korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-12-19 17:14:40 +08:00
Code Issues Packages Projects Releases Wiki Activity
6ececdc513
linux/net/tls/tls_sw.c
Jakub Kicinski 6ececdc513 tls: rx: async: adjust record geometry immediately 
Async crypto TLS Rx currently waits for crypto to be done
in order to strip the TLS header and tailer. Simplify
the code by moving the pointers immediately, since only
TLS 1.2 is supported here there is no message padding.

This simplifies the decryption into a new skb in the next
patch as we don't have to worry about input vs output
skb in the decrypt_done() handler any more.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2022-07-18 11:24:11 +01:00

2652 lines
66 KiB
C
Raw Blame History

/*
* Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
* Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
* Copyright (c) 2016-2017, Lance Chao <lancerchao@fb.com>. All rights reserved.
* Copyright (c) 2016, Fridolin Pokorny <fridolin.pokorny@gmail.com>. All rights reserved.
* Copyright (c) 2016, Nikos Mavrogiannopoulos <nmav@gnutls.org>. All rights reserved.
* Copyright (c) 2018, Covalent IO, Inc. http://covalent.io
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/bug.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
#include <linux/splice.h>
#include <crypto/aead.h>
#include <net/strparser.h>
#include <net/tls.h>
#include "tls.h"
struct tls_decrypt_arg {
struct_group(inargs,
bool zc;
bool async;
u8 tail;
);
struct sk_buff *skb;
};
struct tls_decrypt_ctx {
u8 iv[MAX_IV_SIZE];
u8 aad[TLS_MAX_AAD_SIZE];
u8 tail;
struct scatterlist sg[];
};
noinline void tls_err_abort(struct sock *sk, int err)
{
WARN_ON_ONCE(err >= 0);
/* sk->sk_err should contain a positive error code. */
sk->sk_err = -err;
sk_error_report(sk);
}
static int __skb_nsg(struct sk_buff *skb, int offset, int len,
unsigned int recursion_level)
{
int start = skb_headlen(skb);
int i, chunk = start - offset;
struct sk_buff *frag_iter;
int elt = 0;
if (unlikely(recursion_level >= 24))
return -EMSGSIZE;
if (chunk > 0) {
if (chunk > len)
chunk = len;
elt++;
len -= chunk;
if (len == 0)
return elt;
offset += chunk;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
WARN_ON(start > offset + len);
end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
chunk = end - offset;
if (chunk > 0) {
if (chunk > len)
chunk = len;
elt++;
len -= chunk;
if (len == 0)
return elt;
offset += chunk;
}
start = end;
}
if (unlikely(skb_has_frag_list(skb))) {
skb_walk_frags(skb, frag_iter) {
int end, ret;
WARN_ON(start > offset + len);
end = start + frag_iter->len;
chunk = end - offset;
if (chunk > 0) {
if (chunk > len)
chunk = len;
ret = __skb_nsg(frag_iter, offset - start, chunk,
recursion_level + 1);
if (unlikely(ret < 0))
return ret;
elt += ret;
len -= chunk;
if (len == 0)
return elt;
offset += chunk;
}
start = end;
}
}
BUG_ON(len);
return elt;
}
/* Return the number of scatterlist elements required to completely map the
* skb, or -EMSGSIZE if the recursion depth is exceeded.
*/
static int skb_nsg(struct sk_buff *skb, int offset, int len)
{
return __skb_nsg(skb, offset, len, 0);
}
static int tls_padding_length(struct tls_prot_info *prot, struct sk_buff *skb,
struct tls_decrypt_arg *darg)
{
struct strp_msg *rxm = strp_msg(skb);
struct tls_msg *tlm = tls_msg(skb);
int sub = 0;
/* Determine zero-padding length */
if (prot->version == TLS_1_3_VERSION) {
int offset = rxm->full_len - TLS_TAG_SIZE - 1;
char content_type = darg->zc ? darg->tail : 0;
int err;
while (content_type == 0) {
if (offset < prot->prepend_size)
return -EBADMSG;
err = skb_copy_bits(skb, rxm->offset + offset,
&content_type, 1);
if (err)
return err;
if (content_type)
break;
sub++;
offset--;
}
tlm->control = content_type;
}
return sub;
}
static void tls_decrypt_done(struct crypto_async_request *req, int err)
{
struct aead_request *aead_req = (struct aead_request *)req;
struct scatterlist *sgout = aead_req->dst;
struct scatterlist *sgin = aead_req->src;
struct tls_sw_context_rx *ctx;
struct tls_context *tls_ctx;
struct scatterlist *sg;
unsigned int pages;
struct sock *sk;
sk = (struct sock *)req->data;
tls_ctx = tls_get_ctx(sk);
ctx = tls_sw_ctx_rx(tls_ctx);
/* Propagate if there was an err */
if (err) {
if (err == -EBADMSG)
TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR);
ctx->async_wait.err = err;
tls_err_abort(sk, err);
}
/* Free the destination pages if skb was not decrypted inplace */
if (sgout != sgin) {
/* Skip the first S/G entry as it points to AAD */
for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
if (!sg)
break;
put_page(sg_page(sg));
}
}
kfree(aead_req);
spin_lock_bh(&ctx->decrypt_compl_lock);
if (!atomic_dec_return(&ctx->decrypt_pending))
complete(&ctx->async_wait.completion);
spin_unlock_bh(&ctx->decrypt_compl_lock);
}
static int tls_do_decryption(struct sock *sk,
struct scatterlist *sgin,
struct scatterlist *sgout,
char *iv_recv,
size_t data_len,
struct aead_request *aead_req,
struct tls_decrypt_arg *darg)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
int ret;
aead_request_set_tfm(aead_req, ctx->aead_recv);
aead_request_set_ad(aead_req, prot->aad_size);
aead_request_set_crypt(aead_req, sgin, sgout,
data_len + prot->tag_size,
(u8 *)iv_recv);
if (darg->async) {
aead_request_set_callback(aead_req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_decrypt_done, sk);
atomic_inc(&ctx->decrypt_pending);
} else {
aead_request_set_callback(aead_req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
crypto_req_done, &ctx->async_wait);
}
ret = crypto_aead_decrypt(aead_req);
if (ret == -EINPROGRESS) {
if (darg->async)
return 0;
ret = crypto_wait_req(ret, &ctx->async_wait);
}
darg->async = false;
return ret;
}
static void tls_trim_both_msgs(struct sock *sk, int target_size)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec;
sk_msg_trim(sk, &rec->msg_plaintext, target_size);
if (target_size > 0)
target_size += prot->overhead_size;
sk_msg_trim(sk, &rec->msg_encrypted, target_size);
}
static int tls_alloc_encrypted_msg(struct sock *sk, int len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec;
struct sk_msg *msg_en = &rec->msg_encrypted;
return sk_msg_alloc(sk, msg_en, len, 0);
}
static int tls_clone_plaintext_msg(struct sock *sk, int required)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec;
struct sk_msg *msg_pl = &rec->msg_plaintext;
struct sk_msg *msg_en = &rec->msg_encrypted;
int skip, len;
/* We add page references worth len bytes from encrypted sg
* at the end of plaintext sg. It is guaranteed that msg_en
* has enough required room (ensured by caller).
*/
len = required - msg_pl->sg.size;
/* Skip initial bytes in msg_en's data to be able to use
* same offset of both plain and encrypted data.
*/
skip = prot->prepend_size + msg_pl->sg.size;
return sk_msg_clone(sk, msg_pl, msg_en, skip, len);
}
static struct tls_rec *tls_get_rec(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct sk_msg *msg_pl, *msg_en;
struct tls_rec *rec;
int mem_size;
mem_size = sizeof(struct tls_rec) + crypto_aead_reqsize(ctx->aead_send);
rec = kzalloc(mem_size, sk->sk_allocation);
if (!rec)
return NULL;
msg_pl = &rec->msg_plaintext;
msg_en = &rec->msg_encrypted;
sk_msg_init(msg_pl);
sk_msg_init(msg_en);
sg_init_table(rec->sg_aead_in, 2);
sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, prot->aad_size);
sg_unmark_end(&rec->sg_aead_in[1]);
sg_init_table(rec->sg_aead_out, 2);
sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, prot->aad_size);
sg_unmark_end(&rec->sg_aead_out[1]);
return rec;
}
static void tls_free_rec(struct sock *sk, struct tls_rec *rec)
{
sk_msg_free(sk, &rec->msg_encrypted);
sk_msg_free(sk, &rec->msg_plaintext);
kfree(rec);
}
static void tls_free_open_rec(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec;
if (rec) {
tls_free_rec(sk, rec);
ctx->open_rec = NULL;
}
}
int tls_tx_records(struct sock *sk, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
struct sk_msg *msg_en;
int tx_flags, rc = 0;
if (tls_is_partially_sent_record(tls_ctx)) {
rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
if (flags == -1)
tx_flags = rec->tx_flags;
else
tx_flags = flags;
rc = tls_push_partial_record(sk, tls_ctx, tx_flags);
if (rc)
goto tx_err;
/* Full record has been transmitted.
* Remove the head of tx_list
*/
list_del(&rec->list);
sk_msg_free(sk, &rec->msg_plaintext);
kfree(rec);
}
/* Tx all ready records */
list_for_each_entry_safe(rec, tmp, &ctx->tx_list, list) {
if (READ_ONCE(rec->tx_ready)) {
if (flags == -1)
tx_flags = rec->tx_flags;
else
tx_flags = flags;
msg_en = &rec->msg_encrypted;
rc = tls_push_sg(sk, tls_ctx,
&msg_en->sg.data[msg_en->sg.curr],
0, tx_flags);
if (rc)
goto tx_err;
list_del(&rec->list);
sk_msg_free(sk, &rec->msg_plaintext);
kfree(rec);
} else {
break;
}
}
tx_err:
if (rc < 0 && rc != -EAGAIN)
tls_err_abort(sk, -EBADMSG);
return rc;
}
static void tls_encrypt_done(struct crypto_async_request *req, int err)
{
struct aead_request *aead_req = (struct aead_request *)req;
struct sock *sk = req->data;
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct scatterlist *sge;
struct sk_msg *msg_en;
struct tls_rec *rec;
bool ready = false;
int pending;
rec = container_of(aead_req, struct tls_rec, aead_req);
msg_en = &rec->msg_encrypted;
sge = sk_msg_elem(msg_en, msg_en->sg.curr);
sge->offset -= prot->prepend_size;
sge->length += prot->prepend_size;
/* Check if error is previously set on socket */
if (err || sk->sk_err) {
rec = NULL;
/* If err is already set on socket, return the same code */
if (sk->sk_err) {
ctx->async_wait.err = -sk->sk_err;
} else {
ctx->async_wait.err = err;
tls_err_abort(sk, err);
}
}
if (rec) {
struct tls_rec *first_rec;
/* Mark the record as ready for transmission */
smp_store_mb(rec->tx_ready, true);
/* If received record is at head of tx_list, schedule tx */
first_rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
if (rec == first_rec)
ready = true;
}
spin_lock_bh(&ctx->encrypt_compl_lock);
pending = atomic_dec_return(&ctx->encrypt_pending);
if (!pending && ctx->async_notify)
complete(&ctx->async_wait.completion);
spin_unlock_bh(&ctx->encrypt_compl_lock);
if (!ready)
return;
/* Schedule the transmission */
if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
schedule_delayed_work(&ctx->tx_work.work, 1);
}
static int tls_do_encryption(struct sock *sk,
struct tls_context *tls_ctx,
struct tls_sw_context_tx *ctx,
struct aead_request *aead_req,
size_t data_len, u32 start)
{
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_rec *rec = ctx->open_rec;
struct sk_msg *msg_en = &rec->msg_encrypted;
struct scatterlist *sge = sk_msg_elem(msg_en, start);
int rc, iv_offset = 0;
/* For CCM based ciphers, first byte of IV is a constant */
switch (prot->cipher_type) {
case TLS_CIPHER_AES_CCM_128:
rec->iv_data[0] = TLS_AES_CCM_IV_B0_BYTE;
iv_offset = 1;
break;
case TLS_CIPHER_SM4_CCM:
rec->iv_data[0] = TLS_SM4_CCM_IV_B0_BYTE;
iv_offset = 1;
break;
}
memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
prot->iv_size + prot->salt_size);
tls_xor_iv_with_seq(prot, rec->iv_data + iv_offset,
tls_ctx->tx.rec_seq);
sge->offset += prot->prepend_size;
sge->length -= prot->prepend_size;
msg_en->sg.curr = start;
aead_request_set_tfm(aead_req, ctx->aead_send);
aead_request_set_ad(aead_req, prot->aad_size);
aead_request_set_crypt(aead_req, rec->sg_aead_in,
rec->sg_aead_out,
data_len, rec->iv_data);
aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
tls_encrypt_done, sk);
/* Add the record in tx_list */
list_add_tail((struct list_head *)&rec->list, &ctx->tx_list);
atomic_inc(&ctx->encrypt_pending);
rc = crypto_aead_encrypt(aead_req);
if (!rc || rc != -EINPROGRESS) {
atomic_dec(&ctx->encrypt_pending);
sge->offset -= prot->prepend_size;
sge->length += prot->prepend_size;
}
if (!rc) {
WRITE_ONCE(rec->tx_ready, true);
} else if (rc != -EINPROGRESS) {
list_del(&rec->list);
return rc;
}
/* Unhook the record from context if encryption is not failure */
ctx->open_rec = NULL;
tls_advance_record_sn(sk, prot, &tls_ctx->tx);
return rc;
}
static int tls_split_open_record(struct sock *sk, struct tls_rec *from,
struct tls_rec **to, struct sk_msg *msg_opl,
struct sk_msg *msg_oen, u32 split_point,
u32 tx_overhead_size, u32 *orig_end)
{
u32 i, j, bytes = 0, apply = msg_opl->apply_bytes;
struct scatterlist *sge, *osge, *nsge;
u32 orig_size = msg_opl->sg.size;
struct scatterlist tmp = { };
struct sk_msg *msg_npl;
struct tls_rec *new;
int ret;
new = tls_get_rec(sk);
if (!new)
return -ENOMEM;
ret = sk_msg_alloc(sk, &new->msg_encrypted, msg_opl->sg.size +
tx_overhead_size, 0);
if (ret < 0) {
tls_free_rec(sk, new);
return ret;
}
*orig_end = msg_opl->sg.end;
i = msg_opl->sg.start;
sge = sk_msg_elem(msg_opl, i);
while (apply && sge->length) {
if (sge->length > apply) {
u32 len = sge->length - apply;
get_page(sg_page(sge));
sg_set_page(&tmp, sg_page(sge), len,
sge->offset + apply);
sge->length = apply;
bytes += apply;
apply = 0;
} else {
apply -= sge->length;
bytes += sge->length;
}
sk_msg_iter_var_next(i);
if (i == msg_opl->sg.end)
break;
sge = sk_msg_elem(msg_opl, i);
}
msg_opl->sg.end = i;
msg_opl->sg.curr = i;
msg_opl->sg.copybreak = 0;
msg_opl->apply_bytes = 0;
msg_opl->sg.size = bytes;
msg_npl = &new->msg_plaintext;
msg_npl->apply_bytes = apply;
msg_npl->sg.size = orig_size - bytes;
j = msg_npl->sg.start;
nsge = sk_msg_elem(msg_npl, j);
if (tmp.length) {
memcpy(nsge, &tmp, sizeof(*nsge));
sk_msg_iter_var_next(j);
nsge = sk_msg_elem(msg_npl, j);
}
osge = sk_msg_elem(msg_opl, i);
while (osge->length) {
memcpy(nsge, osge, sizeof(*nsge));
sg_unmark_end(nsge);
sk_msg_iter_var_next(i);
sk_msg_iter_var_next(j);
if (i == *orig_end)
break;
osge = sk_msg_elem(msg_opl, i);
nsge = sk_msg_elem(msg_npl, j);
}
msg_npl->sg.end = j;
msg_npl->sg.curr = j;
msg_npl->sg.copybreak = 0;
*to = new;
return 0;
}
static void tls_merge_open_record(struct sock *sk, struct tls_rec *to,
struct tls_rec *from, u32 orig_end)
{
struct sk_msg *msg_npl = &from->msg_plaintext;
struct sk_msg *msg_opl = &to->msg_plaintext;
struct scatterlist *osge, *nsge;
u32 i, j;
i = msg_opl->sg.end;
sk_msg_iter_var_prev(i);
j = msg_npl->sg.start;
osge = sk_msg_elem(msg_opl, i);
nsge = sk_msg_elem(msg_npl, j);
if (sg_page(osge) == sg_page(nsge) &&
osge->offset + osge->length == nsge->offset) {
osge->length += nsge->length;
put_page(sg_page(nsge));
}
msg_opl->sg.end = orig_end;
msg_opl->sg.curr = orig_end;
msg_opl->sg.copybreak = 0;
msg_opl->apply_bytes = msg_opl->sg.size + msg_npl->sg.size;
msg_opl->sg.size += msg_npl->sg.size;
sk_msg_free(sk, &to->msg_encrypted);
sk_msg_xfer_full(&to->msg_encrypted, &from->msg_encrypted);
kfree(from);
}
static int tls_push_record(struct sock *sk, int flags,
unsigned char record_type)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec, *tmp = NULL;
u32 i, split_point, orig_end;
struct sk_msg *msg_pl, *msg_en;
struct aead_request *req;
bool split;
int rc;
if (!rec)
return 0;
msg_pl = &rec->msg_plaintext;
msg_en = &rec->msg_encrypted;
split_point = msg_pl->apply_bytes;
split = split_point && split_point < msg_pl->sg.size;
if (unlikely((!split &&
msg_pl->sg.size +
prot->overhead_size > msg_en->sg.size) ||
(split &&
split_point +
prot->overhead_size > msg_en->sg.size))) {
split = true;
split_point = msg_en->sg.size;
}
if (split) {
rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en,
split_point, prot->overhead_size,
&orig_end);
if (rc < 0)
return rc;
/* This can happen if above tls_split_open_record allocates
* a single large encryption buffer instead of two smaller
* ones. In this case adjust pointers and continue without
* split.
*/
if (!msg_pl->sg.size) {
tls_merge_open_record(sk, rec, tmp, orig_end);
msg_pl = &rec->msg_plaintext;
msg_en = &rec->msg_encrypted;
split = false;
}
sk_msg_trim(sk, msg_en, msg_pl->sg.size +
prot->overhead_size);
}
rec->tx_flags = flags;
req = &rec->aead_req;
i = msg_pl->sg.end;
sk_msg_iter_var_prev(i);
rec->content_type = record_type;
if (prot->version == TLS_1_3_VERSION) {
/* Add content type to end of message. No padding added */
sg_set_buf(&rec->sg_content_type, &rec->content_type, 1);
sg_mark_end(&rec->sg_content_type);
sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1,
&rec->sg_content_type);
} else {
sg_mark_end(sk_msg_elem(msg_pl, i));
}
if (msg_pl->sg.end < msg_pl->sg.start) {
sg_chain(&msg_pl->sg.data[msg_pl->sg.start],
MAX_SKB_FRAGS - msg_pl->sg.start + 1,
msg_pl->sg.data);
}
i = msg_pl->sg.start;
sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
i = msg_en->sg.end;
sk_msg_iter_var_prev(i);
sg_mark_end(sk_msg_elem(msg_en, i));
i = msg_en->sg.start;
sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]);
tls_make_aad(rec->aad_space, msg_pl->sg.size + prot->tail_size,
tls_ctx->tx.rec_seq, record_type, prot);
tls_fill_prepend(tls_ctx,
page_address(sg_page(&msg_en->sg.data[i])) +
msg_en->sg.data[i].offset,
msg_pl->sg.size + prot->tail_size,
record_type);
tls_ctx->pending_open_record_frags = false;
rc = tls_do_encryption(sk, tls_ctx, ctx, req,
msg_pl->sg.size + prot->tail_size, i);
if (rc < 0) {
if (rc != -EINPROGRESS) {
tls_err_abort(sk, -EBADMSG);
if (split) {
tls_ctx->pending_open_record_frags = true;
tls_merge_open_record(sk, rec, tmp, orig_end);
}
}
ctx->async_capable = 1;
return rc;
} else if (split) {
msg_pl = &tmp->msg_plaintext;
msg_en = &tmp->msg_encrypted;
sk_msg_trim(sk, msg_en, msg_pl->sg.size + prot->overhead_size);
tls_ctx->pending_open_record_frags = true;
ctx->open_rec = tmp;
}
return tls_tx_records(sk, flags);
}
static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
bool full_record, u8 record_type,
ssize_t *copied, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct sk_msg msg_redir = { };
struct sk_psock *psock;
struct sock *sk_redir;
struct tls_rec *rec;
bool enospc, policy;
int err = 0, send;
u32 delta = 0;
policy = !(flags & MSG_SENDPAGE_NOPOLICY);
psock = sk_psock_get(sk);
if (!psock || !policy) {
err = tls_push_record(sk, flags, record_type);
if (err && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
err = -sk->sk_err;
}
if (psock)
sk_psock_put(sk, psock);
return err;
}
more_data:
enospc = sk_msg_full(msg);
if (psock->eval == __SK_NONE) {
delta = msg->sg.size;
psock->eval = sk_psock_msg_verdict(sk, psock, msg);
delta -= msg->sg.size;
}
if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
!enospc && !full_record) {
err = -ENOSPC;
goto out_err;
}
msg->cork_bytes = 0;
send = msg->sg.size;
if (msg->apply_bytes && msg->apply_bytes < send)
send = msg->apply_bytes;
switch (psock->eval) {
case __SK_PASS:
err = tls_push_record(sk, flags, record_type);
if (err && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
err = -sk->sk_err;
goto out_err;
}
break;
case __SK_REDIRECT:
sk_redir = psock->sk_redir;
memcpy(&msg_redir, msg, sizeof(*msg));
if (msg->apply_bytes < send)
msg->apply_bytes = 0;
else
msg->apply_bytes -= send;
sk_msg_return_zero(sk, msg, send);
msg->sg.size -= send;
release_sock(sk);
err = tcp_bpf_sendmsg_redir(sk_redir, &msg_redir, send, flags);
lock_sock(sk);
if (err < 0) {
*copied -= sk_msg_free_nocharge(sk, &msg_redir);
msg->sg.size = 0;
}
if (msg->sg.size == 0)
tls_free_open_rec(sk);
break;
case __SK_DROP:
default:
sk_msg_free_partial(sk, msg, send);
if (msg->apply_bytes < send)
msg->apply_bytes = 0;
else
msg->apply_bytes -= send;
if (msg->sg.size == 0)
tls_free_open_rec(sk);
*copied -= (send + delta);
err = -EACCES;
}
if (likely(!err)) {
bool reset_eval = !ctx->open_rec;
rec = ctx->open_rec;
if (rec) {
msg = &rec->msg_plaintext;
if (!msg->apply_bytes)
reset_eval = true;
}
if (reset_eval) {
psock->eval = __SK_NONE;
if (psock->sk_redir) {
sock_put(psock->sk_redir);
psock->sk_redir = NULL;
}
}
if (rec)
goto more_data;
}
out_err:
sk_psock_put(sk, psock);
return err;
}
static int tls_sw_push_pending_record(struct sock *sk, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec = ctx->open_rec;
struct sk_msg *msg_pl;
size_t copied;
if (!rec)
return 0;
msg_pl = &rec->msg_plaintext;
copied = msg_pl->sg.size;
if (!copied)
return 0;
return bpf_exec_tx_verdict(msg_pl, sk, true, TLS_RECORD_TYPE_DATA,
&copied, flags);
}
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
bool async_capable = ctx->async_capable;
unsigned char record_type = TLS_RECORD_TYPE_DATA;
bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
bool eor = !(msg->msg_flags & MSG_MORE);
size_t try_to_copy;
ssize_t copied = 0;
struct sk_msg *msg_pl, *msg_en;
struct tls_rec *rec;
int required_size;
int num_async = 0;
bool full_record;
int record_room;
int num_zc = 0;
int orig_size;
int ret = 0;
int pending;
if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
MSG_CMSG_COMPAT))
return -EOPNOTSUPP;
mutex_lock(&tls_ctx->tx_lock);
lock_sock(sk);
if (unlikely(msg->msg_controllen)) {
ret = tls_process_cmsg(sk, msg, &record_type);
if (ret) {
if (ret == -EINPROGRESS)
num_async++;
else if (ret != -EAGAIN)
goto send_end;
}
}
while (msg_data_left(msg)) {
if (sk->sk_err) {
ret = -sk->sk_err;
goto send_end;
}
if (ctx->open_rec)
rec = ctx->open_rec;
else
rec = ctx->open_rec = tls_get_rec(sk);
if (!rec) {
ret = -ENOMEM;
goto send_end;
}
msg_pl = &rec->msg_plaintext;
msg_en = &rec->msg_encrypted;
orig_size = msg_pl->sg.size;
full_record = false;
try_to_copy = msg_data_left(msg);
record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
if (try_to_copy >= record_room) {
try_to_copy = record_room;
full_record = true;
}
required_size = msg_pl->sg.size + try_to_copy +
prot->overhead_size;
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
alloc_encrypted:
ret = tls_alloc_encrypted_msg(sk, required_size);
if (ret) {
if (ret != -ENOSPC)
goto wait_for_memory;
/* Adjust try_to_copy according to the amount that was
* actually allocated. The difference is due
* to max sg elements limit
*/
try_to_copy -= required_size - msg_en->sg.size;
full_record = true;
}
if (!is_kvec && (full_record || eor) && !async_capable) {
u32 first = msg_pl->sg.end;
ret = sk_msg_zerocopy_from_iter(sk, &msg->msg_iter,
msg_pl, try_to_copy);
if (ret)
goto fallback_to_reg_send;
num_zc++;
copied += try_to_copy;
sk_msg_sg_copy_set(msg_pl, first);
ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
record_type, &copied,
msg->msg_flags);
if (ret) {
if (ret == -EINPROGRESS)
num_async++;
else if (ret == -ENOMEM)
goto wait_for_memory;
else if (ctx->open_rec && ret == -ENOSPC)
goto rollback_iter;
else if (ret != -EAGAIN)
goto send_end;
}
continue;
rollback_iter:
copied -= try_to_copy;
sk_msg_sg_copy_clear(msg_pl, first);
iov_iter_revert(&msg->msg_iter,
msg_pl->sg.size - orig_size);
fallback_to_reg_send:
sk_msg_trim(sk, msg_pl, orig_size);
}
required_size = msg_pl->sg.size + try_to_copy;
ret = tls_clone_plaintext_msg(sk, required_size);
if (ret) {
if (ret != -ENOSPC)
goto send_end;
/* Adjust try_to_copy according to the amount that was
* actually allocated. The difference is due
* to max sg elements limit
*/
try_to_copy -= required_size - msg_pl->sg.size;
full_record = true;
sk_msg_trim(sk, msg_en,
msg_pl->sg.size + prot->overhead_size);
}
if (try_to_copy) {
ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter,
msg_pl, try_to_copy);
if (ret < 0)
goto trim_sgl;
}
/* Open records defined only if successfully copied, otherwise
* we would trim the sg but not reset the open record frags.
*/
tls_ctx->pending_open_record_frags = true;
copied += try_to_copy;
if (full_record || eor) {
ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
record_type, &copied,
msg->msg_flags);
if (ret) {
if (ret == -EINPROGRESS)
num_async++;
else if (ret == -ENOMEM)
goto wait_for_memory;
else if (ret != -EAGAIN) {
if (ret == -ENOSPC)
ret = 0;
goto send_end;
}
}
}
continue;
wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
ret = sk_stream_wait_memory(sk, &timeo);
if (ret) {
trim_sgl:
if (ctx->open_rec)
tls_trim_both_msgs(sk, orig_size);
goto send_end;
}
if (ctx->open_rec && msg_en->sg.size < required_size)
goto alloc_encrypted;
}
if (!num_async) {
goto send_end;
} else if (num_zc) {
/* Wait for pending encryptions to get completed */
spin_lock_bh(&ctx->encrypt_compl_lock);
ctx->async_notify = true;
pending = atomic_read(&ctx->encrypt_pending);
spin_unlock_bh(&ctx->encrypt_compl_lock);
if (pending)
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
else
reinit_completion(&ctx->async_wait.completion);
/* There can be no concurrent accesses, since we have no
* pending encrypt operations
*/
WRITE_ONCE(ctx->async_notify, false);
if (ctx->async_wait.err) {
ret = ctx->async_wait.err;
copied = 0;
}
}
/* Transmit if any encryptions have completed */
if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
cancel_delayed_work(&ctx->tx_work.work);
tls_tx_records(sk, msg->msg_flags);
}
send_end:
ret = sk_stream_error(sk, msg->msg_flags, ret);
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
return copied > 0 ? copied : ret;
}
static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_prot_info *prot = &tls_ctx->prot_info;
unsigned char record_type = TLS_RECORD_TYPE_DATA;
struct sk_msg *msg_pl;
struct tls_rec *rec;
int num_async = 0;
ssize_t copied = 0;
bool full_record;
int record_room;
int ret = 0;
bool eor;
eor = !(flags & MSG_SENDPAGE_NOTLAST);
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
/* Call the sk_stream functions to manage the sndbuf mem. */
while (size > 0) {
size_t copy, required_size;
if (sk->sk_err) {
ret = -sk->sk_err;
goto sendpage_end;
}
if (ctx->open_rec)
rec = ctx->open_rec;
else
rec = ctx->open_rec = tls_get_rec(sk);
if (!rec) {
ret = -ENOMEM;
goto sendpage_end;
}
msg_pl = &rec->msg_plaintext;
full_record = false;
record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size;
copy = size;
if (copy >= record_room) {
copy = record_room;
full_record = true;
}
required_size = msg_pl->sg.size + copy + prot->overhead_size;
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
alloc_payload:
ret = tls_alloc_encrypted_msg(sk, required_size);
if (ret) {
if (ret != -ENOSPC)
goto wait_for_memory;
/* Adjust copy according to the amount that was
* actually allocated. The difference is due
* to max sg elements limit
*/
copy -= required_size - msg_pl->sg.size;
full_record = true;
}
sk_msg_page_add(msg_pl, page, copy, offset);
sk_mem_charge(sk, copy);
offset += copy;
size -= copy;
copied += copy;
tls_ctx->pending_open_record_frags = true;
if (full_record || eor || sk_msg_full(msg_pl)) {
ret = bpf_exec_tx_verdict(msg_pl, sk, full_record,
record_type, &copied, flags);
if (ret) {
if (ret == -EINPROGRESS)
num_async++;
else if (ret == -ENOMEM)
goto wait_for_memory;
else if (ret != -EAGAIN) {
if (ret == -ENOSPC)
ret = 0;
goto sendpage_end;
}
}
}
continue;
wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
ret = sk_stream_wait_memory(sk, &timeo);
if (ret) {
if (ctx->open_rec)
tls_trim_both_msgs(sk, msg_pl->sg.size);
goto sendpage_end;
}
if (ctx->open_rec)
goto alloc_payload;
}
if (num_async) {
/* Transmit if any encryptions have completed */
if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
cancel_delayed_work(&ctx->tx_work.work);
tls_tx_records(sk, flags);
}
}
sendpage_end:
ret = sk_stream_error(sk, flags, ret);
return copied > 0 ? copied : ret;
}
int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY |
MSG_NO_SHARED_FRAGS))
return -EOPNOTSUPP;
return tls_sw_do_sendpage(sk, page, offset, size, flags);
}
int tls_sw_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
int ret;
if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
return -EOPNOTSUPP;
mutex_lock(&tls_ctx->tx_lock);
lock_sock(sk);
ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
return ret;
}
static int
tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
long timeo)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
while (!ctx->recv_pkt) {
if (!sk_psock_queue_empty(psock))
return 0;
if (sk->sk_err)
return sock_error(sk);
if (!skb_queue_empty(&sk->sk_receive_queue)) {
__strp_unpause(&ctx->strp);
if (ctx->recv_pkt)
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN)
return 0;
if (sock_flag(sk, SOCK_DONE))
return 0;
if (nonblock || !timeo)
return -EAGAIN;
add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
sk_wait_event(sk, &timeo,
ctx->recv_pkt || !sk_psock_queue_empty(psock),
&wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
/* Handle signals */
if (signal_pending(current))
return sock_intr_errno(timeo);
}
return 1;
}
static int tls_setup_from_iter(struct iov_iter *from,
int length, int *pages_used,
struct scatterlist *to,
int to_max_pages)
{
int rc = 0, i = 0, num_elem = *pages_used, maxpages;
struct page *pages[MAX_SKB_FRAGS];
unsigned int size = 0;
ssize_t copied, use;
size_t offset;
while (length > 0) {
i = 0;
maxpages = to_max_pages - num_elem;
if (maxpages == 0) {
rc = -EFAULT;
goto out;
}
copied = iov_iter_get_pages(from, pages,
length,
maxpages, &offset);
if (copied <= 0) {
rc = -EFAULT;
goto out;
}
iov_iter_advance(from, copied);
length -= copied;
size += copied;
while (copied) {
use = min_t(int, copied, PAGE_SIZE - offset);
sg_set_page(&to[num_elem],
pages[i], use, offset);
sg_unmark_end(&to[num_elem]);
/* We do not uncharge memory from this API */
offset = 0;
copied -= use;
i++;
num_elem++;
}
}
/* Mark the end in the last sg entry if newly added */
if (num_elem > *pages_used)
sg_mark_end(&to[num_elem - 1]);
out:
if (rc)
iov_iter_revert(from, size);
*pages_used = num_elem;
return rc;
}
/* Decrypt handlers
*
* tls_decrypt_sg() and tls_decrypt_device() are decrypt handlers.
* They must transform the darg in/out argument are as follows:
* | Input | Output
* -------------------------------------------------------------------
* zc | Zero-copy decrypt allowed | Zero-copy performed
* async | Async decrypt allowed | Async crypto used / in progress
* skb | * | Output skb
*/
/* This function decrypts the input skb into either out_iov or in out_sg
* or in skb buffers itself. The input parameter 'darg->zc' indicates if
* zero-copy mode needs to be tried or not. With zero-copy mode, either
* out_iov or out_sg must be non-NULL. In case both out_iov and out_sg are
* NULL, then the decryption happens inside skb buffers itself, i.e.
* zero-copy gets disabled and 'darg->zc' is updated.
*/
static int tls_decrypt_sg(struct sock *sk, struct iov_iter *out_iov,
struct scatterlist *out_sg,
struct tls_decrypt_arg *darg)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct tls_prot_info *prot = &tls_ctx->prot_info;
int n_sgin, n_sgout, aead_size, err, pages = 0;
struct sk_buff *skb = tls_strp_msg(ctx);
struct strp_msg *rxm = strp_msg(skb);
struct tls_msg *tlm = tls_msg(skb);
struct aead_request *aead_req;
struct sk_buff *unused;
struct scatterlist *sgin = NULL;
struct scatterlist *sgout = NULL;
const int data_len = rxm->full_len - prot->overhead_size;
int tail_pages = !!prot->tail_size;
struct tls_decrypt_ctx *dctx;
int iv_offset = 0;
u8 *mem;
if (darg->zc && (out_iov || out_sg)) {
if (out_iov)
n_sgout = 1 + tail_pages +
iov_iter_npages_cap(out_iov, INT_MAX, data_len);
else
n_sgout = sg_nents(out_sg);
n_sgin = skb_nsg(skb, rxm->offset + prot->prepend_size,
rxm->full_len - prot->prepend_size);
} else {
n_sgout = 0;
darg->zc = false;
n_sgin = skb_cow_data(skb, 0, &unused);
}
if (n_sgin < 1)
return -EBADMSG;
/* Increment to accommodate AAD */
n_sgin = n_sgin + 1;
/* Allocate a single block of memory which contains
* aead_req || tls_decrypt_ctx.
* Both structs are variable length.
*/
aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv);
mem = kmalloc(aead_size + struct_size(dctx, sg, n_sgin + n_sgout),
sk->sk_allocation);
if (!mem)
return -ENOMEM;
/* Segment the allocated memory */
aead_req = (struct aead_request *)mem;
dctx = (struct tls_decrypt_ctx *)(mem + aead_size);
sgin = &dctx->sg[0];
sgout = &dctx->sg[n_sgin];
/* For CCM based ciphers, first byte of nonce+iv is a constant */
switch (prot->cipher_type) {
case TLS_CIPHER_AES_CCM_128:
dctx->iv[0] = TLS_AES_CCM_IV_B0_BYTE;
iv_offset = 1;
break;
case TLS_CIPHER_SM4_CCM:
dctx->iv[0] = TLS_SM4_CCM_IV_B0_BYTE;
iv_offset = 1;
break;
}
/* Prepare IV */
if (prot->version == TLS_1_3_VERSION ||
prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) {
memcpy(&dctx->iv[iv_offset], tls_ctx->rx.iv,
prot->iv_size + prot->salt_size);
} else {
err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
&dctx->iv[iv_offset] + prot->salt_size,
prot->iv_size);
if (err < 0)
goto exit_free;
memcpy(&dctx->iv[iv_offset], tls_ctx->rx.iv, prot->salt_size);
}
tls_xor_iv_with_seq(prot, &dctx->iv[iv_offset], tls_ctx->rx.rec_seq);
/* Prepare AAD */
tls_make_aad(dctx->aad, rxm->full_len - prot->overhead_size +
prot->tail_size,
tls_ctx->rx.rec_seq, tlm->control, prot);
/* Prepare sgin */
sg_init_table(sgin, n_sgin);
sg_set_buf(&sgin[0], dctx->aad, prot->aad_size);
err = skb_to_sgvec(skb, &sgin[1],
rxm->offset + prot->prepend_size,
rxm->full_len - prot->prepend_size);
if (err < 0)
goto exit_free;
if (n_sgout) {
if (out_iov) {
sg_init_table(sgout, n_sgout);
sg_set_buf(&sgout[0], dctx->aad, prot->aad_size);
err = tls_setup_from_iter(out_iov, data_len,
&pages, &sgout[1],
(n_sgout - 1 - tail_pages));
if (err < 0)
goto fallback_to_reg_recv;
if (prot->tail_size) {
sg_unmark_end(&sgout[pages]);
sg_set_buf(&sgout[pages + 1], &dctx->tail,
prot->tail_size);
sg_mark_end(&sgout[pages + 1]);
}
} else if (out_sg) {
memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
} else {
goto fallback_to_reg_recv;
}
} else {
fallback_to_reg_recv:
sgout = sgin;
pages = 0;
darg->zc = false;
}
/* Prepare and submit AEAD request */
err = tls_do_decryption(sk, sgin, sgout, dctx->iv,
data_len + prot->tail_size, aead_req, darg);
if (err)
goto exit_free_pages;
darg->skb = tls_strp_msg(ctx);
if (darg->async)
return 0;
if (prot->tail_size)
darg->tail = dctx->tail;
exit_free_pages:
/* Release the pages in case iov was mapped to pages */
for (; pages > 0; pages--)
put_page(sg_page(&sgout[pages]));
exit_free:
kfree(mem);
return err;
}
static int
tls_decrypt_device(struct sock *sk, struct tls_context *tls_ctx,
struct tls_decrypt_arg *darg)
{
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
int err;
if (tls_ctx->rx_conf != TLS_HW)
return 0;
err = tls_device_decrypted(sk, tls_ctx);
if (err <= 0)
return err;
darg->zc = false;
darg->async = false;
darg->skb = tls_strp_msg(ctx);
ctx->recv_pkt = NULL;
return 1;
}
static int tls_rx_one_record(struct sock *sk, struct iov_iter *dest,
struct tls_decrypt_arg *darg)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct strp_msg *rxm;
int pad, err;
err = tls_decrypt_device(sk, tls_ctx, darg);
if (err < 0)
return err;
if (err)
goto decrypt_done;
err = tls_decrypt_sg(sk, dest, NULL, darg);
if (err < 0) {
if (err == -EBADMSG)
TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR);
return err;
}
if (darg->async)
goto decrypt_done;
/* If opportunistic TLS 1.3 ZC failed retry without ZC */
if (unlikely(darg->zc && prot->version == TLS_1_3_VERSION &&
darg->tail != TLS_RECORD_TYPE_DATA)) {
darg->zc = false;
if (!darg->tail)
TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXNOPADVIOL);
TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTRETRY);
return tls_rx_one_record(sk, dest, darg);
}
decrypt_done:
if (darg->skb == ctx->recv_pkt)
ctx->recv_pkt = NULL;
pad = tls_padding_length(prot, darg->skb, darg);
if (pad < 0) {
consume_skb(darg->skb);
return pad;
}
rxm = strp_msg(darg->skb);
rxm->full_len -= pad;
rxm->offset += prot->prepend_size;
rxm->full_len -= prot->overhead_size;
tls_advance_record_sn(sk, prot, &tls_ctx->rx);
return 0;
}
int decrypt_skb(struct sock *sk, struct scatterlist *sgout)
{
struct tls_decrypt_arg darg = { .zc = true, };
return tls_decrypt_sg(sk, NULL, sgout, &darg);
}
static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm,
u8 *control)
{
int err;
if (!*control) {
*control = tlm->control;
if (!*control)
return -EBADMSG;
err = put_cmsg(msg, SOL_TLS, TLS_GET_RECORD_TYPE,
sizeof(*control), control);
if (*control != TLS_RECORD_TYPE_DATA) {
if (err || msg->msg_flags & MSG_CTRUNC)
return -EIO;
}
} else if (*control != tlm->control) {
return 0;
}
return 1;
}
static void tls_rx_rec_done(struct tls_sw_context_rx *ctx)
{
consume_skb(ctx->recv_pkt);
ctx->recv_pkt = NULL;
__strp_unpause(&ctx->strp);
}
/* This function traverses the rx_list in tls receive context to copies the
* decrypted records into the buffer provided by caller zero copy is not
* true. Further, the records are removed from the rx_list if it is not a peek
* case and the record has been consumed completely.
*/
static int process_rx_list(struct tls_sw_context_rx *ctx,
struct msghdr *msg,
u8 *control,
size_t skip,
size_t len,
bool zc,
bool is_peek)
{
struct sk_buff *skb = skb_peek(&ctx->rx_list);
struct tls_msg *tlm;
ssize_t copied = 0;
int err;
while (skip && skb) {
struct strp_msg *rxm = strp_msg(skb);
tlm = tls_msg(skb);
err = tls_record_content_type(msg, tlm, control);
if (err <= 0)
goto out;
if (skip < rxm->full_len)
break;
skip = skip - rxm->full_len;
skb = skb_peek_next(skb, &ctx->rx_list);
}
while (len && skb) {
struct sk_buff *next_skb;
struct strp_msg *rxm = strp_msg(skb);
int chunk = min_t(unsigned int, rxm->full_len - skip, len);
tlm = tls_msg(skb);
err = tls_record_content_type(msg, tlm, control);
if (err <= 0)
goto out;
if (!zc || (rxm->full_len - skip) > len) {
err = skb_copy_datagram_msg(skb, rxm->offset + skip,
msg, chunk);
if (err < 0)
goto out;
}
len = len - chunk;
copied = copied + chunk;
/* Consume the data from record if it is non-peek case*/
if (!is_peek) {
rxm->offset = rxm->offset + chunk;
rxm->full_len = rxm->full_len - chunk;
/* Return if there is unconsumed data in the record */
if (rxm->full_len - skip)
break;
}
/* The remaining skip-bytes must lie in 1st record in rx_list.
* So from the 2nd record, 'skip' should be 0.
*/
skip = 0;
if (msg)
msg->msg_flags |= MSG_EOR;
next_skb = skb_peek_next(skb, &ctx->rx_list);
if (!is_peek) {
__skb_unlink(skb, &ctx->rx_list);
consume_skb(skb);
}
skb = next_skb;
}
err = 0;
out:
return copied ? : err;
}
static void
tls_read_flush_backlog(struct sock *sk, struct tls_prot_info *prot,
size_t len_left, size_t decrypted, ssize_t done,
size_t *flushed_at)
{
size_t max_rec;
if (len_left <= decrypted)
return;
max_rec = prot->overhead_size - prot->tail_size + TLS_MAX_PAYLOAD_SIZE;
if (done - *flushed_at < SZ_128K && tcp_inq(sk) > max_rec)
return;
*flushed_at = done;
sk_flush_backlog(sk);
}
static long tls_rx_reader_lock(struct sock *sk, struct tls_sw_context_rx *ctx,
bool nonblock)
{
long timeo;
lock_sock(sk);
timeo = sock_rcvtimeo(sk, nonblock);
while (unlikely(ctx->reader_present)) {
DEFINE_WAIT_FUNC(wait, woken_wake_function);
ctx->reader_contended = 1;
add_wait_queue(&ctx->wq, &wait);
sk_wait_event(sk, &timeo,
!READ_ONCE(ctx->reader_present), &wait);
remove_wait_queue(&ctx->wq, &wait);
if (!timeo)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(timeo);
}
WRITE_ONCE(ctx->reader_present, 1);
return timeo;
}
static void tls_rx_reader_unlock(struct sock *sk, struct tls_sw_context_rx *ctx)
{
if (unlikely(ctx->reader_contended)) {
if (wq_has_sleeper(&ctx->wq))
wake_up(&ctx->wq);
else
ctx->reader_contended = 0;
WARN_ON_ONCE(!ctx->reader_present);
}
WRITE_ONCE(ctx->reader_present, 0);
release_sock(sk);
}
int tls_sw_recvmsg(struct sock *sk,
struct msghdr *msg,
size_t len,
int flags,
int *addr_len)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct sk_psock *psock;
unsigned char control = 0;
ssize_t decrypted = 0;
size_t flushed_at = 0;
struct strp_msg *rxm;
struct tls_msg *tlm;
struct sk_buff *skb;
ssize_t copied = 0;
bool async = false;
int target, err = 0;
long timeo;
bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
bool is_peek = flags & MSG_PEEK;
bool bpf_strp_enabled;
bool zc_capable;
if (unlikely(flags & MSG_ERRQUEUE))
return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR);
psock = sk_psock_get(sk);
timeo = tls_rx_reader_lock(sk, ctx, flags & MSG_DONTWAIT);
if (timeo < 0)
return timeo;
bpf_strp_enabled = sk_psock_strp_enabled(psock);
/* If crypto failed the connection is broken */
err = ctx->async_wait.err;
if (err)
goto end;
/* Process pending decrypted records. It must be non-zero-copy */
err = process_rx_list(ctx, msg, &control, 0, len, false, is_peek);
if (err < 0)
goto end;
copied = err;
if (len <= copied)
goto end;
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
len = len - copied;
zc_capable = !bpf_strp_enabled && !is_kvec && !is_peek &&
ctx->zc_capable;
decrypted = 0;
while (len && (decrypted + copied < target || ctx->recv_pkt)) {
struct tls_decrypt_arg darg;
int to_decrypt, chunk;
err = tls_rx_rec_wait(sk, psock, flags & MSG_DONTWAIT, timeo);
if (err <= 0) {
if (psock) {
chunk = sk_msg_recvmsg(sk, psock, msg, len,
flags);
if (chunk > 0) {
decrypted += chunk;
len -= chunk;
continue;
}
}
goto recv_end;
}
memset(&darg.inargs, 0, sizeof(darg.inargs));
rxm = strp_msg(ctx->recv_pkt);
tlm = tls_msg(ctx->recv_pkt);
to_decrypt = rxm->full_len - prot->overhead_size;
if (zc_capable && to_decrypt <= len &&
tlm->control == TLS_RECORD_TYPE_DATA)
darg.zc = true;
/* Do not use async mode if record is non-data */
if (tlm->control == TLS_RECORD_TYPE_DATA && !bpf_strp_enabled)
darg.async = ctx->async_capable;
else
darg.async = false;
err = tls_rx_one_record(sk, &msg->msg_iter, &darg);
if (err < 0) {
tls_err_abort(sk, -EBADMSG);
goto recv_end;
}
skb = darg.skb;
rxm = strp_msg(skb);
tlm = tls_msg(skb);
async |= darg.async;
/* If the type of records being processed is not known yet,
* set it to record type just dequeued. If it is already known,
* but does not match the record type just dequeued, go to end.
* We always get record type here since for tls1.2, record type
* is known just after record is dequeued from stream parser.
* For tls1.3, we disable async.
*/
err = tls_record_content_type(msg, tlm, &control);
if (err <= 0) {
tls_rx_rec_done(ctx);
put_on_rx_list_err:
__skb_queue_tail(&ctx->rx_list, skb);
goto recv_end;
}
/* periodically flush backlog, and feed strparser */
tls_read_flush_backlog(sk, prot, len, to_decrypt,
decrypted + copied, &flushed_at);
/* TLS 1.3 may have updated the length by more than overhead */
chunk = rxm->full_len;
tls_rx_rec_done(ctx);
if (async) {
/* TLS 1.2-only, to_decrypt must be text length */
chunk = min_t(int, to_decrypt, len);
put_on_rx_list:
decrypted += chunk;
len -= chunk;
__skb_queue_tail(&ctx->rx_list, skb);
continue;
}
if (!darg.zc) {
bool partially_consumed = chunk > len;
if (bpf_strp_enabled) {
err = sk_psock_tls_strp_read(psock, skb);
if (err != __SK_PASS) {
rxm->offset = rxm->offset + rxm->full_len;
rxm->full_len = 0;
if (err == __SK_DROP)
consume_skb(skb);
continue;
}
}
if (partially_consumed)
chunk = len;
err = skb_copy_datagram_msg(skb, rxm->offset,
msg, chunk);
if (err < 0)
goto put_on_rx_list_err;
if (is_peek)
goto put_on_rx_list;
if (partially_consumed) {
rxm->offset += chunk;
rxm->full_len -= chunk;
goto put_on_rx_list;
}
}
decrypted += chunk;
len -= chunk;
consume_skb(skb);
/* Return full control message to userspace before trying
* to parse another message type
*/
msg->msg_flags |= MSG_EOR;
if (control != TLS_RECORD_TYPE_DATA)
break;
}
recv_end:
if (async) {
int ret, pending;
/* Wait for all previously submitted records to be decrypted */
spin_lock_bh(&ctx->decrypt_compl_lock);
reinit_completion(&ctx->async_wait.completion);
pending = atomic_read(&ctx->decrypt_pending);
spin_unlock_bh(&ctx->decrypt_compl_lock);
if (pending) {
ret = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
if (ret) {
if (err >= 0 || err == -EINPROGRESS)
err = ret;
decrypted = 0;
goto end;
}
}
/* Drain records from the rx_list & copy if required */
if (is_peek || is_kvec)
err = process_rx_list(ctx, msg, &control, copied,
decrypted, false, is_peek);
else
err = process_rx_list(ctx, msg, &control, 0,
decrypted, true, is_peek);
decrypted = max(err, 0);
}
copied += decrypted;
end:
tls_rx_reader_unlock(sk, ctx);
if (psock)
sk_psock_put(sk, psock);
return copied ? : err;
}
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
{
struct tls_context *tls_ctx = tls_get_ctx(sock->sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct strp_msg *rxm = NULL;
struct sock *sk = sock->sk;
struct tls_msg *tlm;
struct sk_buff *skb;
ssize_t copied = 0;
int err = 0;
long timeo;
int chunk;
timeo = tls_rx_reader_lock(sk, ctx, flags & SPLICE_F_NONBLOCK);
if (timeo < 0)
return timeo;
if (!skb_queue_empty(&ctx->rx_list)) {
skb = __skb_dequeue(&ctx->rx_list);
} else {
struct tls_decrypt_arg darg;
err = tls_rx_rec_wait(sk, NULL, flags & SPLICE_F_NONBLOCK,
timeo);
if (err <= 0)
goto splice_read_end;
memset(&darg.inargs, 0, sizeof(darg.inargs));
err = tls_rx_one_record(sk, NULL, &darg);
if (err < 0) {
tls_err_abort(sk, -EBADMSG);
goto splice_read_end;
}
tls_rx_rec_done(ctx);
skb = darg.skb;
}
rxm = strp_msg(skb);
tlm = tls_msg(skb);
/* splice does not support reading control messages */
if (tlm->control != TLS_RECORD_TYPE_DATA) {
err = -EINVAL;
goto splice_requeue;
}
chunk = min_t(unsigned int, rxm->full_len, len);
copied = skb_splice_bits(skb, sk, rxm->offset, pipe, chunk, flags);
if (copied < 0)
goto splice_requeue;
if (chunk < rxm->full_len) {
rxm->offset += len;
rxm->full_len -= len;
goto splice_requeue;
}
consume_skb(skb);
splice_read_end:
tls_rx_reader_unlock(sk, ctx);
return copied ? : err;
splice_requeue:
__skb_queue_head(&ctx->rx_list, skb);
goto splice_read_end;
}
bool tls_sw_sock_is_readable(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
bool ingress_empty = true;
struct sk_psock *psock;
rcu_read_lock();
psock = sk_psock(sk);
if (psock)
ingress_empty = list_empty(&psock->ingress_msg);
rcu_read_unlock();
return !ingress_empty || ctx->recv_pkt ||
!skb_queue_empty(&ctx->rx_list);
}
static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
char header[TLS_HEADER_SIZE + MAX_IV_SIZE];
struct strp_msg *rxm = strp_msg(skb);
struct tls_msg *tlm = tls_msg(skb);
size_t cipher_overhead;
size_t data_len = 0;
int ret;
/* Verify that we have a full TLS header, or wait for more data */
if (rxm->offset + prot->prepend_size > skb->len)
return 0;
/* Sanity-check size of on-stack buffer. */
if (WARN_ON(prot->prepend_size > sizeof(header))) {
ret = -EINVAL;
goto read_failure;
}
/* Linearize header to local buffer */
ret = skb_copy_bits(skb, rxm->offset, header, prot->prepend_size);
if (ret < 0)
goto read_failure;
tlm->control = header[0];
data_len = ((header[4] & 0xFF) | (header[3] << 8));
cipher_overhead = prot->tag_size;
if (prot->version != TLS_1_3_VERSION &&
prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
cipher_overhead += prot->iv_size;
if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead +
prot->tail_size) {
ret = -EMSGSIZE;
goto read_failure;
}
if (data_len < cipher_overhead) {
ret = -EBADMSG;
goto read_failure;
}
/* Note that both TLS1.3 and TLS1.2 use TLS_1_2 version here */
if (header[1] != TLS_1_2_VERSION_MINOR ||
header[2] != TLS_1_2_VERSION_MAJOR) {
ret = -EINVAL;
goto read_failure;
}
tls_device_rx_resync_new_rec(strp->sk, data_len + TLS_HEADER_SIZE,
TCP_SKB_CB(skb)->seq + rxm->offset);
return data_len + TLS_HEADER_SIZE;
read_failure:
tls_err_abort(strp->sk, ret);
return ret;
}
static void tls_queue(struct strparser *strp, struct sk_buff *skb)
{
struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
ctx->recv_pkt = skb;
strp_pause(strp);
ctx->saved_data_ready(strp->sk);
}
static void tls_data_ready(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
struct sk_psock *psock;
strp_data_ready(&ctx->strp);
psock = sk_psock_get(sk);
if (psock) {
if (!list_empty(&psock->ingress_msg))
ctx->saved_data_ready(sk);
sk_psock_put(sk, psock);
}
}
void tls_sw_cancel_work_tx(struct tls_context *tls_ctx)
{
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask);
set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
cancel_delayed_work_sync(&ctx->tx_work.work);
}
void tls_sw_release_resources_tx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
struct tls_rec *rec, *tmp;
int pending;
/* Wait for any pending async encryptions to complete */
spin_lock_bh(&ctx->encrypt_compl_lock);
ctx->async_notify = true;
pending = atomic_read(&ctx->encrypt_pending);
spin_unlock_bh(&ctx->encrypt_compl_lock);
if (pending)
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
tls_tx_records(sk, -1);
/* Free up un-sent records in tx_list. First, free
* the partially sent record if any at head of tx_list.
*/
if (tls_ctx->partially_sent_record) {
tls_free_partial_record(sk, tls_ctx);
rec = list_first_entry(&ctx->tx_list,
struct tls_rec, list);
list_del(&rec->list);
sk_msg_free(sk, &rec->msg_plaintext);
kfree(rec);
}
list_for_each_entry_safe(rec, tmp, &ctx->tx_list, list) {
list_del(&rec->list);
sk_msg_free(sk, &rec->msg_encrypted);
sk_msg_free(sk, &rec->msg_plaintext);
kfree(rec);
}
crypto_free_aead(ctx->aead_send);
tls_free_open_rec(sk);
}
void tls_sw_free_ctx_tx(struct tls_context *tls_ctx)
{
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
kfree(ctx);
}
void tls_sw_release_resources_rx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
kfree(tls_ctx->rx.rec_seq);
kfree(tls_ctx->rx.iv);
if (ctx->aead_recv) {
kfree_skb(ctx->recv_pkt);
ctx->recv_pkt = NULL;
__skb_queue_purge(&ctx->rx_list);
crypto_free_aead(ctx->aead_recv);
strp_stop(&ctx->strp);
/* If tls_sw_strparser_arm() was not called (cleanup paths)
* we still want to strp_stop(), but sk->sk_data_ready was
* never swapped.
*/
if (ctx->saved_data_ready) {
write_lock_bh(&sk->sk_callback_lock);
sk->sk_data_ready = ctx->saved_data_ready;
write_unlock_bh(&sk->sk_callback_lock);
}
}
}
void tls_sw_strparser_done(struct tls_context *tls_ctx)
{
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
strp_done(&ctx->strp);
}
void tls_sw_free_ctx_rx(struct tls_context *tls_ctx)
{
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
kfree(ctx);
}
void tls_sw_free_resources_rx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
tls_sw_release_resources_rx(sk);
tls_sw_free_ctx_rx(tls_ctx);
}
/* The work handler to transmitt the encrypted records in tx_list */
static void tx_work_handler(struct work_struct *work)
{
struct delayed_work *delayed_work = to_delayed_work(work);
struct tx_work *tx_work = container_of(delayed_work,
struct tx_work, work);
struct sock *sk = tx_work->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx;
if (unlikely(!tls_ctx))
return;
ctx = tls_sw_ctx_tx(tls_ctx);
if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask))
return;
if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
return;
mutex_lock(&tls_ctx->tx_lock);
lock_sock(sk);
tls_tx_records(sk, -1);
release_sock(sk);
mutex_unlock(&tls_ctx->tx_lock);
}
static bool tls_is_tx_ready(struct tls_sw_context_tx *ctx)
{
struct tls_rec *rec;
rec = list_first_entry(&ctx->tx_list, struct tls_rec, list);
if (!rec)
return false;
return READ_ONCE(rec->tx_ready);
}
void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
{
struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx);
/* Schedule the transmission if tx list is ready */
if (tls_is_tx_ready(tx_ctx) &&
!test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
schedule_delayed_work(&tx_ctx->tx_work.work, 0);
}
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx)
{
struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx);
write_lock_bh(&sk->sk_callback_lock);
rx_ctx->saved_data_ready = sk->sk_data_ready;
sk->sk_data_ready = tls_data_ready;
write_unlock_bh(&sk->sk_callback_lock);
strp_check_rcv(&rx_ctx->strp);
}
void tls_update_rx_zc_capable(struct tls_context *tls_ctx)
{
struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx);
rx_ctx->zc_capable = tls_ctx->rx_no_pad ||
tls_ctx->prot_info.version != TLS_1_3_VERSION;
}
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_crypto_info *crypto_info;
struct tls_sw_context_tx *sw_ctx_tx = NULL;
struct tls_sw_context_rx *sw_ctx_rx = NULL;
struct cipher_context *cctx;
struct crypto_aead **aead;
struct strp_callbacks cb;
u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size;
struct crypto_tfm *tfm;
char *iv, *rec_seq, *key, *salt, *cipher_name;
size_t keysize;
int rc = 0;
if (!ctx) {
rc = -EINVAL;
goto out;
}
if (tx) {
if (!ctx->priv_ctx_tx) {
sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
if (!sw_ctx_tx) {
rc = -ENOMEM;
goto out;
}
ctx->priv_ctx_tx = sw_ctx_tx;
} else {
sw_ctx_tx =
(struct tls_sw_context_tx *)ctx->priv_ctx_tx;
}
} else {
if (!ctx->priv_ctx_rx) {
sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
if (!sw_ctx_rx) {
rc = -ENOMEM;
goto out;
}
ctx->priv_ctx_rx = sw_ctx_rx;
} else {
sw_ctx_rx =
(struct tls_sw_context_rx *)ctx->priv_ctx_rx;
}
}
if (tx) {
crypto_init_wait(&sw_ctx_tx->async_wait);
spin_lock_init(&sw_ctx_tx->encrypt_compl_lock);
crypto_info = &ctx->crypto_send.info;
cctx = &ctx->tx;
aead = &sw_ctx_tx->aead_send;
INIT_LIST_HEAD(&sw_ctx_tx->tx_list);
INIT_DELAYED_WORK(&sw_ctx_tx->tx_work.work, tx_work_handler);
sw_ctx_tx->tx_work.sk = sk;
} else {
crypto_init_wait(&sw_ctx_rx->async_wait);
spin_lock_init(&sw_ctx_rx->decrypt_compl_lock);
init_waitqueue_head(&sw_ctx_rx->wq);
crypto_info = &ctx->crypto_recv.info;
cctx = &ctx->rx;
skb_queue_head_init(&sw_ctx_rx->rx_list);
aead = &sw_ctx_rx->aead_recv;
}
switch (crypto_info->cipher_type) {
case TLS_CIPHER_AES_GCM_128: {
struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
gcm_128_info = (void *)crypto_info;
nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE;
iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
iv = gcm_128_info->iv;
rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
rec_seq = gcm_128_info->rec_seq;
keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE;
key = gcm_128_info->key;
salt = gcm_128_info->salt;
salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE;
cipher_name = "gcm(aes)";
break;
}
case TLS_CIPHER_AES_GCM_256: {
struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
gcm_256_info = (void *)crypto_info;
nonce_size = TLS_CIPHER_AES_GCM_256_IV_SIZE;
tag_size = TLS_CIPHER_AES_GCM_256_TAG_SIZE;
iv_size = TLS_CIPHER_AES_GCM_256_IV_SIZE;
iv = gcm_256_info->iv;
rec_seq_size = TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE;
rec_seq = gcm_256_info->rec_seq;
keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE;
key = gcm_256_info->key;
salt = gcm_256_info->salt;
salt_size = TLS_CIPHER_AES_GCM_256_SALT_SIZE;
cipher_name = "gcm(aes)";
break;
}
case TLS_CIPHER_AES_CCM_128: {
struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
ccm_128_info = (void *)crypto_info;
nonce_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
tag_size = TLS_CIPHER_AES_CCM_128_TAG_SIZE;
iv_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
iv = ccm_128_info->iv;
rec_seq_size = TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE;
rec_seq = ccm_128_info->rec_seq;
keysize = TLS_CIPHER_AES_CCM_128_KEY_SIZE;
key = ccm_128_info->key;
salt = ccm_128_info->salt;
salt_size = TLS_CIPHER_AES_CCM_128_SALT_SIZE;
cipher_name = "ccm(aes)";
break;
}
case TLS_CIPHER_CHACHA20_POLY1305: {
struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305_info;
chacha20_poly1305_info = (void *)crypto_info;
nonce_size = 0;
tag_size = TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE;
iv_size = TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE;
iv = chacha20_poly1305_info->iv;
rec_seq_size = TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE;
rec_seq = chacha20_poly1305_info->rec_seq;
keysize = TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE;
key = chacha20_poly1305_info->key;
salt = chacha20_poly1305_info->salt;
salt_size = TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE;
cipher_name = "rfc7539(chacha20,poly1305)";
break;
}
case TLS_CIPHER_SM4_GCM: {
struct tls12_crypto_info_sm4_gcm *sm4_gcm_info;
sm4_gcm_info = (void *)crypto_info;
nonce_size = TLS_CIPHER_SM4_GCM_IV_SIZE;
tag_size = TLS_CIPHER_SM4_GCM_TAG_SIZE;
iv_size = TLS_CIPHER_SM4_GCM_IV_SIZE;
iv = sm4_gcm_info->iv;
rec_seq_size = TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE;
rec_seq = sm4_gcm_info->rec_seq;
keysize = TLS_CIPHER_SM4_GCM_KEY_SIZE;
key = sm4_gcm_info->key;
salt = sm4_gcm_info->salt;
salt_size = TLS_CIPHER_SM4_GCM_SALT_SIZE;
cipher_name = "gcm(sm4)";
break;
}
case TLS_CIPHER_SM4_CCM: {
struct tls12_crypto_info_sm4_ccm *sm4_ccm_info;
sm4_ccm_info = (void *)crypto_info;
nonce_size = TLS_CIPHER_SM4_CCM_IV_SIZE;
tag_size = TLS_CIPHER_SM4_CCM_TAG_SIZE;
iv_size = TLS_CIPHER_SM4_CCM_IV_SIZE;
iv = sm4_ccm_info->iv;
rec_seq_size = TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE;
rec_seq = sm4_ccm_info->rec_seq;
keysize = TLS_CIPHER_SM4_CCM_KEY_SIZE;
key = sm4_ccm_info->key;
salt = sm4_ccm_info->salt;
salt_size = TLS_CIPHER_SM4_CCM_SALT_SIZE;
cipher_name = "ccm(sm4)";
break;
}
default:
rc = -EINVAL;
goto free_priv;
}
if (crypto_info->version == TLS_1_3_VERSION) {
nonce_size = 0;
prot->aad_size = TLS_HEADER_SIZE;
prot->tail_size = 1;
} else {
prot->aad_size = TLS_AAD_SPACE_SIZE;
prot->tail_size = 0;
}
/* Sanity-check the sizes for stack allocations. */
if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE ||
rec_seq_size > TLS_MAX_REC_SEQ_SIZE || tag_size != TLS_TAG_SIZE ||
prot->aad_size > TLS_MAX_AAD_SIZE) {
rc = -EINVAL;
goto free_priv;
}
prot->version = crypto_info->version;
prot->cipher_type = crypto_info->cipher_type;
prot->prepend_size = TLS_HEADER_SIZE + nonce_size;
prot->tag_size = tag_size;
prot->overhead_size = prot->prepend_size +
prot->tag_size + prot->tail_size;
prot->iv_size = iv_size;
prot->salt_size = salt_size;
cctx->iv = kmalloc(iv_size + salt_size, GFP_KERNEL);
if (!cctx->iv) {
rc = -ENOMEM;
goto free_priv;
}
/* Note: 128 & 256 bit salt are the same size */
prot->rec_seq_size = rec_seq_size;
memcpy(cctx->iv, salt, salt_size);
memcpy(cctx->iv + salt_size, iv, iv_size);
cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
if (!cctx->rec_seq) {
rc = -ENOMEM;
goto free_iv;
}
if (!*aead) {
*aead = crypto_alloc_aead(cipher_name, 0, 0);
if (IS_ERR(*aead)) {
rc = PTR_ERR(*aead);
*aead = NULL;
goto free_rec_seq;
}
}
ctx->push_pending_record = tls_sw_push_pending_record;
rc = crypto_aead_setkey(*aead, key, keysize);
if (rc)
goto free_aead;
rc = crypto_aead_setauthsize(*aead, prot->tag_size);
if (rc)
goto free_aead;
if (sw_ctx_rx) {
tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv);
tls_update_rx_zc_capable(ctx);
sw_ctx_rx->async_capable =
crypto_info->version != TLS_1_3_VERSION &&
!!(tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC);
/* Set up strparser */
memset(&cb, 0, sizeof(cb));
cb.rcv_msg = tls_queue;
cb.parse_msg = tls_read_size;
strp_init(&sw_ctx_rx->strp, sk, &cb);
}
goto out;
free_aead:
crypto_free_aead(*aead);
*aead = NULL;
free_rec_seq:
kfree(cctx->rec_seq);
cctx->rec_seq = NULL;
free_iv:
kfree(cctx->iv);
cctx->iv = NULL;
free_priv:
if (tx) {
kfree(ctx->priv_ctx_tx);
ctx->priv_ctx_tx = NULL;
} else {
kfree(ctx->priv_ctx_rx);
ctx->priv_ctx_rx = NULL;
}
out:
return rc;
}
Reference in New Issue View Git Blame Copy Permalink