From 212ed75dc5fb9d1423b3942c8f872a868cda3466 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 7 Jun 2023 11:55:42 +0200 Subject: netfilter: nf_tables: integrate pipapo into commit protocol The pipapo set backend follows copy-on-update approach, maintaining one clone of the existing datastructure that is being updated. The clone and current datastructures are swapped via rcu from the commit step. The existing integration with the commit protocol is flawed because there is no operation to clean up the clone if the transaction is aborted. Moreover, the datastructure swap happens on set element activation. This patch adds two new operations for sets: commit and abort, these new operations are invoked from the commit and abort steps, after the transactions have been digested, and it updates the pipapo set backend to use it. This patch adds a new ->pending_update field to sets to maintain a list of sets that require this new commit and abort operations. Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2e24ea1d744c..83db182decc8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -462,7 +462,8 @@ struct nft_set_ops { const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); - + void (*commit)(const struct nft_set *set); + void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, @@ -557,6 +558,7 @@ struct nft_set { u16 policy; u16 udlen; unsigned char *udata; + struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; u16 flags:14, -- cgit v1.2.3 From 52f79609c0c5b25fddb88e85f25ce08aa7e3fb42 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 8 Jun 2023 09:23:44 -0700 Subject: net: ethtool: correct MAX attribute value for stats When compiling YNL generated code compiler complains about array-initializer-out-of-bounds. Turns out the MAX value for STATS_GRP uses the value for STATS. This may lead to random corruptions in user space (kernel itself doesn't use this value as it never parses stats). Fixes: f09ea6fb1272 ("ethtool: add a new command for reading standard stats") Signed-off-by: Jakub Kicinski Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/ethtool_netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 1ebf8d455f07..73e2c10dc2cc 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -783,7 +783,7 @@ enum { /* add new constants above here */ __ETHTOOL_A_STATS_GRP_CNT, - ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_CNT - 1) + ETHTOOL_A_STATS_GRP_MAX = (__ETHTOOL_A_STATS_GRP_CNT - 1) }; enum { -- cgit v1.2.3 From 41f2c7c342d3adb1c4dd5f2e3dd831adff16a669 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Fri, 9 Jun 2023 15:22:59 +0300 Subject: net/sched: act_ct: Fix promotion of offloaded unreplied tuple Currently UNREPLIED and UNASSURED connections are added to the nf flow table. This causes the following connection packets to be processed by the flow table which then skips conntrack_in(), and thus such the connections will remain UNREPLIED and UNASSURED even if reply traffic is then seen. Even still, the unoffloaded reply packets are the ones triggering hardware update from new to established state, and if there aren't any to triger an update and/or previous update was missed, hardware can get out of sync with sw and still mark packets as new. Fix the above by: 1) Not skipping conntrack_in() for UNASSURED packets, but still refresh for hardware, as before the cited patch. 2) Try and force a refresh by reply-direction packets that update the hardware rules from new to established state. 3) Remove any bidirectional flows that didn't failed to update in hardware for re-insertion as bidrectional once any new packet arrives. Fixes: 6a9bad0069cf ("net/sched: act_ct: offload UDP NEW connections") Co-developed-by: Vlad Buslov Signed-off-by: Vlad Buslov Signed-off-by: Paul Blakey Reviewed-by: Florian Westphal Link: https://lore.kernel.org/r/1686313379-117663-1-git-send-email-paulb@nvidia.com Signed-off-by: Paolo Abeni --- include/net/netfilter/nf_flow_table.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ebb28ec5b6fa..f37f9f34430c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -268,7 +268,7 @@ int flow_offload_route_init(struct flow_offload *flow, int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow); + struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); -- cgit v1.2.3 From 84ad0af0bccd3691cb951c2974c5cb2c10594d4a Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Sat, 10 Jun 2023 20:30:25 -0700 Subject: net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton Cc: Vlad Buslov Signed-off-by: Peilin Ye Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/net/sch_generic.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 27271f2b37cb..12eadecf8cd0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -137,6 +137,13 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc) refcount_inc(&qdisc->refcnt); } +static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return true; + return refcount_dec_if_one(&qdisc->refcnt); +} + /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ @@ -652,6 +659,7 @@ void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); +void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); -- cgit v1.2.3