--- /dev/null
+From 551844f26da2a9f76c0a698baaffa631d1178645 Mon Sep 17 00:00:00 2001
+From: Paolo Abeni <pabeni@redhat.com>
+Date: Mon, 30 Dec 2024 19:12:31 +0100
+Subject: mptcp: don't always assume copied data in mptcp_cleanup_rbuf()
+
+From: Paolo Abeni <pabeni@redhat.com>
+
+commit 551844f26da2a9f76c0a698baaffa631d1178645 upstream.
+
+Under some corner cases the MPTCP protocol can end-up invoking
+mptcp_cleanup_rbuf() when no data has been copied, but such helper
+assumes the opposite condition.
+
+Explicitly drop such assumption and performs the costly call only
+when strictly needed - before releasing the msk socket lock.
+
+Fixes: fd8976790a6c ("mptcp: be careful on MPTCP-level ack.")
+Cc: stable@vger.kernel.org
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Reviewed-by: Mat Martineau <martineau@kernel.org>
+Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
+Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-2-8608af434ceb@kernel.org
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/mptcp/protocol.c | 18 +++++++++---------
+ 1 file changed, 9 insertions(+), 9 deletions(-)
+
+--- a/net/mptcp/protocol.c
++++ b/net/mptcp/protocol.c
+@@ -528,13 +528,13 @@ static void mptcp_send_ack(struct mptcp_
+ mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow));
+ }
+
+-static void mptcp_subflow_cleanup_rbuf(struct sock *ssk)
++static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied)
+ {
+ bool slow;
+
+ slow = lock_sock_fast(ssk);
+ if (tcp_can_send_ack(ssk))
+- tcp_cleanup_rbuf(ssk, 1);
++ tcp_cleanup_rbuf(ssk, copied);
+ unlock_sock_fast(ssk, slow);
+ }
+
+@@ -551,7 +551,7 @@ static bool mptcp_subflow_could_cleanup(
+ (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED)));
+ }
+
+-static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
++static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied)
+ {
+ int old_space = READ_ONCE(msk->old_wspace);
+ struct mptcp_subflow_context *subflow;
+@@ -559,14 +559,14 @@ static void mptcp_cleanup_rbuf(struct mp
+ int space = __mptcp_space(sk);
+ bool cleanup, rx_empty;
+
+- cleanup = (space > 0) && (space >= (old_space << 1));
+- rx_empty = !__mptcp_rmem(sk);
++ cleanup = (space > 0) && (space >= (old_space << 1)) && copied;
++ rx_empty = !__mptcp_rmem(sk) && copied;
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty))
+- mptcp_subflow_cleanup_rbuf(ssk);
++ mptcp_subflow_cleanup_rbuf(ssk, copied);
+ }
+ }
+
+@@ -2220,9 +2220,6 @@ static int mptcp_recvmsg(struct sock *sk
+
+ copied += bytes_read;
+
+- /* be sure to advertise window change */
+- mptcp_cleanup_rbuf(msk);
+-
+ if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
+ continue;
+
+@@ -2271,6 +2268,7 @@ static int mptcp_recvmsg(struct sock *sk
+ }
+
+ pr_debug("block timeout %ld\n", timeo);
++ mptcp_cleanup_rbuf(msk, copied);
+ err = sk_wait_data(sk, &timeo, NULL);
+ if (err < 0) {
+ err = copied ? : err;
+@@ -2278,6 +2276,8 @@ static int mptcp_recvmsg(struct sock *sk
+ }
+ }
+
++ mptcp_cleanup_rbuf(msk, copied);
++
+ out_err:
+ if (cmsg_flags && copied >= 0) {
+ if (cmsg_flags & MPTCP_CMSG_TS)
--- /dev/null
+From 449e6912a2522af672e99992e1201a454910864e Mon Sep 17 00:00:00 2001
+From: Paolo Abeni <pabeni@redhat.com>
+Date: Mon, 30 Dec 2024 19:12:30 +0100
+Subject: mptcp: fix recvbuffer adjust on sleeping rcvmsg
+
+From: Paolo Abeni <pabeni@redhat.com>
+
+commit 449e6912a2522af672e99992e1201a454910864e upstream.
+
+If the recvmsg() blocks after receiving some data - i.e. due to
+SO_RCVLOWAT - the MPTCP code will attempt multiple times to
+adjust the receive buffer size, wrongly accounting every time the
+cumulative of received data - instead of accounting only for the
+delta.
+
+Address the issue moving mptcp_rcv_space_adjust just after the
+data reception and passing it only the just received bytes.
+
+This also removes an unneeded difference between the TCP and MPTCP
+RX code path implementation.
+
+Fixes: 581302298524 ("mptcp: error out earlier on disconnect")
+Cc: stable@vger.kernel.org
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Reviewed-by: Mat Martineau <martineau@kernel.org>
+Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
+Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-1-8608af434ceb@kernel.org
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/mptcp/protocol.c | 6 +++---
+ 1 file changed, 3 insertions(+), 3 deletions(-)
+
+--- a/net/mptcp/protocol.c
++++ b/net/mptcp/protocol.c
+@@ -1939,6 +1939,8 @@ do_error:
+ goto out;
+ }
+
++static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
++
+ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
+ struct msghdr *msg,
+ size_t len, int flags,
+@@ -1992,6 +1994,7 @@ static int __mptcp_recvmsg_mskq(struct m
+ break;
+ }
+
++ mptcp_rcv_space_adjust(msk, copied);
+ return copied;
+ }
+
+@@ -2268,7 +2271,6 @@ static int mptcp_recvmsg(struct sock *sk
+ }
+
+ pr_debug("block timeout %ld\n", timeo);
+- mptcp_rcv_space_adjust(msk, copied);
+ err = sk_wait_data(sk, &timeo, NULL);
+ if (err < 0) {
+ err = copied ? : err;
+@@ -2276,8 +2278,6 @@ static int mptcp_recvmsg(struct sock *sk
+ }
+ }
+
+- mptcp_rcv_space_adjust(msk, copied);
+-
+ out_err:
+ if (cmsg_flags && copied >= 0) {
+ if (cmsg_flags & MPTCP_CMSG_TS)
--- /dev/null
+From cbb26f7d8451fe56ccac802c6db48d16240feebd Mon Sep 17 00:00:00 2001
+From: Paolo Abeni <pabeni@redhat.com>
+Date: Sat, 21 Dec 2024 09:51:46 +0100
+Subject: mptcp: fix TCP options overflow.
+
+From: Paolo Abeni <pabeni@redhat.com>
+
+commit cbb26f7d8451fe56ccac802c6db48d16240feebd upstream.
+
+Syzbot reported the following splat:
+
+Oops: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN PTI
+KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f]
+CPU: 1 UID: 0 PID: 5836 Comm: sshd Not tainted 6.13.0-rc3-syzkaller #0
+Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/25/2024
+RIP: 0010:_compound_head include/linux/page-flags.h:242 [inline]
+RIP: 0010:put_page+0x23/0x260 include/linux/mm.h:1552
+Code: 90 90 90 90 90 90 90 55 41 57 41 56 53 49 89 fe 48 bd 00 00 00 00 00 fc ff df e8 f8 5e 12 f8 49 8d 5e 08 48 89 d8 48 c1 e8 03 <80> 3c 28 00 74 08 48 89 df e8 8f c7 78 f8 48 8b 1b 48 89 de 48 83
+RSP: 0000:ffffc90003916c90 EFLAGS: 00010202
+RAX: 0000000000000001 RBX: 0000000000000008 RCX: ffff888030458000
+RDX: 0000000000000100 RSI: 0000000000000000 RDI: 0000000000000000
+RBP: dffffc0000000000 R08: ffffffff898ca81d R09: 1ffff110054414ac
+R10: dffffc0000000000 R11: ffffed10054414ad R12: 0000000000000007
+R13: ffff88802a20a542 R14: 0000000000000000 R15: 0000000000000000
+FS: 00007f34f496e800(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000
+CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 00007f9d6ec9ec28 CR3: 000000004d260000 CR4: 00000000003526f0
+DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
+DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
+Call Trace:
+ <TASK>
+ skb_page_unref include/linux/skbuff_ref.h:43 [inline]
+ __skb_frag_unref include/linux/skbuff_ref.h:56 [inline]
+ skb_release_data+0x483/0x8a0 net/core/skbuff.c:1119
+ skb_release_all net/core/skbuff.c:1190 [inline]
+ __kfree_skb+0x55/0x70 net/core/skbuff.c:1204
+ tcp_clean_rtx_queue net/ipv4/tcp_input.c:3436 [inline]
+ tcp_ack+0x2442/0x6bc0 net/ipv4/tcp_input.c:4032
+ tcp_rcv_state_process+0x8eb/0x44e0 net/ipv4/tcp_input.c:6805
+ tcp_v4_do_rcv+0x77d/0xc70 net/ipv4/tcp_ipv4.c:1939
+ tcp_v4_rcv+0x2dc0/0x37f0 net/ipv4/tcp_ipv4.c:2351
+ ip_protocol_deliver_rcu+0x22e/0x440 net/ipv4/ip_input.c:205
+ ip_local_deliver_finish+0x341/0x5f0 net/ipv4/ip_input.c:233
+ NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
+ NF_HOOK+0x3a4/0x450 include/linux/netfilter.h:314
+ __netif_receive_skb_one_core net/core/dev.c:5672 [inline]
+ __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5785
+ process_backlog+0x662/0x15b0 net/core/dev.c:6117
+ __napi_poll+0xcb/0x490 net/core/dev.c:6883
+ napi_poll net/core/dev.c:6952 [inline]
+ net_rx_action+0x89b/0x1240 net/core/dev.c:7074
+ handle_softirqs+0x2d4/0x9b0 kernel/softirq.c:561
+ __do_softirq kernel/softirq.c:595 [inline]
+ invoke_softirq kernel/softirq.c:435 [inline]
+ __irq_exit_rcu+0xf7/0x220 kernel/softirq.c:662
+ irq_exit_rcu+0x9/0x30 kernel/softirq.c:678
+ instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1049 [inline]
+ sysvec_apic_timer_interrupt+0x57/0xc0 arch/x86/kernel/apic/apic.c:1049
+ asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
+RIP: 0033:0x7f34f4519ad5
+Code: 85 d2 74 0d 0f 10 02 48 8d 54 24 20 0f 11 44 24 20 64 8b 04 25 18 00 00 00 85 c0 75 27 41 b8 08 00 00 00 b8 0f 01 00 00 0f 05 <48> 3d 00 f0 ff ff 76 75 48 8b 15 24 73 0d 00 f7 d8 64 89 02 48 83
+RSP: 002b:00007ffec5b32ce0 EFLAGS: 00000246
+RAX: 0000000000000001 RBX: 00000000000668a0 RCX: 00007f34f4519ad5
+RDX: 00007ffec5b32d00 RSI: 0000000000000004 RDI: 0000564f4bc6cae0
+RBP: 0000564f4bc6b5a0 R08: 0000000000000008 R09: 0000000000000000
+R10: 00007ffec5b32de8 R11: 0000000000000246 R12: 0000564f48ea8aa4
+R13: 0000000000000001 R14: 0000564f48ea93e8 R15: 00007ffec5b32d68
+ </TASK>
+
+Eric noted a probable shinfo->nr_frags corruption, which indeed
+occurs.
+
+The root cause is a buggy MPTCP option len computation in some
+circumstances: the ADD_ADDR option should be mutually exclusive
+with DSS since the blamed commit.
+
+Still, mptcp_established_options_add_addr() tries to set the
+relevant info in mptcp_out_options, if the remaining space is
+large enough even when DSS is present.
+
+Since the ADD_ADDR infos and the DSS share the same union
+fields, adding first corrupts the latter. In the worst-case
+scenario, such corruption increases the DSS binary layout,
+exceeding the computed length and possibly overwriting the
+skb shared info.
+
+Address the issue by enforcing mutual exclusion in
+mptcp_established_options_add_addr(), too.
+
+Cc: stable@vger.kernel.org
+Reported-by: syzbot+38a095a81f30d82884c1@syzkaller.appspotmail.com
+Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/538
+Fixes: 1bff1e43a30e ("mptcp: optimize out option generation")
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Link: https://patch.msgid.link/025d9df8cde3c9a557befc47e9bc08fbbe3476e5.1734771049.git.pabeni@redhat.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/mptcp/options.c | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+--- a/net/mptcp/options.c
++++ b/net/mptcp/options.c
+@@ -667,8 +667,15 @@ static bool mptcp_established_options_ad
+ &echo, &drop_other_suboptions))
+ return false;
+
++ /*
++ * Later on, mptcp_write_options() will enforce mutually exclusion with
++ * DSS, bail out if such option is set and we can't drop it.
++ */
+ if (drop_other_suboptions)
+ remaining += opt_size;
++ else if (opts->suboptions & OPTION_MPTCP_DSS)
++ return false;
++
+ len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
+ if (remaining < len)
+ return false;
--- /dev/null
+From 56b824eb49d6258aa0bad09a406ceac3f643cdae Mon Sep 17 00:00:00 2001
+From: Paolo Abeni <pabeni@redhat.com>
+Date: Mon, 30 Dec 2024 19:12:32 +0100
+Subject: mptcp: prevent excessive coalescing on receive
+
+From: Paolo Abeni <pabeni@redhat.com>
+
+commit 56b824eb49d6258aa0bad09a406ceac3f643cdae upstream.
+
+Currently the skb size after coalescing is only limited by the skb
+layout (the skb must not carry frag_list). A single coalesced skb
+covering several MSS can potentially fill completely the receive
+buffer. In such a case, the snd win will zero until the receive buffer
+will be empty again, affecting tput badly.
+
+Fixes: 8268ed4c9d19 ("mptcp: introduce and use mptcp_try_coalesce()")
+Cc: stable@vger.kernel.org # please delay 2 weeks after 6.13-final release
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Reviewed-by: Mat Martineau <martineau@kernel.org>
+Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
+Link: https://patch.msgid.link/20241230-net-mptcp-rbuf-fixes-v1-3-8608af434ceb@kernel.org
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/mptcp/protocol.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+--- a/net/mptcp/protocol.c
++++ b/net/mptcp/protocol.c
+@@ -136,6 +136,7 @@ static bool mptcp_try_coalesce(struct so
+ int delta;
+
+ if (MPTCP_SKB_CB(from)->offset ||
++ ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||
+ !skb_try_coalesce(to, from, &fragstolen, &delta))
+ return false;
+
mm-vmscan-account-for-free-pages-to-prevent-infinite-loop-in-throttle_direct_reclaim.patch
mm-reinstate-ability-to-map-write-sealed-memfd-mappings-read-only.patch
mm-hugetlb-independent-pmd-page-table-shared-count.patch
+mptcp-fix-tcp-options-overflow.patch
+mptcp-fix-recvbuffer-adjust-on-sleeping-rcvmsg.patch
+mptcp-don-t-always-assume-copied-data-in-mptcp_cleanup_rbuf.patch
+mptcp-prevent-excessive-coalescing-on-receive.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
