linux-stable/include/net/tls.h

401 lines
12 KiB
C
Raw Normal View History

/*
* Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved.
* Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved.
*
* 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.
*/
#ifndef _TLS_OFFLOAD_H
#define _TLS_OFFLOAD_H
#include <linux/types.h>
#include <asm/byteorder.h>
#include <linux/crypto.h>
#include <linux/socket.h>
#include <linux/tcp.h>
#include <net/tcp.h>
#include <net/strparser.h>
#include <uapi/linux/tls.h>
/* Maximum data size carried in a TLS record */
#define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14)
#define TLS_HEADER_SIZE 5
#define TLS_NONCE_OFFSET TLS_HEADER_SIZE
#define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type)
#define TLS_RECORD_TYPE_DATA 0x17
#define TLS_AAD_SPACE_SIZE 13
#define TLS_DEVICE_NAME_MAX 32
/*
* This structure defines the routines for Inline TLS driver.
* The following routines are optional and filled with a
* null pointer if not defined.
*
* @name: Its the name of registered Inline tls device
* @dev_list: Inline tls device list
* int (*feature)(struct tls_device *device);
* Called to return Inline TLS driver capability
*
* int (*hash)(struct tls_device *device, struct sock *sk);
* This function sets Inline driver for listen and program
* device specific functioanlity as required
*
* void (*unhash)(struct tls_device *device, struct sock *sk);
* This function cleans listen state set by Inline TLS driver
*/
struct tls_device {
char name[TLS_DEVICE_NAME_MAX];
struct list_head dev_list;
int (*feature)(struct tls_device *device);
int (*hash)(struct tls_device *device, struct sock *sk);
void (*unhash)(struct tls_device *device, struct sock *sk);
};
struct tls_sw_context_tx {
struct crypto_aead *aead_send;
struct crypto_wait async_wait;
char aad_space[TLS_AAD_SPACE_SIZE];
unsigned int sg_plaintext_size;
int sg_plaintext_num_elem;
struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS];
unsigned int sg_encrypted_size;
int sg_encrypted_num_elem;
struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS];
/* AAD | sg_plaintext_data | sg_tag */
struct scatterlist sg_aead_in[2];
/* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */
struct scatterlist sg_aead_out[2];
};
struct tls_sw_context_rx {
struct crypto_aead *aead_recv;
struct crypto_wait async_wait;
struct strparser strp;
void (*saved_data_ready)(struct sock *sk);
tls: fix NULL pointer dereference on poll While hacking on kTLS, I ran into the following panic from an unprivileged netserver / netperf TCP session: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000037f378067 P4D 800000037f378067 PUD 3c0e61067 PMD 0 Oops: 0010 [#1] SMP KASAN PTI CPU: 1 PID: 2289 Comm: netserver Not tainted 4.17.0+ #139 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET47W (1.21 ) 11/28/2016 RIP: 0010: (null) Code: Bad RIP value. RSP: 0018:ffff88036abcf740 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88036f5f6800 RCX: 1ffff1006debed26 RDX: ffff88036abcf920 RSI: ffff8803cb1a4f00 RDI: ffff8803c258c280 RBP: ffff8803c258c280 R08: ffff8803c258c280 R09: ffffed006f559d48 R10: ffff88037aacea43 R11: ffffed006f559d49 R12: ffff8803c258c280 R13: ffff8803cb1a4f20 R14: 00000000000000db R15: ffffffffc168a350 FS: 00007f7e631f4700(0000) GS:ffff8803d1c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 00000003ccf64005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? tls_sw_poll+0xa4/0x160 [tls] ? sock_poll+0x20a/0x680 ? do_select+0x77b/0x11a0 ? poll_schedule_timeout.constprop.12+0x130/0x130 ? pick_link+0xb00/0xb00 ? read_word_at_a_time+0x13/0x20 ? vfs_poll+0x270/0x270 ? deref_stack_reg+0xad/0xe0 ? __read_once_size_nocheck.constprop.6+0x10/0x10 [...] Debugging further, it turns out that calling into ctx->sk_poll() is invalid since sk_poll itself is NULL which was saved from the original TCP socket in order for tls_sw_poll() to invoke it. Looks like the recent conversion from poll to poll_mask callback started in 152524231023 ("net: add support for ->poll_mask in proto_ops") missed to eventually convert kTLS, too: TCP's ->poll was converted over to the ->poll_mask in commit 2c7d3dacebd4 ("net/tcp: convert to ->poll_mask") and therefore kTLS wrongly saved the ->poll old one which is now NULL. Convert kTLS over to use ->poll_mask instead. Also instead of POLLIN | POLLRDNORM use the proper EPOLLIN | EPOLLRDNORM bits as the case in tcp_poll_mask() as well that is mangled here. Fixes: 2c7d3dacebd4 ("net/tcp: convert to ->poll_mask") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Watson <davejwatson@fb.com> Tested-by: Dave Watson <davejwatson@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-11 21:22:04 +00:00
__poll_t (*sk_poll_mask)(struct socket *sock, __poll_t events);
struct sk_buff *recv_pkt;
u8 control;
bool decrypted;
char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
};
net/tls: Add generic NIC offload infrastructure This patch adds a generic infrastructure to offload TLS crypto to a network device. It enables the kernel TLS socket to skip encryption and authentication operations on the transmit side of the data path. Leaving those computationally expensive operations to the NIC. The NIC offload infrastructure builds TLS records and pushes them to the TCP layer just like the SW KTLS implementation and using the same API. TCP segmentation is mostly unaffected. Currently the only exception is that we prevent mixed SKBs where only part of the payload requires offload. In the future we are likely to add a similar restriction following a change cipher spec record. The notable differences between SW KTLS and NIC offloaded TLS implementations are as follows: 1. The offloaded implementation builds "plaintext TLS record", those records contain plaintext instead of ciphertext and place holder bytes instead of authentication tags. 2. The offloaded implementation maintains a mapping from TCP sequence number to TLS records. Thus given a TCP SKB sent from a NIC offloaded TLS socket, we can use the tls NIC offload infrastructure to obtain enough context to encrypt the payload of the SKB. A TLS record is released when the last byte of the record is ack'ed, this is done through the new icsk_clean_acked callback. The infrastructure should be extendable to support various NIC offload implementations. However it is currently written with the implementation below in mind: The NIC assumes that packets from each offloaded stream are sent as plaintext and in-order. It keeps track of the TLS records in the TCP stream. When a packet marked for offload is transmitted, the NIC encrypts the payload in-place and puts authentication tags in the relevant place holders. The responsibility for handling out-of-order packets (i.e. TCP retransmission, qdisc drops) falls on the netdev driver. The netdev driver keeps track of the expected TCP SN from the NIC's perspective. If the next packet to transmit matches the expected TCP SN, the driver advances the expected TCP SN, and transmits the packet with TLS offload indication. If the next packet to transmit does not match the expected TCP SN. The driver calls the TLS layer to obtain the TLS record that includes the TCP of the packet for transmission. Using this TLS record, the driver posts a work entry on the transmit queue to reconstruct the NIC TLS state required for the offload of the out-of-order packet. It updates the expected TCP SN accordingly and transmits the now in-order packet. The same queue is used for packet transmission and TLS context reconstruction to avoid the need for flushing the transmit queue before issuing the context reconstruction request. Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com> Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-30 07:16:16 +00:00
struct tls_record_info {
struct list_head list;
u32 end_seq;
int len;
int num_frags;
skb_frag_t frags[MAX_SKB_FRAGS];
};
struct tls_offload_context {
struct crypto_aead *aead_send;
spinlock_t lock; /* protects records list */
struct list_head records_list;
struct tls_record_info *open_record;
struct tls_record_info *retransmit_hint;
u64 hint_record_sn;
u64 unacked_record_sn;
struct scatterlist sg_tx_data[MAX_SKB_FRAGS];
void (*sk_destruct)(struct sock *sk);
u8 driver_state[];
/* The TLS layer reserves room for driver specific state
* Currently the belief is that there is not enough
* driver specific state to justify another layer of indirection
*/
#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *)))
};
#define TLS_OFFLOAD_CONTEXT_SIZE \
(ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) + \
TLS_DRIVER_STATE_SIZE)
enum {
TLS_PENDING_CLOSED_RECORD
};
struct cipher_context {
u16 prepend_size;
u16 tag_size;
u16 overhead_size;
u16 iv_size;
char *iv;
u16 rec_seq_size;
char *rec_seq;
};
struct tls_context {
union {
struct tls_crypto_info crypto_send;
struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128;
};
union {
struct tls_crypto_info crypto_recv;
struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128;
};
struct list_head list;
struct net_device *netdev;
refcount_t refcount;
void *priv_ctx_tx;
void *priv_ctx_rx;
u8 tx_conf:3;
u8 rx_conf:3;
struct cipher_context tx;
struct cipher_context rx;
struct scatterlist *partially_sent_record;
u16 partially_sent_offset;
unsigned long flags;
bool in_tcp_sendpages;
u16 pending_open_record_frags;
int (*push_pending_record)(struct sock *sk, int flags);
void (*sk_write_space)(struct sock *sk);
void (*sk_proto_close)(struct sock *sk, long timeout);
int (*setsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level,
int optname, char __user *optval,
int __user *optlen);
int (*hash)(struct sock *sk);
void (*unhash)(struct sock *sk);
};
int wait_on_pending_writer(struct sock *sk, long *timeo);
int tls_sk_query(struct sock *sk, int optname, char __user *optval,
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tls_sw_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_sw_close(struct sock *sk, long timeout);
void tls_sw_free_resources_tx(struct sock *sk);
void tls_sw_free_resources_rx(struct sock *sk);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
tls: fix NULL pointer dereference on poll While hacking on kTLS, I ran into the following panic from an unprivileged netserver / netperf TCP session: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000037f378067 P4D 800000037f378067 PUD 3c0e61067 PMD 0 Oops: 0010 [#1] SMP KASAN PTI CPU: 1 PID: 2289 Comm: netserver Not tainted 4.17.0+ #139 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET47W (1.21 ) 11/28/2016 RIP: 0010: (null) Code: Bad RIP value. RSP: 0018:ffff88036abcf740 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff88036f5f6800 RCX: 1ffff1006debed26 RDX: ffff88036abcf920 RSI: ffff8803cb1a4f00 RDI: ffff8803c258c280 RBP: ffff8803c258c280 R08: ffff8803c258c280 R09: ffffed006f559d48 R10: ffff88037aacea43 R11: ffffed006f559d49 R12: ffff8803c258c280 R13: ffff8803cb1a4f20 R14: 00000000000000db R15: ffffffffc168a350 FS: 00007f7e631f4700(0000) GS:ffff8803d1c80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 00000003ccf64005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? tls_sw_poll+0xa4/0x160 [tls] ? sock_poll+0x20a/0x680 ? do_select+0x77b/0x11a0 ? poll_schedule_timeout.constprop.12+0x130/0x130 ? pick_link+0xb00/0xb00 ? read_word_at_a_time+0x13/0x20 ? vfs_poll+0x270/0x270 ? deref_stack_reg+0xad/0xe0 ? __read_once_size_nocheck.constprop.6+0x10/0x10 [...] Debugging further, it turns out that calling into ctx->sk_poll() is invalid since sk_poll itself is NULL which was saved from the original TCP socket in order for tls_sw_poll() to invoke it. Looks like the recent conversion from poll to poll_mask callback started in 152524231023 ("net: add support for ->poll_mask in proto_ops") missed to eventually convert kTLS, too: TCP's ->poll was converted over to the ->poll_mask in commit 2c7d3dacebd4 ("net/tcp: convert to ->poll_mask") and therefore kTLS wrongly saved the ->poll old one which is now NULL. Convert kTLS over to use ->poll_mask instead. Also instead of POLLIN | POLLRDNORM use the proper EPOLLIN | EPOLLRDNORM bits as the case in tcp_poll_mask() as well that is mangled here. Fixes: 2c7d3dacebd4 ("net/tcp: convert to ->poll_mask") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Watson <davejwatson@fb.com> Tested-by: Dave Watson <davejwatson@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-06-11 21:22:04 +00:00
__poll_t tls_sw_poll_mask(struct socket *sock, __poll_t events);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
net/tls: Add generic NIC offload infrastructure This patch adds a generic infrastructure to offload TLS crypto to a network device. It enables the kernel TLS socket to skip encryption and authentication operations on the transmit side of the data path. Leaving those computationally expensive operations to the NIC. The NIC offload infrastructure builds TLS records and pushes them to the TCP layer just like the SW KTLS implementation and using the same API. TCP segmentation is mostly unaffected. Currently the only exception is that we prevent mixed SKBs where only part of the payload requires offload. In the future we are likely to add a similar restriction following a change cipher spec record. The notable differences between SW KTLS and NIC offloaded TLS implementations are as follows: 1. The offloaded implementation builds "plaintext TLS record", those records contain plaintext instead of ciphertext and place holder bytes instead of authentication tags. 2. The offloaded implementation maintains a mapping from TCP sequence number to TLS records. Thus given a TCP SKB sent from a NIC offloaded TLS socket, we can use the tls NIC offload infrastructure to obtain enough context to encrypt the payload of the SKB. A TLS record is released when the last byte of the record is ack'ed, this is done through the new icsk_clean_acked callback. The infrastructure should be extendable to support various NIC offload implementations. However it is currently written with the implementation below in mind: The NIC assumes that packets from each offloaded stream are sent as plaintext and in-order. It keeps track of the TLS records in the TCP stream. When a packet marked for offload is transmitted, the NIC encrypts the payload in-place and puts authentication tags in the relevant place holders. The responsibility for handling out-of-order packets (i.e. TCP retransmission, qdisc drops) falls on the netdev driver. The netdev driver keeps track of the expected TCP SN from the NIC's perspective. If the next packet to transmit matches the expected TCP SN, the driver advances the expected TCP SN, and transmits the packet with TLS offload indication. If the next packet to transmit does not match the expected TCP SN. The driver calls the TLS layer to obtain the TLS record that includes the TCP of the packet for transmission. Using this TLS record, the driver posts a work entry on the transmit queue to reconstruct the NIC TLS state required for the offload of the out-of-order packet. It updates the expected TCP SN accordingly and transmits the now in-order packet. The same queue is used for packet transmission and TLS context reconstruction to avoid the need for flushing the transmit queue before issuing the context reconstruction request. Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com> Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-30 07:16:16 +00:00
int tls_set_device_offload(struct sock *sk, struct tls_context *ctx);
int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tls_device_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
void tls_device_sk_destruct(struct sock *sk);
void tls_device_init(void);
void tls_device_cleanup(void);
struct tls_record_info *tls_get_record(struct tls_offload_context *context,
u32 seq, u64 *p_record_sn);
static inline bool tls_record_is_start_marker(struct tls_record_info *rec)
{
return rec->len == 0;
}
static inline u32 tls_record_start_seq(struct tls_record_info *rec)
{
return rec->end_seq - rec->len;
}
net/tls: Add generic NIC offload infrastructure This patch adds a generic infrastructure to offload TLS crypto to a network device. It enables the kernel TLS socket to skip encryption and authentication operations on the transmit side of the data path. Leaving those computationally expensive operations to the NIC. The NIC offload infrastructure builds TLS records and pushes them to the TCP layer just like the SW KTLS implementation and using the same API. TCP segmentation is mostly unaffected. Currently the only exception is that we prevent mixed SKBs where only part of the payload requires offload. In the future we are likely to add a similar restriction following a change cipher spec record. The notable differences between SW KTLS and NIC offloaded TLS implementations are as follows: 1. The offloaded implementation builds "plaintext TLS record", those records contain plaintext instead of ciphertext and place holder bytes instead of authentication tags. 2. The offloaded implementation maintains a mapping from TCP sequence number to TLS records. Thus given a TCP SKB sent from a NIC offloaded TLS socket, we can use the tls NIC offload infrastructure to obtain enough context to encrypt the payload of the SKB. A TLS record is released when the last byte of the record is ack'ed, this is done through the new icsk_clean_acked callback. The infrastructure should be extendable to support various NIC offload implementations. However it is currently written with the implementation below in mind: The NIC assumes that packets from each offloaded stream are sent as plaintext and in-order. It keeps track of the TLS records in the TCP stream. When a packet marked for offload is transmitted, the NIC encrypts the payload in-place and puts authentication tags in the relevant place holders. The responsibility for handling out-of-order packets (i.e. TCP retransmission, qdisc drops) falls on the netdev driver. The netdev driver keeps track of the expected TCP SN from the NIC's perspective. If the next packet to transmit matches the expected TCP SN, the driver advances the expected TCP SN, and transmits the packet with TLS offload indication. If the next packet to transmit does not match the expected TCP SN. The driver calls the TLS layer to obtain the TLS record that includes the TCP of the packet for transmission. Using this TLS record, the driver posts a work entry on the transmit queue to reconstruct the NIC TLS state required for the offload of the out-of-order packet. It updates the expected TCP SN accordingly and transmits the now in-order packet. The same queue is used for packet transmission and TLS context reconstruction to avoid the need for flushing the transmit queue before issuing the context reconstruction request. Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com> Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-30 07:16:16 +00:00
void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
int tls_push_sg(struct sock *sk, struct tls_context *ctx,
struct scatterlist *sg, u16 first_offset,
int flags);
int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx,
int flags, long *timeo);
static inline bool tls_is_pending_closed_record(struct tls_context *ctx)
{
return test_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags);
}
static inline int tls_complete_pending_work(struct sock *sk,
struct tls_context *ctx,
int flags, long *timeo)
{
int rc = 0;
if (unlikely(sk->sk_write_pending))
rc = wait_on_pending_writer(sk, timeo);
if (!rc && tls_is_pending_closed_record(ctx))
rc = tls_push_pending_closed_record(sk, ctx, flags, timeo);
return rc;
}
static inline bool tls_is_partially_sent_record(struct tls_context *ctx)
{
return !!ctx->partially_sent_record;
}
static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
{
return tls_ctx->pending_open_record_frags;
}
net/tls: Add generic NIC offload infrastructure This patch adds a generic infrastructure to offload TLS crypto to a network device. It enables the kernel TLS socket to skip encryption and authentication operations on the transmit side of the data path. Leaving those computationally expensive operations to the NIC. The NIC offload infrastructure builds TLS records and pushes them to the TCP layer just like the SW KTLS implementation and using the same API. TCP segmentation is mostly unaffected. Currently the only exception is that we prevent mixed SKBs where only part of the payload requires offload. In the future we are likely to add a similar restriction following a change cipher spec record. The notable differences between SW KTLS and NIC offloaded TLS implementations are as follows: 1. The offloaded implementation builds "plaintext TLS record", those records contain plaintext instead of ciphertext and place holder bytes instead of authentication tags. 2. The offloaded implementation maintains a mapping from TCP sequence number to TLS records. Thus given a TCP SKB sent from a NIC offloaded TLS socket, we can use the tls NIC offload infrastructure to obtain enough context to encrypt the payload of the SKB. A TLS record is released when the last byte of the record is ack'ed, this is done through the new icsk_clean_acked callback. The infrastructure should be extendable to support various NIC offload implementations. However it is currently written with the implementation below in mind: The NIC assumes that packets from each offloaded stream are sent as plaintext and in-order. It keeps track of the TLS records in the TCP stream. When a packet marked for offload is transmitted, the NIC encrypts the payload in-place and puts authentication tags in the relevant place holders. The responsibility for handling out-of-order packets (i.e. TCP retransmission, qdisc drops) falls on the netdev driver. The netdev driver keeps track of the expected TCP SN from the NIC's perspective. If the next packet to transmit matches the expected TCP SN, the driver advances the expected TCP SN, and transmits the packet with TLS offload indication. If the next packet to transmit does not match the expected TCP SN. The driver calls the TLS layer to obtain the TLS record that includes the TCP of the packet for transmission. Using this TLS record, the driver posts a work entry on the transmit queue to reconstruct the NIC TLS state required for the offload of the out-of-order packet. It updates the expected TCP SN accordingly and transmits the now in-order packet. The same queue is used for packet transmission and TLS context reconstruction to avoid the need for flushing the transmit queue before issuing the context reconstruction request. Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com> Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-30 07:16:16 +00:00
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
return sk_fullsock(sk) &&
/* matches smp_store_release in tls_set_device_offload */
smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct;
}
static inline void tls_err_abort(struct sock *sk, int err)
{
sk->sk_err = err;
sk->sk_error_report(sk);
}
static inline bool tls_bigint_increment(unsigned char *seq, int len)
{
int i;
for (i = len - 1; i >= 0; i--) {
++seq[i];
if (seq[i] != 0)
break;
}
return (i == -1);
}
static inline void tls_advance_record_sn(struct sock *sk,
struct cipher_context *ctx)
{
if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size))
tls_err_abort(sk, EBADMSG);
tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
ctx->iv_size);
}
static inline void tls_fill_prepend(struct tls_context *ctx,
char *buf,
size_t plaintext_len,
unsigned char record_type)
{
size_t pkt_len, iv_size = ctx->tx.iv_size;
pkt_len = plaintext_len + iv_size + ctx->tx.tag_size;
/* we cover nonce explicit here as well, so buf should be of
* size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE
*/
buf[0] = record_type;
buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version);
buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version);
/* we can use IV for nonce explicit according to spec */
buf[3] = pkt_len >> 8;
buf[4] = pkt_len & 0xFF;
memcpy(buf + TLS_NONCE_OFFSET,
ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size);
}
static inline void tls_make_aad(char *buf,
size_t size,
char *record_sequence,
int record_sequence_size,
unsigned char record_type)
{
memcpy(buf, record_sequence, record_sequence_size);
buf[8] = record_type;
buf[9] = TLS_1_2_VERSION_MAJOR;
buf[10] = TLS_1_2_VERSION_MINOR;
buf[11] = size >> 8;
buf[12] = size & 0xFF;
}
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
return icsk->icsk_ulp_data;
}
static inline struct tls_sw_context_rx *tls_sw_ctx_rx(
const struct tls_context *tls_ctx)
{
return (struct tls_sw_context_rx *)tls_ctx->priv_ctx_rx;
}
static inline struct tls_sw_context_tx *tls_sw_ctx_tx(
const struct tls_context *tls_ctx)
{
return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx;
}
static inline struct tls_offload_context *tls_offload_ctx(
const struct tls_context *tls_ctx)
{
return (struct tls_offload_context *)tls_ctx->priv_ctx_tx;
}
int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
unsigned char *record_type);
void tls_register_device(struct tls_device *device);
void tls_unregister_device(struct tls_device *device);
net/tls: Add generic NIC offload infrastructure This patch adds a generic infrastructure to offload TLS crypto to a network device. It enables the kernel TLS socket to skip encryption and authentication operations on the transmit side of the data path. Leaving those computationally expensive operations to the NIC. The NIC offload infrastructure builds TLS records and pushes them to the TCP layer just like the SW KTLS implementation and using the same API. TCP segmentation is mostly unaffected. Currently the only exception is that we prevent mixed SKBs where only part of the payload requires offload. In the future we are likely to add a similar restriction following a change cipher spec record. The notable differences between SW KTLS and NIC offloaded TLS implementations are as follows: 1. The offloaded implementation builds "plaintext TLS record", those records contain plaintext instead of ciphertext and place holder bytes instead of authentication tags. 2. The offloaded implementation maintains a mapping from TCP sequence number to TLS records. Thus given a TCP SKB sent from a NIC offloaded TLS socket, we can use the tls NIC offload infrastructure to obtain enough context to encrypt the payload of the SKB. A TLS record is released when the last byte of the record is ack'ed, this is done through the new icsk_clean_acked callback. The infrastructure should be extendable to support various NIC offload implementations. However it is currently written with the implementation below in mind: The NIC assumes that packets from each offloaded stream are sent as plaintext and in-order. It keeps track of the TLS records in the TCP stream. When a packet marked for offload is transmitted, the NIC encrypts the payload in-place and puts authentication tags in the relevant place holders. The responsibility for handling out-of-order packets (i.e. TCP retransmission, qdisc drops) falls on the netdev driver. The netdev driver keeps track of the expected TCP SN from the NIC's perspective. If the next packet to transmit matches the expected TCP SN, the driver advances the expected TCP SN, and transmits the packet with TLS offload indication. If the next packet to transmit does not match the expected TCP SN. The driver calls the TLS layer to obtain the TLS record that includes the TCP of the packet for transmission. Using this TLS record, the driver posts a work entry on the transmit queue to reconstruct the NIC TLS state required for the offload of the out-of-order packet. It updates the expected TCP SN accordingly and transmits the now in-order packet. The same queue is used for packet transmission and TLS context reconstruction to avoid the need for flushing the transmit queue before issuing the context reconstruction request. Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com> Signed-off-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-30 07:16:16 +00:00
struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
struct net_device *dev,
struct sk_buff *skb);
int tls_sw_fallback_init(struct sock *sk,
struct tls_offload_context *offload_ctx,
struct tls_crypto_info *crypto_info);
#endif /* _TLS_OFFLOAD_H */