Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

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