From f567655bdb8a8487eb0d6f647fb6e315a29e720a Mon Sep 17 00:00:00 2001 From: Luca Stefani Date: Thu, 6 May 2021 21:37:25 +0200 Subject: [PATCH 1/8] UPSTREAM: binder: Return EFAULT if we fail BINDER_ENABLE_ONEWAY_SPAM_DETECTION All the other ioctl paths return EFAULT in case the copy_from_user/copy_to_user call fails, make oneway spam detection follow the same paradigm. Bug: 254441685 Fixes: a7dc1e6f99df ("binder: tell userspace to dump current backtrace when detected oneway spamming") Acked-by: Todd Kjos Acked-by: Christian Brauner Signed-off-by: Luca Stefani Link: https://lore.kernel.org/r/20210506193726.45118-1-luca.stefani.ge1@gmail.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit ced081a436d21a7d34d4d42acb85058f9cf423f2) Signed-off-by: Lee Jones Change-Id: I5f54cc7505300f106c04ac81da33d8046704f377 --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 1765a4f896e2..4f7fdc2ab881 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5854,7 +5854,7 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) uint32_t enable; if (copy_from_user(&enable, ubuf, sizeof(enable))) { - ret = -EINVAL; + ret = -EFAULT; goto err; } binder_inner_proc_lock(proc); From 0b8367ba8c3bb0d61ed67a0ac41422ae91705192 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 26 Mar 2024 12:33:58 +0100 Subject: [PATCH 2/8] UPSTREAM: udp: do not accept non-tunnel GSO skbs landing in a tunnel When rx-udp-gro-forwarding is enabled UDP packets might be GROed when being forwarded. If such packets might land in a tunnel this can cause various issues and udp_gro_receive makes sure this isn't the case by looking for a matching socket. This is performed in udp4/6_gro_lookup_skb but only in the current netns. This is an issue with tunneled packets when the endpoint is in another netns. In such cases the packets will be GROed at the UDP level, which leads to various issues later on. The same thing can happen with rx-gro-list. We saw this with geneve packets being GROed at the UDP level. In such case gso_size is set; later the packet goes through the geneve rx path, the geneve header is pulled, the offset are adjusted and frag_list skbs are not adjusted with regard to geneve. When those skbs hit skb_fragment, it will misbehave. Different outcomes are possible depending on what the GROed skbs look like; from corrupted packets to kernel crashes. One example is a BUG_ON[1] triggered in skb_segment while processing the frag_list. Because gso_size is wrong (geneve header was pulled) skb_segment thinks there is "geneve header size" of data in frag_list, although it's in fact the next packet. The BUG_ON itself has nothing to do with the issue. This is only one of the potential issues. Looking up for a matching socket in udp_gro_receive is fragile: the lookup could be extended to all netns (not speaking about performances) but nothing prevents those packets from being modified in between and we could still not find a matching socket. It's OK to keep the current logic there as it should cover most cases but we also need to make sure we handle tunnel packets being GROed too early. This is done by extending the checks in udp_unexpected_gso: GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits and landing in a tunnel must be segmented. [1] kernel BUG at net/core/skbuff.c:4408! RIP: 0010:skb_segment+0xd2a/0xf70 __udp_gso_segment+0xaa/0x560 Bug: 254441685 Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Fixes: 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets") Signed-off-by: Antoine Tenart Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller (cherry picked from commit 3d010c8031e39f5fa1e8b13ada77e0321091011f) Signed-off-by: Lee Jones Change-Id: I28f2d205ff3fd88ef83f16a6fb92057a6f7a6423 --- include/linux/udp.h | 28 ++++++++++++++++++++++++++++ net/ipv4/udp.c | 7 +++++++ net/ipv4/udp_offload.c | 6 ++++-- net/ipv6/udp.c | 2 +- 4 files changed, 40 insertions(+), 3 deletions(-) diff --git a/include/linux/udp.h b/include/linux/udp.h index ae58ff3b6b5b..a220880019d6 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -131,6 +131,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -142,6 +160,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 59f158f27273..fdc652bda520 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -540,6 +540,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 0c1aacf6e312..cc9fde88ddb7 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -512,8 +512,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e6fdb842e89d..2b4f2c626d37 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -413,7 +413,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); From 2949c0bf09d8d7c1b1384e3207113aac2443a234 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 26 Mar 2024 12:34:00 +0100 Subject: [PATCH 3/8] UPSTREAM: udp: do not transition UDP GRO fraglist partial checksums to unnecessary UDP GRO validates checksums and in udp4/6_gro_complete fraglist packets are converted to CHECKSUM_UNNECESSARY to avoid later checks. However this is an issue for CHECKSUM_PARTIAL packets as they can be looped in an egress path and then their partial checksums are not fixed. Different issues can be observed, from invalid checksum on packets to traces like: gen01: hw csum failure skb len=3008 headroom=160 headlen=1376 tailroom=0 mac=(106,14) net=(120,40) trans=160 shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0)) csum(0xffff232e ip_summed=2 complete_sw=0 valid=0 level=0) hash(0x77e3d716 sw=1 l4=1) proto=0x86dd pkttype=0 iif=12 ... Fix this by only converting CHECKSUM_NONE packets to CHECKSUM_UNNECESSARY by reusing __skb_incr_checksum_unnecessary. All other checksum types are kept as-is, including CHECKSUM_COMPLETE as fraglist packets being segmented back would have their skb->csum valid. Bug: 254441685 Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Signed-off-by: Antoine Tenart Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller (cherry picked from commit f0b8c30345565344df2e33a8417a27503589247d) Signed-off-by: Lee Jones Change-Id: I29b8543842f63664e901a217f8636f21ffef504b --- net/ipv4/udp_offload.c | 8 +------- net/ipv6/udp_offload.c | 8 +------- 2 files changed, 2 insertions(+), 14 deletions(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index cc9fde88ddb7..e3d754169f97 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -662,13 +662,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6e06c90fa318..ad20e304f634 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -156,13 +156,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } From bf543165c8250e502a05c8a652c78ba5c5aac548 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 26 Mar 2024 12:34:01 +0100 Subject: [PATCH 4/8] UPSTREAM: udp: prevent local UDP tunnel packets from being GROed GRO has a fundamental issue with UDP tunnel packets as it can't detect those in a foolproof way and GRO could happen before they reach the tunnel endpoint. Previous commits have fixed issues when UDP tunnel packets come from a remote host, but if those packets are issued locally they could run into checksum issues. If the inner packet has a partial checksum the information will be lost in the GRO logic, either in udp4/6_gro_complete or in udp_gro_complete_segment and packets will have an invalid checksum when leaving the host. Prevent local UDP tunnel packets from ever being GROed at the outer UDP level. Due to skb->encapsulation being wrongly used in some drivers this is actually only preventing UDP tunnel packets with a partial checksum to be GROed (see iptunnel_handle_offloads) but those were also the packets triggering issues so in practice this should be sufficient. Bug: 254441685 Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Fixes: 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets") Suggested-by: Paolo Abeni Signed-off-by: Antoine Tenart Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller (cherry picked from commit 64235eabc4b5b18c507c08a1f16cdac6c5661220) Signed-off-by: Lee Jones Change-Id: I1f6d19cfd34e04e395b270e5c286fec06d13fedd --- net/ipv4/udp_offload.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e3d754169f97..0ff68f00a535 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -519,6 +519,12 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; From 45b722f73a86ddb2ac62fa199e19572ffe181e44 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Sat, 27 Apr 2024 20:24:19 +0200 Subject: [PATCH 5/8] UPSTREAM: net: core: reject skb_copy(_expand) for fraglist GSO skbs SKB_GSO_FRAGLIST skbs must not be linearized, otherwise they become invalid. Return NULL if such an skb is passed to skb_copy or skb_copy_expand, in order to prevent a crash on a potential later call to skb_gso_segment. Bug: 254441685 Fixes: 3a1296a38d0c ("net: Support GRO/GSO fraglist chaining.") Signed-off-by: Felix Fietkau Signed-off-by: David S. Miller (cherry picked from commit d091e579b864fa790dd6a0cd537a22c383126681) Signed-off-by: Lee Jones Change-Id: I0835421359096bd9566a09037d43db84f371dcb1 --- net/core/skbuff.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3001b05c919c..fec1b4777efb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1527,11 +1527,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb_headroom(skb); - unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = __alloc_skb(size, gfp_mask, - skb_alloc_rx_flag(skb), NUMA_NO_NODE); + struct sk_buff *n; + unsigned int size; + int headerlen; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + + headerlen = skb_headroom(skb); + size = skb_end_offset(skb) + skb->data_len; + n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -1803,12 +1809,17 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask, skb_alloc_rx_flag(skb), - NUMA_NO_NODE); - int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + struct sk_buff *n; + int oldheadroom; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + + oldheadroom = skb_headroom(skb); + n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (!n) return NULL; From 196e23be873afbb2901b85db8be99549a8cbd0f4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 10 May 2024 11:33:39 +0800 Subject: [PATCH 6/8] UPSTREAM: f2fs: compress: don't allow unaligned truncation on released compress inode f2fs image may be corrupted after below testcase: - mkfs.f2fs -O extra_attr,compression -f /dev/vdb - mount /dev/vdb /mnt/f2fs - touch /mnt/f2fs/file - f2fs_io setflags compression /mnt/f2fs/file - dd if=/dev/zero of=/mnt/f2fs/file bs=4k count=4 - f2fs_io release_cblocks /mnt/f2fs/file - truncate -s 8192 /mnt/f2fs/file - umount /mnt/f2fs - fsck.f2fs /dev/vdb [ASSERT] (fsck_chk_inode_blk:1256) --> ino: 0x5 has i_blocks: 0x00000002, but has 0x3 blocks [FSCK] valid_block_count matching with CP [Fail] [0x4, 0x5] [FSCK] other corrupted bugs [Fail] The reason is: partial truncation assume compressed inode has reserved blocks, after partial truncation, valid block count may change w/o .i_blocks and .total_valid_block_count update, result in corruption. This patch only allow cluster size aligned truncation on released compress inode for fixing. Bug: 254441685 Fixes: c61404153eb6 ("f2fs: introduce FI_COMPRESS_RELEASED instead of using IMMUTABLE bit") Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim (cherry picked from commit 29ed2b5dd521ce7c5d8466cd70bf0cc9d07afeee) Signed-off-by: Lee Jones Change-Id: I33ef69b992bdeb4f4f3b7741eaf6ce0e24f689f6 --- fs/f2fs/file.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 7027239e2765..0d95b82703c8 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -890,9 +890,14 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) ATTR_GID | ATTR_TIMES_SET)))) return -EPERM; - if ((attr->ia_valid & ATTR_SIZE) && - !f2fs_is_compress_backend_ready(inode)) - return -EOPNOTSUPP; + if ((attr->ia_valid & ATTR_SIZE)) { + if (!f2fs_is_compress_backend_ready(inode)) + return -EOPNOTSUPP; + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) && + !IS_ALIGNED(attr->ia_size, + F2FS_BLK_TO_BYTES(F2FS_I(inode)->i_cluster_size))) + return -EINVAL; + } err = setattr_prepare(dentry, attr); if (err) From 2cc0b129d22711c4936cb0964315fc87043fbf77 Mon Sep 17 00:00:00 2001 From: Quang Le Date: Mon, 3 Feb 2025 16:58:38 -0800 Subject: [PATCH 7/8] UPSTREAM: pfifo_tail_enqueue: Drop new packet when sch->limit == 0 commit 647cef20e649c576dff271e018d5d15d998b629d upstream. Expected behaviour: In case we reach scheduler's limit, pfifo_tail_enqueue() will drop a packet in scheduler's queue and decrease scheduler's qlen by one. Then, pfifo_tail_enqueue() enqueue new packet and increase scheduler's qlen by one. Finally, pfifo_tail_enqueue() return `NET_XMIT_CN` status code. Weird behaviour: In case we set `sch->limit == 0` and trigger pfifo_tail_enqueue() on a scheduler that has no packet, the 'drop a packet' step will do nothing. This means the scheduler's qlen still has value equal 0. Then, we continue to enqueue new packet and increase scheduler's qlen by one. In summary, we can leverage pfifo_tail_enqueue() to increase qlen by one and return `NET_XMIT_CN` status code. The problem is: Let's say we have two qdiscs: Qdisc_A and Qdisc_B. - Qdisc_A's type must have '->graft()' function to create parent/child relationship. Let's say Qdisc_A's type is `hfsc`. Enqueue packet to this qdisc will trigger `hfsc_enqueue`. - Qdisc_B's type is pfifo_head_drop. Enqueue packet to this qdisc will trigger `pfifo_tail_enqueue`. - Qdisc_B is configured to have `sch->limit == 0`. - Qdisc_A is configured to route the enqueued's packet to Qdisc_B. Enqueue packet through Qdisc_A will lead to: - hfsc_enqueue(Qdisc_A) -> pfifo_tail_enqueue(Qdisc_B) - Qdisc_B->q.qlen += 1 - pfifo_tail_enqueue() return `NET_XMIT_CN` - hfsc_enqueue() check for `NET_XMIT_SUCCESS` and see `NET_XMIT_CN` => hfsc_enqueue() don't increase qlen of Qdisc_A. The whole process lead to a situation where Qdisc_A->q.qlen == 0 and Qdisc_B->q.qlen == 1. Replace 'hfsc' with other type (for example: 'drr') still lead to the same problem. This violate the design where parent's qlen should equal to the sum of its childrens'qlen. Bug impact: This issue can be used for user->kernel privilege escalation when it is reachable. Bug: 395539871 Fixes: 57dbb2d83d10 ("sched: add head drop fifo queue") Reported-by: Quang Le Signed-off-by: Quang Le Signed-off-by: Cong Wang Link: https://patch.msgid.link/20250204005841.223511-2-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 79a955ea4a2e5ddf4a36328959de0de496419888) Signed-off-by: Lee Jones Change-Id: I94a3851190671bc98666cb659e8419ab2767fb03 --- net/sched/sch_fifo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 56f4c1621e44..9de91f69032d 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -38,6 +38,9 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, { unsigned int prev_backlog; + if (unlikely(sch->limit == 0)) + return qdisc_drop(skb, sch, to_free); + if (likely(sch->q.qlen < sch->limit)) return qdisc_enqueue_tail(skb, sch); From 7e39477098b50156535c8f910fee50d6dac2a793 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Wed, 15 Jan 2025 17:37:13 -0800 Subject: [PATCH 8/8] UPSTREAM: net: sched: Disallow replacing of child qdisc from one parent to another [ Upstream commit bc50835e83f60f56e9bec2b392fb5544f250fb6f ] Lion Ackermann was able to create a UAF which can be abused for privilege escalation with the following script Step 1. create root qdisc tc qdisc add dev lo root handle 1:0 drr step2. a class for packet aggregation do demonstrate uaf tc class add dev lo classid 1:1 drr step3. a class for nesting tc class add dev lo classid 1:2 drr step4. a class to graft qdisc to tc class add dev lo classid 1:3 drr step5. tc qdisc add dev lo parent 1:1 handle 2:0 plug limit 1024 step6. tc qdisc add dev lo parent 1:2 handle 3:0 drr step7. tc class add dev lo classid 3:1 drr step 8. tc qdisc add dev lo parent 3:1 handle 4:0 pfifo step 9. Display the class/qdisc layout tc class ls dev lo class drr 1:1 root leaf 2: quantum 64Kb class drr 1:2 root leaf 3: quantum 64Kb class drr 3:1 root leaf 4: quantum 64Kb tc qdisc ls qdisc drr 1: dev lo root refcnt 2 qdisc plug 2: dev lo parent 1:1 qdisc pfifo 4: dev lo parent 3:1 limit 1000p qdisc drr 3: dev lo parent 1:2 step10. trigger the bug <=== prevented by this patch tc qdisc replace dev lo parent 1:3 handle 4:0 step 11. Redisplay again the qdiscs/classes tc class ls dev lo class drr 1:1 root leaf 2: quantum 64Kb class drr 1:2 root leaf 3: quantum 64Kb class drr 1:3 root leaf 4: quantum 64Kb class drr 3:1 root leaf 4: quantum 64Kb tc qdisc ls qdisc drr 1: dev lo root refcnt 2 qdisc plug 2: dev lo parent 1:1 qdisc pfifo 4: dev lo parent 3:1 refcnt 2 limit 1000p qdisc drr 3: dev lo parent 1:2 Observe that a) parent for 4:0 does not change despite the replace request. There can only be one parent. b) refcount has gone up by two for 4:0 and c) both class 1:3 and 3:1 are pointing to it. Step 12. send one packet to plug echo "" | socat -u STDIN UDP4-DATAGRAM:127.0.0.1:8888,priority=$((0x10001)) step13. send one packet to the grafted fifo echo "" | socat -u STDIN UDP4-DATAGRAM:127.0.0.1:8888,priority=$((0x10003)) step14. lets trigger the uaf tc class delete dev lo classid 1:3 tc class delete dev lo classid 1:1 The semantics of "replace" is for a del/add _on the same node_ and not a delete from one node(3:1) and add to another node (1:3) as in step10. While we could "fix" with a more complex approach there could be consequences to expectations so the patch takes the preventive approach of "disallow such config". Bug: 393266309 Joint work with Lion Ackermann Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jamal Hadi Salim Reviewed-by: Simon Horman Link: https://patch.msgid.link/20250116013713.900000-1-kuba@kernel.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin (cherry picked from commit deda09c0543a66fa51554abc5ffd723d99b191bf) Signed-off-by: Lee Jones Change-Id: Id94e8dfb543643e489e33f79af990f23580b9121 --- net/sched/sch_api.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b8dc03a7487e..178044a845df 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1593,6 +1593,10 @@ replay: q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; + if (q->parent != tcm->tcm_parent) { + NL_SET_ERR_MSG(extack, "Cannot move an existing qdisc to a different parent"); + return -EINVAL; + } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST;