kernel/linux.git/include/net/ip6_route.h, branch v6.12.80

net: use dst_dev_rcu() in sk_setup_caps()

2026-01-08T09:15:01+00:00

[ Upstream commit 99a2ace61b211b0be861b07fbaa062fca4b58879 ] Use RCU to protect accesses to dst->dev from sk_setup_caps() and sk_dst_gso_max_size(). Also use dst_dev_rcu() in ip6_dst_mtu_maybe_forward(), and ip_dst_mtu_maybe_forward(). ip4_dst_hoplimit() can use dst_dev_net_rcu(). Fixes: 4a6ce2b6f2ec ("net: introduce a new function dst_dev_put()") Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250828195823.3958522-6-edumazet@google.com Signed-off-by: Jakub Kicinski [Harshit: Backport to 6.12.y, resolve conflict due to missing commit: 22d6c9eebf2e ("net: Unexport shared functions for DCCP.") in 6.12.y] Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman

ipv6: adopt dst_dev() helper

2026-01-08T09:15:01+00:00

[ Upstream commit 1caf27297215a5241f9bfc9c07336349d9034ee3 ] Use the new helper as a step to deal with potential dst->dev races. Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20250630121934.3399505-9-edumazet@google.com Signed-off-by: Jakub Kicinski [Harshit: Backport to 6.12.y, pulled this is a prerequisite] Stable-dep-of: 99a2ace61b21 ("net: use dst_dev_rcu() in sk_setup_caps()") Signed-off-by: Harshit Mogalapalli Signed-off-by: Greg Kroah-Hartman

ipv6: fix source address selection with route leak

2024-07-14T14:34:16+00:00

By default, an address assigned to the output interface is selected when the source address is not specified. This is problematic when a route, configured in a vrf, uses an interface from another vrf (aka route leak). The original vrf does not own the selected source address. Let's add a check against the output interface and call the appropriate function to select the source address. CC: stable@vger.kernel.org Fixes: 0d240e7811c4 ("net: vrf: Implement get_saddr for IPv6") Signed-off-by: Nicolas Dichtel Link: https://patch.msgid.link/20240710081521.3809742-3-nicolas.dichtel@6wind.com Signed-off-by: Jakub Kicinski

ipv6: introduce dst_rt6_info() helper

2024-04-29T12:32:01+00:00

Instead of (struct rt6_info *)dst casts, we can use : #define dst_rt6_info(_ptr) \ container_of_const(_ptr, struct rt6_info, dst) Some places needed missing const qualifiers : ip6_confirm_neigh(), ipv6_anycast_destination(), ipv6_unicast_destination(), has_gateway() v2: added missing parts (David Ahern) Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller

ipv6: annotate data-races around cnf.mtu6

2024-03-01T08:42:31+00:00

idev->cnf.mtu6 might be read locklessly, add appropriate READ_ONCE() and WRITE_ONCE() annotations. Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller

net/ipv6: set expires in rt6_add_dflt_router().

2024-02-12T10:24:12+00:00

Pass the duration of a lifetime (in seconds) to the function rt6_add_dflt_router() so that it can properly set the expiration time. The function ndisc_router_discovery() is the only one that calls rt6_add_dflt_router(), and it will later set the expiration time for the route created by rt6_add_dflt_router(). However, there is a gap of time between calling rt6_add_dflt_router() and setting the expiration time in ndisc_router_discovery(). During this period, there is a possibility that a new route may be removed from the routing table. By setting the correct expiration time in rt6_add_dflt_router(), we can prevent this from happening. The reason for setting RTF_EXPIRES in rt6_add_dflt_router() is to start the Garbage Collection (GC) timer, as it only activates when a route with RTF_EXPIRES is added to a table. Suggested-by: David Ahern Reviewed-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: Kui-Feng Lee Signed-off-by: David S. Miller

ipv6: lockless IPV6_ADDR_PREFERENCES implementation

2023-09-19T16:21:44+00:00

We have data-races while reading np->srcprefs Switch the field to a plain byte, add READ_ONCE() and WRITE_ONCE() annotations where needed, and IPV6_ADDR_PREFERENCES setsockopt() can now be lockless. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230918142321.1794107-1-edumazet@google.com Signed-off-by: Paolo Abeni

ipv6: lockless IPV6_MTU_DISCOVER implementation

2023-09-15T09:33:48+00:00

Most np->pmtudisc reads are racy. Move this 3bit field on a full byte, add annotations and make IPV6_MTU_DISCOVER setsockopt() lockless. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller

IPv6: add extack info for IPv6 address add/delete

2023-07-28T10:01:56+00:00

Add extack info for IPv6 address add/delete, which would be useful for users to understand the problem without having to read kernel code. Suggested-by: Beniamino Galvani Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Hangbin Liu Reviewed-by: Simon Horman Signed-off-by: David S. Miller

net: dst: Prevent false sharing vs. dst_entry:: __refcnt

2023-03-29T01:52:22+00:00

dst_entry::__refcnt is highly contended in scenarios where many connections happen from and to the same IP. The reference count is an atomic_t, so the reference count operations have to take the cache-line exclusive. Aside of the unavoidable reference count contention there is another significant problem which is caused by that: False sharing. perf top identified two affected read accesses. dst_entry::lwtstate and rtable::rt_genid. dst_entry:__refcnt is located at offset 64 of dst_entry, which puts it into a seperate cacheline vs. the read mostly members located at the beginning of the struct. That prevents false sharing vs. the struct members in the first 64 bytes of the structure, but there is also dst_entry::lwtstate which is located after the reference count and in the same cache line. This member is read after a reference count has been acquired. struct rtable embeds a struct dst_entry at offset 0. struct dst_entry has a size of 112 bytes, which means that the struct members of rtable which follow the dst member share the same cache line as dst_entry::__refcnt. Especially rtable::rt_genid is also read by the contexts which have a reference count acquired already. When dst_entry:__refcnt is incremented or decremented via an atomic operation these read accesses stall. This was found when analysing the memtier benchmark in 1:100 mode, which amplifies the problem extremly. Move the rt[6i]_uncached[_list] members out of struct rtable and struct rt6_info into struct dst_entry to provide padding and move the lwtstate member after that so it ends up in the same cache line. The resulting improvement depends on the micro-architecture and the number of CPUs. It ranges from +20% to +120% with a localhost memtier/memcached benchmark. [ tglx: Rearrange struct ] Signed-off-by: Wangyang Guo Signed-off-by: Arjan van de Ven Signed-off-by: Thomas Gleixner Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230323102800.042297517@linutronix.de Signed-off-by: Jakub Kicinski