From 9adbbd6afb7bc40ee9c2086aca69c96e9bf82fc8 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 5 Apr 2024 15:50:47 -0400 Subject: [PATCH 1/7] Bluetooth: L2CAP: Fix not validating setsockopt user input stable inclusion from stable-v6.8.7 commit 8ee0c132a61df9723813c40e742dc5321824daa9 category: bugfix issue: #IBRFC7 CVE: CVE-2024-35965 Signed-off-by: zyf1116 --------------------------------------- [ Upstream commit 4f3951242ace5efc7131932e2e01e6ac6baed846 ] Check user input length before copying data. Fixes: 33575df7be67 ("Bluetooth: move l2cap_sock_setsockopt() to l2cap_sock.c") Fixes: 3ee7b7cd8390 ("Bluetooth: Add BT_MODE socket option") Signed-off-by: Eric Dumazet Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Sasha Levin Signed-off-by: zyf1116 --- net/bluetooth/l2cap_sock.c | 52 +++++++++++++++----------------------- 1 file changed, 20 insertions(+), 32 deletions(-) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 4493fc68efca..d878f422fc02 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -744,7 +744,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; - int len, err = 0; + int err = 0; u32 opt; BT_DBG("sk %p", sk); @@ -771,11 +771,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - len = min_t(unsigned int, sizeof(opts), optlen); - if (copy_from_sockptr(&opts, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + if (err) break; - } if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) { err = -EINVAL; @@ -818,10 +816,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & L2CAP_LM_FIPS) { err = -EINVAL; @@ -902,7 +899,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, struct bt_security sec; struct bt_power pwr; struct l2cap_conn *conn; - int len, err = 0; + int err = 0; u32 opt; u16 mtu; u8 mode; @@ -928,11 +925,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level < BT_SECURITY_LOW || sec.level > BT_SECURITY_FIPS) { @@ -977,10 +972,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) { set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -992,10 +986,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_FLUSHABLE_ON) { err = -EINVAL; @@ -1027,11 +1020,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - len = min_t(unsigned int, sizeof(pwr), optlen); - if (copy_from_sockptr(&pwr, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + if (err) break; - } if (pwr.force_active) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); @@ -1040,10 +1031,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) { err = -EINVAL; @@ -1088,10 +1078,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mtu, optval, sizeof(u16))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + if (err) break; - } if (chan->mode == L2CAP_MODE_EXT_FLOWCTL && sk->sk_state == BT_CONNECTED) @@ -1119,10 +1108,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mode, optval, sizeof(u8))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + if (err) break; - } BT_DBG("mode %u", mode); -- Gitee From 060a93b57d3f2ae0cda59f1b93242b2b166634dc Mon Sep 17 00:00:00 2001 From: Ojaswin Mujoo Date: Thu, 21 Nov 2024 18:08:54 +0530 Subject: [PATCH 2/7] quota: flush quota_release_work upon quota writeback stable inclusion from stable-v5.10.231 commit 6f3821acd7c3143145999248087de5fb4b48cf26 category: bugfix issue: NA CVE: CVE-2024-56780 Signed-off-by: zyf1116 --------------------------------------- [ Upstream commit ac6f420291b3fee1113f21d612fa88b628afab5b ] One of the paths quota writeback is called from is: freeze_super() sync_filesystem() ext4_sync_fs() dquot_writeback_dquots() Since we currently don't always flush the quota_release_work queue in this path, we can end up with the following race: 1. dquot are added to releasing_dquots list during regular operations. 2. FS Freeze starts, however, this does not flush the quota_release_work queue. 3. Freeze completes. 4. Kernel eventually tries to flush the workqueue while FS is frozen which hits a WARN_ON since transaction gets started during frozen state: ext4_journal_check_start+0x28/0x110 [ext4] (unreliable) __ext4_journal_start_sb+0x64/0x1c0 [ext4] ext4_release_dquot+0x90/0x1d0 [ext4] quota_release_workfn+0x43c/0x4d0 Which is the following line: WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); Which ultimately results in generic/390 failing due to dmesg noise. This was detected on powerpc machine 15 cores. To avoid this, make sure to flush the workqueue during dquot_writeback_dquots() so we dont have any pending workitems after freeze. Reported-by: Disha Goel CC: stable@vger.kernel.org Fixes: dabc8b207566 ("quota: fix dqput() to follow the guarantees dquot_srcu should provide") Reviewed-by: Baokun Li Signed-off-by: Ojaswin Mujoo Signed-off-by: Jan Kara Link: https://patch.msgid.link/20241121123855.645335-2-ojaswin@linux.ibm.com Signed-off-by: Sasha Levin Signed-off-by: zyf1116 --- fs/quota/dquot.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index cb5c1feaba98..7ab4b1e53d56 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -692,6 +692,8 @@ int dquot_writeback_dquots(struct super_block *sb, int type) WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)); + flush_delayed_work("a_release_work); + for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; -- Gitee From 7061c3c3b50e1e140fcfd191fd56e3aa4ddeab78 Mon Sep 17 00:00:00 2001 From: Seiji Nishikawa Date: Sun, 1 Dec 2024 01:12:34 +0900 Subject: [PATCH 3/7] mm: vmscan: account for free pages to prevent infinite Loop in throttle_direct_reclaim() stable inclusion from stable-v5.10.233 commit d675fefbaec3815b3ae0af1bebd97f27df3a05c8 category: bugfix issue: NA CVE: CVE-2024-57884 Signed-off-by: zyf1116 --------------------------------------- commit 6aaced5abd32e2a57cd94fd64f824514d0361da8 upstream. The task sometimes continues looping in throttle_direct_reclaim() because allow_direct_reclaim(pgdat) keeps returning false. #0 [ffff80002cb6f8d0] __switch_to at ffff8000080095ac #1 [ffff80002cb6f900] __schedule at ffff800008abbd1c #2 [ffff80002cb6f990] schedule at ffff800008abc50c #3 [ffff80002cb6f9b0] throttle_direct_reclaim at ffff800008273550 #4 [ffff80002cb6fa20] try_to_free_pages at ffff800008277b68 #5 [ffff80002cb6fae0] __alloc_pages_nodemask at ffff8000082c4660 #6 [ffff80002cb6fc50] alloc_pages_vma at ffff8000082e4a98 #7 [ffff80002cb6fca0] do_anonymous_page at ffff80000829f5a8 #8 [ffff80002cb6fce0] __handle_mm_fault at ffff8000082a5974 #9 [ffff80002cb6fd90] handle_mm_fault at ffff8000082a5bd4 At this point, the pgdat contains the following two zones: NODE: 4 ZONE: 0 ADDR: ffff00817fffe540 NAME: "DMA32" SIZE: 20480 MIN/LOW/HIGH: 11/28/45 VM_STAT: NR_FREE_PAGES: 359 NR_ZONE_INACTIVE_ANON: 18813 NR_ZONE_ACTIVE_ANON: 0 NR_ZONE_INACTIVE_FILE: 50 NR_ZONE_ACTIVE_FILE: 0 NR_ZONE_UNEVICTABLE: 0 NR_ZONE_WRITE_PENDING: 0 NR_MLOCK: 0 NR_BOUNCE: 0 NR_ZSPAGES: 0 NR_FREE_CMA_PAGES: 0 NODE: 4 ZONE: 1 ADDR: ffff00817fffec00 NAME: "Normal" SIZE: 8454144 PRESENT: 98304 MIN/LOW/HIGH: 68/166/264 VM_STAT: NR_FREE_PAGES: 146 NR_ZONE_INACTIVE_ANON: 94668 NR_ZONE_ACTIVE_ANON: 3 NR_ZONE_INACTIVE_FILE: 735 NR_ZONE_ACTIVE_FILE: 78 NR_ZONE_UNEVICTABLE: 0 NR_ZONE_WRITE_PENDING: 0 NR_MLOCK: 0 NR_BOUNCE: 0 NR_ZSPAGES: 0 NR_FREE_CMA_PAGES: 0 In allow_direct_reclaim(), while processing ZONE_DMA32, the sum of inactive/active file-backed pages calculated in zone_reclaimable_pages() based on the result of zone_page_state_snapshot() is zero. Additionally, since this system lacks swap, the calculation of inactive/ active anonymous pages is skipped. crash> p nr_swap_pages nr_swap_pages = $1937 = { counter = 0 } As a result, ZONE_DMA32 is deemed unreclaimable and skipped, moving on to the processing of the next zone, ZONE_NORMAL, despite ZONE_DMA32 having free pages significantly exceeding the high watermark. The problem is that the pgdat->kswapd_failures hasn't been incremented. crash> px ((struct pglist_data *) 0xffff00817fffe540)->kswapd_failures $1935 = 0x0 This is because the node deemed balanced. The node balancing logic in balance_pgdat() evaluates all zones collectively. If one or more zones (e.g., ZONE_DMA32) have enough free pages to meet their watermarks, the entire node is deemed balanced. This causes balance_pgdat() to exit early before incrementing the kswapd_failures, as it considers the overall memory state acceptable, even though some zones (like ZONE_NORMAL) remain under significant pressure. The patch ensures that zone_reclaimable_pages() includes free pages (NR_FREE_PAGES) in its calculation when no other reclaimable pages are available (e.g., file-backed or anonymous pages). This change prevents zones like ZONE_DMA32, which have sufficient free pages, from being mistakenly deemed unreclaimable. By doing so, the patch ensures proper node balancing, avoids masking pressure on other zones like ZONE_NORMAL, and prevents infinite loops in throttle_direct_reclaim() caused by allow_direct_reclaim(pgdat) repeatedly returning false. The kernel hangs due to a task stuck in throttle_direct_reclaim(), caused by a node being incorrectly deemed balanced despite pressure in certain zones, such as ZONE_NORMAL. This issue arises from zone_reclaimable_pages() returning 0 for zones without reclaimable file- backed or anonymous pages, causing zones like ZONE_DMA32 with sufficient free pages to be skipped. The lack of swap or reclaimable pages results in ZONE_DMA32 being ignored during reclaim, masking pressure in other zones. Consequently, pgdat->kswapd_failures remains 0 in balance_pgdat(), preventing fallback mechanisms in allow_direct_reclaim() from being triggered, leading to an infinite loop in throttle_direct_reclaim(). This patch modifies zone_reclaimable_pages() to account for free pages (NR_FREE_PAGES) when no other reclaimable pages exist. This ensures zones with sufficient free pages are not skipped, enabling proper balancing and reclaim behavior. [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20241130164346.436469-1-snishika@redhat.com Link: https://lkml.kernel.org/r/20241130161236.433747-2-snishika@redhat.com Fixes: 5a1c84b404a7 ("mm: remove reclaim and compaction retry approximations") Signed-off-by: Seiji Nishikawa Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman Signed-off-by: zyf1116 --- mm/vmscan.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index e319f2d460f3..9a3129b27296 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -213,7 +213,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (get_nr_swap_pages() > 0) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } -- Gitee From 4c70f8744fcecb685ce473b667bf96754c8558ae Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Fri, 10 Jan 2025 14:21:55 +0100 Subject: [PATCH 4/7] bpf: Fix bpf_sk_select_reuseport() memory leak mainline inclusion from mainline-v6.13 commit b3af60928ab9129befa65e6df0310d27300942bf category: bugfix issue: NA CVE: CVE-2025-21683 Signed-off-by: zyf1116 --------------------------------------- As pointed out in the original comment, lookup in sockmap can return a TCP ESTABLISHED socket. Such TCP socket may have had SO_ATTACH_REUSEPORT_EBPF set before it was ESTABLISHED. In other words, a non-NULL sk_reuseport_cb does not imply a non-refcounted socket. Drop sk's reference in both error paths. unreferenced object 0xffff888101911800 (size 2048): comm "test_progs", pid 44109, jiffies 4297131437 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 80 00 01 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc 9336483b): __kmalloc_noprof+0x3bf/0x560 __reuseport_alloc+0x1d/0x40 reuseport_alloc+0xca/0x150 reuseport_attach_prog+0x87/0x140 sk_reuseport_attach_bpf+0xc8/0x100 sk_setsockopt+0x1181/0x1990 do_sock_setsockopt+0x12b/0x160 __sys_setsockopt+0x7b/0xc0 __x64_sys_setsockopt+0x1b/0x30 do_syscall_64+0x93/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Fixes: 64d85290d79c ("bpf: Allow bpf_map_lookup_elem for SOCKMAP and SOCKHASH") Signed-off-by: Michal Luczaj Reviewed-by: Martin KaFai Lau Link: https://patch.msgid.link/20250110-reuseport-memleak-v1-1-fa1ddab0adfe@rbox.co Signed-off-by: Jakub Kicinski Signed-off-by: zyf1116 --- net/core/filter.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 97abd0c98d79..40b38608814c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10055,6 +10055,7 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; + int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) @@ -10062,10 +10063,6 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { - /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ - if (sk_is_refcounted(selected_sk)) - sock_put(selected_sk); - /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. @@ -10073,24 +10070,33 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ - return is_sockarray ? -ENOENT : -EINVAL; + err = is_sockarray ? -ENOENT : -EINVAL; + goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; - if (sk->sk_protocol != selected_sk->sk_protocol) - return -EPROTOTYPE; - else if (sk->sk_family != selected_sk->sk_family) - return -EAFNOSUPPORT; - - /* Catch all. Likely bound to a different sockaddr. */ - return -EBADFD; + if (sk->sk_protocol != selected_sk->sk_protocol) { + err = -EPROTOTYPE; + } else if (sk->sk_family != selected_sk->sk_family) { + err = -EAFNOSUPPORT; + } else { + /* Catch all. Likely bound to a different sockaddr. */ + err = -EBADFD; + } + goto error; } reuse_kern->selected_sk = selected_sk; return 0; +error: + /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ + if (sk_is_refcounted(selected_sk)) + sock_put(selected_sk); + + return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { -- Gitee From 59e339e248f9244ed4ec1738e465150c5d35a0c8 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 8 Jan 2025 22:56:33 +0100 Subject: [PATCH 5/7] netfilter: conntrack: clamp maximum hashtable size to INT_MAX mainline inclusion from mainline-v6.13-rc7 commit b541ba7d1f5a5b7b3e2e22dc9e40e18a7d6dbc13 category: bugfix issue: NA CVE: CVE-2025-21648 Signed-off-by: zyf1116 --------------------------------------- Use INT_MAX as maximum size for the conntrack hashtable. Otherwise, it is possible to hit WARN_ON_ONCE in __kvmalloc_node_noprof() when resizing hashtable because __GFP_NOWARN is unset. See: 0708a0afe291 ("mm: Consider __GFP_NOWARN flag for oversized kvmalloc() calls") Note: hashtable resize is only possible from init_netns. Fixes: 9cc1c73ad666 ("netfilter: conntrack: avoid integer overflow when resizing") Signed-off-by: Pablo Neira Ayuso Signed-off-by: zyf1116 --- net/netfilter/nf_conntrack_core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f82a234ac53a..99d5d8cd3895 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2435,12 +2435,15 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) struct hlist_nulls_head *hash; unsigned int nr_slots, i; - if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head))) + if (*sizep > (INT_MAX / sizeof(struct hlist_nulls_head))) return NULL; BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); + if (nr_slots > (INT_MAX / sizeof(struct hlist_nulls_head))) + return NULL; + hash = kvcalloc(nr_slots, sizeof(struct hlist_nulls_head), GFP_KERNEL); if (hash && nulls) -- Gitee From 36ca57698a28bac510a54f961bca9df6c78092df Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 11 Jul 2022 17:15:26 -0700 Subject: [PATCH 6/7] icmp: Fix a data-race around sysctl_icmp_errors_use_inbound_ifaddr. mainline inclusion from mainline-v5.19-rc7 commit d2efabce81db7eed1c98fa1a3f203f0edd738ac3 category: bugfix issue: NA CVE: CVE-2022-49632 Signed-off-by: zyf1116 --------------------------------------- While reading sysctl_icmp_errors_use_inbound_ifaddr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 1c2fb7f93cb2 ("[IPV4]: Sysctl configurable icmp error source address.") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller Signed-off-by: zyf1116 --- net/ipv4/icmp.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 30230e5c666f..04945a44a48d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -715,7 +715,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 59ba518a85b9..c6726ace37af 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -564,6 +564,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", -- Gitee From bda077dff6f764417dc992c2a08832dc2926bb2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Jan 2025 18:12:41 +0000 Subject: [PATCH 7/7] ipmr: do not call mr_mfc_uses_dev() for unres entries mainline inclusion from mainline-v6.14-rc1 commit 15a901361ec3fb1c393f91880e1cbf24ec0a88bd category: bugfix issue: NA CVE: CVE-2025-21719 Signed-off-by: zyf1116 --------------------------------------- syzbot found that calling mr_mfc_uses_dev() for unres entries would crash [1], because c->mfc_un.res.minvif / c->mfc_un.res.maxvif alias to "struct sk_buff_head unresolved", which contain two pointers. This code never worked, lets remove it. [1] Unable to handle kernel paging request at virtual address ffff5fff2d536613 KASAN: maybe wild-memory-access in range [0xfffefff96a9b3098-0xfffefff96a9b309f] Modules linked in: CPU: 1 UID: 0 PID: 7321 Comm: syz.0.16 Not tainted 6.13.0-rc7-syzkaller-g1950a0af2d55 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mr_mfc_uses_dev net/ipv4/ipmr_base.c:290 [inline] pc : mr_table_dump+0x5a4/0x8b0 net/ipv4/ipmr_base.c:334 lr : mr_mfc_uses_dev net/ipv4/ipmr_base.c:289 [inline] lr : mr_table_dump+0x694/0x8b0 net/ipv4/ipmr_base.c:334 Call trace: mr_mfc_uses_dev net/ipv4/ipmr_base.c:290 [inline] (P) mr_table_dump+0x5a4/0x8b0 net/ipv4/ipmr_base.c:334 (P) mr_rtm_dumproute+0x254/0x454 net/ipv4/ipmr_base.c:382 ipmr_rtm_dumproute+0x248/0x4b4 net/ipv4/ipmr.c:2648 rtnl_dump_all+0x2e4/0x4e8 net/core/rtnetlink.c:4327 rtnl_dumpit+0x98/0x1d0 net/core/rtnetlink.c:6791 netlink_dump+0x4f0/0xbc0 net/netlink/af_netlink.c:2317 netlink_recvmsg+0x56c/0xe64 net/netlink/af_netlink.c:1973 sock_recvmsg_nosec net/socket.c:1033 [inline] sock_recvmsg net/socket.c:1055 [inline] sock_read_iter+0x2d8/0x40c net/socket.c:1125 new_sync_read fs/read_write.c:484 [inline] vfs_read+0x740/0x970 fs/read_write.c:565 ksys_read+0x15c/0x26c fs/read_write.c:708 Fixes: cb167893f41e ("net: Plumb support for filtering ipv4 and ipv6 multicast route dumps") Reported-by: syzbot+5cfae50c0e5f2c500013@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/678fe2d1.050a0220.15cac.00b3.GAE@google.com/T/#u Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250121181241.841212-1-edumazet@google.com Signed-off-by: Jakub Kicinski Signed-off-by: zyf1116 --- net/ipv4/ipmr_base.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index aa8738a91210..0c4bb906af21 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -320,9 +320,6 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; - if (filter->dev && - !mr_mfc_uses_dev(mrt, mfc, filter->dev)) - goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); -- Gitee