linux_dsm_epyc7002/include/linux/skmsg.h
Jakub Kicinski 031097d9e0 net: skmsg: fix TLS 1.3 crash with full sk_msg
TLS 1.3 started using the entry at the end of the SG array
for chaining-in the single byte content type entry. This mostly
works:

[ E E E E E E . . ]
  ^           ^
   start       end

                 E < content type
               /
[ E E E E E E C . ]
  ^           ^
   start       end

(Where E denotes a populated SG entry; C denotes a chaining entry.)

If the array is full, however, the end will point to the start:

[ E E E E E E E E ]
  ^
   start
   end

And we end up overwriting the start:

    E < content type
   /
[ C E E E E E E E ]
  ^
   start
   end

The sg array is supposed to be a circular buffer with start and
end markers pointing anywhere. In case where start > end
(i.e. the circular buffer has "wrapped") there is an extra entry
reserved at the end to chain the two halves together.

[ E E E E E E . . l ]

(Where l is the reserved entry for "looping" back to front.

As suggested by John, let's reserve another entry for chaining
SG entries after the main circular buffer. Note that this entry
has to be pointed to by the end entry so its position is not fixed.

Examples of full messages:

[ E E E E E E E E . l ]
  ^               ^
   start           end

   <---------------.
[ E E . E E E E E E l ]
      ^ ^
   end   start

Now the end will always point to an unused entry, so TLS 1.3
can always use it.

Fixes: 130b392c6c ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-28 22:40:29 -08:00

459 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
#ifndef _LINUX_SKMSG_H
#define _LINUX_SKMSG_H
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/scatterlist.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <net/strparser.h>
#define MAX_MSG_FRAGS MAX_SKB_FRAGS
#define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1)
enum __sk_action {
__SK_DROP = 0,
__SK_PASS,
__SK_REDIRECT,
__SK_NONE,
};
struct sk_msg_sg {
u32 start;
u32 curr;
u32 end;
u32 size;
u32 copybreak;
unsigned long copy;
/* The extra two elements:
* 1) used for chaining the front and sections when the list becomes
* partitioned (e.g. end < start). The crypto APIs require the
* chaining;
* 2) to chain tailer SG entries after the message.
*/
struct scatterlist data[MAX_MSG_FRAGS + 2];
};
static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS);
/* UAPI in filter.c depends on struct sk_msg_sg being first element. */
struct sk_msg {
struct sk_msg_sg sg;
void *data;
void *data_end;
u32 apply_bytes;
u32 cork_bytes;
u32 flags;
struct sk_buff *skb;
struct sock *sk_redir;
struct sock *sk;
struct list_head list;
};
struct sk_psock_progs {
struct bpf_prog *msg_parser;
struct bpf_prog *skb_parser;
struct bpf_prog *skb_verdict;
};
enum sk_psock_state_bits {
SK_PSOCK_TX_ENABLED,
};
struct sk_psock_link {
struct list_head list;
struct bpf_map *map;
void *link_raw;
};
struct sk_psock_parser {
struct strparser strp;
bool enabled;
void (*saved_data_ready)(struct sock *sk);
};
struct sk_psock_work_state {
struct sk_buff *skb;
u32 len;
u32 off;
};
struct sk_psock {
struct sock *sk;
struct sock *sk_redir;
u32 apply_bytes;
u32 cork_bytes;
u32 eval;
struct sk_msg *cork;
struct sk_psock_progs progs;
struct sk_psock_parser parser;
struct sk_buff_head ingress_skb;
struct list_head ingress_msg;
unsigned long state;
struct list_head link;
spinlock_t link_lock;
refcount_t refcnt;
void (*saved_unhash)(struct sock *sk);
void (*saved_close)(struct sock *sk, long timeout);
void (*saved_write_space)(struct sock *sk);
struct proto *sk_proto;
struct sk_psock_work_state work_state;
struct work_struct work;
union {
struct rcu_head rcu;
struct work_struct gc;
};
};
int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len,
int elem_first_coalesce);
int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
u32 off, u32 len);
void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len);
int sk_msg_free(struct sock *sk, struct sk_msg *msg);
int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg);
void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes);
void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg,
u32 bytes);
void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes);
void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes);
int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
{
WARN_ON(i == msg->sg.end && bytes);
}
static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
{
if (psock->apply_bytes) {
if (psock->apply_bytes < bytes)
psock->apply_bytes = 0;
else
psock->apply_bytes -= bytes;
}
}
static inline u32 sk_msg_iter_dist(u32 start, u32 end)
{
return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start);
}
#define sk_msg_iter_var_prev(var) \
do { \
if (var == 0) \
var = NR_MSG_FRAG_IDS - 1; \
else \
var--; \
} while (0)
#define sk_msg_iter_var_next(var) \
do { \
var++; \
if (var == NR_MSG_FRAG_IDS) \
var = 0; \
} while (0)
#define sk_msg_iter_prev(msg, which) \
sk_msg_iter_var_prev(msg->sg.which)
#define sk_msg_iter_next(msg, which) \
sk_msg_iter_var_next(msg->sg.which)
static inline void sk_msg_clear_meta(struct sk_msg *msg)
{
memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy));
}
static inline void sk_msg_init(struct sk_msg *msg)
{
BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS);
memset(msg, 0, sizeof(*msg));
sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS);
}
static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
int which, u32 size)
{
dst->sg.data[which] = src->sg.data[which];
dst->sg.data[which].length = size;
dst->sg.size += size;
src->sg.data[which].length -= size;
src->sg.data[which].offset += size;
}
static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
{
memcpy(dst, src, sizeof(*src));
sk_msg_init(src);
}
static inline bool sk_msg_full(const struct sk_msg *msg)
{
return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS;
}
static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
{
return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
}
static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
{
return &msg->sg.data[which];
}
static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which)
{
return msg->sg.data[which];
}
static inline struct page *sk_msg_page(struct sk_msg *msg, int which)
{
return sg_page(sk_msg_elem(msg, which));
}
static inline bool sk_msg_to_ingress(const struct sk_msg *msg)
{
return msg->flags & BPF_F_INGRESS;
}
static inline void sk_msg_compute_data_pointers(struct sk_msg *msg)
{
struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start);
if (test_bit(msg->sg.start, &msg->sg.copy)) {
msg->data = NULL;
msg->data_end = NULL;
} else {
msg->data = sg_virt(sge);
msg->data_end = msg->data + sge->length;
}
}
static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page,
u32 len, u32 offset)
{
struct scatterlist *sge;
get_page(page);
sge = sk_msg_elem(msg, msg->sg.end);
sg_set_page(sge, page, len, offset);
sg_unmark_end(sge);
__set_bit(msg->sg.end, &msg->sg.copy);
msg->sg.size += len;
sk_msg_iter_next(msg, end);
}
static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
{
do {
if (copy_state)
__set_bit(i, &msg->sg.copy);
else
__clear_bit(i, &msg->sg.copy);
sk_msg_iter_var_next(i);
if (i == msg->sg.end)
break;
} while (1);
}
static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
{
sk_msg_sg_copy(msg, start, true);
}
static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start)
{
sk_msg_sg_copy(msg, start, false);
}
static inline struct sk_psock *sk_psock(const struct sock *sk)
{
return rcu_dereference_sk_user_data(sk);
}
static inline void sk_psock_queue_msg(struct sk_psock *psock,
struct sk_msg *msg)
{
list_add_tail(&msg->list, &psock->ingress_msg);
}
static inline bool sk_psock_queue_empty(const struct sk_psock *psock)
{
return psock ? list_empty(&psock->ingress_msg) : true;
}
static inline void sk_psock_report_error(struct sk_psock *psock, int err)
{
struct sock *sk = psock->sk;
sk->sk_err = err;
sk->sk_error_report(sk);
}
struct sk_psock *sk_psock_init(struct sock *sk, int node);
int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock);
void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock);
void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock);
int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,
struct sk_msg *msg);
static inline struct sk_psock_link *sk_psock_init_link(void)
{
return kzalloc(sizeof(struct sk_psock_link),
GFP_ATOMIC | __GFP_NOWARN);
}
static inline void sk_psock_free_link(struct sk_psock_link *link)
{
kfree(link);
}
struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock);
#if defined(CONFIG_BPF_STREAM_PARSER)
void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link);
#else
static inline void sk_psock_unlink(struct sock *sk,
struct sk_psock_link *link)
{
}
#endif
void __sk_psock_purge_ingress_msg(struct sk_psock *psock);
static inline void sk_psock_cork_free(struct sk_psock *psock)
{
if (psock->cork) {
sk_msg_free(psock->sk, psock->cork);
kfree(psock->cork);
psock->cork = NULL;
}
}
static inline void sk_psock_update_proto(struct sock *sk,
struct sk_psock *psock,
struct proto *ops)
{
psock->saved_unhash = sk->sk_prot->unhash;
psock->saved_close = sk->sk_prot->close;
psock->saved_write_space = sk->sk_write_space;
psock->sk_proto = sk->sk_prot;
sk->sk_prot = ops;
}
static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
sk->sk_write_space = psock->saved_write_space;
if (psock->sk_proto) {
struct inet_connection_sock *icsk = inet_csk(sk);
bool has_ulp = !!icsk->icsk_ulp_data;
if (has_ulp)
tcp_update_ulp(sk, psock->sk_proto);
else
sk->sk_prot = psock->sk_proto;
psock->sk_proto = NULL;
}
}
static inline void sk_psock_set_state(struct sk_psock *psock,
enum sk_psock_state_bits bit)
{
set_bit(bit, &psock->state);
}
static inline void sk_psock_clear_state(struct sk_psock *psock,
enum sk_psock_state_bits bit)
{
clear_bit(bit, &psock->state);
}
static inline bool sk_psock_test_state(const struct sk_psock *psock,
enum sk_psock_state_bits bit)
{
return test_bit(bit, &psock->state);
}
static inline struct sk_psock *sk_psock_get_checked(struct sock *sk)
{
struct sk_psock *psock;
rcu_read_lock();
psock = sk_psock(sk);
if (psock) {
if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) {
psock = ERR_PTR(-EBUSY);
goto out;
}
if (!refcount_inc_not_zero(&psock->refcnt))
psock = ERR_PTR(-EBUSY);
}
out:
rcu_read_unlock();
return psock;
}
static inline struct sk_psock *sk_psock_get(struct sock *sk)
{
struct sk_psock *psock;
rcu_read_lock();
psock = sk_psock(sk);
if (psock && !refcount_inc_not_zero(&psock->refcnt))
psock = NULL;
rcu_read_unlock();
return psock;
}
void sk_psock_stop(struct sock *sk, struct sk_psock *psock);
void sk_psock_destroy(struct rcu_head *rcu);
void sk_psock_drop(struct sock *sk, struct sk_psock *psock);
static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
{
if (refcount_dec_and_test(&psock->refcnt))
sk_psock_drop(sk, psock);
}
static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
{
if (psock->parser.enabled)
psock->parser.saved_data_ready(sk);
else
sk->sk_data_ready(sk);
}
static inline void psock_set_prog(struct bpf_prog **pprog,
struct bpf_prog *prog)
{
prog = xchg(pprog, prog);
if (prog)
bpf_prog_put(prog);
}
static inline void psock_progs_drop(struct sk_psock_progs *progs)
{
psock_set_prog(&progs->msg_parser, NULL);
psock_set_prog(&progs->skb_parser, NULL);
psock_set_prog(&progs->skb_verdict, NULL);
}
#endif /* _LINUX_SKMSG_H */