diff options
| author | Steven Rostedt <rostedt@goodmis.org> | 2026-09-02 09:55:01 -0400 |
|---|---|---|
| committer | Steven Rostedt <rostedt@goodmis.org> | 2026-09-02 11:08:21 -0400 |
| commit | 4617721c502b2ddaa4e324e86da4997edf738fa5 (patch) | |
| tree | 350aa83b47da0b574a814795392b20b0bed83cbc /include/net/inet_ecn.h | |
| download | linux-stable-4617721c502b2ddaa4e324e86da4997edf738fa5.tar.gz linux-stable-4617721c502b2ddaa4e324e86da4997edf738fa5.zip | |
ftrace: Synchronize the initialization of ftrace_opsgrafted
There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.
Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Diffstat (limited to 'include/net/inet_ecn.h')
| -rw-r--r-- | include/net/inet_ecn.h | 337 |
1 files changed, 337 insertions, 0 deletions
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h new file mode 100644 index 000000000..827b87a95 --- /dev/null +++ b/include/net/inet_ecn.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _INET_ECN_H_ +#define _INET_ECN_H_ + +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/if_vlan.h> + +#include <net/inet_sock.h> +#include <net/dsfield.h> +#include <net/checksum.h> + +enum { + INET_ECN_NOT_ECT = 0, + INET_ECN_ECT_1 = 1, + INET_ECN_ECT_0 = 2, + INET_ECN_CE = 3, + INET_ECN_MASK = 3, +}; + +extern int sysctl_tunnel_ecn_log; + +static inline int INET_ECN_is_ce(__u8 dsfield) +{ + return (dsfield & INET_ECN_MASK) == INET_ECN_CE; +} + +static inline int INET_ECN_is_not_ect(__u8 dsfield) +{ + return (dsfield & INET_ECN_MASK) == INET_ECN_NOT_ECT; +} + +static inline int INET_ECN_is_capable(__u8 dsfield) +{ + return dsfield & INET_ECN_ECT_0; +} + +/* + * RFC 3168 9.1.1 + * The full-functionality option for ECN encapsulation is to copy the + * ECN codepoint of the inside header to the outside header on + * encapsulation if the inside header is not-ECT or ECT, and to set the + * ECN codepoint of the outside header to ECT(0) if the ECN codepoint of + * the inside header is CE. + */ +static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) +{ + outer &= ~INET_ECN_MASK; + outer |= !INET_ECN_is_ce(inner) ? (inner & INET_ECN_MASK) : + INET_ECN_ECT_0; + return outer; +} + +/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + +static inline void INET_ECN_xmit(struct sock *sk) +{ + __INET_ECN_xmit(sk, false); +} + +static inline void INET_ECN_dontxmit(struct sock *sk) +{ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + if (inet6_sk(sk) != NULL) + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; +} + +#define IP6_ECN_flow_init(label) do { \ + (label) &= ~htonl(INET_ECN_MASK << 20); \ + } while (0) + +#define IP6_ECN_flow_xmit(sk, label) do { \ + if (INET_ECN_is_capable(inet6_sk(sk)->tclass)) \ + (label) |= htonl(INET_ECN_ECT_0 << 20); \ + } while (0) + +static inline int IP_ECN_set_ce(struct iphdr *iph) +{ + u32 ecn = (iph->tos + 1) & INET_ECN_MASK; + __be16 check_add; + + /* + * After the last operation we have (in binary): + * INET_ECN_NOT_ECT => 01 + * INET_ECN_ECT_1 => 10 + * INET_ECN_ECT_0 => 11 + * INET_ECN_CE => 00 + */ + if (!(ecn & 2)) + return !ecn; + + /* + * The following gives us: + * INET_ECN_ECT_1 => check += htons(0xFFFD) + * INET_ECN_ECT_0 => check += htons(0xFFFE) + */ + check_add = (__force __be16)((__force u16)htons(0xFFFB) + + (__force u16)htons(ecn)); + + iph->check = csum16_add(iph->check, check_add); + iph->tos |= INET_ECN_CE; + return 1; +} + +static inline int IP_ECN_set_ect1(struct iphdr *iph) +{ + if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + iph->check = csum16_add(iph->check, htons(0x1)); + iph->tos ^= INET_ECN_MASK; + return 1; +} + +static inline void IP_ECN_clear(struct iphdr *iph) +{ + iph->tos &= ~INET_ECN_MASK; +} + +static inline void ipv4_copy_dscp(unsigned int dscp, struct iphdr *inner) +{ + dscp &= ~INET_ECN_MASK; + ipv4_change_dsfield(inner, INET_ECN_MASK, dscp); +} + +struct ipv6hdr; + +/* Note: + * IP_ECN_set_ce() has to tweak IPV4 checksum when setting CE, + * meaning both changes have no effect on skb->csum if/when CHECKSUM_COMPLETE + * In IPv6 case, no checksum compensates the change in IPv6 header, + * so we have to update skb->csum. + */ +static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if (INET_ECN_is_not_ect(ipv6_get_dsfield(iph))) + return 0; + + from = *(__be32 *)iph; + to = from | htonl(INET_ECN_CE << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + +static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + from = *(__be32 *)iph; + to = from ^ htonl(INET_ECN_MASK << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + +static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) +{ + dscp &= ~INET_ECN_MASK; + ipv6_change_dsfield(inner, INET_ECN_MASK, dscp); +} + +static inline int INET_ECN_set_ce(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ce(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ce(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + +static inline int skb_get_dsfield(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + break; + return ipv4_get_dsfield(ip_hdr(skb)); + + case cpu_to_be16(ETH_P_IPV6): + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + break; + return ipv6_get_dsfield(ipv6_hdr(skb)); + } + + return -1; +} + +static inline int INET_ECN_set_ect1(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ect1(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + +/* + * RFC 6040 4.2 + * To decapsulate the inner header at the tunnel egress, a compliant + * tunnel egress MUST set the outgoing ECN field to the codepoint at the + * intersection of the appropriate arriving inner header (row) and outer + * header (column) in Figure 4 + * + * +---------+------------------------------------------------+ + * |Arriving | Arriving Outer Header | + * | Inner +---------+------------+------------+------------+ + * | Header | Not-ECT | ECT(0) | ECT(1) | CE | + * +---------+---------+------------+------------+------------+ + * | Not-ECT | Not-ECT |Not-ECT(!!!)|Not-ECT(!!!)| <drop>(!!!)| + * | ECT(0) | ECT(0) | ECT(0) | ECT(1) | CE | + * | ECT(1) | ECT(1) | ECT(1) (!) | ECT(1) | CE | + * | CE | CE | CE | CE(!!!)| CE | + * +---------+---------+------------+------------+------------+ + * + * Figure 4: New IP in IP Decapsulation Behaviour + * + * returns 0 on success + * 1 if something is broken and should be logged (!!! above) + * 2 if packet should be dropped + */ +static inline int __INET_ECN_decapsulate(__u8 outer, __u8 inner, bool *set_ce) +{ + if (INET_ECN_is_not_ect(inner)) { + switch (outer & INET_ECN_MASK) { + case INET_ECN_NOT_ECT: + return 0; + case INET_ECN_ECT_0: + case INET_ECN_ECT_1: + return 1; + case INET_ECN_CE: + return 2; + } + } + + *set_ce = INET_ECN_is_ce(outer); + return 0; +} + +static inline int INET_ECN_decapsulate(struct sk_buff *skb, + __u8 outer, __u8 inner) +{ + bool set_ce = false; + int rc; + + rc = __INET_ECN_decapsulate(outer, inner, &set_ce); + if (!rc) { + if (set_ce) + INET_ECN_set_ce(skb); + else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) + INET_ECN_set_ect1(skb); + } + + return rc; +} + +static inline int IP_ECN_decapsulate(const struct iphdr *oiph, + struct sk_buff *skb) +{ + __u8 inner; + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + inner = ip_hdr(skb)->tos; + break; + case htons(ETH_P_IPV6): + inner = ipv6_get_dsfield(ipv6_hdr(skb)); + break; + default: + return 0; + } + + return INET_ECN_decapsulate(skb, oiph->tos, inner); +} + +static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, + struct sk_buff *skb) +{ + __u8 inner; + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + inner = ip_hdr(skb)->tos; + break; + case htons(ETH_P_IPV6): + inner = ipv6_get_dsfield(ipv6_hdr(skb)); + break; + default: + return 0; + } + + return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); +} +#endif |
