL,
BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
BPF_PROG_TYPE_CGROUP_SOCKOPT,
}; };
enum bpf_attach_type { enum bpf_attach_type {
...@@ -194,6 +195,8 @@ enum bpf_attach_type { ...@@ -194,6 +195,8 @@ enum bpf_attach_type {
BPF_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL,
BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP4_RECVMSG,
BPF_CGROUP_UDP6_RECVMSG, BPF_CGROUP_UDP6_RECVMSG,
BPF_CGROUP_GETSOCKOPT,
BPF_CGROUP_SETSOCKOPT,
__MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
}; };
...@@ -3541,4 +3544,15 @@ struct bpf_sysctl { ...@@ -3541,4 +3544,15 @@ struct bpf_sysctl {
*/ */
}; };
struct bpf_sockopt {
__bpf_md_ptr(struct bpf_sock *, sk);
__bpf_md_ptr(void *, optval);
__bpf_md_ptr(void *, optval_end);
__s32 level;
__s32 optname;
__s32 optlen;
__s32 retval;
};
#endif /* _UAPI__LINUX_BPF_H__ */ #endif /* _UAPI__LINUX_BPF_H__ */
...@@ -15,6 +15,7 @@ ...@@ -15,6 +15,7 @@
#include <linux/bpf.h> #include <linux/bpf.h>
#include <linux/bpf-cgroup.h> #include <linux/bpf-cgroup.h>
#include <net/sock.h> #include <net/sock.h>
#include <net/bpf_sk_storage.h>
#include "../cgroup/cgroup-internal.h" #include "../cgroup/cgroup-internal.h"
...@@ -938,6 +939,188 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, ...@@ -938,6 +939,188 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
} }
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
enum bpf_attach_type attach_type)
{
struct bpf_prog_array *prog_array;
bool empty;
rcu_read_lock();
prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]);
empty = bpf_prog_array_is_empty(prog_array);
rcu_read_unlock();
return empty;
}
static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
{
if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0)
return -EINVAL;
ctx->optval = kzalloc(max_optlen, GFP_USER);
if (!ctx->optval)
return -ENOMEM;
ctx->optval_end = ctx->optval + max_optlen;
ctx->optlen = max_optlen;
return 0;
}
static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
{
kfree(ctx->optval);
}
int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
int *optname, char __user *optval,
int *optlen, char **kernel_optval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
struct bpf_sockopt_kern ctx = {
.sk = sk,
.level = *level,
.optname = *optname,
};
int ret;
/* Opportunistic check to see whether we have any BPF program
* attached to the hook so we don't waste time allocating
* memory and locking the socket.
*/
if (!cgroup_bpf_enabled ||
__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
return 0;
ret = sockopt_alloc_buf(&ctx, *optlen);
if (ret)
return ret;
if (copy_from_user(ctx.optval, optval, *optlen) != 0) {
ret = -EFAULT;
goto out;
}
lock_sock(sk);
ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT],
&ctx, BPF_PROG_RUN);
release_sock(sk);
if (!ret) {
ret = -EPERM;
goto out;
}
if (ctx.optlen == -1) {
/* optlen set to -1, bypass kernel */
ret = 1;
} else if (ctx.optlen > *optlen || ctx.optlen < -1) {
/* optlen is out of bounds */
ret = -EFAULT;
} else {
/* optlen within bounds, run kernel handler */
ret = 0;
/* export any potential modifications */
*level = ctx.level;
*optname = ctx.optname;
*optlen = ctx.optlen;
*kernel_optval = ctx.optval;
}
out:
if (ret)
sockopt_free_buf(&ctx);
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt);
int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
int optname, char __user *optval,
int __user *optlen, int max_optlen,
int retval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
struct bpf_sockopt_kern ctx = {
.sk = sk,
.level = level,
.optname = optname,
.retval = retval,
};
int ret;
/* Opportunistic check to see whether we have any BPF program
* attached to the hook so we don't waste time allocating
* memory and locking the socket.
*/
if (!cgroup_bpf_enabled ||
__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
return retval;
ret = sockopt_alloc_buf(&ctx, max_optlen);
if (ret)
return ret;
if (!retval) {
/* If kernel getsockopt finished successfully,
* copy whatever was returned to the user back
* into our temporary buffer. Set optlen to the
* one that kernel returned as well to let
* BPF programs inspect the value.
*/
if (get_user(ctx.optlen, optlen)) {
ret = -EFAULT;
goto out;
}
if (ctx.optlen > max_optlen)
ctx.optlen = max_optlen;
if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) {
ret = -EFAULT;
goto out;
}
}
lock_sock(sk);
ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
&ctx, BPF_PROG_RUN);
release_sock(sk);
if (!ret) {
ret = -EPERM;
goto out;
}
if (ctx.optlen > max_optlen) {
ret = -EFAULT;
goto out;
}
/* BPF programs only allowed to set retval to 0, not some
* arbitrary value.
*/
if (ctx.retval != 0 && ctx.retval != retval) {
ret = -EFAULT;
goto out;
}
if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
put_user(ctx.optlen, optlen)) {
ret = -EFAULT;
goto out;
}
ret = ctx.retval;
out:
sockopt_free_buf(&ctx);
return ret;
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt);
static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
size_t *lenp) size_t *lenp)
{ {
...@@ -1198,3 +1381,153 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = { ...@@ -1198,3 +1381,153 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
const struct bpf_prog_ops cg_sysctl_prog_ops = { const struct bpf_prog_ops cg_sysctl_prog_ops = {
}; };
static const struct bpf_func_proto *
cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_sk_storage_get:
return &bpf_sk_storage_get_proto;
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
#ifdef CONFIG_INET
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
#endif
default:
return cgroup_base_func_proto(func_id, prog);
}
}
static bool cg_sockopt_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
{
const int size_default = sizeof(__u32);
if (off < 0 || off >= sizeof(struct bpf_sockopt))
return false;
if (off % size != 0)
return false;
if (type == BPF_WRITE) {
switch (off) {
case offsetof(struct bpf_sockopt, retval):
if (size != size_default)
return false;
return prog->expected_attach_type ==
BPF_CGROUP_GETSOCKOPT;
case offsetof(struct bpf_sockopt, optname):
/* fallthrough */
case offsetof(struct bpf_sockopt, level):
if (size != size_default)
return false;
return prog->expected_attach_type ==
BPF_CGROUP_SETSOCKOPT;
case offsetof(struct bpf_sockopt, optlen):
return size == size_default;
default:
return false;
}
}
switch (off) {
case offsetof(struct bpf_sockopt, sk):
if (size != sizeof(__u64))
return false;
info->reg_type = PTR_TO_SOCKET;
break;
case offsetof(struct bpf_sockopt, optval):
if (size != sizeof(__u64))
return false;
info->reg_type = PTR_TO_PACKET;
break;
case offsetof(struct bpf_sockopt, optval_end):
if (size != sizeof(__u64))
return false;
info->reg_type = PTR_TO_PACKET_END;
break;
case offsetof(struct bpf_sockopt, retval):
if (size != size_default)
return false;
return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT;
default:
if (size != size_default)
return false;
break;
}
return true;
}
#define CG_SOCKOPT_ACCESS_FIELD(T, F) \
T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \
si->dst_reg, si->src_reg, \
offsetof(struct bpf_sockopt_kern, F))
static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
struct bpf_insn *insn = insn_buf;
switch (si->off) {
case offsetof(struct bpf_sockopt, sk):
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk);
break;
case offsetof(struct bpf_sockopt, level):
if (type == BPF_WRITE)
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level);
else
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level);
break;
case offsetof(struct bpf_sockopt, optname):
if (type == BPF_WRITE)
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname);
else
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname);
break;
case offsetof(struct bpf_sockopt, optlen):
if (type == BPF_WRITE)
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen);
else
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
break;
case offsetof(struct bpf_sockopt, retval):
if (type == BPF_WRITE)
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
else
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
break;
case offsetof(struct bpf_sockopt, optval):
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
break;
case offsetof(struct bpf_sockopt, optval_end):
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end);
break;
}
return insn - insn_buf;
}
static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf,
bool direct_write,
const struct bpf_prog *prog)
{
/* Nothing to do for sockopt argument. The data is kzalloc'ated.
*/
return 0;
}
const struct bpf_verifier_ops cg_sockopt_verifier_ops = {
.get_func_proto = cg_sockopt_func_proto,
.is_valid_access = cg_sockopt_is_valid_access,
.convert_ctx_access = cg_sockopt_convert_ctx_access,
.gen_prologue = cg_sockopt_get_prologue,
};
const struct bpf_prog_ops cg_sockopt_prog_ops = {
};
...@@ -1809,6 +1809,15 @@ int bpf_prog_array_length(struct bpf_prog_array *array) ...@@ -1809,6 +1809,15 @@ int bpf_prog_array_length(struct bpf_prog_array *array)
return cnt; return cnt;
} }
bool bpf_prog_array_is_empty(struct bpf_prog_array *array)
{
struct bpf_prog_array_item *item;
for (item = array->items; item->prog; item++)
if (item->prog != &dummy_bpf_prog.prog)
return false;
return true;
}
static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, static bool bpf_prog_array_copy_core(struct bpf_prog_array *array,
u32 *prog_ids, u32 *prog_ids,
......
...@@ -1590,6 +1590,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, ...@@ -1590,6 +1590,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
default: default:
return -EINVAL; return -EINVAL;
} }
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
switch (expected_attach_type) {
case BPF_CGROUP_SETSOCKOPT:
case BPF_CGROUP_GETSOCKOPT:
return 0;
default:
return -EINVAL;
}
default: default:
return 0; return 0;
} }
...@@ -1840,6 +1848,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, ...@@ -1840,6 +1848,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
switch (prog->type) { switch (prog->type) {
case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
return attach_type == prog->expected_attach_type ? 0 : -EINVAL; return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SKB:
return prog->enforce_expected_attach_type && return prog->enforce_expected_attach_type &&
...@@ -1912,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr) ...@@ -1912,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_CGROUP_SYSCTL: case BPF_CGROUP_SYSCTL:
ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
break; break;
case BPF_CGROUP_GETSOCKOPT:
case BPF_CGROUP_SETSOCKOPT:
ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
break;
default: default:
return -EINVAL; return -EINVAL;
} }
...@@ -1995,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr) ...@@ -1995,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_CGROUP_SYSCTL: case BPF_CGROUP_SYSCTL:
ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
break; break;
case BPF_CGROUP_GETSOCKOPT:
case BPF_CGROUP_SETSOCKOPT:
ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
break;
default: default:
return -EINVAL; return -EINVAL;
} }
...@@ -2031,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr, ...@@ -2031,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE: case BPF_CGROUP_DEVICE:
case BPF_CGROUP_SYSCTL: case BPF_CGROUP_SYSCTL:
case BPF_CGROUP_GETSOCKOPT:
case BPF_CGROUP_SETSOCKOPT:
break; break;
case BPF_LIRC_MODE2: case BPF_LIRC_MODE2:
return lirc_prog_query(attr, uattr); return lirc_prog_query(attr, uattr);
......
...@@ -2215,6 +2215,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, ...@@ -2215,6 +2215,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
env->seen_direct_write = true; env->seen_direct_write = true;
return true; return true;
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
if (t == BPF_WRITE)
env->seen_direct_write = true;
return true;
default: default:
return false; return false;
} }
...@@ -6066,6 +6073,7 @@ static int check_return_code(struct bpf_verifier_env *env) ...@@ -6066,6 +6073,7 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SYSCTL:
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
break; break;
default: default:
return 0; return 0;
......
...@@ -5651,7 +5651,7 @@ BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) ...@@ -5651,7 +5651,7 @@ BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
return (unsigned long)NULL; return (unsigned long)NULL;
} }
static const struct bpf_func_proto bpf_tcp_sock_proto = { const struct bpf_func_proto bpf_tcp_sock_proto = {
.func = bpf_tcp_sock, .func = bpf_tcp_sock,
.gpl_only = false, .gpl_only = false,
.ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL,
......
...@@ -2051,6 +2051,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, ...@@ -2051,6 +2051,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size,
static int __sys_setsockopt(int fd, int level, int optname, static int __sys_setsockopt(int fd, int level, int optname,
char __user *optval, int optlen) char __user *optval, int optlen)
{ {
mm_segment_t oldfs = get_fs();
char *kernel_optval = NULL;
int err, fput_needed; int err, fput_needed;
struct socket *sock; struct socket *sock;
...@@ -2063,6 +2065,22 @@ static int __sys_setsockopt(int fd, int level, int optname, ...@@ -2063,6 +2065,22 @@ static int __sys_setsockopt(int fd, int level, int optname,
if (err) if (err)
goto out_put; goto out_put;
err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level,
&optname, optval, &optlen,
&kernel_optval);
if (err < 0) {
goto out_put;
} else if (err > 0) {
err = 0;
goto out_put;
}
if (kernel_optval) {
set_fs(KERNEL_DS);
optval = (char __user __force *)kernel_optval;
}
if (level == SOL_SOCKET) if (level == SOL_SOCKET)
err = err =
sock_setsockopt(sock, level, optname, optval, sock_setsockopt(sock, level, optname, optval,
...@@ -2071,6 +2089,11 @@ static int __sys_setsockopt(int fd, int level, int optname, ...@@ -2071,6 +2089,11 @@ static int __sys_setsockopt(int fd, int level, int optname,
err = err =
sock->ops->setsockopt(sock, level, optname, optval, sock->ops->setsockopt(sock, level, optname, optval,
optlen); optlen);
if (kernel_optval) {
set_fs(oldfs);
kfree(kernel_optval);
}
out_put: out_put:
fput_light(sock->file, fput_needed); fput_light(sock->file, fput_needed);
} }
...@@ -2093,6 +2116,7 @@ static int __sys_getsockopt(int fd, int level, int optname, ...@@ -2093,6 +2116,7 @@ static int __sys_getsockopt(int fd, int level, int optname,
{ {
int err, fput_needed; int err, fput_needed;
struct socket *sock; struct socket *sock;
int max_optlen;
sock = sockfd_lookup_light(fd, &err, &fput_needed); sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock != NULL) { if (sock != NULL) {
...@@ -2100,6 +2124,8 @@ static int __sys_getsockopt(int fd, int level, int optname, ...@@ -2100,6 +2124,8 @@ static int __sys_getsockopt(int fd, int level, int optname,
if (err) if (err)
goto out_put; goto out_put;
max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
if (level == SOL_SOCKET) if (level == SOL_SOCKET)
err = err =
sock_getsockopt(sock, level, optname, optval, sock_getsockopt(sock, level, optname, optval,
...@@ -2108,6 +2134,10 @@ static int __sys_getsockopt(int fd, int level, int optname, ...@@ -2108,6 +2134,10 @@ static int __sys_getsockopt(int fd, int level, int optname,
err = err =
sock->ops->getsockopt(sock, level, optname, optval, sock->ops->getsockopt(sock, level, optname, optval,
optlen); optlen);
err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname,
optval, optlen,
max_optlen, err);
out_put: out_put:
fput_light(sock->file, fput_needed); fput_light(sock->file, fput_needed);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment