From: Greg Kroah-Hartman Date: Mon, 21 Oct 2024 09:50:46 +0000 (+0200) Subject: 5.10-stable patches X-Git-Tag: v5.10.228~13 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=dc6a2c7bc1b9285f033501f2b5a8e3a4e156c418;p=thirdparty%2Fkernel%2Fstable-queue.git 5.10-stable patches added patches: mptcp-handle-consistently-dss-corruption.patch mptcp-track-and-update-contiguous-data-status.patch nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch powerpc-mm-always-update-max-min_low_pfn-in-mem_topology_setup.patch tcp-fix-mptcp-dss-corruption-due-to-large-pmtu-xmit.patch --- diff --git a/queue-5.10/mptcp-handle-consistently-dss-corruption.patch b/queue-5.10/mptcp-handle-consistently-dss-corruption.patch new file mode 100644 index 00000000000..5850f8c44dd --- /dev/null +++ b/queue-5.10/mptcp-handle-consistently-dss-corruption.patch @@ -0,0 +1,111 @@ +From stable+bounces-86910-greg=kroah.com@vger.kernel.org Sat Oct 19 12:29:23 2024 +From: "Matthieu Baerts (NGI0)" +Date: Sat, 19 Oct 2024 12:29:08 +0200 +Subject: mptcp: handle consistently DSS corruption +To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org +Cc: Paolo Abeni , sashal@kernel.org, Matthieu Baerts , Jakub Kicinski +Message-ID: <20241019102905.3383483-7-matttbe@kernel.org> + +From: Paolo Abeni + +commit e32d262c89e2b22cb0640223f953b548617ed8a6 upstream. + +Bugged peer implementation can send corrupted DSS options, consistently +hitting a few warning in the data path. Use DEBUG_NET assertions, to +avoid the splat on some builds and handle consistently the error, dumping +related MIBs and performing fallback and/or reset according to the +subflow type. + +Fixes: 6771bfd9ee24 ("mptcp: update mptcp ack sequence from work queue") +Cc: stable@vger.kernel.org +Signed-off-by: Paolo Abeni +Reviewed-by: Matthieu Baerts (NGI0) +Signed-off-by: Matthieu Baerts (NGI0) +Link: https://patch.msgid.link/20241008-net-mptcp-fallback-fixes-v1-1-c6fb8e93e551@kernel.org +Signed-off-by: Jakub Kicinski +[ Conflicts in mib.[ch], because commit 104125b82e5c ("mptcp: add mib + for infinite map sending") is linked to a new feature, not available + in this version. Resolving the conflicts is easy, simply adding the + new lines declaring the new "DSS corruptions" MIB entries. + Also removed in protocol.c and subflow.c all DEBUG_NET_WARN_ON_ONCE + because they are not defined in this version: enough with the MIB + counters that have been added in this commit. ] +Signed-off-by: Matthieu Baerts (NGI0) +Signed-off-by: Greg Kroah-Hartman +--- + net/mptcp/mib.c | 2 ++ + net/mptcp/mib.h | 2 ++ + net/mptcp/protocol.c | 20 +++++++++++++++++--- + net/mptcp/subflow.c | 2 +- + 4 files changed, 22 insertions(+), 4 deletions(-) + +--- a/net/mptcp/mib.c ++++ b/net/mptcp/mib.c +@@ -23,6 +23,8 @@ static const struct snmp_mib mptcp_snmp_ + SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), + SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), + SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), ++ SNMP_MIB_ITEM("DSSCorruptionFallback", MPTCP_MIB_DSSCORRUPTIONFALLBACK), ++ SNMP_MIB_ITEM("DSSCorruptionReset", MPTCP_MIB_DSSCORRUPTIONRESET), + SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), + SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), + SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), +--- a/net/mptcp/mib.h ++++ b/net/mptcp/mib.h +@@ -16,6 +16,8 @@ enum linux_mptcp_mib_field { + MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ + MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ + MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ ++ MPTCP_MIB_DSSCORRUPTIONFALLBACK,/* DSS corruption detected, fallback */ ++ MPTCP_MIB_DSSCORRUPTIONRESET, /* DSS corruption detected, MPJ subflow reset */ + MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ + MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ + MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ +--- a/net/mptcp/protocol.c ++++ b/net/mptcp/protocol.c +@@ -457,6 +457,18 @@ static void mptcp_check_data_fin(struct + } + } + ++static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) ++{ ++ if (READ_ONCE(msk->allow_infinite_fallback)) { ++ MPTCP_INC_STATS(sock_net(ssk), ++ MPTCP_MIB_DSSCORRUPTIONFALLBACK); ++ mptcp_do_fallback(ssk); ++ } else { ++ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONRESET); ++ mptcp_subflow_reset(ssk); ++ } ++} ++ + static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, + struct sock *ssk, + unsigned int *bytes) +@@ -519,10 +531,12 @@ static bool __mptcp_move_skbs_from_subfl + moved += len; + seq += len; + +- if (WARN_ON_ONCE(map_remaining < len)) +- break; ++ if (unlikely(map_remaining < len)) ++ mptcp_dss_corruption(msk, ssk); + } else { +- WARN_ON_ONCE(!fin); ++ if (unlikely(!fin)) ++ mptcp_dss_corruption(msk, ssk); ++ + sk_eat_skb(ssk, skb); + done = true; + } +--- a/net/mptcp/subflow.c ++++ b/net/mptcp/subflow.c +@@ -702,7 +702,7 @@ static bool skb_is_fully_mapped(struct s + unsigned int skb_consumed; + + skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq; +- if (WARN_ON_ONCE(skb_consumed >= skb->len)) ++ if (unlikely(skb_consumed >= skb->len)) + return true; + + return skb->len - skb_consumed <= subflow->map_data_len - diff --git a/queue-5.10/mptcp-track-and-update-contiguous-data-status.patch b/queue-5.10/mptcp-track-and-update-contiguous-data-status.patch new file mode 100644 index 00000000000..ba9ac16e304 --- /dev/null +++ b/queue-5.10/mptcp-track-and-update-contiguous-data-status.patch @@ -0,0 +1,95 @@ +From stable+bounces-86909-greg=kroah.com@vger.kernel.org Sat Oct 19 12:29:21 2024 +From: "Matthieu Baerts (NGI0)" +Date: Sat, 19 Oct 2024 12:29:07 +0200 +Subject: mptcp: track and update contiguous data status +To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org +Cc: Geliang Tang , sashal@kernel.org, Paolo Abeni , Mat Martineau , "David S . Miller" , Matthieu Baerts +Message-ID: <20241019102905.3383483-6-matttbe@kernel.org> + +From: Geliang Tang + +commit 0530020a7c8f2204e784f0dbdc882bbd961fdbde upstream. + +This patch adds a new member allow_infinite_fallback in mptcp_sock, +which is initialized to 'true' when the connection begins and is set +to 'false' on any retransmit or successful MP_JOIN. Only do infinite +mapping fallback if there is a single subflow AND there have been no +retransmissions AND there have never been any MP_JOINs. + +Suggested-by: Paolo Abeni +Signed-off-by: Geliang Tang +Signed-off-by: Mat Martineau +Signed-off-by: David S. Miller +Stable-dep-of: e32d262c89e2 ("mptcp: handle consistently DSS corruption") +[ Conflicts in protocol.c, because commit 3e5014909b56 ("mptcp: cleanup + MPJ subflow list handling") is not in this version. This commit is + linked to a new feature, changing the context around. The new line + can still be added at the same place. + Conflicts in protocol.h, because commit 4f6e14bd19d6 ("mptcp: support + TCP_CORK and TCP_NODELAY") is not in this version. This commit is + linked to a new feature, changing the context around. The new line can + still be added at the same place. + Conflicts in subflow.c, because commit 0348c690ed37 ("mptcp: add the + fallback check") is not in this version. This commit is linked to a + new feature, changing the context around. The new line can still be + added at the same place. + Extra conflicts in v5.10, because the context has been changed. ] +Signed-off-by: Matthieu Baerts (NGI0) +Signed-off-by: Greg Kroah-Hartman +--- + net/mptcp/protocol.c | 6 +++++- + net/mptcp/protocol.h | 1 + + net/mptcp/subflow.c | 1 + + 3 files changed, 7 insertions(+), 1 deletion(-) + +--- a/net/mptcp/protocol.c ++++ b/net/mptcp/protocol.c +@@ -1810,9 +1810,11 @@ static void mptcp_worker(struct work_str + if (!mptcp_ext_cache_refill(msk)) + break; + } +- if (copied) ++ if (copied) { + tcp_push(ssk, msg.msg_flags, mss_now, tcp_sk(ssk)->nonagle, + size_goal); ++ WRITE_ONCE(msk->allow_infinite_fallback, false); ++ } + + dfrag->data_seq = orig_write_seq; + dfrag->offset = orig_offset; +@@ -1845,6 +1847,7 @@ static int __mptcp_init_sock(struct sock + + msk->first = NULL; + inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; ++ WRITE_ONCE(msk->allow_infinite_fallback, true); + + mptcp_pm_data_init(msk); + +@@ -2543,6 +2546,7 @@ bool mptcp_finish_join(struct sock *sk) + if (parent_sock && !sk->sk_socket) + mptcp_sock_graft(sk, parent_sock); + subflow->map_seq = READ_ONCE(msk->ack_seq); ++ WRITE_ONCE(msk->allow_infinite_fallback, false); + return true; + } + +--- a/net/mptcp/protocol.h ++++ b/net/mptcp/protocol.h +@@ -213,6 +213,7 @@ struct mptcp_sock { + bool rcv_data_fin; + bool snd_data_fin_enable; + bool use_64bit_ack; /* Set when we received a 64-bit DSN */ ++ bool allow_infinite_fallback; + spinlock_t join_list_lock; + struct work_struct work; + struct sk_buff *ooo_last_skb; +--- a/net/mptcp/subflow.c ++++ b/net/mptcp/subflow.c +@@ -1179,6 +1179,7 @@ int __mptcp_subflow_connect(struct sock + list_add_tail(&subflow->node, &msk->join_list); + spin_unlock_bh(&msk->join_list_lock); + ++ WRITE_ONCE(msk->allow_infinite_fallback, false); + return err; + + failed: diff --git a/queue-5.10/nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch b/queue-5.10/nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch new file mode 100644 index 00000000000..d5e400565c3 --- /dev/null +++ b/queue-5.10/nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch @@ -0,0 +1,231 @@ +From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 +From: Ryusuke Konishi +Date: Fri, 4 Oct 2024 12:35:31 +0900 +Subject: nilfs2: propagate directory read errors from nilfs_find_entry() + +From: Ryusuke Konishi + +commit 08cfa12adf888db98879dbd735bc741360a34168 upstream. + +Syzbot reported that a task hang occurs in vcs_open() during a fuzzing +test for nilfs2. + +The root cause of this problem is that in nilfs_find_entry(), which +searches for directory entries, ignores errors when loading a directory +page/folio via nilfs_get_folio() fails. + +If the filesystem images is corrupted, and the i_size of the directory +inode is large, and the directory page/folio is successfully read but +fails the sanity check, for example when it is zero-filled, +nilfs_check_folio() may continue to spit out error messages in bursts. + +Fix this issue by propagating the error to the callers when loading a +page/folio fails in nilfs_find_entry(). + +The current interface of nilfs_find_entry() and its callers is outdated +and cannot propagate error codes such as -EIO and -ENOMEM returned via +nilfs_find_entry(), so fix it together. + +Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com +Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") +Signed-off-by: Ryusuke Konishi +Reported-by: Lizhi Xu +Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com +Reported-by: syzbot+8a192e8d090fa9a31135@syzkaller.appspotmail.com +Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 +Cc: +Signed-off-by: Andrew Morton +Signed-off-by: Greg Kroah-Hartman +--- + fs/nilfs2/dir.c | 50 +++++++++++++++++++++++++++----------------------- + fs/nilfs2/namei.c | 39 ++++++++++++++++++++++++++------------- + fs/nilfs2/nilfs.h | 2 +- + 3 files changed, 54 insertions(+), 37 deletions(-) + +--- a/fs/nilfs2/dir.c ++++ b/fs/nilfs2/dir.c +@@ -331,6 +331,8 @@ static int nilfs_readdir(struct file *fi + * returns the page in which the entry was found, and the entry itself + * (as a parameter - res_dir). Page is returned mapped and unlocked. + * Entry is guaranteed to be valid. ++ * ++ * On failure, returns an error pointer and the caller should ignore res_page. + */ + struct nilfs_dir_entry * + nilfs_find_entry(struct inode *dir, const struct qstr *qstr, +@@ -358,22 +360,24 @@ nilfs_find_entry(struct inode *dir, cons + do { + char *kaddr = nilfs_get_page(dir, n, &page); + +- if (!IS_ERR(kaddr)) { +- de = (struct nilfs_dir_entry *)kaddr; +- kaddr += nilfs_last_byte(dir, n) - reclen; +- while ((char *) de <= kaddr) { +- if (de->rec_len == 0) { +- nilfs_error(dir->i_sb, +- "zero-length directory entry"); +- nilfs_put_page(page); +- goto out; +- } +- if (nilfs_match(namelen, name, de)) +- goto found; +- de = nilfs_next_entry(de); ++ if (IS_ERR(kaddr)) ++ return ERR_CAST(kaddr); ++ ++ de = (struct nilfs_dir_entry *)kaddr; ++ kaddr += nilfs_last_byte(dir, n) - reclen; ++ while ((char *)de <= kaddr) { ++ if (de->rec_len == 0) { ++ nilfs_error(dir->i_sb, ++ "zero-length directory entry"); ++ nilfs_put_page(page); ++ goto out; + } +- nilfs_put_page(page); ++ if (nilfs_match(namelen, name, de)) ++ goto found; ++ de = nilfs_next_entry(de); + } ++ nilfs_put_page(page); ++ + if (++n >= npages) + n = 0; + /* next page is past the blocks we've got */ +@@ -386,7 +390,7 @@ nilfs_find_entry(struct inode *dir, cons + } + } while (n != start); + out: +- return NULL; ++ return ERR_PTR(-ENOENT); + + found: + *res_page = page; +@@ -431,19 +435,19 @@ fail: + return NULL; + } + +-ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) ++int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) + { +- ino_t res = 0; + struct nilfs_dir_entry *de; + struct page *page; + + de = nilfs_find_entry(dir, qstr, &page); +- if (de) { +- res = le64_to_cpu(de->inode); +- kunmap(page); +- put_page(page); +- } +- return res; ++ if (IS_ERR(de)) ++ return PTR_ERR(de); ++ ++ *ino = le64_to_cpu(de->inode); ++ kunmap(page); ++ put_page(page); ++ return 0; + } + + /* Releases the page */ +--- a/fs/nilfs2/namei.c ++++ b/fs/nilfs2/namei.c +@@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct d + { + struct inode *inode; + ino_t ino; ++ int res; + + if (dentry->d_name.len > NILFS_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); + +- ino = nilfs_inode_by_name(dir, &dentry->d_name); +- inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; ++ res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); ++ if (res) { ++ if (res != -ENOENT) ++ return ERR_PTR(res); ++ inode = NULL; ++ } else { ++ inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); ++ } ++ + return d_splice_alias(inode, dentry); + } + +@@ -261,10 +269,11 @@ static int nilfs_do_unlink(struct inode + struct page *page; + int err; + +- err = -ENOENT; + de = nilfs_find_entry(dir, &dentry->d_name, &page); +- if (!de) ++ if (IS_ERR(de)) { ++ err = PTR_ERR(de); + goto out; ++ } + + inode = d_inode(dentry); + err = -EIO; +@@ -358,10 +367,11 @@ static int nilfs_rename(struct inode *ol + if (unlikely(err)) + return err; + +- err = -ENOENT; + old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_page); +- if (!old_de) ++ if (IS_ERR(old_de)) { ++ err = PTR_ERR(old_de); + goto out; ++ } + + if (S_ISDIR(old_inode->i_mode)) { + err = -EIO; +@@ -378,10 +388,12 @@ static int nilfs_rename(struct inode *ol + if (dir_de && !nilfs_empty_dir(new_inode)) + goto out_dir; + +- err = -ENOENT; +- new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_page); +- if (!new_de) ++ new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, ++ &new_page); ++ if (IS_ERR(new_de)) { ++ err = PTR_ERR(new_de); + goto out_dir; ++ } + nilfs_set_link(new_dir, new_de, new_page, old_inode); + nilfs_mark_inode_dirty(new_dir); + new_inode->i_ctime = current_time(new_inode); +@@ -435,14 +447,15 @@ out: + */ + static struct dentry *nilfs_get_parent(struct dentry *child) + { +- unsigned long ino; ++ ino_t ino; ++ int res; + struct inode *inode; + struct qstr dotdot = QSTR_INIT("..", 2); + struct nilfs_root *root; + +- ino = nilfs_inode_by_name(d_inode(child), &dotdot); +- if (!ino) +- return ERR_PTR(-ENOENT); ++ res = nilfs_inode_by_name(d_inode(child), &dotdot, &ino); ++ if (res) ++ return ERR_PTR(res); + + root = NILFS_I(d_inode(child))->i_root; + +--- a/fs/nilfs2/nilfs.h ++++ b/fs/nilfs2/nilfs.h +@@ -233,7 +233,7 @@ static inline __u32 nilfs_mask_flags(umo + + /* dir.c */ + extern int nilfs_add_link(struct dentry *, struct inode *); +-extern ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); ++int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); + extern int nilfs_make_empty(struct inode *, struct inode *); + extern struct nilfs_dir_entry * + nilfs_find_entry(struct inode *, const struct qstr *, struct page **); diff --git a/queue-5.10/powerpc-mm-always-update-max-min_low_pfn-in-mem_topology_setup.patch b/queue-5.10/powerpc-mm-always-update-max-min_low_pfn-in-mem_topology_setup.patch new file mode 100644 index 00000000000..1d8852dff9d --- /dev/null +++ b/queue-5.10/powerpc-mm-always-update-max-min_low_pfn-in-mem_topology_setup.patch @@ -0,0 +1,46 @@ +From 7b31f7dadd7074fa70bb14a53bd286ffdfc98b04 Mon Sep 17 00:00:00 2001 +From: "Aneesh Kumar K.V" +Date: Mon, 4 Jul 2022 12:08:51 +0530 +Subject: powerpc/mm: Always update max/min_low_pfn in mem_topology_setup() + +From: Aneesh Kumar K.V + +commit 7b31f7dadd7074fa70bb14a53bd286ffdfc98b04 upstream. + +For both CONFIG_NUMA enabled/disabled use mem_topology_setup() to +update max/min_low_pfn. + +This also adds min_low_pfn update to CONFIG_NUMA which was initialized +to zero before. (mpe: Though MEMORY_START is == 0 for PPC64=y which is +all possible NUMA=y systems) + +Signed-off-by: Aneesh Kumar K.V +Signed-off-by: Michael Ellerman +Link: https://lore.kernel.org/r/20220704063851.295482-1-aneesh.kumar@linux.ibm.com +Signed-off-by: Greg Kroah-Hartman +--- + arch/powerpc/mm/numa.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/arch/powerpc/mm/numa.c ++++ b/arch/powerpc/mm/numa.c +@@ -1177,6 +1177,9 @@ void __init mem_topology_setup(void) + { + int cpu; + ++ max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; ++ min_low_pfn = MEMORY_START >> PAGE_SHIFT; ++ + /* + * Linux/mm assumes node 0 to be online at boot. However this is not + * true on PowerPC, where node 0 is similar to any other node, it +@@ -1221,9 +1224,6 @@ void __init initmem_init(void) + { + int nid; + +- max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; +- max_pfn = max_low_pfn; +- + memblock_dump_all(); + + for_each_online_node(nid) { diff --git a/queue-5.10/series b/queue-5.10/series index 08f1ff5d880..87dc8e3b40e 100644 --- a/queue-5.10/series +++ b/queue-5.10/series @@ -44,3 +44,8 @@ x86-apic-always-explicitly-disarm-tsc-deadline-timer.patch x86-entry_32-do-not-clobber-user-eflags.zf.patch x86-entry_32-clear-cpu-buffers-after-register-restore-in-nmi-return.patch irqchip-gic-v4-don-t-allow-a-vmovp-on-a-dying-vpe.patch +mptcp-track-and-update-contiguous-data-status.patch +mptcp-handle-consistently-dss-corruption.patch +tcp-fix-mptcp-dss-corruption-due-to-large-pmtu-xmit.patch +nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch +powerpc-mm-always-update-max-min_low_pfn-in-mem_topology_setup.patch diff --git a/queue-5.10/tcp-fix-mptcp-dss-corruption-due-to-large-pmtu-xmit.patch b/queue-5.10/tcp-fix-mptcp-dss-corruption-due-to-large-pmtu-xmit.patch new file mode 100644 index 00000000000..0683633a75a --- /dev/null +++ b/queue-5.10/tcp-fix-mptcp-dss-corruption-due-to-large-pmtu-xmit.patch @@ -0,0 +1,144 @@ +From stable+bounces-86911-greg=kroah.com@vger.kernel.org Sat Oct 19 12:29:21 2024 +From: "Matthieu Baerts (NGI0)" +Date: Sat, 19 Oct 2024 12:29:09 +0200 +Subject: tcp: fix mptcp DSS corruption due to large pmtu xmit +To: mptcp@lists.linux.dev, stable@vger.kernel.org, gregkh@linuxfoundation.org +Cc: Paolo Abeni , sashal@kernel.org, syzbot+d1bff73460e33101f0e7@syzkaller.appspotmail.com, Matthieu Baerts , Jakub Kicinski +Message-ID: <20241019102905.3383483-8-matttbe@kernel.org> + +From: Paolo Abeni + +commit 4dabcdf581217e60690467a37c956a5b8dbc6bd9 upstream. + +Syzkaller was able to trigger a DSS corruption: + + TCP: request_sock_subflow_v4: Possible SYN flooding on port [::]:20002. Sending cookies. + ------------[ cut here ]------------ + WARNING: CPU: 0 PID: 5227 at net/mptcp/protocol.c:695 __mptcp_move_skbs_from_subflow+0x20a9/0x21f0 net/mptcp/protocol.c:695 + Modules linked in: + CPU: 0 UID: 0 PID: 5227 Comm: syz-executor350 Not tainted 6.11.0-syzkaller-08829-gaf9c191ac2a0 #0 + Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024 + RIP: 0010:__mptcp_move_skbs_from_subflow+0x20a9/0x21f0 net/mptcp/protocol.c:695 + Code: 0f b6 dc 31 ff 89 de e8 b5 dd ea f5 89 d8 48 81 c4 50 01 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 98 da ea f5 90 <0f> 0b 90 e9 47 ff ff ff e8 8a da ea f5 90 0f 0b 90 e9 99 e0 ff ff + RSP: 0018:ffffc90000006db8 EFLAGS: 00010246 + RAX: ffffffff8ba9df18 RBX: 00000000000055f0 RCX: ffff888030023c00 + RDX: 0000000000000100 RSI: 00000000000081e5 RDI: 00000000000055f0 + RBP: 1ffff110062bf1ae R08: ffffffff8ba9cf12 R09: 1ffff110062bf1b8 + R10: dffffc0000000000 R11: ffffed10062bf1b9 R12: 0000000000000000 + R13: dffffc0000000000 R14: 00000000700cec61 R15: 00000000000081e5 + FS: 000055556679c380(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000 + CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + CR2: 0000000020287000 CR3: 0000000077892000 CR4: 00000000003506f0 + DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 + DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 + Call Trace: + + move_skbs_to_msk net/mptcp/protocol.c:811 [inline] + mptcp_data_ready+0x29c/0xa90 net/mptcp/protocol.c:854 + subflow_data_ready+0x34a/0x920 net/mptcp/subflow.c:1490 + tcp_data_queue+0x20fd/0x76c0 net/ipv4/tcp_input.c:5283 + tcp_rcv_established+0xfba/0x2020 net/ipv4/tcp_input.c:6237 + tcp_v4_do_rcv+0x96d/0xc70 net/ipv4/tcp_ipv4.c:1915 + tcp_v4_rcv+0x2dc0/0x37f0 net/ipv4/tcp_ipv4.c:2350 + 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:5662 [inline] + __netif_receive_skb+0x2bf/0x650 net/core/dev.c:5775 + process_backlog+0x662/0x15b0 net/core/dev.c:6107 + __napi_poll+0xcb/0x490 net/core/dev.c:6771 + napi_poll net/core/dev.c:6840 [inline] + net_rx_action+0x89b/0x1240 net/core/dev.c:6962 + handle_softirqs+0x2c5/0x980 kernel/softirq.c:554 + do_softirq+0x11b/0x1e0 kernel/softirq.c:455 + + + __local_bh_enable_ip+0x1bb/0x200 kernel/softirq.c:382 + local_bh_enable include/linux/bottom_half.h:33 [inline] + rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline] + __dev_queue_xmit+0x1764/0x3e80 net/core/dev.c:4451 + dev_queue_xmit include/linux/netdevice.h:3094 [inline] + neigh_hh_output include/net/neighbour.h:526 [inline] + neigh_output include/net/neighbour.h:540 [inline] + ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:236 + ip_local_out net/ipv4/ip_output.c:130 [inline] + __ip_queue_xmit+0x118c/0x1b80 net/ipv4/ip_output.c:536 + __tcp_transmit_skb+0x2544/0x3b30 net/ipv4/tcp_output.c:1466 + tcp_transmit_skb net/ipv4/tcp_output.c:1484 [inline] + tcp_mtu_probe net/ipv4/tcp_output.c:2547 [inline] + tcp_write_xmit+0x641d/0x6bf0 net/ipv4/tcp_output.c:2752 + __tcp_push_pending_frames+0x9b/0x360 net/ipv4/tcp_output.c:3015 + tcp_push_pending_frames include/net/tcp.h:2107 [inline] + tcp_data_snd_check net/ipv4/tcp_input.c:5714 [inline] + tcp_rcv_established+0x1026/0x2020 net/ipv4/tcp_input.c:6239 + tcp_v4_do_rcv+0x96d/0xc70 net/ipv4/tcp_ipv4.c:1915 + sk_backlog_rcv include/net/sock.h:1113 [inline] + __release_sock+0x214/0x350 net/core/sock.c:3072 + release_sock+0x61/0x1f0 net/core/sock.c:3626 + mptcp_push_release net/mptcp/protocol.c:1486 [inline] + __mptcp_push_pending+0x6b5/0x9f0 net/mptcp/protocol.c:1625 + mptcp_sendmsg+0x10bb/0x1b10 net/mptcp/protocol.c:1903 + sock_sendmsg_nosec net/socket.c:730 [inline] + __sock_sendmsg+0x1a6/0x270 net/socket.c:745 + ____sys_sendmsg+0x52a/0x7e0 net/socket.c:2603 + ___sys_sendmsg net/socket.c:2657 [inline] + __sys_sendmsg+0x2aa/0x390 net/socket.c:2686 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x77/0x7f + RIP: 0033:0x7fb06e9317f9 + Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 + RSP: 002b:00007ffe2cfd4f98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e + RAX: ffffffffffffffda RBX: 00007fb06e97f468 RCX: 00007fb06e9317f9 + RDX: 0000000000000000 RSI: 0000000020000080 RDI: 0000000000000005 + RBP: 00007fb06e97f446 R08: 0000555500000000 R09: 0000555500000000 + R10: 0000555500000000 R11: 0000000000000246 R12: 00007fb06e97f406 + R13: 0000000000000001 R14: 00007ffe2cfd4fe0 R15: 0000000000000003 + + +Additionally syzkaller provided a nice reproducer. The repro enables +pmtu on the loopback device, leading to tcp_mtu_probe() generating +very large probe packets. + +tcp_can_coalesce_send_queue_head() currently does not check for +mptcp-level invariants, and allowed the creation of cross-DSS probes, +leading to the mentioned corruption. + +Address the issue teaching tcp_can_coalesce_send_queue_head() about +mptcp using the tcp_skb_can_collapse(), also reducing the code +duplication. + +Fixes: 85712484110d ("tcp: coalesce/collapse must respect MPTCP extensions") +Cc: stable@vger.kernel.org +Reported-by: syzbot+d1bff73460e33101f0e7@syzkaller.appspotmail.com +Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/513 +Signed-off-by: Paolo Abeni +Acked-by: Matthieu Baerts (NGI0) +Signed-off-by: Matthieu Baerts (NGI0) +Link: https://patch.msgid.link/20241008-net-mptcp-fallback-fixes-v1-2-c6fb8e93e551@kernel.org +Signed-off-by: Jakub Kicinski +[ Conflict in tcp_output.c, because commit 65249feb6b3d ("net: add + support for skbs with unreadable frags"), and commit 9b65b17db723 + ("net: avoid double accounting for pure zerocopy skbs") are not in + this version. These commits are linked to new features and introduce + new conditions which cause the conflicts. Resolving this is easy: we + can ignore the missing new condition, and use tcp_skb_can_collapse() + like in the original patch. ] +Signed-off-by: Matthieu Baerts (NGI0) +Signed-off-by: Greg Kroah-Hartman +--- + net/ipv4/tcp_output.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/ipv4/tcp_output.c ++++ b/net/ipv4/tcp_output.c +@@ -2305,7 +2305,7 @@ static bool tcp_can_coalesce_send_queue_ + if (len <= skb->len) + break; + +- if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) ++ if (tcp_has_tx_tstamp(skb) || !tcp_skb_can_collapse(skb, next)) + return false; + + len -= skb->len;