From 210620ae44a83f25220450bbfcc22e6fe986b25f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:37 -0700 Subject: tls: rx: strp: set the skb->len of detached / CoW'ed skbs alloc_skb_with_frags() fills in page frag sizes but does not set skb->len and skb->data_len. Set those correctly otherwise device offload will most likely generate an empty skb and hit the BUG() at the end of __skb_nsg(). Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 955ac3e0bf4d..24016c865e00 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -56,6 +56,8 @@ static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) offset += skb_frag_size(frag); } + skb->len = strp->stm.full_len; + skb->data_len = strp->stm.full_len; skb_copy_header(skb, strp->anchor); rxm = strp_msg(skb); rxm->offset = 0; -- cgit From 14c4be92ebb3e36e392aa9dd8f314038a9f96f3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:38 -0700 Subject: tls: rx: strp: force mixed decrypted records into copy mode If a record is partially decrypted we'll have to CoW it, anyway, so go into copy mode and allocate a writable skb right away. This will make subsequent fix simpler because we won't have to teach tls_strp_msg_make_copy() how to copy skbs while preserving decrypt status. Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 24016c865e00..2b6fa9855999 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -317,15 +317,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; } -static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq; - skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->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; @@ -333,6 +337,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp) if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; } return true; @@ -413,7 +419,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); } - if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); strp->msg_ready = 1; -- cgit From 8b0c0dc9fbbd01e58a573a41c38885f9e4c17696 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:39 -0700 Subject: tls: rx: strp: fix determining record length in copy mode We call tls_rx_msg_size(skb) before doing skb->len += chunk. So the tls_rx_msg_size() code will see old skb->len, most likely leading to an over-read. Worst case we will over read an entire record, next iteration will try to trim the skb but may end up turning frag len negative or discarding the subsequent record (since we already told TCP we've read it during previous read but now we'll trim it out of the skb). Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 2b6fa9855999..e2e48217e7ac 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -210,19 +210,28 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size(frag), chunk)); - sz = tls_rx_msg_size(strp, strp->anchor); + skb->len += chunk; + skb->data_len += chunk; + skb_frag_size_add(frag, chunk); + + sz = tls_rx_msg_size(strp, skb); if (sz < 0) { desc->error = sz; return 0; } /* We may have over-read, sz == 0 is guaranteed under-read */ - if (sz > 0) - chunk = min_t(size_t, chunk, sz - skb->len); + 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; + } - skb->len += chunk; - skb->data_len += chunk; - skb_frag_size_add(frag, chunk); frag++; len -= chunk; offset += chunk; -- cgit From c1c607b1e5d5477d82ca6a86a05a4f10907b33ee Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:40 -0700 Subject: tls: rx: strp: factor out copying skb data We'll need to copy input skbs individually in the next patch. Factor that code out (without assuming we're copying a full record). Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index e2e48217e7ac..61fbf84baf9e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -34,31 +34,44 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) strp->anchor = NULL; } -/* 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) +static struct sk_buff * +tls_strp_skb_copy(struct tls_strparser *strp, struct sk_buff *in_skb, + int offset, int len) { - struct strp_msg *rxm; struct sk_buff *skb; - int i, err, offset; + int i, err; - skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER, + skb = alloc_skb_with_frags(0, len, TLS_PAGE_ORDER, &err, strp->sk->sk_allocation); if (!skb) return NULL; - offset = strp->stm.offset; 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(strp->anchor, offset, + WARN_ON_ONCE(skb_copy_bits(in_skb, offset, skb_frag_address(frag), skb_frag_size(frag))); offset += skb_frag_size(frag); } - skb->len = strp->stm.full_len; - skb->data_len = strp->stm.full_len; - skb_copy_header(skb, strp->anchor); + 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; -- cgit From eca9bfafee3a0487e59c59201ae14c7594ba940a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:41 -0700 Subject: tls: rx: strp: preserve decryption status of skbs when needed When receive buffer is small we try to copy out the data from TCP into a skb maintained by TLS to prevent connection from stalling. Unfortunately if a single record is made up of a mix of decrypted and non-decrypted skbs combining them into a single skb leads to loss of decryption status, resulting in decryption errors or data corruption. Similarly when trying to use TCP receive queue directly we need to make sure that all the skbs within the record have the same status. If we don't the mixed status will be detected correctly but we'll CoW the anchor, again collapsing it into a single paged skb without decrypted status preserved. So the "fixup" code will not know which parts of skb to re-encrypt. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 117 +++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 100 insertions(+), 17 deletions(-) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 61fbf84baf9e..da95abbb7ea3 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -29,7 +29,8 @@ 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); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } @@ -195,22 +196,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) 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(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +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) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz; - if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; len = in_len; @@ -228,10 +229,8 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size_add(frag, chunk); sz = tls_rx_msg_size(strp, skb); - if (sz < 0) { - desc->error = sz; - return 0; - } + if (sz < 0) + return sz; /* We may have over-read, sz == 0 is guaranteed under-read */ if (unlikely(sz && sz < skb->len)) { @@ -271,15 +270,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; } - if (strp->stm.full_len == skb->len) { +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; strp->msg_ready = 1; tls_rx_msg_ready(strp); } -read_done: - return in_len - len; + return ret; } static int tls_strp_read_copyin(struct tls_strparser *strp) -- cgit From 8a0d57df8938e9fd2e99d47a85b7f37d86f91097 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 May 2023 22:17:41 -0700 Subject: tls: improve lockless access safety of tls_err_abort() Most protos' poll() methods insert a memory barrier between writes to sk_err and sk_error_report(). This dates back to commit a4d258036ed9 ("tcp: Fix race in tcp_poll"). I guess we should do the same thing in TLS, tcp_poll() does not hold the socket lock. Fixes: 3c4d7559159b ("tls: kernel TLS support") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/tls/tls_strp.c') diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index da95abbb7ea3..f37f4a0fcd3c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err) strp->stopped = 1; /* Report an error on the lower socket */ - strp->sk->sk_err = -err; + WRITE_ONCE(strp->sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(strp->sk); } -- cgit