#ifndef _INET_ECN_H_
#define _INET_ECN_H_

#include <linux/ip.h>
#include <linux/skbuff.h>

#include <net/inet_sock.h>
#include <net/dsfield.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;
}

static inline void INET_ECN_xmit(struct sock *sk)
{
	inet_sk(sk)->tos |= INET_ECN_ECT_0;
	if (inet6_sk(sk) != NULL)
		inet6_sk(sk)->tclass |= INET_ECN_ECT_0;
}

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 check = (__force u32)iph->check;
	u32 ecn = (iph->tos + 1) & INET_ECN_MASK;

	/*
	 * 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 += (__force u16)htons(0xFFFB) + (__force u16)htons(ecn);

	iph->check = (__force __sum16)(check + (check>=0xFFFF));
	iph->tos |= INET_ECN_CE;
	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 void IP6_ECN_clear(struct ipv6hdr *iph)
{
	*(__be32*)iph &= ~htonl(INET_ECN_MASK << 20);
}

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) {
	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;
}

/*
 * 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(struct sk_buff *skb,
				       __u8 outer, __u8 inner)
{
	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;
		}
	}

	if (INET_ECN_is_ce(outer))
		INET_ECN_set_ce(skb);

	return 0;
}

static inline int IP_ECN_decapsulate(const struct iphdr *oiph,
				     struct sk_buff *skb)
{
	__u8 inner;

	if (skb->protocol == htons(ETH_P_IP))
		inner = ip_hdr(skb)->tos;
	else if (skb->protocol == htons(ETH_P_IPV6))
		inner = ipv6_get_dsfield(ipv6_hdr(skb));
	else
		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;

	if (skb->protocol == htons(ETH_P_IP))
		inner = ip_hdr(skb)->tos;
	else if (skb->protocol == htons(ETH_P_IPV6))
		inner = ipv6_get_dsfield(ipv6_hdr(skb));
	else
		return 0;

	return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner);
}
#endif
ht)\n",
	       addr);
	abort();
}

static void run_bind_test(void)
{
	unsigned int *p = bindstack;

	p[0] = 0xf001f001;

	write(sysrqfd, "x", 1);

	/* Set trap on access to p[0] */
	protect_low(PROT_NONE);

	write(sysrqfd, "x", 1);

	/* Clear trap on access to p[0] */
	protect_low(PROT_READ | PROT_WRITE | PROT_EXEC);

	write(sysrqfd, "x", 1);

	/* Check the contents of p[0] */
	if (p[0] != 0xf001f001) {
		write(sysrqfd, "x", 1);

		/* Reached, but shouldn't be */
		printf("badness, shouldn't happen but does\n");
		abort();
	}
}

int main(void)
{
	struct sigaction sa;

	sysrqfd = open("/proc/sysrq-trigger", O_WRONLY);

	if (sigprocmask(SIG_BLOCK, NULL, &amp;sa.sa_mask)) {
		perror("sigprocmask");
		return 0;
	}

	sa.sa_sigaction = sigbus_handler;
	sa.sa_flags = SA_SIGINFO | SA_NODEFER | SA_RESTART;
	if (sigaction(SIGBUS, &amp;sa, NULL)) {
		perror("sigaction");
		return 0;
	}

	bindstack = mmap(NULL,
			 BINDSTACK_SIZE,
			 PROT_READ | PROT_WRITE | PROT_EXEC,
			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
	if (bindstack == MAP_FAILED) {
		perror("mmap bindstack");
		return 0;
	}

	printf("bindstack: %p\n", bindstack);

	run_bind_test();

	printf("done\n");

	return 0;
}

There are multiple ingredients for this:

 1) PAGE_NONE is defined to _CACHE_CACHABLE_NONCOHERENT, which is CCA 3
    on all platforms except SB1 where it's CCA 5.
 2) _page_cachable_default must have bits set which are not set
    _CACHE_CACHABLE_NONCOHERENT.
 3) Either the defective version of pte_modify for XPA or the standard
    version must be in used.  However pte_modify for the 36 bit address
    space support is no affected.

In that case additional bits in the final CCA mode may generate an invalid
value for the CCA field.  On the R10000 system where this was tracked
down for example a CCA 7 has been observed, which is Uncached Accelerated.

Fixed by:

 1) Using the proper CCA mode for PAGE_NONE just like for all the other
    PAGE_* pte/pmd bits.
 2) Fix the two affected variants of pte_modify.

Further code inspection also shows the same issue to exist in pmd_modify
which would affect huge page systems.

Issue in pte_modify tracked down by Alastair Bridgewater, PAGE_NONE
and pmd_modify issue found by me.

The history of this goes back beyond Linus' git history.  Chris Dearman's
commit 351336929ccf222ae38ff0cb7a8dd5fd5c6236a0 ("[MIPS] Allow setting of
the cache attribute at run time.") missed the opportunity to fix this
but it was originally introduced in lmo commit
d523832cf12007b3242e50bb77d0c9e63e0b6518 ("Missing from last commit.")
and 32cc38229ac7538f2346918a09e75413e8861f87 ("New configuration option
CONFIG_MIPS_UNCACHED.")

Signed-off-by: Ralf Baechle &lt;ralf@linux-mips.org&gt;
Reported-by: Alastair Bridgewater &lt;alastair.bridgewater@gmail.com&gt;
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=6d037de90a1fd7b4879b48d4dd5c4839b271be98'>Diffstat</a> (limited to 'Documentation/fb')</div><table summary='diffstat' class='diffstat'>