Resguardo inicial

linux-7.2.3/net/tls/Kconfig

@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# TLS configuration
+#
+config TLS
+	tristate "Transport Layer Security support"
+	depends on INET
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_GCM
+	select NET_SOCK_MSG
+	default n
+	help
+	Enable kernel support for TLS protocol. This allows symmetric
+	encryption handling of the TLS protocol to be done in-kernel.
+
+	If unsure, say N.
+
+config TLS_DEVICE
+	bool "Transport Layer Security HW offload"
+	depends on TLS
+	select SKB_DECRYPTED
+	select SOCK_VALIDATE_XMIT
+	select SOCK_RX_QUEUE_MAPPING
+	default n
+	help
+	Enable kernel support for HW offload of the TLS protocol.
+
+	If unsure, say N.

linux-7.2.3/net/tls/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the TLS subsystem.
+#
+
+CFLAGS_trace.o := -I$(src)
+
+obj-$(CONFIG_TLS) += tls.o
+
+tls-y := tls_main.o tls_sw.o tls_proc.o trace.o tls_strp.o
+
+tls-$(CONFIG_TLS_DEVICE) += tls_device.o tls_device_fallback.o

linux-7.2.3/net/tls/tls.h

@@ -0,0 +1,383 @@
+/*
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ * 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_INT_H
+#define _TLS_INT_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+#include <linux/skmsg.h>
+#include <net/tls.h>
+#include <net/tls_prot.h>
+
+#define TLS_PAGE_ORDER	(min_t(unsigned int, PAGE_ALLOC_COSTLY_ORDER,	\
+			       TLS_MAX_PAYLOAD_SIZE >> PAGE_SHIFT))
+
+#define __TLS_INC_STATS(net, field)				\
+	__SNMP_INC_STATS((net)->mib.tls_statistics, field)
+#define TLS_INC_STATS(net, field)				\
+	SNMP_INC_STATS((net)->mib.tls_statistics, field)
+#define TLS_DEC_STATS(net, field)				\
+	SNMP_DEC_STATS((net)->mib.tls_statistics, field)
+
+struct tls_cipher_desc {
+	unsigned int nonce;
+	unsigned int iv;
+	unsigned int key;
+	unsigned int salt;
+	unsigned int tag;
+	unsigned int rec_seq;
+	unsigned int iv_offset;
+	unsigned int key_offset;
+	unsigned int salt_offset;
+	unsigned int rec_seq_offset;
+	char *cipher_name;
+	bool offloadable;
+	size_t crypto_info;
+};
+
+#define TLS_CIPHER_MIN TLS_CIPHER_AES_GCM_128
+#define TLS_CIPHER_MAX TLS_CIPHER_ARIA_GCM_256
+extern const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN];
+
+static inline const struct tls_cipher_desc *get_cipher_desc(u16 cipher_type)
+{
+	if (cipher_type < TLS_CIPHER_MIN || cipher_type > TLS_CIPHER_MAX)
+		return NULL;
+
+	return &tls_cipher_desc[cipher_type - TLS_CIPHER_MIN];
+}
+
+static inline char *crypto_info_iv(struct tls_crypto_info *crypto_info,
+				   const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->iv_offset;
+}
+
+static inline char *crypto_info_key(struct tls_crypto_info *crypto_info,
+				    const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->key_offset;
+}
+
+static inline char *crypto_info_salt(struct tls_crypto_info *crypto_info,
+				     const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->salt_offset;
+}
+
+static inline char *crypto_info_rec_seq(struct tls_crypto_info *crypto_info,
+					const struct tls_cipher_desc *cipher_desc)
+{
+	return (char *)crypto_info + cipher_desc->rec_seq_offset;
+}
+
+
+/* TLS records are maintained in 'struct tls_rec'. It stores the memory pages
+ * allocated or mapped for each TLS record. After encryption, the records are
+ * stores in a linked list.
+ */
+struct tls_rec {
+	struct list_head list;
+	int tx_ready;
+	int tx_flags;
+
+	struct sk_msg msg_plaintext;
+	struct sk_msg msg_encrypted;
+
+	/* AAD | msg_plaintext.sg.data | sg_tag */
+	struct scatterlist sg_aead_in[2];
+	/* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */
+	struct scatterlist sg_aead_out[2];
+
+	char content_type;
+	struct scatterlist sg_content_type;
+
+	struct sock *sk;
+
+	char aad_space[TLS_AAD_SPACE_SIZE];
+	u8 iv_data[TLS_MAX_IV_SIZE];
+
+	/* Must be last --ends in a flexible-array member. */
+	struct aead_request aead_req;
+};
+
+int __net_init tls_proc_init(struct net *net);
+void __net_exit tls_proc_fini(struct net *net);
+
+struct tls_context *tls_ctx_create(struct sock *sk);
+void tls_ctx_free(struct sock *sk, struct tls_context *ctx);
+void update_sk_prot(struct sock *sk, struct tls_context *ctx);
+
+int wait_on_pending_writer(struct sock *sk, long *timeo);
+void tls_err_abort(struct sock *sk, int err);
+void tls_strp_abort_strp(struct tls_strparser *strp, int err);
+
+int init_prot_info(struct tls_prot_info *prot,
+		   const struct tls_crypto_info *crypto_info,
+		   const struct tls_cipher_desc *cipher_desc);
+int tls_set_sw_offload(struct sock *sk, int tx,
+		       struct tls_crypto_info *new_crypto_info);
+void tls_update_rx_zc_capable(struct tls_context *tls_ctx);
+void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
+void tls_sw_strparser_done(struct tls_context *tls_ctx);
+int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+void tls_sw_splice_eof(struct socket *sock);
+void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
+void tls_sw_release_resources_tx(struct sock *sk);
+void tls_sw_free_ctx_tx(struct tls_context *tls_ctx);
+void tls_sw_free_resources_rx(struct sock *sk);
+void tls_sw_release_resources_rx(struct sock *sk);
+void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
+int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+		   int flags);
+bool tls_sw_sock_is_readable(struct sock *sk);
+ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
+			   struct pipe_inode_info *pipe,
+			   size_t len, unsigned int flags);
+int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc,
+		     sk_read_actor_t read_actor);
+
+int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
+void tls_device_splice_eof(struct socket *sock);
+int tls_tx_records(struct sock *sk, int flags);
+
+void tls_sw_write_space(struct sock *sk, struct tls_context *ctx);
+void tls_device_write_space(struct sock *sk, struct tls_context *ctx);
+
+int tls_process_cmsg(struct sock *sk, struct msghdr *msg,
+		     unsigned char *record_type);
+int decrypt_skb(struct sock *sk, struct scatterlist *sgout);
+
+int tls_sw_fallback_init(struct sock *sk,
+			 struct tls_offload_context_tx *offload_ctx,
+			 struct tls_crypto_info *crypto_info);
+
+int tls_strp_dev_init(void);
+void tls_strp_dev_exit(void);
+
+void tls_strp_done(struct tls_strparser *strp);
+void __tls_strp_done(struct tls_strparser *strp);
+void tls_strp_stop(struct tls_strparser *strp);
+int tls_strp_init(struct tls_strparser *strp, struct sock *sk);
+void tls_strp_data_ready(struct tls_strparser *strp);
+
+void tls_strp_check_rcv(struct tls_strparser *strp, bool announce);
+void tls_strp_msg_consume(struct tls_strparser *strp);
+
+int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb);
+void tls_rx_msg_maybe_announce(struct tls_strparser *strp);
+
+bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh);
+int tls_strp_msg_cow(struct tls_sw_context_rx *ctx);
+struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx);
+int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst);
+
+static inline struct tls_msg *tls_msg(struct sk_buff *skb)
+{
+	struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb;
+
+	return &scb->tls;
+}
+
+static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx)
+{
+	DEBUG_NET_WARN_ON_ONCE(!ctx->strp.msg_ready || !ctx->strp.anchor->len);
+	return ctx->strp.anchor;
+}
+
+static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx)
+{
+	return READ_ONCE(ctx->strp.msg_ready);
+}
+
+static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx)
+{
+	return ctx->strp.mixed_decrypted;
+}
+
+#ifdef CONFIG_TLS_DEVICE
+int tls_device_init(void);
+void tls_device_cleanup(void);
+int tls_set_device_offload(struct sock *sk);
+void tls_device_free_resources_tx(struct sock *sk);
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
+void tls_device_offload_cleanup_rx(struct sock *sk);
+void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq);
+int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx);
+#else
+static inline int tls_device_init(void) { return 0; }
+static inline void tls_device_cleanup(void) {}
+
+static inline int
+tls_set_device_offload(struct sock *sk)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void tls_device_free_resources_tx(struct sock *sk) {}
+
+static inline int
+tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void tls_device_offload_cleanup_rx(struct sock *sk) {}
+static inline void
+tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {}
+
+static inline int
+tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx)
+{
+	return 0;
+}
+#endif
+
+int tls_push_sg(struct sock *sk, struct tls_context *ctx,
+		struct scatterlist *sg, u16 first_offset,
+		int flags);
+int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
+			    int flags);
+void tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
+
+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;
+}
+
+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_bigint_subtract(unsigned char *seq, int  n)
+{
+	u64 rcd_sn;
+	__be64 *p;
+
+	BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8);
+
+	p = (__be64 *)seq;
+	rcd_sn = be64_to_cpu(*p);
+	*p = cpu_to_be64(rcd_sn - n);
+}
+
+static inline void
+tls_advance_record_sn(struct sock *sk, struct tls_prot_info *prot,
+		      struct cipher_context *ctx)
+{
+	if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
+		tls_err_abort(sk, -EBADMSG);
+
+	if (prot->version != TLS_1_3_VERSION &&
+	    prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
+		tls_bigint_increment(ctx->iv + prot->salt_size,
+				     prot->iv_size);
+}
+
+static inline void
+tls_xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq)
+{
+	int i;
+
+	if (prot->version == TLS_1_3_VERSION ||
+	    prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) {
+		for (i = 0; i < 8; i++)
+			iv[i + 4] ^= seq[i];
+	}
+}
+
+static inline void
+tls_fill_prepend(struct tls_context *ctx, char *buf, size_t plaintext_len,
+		 unsigned char record_type)
+{
+	struct tls_prot_info *prot = &ctx->prot_info;
+	size_t pkt_len, iv_size = prot->iv_size;
+
+	pkt_len = plaintext_len + prot->tag_size;
+	if (prot->version != TLS_1_3_VERSION &&
+	    prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) {
+		pkt_len += iv_size;
+
+		memcpy(buf + TLS_NONCE_OFFSET,
+		       ctx->tx.iv + prot->salt_size, iv_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] = prot->version == TLS_1_3_VERSION ?
+		   TLS_RECORD_TYPE_DATA : record_type;
+	/* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */
+	buf[1] = TLS_1_2_VERSION_MINOR;
+	buf[2] = TLS_1_2_VERSION_MAJOR;
+	/* we can use IV for nonce explicit according to spec */
+	buf[3] = pkt_len >> 8;
+	buf[4] = pkt_len & 0xFF;
+}
+
+static inline
+void tls_make_aad(char *buf, size_t size, char *record_sequence,
+		  unsigned char record_type, struct tls_prot_info *prot)
+{
+	if (prot->version != TLS_1_3_VERSION) {
+		memcpy(buf, record_sequence, prot->rec_seq_size);
+		buf += 8;
+	} else {
+		size += prot->tag_size;
+	}
+
+	buf[0] = prot->version == TLS_1_3_VERSION ?
+		  TLS_RECORD_TYPE_DATA : record_type;
+	buf[1] = TLS_1_2_VERSION_MAJOR;
+	buf[2] = TLS_1_2_VERSION_MINOR;
+	buf[3] = size >> 8;
+	buf[4] = size & 0xFF;
+}
+
+#endif

linux-7.2.3/net/tls/tls_device_fallback.c

@@ -0,0 +1,471 @@
+/* Copyright (c) 2018, Mellanox Technologies 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.
+ */
+
+#include <net/tls.h>
+#include <crypto/aead.h>
+#include <crypto/scatterwalk.h>
+#include <net/ip6_checksum.h>
+#include <linux/skbuff_ref.h>
+
+#include "tls.h"
+
+static int tls_enc_record(struct aead_request *aead_req,
+			  struct crypto_aead *aead, char *aad,
+			  char *iv, __be64 rcd_sn,
+			  struct scatter_walk *in,
+			  struct scatter_walk *out, int *in_len,
+			  struct tls_prot_info *prot)
+{
+	unsigned char buf[TLS_HEADER_SIZE + TLS_MAX_IV_SIZE];
+	const struct tls_cipher_desc *cipher_desc;
+	struct scatterlist sg_in[3];
+	struct scatterlist sg_out[3];
+	unsigned int buf_size;
+	u16 len;
+	int rc;
+
+	cipher_desc = get_cipher_desc(prot->cipher_type);
+	DEBUG_NET_WARN_ON_ONCE(!cipher_desc || !cipher_desc->offloadable);
+
+	buf_size = TLS_HEADER_SIZE + cipher_desc->iv;
+	len = min_t(int, *in_len, buf_size);
+
+	memcpy_from_scatterwalk(buf, in, len);
+	memcpy_to_scatterwalk(out, buf, len);
+
+	*in_len -= len;
+	if (!*in_len)
+		return 0;
+
+	len = buf[4] | (buf[3] << 8);
+	len -= cipher_desc->iv;
+
+	tls_make_aad(aad, len - cipher_desc->tag, (char *)&rcd_sn, buf[0], prot);
+
+	memcpy(iv + cipher_desc->salt, buf + TLS_HEADER_SIZE, cipher_desc->iv);
+
+	sg_init_table(sg_in, ARRAY_SIZE(sg_in));
+	sg_init_table(sg_out, ARRAY_SIZE(sg_out));
+	sg_set_buf(sg_in, aad, TLS_AAD_SPACE_SIZE);
+	sg_set_buf(sg_out, aad, TLS_AAD_SPACE_SIZE);
+	scatterwalk_get_sglist(in, sg_in + 1);
+	scatterwalk_get_sglist(out, sg_out + 1);
+
+	*in_len -= len;
+	if (*in_len < 0) {
+		*in_len += cipher_desc->tag;
+		/* the input buffer doesn't contain the entire record.
+		 * trim len accordingly. The resulting authentication tag
+		 * will contain garbage, but we don't care, so we won't
+		 * include any of it in the output skb
+		 * Note that we assume the output buffer length
+		 * is larger then input buffer length + tag size
+		 */
+		if (*in_len < 0)
+			len += *in_len;
+
+		*in_len = 0;
+	}
+
+	if (*in_len) {
+		scatterwalk_skip(in, len);
+		scatterwalk_skip(out, len);
+	}
+
+	len -= cipher_desc->tag;
+	aead_request_set_crypt(aead_req, sg_in, sg_out, len, iv);
+
+	rc = crypto_aead_encrypt(aead_req);
+
+	return rc;
+}
+
+static void tls_init_aead_request(struct aead_request *aead_req,
+				  struct crypto_aead *aead)
+{
+	aead_request_set_tfm(aead_req, aead);
+	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
+}
+
+static struct aead_request *tls_alloc_aead_request(struct crypto_aead *aead,
+						   gfp_t flags)
+{
+	unsigned int req_size = sizeof(struct aead_request) +
+		crypto_aead_reqsize(aead);
+	struct aead_request *aead_req;
+
+	aead_req = kzalloc(req_size, flags);
+	if (aead_req)
+		tls_init_aead_request(aead_req, aead);
+	return aead_req;
+}
+
+static int tls_enc_records(struct aead_request *aead_req,
+			   struct crypto_aead *aead, struct scatterlist *sg_in,
+			   struct scatterlist *sg_out, char *aad, char *iv,
+			   u64 rcd_sn, int len, struct tls_prot_info *prot)
+{
+	struct scatter_walk out, in;
+	int rc;
+
+	scatterwalk_start(&in, sg_in);
+	scatterwalk_start(&out, sg_out);
+
+	do {
+		rc = tls_enc_record(aead_req, aead, aad, iv,
+				    cpu_to_be64(rcd_sn), &in, &out, &len, prot);
+		rcd_sn++;
+
+	} while (rc == 0 && len);
+
+	return rc;
+}
+
+static void update_chksum(struct sk_buff *skb, int headln)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+	int datalen = skb->len - headln;
+	const struct ipv6hdr *ipv6h;
+	const struct iphdr *iph;
+
+	/* We only changed the payload so if we are using partial we don't
+	 * need to update anything.
+	 */
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL))
+		return;
+
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	skb->csum_start = skb_transport_header(skb) - skb->head;
+	skb->csum_offset = offsetof(struct tcphdr, check);
+
+	if (skb->sk->sk_family == AF_INET6) {
+		ipv6h = ipv6_hdr(skb);
+		th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+					     datalen, IPPROTO_TCP, 0);
+	} else {
+		iph = ip_hdr(skb);
+		th->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen,
+					       IPPROTO_TCP, 0);
+	}
+}
+
+static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
+{
+	struct sock *sk = skb->sk;
+	int delta;
+
+	skb_copy_header(nskb, skb);
+
+	skb_put(nskb, skb->len);
+	memcpy(nskb->data, skb->data, headln);
+
+	nskb->destructor = skb->destructor;
+	nskb->sk = sk;
+	skb->destructor = NULL;
+	skb->sk = NULL;
+
+	update_chksum(nskb, headln);
+
+	/* sock_efree means skb must gone through skb_orphan_partial() */
+	if (nskb->destructor == sock_efree)
+		return;
+
+	delta = nskb->truesize - skb->truesize;
+	if (likely(delta < 0))
+		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+	else if (delta)
+		refcount_add(delta, &sk->sk_wmem_alloc);
+}
+
+/* This function may be called after the user socket is already
+ * closed so make sure we don't use anything freed during
+ * tls_sk_proto_close here
+ */
+
+static int fill_sg_in(struct scatterlist *sg_in,
+		      struct sk_buff *skb,
+		      struct tls_offload_context_tx *ctx,
+		      u64 *rcd_sn,
+		      s32 *sync_size,
+		      int *resync_sgs)
+{
+	int tcp_payload_offset = skb_tcp_all_headers(skb);
+	int payload_len = skb->len - tcp_payload_offset;
+	u32 tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	struct tls_record_info *record;
+	unsigned long flags;
+	int remaining;
+	int i;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	record = tls_get_record(ctx, tcp_seq, rcd_sn);
+	if (!record) {
+		spin_unlock_irqrestore(&ctx->lock, flags);
+		return -EINVAL;
+	}
+
+	*sync_size = tcp_seq - tls_record_start_seq(record);
+	if (*sync_size < 0) {
+		int is_start_marker = tls_record_is_start_marker(record);
+
+		spin_unlock_irqrestore(&ctx->lock, flags);
+		/* This should only occur if the relevant record was
+		 * already acked. In that case it should be ok
+		 * to drop the packet and avoid retransmission.
+		 *
+		 * There is a corner case where the packet contains
+		 * both an acked and a non-acked record.
+		 * We currently don't handle that case and rely
+		 * on TCP to retransmit a packet that doesn't contain
+		 * already acked payload.
+		 */
+		if (!is_start_marker)
+			*sync_size = 0;
+		return -EINVAL;
+	}
+
+	remaining = *sync_size;
+	for (i = 0; remaining > 0; i++) {
+		skb_frag_t *frag = &record->frags[i];
+
+		__skb_frag_ref(frag);
+		sg_set_page(sg_in + i, skb_frag_page(frag),
+			    skb_frag_size(frag), skb_frag_off(frag));
+
+		remaining -= skb_frag_size(frag);
+
+		if (remaining < 0)
+			sg_in[i].length += remaining;
+	}
+	*resync_sgs = i;
+
+	spin_unlock_irqrestore(&ctx->lock, flags);
+	if (skb_to_sgvec(skb, &sg_in[i], tcp_payload_offset, payload_len) < 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void fill_sg_out(struct scatterlist sg_out[3], void *buf,
+			struct tls_context *tls_ctx,
+			struct sk_buff *nskb,
+			int tcp_payload_offset,
+			int payload_len,
+			int sync_size,
+			void *dummy_buf)
+{
+	const struct tls_cipher_desc *cipher_desc =
+		get_cipher_desc(tls_ctx->crypto_send.info.cipher_type);
+
+	sg_set_buf(&sg_out[0], dummy_buf, sync_size);
+	sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len);
+	/* Add room for authentication tag produced by crypto */
+	dummy_buf += sync_size;
+	sg_set_buf(&sg_out[2], dummy_buf, cipher_desc->tag);
+}
+
+static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
+				   struct scatterlist sg_out[3],
+				   struct scatterlist *sg_in,
+				   struct sk_buff *skb,
+				   s32 sync_size, u64 rcd_sn)
+{
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
+	int tcp_payload_offset = skb_tcp_all_headers(skb);
+	int payload_len = skb->len - tcp_payload_offset;
+	const struct tls_cipher_desc *cipher_desc;
+	void *buf, *iv, *aad, *dummy_buf, *salt;
+	struct aead_request *aead_req;
+	struct sk_buff *nskb = NULL;
+	int buf_len;
+
+	aead_req = tls_alloc_aead_request(ctx->aead_send, GFP_ATOMIC);
+	if (!aead_req)
+		return NULL;
+
+	cipher_desc = get_cipher_desc(tls_ctx->crypto_send.info.cipher_type);
+	DEBUG_NET_WARN_ON_ONCE(!cipher_desc || !cipher_desc->offloadable);
+
+	buf_len = cipher_desc->salt + cipher_desc->iv + TLS_AAD_SPACE_SIZE +
+		  sync_size + cipher_desc->tag;
+	buf = kmalloc(buf_len, GFP_ATOMIC);
+	if (!buf)
+		goto free_req;
+
+	iv = buf;
+	salt = crypto_info_salt(&tls_ctx->crypto_send.info, cipher_desc);
+	memcpy(iv, salt, cipher_desc->salt);
+	aad = buf + cipher_desc->salt + cipher_desc->iv;
+	dummy_buf = aad + TLS_AAD_SPACE_SIZE;
+
+	nskb = alloc_skb(skb_headroom(skb) + skb->len, GFP_ATOMIC);
+	if (!nskb)
+		goto free_buf;
+
+	skb_reserve(nskb, skb_headroom(skb));
+
+	fill_sg_out(sg_out, buf, tls_ctx, nskb, tcp_payload_offset,
+		    payload_len, sync_size, dummy_buf);
+
+	if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv,
+			    rcd_sn, sync_size + payload_len,
+			    &tls_ctx->prot_info) < 0)
+		goto free_nskb;
+
+	complete_skb(nskb, skb, tcp_payload_offset);
+
+	/* validate_xmit_skb_list assumes that if the skb wasn't segmented
+	 * nskb->prev will point to the skb itself
+	 */
+	nskb->prev = nskb;
+
+free_buf:
+	kfree(buf);
+free_req:
+	kfree(aead_req);
+	return nskb;
+free_nskb:
+	kfree_skb(nskb);
+	nskb = NULL;
+	goto free_buf;
+}
+
+static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb)
+{
+	int tcp_payload_offset = skb_tcp_all_headers(skb);
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
+	int payload_len = skb->len - tcp_payload_offset;
+	struct scatterlist *sg_in, sg_out[3];
+	struct sk_buff *nskb = NULL;
+	int sg_in_max_elements;
+	int resync_sgs = 0;
+	s32 sync_size = 0;
+	u64 rcd_sn;
+
+	/* worst case is:
+	 * MAX_SKB_FRAGS in tls_record_info
+	 * MAX_SKB_FRAGS + 1 in SKB head and frags.
+	 */
+	sg_in_max_elements = 2 * MAX_SKB_FRAGS + 1;
+
+	if (!payload_len)
+		return skb;
+
+	sg_in = kmalloc_objs(*sg_in, sg_in_max_elements, GFP_ATOMIC);
+	if (!sg_in)
+		goto free_orig;
+
+	sg_init_table(sg_in, sg_in_max_elements);
+	sg_init_table(sg_out, ARRAY_SIZE(sg_out));
+
+	if (fill_sg_in(sg_in, skb, ctx, &rcd_sn, &sync_size, &resync_sgs)) {
+		/* bypass packets before kernel TLS socket option was set */
+		if (sync_size < 0 && payload_len <= -sync_size)
+			nskb = skb_get(skb);
+		goto put_sg;
+	}
+
+	nskb = tls_enc_skb(tls_ctx, sg_out, sg_in, skb, sync_size, rcd_sn);
+
+put_sg:
+	while (resync_sgs)
+		put_page(sg_page(&sg_in[--resync_sgs]));
+	kfree(sg_in);
+free_orig:
+	if (nskb)
+		consume_skb(skb);
+	else
+		kfree_skb(skb);
+	return nskb;
+}
+
+struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
+				      struct net_device *dev,
+				      struct sk_buff *skb)
+{
+	if (dev == rcu_dereference_bh(tls_get_ctx(sk)->netdev) ||
+	    netif_is_bond_master(dev))
+		return skb;
+
+	return tls_sw_fallback(sk, skb);
+}
+EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);
+
+struct sk_buff *tls_validate_xmit_skb_sw(struct sock *sk,
+					 struct net_device *dev,
+					 struct sk_buff *skb)
+{
+	return tls_sw_fallback(sk, skb);
+}
+
+struct sk_buff *tls_encrypt_skb(struct sk_buff *skb)
+{
+	return tls_sw_fallback(skb->sk, skb);
+}
+EXPORT_SYMBOL_GPL(tls_encrypt_skb);
+
+int tls_sw_fallback_init(struct sock *sk,
+			 struct tls_offload_context_tx *offload_ctx,
+			 struct tls_crypto_info *crypto_info)
+{
+	const struct tls_cipher_desc *cipher_desc;
+	int rc;
+
+	cipher_desc = get_cipher_desc(crypto_info->cipher_type);
+	if (!cipher_desc || !cipher_desc->offloadable)
+		return -EINVAL;
+
+	offload_ctx->aead_send =
+	    crypto_alloc_aead(cipher_desc->cipher_name, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(offload_ctx->aead_send)) {
+		rc = PTR_ERR(offload_ctx->aead_send);
+		pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc);
+		offload_ctx->aead_send = NULL;
+		goto err_out;
+	}
+
+	rc = crypto_aead_setkey(offload_ctx->aead_send,
+				crypto_info_key(crypto_info, cipher_desc),
+				cipher_desc->key);
+	if (rc)
+		goto free_aead;
+
+	rc = crypto_aead_setauthsize(offload_ctx->aead_send, cipher_desc->tag);
+	if (rc)
+		goto free_aead;
+
+	return 0;
+free_aead:
+	crypto_free_aead(offload_ctx->aead_send);
+err_out:
+	return rc;
+}

linux-7.2.3/net/tls/tls_proc.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/snmp.h>
+#include <net/tls.h>
+
+#include "tls.h"
+
+#ifdef CONFIG_PROC_FS
+static const struct snmp_mib tls_mib_list[] = {
+	SNMP_MIB_ITEM("TlsCurrTxSw", LINUX_MIB_TLSCURRTXSW),
+	SNMP_MIB_ITEM("TlsCurrRxSw", LINUX_MIB_TLSCURRRXSW),
+	SNMP_MIB_ITEM("TlsCurrTxDevice", LINUX_MIB_TLSCURRTXDEVICE),
+	SNMP_MIB_ITEM("TlsCurrRxDevice", LINUX_MIB_TLSCURRRXDEVICE),
+	SNMP_MIB_ITEM("TlsTxSw", LINUX_MIB_TLSTXSW),
+	SNMP_MIB_ITEM("TlsRxSw", LINUX_MIB_TLSRXSW),
+	SNMP_MIB_ITEM("TlsTxDevice", LINUX_MIB_TLSTXDEVICE),
+	SNMP_MIB_ITEM("TlsRxDevice", LINUX_MIB_TLSRXDEVICE),
+	SNMP_MIB_ITEM("TlsDecryptError", LINUX_MIB_TLSDECRYPTERROR),
+	SNMP_MIB_ITEM("TlsRxDeviceResync", LINUX_MIB_TLSRXDEVICERESYNC),
+	SNMP_MIB_ITEM("TlsDecryptRetry", LINUX_MIB_TLSDECRYPTRETRY),
+	SNMP_MIB_ITEM("TlsRxNoPadViolation", LINUX_MIB_TLSRXNOPADVIOL),
+	SNMP_MIB_ITEM("TlsRxRekeyOk", LINUX_MIB_TLSRXREKEYOK),
+	SNMP_MIB_ITEM("TlsRxRekeyError", LINUX_MIB_TLSRXREKEYERROR),
+	SNMP_MIB_ITEM("TlsTxRekeyOk", LINUX_MIB_TLSTXREKEYOK),
+	SNMP_MIB_ITEM("TlsTxRekeyError", LINUX_MIB_TLSTXREKEYERROR),
+	SNMP_MIB_ITEM("TlsRxRekeyReceived", LINUX_MIB_TLSRXREKEYRECEIVED),
+};
+
+static int tls_statistics_seq_show(struct seq_file *seq, void *v)
+{
+	unsigned long buf[ARRAY_SIZE(tls_mib_list)];
+	const int cnt = ARRAY_SIZE(tls_mib_list);
+	struct net *net = seq->private;
+	int i;
+
+	memset(buf, 0, sizeof(buf));
+	snmp_get_cpu_field_batch_cnt(buf, tls_mib_list, cnt,
+				     net->mib.tls_statistics);
+	for (i = 0; i < cnt; i++)
+		seq_printf(seq, "%-32s\t%lu\n", tls_mib_list[i].name, buf[i]);
+
+	return 0;
+}
+#endif
+
+int __net_init tls_proc_init(struct net *net)
+{
+#ifdef CONFIG_PROC_FS
+	if (!proc_create_net_single("tls_stat", 0444, net->proc_net,
+				    tls_statistics_seq_show, NULL))
+		return -ENOMEM;
+#endif /* CONFIG_PROC_FS */
+
+	return 0;
+}
+
+void __net_exit tls_proc_fini(struct net *net)
+{
+	remove_proc_entry("tls_stat", net->proc_net);
+}

linux-7.2.3/net/tls/tls_strp.c

@@ -0,0 +1,658 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */
+
+#include <linux/skbuff.h>
+#include <linux/skbuff_ref.h>
+#include <linux/workqueue.h>
+#include <net/strparser.h>
+#include <net/tcp.h>
+#include <net/sock.h>
+#include <net/tls.h>
+
+#include "tls.h"
+
+static struct workqueue_struct *tls_strp_wq;
+
+void tls_strp_abort_strp(struct tls_strparser *strp, int err)
+{
+	if (strp->stopped)
+		return;
+
+	strp->stopped = 1;
+
+	/* Report an error on the lower socket */
+	WRITE_ONCE(strp->sk->sk_err, -err);
+	/* Paired with smp_rmb() in tcp_poll() */
+	smp_wmb();
+	sk_error_report(strp->sk);
+}
+
+static void tls_strp_anchor_free(struct tls_strparser *strp)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(strp->anchor);
+
+	DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1);
+	if (!strp->copy_mode)
+		shinfo->frag_list = NULL;
+	consume_skb(strp->anchor);
+	strp->anchor = NULL;
+}
+
+static struct sk_buff *
+tls_strp_skb_copy(struct tls_strparser *strp, struct sk_buff *in_skb,
+		  int offset, int len)
+{
+	struct sk_buff *skb;
+	int i, err;
+
+	skb = alloc_skb_with_frags(0, len, TLS_PAGE_ORDER,
+				   &err, strp->sk->sk_allocation);
+	if (!skb)
+		return NULL;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON_ONCE(skb_copy_bits(in_skb, offset,
+					   skb_frag_address(frag),
+					   skb_frag_size(frag)));
+		offset += skb_frag_size(frag);
+	}
+
+	skb->len = len;
+	skb->data_len = len;
+	skb_copy_header(skb, in_skb);
+	return skb;
+}
+
+/* Create a new skb with the contents of input copied to its page frags */
+static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp)
+{
+	struct strp_msg *rxm;
+	struct sk_buff *skb;
+
+	skb = tls_strp_skb_copy(strp, strp->anchor, strp->stm.offset,
+				strp->stm.full_len);
+	if (!skb)
+		return NULL;
+
+	rxm = strp_msg(skb);
+	rxm->offset = 0;
+	return skb;
+}
+
+/* Steal the input skb, input msg is invalid after calling this function */
+struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx)
+{
+	struct tls_strparser *strp = &ctx->strp;
+
+#ifdef CONFIG_TLS_DEVICE
+	DEBUG_NET_WARN_ON_ONCE(!strp->anchor->decrypted);
+#else
+	/* This function turns an input into an output,
+	 * that can only happen if we have offload.
+	 */
+	WARN_ON(1);
+#endif
+
+	if (strp->copy_mode) {
+		struct sk_buff *skb;
+
+		/* Replace anchor with an empty skb, this is a little
+		 * dangerous but __tls_cur_msg() warns on empty skbs
+		 * so hopefully we'll catch abuses.
+		 */
+		skb = alloc_skb(0, strp->sk->sk_allocation);
+		if (!skb)
+			return NULL;
+
+		swap(strp->anchor, skb);
+		return skb;
+	}
+
+	return tls_strp_msg_make_copy(strp);
+}
+
+/* Force the input skb to be in copy mode. The data ownership remains
+ * with the input skb itself (meaning unpause will wipe it) but it can
+ * be modified.
+ */
+int tls_strp_msg_cow(struct tls_sw_context_rx *ctx)
+{
+	struct tls_strparser *strp = &ctx->strp;
+	struct sk_buff *skb;
+
+	if (strp->copy_mode)
+		return 0;
+
+	skb = tls_strp_msg_make_copy(strp);
+	if (!skb)
+		return -ENOMEM;
+
+	tls_strp_anchor_free(strp);
+	strp->anchor = skb;
+
+	tcp_read_done(strp->sk, strp->stm.full_len);
+	strp->copy_mode = 1;
+
+	return 0;
+}
+
+/* Make a clone (in the skb sense) of the input msg to keep a reference
+ * to the underlying data. The reference-holding skbs get placed on
+ * @dst.
+ */
+int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(strp->anchor);
+
+	if (strp->copy_mode) {
+		struct sk_buff *skb;
+
+		WARN_ON_ONCE(!shinfo->nr_frags);
+
+		/* We can't skb_clone() the anchor, it gets wiped by unpause */
+		skb = alloc_skb(0, strp->sk->sk_allocation);
+		if (!skb)
+			return -ENOMEM;
+
+		__skb_queue_tail(dst, strp->anchor);
+		strp->anchor = skb;
+	} else {
+		struct sk_buff *iter, *clone;
+		int chunk, len, offset;
+
+		offset = strp->stm.offset;
+		len = strp->stm.full_len;
+		iter = shinfo->frag_list;
+
+		while (len > 0) {
+			if (iter->len <= offset) {
+				offset -= iter->len;
+				goto next;
+			}
+
+			chunk = iter->len - offset;
+			offset = 0;
+
+			clone = skb_clone(iter, strp->sk->sk_allocation);
+			if (!clone)
+				return -ENOMEM;
+			__skb_queue_tail(dst, clone);
+
+			len -= chunk;
+next:
+			iter = iter->next;
+		}
+	}
+
+	return 0;
+}
+
+static void tls_strp_flush_anchor_copy(struct tls_strparser *strp)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(strp->anchor);
+	int i;
+
+	DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1);
+
+	for (i = 0; i < shinfo->nr_frags; i++)
+		__skb_frag_unref(&shinfo->frags[i], false);
+	shinfo->nr_frags = 0;
+	if (strp->copy_mode) {
+		kfree_skb_list(shinfo->frag_list);
+		shinfo->frag_list = NULL;
+	}
+	strp->copy_mode = 0;
+	strp->mixed_decrypted = 0;
+}
+
+static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb,
+				struct sk_buff *in_skb, unsigned int offset,
+				size_t in_len)
+{
+	unsigned int nfrag = skb->len / PAGE_SIZE;
+	size_t len, chunk;
+	skb_frag_t *frag;
+	int sz;
+
+	if (unlikely(nfrag >= skb_shinfo(skb)->nr_frags)) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return -EMSGSIZE;
+	}
+
+	frag = &skb_shinfo(skb)->frags[nfrag];
+
+	len = in_len;
+	/* First make sure we got the header */
+	if (!strp->stm.full_len) {
+		/* Assume one page is more than enough for headers */
+		chunk =	min_t(size_t, len, PAGE_SIZE - skb_frag_size(frag));
+		WARN_ON_ONCE(skb_copy_bits(in_skb, offset,
+					   skb_frag_address(frag) +
+					   skb_frag_size(frag),
+					   chunk));
+
+		skb->len += chunk;
+		skb->data_len += chunk;
+		skb_frag_size_add(frag, chunk);
+
+		sz = tls_rx_msg_size(strp, skb);
+		if (sz < 0)
+			return sz;
+
+		/* We may have over-read, sz == 0 is guaranteed under-read */
+		if (unlikely(sz && sz < skb->len)) {
+			int over = skb->len - sz;
+
+			WARN_ON_ONCE(over > chunk);
+			skb->len -= over;
+			skb->data_len -= over;
+			skb_frag_size_add(frag, -over);
+
+			chunk -= over;
+		}
+
+		frag++;
+		len -= chunk;
+		offset += chunk;
+
+		strp->stm.full_len = sz;
+		if (!strp->stm.full_len)
+			goto read_done;
+	}
+
+	/* Load up more data */
+	while (len && strp->stm.full_len > skb->len) {
+		chunk =	min_t(size_t, len, strp->stm.full_len - skb->len);
+		chunk = min_t(size_t, chunk, PAGE_SIZE - skb_frag_size(frag));
+		WARN_ON_ONCE(skb_copy_bits(in_skb, offset,
+					   skb_frag_address(frag) +
+					   skb_frag_size(frag),
+					   chunk));
+
+		skb->len += chunk;
+		skb->data_len += chunk;
+		skb_frag_size_add(frag, chunk);
+		frag++;
+		len -= chunk;
+		offset += chunk;
+	}
+
+read_done:
+	return in_len - len;
+}
+
+static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb,
+			       struct sk_buff *in_skb, unsigned int offset,
+			       size_t in_len)
+{
+	struct sk_buff *nskb, *first, *last;
+	struct skb_shared_info *shinfo;
+	size_t chunk;
+	int sz;
+
+	if (strp->stm.full_len)
+		chunk = strp->stm.full_len - skb->len;
+	else
+		chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE;
+	chunk = min(chunk, in_len);
+
+	nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk);
+	if (!nskb)
+		return -ENOMEM;
+
+	shinfo = skb_shinfo(skb);
+	if (!shinfo->frag_list) {
+		shinfo->frag_list = nskb;
+		nskb->prev = nskb;
+	} else {
+		first = shinfo->frag_list;
+		last = first->prev;
+		last->next = nskb;
+		first->prev = nskb;
+	}
+
+	skb->len += chunk;
+	skb->data_len += chunk;
+
+	if (!strp->stm.full_len) {
+		sz = tls_rx_msg_size(strp, skb);
+		if (sz < 0)
+			return sz;
+
+		/* We may have over-read, sz == 0 is guaranteed under-read */
+		if (unlikely(sz && sz < skb->len)) {
+			int over = skb->len - sz;
+
+			WARN_ON_ONCE(over > chunk);
+			skb->len -= over;
+			skb->data_len -= over;
+			__pskb_trim(nskb, nskb->len - over);
+
+			chunk -= over;
+		}
+
+		strp->stm.full_len = sz;
+	}
+
+	return chunk;
+}
+
+static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb,
+			   unsigned int offset, size_t in_len)
+{
+	struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data;
+	struct sk_buff *skb;
+	int ret;
+
+	if (strp->msg_ready)
+		return 0;
+
+	skb = strp->anchor;
+	if (!skb->len)
+		skb_copy_decrypted(skb, in_skb);
+	else
+		strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb);
+
+	if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted)
+		ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len);
+	else
+		ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len);
+	if (ret < 0) {
+		desc->error = ret;
+		ret = 0;
+	}
+
+	if (strp->stm.full_len && strp->stm.full_len == skb->len) {
+		desc->count = 0;
+
+		WRITE_ONCE(strp->msg_ready, 1);
+	}
+
+	return ret;
+}
+
+static int tls_strp_read_copyin(struct tls_strparser *strp)
+{
+	read_descriptor_t desc;
+
+	desc.arg.data = strp;
+	desc.error = 0;
+	desc.count = 1; /* give more than one skb per call */
+
+	/* sk should be locked here, so okay to do read_sock */
+	tcp_read_sock(strp->sk, &desc, tls_strp_copyin);
+
+	return desc.error;
+}
+
+static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort)
+{
+	struct skb_shared_info *shinfo;
+	struct page *page;
+	int need_spc, len;
+
+	/* If the rbuf is small or rcv window has collapsed to 0 we need
+	 * to read the data out. Otherwise the connection will stall.
+	 * Without pressure threshold of INT_MAX will never be ready.
+	 */
+	if (likely(qshort && !tcp_epollin_ready(strp->sk, INT_MAX)))
+		return 0;
+
+	shinfo = skb_shinfo(strp->anchor);
+
+	/* If we don't know the length go max plus page for cipher overhead */
+	need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE;
+
+	for (len = need_spc; len > 0; len -= PAGE_SIZE) {
+		page = alloc_page(strp->sk->sk_allocation);
+		if (!page) {
+			tls_strp_flush_anchor_copy(strp);
+			return -ENOMEM;
+		}
+
+		skb_fill_page_desc(strp->anchor, shinfo->nr_frags++,
+				   page, 0, 0);
+	}
+
+	shinfo->frag_list = NULL;
+
+	strp->copy_mode = 1;
+	strp->stm.offset = 0;
+
+	strp->anchor->len = 0;
+	strp->anchor->data_len = 0;
+	strp->anchor->truesize = round_up(need_spc, PAGE_SIZE);
+
+	tls_strp_read_copyin(strp);
+
+	return 0;
+}
+
+static bool tls_strp_check_queue_ok(struct tls_strparser *strp)
+{
+	unsigned int len = strp->stm.offset + strp->stm.full_len;
+	struct sk_buff *first, *skb;
+	u32 seq;
+
+	first = skb_shinfo(strp->anchor)->frag_list;
+	skb = first;
+	seq = TCP_SKB_CB(first)->seq;
+
+	/* Make sure there's no duplicate data in the queue,
+	 * and the decrypted status matches.
+	 */
+	while (skb->len < len) {
+		seq += skb->len;
+		len -= skb->len;
+		skb = skb->next;
+
+		if (TCP_SKB_CB(skb)->seq != seq)
+			return false;
+		if (skb_cmp_decrypted(first, skb))
+			return false;
+	}
+
+	return true;
+}
+
+static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len)
+{
+	struct tcp_sock *tp = tcp_sk(strp->sk);
+	struct sk_buff *first;
+	u32 offset;
+
+	first = tcp_recv_skb(strp->sk, tp->copied_seq, &offset);
+	if (WARN_ON_ONCE(!first))
+		return;
+
+	/* Bestow the state onto the anchor */
+	strp->anchor->len = offset + len;
+	strp->anchor->data_len = offset + len;
+	strp->anchor->truesize = offset + len;
+
+	skb_shinfo(strp->anchor)->frag_list = first;
+
+	skb_copy_header(strp->anchor, first);
+	strp->anchor->destructor = NULL;
+
+	strp->stm.offset = offset;
+}
+
+bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh)
+{
+	struct strp_msg *rxm;
+	struct tls_msg *tlm;
+
+	DEBUG_NET_WARN_ON_ONCE(!strp->msg_ready);
+	DEBUG_NET_WARN_ON_ONCE(!strp->stm.full_len);
+
+	if (!strp->copy_mode && force_refresh) {
+		if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) {
+			WRITE_ONCE(strp->msg_ready, 0);
+			strp->msg_announced = 0;
+			memset(&strp->stm, 0, sizeof(strp->stm));
+			return false;
+		}
+
+		tls_strp_load_anchor_with_queue(strp, strp->stm.full_len);
+	}
+
+	rxm = strp_msg(strp->anchor);
+	rxm->full_len	= strp->stm.full_len;
+	rxm->offset	= strp->stm.offset;
+	tlm = tls_msg(strp->anchor);
+	tlm->control	= strp->mark;
+
+	return true;
+}
+
+/* Called with lock held on lower socket */
+static int tls_strp_read_sock(struct tls_strparser *strp)
+{
+	int sz, inq;
+
+	inq = tcp_inq(strp->sk);
+	if (inq < 1)
+		return 0;
+
+	if (unlikely(strp->copy_mode))
+		return tls_strp_read_copyin(strp);
+
+	if (inq < strp->stm.full_len)
+		return tls_strp_read_copy(strp, true);
+
+	tls_strp_load_anchor_with_queue(strp, inq);
+	if (!strp->stm.full_len) {
+		sz = tls_rx_msg_size(strp, strp->anchor);
+		if (sz < 0)
+			return sz;
+
+		strp->stm.full_len = sz;
+
+		if (!strp->stm.full_len || inq < strp->stm.full_len)
+			return tls_strp_read_copy(strp, true);
+	}
+
+	if (!tls_strp_check_queue_ok(strp))
+		return tls_strp_read_copy(strp, false);
+
+	WRITE_ONCE(strp->msg_ready, 1);
+
+	return 0;
+}
+
+/* Parse queued data. When @announce is true and parsing produces a
+ * newly-ready record, fire the consumer notification. Callers that
+ * need to notify a waiter about a record parsed by another path
+ * should invoke tls_rx_msg_maybe_announce() directly.
+ */
+void tls_strp_check_rcv(struct tls_strparser *strp, bool announce)
+{
+	if (unlikely(strp->stopped) || strp->msg_ready)
+		return;
+
+	if (tls_strp_read_sock(strp) == -ENOMEM)
+		queue_work(tls_strp_wq, &strp->work);
+	else if (announce && strp->msg_ready)
+		tls_rx_msg_maybe_announce(strp);
+}
+
+/* Lower sock lock held */
+void tls_strp_data_ready(struct tls_strparser *strp)
+{
+	/* This check is needed to synchronize with do_tls_strp_work.
+	 * do_tls_strp_work acquires a process lock (lock_sock) whereas
+	 * the lock held here is bh_lock_sock. The two locks can be
+	 * held by different threads at the same time, but bh_lock_sock
+	 * allows a thread in BH context to safely check if the process
+	 * lock is held. In this case, if the lock is held, queue work.
+	 */
+	if (sock_owned_by_user_nocheck(strp->sk)) {
+		queue_work(tls_strp_wq, &strp->work);
+		return;
+	}
+
+	tls_strp_check_rcv(strp, true);
+}
+
+static void tls_strp_work(struct work_struct *w)
+{
+	struct tls_strparser *strp =
+		container_of(w, struct tls_strparser, work);
+
+	lock_sock(strp->sk);
+	tls_strp_check_rcv(strp, true);
+	release_sock(strp->sk);
+}
+
+/* Release the current record without triggering a check for the
+ * next record. Callers must invoke tls_strp_check_rcv() before
+ * releasing the socket lock, or queued data will stall until the
+ * next tls_strp_data_ready() event.
+ */
+void tls_strp_msg_consume(struct tls_strparser *strp)
+{
+	WARN_ON(!strp->stm.full_len);
+
+	if (likely(!strp->copy_mode))
+		tcp_read_done(strp->sk, strp->stm.full_len);
+	else
+		tls_strp_flush_anchor_copy(strp);
+
+	WRITE_ONCE(strp->msg_ready, 0);
+	strp->msg_announced = 0;
+	memset(&strp->stm, 0, sizeof(strp->stm));
+}
+
+void tls_strp_stop(struct tls_strparser *strp)
+{
+	strp->stopped = 1;
+}
+
+int tls_strp_init(struct tls_strparser *strp, struct sock *sk)
+{
+	memset(strp, 0, sizeof(*strp));
+
+	strp->sk = sk;
+
+	strp->anchor = alloc_skb(0, GFP_KERNEL);
+	if (!strp->anchor)
+		return -ENOMEM;
+
+	INIT_WORK(&strp->work, tls_strp_work);
+
+	return 0;
+}
+
+/* strp must already be stopped so that tls_strp_recv will no longer be called.
+ * Note that tls_strp_done is not called with the lower socket held.
+ */
+void tls_strp_done(struct tls_strparser *strp)
+{
+	WARN_ON(!strp->stopped);
+
+	cancel_work_sync(&strp->work);
+	__tls_strp_done(strp);
+}
+
+/* For setup error paths where the strparser was initialized but never armed. */
+void __tls_strp_done(struct tls_strparser *strp)
+{
+	tls_strp_anchor_free(strp);
+}
+
+int __init tls_strp_dev_init(void)
+{
+	tls_strp_wq = create_workqueue("tls-strp");
+	if (unlikely(!tls_strp_wq))
+		return -ENOMEM;
+
+	return 0;
+}
+
+void tls_strp_dev_exit(void)
+{
+	destroy_workqueue(tls_strp_wq);
+}

linux-7.2.3/net/tls/trace.c

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#endif

linux-7.2.3/net/tls/trace.h

@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (C) 2019 Netronome Systems, Inc. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tls
+
+#if !defined(_TLS_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _TLS_TRACE_H_
+
+#include <linux/unaligned.h>
+#include <linux/tracepoint.h>
+
+struct sock;
+
+TRACE_EVENT(tls_device_offload_set,
+
+	TP_PROTO(struct sock *sk, int dir, u32 tcp_seq, u8 *rec_no, int ret),
+
+	TP_ARGS(sk, dir, tcp_seq, rec_no, ret),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u64,		rec_no		)
+		__field(	int,		dir		)
+		__field(	u32,		tcp_seq		)
+		__field(	int,		ret		)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->rec_no = get_unaligned_be64(rec_no);
+		__entry->dir = dir;
+		__entry->tcp_seq = tcp_seq;
+		__entry->ret = ret;
+	),
+
+	TP_printk(
+		"sk=%p direction=%d tcp_seq=%u rec_no=%llu ret=%d",
+		__entry->sk, __entry->dir, __entry->tcp_seq, __entry->rec_no,
+		__entry->ret
+	)
+);
+
+TRACE_EVENT(tls_device_decrypted,
+
+	TP_PROTO(struct sock *sk, u32 tcp_seq, u8 *rec_no, u32 rec_len,
+		 bool encrypted, bool decrypted),
+
+	TP_ARGS(sk, tcp_seq, rec_no, rec_len, encrypted, decrypted),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u64,		rec_no		)
+		__field(	u32,		tcp_seq		)
+		__field(	u32,		rec_len		)
+		__field(	bool,		encrypted	)
+		__field(	bool,		decrypted	)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->rec_no = get_unaligned_be64(rec_no);
+		__entry->tcp_seq = tcp_seq;
+		__entry->rec_len = rec_len;
+		__entry->encrypted = encrypted;
+		__entry->decrypted = decrypted;
+	),
+
+	TP_printk(
+		"sk=%p tcp_seq=%u rec_no=%llu len=%u encrypted=%d decrypted=%d",
+		__entry->sk, __entry->tcp_seq,
+		__entry->rec_no, __entry->rec_len,
+		__entry->encrypted, __entry->decrypted
+	)
+);
+
+TRACE_EVENT(tls_device_rx_resync_send,
+
+	TP_PROTO(struct sock *sk, u32 tcp_seq, u8 *rec_no, int sync_type),
+
+	TP_ARGS(sk, tcp_seq, rec_no, sync_type),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u64,		rec_no		)
+		__field(	u32,		tcp_seq		)
+		__field(	int,		sync_type	)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->rec_no = get_unaligned_be64(rec_no);
+		__entry->tcp_seq = tcp_seq;
+		__entry->sync_type = sync_type;
+	),
+
+	TP_printk(
+		"sk=%p tcp_seq=%u rec_no=%llu sync_type=%d",
+		__entry->sk, __entry->tcp_seq, __entry->rec_no,
+		__entry->sync_type
+	)
+);
+
+TRACE_EVENT(tls_device_rx_resync_nh_schedule,
+
+	TP_PROTO(struct sock *sk),
+
+	TP_ARGS(sk),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+	),
+
+	TP_printk(
+		"sk=%p", __entry->sk
+	)
+);
+
+TRACE_EVENT(tls_device_rx_resync_nh_delay,
+
+	TP_PROTO(struct sock *sk, u32 sock_data, u32 rec_len),
+
+	TP_ARGS(sk, sock_data, rec_len),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u32,		sock_data	)
+		__field(	u32,		rec_len		)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->sock_data = sock_data;
+		__entry->rec_len = rec_len;
+	),
+
+	TP_printk(
+		"sk=%p sock_data=%u rec_len=%u",
+		__entry->sk, __entry->sock_data, __entry->rec_len
+	)
+);
+
+TRACE_EVENT(tls_device_tx_resync_req,
+
+	TP_PROTO(struct sock *sk, u32 tcp_seq, u32 exp_tcp_seq),
+
+	TP_ARGS(sk, tcp_seq, exp_tcp_seq),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u32,		tcp_seq		)
+		__field(	u32,		exp_tcp_seq	)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->tcp_seq = tcp_seq;
+		__entry->exp_tcp_seq = exp_tcp_seq;
+	),
+
+	TP_printk(
+		"sk=%p tcp_seq=%u exp_tcp_seq=%u",
+		__entry->sk, __entry->tcp_seq, __entry->exp_tcp_seq
+	)
+);
+
+TRACE_EVENT(tls_device_tx_resync_send,
+
+	TP_PROTO(struct sock *sk, u32 tcp_seq, u8 *rec_no),
+
+	TP_ARGS(sk, tcp_seq, rec_no),
+
+	TP_STRUCT__entry(
+		__field(	struct sock *,	sk		)
+		__field(	u64,		rec_no		)
+		__field(	u32,		tcp_seq		)
+	),
+
+	TP_fast_assign(
+		__entry->sk = sk;
+		__entry->rec_no = get_unaligned_be64(rec_no);
+		__entry->tcp_seq = tcp_seq;
+	),
+
+	TP_printk(
+		"sk=%p tcp_seq=%u rec_no=%llu",
+		__entry->sk, __entry->tcp_seq, __entry->rec_no
+	)
+);
+
+#endif /* _TLS_TRACE_H_ */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>