Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-11-26

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Extend BTF to support function call types and improve the BPF
   symbol handling with this info for kallsyms and bpftool program
   dump to make debugging easier, from Martin and Yonghong.

2) Optimize LPM lookups by making longest_prefix_match() handle
   multiple bytes at a time, from Eric.

3) Adds support for loading and attaching flow dissector BPF progs
   from bpftool, from Stanislav.

4) Extend the sk_lookup() helper to be supported from XDP, from Nitin.

5) Enable verifier to support narrow context loads with offset > 0
   to adapt to LLVM code generation (currently only offset of 0 was
   supported). Add test cases as well, from Andrey.

6) Simplify passing device functions for offloaded BPF progs by
   adding callbacks to bpf_prog_offload_ops instead of ndo_bpf.
   Also convert nfp and netdevsim to make use of them, from Quentin.

7) Add support for sock_ops based BPF programs to send events to
   the perf ring-buffer through perf_event_output helper, from
   Sowmini and Daniel.

8) Add read / write support for skb->tstamp from tc BPF and cg BPF
   programs to allow for supporting rate-limiting in EDT qdiscs
   like fq from BPF side, from Vlad.

9) Extend libbpf API to support map in map types and add test cases
   for it as well to BPF kselftests, from Nikita.

10) Account the maximum packet offset accessed by a BPF program in
    the verifier and use it for optimizing nfp JIT, from Jiong.

11) Fix error handling regarding kprobe_events in BPF sample loader,
    from Daniel T.

12) Add support for queue and stack map type in bpftool, from David.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller
2018-11-26 13:08:17 -08:00
63 changed files with 4213 additions and 601 deletions
@@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app)
app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf);
}
bpf->bpf_dev = bpf_offload_dev_create();
bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops);
err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
if (err)
goto err_free_neutral_maps;
@@ -509,7 +509,11 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
int nfp_bpf_jit(struct nfp_prog *prog);
bool nfp_bpf_supported_opcode(u8 code);
extern const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops;
int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
int prev_insn_idx);
int nfp_bpf_finalize(struct bpf_verifier_env *env);
extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops;
struct netdev_bpf;
struct nfp_app;
@@ -33,9 +33,6 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
struct nfp_bpf_neutral_map *record;
int err;
/* Map record paths are entered via ndo, update side is protected. */
ASSERT_RTNL();
/* Reuse path - other offloaded program is already tracking this map. */
record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id,
nfp_bpf_maps_neutral_params);
@@ -84,8 +81,6 @@ nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog)
bool freed = false;
int i;
ASSERT_RTNL();
for (i = 0; i < nfp_prog->map_records_cnt; i++) {
if (--nfp_prog->map_records[i]->count) {
nfp_prog->map_records[i] = NULL;
@@ -187,11 +182,10 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
kfree(nfp_prog);
}
static int
nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
struct netdev_bpf *bpf)
static int nfp_bpf_verifier_prep(struct bpf_prog *prog)
{
struct bpf_prog *prog = bpf->verifier.prog;
struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
struct nfp_app *app = nn->app;
struct nfp_prog *nfp_prog;
int ret;
@@ -209,7 +203,6 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
goto err_free;
nfp_prog->verifier_meta = nfp_prog_first_meta(nfp_prog);
bpf->verifier.ops = &nfp_bpf_analyzer_ops;
return 0;
@@ -219,8 +212,9 @@ err_free:
return ret;
}
static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
static int nfp_bpf_translate(struct bpf_prog *prog)
{
struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
unsigned int max_instr;
int err;
@@ -242,15 +236,13 @@ static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog);
}
static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog)
static void nfp_bpf_destroy(struct bpf_prog *prog)
{
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
kvfree(nfp_prog->prog);
nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog);
nfp_prog_free(nfp_prog);
return 0;
}
/* Atomic engine requires values to be in big endian, we need to byte swap
@@ -422,12 +414,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
{
switch (bpf->command) {
case BPF_OFFLOAD_VERIFIER_PREP:
return nfp_bpf_verifier_prep(app, nn, bpf);
case BPF_OFFLOAD_TRANSLATE:
return nfp_bpf_translate(nn, bpf->offload.prog);
case BPF_OFFLOAD_DESTROY:
return nfp_bpf_destroy(nn, bpf->offload.prog);
case BPF_OFFLOAD_MAP_ALLOC:
return nfp_bpf_map_alloc(app->priv, bpf->offmap);
case BPF_OFFLOAD_MAP_FREE:
@@ -489,14 +475,15 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
unsigned int max_mtu, max_stack, max_prog_len;
unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
dma_addr_t dma_addr;
void *img;
int err;
max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
if (max_mtu < nn->dp.netdev->mtu) {
NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary");
fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
if (fw_mtu < pkt_off) {
NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
return -EOPNOTSUPP;
}
@@ -600,3 +587,11 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
return 0;
}
const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
.insn_hook = nfp_verify_insn,
.finalize = nfp_bpf_finalize,
.prepare = nfp_bpf_verifier_prep,
.translate = nfp_bpf_translate,
.destroy = nfp_bpf_destroy,
};
@@ -623,8 +623,8 @@ nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
return 0;
}
static int
nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
int prev_insn_idx)
{
struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
@@ -745,7 +745,7 @@ continue_subprog:
goto continue_subprog;
}
static int nfp_bpf_finalize(struct bpf_verifier_env *env)
int nfp_bpf_finalize(struct bpf_verifier_env *env)
{
struct bpf_subprog_info *info;
struct nfp_prog *nfp_prog;
@@ -788,8 +788,3 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env)
return 0;
}
const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
.insn_hook = nfp_verify_insn,
.finalize = nfp_bpf_finalize,
};
+27 -25
View File
@@ -91,11 +91,6 @@ static int nsim_bpf_finalize(struct bpf_verifier_env *env)
return 0;
}
static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
.insn_hook = nsim_bpf_verify_insn,
.finalize = nsim_bpf_finalize,
};
static bool nsim_xdp_offload_active(struct netdevsim *ns)
{
return ns->xdp_hw.prog;
@@ -263,6 +258,24 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
return 0;
}
static int nsim_bpf_verifier_prep(struct bpf_prog *prog)
{
struct netdevsim *ns = netdev_priv(prog->aux->offload->netdev);
if (!ns->bpf_bind_accept)
return -EOPNOTSUPP;
return nsim_bpf_create_prog(ns, prog);
}
static int nsim_bpf_translate(struct bpf_prog *prog)
{
struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv;
state->state = "xlated";
return 0;
}
static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
{
struct nsim_bpf_bound_prog *state;
@@ -275,6 +288,14 @@ static void nsim_bpf_destroy_prog(struct bpf_prog *prog)
kfree(state);
}
static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = {
.insn_hook = nsim_bpf_verify_insn,
.finalize = nsim_bpf_finalize,
.prepare = nsim_bpf_verifier_prep,
.translate = nsim_bpf_translate,
.destroy = nsim_bpf_destroy_prog,
};
static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
{
if (bpf->prog && bpf->prog->aux->offload) {
@@ -533,30 +554,11 @@ static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap)
int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
{
struct netdevsim *ns = netdev_priv(dev);
struct nsim_bpf_bound_prog *state;
int err;
ASSERT_RTNL();
switch (bpf->command) {
case BPF_OFFLOAD_VERIFIER_PREP:
if (!ns->bpf_bind_accept)
return -EOPNOTSUPP;
err = nsim_bpf_create_prog(ns, bpf->verifier.prog);
if (err)
return err;
bpf->verifier.ops = &nsim_bpf_analyzer_ops;
return 0;
case BPF_OFFLOAD_TRANSLATE:
state = bpf->offload.prog->aux->offload->dev_priv;
state->state = "xlated";
return 0;
case BPF_OFFLOAD_DESTROY:
nsim_bpf_destroy_prog(bpf->offload.prog);
return 0;
case XDP_QUERY_PROG:
return xdp_attachment_query(&ns->xdp, bpf);
case XDP_QUERY_PROG_HW:
@@ -599,7 +601,7 @@ int nsim_bpf_init(struct netdevsim *ns)
if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
return -ENOMEM;
ns->sdev->bpf_dev = bpf_offload_dev_create();
ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops);
err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
if (err)
return err;
+11 -3
View File
@@ -268,15 +268,18 @@ struct bpf_prog_offload_ops {
int (*insn_hook)(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int (*finalize)(struct bpf_verifier_env *env);
int (*prepare)(struct bpf_prog *prog);
int (*translate)(struct bpf_prog *prog);
void (*destroy)(struct bpf_prog *prog);
};
struct bpf_prog_offload {
struct bpf_prog *prog;
struct net_device *netdev;
struct bpf_offload_dev *offdev;
void *dev_priv;
struct list_head offloads;
bool dev_state;
const struct bpf_prog_offload_ops *dev_ops;
void *jited_image;
u32 jited_len;
};
@@ -293,6 +296,7 @@ struct bpf_prog_aux {
atomic_t refcnt;
u32 used_map_cnt;
u32 max_ctx_offset;
u32 max_pkt_offset;
u32 stack_depth;
u32 id;
u32 func_cnt;
@@ -312,6 +316,8 @@ struct bpf_prog_aux {
void *security;
#endif
struct bpf_prog_offload *offload;
struct btf *btf;
u32 type_id; /* type id for this prog/func */
union {
struct work_struct work;
struct rcu_head rcu;
@@ -523,7 +529,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
}
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
union bpf_attr __user *uattr);
void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
/* Map specifics */
@@ -691,7 +698,8 @@ int bpf_map_offload_get_next_key(struct bpf_map *map,
bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
struct bpf_offload_dev *bpf_offload_dev_create(void);
struct bpf_offload_dev *
bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops);
void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
struct net_device *netdev);
+2 -1
View File
@@ -204,6 +204,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
struct bpf_subprog_info {
u32 start; /* insn idx of function entry point */
u16 stack_depth; /* max. stack depth used by this function */
u32 type_id; /* btf type_id for this subprog */
};
/* single container for all structs
@@ -245,7 +246,7 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
return cur_func(env)->regs;
}
int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env);
int bpf_prog_offload_verifier_prep(struct bpf_prog *prog);
int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int bpf_prog_offload_finalize(struct bpf_verifier_env *env);
+16
View File
@@ -47,4 +47,20 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
int btf_get_fd_by_id(u32 id);
u32 btf_id(const struct btf *btf);
#ifdef CONFIG_BPF_SYSCALL
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
const char *btf_name_by_offset(const struct btf *btf, u32 offset);
#else
static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
u32 type_id)
{
return NULL;
}
static inline const char *btf_name_by_offset(const struct btf *btf,
u32 offset)
{
return NULL;
}
#endif
#endif
+1 -15
View File
@@ -668,24 +668,10 @@ static inline u32 bpf_ctx_off_adjust_machine(u32 size)
return size;
}
static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access,
u32 size_default)
{
size_default = bpf_ctx_off_adjust_machine(size_default);
size_access = bpf_ctx_off_adjust_machine(size_access);
#ifdef __LITTLE_ENDIAN
return (off & (size_default - 1)) == 0;
#else
return (off & (size_default - 1)) + size_access == size_default;
#endif
}
static inline bool
bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
{
return bpf_ctx_narrow_align_ok(off, size, size_default) &&
size <= size_default && (size & (size - 1)) == 0;
return size <= size_default && (size & (size - 1)) == 0;
}
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
-12
View File
@@ -865,9 +865,6 @@ enum bpf_netdev_command {
XDP_QUERY_PROG,
XDP_QUERY_PROG_HW,
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_VERIFIER_PREP,
BPF_OFFLOAD_TRANSLATE,
BPF_OFFLOAD_DESTROY,
BPF_OFFLOAD_MAP_ALLOC,
BPF_OFFLOAD_MAP_FREE,
XDP_QUERY_XSK_UMEM,
@@ -893,15 +890,6 @@ struct netdev_bpf {
/* flags with which program was installed */
u32 prog_flags;
};
/* BPF_OFFLOAD_VERIFIER_PREP */
struct {
struct bpf_prog *prog;
const struct bpf_prog_offload_ops *ops; /* callee set */
} verifier;
/* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */
struct {
struct bpf_prog *prog;
} offload;
/* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */
struct {
struct bpf_offloaded_map *offmap;
+24 -3
View File
@@ -257,9 +257,6 @@ enum bpf_attach_type {
/* Specify numa node during map creation */
#define BPF_F_NUMA_NODE (1U << 2)
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
#define BPF_OBJ_NAME_LEN 16U
/* Flags for accessing BPF object */
@@ -269,6 +266,12 @@ enum bpf_attach_type {
/* Flag for stack_map, store build_id+offset instead of pointer */
#define BPF_F_STACK_BUILD_ID (1U << 5)
/* Zero-initialize hash function seed. This should only be used for testing. */
#define BPF_F_ZERO_SEED (1U << 6)
/* flags for BPF_PROG_QUERY */
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
enum bpf_stack_build_id_status {
/* user space need an empty entry to identify end of a trace */
BPF_STACK_BUILD_ID_EMPTY = 0,
@@ -335,6 +338,10 @@ union bpf_attr {
* (context accesses, allowed helpers, etc).
*/
__u32 expected_attach_type;
__u32 prog_btf_fd; /* fd pointing to BTF type data */
__u32 func_info_rec_size; /* userspace bpf_func_info size */
__aligned_u64 func_info; /* func info */
__u32 func_info_cnt; /* number of bpf_func_info records */
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2201,6 +2208,8 @@ union bpf_attr {
* **CONFIG_NET** configuration option.
* Return
* Pointer to *struct bpf_sock*, or NULL in case of failure.
* For sockets with reuseport option, *struct bpf_sock*
* return is from reuse->socks[] using hash of the packet.
*
* struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
* Description
@@ -2233,6 +2242,8 @@ union bpf_attr {
* **CONFIG_NET** configuration option.
* Return
* Pointer to *struct bpf_sock*, or NULL in case of failure.
* For sockets with reuseport option, *struct bpf_sock*
* return is from reuse->socks[] using hash of the packet.
*
* int bpf_sk_release(struct bpf_sock *sk)
* Description
@@ -2457,6 +2468,7 @@ struct __sk_buff {
__u32 data_meta;
struct bpf_flow_keys *flow_keys;
__u64 tstamp;
};
struct bpf_tunnel_key {
@@ -2631,6 +2643,10 @@ struct bpf_prog_info {
__u32 nr_jited_func_lens;
__aligned_u64 jited_ksyms;
__aligned_u64 jited_func_lens;
__u32 btf_id;
__u32 func_info_rec_size;
__aligned_u64 func_info;
__u32 func_info_cnt;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -2942,4 +2958,9 @@ struct bpf_flow_keys {
};
};
struct bpf_func_info {
__u32 insn_offset;
__u32 type_id;
};
#endif /* _UAPI__LINUX_BPF_H__ */
+15 -3
View File
@@ -40,7 +40,8 @@ struct btf_type {
/* "size" is used by INT, ENUM, STRUCT and UNION.
* "size" tells the size of the type it is describing.
*
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
* "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
* FUNC and FUNC_PROTO.
* "type" is a type_id referring to another type.
*/
union {
@@ -64,8 +65,10 @@ struct btf_type {
#define BTF_KIND_VOLATILE 9 /* Volatile */
#define BTF_KIND_CONST 10 /* Const */
#define BTF_KIND_RESTRICT 11 /* Restrict */
#define BTF_KIND_MAX 11
#define NR_BTF_KINDS 12
#define BTF_KIND_FUNC 12 /* Function */
#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
#define BTF_KIND_MAX 13
#define NR_BTF_KINDS 14
/* For some specific BTF_KIND, "struct btf_type" is immediately
* followed by extra data.
@@ -110,4 +113,13 @@ struct btf_member {
__u32 offset; /* offset in bits */
};
/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
* The exact number of btf_param is stored in the vlen (of the
* info in "struct btf_type").
*/
struct btf_param {
__u32 name_off;
__u32 type;
};
#endif /* _UAPI__LINUX_BTF_H__ */
+359 -63
View File
File diff suppressed because it is too large Load Diff
+13
View File
@@ -21,12 +21,14 @@
* Kris Katterjohn - Added many additional checks in bpf_check_classic()
*/
#include <uapi/linux/btf.h>
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/random.h>
#include <linux/moduleloader.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/frame.h>
#include <linux/rbtree_latch.h>
#include <linux/kallsyms.h>
@@ -390,6 +392,8 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
{
const char *end = sym + KSYM_NAME_LEN;
const struct btf_type *type;
const char *func_name;
BUILD_BUG_ON(sizeof("bpf_prog_") +
sizeof(prog->tag) * 2 +
@@ -404,6 +408,15 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_");
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
/* prog->aux->name will be ignored if full btf name is available */
if (prog->aux->btf) {
type = btf_type_by_id(prog->aux->btf, prog->aux->type_id);
func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
snprintf(sym, (size_t)(end - sym), "_%s", func_name);
return;
}
if (prog->aux->name[0])
snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name);
else
+11 -2
View File
@@ -23,7 +23,7 @@
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
BPF_F_RDONLY | BPF_F_WRONLY)
BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
struct bucket {
struct hlist_nulls_head head;
@@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr)
*/
bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED);
int numa_node = bpf_map_attr_numa_node(attr);
BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
@@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr)
*/
return -EPERM;
if (zero_seed && !capable(CAP_SYS_ADMIN))
/* Guard against local DoS, and discourage production use. */
return -EPERM;
if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
/* reserved bits should not be used */
return -EINVAL;
@@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (!htab->buckets)
goto free_htab;
htab->hashrnd = get_random_int();
if (htab->map.map_flags & BPF_F_ZERO_SEED)
htab->hashrnd = 0;
else
htab->hashrnd = get_random_int();
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
raw_spin_lock_init(&htab->buckets[i].lock);
+1 -2
View File
@@ -7,8 +7,7 @@
#include <linux/rbtree.h>
#include <linux/slab.h>
DEFINE_PER_CPU(struct bpf_cgroup_storage*,
bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
#ifdef CONFIG_CGROUP_BPF
+49 -10
View File
@@ -168,20 +168,59 @@ static size_t longest_prefix_match(const struct lpm_trie *trie,
const struct lpm_trie_node *node,
const struct bpf_lpm_trie_key *key)
{
size_t prefixlen = 0;
size_t i;
u32 limit = min(node->prefixlen, key->prefixlen);
u32 prefixlen = 0, i = 0;
for (i = 0; i < trie->data_size; i++) {
size_t b;
BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32));
BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32));
b = 8 - fls(node->data[i] ^ key->data[i]);
prefixlen += b;
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT)
if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen)
return min(node->prefixlen, key->prefixlen);
/* data_size >= 16 has very small probability.
* We do not use a loop for optimal code generation.
*/
if (trie->data_size >= 8) {
u64 diff = be64_to_cpu(*(__be64 *)node->data ^
*(__be64 *)key->data);
if (b < 8)
break;
prefixlen = 64 - fls64(diff);
if (prefixlen >= limit)
return limit;
if (diff)
return prefixlen;
i = 8;
}
#endif
while (trie->data_size >= i + 4) {
u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^
*(__be32 *)&key->data[i]);
prefixlen += 32 - fls(diff);
if (prefixlen >= limit)
return limit;
if (diff)
return prefixlen;
i += 4;
}
if (trie->data_size >= i + 2) {
u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^
*(__be16 *)&key->data[i]);
prefixlen += 16 - fls(diff);
if (prefixlen >= limit)
return limit;
if (diff)
return prefixlen;
i += 2;
}
if (trie->data_size >= i + 1) {
prefixlen += 8 - fls(node->data[i] ^ key->data[i]);
if (prefixlen >= limit)
return limit;
}
return prefixlen;
+28 -48
View File
@@ -33,6 +33,7 @@
static DECLARE_RWSEM(bpf_devs_lock);
struct bpf_offload_dev {
const struct bpf_prog_offload_ops *ops;
struct list_head netdevs;
};
@@ -106,6 +107,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
err = -EINVAL;
goto err_unlock;
}
offload->offdev = ondev->offdev;
prog->aux->offload = offload;
list_add_tail(&offload->offloads, &ondev->progs);
dev_put(offload->netdev);
@@ -121,40 +123,20 @@ err_maybe_put:
return err;
}
static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd,
struct netdev_bpf *data)
int bpf_prog_offload_verifier_prep(struct bpf_prog *prog)
{
struct bpf_prog_offload *offload = prog->aux->offload;
struct net_device *netdev;
struct bpf_prog_offload *offload;
int ret = -ENODEV;
ASSERT_RTNL();
down_read(&bpf_devs_lock);
offload = prog->aux->offload;
if (offload) {
ret = offload->offdev->ops->prepare(prog);
offload->dev_state = !ret;
}
up_read(&bpf_devs_lock);
if (!offload)
return -ENODEV;
netdev = offload->netdev;
data->command = cmd;
return netdev->netdev_ops->ndo_bpf(netdev, data);
}
int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env)
{
struct netdev_bpf data = {};
int err;
data.verifier.prog = env->prog;
rtnl_lock();
err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data);
if (err)
goto exit_unlock;
env->prog->aux->offload->dev_ops = data.verifier.ops;
env->prog->aux->offload->dev_state = true;
exit_unlock:
rtnl_unlock();
return err;
return ret;
}
int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
@@ -166,7 +148,8 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
down_read(&bpf_devs_lock);
offload = env->prog->aux->offload;
if (offload)
ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
ret = offload->offdev->ops->insn_hook(env, insn_idx,
prev_insn_idx);
up_read(&bpf_devs_lock);
return ret;
@@ -180,8 +163,8 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
down_read(&bpf_devs_lock);
offload = env->prog->aux->offload;
if (offload) {
if (offload->dev_ops->finalize)
ret = offload->dev_ops->finalize(env);
if (offload->offdev->ops->finalize)
ret = offload->offdev->ops->finalize(env);
else
ret = 0;
}
@@ -193,12 +176,9 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
{
struct bpf_prog_offload *offload = prog->aux->offload;
struct netdev_bpf data = {};
data.offload.prog = prog;
if (offload->dev_state)
WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data));
offload->offdev->ops->destroy(prog);
/* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
bpf_prog_free_id(prog, true);
@@ -210,24 +190,22 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
void bpf_prog_offload_destroy(struct bpf_prog *prog)
{
rtnl_lock();
down_write(&bpf_devs_lock);
if (prog->aux->offload)
__bpf_prog_offload_destroy(prog);
up_write(&bpf_devs_lock);
rtnl_unlock();
}
static int bpf_prog_offload_translate(struct bpf_prog *prog)
{
struct netdev_bpf data = {};
int ret;
struct bpf_prog_offload *offload;
int ret = -ENODEV;
data.offload.prog = prog;
rtnl_lock();
ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data);
rtnl_unlock();
down_read(&bpf_devs_lock);
offload = prog->aux->offload;
if (offload)
ret = offload->offdev->ops->translate(prog);
up_read(&bpf_devs_lock);
return ret;
}
@@ -655,7 +633,8 @@ unlock:
}
EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
struct bpf_offload_dev *bpf_offload_dev_create(void)
struct bpf_offload_dev *
bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
{
struct bpf_offload_dev *offdev;
int err;
@@ -673,6 +652,7 @@ struct bpf_offload_dev *bpf_offload_dev_create(void)
if (!offdev)
return ERR_PTR(-ENOMEM);
offdev->ops = ops;
INIT_LIST_HEAD(&offdev->netdevs);
return offdev;
+55 -4
View File
@@ -1213,6 +1213,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
bpf_prog_kallsyms_del_all(prog);
btf_put(prog->aux->btf);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
@@ -1437,9 +1438,9 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type
#define BPF_PROG_LOAD_LAST_FIELD func_info_cnt
static int bpf_prog_load(union bpf_attr *attr)
static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog;
@@ -1525,7 +1526,7 @@ static int bpf_prog_load(union bpf_attr *attr)
goto free_prog;
/* run eBPF verifier */
err = bpf_check(&prog, attr);
err = bpf_check(&prog, attr, uattr);
if (err < 0)
goto free_used_maps;
@@ -2079,6 +2080,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.xlated_prog_len = 0;
info.nr_jited_ksyms = 0;
info.nr_jited_func_lens = 0;
info.func_info_cnt = 0;
goto done;
}
@@ -2216,6 +2218,55 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
}
if (prog->aux->btf) {
u32 ucnt, urec_size;
info.btf_id = btf_id(prog->aux->btf);
ucnt = info.func_info_cnt;
info.func_info_cnt = prog->aux->func_cnt ? : 1;
urec_size = info.func_info_rec_size;
info.func_info_rec_size = sizeof(struct bpf_func_info);
if (ucnt) {
/* expect passed-in urec_size is what the kernel expects */
if (urec_size != info.func_info_rec_size)
return -EINVAL;
if (bpf_dump_raw_ok()) {
struct bpf_func_info kern_finfo;
char __user *user_finfo;
u32 i, insn_offset;
user_finfo = u64_to_user_ptr(info.func_info);
if (prog->aux->func_cnt) {
ucnt = min_t(u32, info.func_info_cnt, ucnt);
insn_offset = 0;
for (i = 0; i < ucnt; i++) {
kern_finfo.insn_offset = insn_offset;
kern_finfo.type_id = prog->aux->func[i]->aux->type_id;
if (copy_to_user(user_finfo, &kern_finfo,
sizeof(kern_finfo)))
return -EFAULT;
/* func[i]->len holds the prog len */
insn_offset += prog->aux->func[i]->len;
user_finfo += urec_size;
}
} else {
kern_finfo.insn_offset = 0;
kern_finfo.type_id = prog->aux->type_id;
if (copy_to_user(user_finfo, &kern_finfo,
sizeof(kern_finfo)))
return -EFAULT;
}
} else {
info.func_info_cnt = 0;
}
}
} else {
info.func_info_cnt = 0;
}
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
@@ -2501,7 +2552,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
err = map_get_next_key(&attr);
break;
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr);
err = bpf_prog_load(&attr, uattr);
break;
case BPF_OBJ_PIN:
err = bpf_obj_pin(&attr);
+148 -7
View File
@@ -11,10 +11,12 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <uapi/linux/btf.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
@@ -1455,6 +1457,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
/* __check_packet_access has made sure "off + size - 1" is within u16.
* reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
* otherwise find_good_pkt_pointers would have refused to set range info
* that __check_packet_access would have rejected this pkt access.
* Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
*/
env->prog->aux->max_pkt_offset =
max_t(u32, env->prog->aux->max_pkt_offset,
off + reg->umax_value + size - 1);
return err;
}
@@ -4628,6 +4641,114 @@ err_free:
return ret;
}
/* The minimum supported BTF func info size */
#define MIN_BPF_FUNCINFO_SIZE 8
#define MAX_FUNCINFO_REC_SIZE 252
static int check_btf_func(struct bpf_prog *prog, struct bpf_verifier_env *env,
union bpf_attr *attr, union bpf_attr __user *uattr)
{
u32 i, nfuncs, urec_size, min_size, prev_offset;
u32 krec_size = sizeof(struct bpf_func_info);
struct bpf_func_info krecord = {};
const struct btf_type *type;
void __user *urecord;
struct btf *btf;
int ret = 0;
nfuncs = attr->func_info_cnt;
if (!nfuncs)
return 0;
if (nfuncs != env->subprog_cnt) {
verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
return -EINVAL;
}
urec_size = attr->func_info_rec_size;
if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
urec_size > MAX_FUNCINFO_REC_SIZE ||
urec_size % sizeof(u32)) {
verbose(env, "invalid func info rec size %u\n", urec_size);
return -EINVAL;
}
btf = btf_get_by_fd(attr->prog_btf_fd);
if (IS_ERR(btf)) {
verbose(env, "unable to get btf from fd\n");
return PTR_ERR(btf);
}
urecord = u64_to_user_ptr(attr->func_info);
min_size = min_t(u32, krec_size, urec_size);
for (i = 0; i < nfuncs; i++) {
ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
if (ret) {
if (ret == -E2BIG) {
verbose(env, "nonzero tailing record in func info");
/* set the size kernel expects so loader can zero
* out the rest of the record.
*/
if (put_user(min_size, &uattr->func_info_rec_size))
ret = -EFAULT;
}
goto free_btf;
}
if (copy_from_user(&krecord, urecord, min_size)) {
ret = -EFAULT;
goto free_btf;
}
/* check insn_offset */
if (i == 0) {
if (krecord.insn_offset) {
verbose(env,
"nonzero insn_offset %u for the first func info record",
krecord.insn_offset);
ret = -EINVAL;
goto free_btf;
}
} else if (krecord.insn_offset <= prev_offset) {
verbose(env,
"same or smaller insn offset (%u) than previous func info record (%u)",
krecord.insn_offset, prev_offset);
ret = -EINVAL;
goto free_btf;
}
if (env->subprog_info[i].start != krecord.insn_offset) {
verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
ret = -EINVAL;
goto free_btf;
}
/* check type_id */
type = btf_type_by_id(btf, krecord.type_id);
if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) {
verbose(env, "invalid type id %d in func info",
krecord.type_id);
ret = -EINVAL;
goto free_btf;
}
if (i == 0)
prog->aux->type_id = krecord.type_id;
env->subprog_info[i].type_id = krecord.type_id;
prev_offset = krecord.insn_offset;
urecord += urec_size;
}
prog->aux->btf = btf;
return 0;
free_btf:
btf_put(btf);
return ret;
}
/* check %cur's range satisfies %old's */
static bool range_within(struct bpf_reg_state *old,
struct bpf_reg_state *cur)
@@ -5707,10 +5828,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
int i, cnt, size, ctx_field_size, delta = 0;
const int insn_cnt = env->prog->len;
struct bpf_insn insn_buf[16], *insn;
u32 target_size, size_default, off;
struct bpf_prog *new_prog;
enum bpf_access_type type;
bool is_narrower_load;
u32 target_size;
if (ops->gen_prologue || env->seen_direct_write) {
if (!ops->gen_prologue) {
@@ -5803,9 +5924,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
* we will apply proper mask to the result.
*/
is_narrower_load = size < ctx_field_size;
size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
off = insn->off;
if (is_narrower_load) {
u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size);
u32 off = insn->off;
u8 size_code;
if (type == BPF_WRITE) {
@@ -5833,12 +5954,23 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
}
if (is_narrower_load && size < target_size) {
if (ctx_field_size <= 4)
u8 shift = (off & (size_default - 1)) * 8;
if (ctx_field_size <= 4) {
if (shift)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
insn->dst_reg,
shift);
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
(1 << size * 8) - 1);
else
} else {
if (shift)
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
insn->dst_reg,
shift);
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
(1 << size * 8) - 1);
}
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
@@ -5917,6 +6049,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func[i]->aux->name[0] = 'F';
func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
func[i]->jit_requested = 1;
/* the btf will be freed only at prog->aux */
func[i]->aux->btf = prog->aux->btf;
func[i]->aux->type_id = env->subprog_info[i].type_id;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -6138,6 +6273,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
*/
prog->cb_access = 1;
env->prog->aux->stack_depth = MAX_BPF_STACK;
env->prog->aux->max_pkt_offset = MAX_PACKET_OFF;
/* mark bpf_tail_call as different opcode to avoid
* conditional branch in the interpeter for every normal
@@ -6302,7 +6438,8 @@ static void free_states(struct bpf_verifier_env *env)
kfree(env->explored_states);
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
union bpf_attr __user *uattr)
{
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
@@ -6356,7 +6493,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
goto skip_full_check;
if (bpf_prog_is_dev_bound(env->prog->aux)) {
ret = bpf_prog_offload_verifier_prep(env);
ret = bpf_prog_offload_verifier_prep(env->prog);
if (ret)
goto skip_full_check;
}
@@ -6374,6 +6511,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
if (ret < 0)
goto skip_full_check;
ret = check_btf_func(env->prog, env, attr, uattr);
if (ret < 0)
goto skip_full_check;
ret = do_check(env);
if (env->cur_state) {
free_verifier_state(env->cur_state, true);

Some files were not shown because too many files have changed in this diff Show More