mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
1b98658968
Lorenz Bauer [thanks!] reported that a ptr returned by bpf_tcp_sock(sk)
can still be accessed after bpf_sk_release(sk).
Both bpf_tcp_sock() and bpf_sk_fullsock() have the same issue.
This patch addresses them together.
A simple reproducer looks like this:
sk = bpf_sk_lookup_tcp();
/* if (!sk) ... */
tp = bpf_tcp_sock(sk);
/* if (!tp) ... */
bpf_sk_release(sk);
snd_cwnd = tp->snd_cwnd; /* oops! The verifier does not complain. */
The problem is the verifier did not scrub the register's states of
the tcp_sock ptr (tp) after bpf_sk_release(sk).
[ Note that when calling bpf_tcp_sock(sk), the sk is not always
refcount-acquired. e.g. bpf_tcp_sock(skb->sk). The verifier works
fine for this case. ]
Currently, the verifier does not track if a helper's return ptr (in REG_0)
is "carry"-ing one of its argument's refcount status. To carry this info,
the reg1->id needs to be stored in reg0.
One approach was tried, like "reg0->id = reg1->id", when calling
"bpf_tcp_sock()". The main idea was to avoid adding another "ref_obj_id"
for the same reg. However, overlapping the NULL marking and ref
tracking purpose in one "id" does not work well:
ref_sk = bpf_sk_lookup_tcp();
fullsock = bpf_sk_fullsock(ref_sk);
tp = bpf_tcp_sock(ref_sk);
if (!fullsock) {
bpf_sk_release(ref_sk);
return 0;
}
/* fullsock_reg->id is marked for NOT-NULL.
* Same for tp_reg->id because they have the same id.
*/
/* oops. verifier did not complain about the missing !tp check */
snd_cwnd = tp->snd_cwnd;
Hence, a new "ref_obj_id" is needed in "struct bpf_reg_state".
With a new ref_obj_id, when bpf_sk_release(sk) is called, the verifier can
scrub all reg states which has a ref_obj_id match. It is done with the
changes in release_reg_references() in this patch.
While fixing it, sk_to_full_sk() is removed from bpf_tcp_sock() and
bpf_sk_fullsock() to avoid these helpers from returning
another ptr. It will make bpf_sk_release(tp) possible:
sk = bpf_sk_lookup_tcp();
/* if (!sk) ... */
tp = bpf_tcp_sock(sk);
/* if (!tp) ... */
bpf_sk_release(tp);
A separate helper "bpf_get_listener_sock()" will be added in a later
patch to do sk_to_full_sk().
Misc change notes:
- To allow bpf_sk_release(tp), the arg of bpf_sk_release() is changed
from ARG_PTR_TO_SOCKET to ARG_PTR_TO_SOCK_COMMON. ARG_PTR_TO_SOCKET
is removed from bpf.h since no helper is using it.
- arg_type_is_refcounted() is renamed to arg_type_may_be_refcounted()
because ARG_PTR_TO_SOCK_COMMON is the only one and skb->sk is not
refcounted. All bpf_sk_release(), bpf_sk_fullsock() and bpf_tcp_sock()
take ARG_PTR_TO_SOCK_COMMON.
- check_refcount_ok() ensures is_acquire_function() cannot take
arg_type_may_be_refcounted() as its argument.
- The check_func_arg() can only allow one refcount-ed arg. It is
guaranteed by check_refcount_ok() which ensures at most one arg can be
refcounted. Hence, it is a verifier internal error if >1 refcount arg
found in check_func_arg().
- In release_reference(), release_reference_state() is called
first to ensure a match on "reg->ref_obj_id" can be found before
scrubbing the reg states with release_reg_references().
- reg_is_refcounted() is no longer needed.
1. In mark_ptr_or_null_regs(), its usage is replaced by
"ref_obj_id && ref_obj_id == id" because,
when is_null == true, release_reference_state() should only be
called on the ref_obj_id obtained by a acquire helper (i.e.
is_acquire_function() == true). Otherwise, the following
would happen:
sk = bpf_sk_lookup_tcp();
/* if (!sk) { ... } */
fullsock = bpf_sk_fullsock(sk);
if (!fullsock) {
/*
* release_reference_state(fullsock_reg->ref_obj_id)
* where fullsock_reg->ref_obj_id == sk_reg->ref_obj_id.
*
* Hence, the following bpf_sk_release(sk) will fail
* because the ref state has already been released in the
* earlier release_reference_state(fullsock_reg->ref_obj_id).
*/
bpf_sk_release(sk);
}
2. In release_reg_references(), the current reg_is_refcounted() call
is unnecessary because the id check is enough.
- The type_is_refcounted() and type_is_refcounted_or_null()
are no longer needed also because reg_is_refcounted() is removed.
Fixes: 655a51e536
("bpf: Add struct bpf_tcp_sock and BPF_FUNC_tcp_sock")
Reported-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
317 lines
11 KiB
C
317 lines
11 KiB
C
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#ifndef _LINUX_BPF_VERIFIER_H
|
|
#define _LINUX_BPF_VERIFIER_H 1
|
|
|
|
#include <linux/bpf.h> /* for enum bpf_reg_type */
|
|
#include <linux/filter.h> /* for MAX_BPF_STACK */
|
|
#include <linux/tnum.h>
|
|
|
|
/* Maximum variable offset umax_value permitted when resolving memory accesses.
|
|
* In practice this is far bigger than any realistic pointer offset; this limit
|
|
* ensures that umax_value + (int)off + (int)size cannot overflow a u64.
|
|
*/
|
|
#define BPF_MAX_VAR_OFF (1 << 29)
|
|
/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures
|
|
* that converting umax_value to int cannot overflow.
|
|
*/
|
|
#define BPF_MAX_VAR_SIZ (1 << 29)
|
|
|
|
/* Liveness marks, used for registers and spilled-regs (in stack slots).
|
|
* Read marks propagate upwards until they find a write mark; they record that
|
|
* "one of this state's descendants read this reg" (and therefore the reg is
|
|
* relevant for states_equal() checks).
|
|
* Write marks collect downwards and do not propagate; they record that "the
|
|
* straight-line code that reached this state (from its parent) wrote this reg"
|
|
* (and therefore that reads propagated from this state or its descendants
|
|
* should not propagate to its parent).
|
|
* A state with a write mark can receive read marks; it just won't propagate
|
|
* them to its parent, since the write mark is a property, not of the state,
|
|
* but of the link between it and its parent. See mark_reg_read() and
|
|
* mark_stack_slot_read() in kernel/bpf/verifier.c.
|
|
*/
|
|
enum bpf_reg_liveness {
|
|
REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
|
|
REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */
|
|
REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */
|
|
REG_LIVE_DONE = 4, /* liveness won't be updating this register anymore */
|
|
};
|
|
|
|
struct bpf_reg_state {
|
|
/* Ordering of fields matters. See states_equal() */
|
|
enum bpf_reg_type type;
|
|
union {
|
|
/* valid when type == PTR_TO_PACKET */
|
|
u16 range;
|
|
|
|
/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
|
|
* PTR_TO_MAP_VALUE_OR_NULL
|
|
*/
|
|
struct bpf_map *map_ptr;
|
|
|
|
/* Max size from any of the above. */
|
|
unsigned long raw;
|
|
};
|
|
/* Fixed part of pointer offset, pointer types only */
|
|
s32 off;
|
|
/* For PTR_TO_PACKET, used to find other pointers with the same variable
|
|
* offset, so they can share range knowledge.
|
|
* For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
|
|
* came from, when one is tested for != NULL.
|
|
* For PTR_TO_SOCKET this is used to share which pointers retain the
|
|
* same reference to the socket, to determine proper reference freeing.
|
|
*/
|
|
u32 id;
|
|
/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
|
|
* from a pointer-cast helper, bpf_sk_fullsock() and
|
|
* bpf_tcp_sock().
|
|
*
|
|
* Consider the following where "sk" is a reference counted
|
|
* pointer returned from "sk = bpf_sk_lookup_tcp();":
|
|
*
|
|
* 1: sk = bpf_sk_lookup_tcp();
|
|
* 2: if (!sk) { return 0; }
|
|
* 3: fullsock = bpf_sk_fullsock(sk);
|
|
* 4: if (!fullsock) { bpf_sk_release(sk); return 0; }
|
|
* 5: tp = bpf_tcp_sock(fullsock);
|
|
* 6: if (!tp) { bpf_sk_release(sk); return 0; }
|
|
* 7: bpf_sk_release(sk);
|
|
* 8: snd_cwnd = tp->snd_cwnd; // verifier will complain
|
|
*
|
|
* After bpf_sk_release(sk) at line 7, both "fullsock" ptr and
|
|
* "tp" ptr should be invalidated also. In order to do that,
|
|
* the reg holding "fullsock" and "sk" need to remember
|
|
* the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id
|
|
* such that the verifier can reset all regs which have
|
|
* ref_obj_id matching the sk_reg->id.
|
|
*
|
|
* sk_reg->ref_obj_id is set to sk_reg->id at line 1.
|
|
* sk_reg->id will stay as NULL-marking purpose only.
|
|
* After NULL-marking is done, sk_reg->id can be reset to 0.
|
|
*
|
|
* After "fullsock = bpf_sk_fullsock(sk);" at line 3,
|
|
* fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id.
|
|
*
|
|
* After "tp = bpf_tcp_sock(fullsock);" at line 5,
|
|
* tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id
|
|
* which is the same as sk_reg->ref_obj_id.
|
|
*
|
|
* From the verifier perspective, if sk, fullsock and tp
|
|
* are not NULL, they are the same ptr with different
|
|
* reg->type. In particular, bpf_sk_release(tp) is also
|
|
* allowed and has the same effect as bpf_sk_release(sk).
|
|
*/
|
|
u32 ref_obj_id;
|
|
/* For scalar types (SCALAR_VALUE), this represents our knowledge of
|
|
* the actual value.
|
|
* For pointer types, this represents the variable part of the offset
|
|
* from the pointed-to object, and is shared with all bpf_reg_states
|
|
* with the same id as us.
|
|
*/
|
|
struct tnum var_off;
|
|
/* Used to determine if any memory access using this register will
|
|
* result in a bad access.
|
|
* These refer to the same value as var_off, not necessarily the actual
|
|
* contents of the register.
|
|
*/
|
|
s64 smin_value; /* minimum possible (s64)value */
|
|
s64 smax_value; /* maximum possible (s64)value */
|
|
u64 umin_value; /* minimum possible (u64)value */
|
|
u64 umax_value; /* maximum possible (u64)value */
|
|
/* parentage chain for liveness checking */
|
|
struct bpf_reg_state *parent;
|
|
/* Inside the callee two registers can be both PTR_TO_STACK like
|
|
* R1=fp-8 and R2=fp-8, but one of them points to this function stack
|
|
* while another to the caller's stack. To differentiate them 'frameno'
|
|
* is used which is an index in bpf_verifier_state->frame[] array
|
|
* pointing to bpf_func_state.
|
|
*/
|
|
u32 frameno;
|
|
enum bpf_reg_liveness live;
|
|
};
|
|
|
|
enum bpf_stack_slot_type {
|
|
STACK_INVALID, /* nothing was stored in this stack slot */
|
|
STACK_SPILL, /* register spilled into stack */
|
|
STACK_MISC, /* BPF program wrote some data into this slot */
|
|
STACK_ZERO, /* BPF program wrote constant zero */
|
|
};
|
|
|
|
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
|
|
|
|
struct bpf_stack_state {
|
|
struct bpf_reg_state spilled_ptr;
|
|
u8 slot_type[BPF_REG_SIZE];
|
|
};
|
|
|
|
struct bpf_reference_state {
|
|
/* Track each reference created with a unique id, even if the same
|
|
* instruction creates the reference multiple times (eg, via CALL).
|
|
*/
|
|
int id;
|
|
/* Instruction where the allocation of this reference occurred. This
|
|
* is used purely to inform the user of a reference leak.
|
|
*/
|
|
int insn_idx;
|
|
};
|
|
|
|
/* state of the program:
|
|
* type of all registers and stack info
|
|
*/
|
|
struct bpf_func_state {
|
|
struct bpf_reg_state regs[MAX_BPF_REG];
|
|
/* index of call instruction that called into this func */
|
|
int callsite;
|
|
/* stack frame number of this function state from pov of
|
|
* enclosing bpf_verifier_state.
|
|
* 0 = main function, 1 = first callee.
|
|
*/
|
|
u32 frameno;
|
|
/* subprog number == index within subprog_stack_depth
|
|
* zero == main subprog
|
|
*/
|
|
u32 subprogno;
|
|
|
|
/* The following fields should be last. See copy_func_state() */
|
|
int acquired_refs;
|
|
struct bpf_reference_state *refs;
|
|
int allocated_stack;
|
|
struct bpf_stack_state *stack;
|
|
};
|
|
|
|
#define MAX_CALL_FRAMES 8
|
|
struct bpf_verifier_state {
|
|
/* call stack tracking */
|
|
struct bpf_func_state *frame[MAX_CALL_FRAMES];
|
|
u32 curframe;
|
|
u32 active_spin_lock;
|
|
bool speculative;
|
|
};
|
|
|
|
#define bpf_get_spilled_reg(slot, frame) \
|
|
(((slot < frame->allocated_stack / BPF_REG_SIZE) && \
|
|
(frame->stack[slot].slot_type[0] == STACK_SPILL)) \
|
|
? &frame->stack[slot].spilled_ptr : NULL)
|
|
|
|
/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */
|
|
#define bpf_for_each_spilled_reg(iter, frame, reg) \
|
|
for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \
|
|
iter < frame->allocated_stack / BPF_REG_SIZE; \
|
|
iter++, reg = bpf_get_spilled_reg(iter, frame))
|
|
|
|
/* linked list of verifier states used to prune search */
|
|
struct bpf_verifier_state_list {
|
|
struct bpf_verifier_state state;
|
|
struct bpf_verifier_state_list *next;
|
|
};
|
|
|
|
/* Possible states for alu_state member. */
|
|
#define BPF_ALU_SANITIZE_SRC 1U
|
|
#define BPF_ALU_SANITIZE_DST 2U
|
|
#define BPF_ALU_NEG_VALUE (1U << 2)
|
|
#define BPF_ALU_NON_POINTER (1U << 3)
|
|
#define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \
|
|
BPF_ALU_SANITIZE_DST)
|
|
|
|
struct bpf_insn_aux_data {
|
|
union {
|
|
enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
|
|
unsigned long map_state; /* pointer/poison value for maps */
|
|
s32 call_imm; /* saved imm field of call insn */
|
|
u32 alu_limit; /* limit for add/sub register with pointer */
|
|
};
|
|
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
|
|
int sanitize_stack_off; /* stack slot to be cleared */
|
|
bool seen; /* this insn was processed by the verifier */
|
|
u8 alu_state; /* used in combination with alu_limit */
|
|
unsigned int orig_idx; /* original instruction index */
|
|
};
|
|
|
|
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
|
|
|
|
#define BPF_VERIFIER_TMP_LOG_SIZE 1024
|
|
|
|
struct bpf_verifier_log {
|
|
u32 level;
|
|
char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
|
|
char __user *ubuf;
|
|
u32 len_used;
|
|
u32 len_total;
|
|
};
|
|
|
|
static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
|
|
{
|
|
return log->len_used >= log->len_total - 1;
|
|
}
|
|
|
|
static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
|
|
{
|
|
return log->level && log->ubuf && !bpf_verifier_log_full(log);
|
|
}
|
|
|
|
#define BPF_MAX_SUBPROGS 256
|
|
|
|
struct bpf_subprog_info {
|
|
u32 start; /* insn idx of function entry point */
|
|
u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
|
|
u16 stack_depth; /* max. stack depth used by this function */
|
|
};
|
|
|
|
/* single container for all structs
|
|
* one verifier_env per bpf_check() call
|
|
*/
|
|
struct bpf_verifier_env {
|
|
u32 insn_idx;
|
|
u32 prev_insn_idx;
|
|
struct bpf_prog *prog; /* eBPF program being verified */
|
|
const struct bpf_verifier_ops *ops;
|
|
struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
|
|
int stack_size; /* number of states to be processed */
|
|
bool strict_alignment; /* perform strict pointer alignment checks */
|
|
struct bpf_verifier_state *cur_state; /* current verifier state */
|
|
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
|
|
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
|
|
u32 used_map_cnt; /* number of used maps */
|
|
u32 id_gen; /* used to generate unique reg IDs */
|
|
bool allow_ptr_leaks;
|
|
bool seen_direct_write;
|
|
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
|
|
const struct bpf_line_info *prev_linfo;
|
|
struct bpf_verifier_log log;
|
|
struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
|
|
u32 subprog_cnt;
|
|
};
|
|
|
|
__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
|
|
const char *fmt, va_list args);
|
|
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
|
|
const char *fmt, ...);
|
|
|
|
static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
|
|
{
|
|
struct bpf_verifier_state *cur = env->cur_state;
|
|
|
|
return cur->frame[cur->curframe];
|
|
}
|
|
|
|
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_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);
|
|
void
|
|
bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
|
|
struct bpf_insn *insn);
|
|
void
|
|
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
|
|
|
|
#endif /* _LINUX_BPF_VERIFIER_H */
|